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
“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.”
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.
“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.