Far from the Microsofts and Googles of the world, a century-old industry – oil and gas – is hoping that generative artificial intelligence will make petroleum production more efficient and easier on its workforce.
Long before the current craze around generative AI (Gen AI), the energy sector was using traditional artificial intelligence through the use of data to identify oil and gas reserves.
But the industry sees greater potential to save money, reduce accidents and lower greenhouse gases through Gen AI, which exponentially increases and diversifies the data that can be analyzed.
Unlike traditional AI, which has been restricted to programmers and data analysts, the new AI systems can also be broadly utilized in the workforce.
According to Tim Hafke, a content marketing specialist at AlphaSense, “extracting this data from the vast amounts of data generated by drilling activity has historically been a major challenge for industry leaders.” “Gen AI steps in at this point.”
Refineries that turn crude oil into gasoline are among the downstream industries that have relied more and more in recent years on “digital twins,” which are computer-modeled duplicates of real facilities.
They enable businesses to conduct simulations in order to identify potential risks, evaluate operational problems at actual facilities, and carry out predictive maintenance (PdM).
During a panel discussion at the CERAWeek energy conference, Microsoft vice president Matthew Kerner described this as an introduction to generative AI and a means “to explain why the predictive model made the prediction it did” and provide context to better address the problem.
Rob McGreevy of Aveva, an industrial software business, stated during the panel that people in the field could benefit from next-generation chatbots like the well-known ChatGPT.
According to McGreevy, a data-driven chatbot might enable troubleshooting personnel in the oilfield or refinery to assess operational parameters like wellhead pressure and ambient factors like humidity in order to identify issues rapidly.
Quick fixes are possible with a thorough report that can be obtained in a matter of seconds, saving both time and money.
‘Less risk’
During refinery maintenance, “you’re putting people in harm’s way to do the work. If you can do those repairs faster, you’re going to have less risk,” said Matthew Babin, head of energy and natural resources at software company Palantir Technologies.
The Gen AI interface provides “access to maintenance manuals, so you can see how the maintenance on that device should be done,” all in plain English, thanks to a chatbot, McGreevy said.
Such a system could also facilitate the repair work itself, taking the guesswork out of decision-making.
According to McGreevey, the technology would enable a business to utilize a computer model of a facility, for instance, to ascertain whether there is enough space to erect scaffolding or use a ladder.
Another benefit, according to McGreevy, might be for incoming hires: “I think we can shorten dramatically the time it takes for people coming on board to be proficient to safely operate these facilities at scale.”
An oil facility’s carbon footprint can be decreased thanks to increased efficiencies brought about by Gen AI. However, massive amounts of electricity are also needed to run the equipment, mostly in data centers.
