techxplore.com | Vandana Suresh, Texas A&M University

Texas A&M University researchers have designed a reinforcement learning algorithm that automates the process of predicting the properties of the underground environment, facilitating the accurate forecasting of oil and gas reserves.

Within the Earth’s crust, layers of rock hold bountiful reservoirs of groundwater, oil and natural gas. Now, using machine learning, researchers at Texas A&M University have developed an algorithm that automates the process of determining key features of the Earth’s subterranean environment. They said this research might help with accurate forecasting of our natural reserves.

Specifically, the researchers’ algorithm is designed on the principle of reinforcement or reward learning. Here, the computer algorithm converges on the correct description of the underground environment based on rewards it accrues for making correct predictions of the pressure and flow expected from boreholes.

“Subsurface systems that are typically a mile below our feet are completely opaque. At that depth we cannot see anything and have to use instruments to measure quantities, like pressure and rates of flow,” said Siddharth Misra, associate professor in the Harold Vance Department of Petroleum Engineering and the Department of Geology and Geophysics. “Although my current study is a first step, my goal is to have a completely automated way of using that information to accurately characterize the properties of the subsurface.”

The algorithm is described in the December issue of the journal Applied Energy.

Simulating the geology of the underground environment can greatly facilitate forecasting of oil and gas reserves, predicting groundwater systems and anticipating seismic hazards. Depending on the intended application, boreholes serve as exit sites for oil, gas and water or entry sites for excess atmospheric carbon dioxide that need to be trapped underground.

Along the length of the boreholes, drilling operators can ascertain the pressures and flow rates of liquids or gas by placing sensors. Conventionally, these sensor measurements are plugged into elaborate mathematical formulations, or reservoir models, that predict the properties of the subsurface such as the porosity and permeability of rocks.

But reservoir models are mathematically cumbersome, require extensive human intervention, and at times, even give a flawed picture of the underground geology. Misra said there has been an ongoing effort to construct algorithms that are free from human involvement yet accurate.

Machine learning algorithm

For their study, Misra and his team chose a type of machine-learning algorithm based on the concept of reinforcement learning. Simply put, the software learns to make a series of decisions based on feedback from its computational environment.

“Imagine a bird in a cage. The bird will interact with the boundaries of the cage where it can sit or swing or where there is food and water. It keeps getting feedback from its environment, which helps it decide which places in the cage it would rather be at a given time,” Misra said. “Algorithms based on reinforcement learning are based on a similar idea. They too interact with an environment, but it’s a computational environment, to reach a decision or a solution to a given problem.”

So, these algorithms are rewarded for favorable predictions and are penalized for unfavorable ones. Over time, reinforcement-based algorithms arrive at the correct solution by maximizing their accrued reward.

einforcement-based algorithms

Another technical advantage of reinforcement-based algorithms is that they do not make any presuppositions about the pattern of data. For example, Misra’s algorithm does not assume that the pressure measured at a certain time and depth is related to what the pressure was at the same depth in the past. This property makes his algorithm less biased, thereby reducing the chances of error at predicting the subterranean environment.

When initiated, Misra’s algorithm begins by randomly guessing a value for porosity and permeability of the rocks constituting the subsurface. Based on these values, the algorithm calculates a flow rate and pressure that it expects from a borehole. If these values do not match the actual values obtained from field measurements, also known as historical data, the algorithm is penalized. Consequently, it is forced to correct its next guess for the porosity and permeability. However, if its guesses were somewhat correct, the algorithm is rewarded and makes further guesses along that direction.

The researchers found that within 10 iterations of reinforcement learning the algorithm was able to correctly and very quickly predict the properties of simple subsurface scenarios.

Misra noted that although the subsurface simulated in their study was simplistic, their work is still a proof of concept that reinforcement algorithms can be used successfully in automated reservoir-property predictions, also referred as automated history matching.

“A subsurface system can have 10 or 20 boreholes spread over a two- to five-mile radius. If we understand the subsurface clearly, we can plan and predict a lot of things in advance, for example, we would be able to anticipate subsurface environments if we go a bit deeper or the flow rate of gas at that depth,” Misra said. “In this study, we have turned history matching into a sequential decision-making problem, which has the potential to reduce engineers’ efforts, mitigate human bias and remove the need of large sets of labeled training data.”

He said future work will focus on simulating more complex reservoirs and improving the computational efficiency of the algorithm.

This blogpost is originally from Aquantico | Challenge, innovate & deliver value

Enterprise AI | BY Todd R. Weiss

Shell, C3.ai, Microsoft and Baker Hughes are collaborating on an Open AI Energy Initiative (OAI) that aims to grow AI use across the energy and process manufacturing industries.

The OAI is envisioned by the partners as an open ecosystem of AI technologies that will provide a framework for energy operators, service providers, equipment providers and the software vendors who serve them to create new AI and physics-based models, monitoring, diagnostics and more to help solve critical industry needs, according to the group.

Some 92 percent of all facility systems shutdowns and process upsets are unplanned, which often leads to service disruptions which cause problems for customers. That is one of the industry challenges the OAI will be targeting as it works to gather and disseminate AI technologies and information that can be freely used to prevent such disruptions, the group said.

AI & data analytics to solve complex problems

As it begins its work, the OAI will first focus on using AI to improve systems reliability, uptime and performance of energy assets and processes.

Powering the OAI’s launch is the BakerHughesC3 (BHC3) AI Suite and cloud services from Microsoft Azure, which are being used to provide a broad range of capabilities to OAI users. Included in the AI Suite is a BHC3 Reliability application, which will serve as a foundation for the first work. BHC3 Reliability is an AI-based application that provides reliability, process, and maintenance engineers with AI-enabled insights that can be used to predict process and equipment performance risks.

BHC3 AI Suite’s ability to integrate enterprise-scale data from disparate data sources and train AI reliability models that cover full plant operations while taking full advantage of Azure, Microsoft’s scalable, enterprise-class cloud infrastructure. The OAL will combine the BHC3 Reliability application and Azure resources with technologies from all four partners and other leading energy companies to offer interoperable AI models, monitoring, diagnostics, prescriptive actions and services, according to the group.

AI applications and AI algorithms marketplace

Ed Abbo, of C3.ai

“What we’re enabling is the transition and or digital transformation of the energy industry,” Ed Abbo, president and Chief Technology Officer at C3.ai, told Enterprise.AI. “What that means is that we’re allowing for a marketplace of AI applications and AI algorithms that initially will start with reliability, to reduce what’s referred to as non-productive time in the oil and gas industry and in process industries.”

The OAI is being created as an open ecosystem so that other energy companies, power companies, oil and gas vendors, refining companies and software makers can participate, subscribe to the group’s algorithms and then publish their algorithms through the marketplace, said Abbo.

“Non-productive time in oil and gas is when a refinery is down because a piece of equipment isn’t working or a pump or compressor is not working,” he said. “Where AI fits in is that these are algorithms that can anticipate or predict the need for maintenance in advance of failure, to basically make predictions based on the data from sensors and prior maintenance on things that are likely to fail in the not-so-distant future that would cause downtime.”

Armed with those predictions and warnings, plant or systems operators are alerted so they can take actions to improve the operational efficiency and uptime of the facility, said Abbo.

The four partners of the OAI provide a very solid foundation for the nascent group “because it’s representative of the ecosystem that we believe will form around this initiative,” added Abbo. “The fact that Shell is in it and is publishing their algorithms [as part of the project] is highly encouraging, because that means that other oil and gas companies will follow suit. The fact that Baker Hughes, as an equipment provider and all-field services provider, is included means that others will also participate. And software vendors like C3.ai and … Microsoft [being involved] is an industry first using AI applications. I think we’ll see this ecosystem grow.”

Driving Targeted AI Changes for the Energy Sector

Dan Brennan, of Baker Hughes

Dan Brennan, a senior vice president and general manager for energy technology company Baker Hughes, said the OAI envisions driving AI to make changes that can help resolve the challenges being faced in these industries.

“The opportunity here is leveraging AI technologies to take really a dramatically different approach, and it’s what we refer to as a ‘system of systems’ approach,” said Brennan. By having scalable technology that allows operators to ingest data including maintenance records, telemetry and more, it can then be used to identify systems problems early. “It’s the word ‘early’ that’s the important thing here for the energy industry.

If you’re able to avoid or at least know within 30 or 60 days that there is a maintenance event that has to occur, there’s a tremendous amount of logistics and scheduling that has to go in there. Is there a planned maintenance window coming up? Is there an unplanned maintenance window coming up? The opportunity here for AI is really to start to get awareness early in the process where there’s potential degradation or failures coming in.”

Those problems can include pipes that are about to crack, shaft bearings that will soon fail, vibrations that are starting to ominously grow within facilities and a myriad of other potential machine failures.

“The short answer is it could be all the above,” said Brennan. “If you take the example of a refinery or petrochemical facility and really large complex facilities, they’re generally very well-instrumented today. So, there could be data that’s coming off of a condition monitoring system. Generally speaking, most of our customers have pretty mature implementations of these operational technology systems that are out there.”

A Step Forward for AI in Industry

Kevin Prouty, an energy and manufacturing insights analyst with IDC, called the creation of the new OAI a solid move.

Kevin Prouty,, of IDC

“It’s the culmination of a series of trends in all industries, but especially in oil and gas,” he said. “It’s taking an infrastructure platform (Microsoft Azure), an AI platform (C3.ai), an industry technologist (Baker Hughes), and an industry titan (Shell) and getting them all on the same AI page.”

Through the OAI, the four partners “potentially solve a lot of sticky issues that have plagued data management and AI, namely who owns the data, the models, and the IP,” said Prouty. “C3.ai and Baker Hughes have solved many of the technical issues with AI, but having a prebuilt platform that solves many of those issues will accelerate AI adoption and the push for Industry 4.0 in energy.”

The use of AI in working to solve some of the biggest problems in the energy industry is probably the most compelling application of AI today, said Prouty.

“It’s that step towards autonomous operations that Industry 4.0 has been striving for,” he said. “It’s still a way off, but getting the operating models out in the open and having non-technical issues addressed is a big first step.”

The ideas seen in the OAI initiative could be used for other industries as well, he added. “Chemical and petrochemical [initiatives] are only a short step away from oil and gas operations,” he said. Also important is that “Shell has made a significant commitment to support the initiative with its own models and analysis,” added Prouty.

This blogpost is originally from Aquantico | Challenge, innovate & deliver value

Engineering.com| BY Zeeshan Hussain

Major players in oil and gas invest in big data analytics and predictive maintenance solutions in the wake of increasing instability in the industry.

Eni SpA, an Italian oil and gas (O&G) multinational, recently announced a partnership with Google Cloud. BP and Amazon also agreed to further collaborations. Why are supermajors in the O&G industry collaborating with tech companies, and what benefits come out of such enterprises?

There has recently been unprecedented upheaval in the global O&G industry due to various complex challenges, including upstream volatility, midstream constraints, industry consolidation and shifting customer demands based on an increasing swing toward greener alternatives. With an unprecedented drop in demand due to COVID-19 becoming the proverbial straw on the camel’s back, it has become imperative for businesses to go on a cost-cutting drive.

Contrary to popular belief, the oil business is very technologically advanced. Cutting-edge tools are used to map out and drill into complex rock formations thousands of feet below the ground.  For example, Total S.A, the French oil major, and Eni are running two of the most powerful supercomputers in the world. Total’s Pangea has clocked speeds of more than 5 quadrillion calculations a second (yes, that is extremely fast), according to The Top 500 List.

Nevertheless, the industry has fallen behind in terms of digital transformation and leveraging real-time data. In late 2014, MIT Sloane Management Review and Deloitte scored the O&G sector’s ” digital maturity ” at 4.68 out of 10. By the fall of 2019, things got even worse, with O&G scoring a mere 1.3, easily the lowest amongst all the sectors. However, this is changing due to the perfect storm of advancements in technologies, falling costs of digitalization and lower oil prices, which may never reach the high levels previously attained. PwC has reported that O&G executives see the most potential in cloud computing, energy analytics and machine learning.

To accomplish this, big oil has finally joined other industries in the digitalization drive and turned to big tech to provide.

Data Is the New Oil

An enormous amount of data is constantly being generated by the O&G industry:

• Data volume for a single well exceeds 10 TB per day, thanks to optical fibers combined with various sensors being used in wells to record different parameters, such as fluid pressure, temperature and composition.
• A single offshore drilling rig can create over one terabyte (TB) of data per day, especially due to recent innovations in drilling tools, such as logging while drilling (LWD) and measurement while drilling (MWD).
• A large refinery generates one terabyte of data daily.
• Pipeline inspections generate approximately 1.5 TB for every 600 km inspected and ultrasounds around 1.2 TB for eight hours of scanning.
• Seismic surveys collect around 10 TB each.

But what can be done with such oceans of data? This is where big tech is providing expertise, innovation and new technologies for the digitalization of big oil.

A Match Made in Cyberspace

Within the past couple of years, Microsoft has announced collaborations with Chevron, ExxonMobil, Suncor and Petrobras. These partnerships have established Microsoft Azure as their primary cloud provider in order to harness the power of cloud computing, big data and machine learning.

Halliburton is using Microsoft’s technologies, such as machine learning and augmented reality (AR), an example being DecisionSpace365 created on Azure. It enables real-time data streaming from devices in oil fields and the ability to apply deep-learning models for optimized drilling and production, consequently lowering costs for customers. Predictive deep-learning algorithms help optimize field assets and enable exploration and deep-earth models by using software to fill gaps in sensor data while reducing the number of steps and time required for rendering models.

Suncor, a Canadian energy company specializing primarily in oil sands, is applying Microsoft’s technologies in various ways. One example is its use of fully autonomous trucks at its oil sands mines. Employees at some of their facilities wear wireless badges, allowing the company to track and analyze frontline maintenance work with the goal to improve safety and productivity.

Amazon Web Services (AWS) counts BP and Shell amongst its customers. BP in particular has significantly expanded its relationship with AWS by agreeing to supply renewable energy to power Amazon’s operations. In exchange, Amazon will help BP digitize its infrastructure and operations. This includes applications migration from BP’s own European mega data centers to the AWS cloud, in addition to collaborating on different AI and machine-learning initiatives. In this way, BP can reduce energy use and emissions from its own digital infrastructure and data centers. The resulting lower operating costs are the cherry on top of the cake.

Total and Google Cloud signed an agreement to jointly develop AI solutions. These can be applied to subsurface data analysis for O&G exploration and production, most notably from seismic studies (using Computer Vision technology) and to automate the analysis of technical documents (using Natural Language Processing technology).

Eni has also linked up with Google Cloud to construct a new digital platform, Open-es, to support sustainability in the industrial supply chain. It will be open to all players in the energy sector to pool data, best practices and sustainability models. Knowledge-sharing will set in motion an upsurge in safety and efficiency across the industry.

Schlumberger, partnering with Google, is deploying its O&G software suite, including the WesternGeco Omega geophysical data processing platform and Software Integrated Solutions DELFI cognitive E&P environment on Google Cloud Platform (GCP), to perform seismic processing, interpretation and subsurface modeling.

Digital Twins

Graphics processing units (GPUs), due to their enormous processing power, offer benefits through the concept of digital twins. A digital twin is a continuously learning virtual digital copy of all assets, systems and processes. It can predict asset behavior and capacity to deliver on specific outcomes within given parameters and cost constraints.

NVIDIA is assisting Baker Hughes in employing GPU-accelerated computing to work on platforms and build AI-enabled services for major O&G operators across the globe.

Similarly, Shell has chosen Bentley’s iTwin platform, which is an Azure cloud-based platform providing interoperability across supply chain systems. This will allow Shell to manage and analyze data, integrate with existing systems, and increase collaboration across business operations.

Data Can Predict the Future

According to research by Kimberlite, just 3.65 days of unplanned downtime a year can cost O&G companies approximately $5 million. An average offshore O&G company experiences about 27 days of unplanned downtime a year, which can amount to $38 million in losses. In some cases, this number can rise to as much as $88 million.

Driven by the Internet of Things (IoT), operations and maintenance are turning more proactive and predictive as opposed to reactive and planned. Data can be leveraged from sensors (e.g. temperature, vibration, flow rate sensors, etc.) to identify any anomalies in equipment behavior and forecast failure modes within a certain timeframe.

Predictive-maintenance solutions help O&G companies forecast equipment breakdowns before they can have an adverse impact on their safety levels and bottom line. Schneider Electric reports that applying IoT-enabled predictive-maintenance solutions can help save $4 million due to early identification of rotating machinery damage, $500,000 due to early identification of coupling failures and $370,000 due to early identification of heat exchanger valve problems.

It can also improve asset utilization and increase productivity by making operations more flexible and agile. By comparing operational data across multiple pieces of equipment, IoT solutions can help estimate machine utilization, identify the periods of best performance and establish best practices to improve performance across the entire O&G supply chain—from exploration to refining and distribution.

While the O&G sector produces 29 percent of methane emissions, the greenhouse effect of methane is 86 times higher than that of carbon dioxide. In the U.S. alone, the O&G industry releases 1 million tons of methane into the environment every year due to leakages. IoT helps identify and reduce pipeline leaks, thus decreasing environmental damage.

Augmented/Virtual Reality (AR/VR)

O&G companies are also adopting AR/VR for subsurface studies, training and simulation, maintenance and planning. Hard hats equipped with AR can project instructions for the technician directly onto the equipment to conduct an inspection or maintain a system. Instead of being dependent on manuals, AR enables this information to be delivered graphically, thus increasing efficiency and reducing errors.

VR can be used for practical training instead of in a classroom or on location. Trainees use a VR headset to enter an environment or interact with a piece of equipment virtually. During the process, it provides invaluable hands-on training at a fraction of the cost. Likewise, VR apps connected to sensors enable engineers to monitor equipment in real-time without needing to be onsite. Geoscientists are also able to visualize seismic data through VR, and even drill virtually, so that they can better determine where to explore.

Socially Distanced Drilling and Operations

The three largest service providers in this field are Schlumberger, Halliburton and Baker Hughes. Before the pandemic, O&G companies always counted on these specialists to be onsite and control drill bits and interpret real-time data. Now, to adhere to travel restrictions and social-distancing recommendations, drillers had to work from home.

For ongoing operations, during the second quarter of the year, Baker Hughes and Schlumberger both had two-thirds of their drilling activity supported by remote work. For Schlumberger, this was up 25 percent from the first quarter. For Baker Hughes, it was up 20 percent. Halliburton, the largest U.S. fracking company, has reduced the number of onsite engineers by shifting work to real-time operation centers. All of them have cited the adoption of remote work, which allowed them to shut down many operational sites, as the leading cause of significant operating cost reductions.

For drilling new wells, due to travel restrictions, many companies might not have been able to achieve their targets without the adoption of remote technology. Chevron was able to continue directional drilling in the Permian Basin of West Texas and New Mexico by setting up a remote team based mostly out of their homes in Houston because they were able to get real-time data through Azure.

ExxonMobil was able to make its Permian Basin operations totally cloud-based, leading to secure and reliable collection of live data from the oil field assets. This has allowed for quicker and more accurate decision-making on drilling optimization, well completions and personnel deployment.

There is no doubt that the confluence of technologies is beneficial not only for the O&G industry but also the whole world. It will reduce health and safety incidents and lead to better-trained personnel by allowing remote work and simulations unless absolutely necessary. Predictive maintenance will save tons of money by streamlining maintenance plans, as well as an overall reduction in the number of catastrophic failures over time. Goldman Sachs estimates that a 1 percent reduction in the O&G industry’s capex (capital expenses), opex (operating expenses) and inventory management can result in savings of about $140 billion over a 10-year period. Last but not least, all these factors will lead to considerably minimizing adverse effects on the environment, thus protecting our precious lands, oceans and wildlife.

This blogpost is originally from Aquantico | Challenge, innovate & deliver value

Maritime Logistics | BY Matthew Tremblay, ABS

Industries are adapting to an increasingly digitalized landscape. The floating production, storage and offloading (FPSO) industry is no different. As concerted efforts are made to improve project economics Matt Tremblay, ABS Senior Vice President, Global Offshore, discusses how digitalisation and data analytics can increase safety, reduce costs, and build robust technical and operational capabilities.

No one could have predicted what a challenging year 2020 would become. Offshore production activity fluctuated dramatically with changing market economics and a global pandemic, the fall out of heightened geopolitical tensions, not to mention new IMO regulations introduced at the beginning of this year.

On the horizon, however, is positive news. Markets are beginning to evolve, and an example of this is Brazil, where both Petrobras and international oil companies are again active. Increased activity is also taking place in the North Sea, and in Australia. New entrants are making strong headway in regions such as Mexico, where Petroleum Reform is opening offshore exploration and production to foreign companies.

Evolving FPSOs through the influence of digitalisation
With these positive developments, the Floating Production Storage and Offloading (FPSO) markets and the assets themselves, continue to evolve.

With the largest fleet of classed FPSOs, ABS has supported their development in both size and complexity. At its core, an FPSO is simply a production, storage, and offloading system. While the basic design concept hasn’t fundamentally changed, what is evolving are the technologies, systems, and tools available for an FPSO to optimize its design and operation.

Influencing this change are the fundamentals of how asset management can be applied to achieve leaner, cost-effective operations and reliable exploration activities. There is a primary focus on improving maintenance scheduling and performance, reducing human factor involvement, and increasing the lifetime use of the FPSO asset, safely. The importance of digitalisation is increasingly becoming a priority on the boardroom agenda of many operators, particularly with industry-wide initiatives toward net-zero carbon.

Managing complex assets

Managing the integrity of an FPSO poses a particular set of challenges, and integrity management is still often managed using outdated, labor-intensive spreadsheets or other basic systems.

However, mindsets are changing with increasing awareness on how data can be leveraged to help provide real-time answers to common maintenance, operations and performance questions.

One of the benefits of digitalisation is the increase in performance and productivity that can be achieved with a minute-by-minute visibility of how an FPSO is operating. Giving an owner-operator the opportunity to clearly track the change in asset condition over time, from construction through to late-life, helps make more informed decisions, supported by more reliable data, making the industry safer.

Considering the challenges of FPSO operations, fewer, more focused inspections that reduce the need for tanks or equipment to be physically examined while maintaining safety standards, represent a compelling proposition. As does an optimized maintenance system to improve uptime and increase reliability. Combine this, and you have a simpler way to manage maintenance crews on board, optimize turnarounds, simplify logistics, streamline the POB, and improve operations. The end result leads to safer operations, a reduction in OPEX, and improved profitability.

The trick is how to avoid adding unacceptable risk. It’s why ABS has moved to develop solutions using data science as the basis for an informed and targeted decision-making process, using predictive analytics to guide operational decisions. Examples include analysis of early corrosion detection and coating failures using machine learning and pattern identification intelligence, and real-time monitoring and transparency into how a vessel’s operational profile and loading patterns are affecting its structural integrity, providing predictive alerts for detected anomalies to reduce the risk of unplanned downtime and improvement in maintenance strategies.

The goal in moving to a condition-based system is that you are letting the condition of the asset – such as the FPSO hull – tell you how often you need to inspect and maintain it. For example, consistent hull inspections showing no corrosion may allow you to increase your inspection interval.

It starts with collecting data that will be processed and analyzed. Most of this data is something we already have, such as the original design information, the engineering assessments and analysis, the inspection records, and survey results. Environmental data may be acquired from industry sources or measured onboard. Operational data such as loading patterns, production profiles, failure modes, maintenance data, are also available by manual intervention and measurement, or through sensor-based monitoring systems.

When you combine all this information with diagnostic and potentially prognostic models, can then detect health and performance anomalies in the form of impending failure or performance degradation at an early stage.

This provides valuable information for corrective and preventative actions by allowing both onboard and onshore management teams to observe the condition and status of their vessels’ integrity. This information empowers operators to develop appropriate strategies for maintaining their assets, optimizing decision-making, and managing integrity and maintenance as efficiently as possible to avoid unexpected downtime and productivity loss in operations.

Creating your data ecosystem

With any offshore unit, and in any operation, there are different kinds of data generated. There is data generated from the operational side, such as oil and vibration testing. There is data generated from repairs, maintenance, warranty claims, CMMS data, as well as met-ocean conditions and environment data.

All these data configurations are very diverse and were traditionally kept in silos. Today, we’re able to combine data sets from multiple sources together with technologies that help operators make better and more informed to-the-minute decisions. Combining multiple data sets generates big data analytics, which is the concept of using different data sources to create penetrating new insights.

Auditing your data and applying digital technology will automate the translation and data analysis process.

Digital solutions can then be used to visualize the status of that asset, and monitoring tools can be used to help you focus on the big picture. For example, combining data analytics with Artificial Intelligence (AI) can investigate the ‘what if scenarios’ and provide future insights, enabling operators to begin to answer not only what happened, but also what will happen.

Building a Digital Asset Framework: Digital twin

“Digital Twin” is a familiar term, but it is a term that is hard to define. For example, if you assessed 10 separate projects, each with their own Digital Twin, all 10 of them would give you a different description of what it is, what it does, and what it delivers.

This is not necessarily a bad thing, and in reality, no two projects will be the same, particularly in the design and operation of FPSOs where there are vast technical challenges that require numerous detailed process, control, safety, and flow simulations to maximize production, from subsea to offloading.

In a Digital Twin, physics-induced data are used to mirror and predict the status and life of its corresponding physical twin. This enhances the operation of an FPSO by helping to both visualize and predict the performance of that asset. As the digital twin is designed to continuously collect and process operating data from sensors and other data sources, it presents a constantly evolving picture of the FPSO’s living status at all times.

While you may not need all of the potential analysis capability available today to support a new FPSO that has just been installed, it is beneficial to deliver a new FPSO with a robust condition model to allow you to begin the full lifecycle of the model alongside the physical asset. Ultimately, it allows operators to better calculate and forecast the remaining life of their asset.

Applying Digital Twin technology as part of a “Digital Asset Framework”, allows for a single source of truth that can be shared with stakeholders, including owners, operators, project financiers, insurance providers, and regulators alike. Everybody can access the same reports, data, and insights in a way that makes sense through data visualization.

Digital-driven business outcomes

The digital solutions applied to an FPSO impact its entire value chain, from equipment and inventory to operational efficiency, including optimization of inspections and onboard activities. Coupling these digital solutions with traditional risk-based inspection and maintenance planning techniques has shown a 10:1 return on investment opportunity over the total asset life due to optimized repair and inspection planning.

In early project CapEx planning, condition models, sensor data ingestion tools, remote inspection technology, are all aspects of what should be looked at to ensure an FPSO is future-proofed, so that in 10 years from now, an operator can apply the latest predictive analytics techniques to forecast its remaining asset life.

Where operators manage a fleet of multiple offshore units, using the right digital tools and data insight offers benchmarking that helps compare one offshore unit’s performance against another in the fleet. This gives further opportunity to improve asset management activities through the efficient allocation or re-allocation of resources resulting in streamlined scheduling of fleet maintenance activities that are focused and specific.

A connected future

The transition from legacy systems to Digital Twin driven operations will be incremental, which will naturally incorporate a range of digital solutions to improve asset management and optimization.

The digital tools now entering the market allow operators to ingest, store, track, and analyze condition data in a way that was never possible before. These are technologies we are both building and implementing, focused on three primary goals; improving asset reliability, streamlining the Class process on offshore operations, and ultimately, supporting the improved profitability of the industry. Of course, this is all rooted in a framework of safety and quality spanning an end-to-end solution.

ABS has developed several innovations to support the monitoring and management of structural, machinery, and condition metrics needed for asset management and regulatory compliance.

ABS Condition Manager is just one of a suite of advanced new digital services and applications launched by ABS that offer unprecedented understanding of the status of an asset. A compartment-based, digital visualization of an asset’s condition, including inspection and repair history, as well as critical area monitoring using Class and operational data, the ABS Condition Manager application is a good example of how digital technologies can empower users with insights surrounding structural health, anomaly impacts and maintenance opportunities. The ability of Condition Manager to seamlessly integrate with onboard CMMS systems can result in up to a 50% reduction in effort to prepare annual maintenance work plans.

ABS is also exploring practical applications of AI-enabled inspection capabilities in areas such as corrosion detection, machinery performance, and monitoring, through to accumulated fatigue damage on structures based on asset-specific data, and even metocean route planning.

As we continue to move deeper into a condition-based and ultimately predictive approach, we are looking towards more sophisticated AI and using additional data from onboard sensors for advanced monitoring of vessel health, from the hull structure to whole-life integrity support with ‘live’ operation decision support.

From the design concept, through to construction, operations, and end of life, Class is connected to the asset, and the digital tools and technology that support it are transforming the future of FPSO operations.

This blogpost is originally from Aquantico | Challenge, innovate & deliver value

Plantservices.com | By Sheila Kennedy, CMRP, contributing editor

Maintenance and reliability best practices are continually improving and so are the technologies that support them. Firmly embedded in the realm of the “best” is predictive maintenance (PdM), which combines real-time monitoring of asset condition, environmental, and/or operational data with smart analytics to detect, assess, and forewarn of impending problems.

Prescriptive maintenance (RxM) takes PdM a step further by prescribing corrective actions for deteriorating conditions and including them in the alerts. RxM is a newer concept just gaining ground that is made possible by machine learning (ML), artificial intelligence (AI), and the internet of things (IoT).

“Preventing dreaded unplanned downtime provides a clear business benefit and driver for adoption of PdM,” said Ralph Rio, vice president at ARC Advisory Group. “Unplanned downtime often cascades into major losses including revenue, WIP materials, and larger equipment repair costs.”

Additionally, the costs for implementation and support of a PdM application have dramatically lowered with the IoT, cloud platforms, microservices for analytics, and wireless sensors, Rio observes. “Clear benefits and lower costs have improved financial justification and driven adoption in a wide range of industries,” he added.

The six case studies summarized below illustrate some of the numerous ways PdM and RxM are transformative.

BASF / Schneider Electric

BASF, the largest chemical company in the world, has digitalization as a corporate strategy. This includes using data to better forecast maintenance requirements and reduce unexpected shutdowns.

One such initiative involved an electrical infrastructure expansion at BASF’s Beaumont, TX, plant. Since production efficiency depends on having predictable electrical power, the plant chose to enable remote monitoring and management of its new power distribution substation’s operations and asset health with EcoStruxure Asset Advisor from Schneider Electric. The data-driven, IIoT-enabled service employs asset sensors for continuous condition monitoring along with predictive analytics to identify threats that could lead to asset failures.

BASF also has access to customized, proactive advice about how to prevent failures and improve its maintenance strategies through its partnership with Schneider Electric’s Connected Services Hub (formerly Service Bureau).

Read “How 7 companies are accelerating PdM and RxM at their plants”
The use case involved having more than 100 condition variables continually collected, measured, and computed for 63 substation assets. The asset data is monitored and analyzed from a digital dashboard that provides 24/7 insight into the substation’s global health index and specific asset statuses, from any location.

“We were surprised by some of the things that we found out. Asset Advisor is helping us to prevent catastrophic failures,” said Lee Perry, electrical design engineer at BASF. The cloud-based service “connects assets so we can look at the health of not just our electrical distribution equipment, but also the motor control centers and the motors that actually drive the process,” he explained.

“If there’s an issue, then we get an email from the Service Bureau saying, ‘We’re noticing this.’ I can log in to it remotely, look at the same information, and help troubleshoot that issue,” added Perry.

With around-the-clock access to data and expert guidance, the plant has the information it needs to make the right decisions at the right time, perform PdM to optimize asset health, and take steps to improve the efficiency of critical electrical distribution assets. These actions consequently benefit plant uptime, performance, productivity, and safety.

ALCOA / Senseye

PdM is a key part of Alcoa’s strategy to become a more stable and profitable organization. To help automate PdM and reduce downtime and maintenance costs, a proof-of-concept (POC) project involving 50 assets across two casthouse systems was conducted at its Fjar∂aál aluminum smelter in Iceland. The solution is now being expanded to at least 1,000 assets in Fjar∂aál and is scalable enterprise wide.

Senseye was chosen to unify and synchronize the equipment sensor data in the plant’s OSIsoft PI ecosystem with maintenance data in its Oracle eAM solution. From the current and historical ingested data, it automatically builds models and starts learning, without having to set up parameters or alarm levels. Isolated peaks in raw data create signatures that reveal trends and hidden failures. Predictive analytics identify what is happening and why, and can provide prognostic insights on the asset’s remaining useful life.

Operators are automatically notified of cases needing attention and can drill down for further details. It is “like having a thousand eyes in the plant” letting you know when data streams start to move away from normal, explained Árni Einarsson, reliability implementation manager at Alcoa in his presentation at OSIsoft PI World San Francisco 2020.

For instance, an idling current increase provided an indication of a fault in the HDC saw motor system. It was determined a belt guard had come loose and was in contact with the sawing drive, damaging the belt. Replacing the belts and fastening the belt cover during a maintenance shutdown resolved the issue, avoiding 12 hours of unplanned downtime.

A sensor failure detected in a coiler rod cropping shear motor prompted the discovery that a lower pinch roller sensor had come loose, leading to a sharp increase in shear motor torque. Re-fastening the sensor returned the torque to normal levels, avoiding three hours of unplanned downtime.

In total, Alcoa reduced unplanned downtime of the machinery by up to 20 percent and achieved full ROI in 4-6 months. “With the POC completed, we were able to scale the solution to other parts of the business,” said Einarsson. “The focus is on finding the best business cases to continue.”

Duke Energy Renewables / Seeq

Duke Energy Renewables, an owner/operator of wind and solar farms across the U.S., used advanced analytics and ML to automate profiling and detection of failing contactors on one of its wind turbines. “This was a trial run with one use case that was interesting, the data was available, and it seemed like a good candidate. We wanted to get up and running fast and to see if this even works for us,” said Abhi Hullatti, manager of performance analytics at Duke Energy Renewables, in his presentation at the ARC Industry Forum Orlando 2020.

Hullatti described how each turbine has six contactors that help to ensure that when the generator kicks in, it ramps up smoothly and synchronizes with the electrical grid. When any of the six contactors fail, the turbine goes offline for 2-10 days for diagnosis and repair. Turbine contactors at one site tended to fail more frequently than at others. Automating the prediction of impending failure would enable PdM, improve uptime, reduce maintenance costs, and allow better management of spare parts inventory.

Using an automated profiling tool from Seeq, a model was trained to look for the contactor fault error code and plausible leading-indicator signals (reactive power, active power, current, wind speed, rotor speed, and generator speed), to recognize what normal behavior looks like, and to provide one-hour advance notification of a fault.

The model ran against 2.5 years of cleansed signal data for the turbine and it found 12 occurrences of the error code, mostly within the few months preceding a failure. There were no false positives leading up to that outage, and no further error codes or predictions followed once all the contactors were replaced. The model can run continuously once it is validated and it will give automatic notification when something is going wrong, said Hullatti.

“The results are extremely promising, so we want to next expand this model to the rest of our turbines at that site, and also, more interestingly, look at other failure modes. That will be a lot more complex but also far more financially rewarding,” observed Hullatti. The return on the ability to catch a generator that is about to fail, and act proactively instead of reactively, is in the hundreds of thousands of dollars per event, he explained.

Global Mining Company / Uptake

A leading global mining company needed to predict and prevent failures that can cause unplanned downtime in its material transport operations. The company owns and operates a network of private railway tracks, rolling stock, and signals that move iron ore from its mining sites to the seaport. Any faults, delays, or breakdowns in the process of moving the high-value material is not only costly from an equipment maintenance and operational performance perspective, but it can also be potentially catastrophic.

The trains and rail infrastructure already produce immense amounts of data from wayside telematics devices. If harnessed, the Wheel Impact Load Detection (WILD), Wheel Condition Monitoring (WCM), Hot-Box Temperature Detection (HBD), and Bearing Acoustic Measurement (BAM) data could provide operational and condition insights into anomalies with sufficient time to take corrective actions.

The mining company chose Uptake, an industrial AI software company, to provide the necessary visibility into degrading asset conditions across the network and advanced analytics to prescribe recommended solutions. The software is now analyzing the four telematics data sources for indications of faulty wheels, wheel bearings, and axles on 10,000 rail cars.

Events are ranked according to criticality. Each high-severity wheel or bearing downtime event for a rail car costs the company at least $6,000 and requires immediate attention to return it to operation. Previously unforeseen, the mining company now has roughly a weeks’ advance notice on high-severity wheel alerts, 11 days’ notice of high-severity bearing alerts, two weeks on medium-severity alerts, and a month on opportunistic events.

With the advanced notice of issues and prescriptive alerts, the company can proactively bundle its maintenance activity, significantly reducing downtime and avoiding rail car failure. As a result, it is able to reduce its single-car unscheduled maintenance events by an estimated 50 percent, from 1,850+ per year to 925+ per year, which represents approximately $34 million in savings over five years.

Cement Plant / Aspentech

A cement plant that had struggled with cyclone blockage in its cement kilns was one of several PdM case studies shared by Chris Williams, global director of asset performance management (APM) services for AspenTech, at his ARC Industry Forum Orlando 2020 workshop. Frequent blockages in filters and cyclones limit production and increase maintenance costs, he explained. Subtle changes in the preheater process can eventually lead to blockage.

To reduce downtime and optimize maintenance, the plant sought a solution to predict and avoid cyclone blockages through early and accurate detection. Having the added benefit of RxM capabilities to resolve emerging problems quicker would minimize production losses.

The cement plant chose a PdM and RxM solution with AI and ML capabilities from AspenTech. Maestro for Aspen Mtell was used to build enhanced agents capable of predicting cyclone blockages. The failure agents trained on past blockages to identify the failure signatures that precede degradation, breakdowns, and process disruptions, and learned to recognize the pattern.

The multivariate (MV) models helped the plant to better understand the root cause of the condition and provided prescriptive guidance on feed composition and kiln operating conditions to the operators, enabling them to quickly bring the process back to normal operation. Within weeks, the solution was able to provide several days of early warning. “Eliminating just 25 percent of blockages generated over $1 million in savings,” said Williams.

Wärtsilä / Pega

Wärtsilä, a Finnish technology and service provider for energy and marine markets around the world, needed to improve its ability to process and analyze asset condition data received daily from thousands of equipment installations. An IoT engine upgrade was needed to help preempt performance issues with its customers’ power plants and vessels, and to automate feedback to each customer. Its legacy system could not sufficiently scale to handle the desired automation.

Many of Wärtsilä’s installations have multiple engines per site, and each engine has attached equipment and hundreds of sensors generating condition-based data. To better harness the global data, the company needed to map it to a normalized data structure for quick processing and apply a rules framework to assess the sensor data for anomalies. This would enable PdM practices to preempt equipment failures and also help to optimize service support.

Read “RxM: What is prescriptive maintenance, and how soon will you need it?”
The company worked previously with Pega on other projects and chose the Pega Platform to extend its existing IoT capabilities. The digital transformation platform for Digital Prescriptive Maintenance is designed to help optimize the cost and duty-cycle of devices and systems.

With the new IoT-powered solution, Wärtsilä now compiles all incoming sensor data in a data lake in the cloud, where it is normalized and fed into the Pega Platform. Using a complex rules framework, the data is processed to identify exceptions that may indicate a developing risk of engine failure or a reduction in equipment performance. Daily feedback reports document the findings and prescribe recommended actions, enabling the company to save time and money by avoiding unplanned downtime and production problems.

Benefits to the customers include improved environmental and economic performance and long-term predictability of their vessels or power plants. Wärtsilä is also benefitting from optimized equipment maintenance, improved reliability and performance, and increased sales of proactive maintenance contracts.

Each of these industry leaders is enjoying the rewards of using maintenance and reliability best practices. With the benefits of PdM and RxM being realized, the old ways of doing business seem antiquated and companies like these are not looking back.

This blogpost is originally from Aquantico | Challenge, innovate & deliver value

Algorithm-X Lab | BY KC Cheung

Machine learning in oil & gas can be used to enhance the capabilities of this increasingly competitive sector. Not only can it help to streamline the workforce. The technology can also be used to optimise extraction and deliver accurate models.

These benefits are just some of the reasons why machine learning in oil & gas is becoming increasingly important.

Here are 10 ways that the impact of machine learning in oil & gas industries is being felt.

Table of Contents

• Accurate Modelling
• Pinpointing Exactly Where to Dig with Machine Learning
• Applying Machine Learning in oil & gas to Improve Subsurface Characterisation
• Optimizing Drilling Operations
• Solving Problems Quickly with Machine Learning Applications
• Predictive Maintenance
• Internet of Things
• Predictive Software For Energy Purchases Customer Market
• Replacing Manual Workers
• Machine Learning to Predict Operational Outcomes

Accurate Modelling

One of the most noticeable impacts of machine learning in oil & gas focused industries is how it transforms discovery processes.

Applications employing machine learning in oil & gas enable computers to quickly and accurately analyse huge amounts of data. This includes being able to sift precisely through signals and noise in seismic data. After this information has been gathered and analysed modern software applications can construct accurate geological models.

This allows operatives to predict, accurately, what is beneath the surface before drilling has begun. It is believed that, if adopted over the entire industry, this will decrease the number of dry wellheads by 10%

Current Applications in Modelling

One current application of machine learning in oil & gas can be seen in the Dutch Central Graben in the North Sea. By using machine learning in oil & gas in this manner has allowed engineers to auto-track a Jurassic seismic horizon. This has been done with only a few manual seed points.

The latest generations of algorithms are producing more detailed and accurate results than any previous modeling. These algorithms also don’t lose their accuracy when asked to analyse difficult terrain.

Faults or stratigraphically complex areas can be accurately mapped in detail. There is always a need for the models to be checked.

However, so far, this application is proving itself to be quicker and just as accurate as a human model.

Machine Learning can Improve Drilling Operations

Despite these developments, scientists have been slow to fully realise the benefits of machine learning in oil & gas industries. Multivariate modelling is now becoming the most reliable way to develop resource plays.

This allows users to maximize tools such as NPV, IP30, or EUR. One of the leaders in this sector is Drilling Infos smart application DI Transform.

This software solution allows for user-directed extraction of geophysical and geological data, robust data QC, and powerful model building. This information can be implemented in a number of different ways.

One of the most useful applications is in the building of detailed, accurate models. A detailed, accurate and reliable model, like those constructed by machine learning, is priceless.

It allows you to know exactly where to drill and what you will be drilling through. This allows problems to be solved almost before they are encountered.

By using these models companies can save money and increase productivity. It is clear that this will be an invaluable application for oil & gas operations.

Pinpointing Exactly Where to Dig with Machine Learning

Geoscience consulting firm Rock Solid Images (RSI), specialise in borehole characterisation. RSI is a leading firm in the field of interpreting seismic data with well log data. This is largely because they have been able to reliably combine complex geologic models with established rock physics methods.

Combining this information allows them to reliably pinpoint where, under rock formations, oil and gas is present. RSI is currently involved in a project that aims to reduce the risks that come with exploration drilling.

If they are successful it could be a significant moment for the oil & gas industry.

Process Optimization

RSI is also working to use machine learning algorithms that can accurately model remote, hard to reach locations. This is being done by using models of well explored and documented areas that have similar geology.

It is hoped that, in time, this prediction mapping ability will become portable.

For example, these models will be able to accurately map Barents Sea rock properties using geological information gathered in mid-Norway. This application of machine learning in oil & gas operations can help to optimize the exploration and drilling processes.

Every time a well is dug, many fields of data are recorded. This raw data is analysed by a petrophysicist before being fed into sophisticated software. One such application is RSIs rockAVO software, this allows pattern recognition to take place.

Consequently, users of the software can read the rock physics of existing wells. This information gives the user a detailed picture of the geology of the area.

By studying this known information RSI is aiming to predict the geology elsewhere in the region. This means that less boreholes or test holes need to be dug, saving time and money. By using machine learning this way we can make informed decisions about where to dig.

Machine Learning to Provide well Placement Solutions

University of Texas PhD student Azor Nwachukwu, is conducting research into geostatistics and reservoir characterisation.

In particular how these can be optimized by using machine learning in exploration. Nwachukwu is part of a team working to determine a better method for well placement.

Traditionally determining well placement has involved a reservoir simulator being used a function evaluator. This is both time-consuming and expensive.

A data driven model is a more accessible, quicker and more accurate alternative. It is also able to create models in complex situations and inaccessible areas.

It’s hoped that their machine learning in oil & gas based proxy will solve the inefficiencies of traditional reservoir simulators. By including connectivity networks data related to spacing, coverage and well-to-well connectivity is also utilised. This increases the amount of accurate, real-time, useful information that can be analyzed.

This, in turn, improves geological realisations in modelling.

This application of machine learning in oil & gas exploration and extraction allows for a quicker, more accurate process.

This, in turn, will help to make the process more efficient.

Applying Machine Learning in oil & gas to Improve Subsurface Characterisation

Deep and machine learning in oil & gas extraction processes can also help to improve subsurface characterisation.

PhD candidate Hao Li, from the Mewbourne School of Petroleum and Geological Engineering at the University of Oklahoma is one of the leading lights in this field.

Hao Li is researching well logging, machine learning, deep learning and petrophysics. He is combining this with unconventional enhanced oil recovery. The end aim of this process is to use deep learning to improve subsurface characterization.

A consequence of this work concerns NMR logs and their accessibility. NMR logs are used to provide insight into fluid composition. It also informs the users of the pore size distribution of a formation. While this technology is incredibly useful it can be expensive to acquire and implement.

Hao Li is aiming to use deep learning to create a synthetic alternative.

Exploration Phase

Machine learning in oil & gas, as well as other implementations, uses Bayesian statistics. This is a branch of mathematics that utilises ”degrees of belief” and interpretations of probability.

Applying Bayesian statistics allows machine learning in oil & gas, and other applications, to create algorithms that analyse data. It also enables predictions to be made, based on the information analysed.

There are many potential applications of machine learning in oil & gas exploration. In fact, it is a perfect utilisation of machine learning. Machine learning in oil & gas enables patterns to be quickly identified across multiple variables.

This application of machine learning in oil & gas exploration speeds up what is a time-intensive process.

MORE – Data Science – 8 Powerful Applications

Smart Solutions can Enhance Reservoir Modelling

Known as reservoir modelling this also allows users to predict how formations will react to certain drilling techniques. By using machine learning in oil & gas exploration in this way we will know where and how to drill. A combination of algorithms and fuzzy logic will verify these models.

As well as verifying models, this also allows for accurate predictions to be made when information is incomplete or deemed unreliable. This application allows for a model to be constructed and for virtual drilling will take place.

Allowing engineers to pinpoint the best route through a rock formation. This process can occur long before any physical drilling equipment even arrives on site. Knowing exactly what is beneath the ground, and how the ground will react to drilling, we can avoid further flops like McMoRan’s ultra deepwater well.

Machine learning in oil & gas, as well as AI and case based reasoning, will save time and money. It will also help operatives to learn lessons from past successes and mistakes.

The more this technology is used, and the more information it is given, the more accurate the models will become.

Optimizing Drilling Operations

Applying AI and machine learning in oil & gas industries will improve operations. This will occur by enabling effective decision-making processes and optimizing drilling operations. By constructing complex models, based on collected data, AI will learn from past operations.

This will allow the technology to learn and improve as more data is recorded. The more we implement AI and machine learning in oil & gas industries, the better the potential to revolutionise workflow.

Chiranth Hegde, a data scientist, is helping Shell to incorporate machine learning, analytics and well connectivity. With Shell, Hegde is working to develop an end-to-end coupled drilling optimization advisor.

This will make use of the latest advances in machine learning. In the oil & gas sectors, companies have been slow to realise the potential of these technologies. This is slowly changing as companies become increasingly aware of the possibilities.

What makes Hegde’s work stand out is that until now optimization studies have looked at drilling metric, mechanical specific energy (MSE), or vibrations.

This has been looked at in isolation, independent of other factors. As a result, it doesn’t represent bottomhole conditions accurately. By combining a number of factors, Hegde is developing a coupled model.

While difficult to achieve it will be able to fully represent the complex parameters of a downhole.

Drilling Automation

Drilling can involve a great number of people all trying to carry out their individual, complex tasks. Each of these tasks must be carried out safely and correctly, often within a set time frame, for the rest of the operation to run smoothly.

Being able to access real-time information detailing all the operations is a valuable tool. Applying machine learning in oil & gas extraction in this way makes the industry safer and more efficient.

Today modern rigs are equipped with a number of sensors. These can measure all the relevant parameters connected with vessel and drilling operations. The sensors are also able to monitor the actual hole as drilling takes place.

Coupled with machine learning in oil & gas applications engineers are able to make advanced interpretations of computer-based video information. This can be done quickly and efficiently, meaning that little time is lost.

Increasingly operators, such as Anadarko, are using machine learning in oil & gas exploration to operate in deepwater areas such as the Gulf of Mexico.

Solving Problems Quickly with Machine Learning Applications

Applying machine learning in oil & gas operations allows for complex problems to be solved quickly and efficiently. In particular, machine learning algorithms can be used for case-based reasoning (CBR).

This means that the algorithms can be used to quickly sort through massive databases of recorded problems. The algorithms are then able to identify similar cases.

Once a similar case, or cases, is identified the software identifies how the issue has previously been solved. This can speed up problem resolution times, saving money and improving efficiency.

Predictive Maintenance

Another positive implication of machine learning in oil & gas is in the field of predictive maintenance. At every stage from exploration to delivery, the oil & gas industry relies on a number of large, expensive machines. If these aren’t working and well maintained then delays can occur and money will be lost.

By using predictive maintenance machine learning in oil & gas will keep the machines working and delivering.

This uses machine learning in oil & gas to create automated analytical models. This, otherwise known as predictive maintenance, will keep industrial equipment working. The machine learning algorithms used in Predix can process data from equipment sensors.

It will then analyse all the relevant information.

As well as performance levels this includes other factors such as weather and environmental conditions. This information is then compared against ideal performance data already stored in the database.

Should a discrepancy be noted the technicians are alerted. The machine can then be restored to its maximum before a fatal break down occurs.

Predictive Maintenance Models can Improve Productivity

GE Digital’s predictive maintenance models have already been adopted by the Administracion Nacional de Combustibles, Alcohol y Portland (ANCAP) of Uruguay.

A state company ANCAP is responsible for providing the fuel to heat the nations homes and businesses. Additionally, it is responsible for everything from ovens to agricultural machines and transportation.

Predix has enabled ANCAP to manage large amounts of data quickly and accurately. Creating an efficient system and a stable company. By centralizing the system ANCAP can track field data such as liquid and gas flow rates. It also allows for real-time analysis of tank levels and volumes.

This enables the company to monitor not only the effectiveness of their equipment. They can also monitor other important factors such as daily throughputs from process units.

They can also analyse, and then predict how weather conditions will affect their business and demand levels. Thanks to the implementation of machine learning in oil & gas this can all be done automatically.

When processed the software can then format the data into spreadsheets and upload it to the relevant websites.

Machine Learning in oil & gas can be used to Improve Efficiency

The value of being able to quickly collate and interpret this information can’t be underestimated. For example, ANCAP is now able to not only calculate but also project the efficiency of their furnaces.

This allows for trends to be easily spotted and for more accurate predictions to be made. It also allows for an accurate assessment of each furnace’s performance. GE Digital has announced that by implementing Predix, ANCAP has cut the time its employees spend on routine processes by 60%.

The company has also managed to cut fuel usage by 20%. Predix is a potentially powerful tool. By implementing this and similar applications of machine learning, in Gas & Oil significant savings may be made.

Not only in terms of data analysis time but also by helping to increase efficiency and cut waste. It is estimated that predictive maintenance may increase asset uptime by up to five percent.

This, in the competitive oil and gas industry, can give a company a real edge.

Internet of Things

Falling prices in recent years have squeezed cash flows.

This has forced companies to reconsider exploration and production strategies. By using machine learning in oil & gas industries we may be able to better respond to fluctuations in cost and demand.

This is one of the ways that machine learning in oil & gas will transform business models and processes.

Meaning that oil & gas companies will be able to compete effectively in the digital age. The internet of things, sensor data and applications associated with machine learning in oil & gas allow for information to be accessed across multiple touchpoints.

Benjamin Beberness, vice president and global head of the Oil and Gas Industry Business Unit at SAP, highlighted the importance of machine learning in the oil & gas industry.

Speaking on the S.M.A.C. Talk Technology Podcast, Beberness highlighted the importance of employees being able to access the information they need at their fingertips.

Beberness said, “Companies don’t want their employees to have to be going back and forth between the office and the field.”

What happens When Data is Available?

It is not just that the data must be accessible.

It must also be used correctly. In this area, artificial intelligence and machine learning in oil & gas can make a significant impact. When oil prices rise many companies adopt a “production at all costs approach”.

Using AI tools and machine learning in oil & gas areas allows companies to move away from this established business model. By doing so companies can maximise all their assets, reducing waste and needless expenditure.

For example, remote sensors can be connected to wireless networks. This allows for remote data collection. Once collected the data can be centrally analyzed before being processed into forecasting models.

Applications of Machine Learning in oil & gas can Transform Business Models

Implementing AI and machine learning in oil & gas allow companies to predict profits, and losses precisely. This will allow for production costs to be optimized, accounting for a number of ever-changing factors.

The information gained from data visualisation could be combined with current market demand and financial reports.

This allows companies to plan their next drilling operation. Using AI and machine learning in oil & gas in this way will allow companies to shift business models. The traditional “produce at all costs” model will be replaced by a “produce in context” model.

This shift, Beberness thinks, will allow companies to be more flexible and able to deal with low oil prices.

When implemented in this way AI algorithms and machine learning in oil & gas will help companies navigate market ebbs, such as a consumer shift towards electric cars.

Predictions by McKinsey suggests that adopting AI and machine learning in oil & gas supply chains could gain $50 billion in savings, increasing profits.

Many Companies are Already Seeking to Implement Machine Learning

HortonWorks, based in San Francisco, offers similar applications of AI and machine learning in oil & gas industries. Their Hybrid Data Platform (HDP) software is an open-source application.

It is able to process large datasets from multiple sources. Thus helping companies to predict well yield and know when to do maintenance on equipment.

The HDP, like similar applications, can store sensor and seismic data as well as weather data, drilling information and geolocation reports. Additionally, it can also store text files, videos, emails, social media pages in a large data repository.

The implication for this application of machine learning in oil & gas is great. It will allow engineers to use collected data to set benchmarks to achieve a high margin yield. Should the system notice that the current yields are not meeting the benchmark it will warn engineers, highlighting the causes.

This allows for problems to be solved quickly and yields to be optimized. Noble Energy has worked with Horton to predict and prevent downtime in its hydrocarbon infrastructure. In future Noble Energy also aims to use Hortons HDP to improve safety across its sites.

In addition to Noble Energy, HortonWorks has worked with a number of major companies and organisations.

These include John Hopkins University, Mayo Clinic, Expedia, Fuso and Nissan.

Predictive Software For Energy Purchases Customer Market

Enterprise Miner is the name of a predictive software program developed by SAS. The company hopes that it can use machine learning in oil & gas operations to develop predictive models.

This is can be done by employing deep learning, natural language processing (NLP) and computer vision. SAS uses NLP algorithms to extract business insight and emerging trends from speech, sound and text.

It also aims to use computer vision algorithms to determine the objects shown in videos and images. This information can then be processed and analyzed by deep learning algorithms.

These identify patterns that can be used to make predictions and preventative recommendations. SAS haven’t confined themselves to AI and machine learning in oil & gas industries.

They have also helped Old Dominion Electric Cooperative (ODEC) to forecast energy demand. ODEC provides power to 11 distribution cooperatives in Virginia, Delaware and Maryland, serving over 1 million customers. Linking up with SAS has allowed the company to purchase and provide energy at an affordable price.

SAS has provided ODEC with industry-specific models. This has allowed for accurate forecast modelling and predictions. Case studies suggest that this partnership has helped to save the utility companies customers millions.

This allows ODEC to plan, with confidence, its markets power need up to 20 years into the future.

Replacing Manual Workers

Machine learning in oil & gas will not replace manual operatives entirely.

While it will account for some streamlining, human operatives will still be required. Using machine learning in oil & gas industries will allow skilled workers to become more efficient. It can also save them from conducting needless tasks.

Finally adopting more applications centred on machine learning in oil & gas can make the industry safer. Geoscientists will still need to have strong core geoscience skills, this aspect will never change.

However as machine learning in oil & gas becomes more widespread geoscientists will also need other skills. They will have to embrace the next generation of machine learning in oil & gas based toolsets.

The geoscientists who do this will be able to thrive in the industry of tomorrow. They will be equipped with a hybrid skillset, combining geoscience with mathematical fluency, coding ability and creative problem-solving.

There will also be a need to communicate across domains, allowing information to be accessed and understood by a wide audience.

A new Skill set for Workers

All of this may alienate, or seem scary to the current workforce. However, it is necessary and workers will soon become adept at these skills.Workers who can properly deliver all these skills will become commonplace.

They will also be best served by machine learning algorithms that are fed by standardised, quality data. This will yield the best possible results. Data companies such as TGS are aiming to provide both.

Tasks such as collecting and maintaining data will fall increasingly on AI and machine learning, in oil & gas as well as other industries. While this will allow for a standardised information base to be created it won’t completely negate the need for human workers.

Geoscientists and engineers will still be required to interpret and vet the information. Data scientists will also be required, helping the experts within the industry to continue developing algorithms. As these algorithms become increasingly complex there will also be a need for data scientists to help understand the systems.

Machine Learning to Predict Operational Outcomes

One company hoping to implement machine learning in oil & gas is Maana. Based in California, the company has developed a software called Knowledge Platform.

This, they hope, will help oil and gas companies to predict operational outcomes. Machine learning and natural language processing will also help employees to make informed decisions.

Maana claims that its software can quickly process unstructured data. This is data such as weather reports, call center records, job reports and everything else. The Knowledge platform algorithms can then interpret this data, searching through the platform’s database looking for similar patterns.

This information is presented in the form of graphs, illustrating trends in performance or expenditure. Experts on the subject matter can then interpret the graphs quickly and easily. This can speed up problem-solving by quickly highlighting potential solutions.

Smart Tools can also Optimize Performance and Output

In addition to language-based data Knowledge platforms can also be used to collect detailed sensor data during pumping operations.

This is then analyzed identifying patterns that could lead to pump failures. If this pattern is highlighted before the pump fails it can save time and money.

It will also prevent hours being lost to broken machinery.

This can optimize drilling performance.

Maana’s software, as well as similar applications in machine learning in oil & gas, can also affect savings across the industry. The application can also increase billable hours, reduce overall costs and streamline operations. Maersk, Airbus, Chevron and Shell are all clients of Maana as is General Electric.

Machine learning in oil and gas operations, according to McKinsey are yet to be fully maximised. The 2017 McKinsey report suggests that the average offshore platform operates at about 77% of its maximum production potential. When this is spread across the industry it equates to a daily loss of 10 million barrels.

That is about $200 billion in annual revenue.

As time progresses our world is increasingly influenced by the abilities of AI and Machine learning. In oil & gas operations adoption and realisation have been slow. However slowly AI and machine learning in oil & gas are taking hold.

Machine Learning in Oil & Gas Applications can Transform the Industry

Machine learning in oil & gas will not only improve the customer experience but can also help to keep costs low across the process.

The possible advantages that can be brought by machine learning in oil & gas to this competitive sector are massive.

Images: Flickr Unsplash Pixabay Wiki & Others

This blogpost is originally from Aquantico | Challenge, innovate & deliver value

Oil & Gas Engineering | BY MICHAEL FRY

BOP system tester uses analytics software to help its oil & gas clients avoid downtime and incident

In April 2010, the malfunction of a blowout preventer (BOP) contributed to the Deepwater Horizon disaster in the Gulf of Mexico, leading to the loss of life of 11 crew members and one of the worst oil spills in U.S. history. Since then, a movie was made about the incident, with an unsurprisingly Hollywood take. In addition, there has been a not-so-surprising emphasis on comprehensive BOP monitoring throughout the oil & gas industry.

BOPs are assemblies of valves, hydraulics, and electrical devices used to seal, control, and monitor wells to prevent the uncontrolled release of oil or gas (See figure 1). They are deployed on both land and ocean drilling rigs, and they are secured to the wellhead at the top of the wellbore.

To comply with regulations instituted in 2019, BOP system testing must be handled by third-party companies, such as Deepwater Subsea, headquartered in Katy, Texas. Deepwater Subsea provides these services to its clients by streaming data from BOP systems located anywhere in the world to their monitoring center for analysis and reporting.

In addition to BOP testing, Deepwater Subsea provides subsea operational support and training with their team of subject matter experts (SMEs), all of whom are highly trained specialists, to provide downtime reduction and operational performance improvements.

To provide these services, the SMEs make extensive use of Seeq advanced analytics software to create insights from the streamed data.

Searching for a better solution

Initial Deepwater Subsea projects reinforced the need for an improved solution in an industry where many operators and service companies were set in their own established, and often inefficient, procedures. Like most operators, Deepwater Subsea was using general purpose tools such as Excel to analyze data, making it difficult to predict and troubleshoot problems, and to help its customers meet regulatory requirements.

As part of BOP regulatory compliance, reports must be sent to the Bureau of Safety and Environmental Enforcement, which often requires customized reports going back months or even years. These must be created quickly and efficiently, a task not well suited to spreadsheets.

Achieving operational excellence for operators requires analyzing rig data, producing compliance reports, generating failure reports, and conducting regular inspections. The information generated by these activities provides operators with historical lessons, key performance indicators, operational logs, and inspection reports — which they use to improve their operations and comply with regulations.

Delivery of these services is complicated by geography, as most BOPs are installed thousands of feet below water or land surface. Another issue is the sheer volume of data, with up to forty thousand data tags coming into the Deepwater Subsea monitoring center daily, streaming in real-time 24/7/365.

This data must be quickly and accurately analyzed, with any problems immediately brought to the attention of the operator. The main goal is preventing failure of a BOP system, but an important secondary goal is keeping a system in operation, if a problem is found that does not jeopardize BOP operation.

To attain the required level of certainty, Deepwater Subsea switched from spreadsheets to Seeq for interacting with the data of interest, creating insights and producing customized reports.

Deployment details

Deepwater Subsea uses the OSIsoft PI data historian to collect and store time-series data from its clients’ wells and BOP systems. This data is primarily pressure measurements from the hydraulic system that controls different aspects of BOP operation, and the method of communication from a rig to the monitoring center is typically via a VSAT satellite communication system.

In addition to real-time data streamed from wells regarding BOP system operation, the historian also contains BOP asset information such as make, model, serial number, date of manufacture, date of installation, date of last maintenance, historical failure and leak data, and the like.

A Seeq system reliability engineer initially worked with Deepwater Subsea SMEs to install the software, which took less than two hours. Upon installation, Seeq automatically detected, connected to, and indexed the PI system data. When new data sets need to be analyzed, the data extraction process is quick and easy, in contrast to spreadsheets where data must be manually copied from the historian and pasted into the spreadsheet.

Multiple PI systems can be connected to provide data comparison across different sites. Tight integration between Seeq and OSIsoft PI’s asset framework is used for analytics and asset-relative displays. Seeq also offers integration with Event Frames and PI Notifications to enable the reuse of existing investments in software and analytical configurations.

The combination of Seeq and OSIsoft PI also provides integration with other tools such as Microsoft Excel and Power BI for pivot tables, graphing, and business analysis.

Deepwater Subsea runs Seeq as a SaaS application on Microsoft’s Azure cloud service platform. Cloud-hosting provides several advantages as compared to an on-premises installation. Local server hardware and support is not required; scalability is quick, easy, and nearly infinite; and security, backups and other features are provided by the cloud-hosting company. Offloading these activities allows Deepwater Subsea to focus on its core mission.

Focus on the BOP

Using the software’s unique analytics capabilities, SMEs at the monitoring center apply their domain expertise to help detect BOP system anomalies. SMEs can now accurately quantify changes in BOP control system performance, pressure leaks and more, and quickly share this information with rig personnel.

Data tags can be pulled in, captured and overlaid on historical data to analyze asset performance, such as the results of pressure tests (Figure 3). The data in the historian is not disturbed by these activities, and full fidelity PI data is cached and always ready for quick acces

The ability to overlay the previous test results for comparison allows Deepwater Subsea monitoring personnel to ensure that the mechanical integrity of the equipment has not changed.

BOP systems can have over one hundred functions associated with a single hydraulic circuit, and pinpointing a problem, often due to a leaking component, is extremely challenging. Using Seeq, SMEs can look at a signal (for example, a manifold regulator pressure trend), and compare it to other signals over any desired time. These signals can be overlaid on top of each other, allowing quick identification of which component is leaking or causing some other type of problem.

An example result would be an upper outer choke in a BOP system that leaks when a valve is closed. Further analysis can reveal whether this is a problem which must be addressed immediately, or if repair can safely be deferred to allow proactive instead of reactive maintenance. Each of these items could have resulted in a non-productive time event, resulting in millions in lost revenue.

Increasing uptime

Deepwater Subsea’s monitoring services have resulted in significant improvements for its oil & gas operator clients. Some of the operators seeking approvals from the Bureau of Safety and Environmental Enforcement (BSEE) have been able to extend BOP testing intervals from 14 to 21 days, saving them approximately $10 million annually per rig. These testing interval extensions not only decrease downtime, they also provide an opportunity for more detailed analyses during which problems can be pinpointed. This helps speed maintenance and repairs by ensuring the right parts and personnel are on hand to perform the required work.

Figure 5: Analyzing a BOP system leak with Seeq allowed regulatory approval for continued safe operation. Courtesy: Deepwater Subsea

They submitted a report to the BSEE showing the leak would not impact BOP performance, and approval of this report allowed the operator to keep the BOP system in operation. The subsequent return on investment associated with a week of avoiding non-productive time for pulling and servicing the BOP was approximately $2.5 million.

Final words

Following this initial success, Deepwater Subsea has recently expanded its deployment to include Seeq Data Lab, which provides an environment optimized for developing, training and deploying machine language models and enhanced visualizations.

Further expansion of services is planned to analyze data from many other aspects of rig operation. Seeq has enabled Deepwater Subsea to partner with many clients to deliver improved operation, comprehensive reporting, minimized downtime, superior worker safety and better environmental protection.

This blogpost is originally from Aquantico | Challenge, innovate & deliver value

Forbes | By Bernard Marr

What does it take to become a more data-driven business? This is a question that every organization, not just tech companies, needs to grapple with, or they will falter in the future. One of my customers is Shell – a company that is doing a great job of becoming more data-driven. One of the driving forces to make the company more data-driven is Dan Jeavons, Data Science Manager at the global energy and petrochemical company. With this article (and related videos), I want to share the learning experiences they had as they prioritized data-driven operations.

Why Must Organizations Become Data-Driven?

Does growing 30 percent annually sound appealing? According to Forrester, that’s what data-driven organizations can expect to achieve in addition to being profitable and acquiring and retaining new customers. Most organizations realize data should be central to decision-making; however, leaping from knowing to doing isn’t as straightforward.

Think Strategically about Data

The starting point for any data strategy must be to examine your business challenges—what’s your business strategy, overall business goals, your biggest challenges, and unanswered questions.

Before jumping into investing in data infrastructure and data-driven decisions, take a step back and determine how data can become relevant to the strategy of the business, this will help you to determine what data you need.

At Shell, Jeavons explained the value of a two-speed approach. “It’s very easy to think about culture and standards and technologies and try to get that all right, but at the same time, we have to make it matter to the business. What we try to do is to think about minimal viable products that are going to have a significant business impact immediately and use that to inform the KPIs that really matter to the business. Then, line up to that, which data really matters and how to invest in data quality, data standards, and technology to support doing this at scale.”

It’s important to review the data you have access to and determine how you will acquire data diversity, and what new sets of data must be acquired to solve your particular business challenges.

Learn from Tech Companies

Shell, and the entire oil and gas industry, has been incredibly data-intensive for a very long time. However, with the cloud, digitalization, and new technologies emerging, the value and importance of data have gone up.

Jeavons shared, “What we’ve been trying to think through is how do we use data enterprise-wide. We recognize that some of the skills that cloud-based technology companies have developed and the way in which they think of data are quite different than the way we’ve thought about it historically, so we want to learn from them.”

Jeavons encourages organizations to leverage the best practices and learn from what’s going on in the market to bring expertise to your organization.

Data technology and discipline

Once you have determined data sources and know where to get the data you need, you must look at the technology and some of the tools to help determine where to store the data, how to analyze it, and turn it into insights. Technology is another key enabler to becoming a more data-driven business.

Jeavons explained how Shell is disciplined about the data the company collects and stores, and they “learned that when you start down this road, it’s very easy to get tempted to go after lots of data and then look for a problem. Our experience is that if you put all the data in one place, it’s harder to sift through.”

Shell built a phenomenal data set—likely the largest curated set of data on the planet Jevon asserts. “At the same time, we’re focused on not pulling all sets of data, but only sets of data that will drive business,” he said.

Data is an asset but also a potential liability. It’s important for organizations to only aggregate and integrate the data that is known to be of value, and that can be controlled. Your organization needs to be clear on why you’re collecting data and the benefit you will drive from it. How can you envision that data being used in the future? How are you going to control access to that data in such a way that you deal with it in a secure, reliable, and well-managed fashion? When someone gains access to that data, how will they know what they’re looking at?

Skills and Organizational Culture

It’s important to make sure that people in your organization have the skills to use the data and the ability to access the data, know how to use it, and gain insights. The organizational culture needs to support fact-based, data-driven decision-making, and make sure it’s encouraged and the norm.

At Shell, Jeavons explained, they invested in professionalizing the core work of data scientists and others who would spend all their time working on the most complex problems the company had. They developed tailored training programs and aligned these roles with other disciplines in the company and made data science as important as petrophysics, as an example.

Then, for the citizen data scientists—people who are in the business who need to use the data to solve their own problems—Shell had to make sure they understood how to access the data, develop their own algorithms and work with the data.

Another group, called the Shell AI community, that numbers roughly 2,000 people, is learning about what it means to use data in new ways to drive their own business performance. This is an area where there is a lot of excitement and real traction. People are starting to adopt this at scale and learning how to better use data in their areas of expertise. Shell schedules hackathons between data specialists and this AI community where they collaborate to develop small-scale rapid solutions in a very, very short timescale.

Finally, another essential role in the data-driven business culture of Shell spans the business and data communities. These business translators can speak the language of business as well as data technology. These roles are absolutely crucial. Shell invested heavily in training these people and worked with them to define ways in which the company can translate what they need in terms of a business outcome perspective into a valuable piece of work data scientists can do. These are essential personnel, and they tend to self-identify from the business world and have a key interest in using technology and applying it to solve business issues.

Data Governance

The last component of becoming a data-driven business regards data governance. Every organization needs to make sure the data that’s collected is treated and stored securely, the right legal framework is established, and it is known who has access to the data and who can use it.

 ———

For more on AI and technology trends, see Bernard Marr’s book Artificial Intelligence in Practice: How 50 Companies Used AI and Machine Learning To Solve Problems and his forthcoming book Tech Trends in Practice: The 25 Technologies That Are Driving The 4^Th Industrial Revolution, which is available to pre-order now.

This blogpost is originally from Aquantico | Challenge, innovate & deliver value

White Space Energy | BY Norbert Dolle

Introduction

Well trajectory planning is a high-stake and complex multi-disciplinary work activity for Oil & Gas operators. The work involves experts from geoscience, reservoir engineering, drilling, completions and facilities. Each are using specialist software to evaluate and define reservoir targets, subsurface hazards and engineering constraints. “Likes” and “dislikes” of trajectory options are expressed in different terms by the various disciplines. This often leads to an iterative and time-consuming process, influenced by human bias. Time quickly becomes a limiting factor, with a business risk of unrealized value due to incomplete understanding of the full option space and associated uncertainties, risks and rewards.

To mitigate the above challenges, we have developed a collaborative game-based approach to well trajectory planning supported by Artificial Intelligence (AI). This approach has been tested using Equinor’s open source Volve dataset, which demonstrates the potential to significantly reduce cycle time and improve decision quality.

Our Game Approach

Oil & Gas companies generate value through the quality of their decisions. Often, these decisions are very complex. There are millions of choices, conflicting business drivers, lots of uncertainty, hidden bias, and so forth. These complexities all add up, which makes good decision making very hard – for humans.

In contrast to humans, Game AI is designed to handle such complexities. These latest AI algorithms mimic human ability to learn from experience and have become famous for achieving super-human performance in sophisticated and complex games such as Chess, Go, StarCraft and Poker.

In this paper we describe our game approach to well trajectory planning, and demonstrate how AI can be used to support humans in making faster and better decisions.

The approach will be described using the following three steps:

1. Building the game
2. Playing the game
3. Analysing strategies

Step 1 – Building the game

When seen through a gamification lens, well trajectory planning is very similar to a video game such as PacMan. Players can “collect” rewards in the game, such as remaining oil or gas. There are also items to avoid, such as drilling hazards. And there are movement rules, things like maximum dog leg severity, total well length and trajectory tortuosity. In the next sections we will describe how these rewards, obstacles and movement rules are built into a case-specific game environment.

Rewards, obstacles and movement rules are available as existing static, dynamic and engineering models, interpretations and opinions. The key differentiator of the game approach (in contrast to the current siloed ways of working) is that contributions from all disciplines are incorporated in a single (game) environment, whichsignificantly improves integration and strengthens collaboration.

For this project we used Equinor’s open-source Volve dataset as basis. To make the case more interesting as a demonstrator of our Game AI approach, we have assumed that a secondary gas cap has been created in the first phases of the field development. The remaining oil is consequently a thin oil rim of about 30 meters thickness. Furthermore, we have assumed that gas cap and aquifer strenghts are such that the highest recovery efficiency is associated with offtake from the middle of the rim, and therefore the ideal placement of (horizontal) wells is exactly in between the Gas Oil Contact (GOC) and the Oil Water Contact (OWC). The resulting positive reward system, i.e. the “points” that can be scored in the game, is schematically shown in Figure 1 as a multiplication of net pore volume, mobile oil saturation and recovery efficiency.

For the purpose of the actual demonstrator, this reward system was further expanded with recoverable oil per length of reservoir penetration (barrels per m) and a proxy value per barrel ($/bbl) to reflect economics.

While the oil represents the positive reward in this well trajectory planning game, there are also negative rewards or penalties that can be accumulated. These “obstacles” are shown in Figure 2 and consist of:

• Existing wells. Existing well include a minimum separation distance for anti-collision purposes. Hitting one of these leads to a negative reward of minus infinity, therefore means “game over”.
• Faults. The negative reward is angle-dependent, reflecting that the drilling risks vary by the angle under which the fault plane is penetrated.
• Shallow gas. Drilling through shallow gas can be a significant drilling hazard, in particular when being unprepared for it. The severity of the negative reward can be varied based on the perceived managability of the risk, and to evaluate robustness of the ultimate highest ranking well trajectories.

Drilling and completion cost can equally be included in the reward system, or added as post-processing in the analysis (Step 3).

The movement rules in this game are defined by parameters such as surface location, kick-off depth and maximum dog leg constraints. Other design considerations, such as maximum inclinations and/or allowable azimuths for casing design, can either be brought in as rules or taken into account in the analysis of the strategies.

All the above reward system elements and movement rules are programmed into a custom game environment using Python. This makes the approach extremely flexible, which is one of its key strengths. For example, the game environment in this project is entirely deterministic – but stochasticity (e.g. representing subsurface uncertainty) can be easily built in when that is preferred for decision making.

Step 2 – Playing the game

The game is played by a virtual player, our AI assistant. The aim of this particular demonstrator game was to explore the option space of drillable wells and find the “preferred next well to drill”.

Since we want to give decision makers an understanding of the full option space of valuable and feasible wells, the AI assistant has a simple task: design drillable wells that collect as much reward as possible whilst avoiding or minimising penalties.

Designing drillable well trajectories involves a sequence of decisions, which makes the process very suitable for AI algorithms. Different solver architectures, or algorithms, can be used to play this game. This is similar to how companies such as Google-owned DeepMind develop customized solvers for games such as Go and StarCraft. Each architecture has pros and cons and very often it is the problem definition (i.e. the game objectives) that determines which solver is most effective. For this project, three solver architectures were considered: Reinforcement Learning, Evolutionary Algorithms and Tree Search algorithms (see Figure 3).

We landed on a Tree Search algorithm with an evolutionary layer on top as the most fit-for-purpose architecture in this case, mainly owing to its performance (i.e. speed) and exploration capability (i.e. it looks “wide” in the option space).

The strength and flexiblity of our approach came through in this project by using the same game set up to design, evaluate and compare trajectories for different well types: from new wells at different surface locations, to shallow and deep sidetracks. For the AI, these are simply different starting points and movement rules (e.g. reflecting the range of feasible whipstock settings for sidetracks).

Step 3 – Analysing strategies

It is one thing to have an AI that designs thousands of feasible well trajectories per minute. It is another thing to make this data available for effective analysis and quality decision making. Decision making in Oil & Gas is often a complex task due to competing business drivers (safety, sustainability, cost, value). In the case of well trajectory planning, the preferred choice can depend on many things. From quantifiable parameters such as oil price, cost, budget availability, drilling contractor performance and subsurface uncertainty, to softer items such as risk appetite, experience and gutfeel. The analysis of the game play results should therefore allow all these aspects to be taken into account.

In general terms we use a 2-step approach to facilitate the analysis and decision-making:

1.     Reduce the number of options without risking decision quality. This can be done in various ways. We have previously used clustering techiques for this purpose, i.e. lumping sets of “similar” well trajectories into a single trajectory that is representive for the entire set. Another option, used in the project, is to only consider the trajectories that are on (or near to) the Pareto front (Ref. Jahan et al).

2.     Present the remaining options in a bespoke analysis dashboard. The dashboard visualises the options, allows interactive filtering and quantifies the trade-offs between key decision metrics. The dashboard used for the project described in this paper is presented in Figure 4.

The collaborative aspects of the game come to fruition when the integrated team uses the dashboard to discuss and evaluate options. The interactive overview of considerations and opinions stimulates a healthy cross-disciplinary challenge and helps the team to understand the trade-offs and/or to ask “what if” questions to further improve robustness of the preferred choice(s).

Key Take Aways

This article describes how we have developed a game-based approach to well trajectory design supported by Artificial Intelligence (AI). This approach has been tested using the Volve dataset, which demonstrates the potential to significantly reduce cycle time and improve decision quality.

Based on the Volve dataset we have built a game environment that incorporates subsurface rewards, obstacles and movement rules. Using AI as a virtual player in this environment, our approach leads to a complete overview of the option space, and associated trade-offs across different business drivers, at a fraction of the time that it takes manual workflows to give similar insight. The results from the AI assisted game play are presented in a bespoke analysis dashboard to facilitate decision making.

This game-based approach to Well Trajectory Planning offers a significant opportunity for better and faster decisions in situations where manual workflows are overly time consuming, potentially biased or both. This includes fields with complex geology (e.g. stacked and compartmentalised with multiple drilling hazards), mature assets with congested surface and subsurface infrastructure (where picking well trajectories could be a significant issue due to anti-collision constraints) and field developments where the trade-offs between drilling and surface expenditures pose a challenging optimisation problem.

Acknowledgements

We thank Equinor for supporting this joint effort and the valuable discussions along the way, as well as for making the Volve dataset publicly available

Note: this article is co-authored by Einar Landre & Olav Ragnvald Hansen from Equinor, and Tom Savels & Germonda Reijnen from White Space Energy

This blogpost is originally from Aquantico | Challenge, innovate & deliver value

Emerj  | BY Ayn de Jesus

McKinsey reported that most oil and gas operators have not maximized the production potential of their assets. A typical offshore platform, according to the 2017 report, runs at about 77% of its maximum production potential. Industry-wide, the shortfall comes to about 10 million barrels per day, or $200 billion in annual revenue.

To help optimize production, operators might consider adopting advanced analytics, which combines engineering, data science, and computing power to enable businesses to forecast yields or maximize industry assets.

In adopting analytics, it follows that AI would find its way into the oil and gas industry. As of now, numerous companies claim to assist engineers and data scientists in aspects of their roles, such as predictive maintenance on equipment, predicting supply and demand, and streamlining routine processes.

Predictive analytics emergence

We researched the space to better understand where predictive analytics comes into play in the oil and gas industry and to answer the following questions:

• What types of predictive analytics applications are currently in use in oil and gas?
• What tangible results have predictive analytics driven in oil and gas?
• Are there common trends among these innovation efforts? How could these trends affect the future of oil and gas?

This report covers vendors offering software across two applications:

• Predictive Maintenance
• Business Intelligence

This article intends to provide business leaders in the oil and gas space with an idea of what they can currently expect from AI in this industry. We hope that this article allows business leaders in the oil and gas industry to garner insights they can confidently relay to their executive teams so they can make informed decisions when thinking about AI adoption. At the very least, this article intends to reduce the time business leaders spend researching AI companies with whom they may (or may not) be interested in working.

Predictive Maintenance

GE Digital’s Predix

GE Digital, a subsidiary of General Electric, offers Predix, which the company claims can help oil and gas businesses create automated analytics models that could help in the predictive maintenance of its industrial equipment using machine learning.

Predix explains that the application’s machine learning algorithms are able to process data that sensors collect, such as equipment or parts performance, environmental data, and weather conditions, among others. The algorithms then compare these against the ideal performance data contained in the database. If the algorithms find discrepancies between the current and ideal state, the application is triggered to send an alert to technicians. who in turn conduct predictive maintenance or part replacement.

For instance, in a wind farm, one turbine is performing below optimum levels. The technician gathers the data collected by sensors about the parts of the turbine, such as the wind blades and turbine axle. The technician might also consider reviewing the wind speed. The turbine’s performance history will then be compared with that of other turbines at the wind farm.

The in-house technician may share the information with the field technician through a connected tablet or smartphone, who is prompted to inspect the underperforming turbine in person. Repairs are then conducted if needed.

Below is a short 3-minute video demonstrating how Predix works:https://www.youtube.com/embed/6mb0gnBUmNk

GE Digital claims to have helped the Administracion Nacional de Combustibles, Alcohol y Portland (ANCAP) of Uruguay. The state-owned company provides the fuel that heats homes and business and fuels cooking equipment, agricultural machines, and transportation. The company was faced with the challenge of managing large amounts of data and needed a solution to make processes more efficient, optimize energy consumption, integrate operational data from various sources, and ensure the sustainability of the company.

The company turned to Predix’s human-machine interface and supervisory control and data acquisition (HMI-SCADA) application called iFIX. The project was implemented in five distribution plants, with more than 1,000 screens deployed. Employees at each location learned to use the system to input critical data.

With the centralized system, ANCAP was reportedly able to track field data, such as gas and liquid flow rates, composition analyzers, and tank levels and volumes. The system also enabled the company to monitor the performance rates of equipment, daily throughputs from process units, and weather conditions. This data was automatically processed, formatted to a spreadsheet, and uploaded to the government’s website.

With this data, ANCAP was able to calculate and project the efficiency of its furnaces using this data. although the case study did not explain how efficiency was defined. The data was recorded in the server to enable the team to study trends related to the furnace’s performance.

According to GE Digital, implementing Predix allowed ANCAP to cut the time spent on routine processes by 60% and save 20% more fuel. Management also reportedly stopped asking employees for manual reports

GE Digital also lists Exelon, Gerdau, Spomlek, Lek Pharmaceuticals, and the City of San Luis Obispo as some of its clients.

Vincent Yates is the Chief Data Scientist at GE Digital. He holds a PhD in Statistics from the University of California, Berkeley. Previously, Yates served as Head of Data Science in Seattle at Uber, Director of Analytics Engineering at Zillow Group, and Office Analytics Team Manager at Microsoft.

Maana

Maana is a California-based company with over 100 employees. The company offers a software called the Knowledge Platform, which they claim can help oil and gas companies predict operational outcomes and help employees make better-informed decisions using machine learning and natural language processing.

Maana claims its software can mine, process, and analyze a company’s unstructured data, such as job reports, maintenance records, equipment sensors, weather data, call center records, and other types of media from disparate company sources. Then, Knowledge Platform’s natural language processing algorithms interpret the data from these reports. The machine learning algorithms crawl through the platform’s database to find patterns that are similar to the current problem the company is aiming to solve.

When the algorithms find similarities, the system then provides feedback in the form of graphs to show the trend of, for instance, equipment performance or expenditures. This allows the company’s subject matter experts to interpret the graphs and make recommendations on how to solve the problem.

Below is a short 2-minute video demonstrating how the Knowledge Platform works:https://www.youtube.com/embed/vRbogYIsluI

Maana claims to have helped an unnamed Fortune 20 oil company make optimal pump selections, increase billable hours and reduce overall costs using the application. The company’s maintenance experts used the platform to collect data related to existing pump operations. The data came in the form of run-and-pull reports, pump failure reports, pump sensor data and high-frequency data flows. Much of the data described past inspections of failed pumps retrieved from wells and was reported by field employees.

Aside from language-based data, the company also collected detailed sensor data during pump operations. The application was able to classify the data and recognize the patterns that could lead to pump failure.

According to Maana, this enabled employees to validate their hypotheses and identify the causes of pump failures, predict similar scenarios in the future, and choose the right pump for each kind of well. Overall, this allowed the company to conduct maintenance that would reduce the risk of pump failures and production downtime.

Maana also lists Shell, General Electric, Airbus, Maersk, Chevron as some of their clients.

Steven Gustafson is Chief Scientist at Maana. He holds a PhD in Computer Science from the University of Nottingham. Previously, Gustafson served as R&D Leader, Knowledge Discovery Lab at General Electric Global Research.

Business Intelligence

HortonWorks

HortonWorks is a San Francisco-based company with about 1,300 employees. The company offers a software called Hybrid Data Platform (HDP), an open-source application that processes large datasets from multiple sources, which they claim can help oil and gas companies predict well yield do maintenance on equipment.

Hortonworks claims that HDP can store and process its structured and unstructured data, such as sensor or seismic data, weather, drilling and completions data, geolocation, text files, video, social media, email, and more. These are stored in a data repository.

For instance, an oil and gas company may want to set standards of yield per well to achieve the highest margins. To set the benchmarks, the engineers might use seismic data, pump rates, fluid temperatures, and other factors that influence yield.

The software’s machine learning model would then take these predefined benchmarks, search the HDP database for similar standards, and compare the corresponding well yields. If the algorithms find that the current yields are lower, based on the influencing factors, the system informs the users through the dashboard.

Below is a short 2-minute video demonstrating how HDP works:https://www.youtube.com/embed/3Y0eLP3ZizM

Horton claims to have helped Noble Energy predict and prevent downtime in its hydrocarbon infrastructure. The case study reports that HDP was used to look for potential lost opportunity through downtime, but did not provide details. However, we can infer that the application’s machine learning model reviewed the data from sensor streams, drilling reports, location data, engineering notes, and technical manuals, etc.  

Then, the algorithms may have matched these with historical data related to factors that could affect production, such as equipment failure and decline in the output of existing oil wells, among others. This would have enabled Noble Energy to take measures to maintain equipment and possibly discover new wells.

In the future, Noble Energy intends to use HDP to improve safety and prevent injuries among employees in its locations.

Hortonworks also lists Fuso, Johns Hopkins University, Nissan, Yahoo! Japan, Mayo Clinic, SoftBank, Expedia, and Symantec as some of its clients.

Scott Gnau is CTO at Hortonworks. He holds a BS in Electrical Engineering from Drexel University. Previously, Gnau served as President of at Teradata labs for nine years, where he provided direction for research, development, and sales support activities related to Teradata integrated data warehousing and big data analytics.

SAS

SAS offers a predictive software called Enterprise Miner, which they claim can help oil and gas businesses streamline the data mining process to develop predictive models using deep learning, computer vision, and natural language processing (NLP).

SAS claims that NLP algorithms are capable of extracting business insights and emerging trends from texts, speech and sound, while computer vision algorithms determine the objects inside images and videos. The information extracted by these technologies are then processed and analyzed by deep learning algorithms, which recognize patterns in the data to create predictions and preventive recommendations.

Below is a short 3-minute video demonstrating how SAS artificial intelligence-driven applications work: https://www.youtube.com/embed/4qKtQD5133k

SAS does not have oil and gas-related case studies but claims to have helped Old Dominion Electric Cooperative (ODEC) forecast energy demand and save its utility customers millions in its first year of using SAS Analytics, according to the case study.

ODEC provides wholesale power to 11 distribution cooperatives in Virginia, Maryland, and Delaware that serve 1 million member customers. For energy purchases, the cooperative must contract energy months in advance to ensure affordable supply at wholesale prices. Wrong forecasts might force ODEC to buy energy at higher spot prices

In the past, ODEC used traditional spreadsheets to create forecasts. SAS enabled ODEC to forecast more accurately using a variety of industry-specific models that support system analysis, hedging, financial forecasts, and future resources for energy and demand.

According to the case study, using SAS allowed ODEC to understand each cooperative’s market while providing a big-picture look. This enabled the client to plan for its markets’ power needs five, 10, or 20 years into the future. The company did not provide further details or specific numbers.

SAS also lists Honda, Bank of America, Nestle, Lufthansa, Konica Minolta, and World Wildlife Fund as some of its past clients.

Wayne Thompson is Chief Data Scientist at SAS where he has served for 26 years. He holds a PhD in Agronomy and Statistics and another in Plant Sciences; Minor Statistics. Both are from the University of Tennessee.

Takeaways for Business Leaders in the Oil and Gas industry

Most of the companies covered in this report offer solutions for preventive maintenance and production-related analytics. Worthy of note is that all of the companies’ AI efforts are spearheaded by PhD-level talent except Hortonworks.

That said, only Maana offers solutions exclusively for industrial production and oil and gas companies; the other companies covered in this report service multiple industries. Maana’s specificity could work in its favor, as its machine learning models might be trained exclusively on industrial databases, which could increase its models’ accuracies. This is speculation, however. 

Although no company provided hard times on how long their software would take to integrate, based on one case study, we infer that the integration product could be long.

Overall, predictive analytics applications for the oil and gas industry seem to legitimately involve AI, unlike other sectors that are more nascent in terms of AI.

This blogpost is originally from Aquantico | Challenge, innovate & deliver value