Making Legacy Engineering Data Sweat

A pioneering application of artificial intelligence at Woodside Energy is finally ready for wider deployment in oil and gas.    I learned about this use case back in 2016, at APPEA’s annual conference in Perth, where Woodside’s data science team presented their work. Surprisingly, few companies bothered to replicate this innovation, even though it was both proven and easy to execute. Many oil and gas facilities have been in production for decades, and want to be in production for decades more. Not only do these assets handily outlast their designers, but they’re now outlasting their maintenance engineering staff, operations, logistics managers, and key suppliers. In short, the complete original workforce. But the oil and gas industry has long relied on the memory of its people to recall critical information about its assets, information beyond the kinds of data easily found in modern systems. Answers to questions like “why did we design it this way”, and “have we encountered this problem before” depend on the memories of workers. Oil and gas companies cannot reliably use ChatGPT, as it was trained on the whole of the internet, and is a mix of fact and fiction, science and religion, truth and lies, and faulty logic. However, training a private version of ChatGPT unlocks a huge use case that was proven many years ago.