AI
Teaching AI to run with the turbines
Woodside Energy has transitioned from traditional predictive analytics to deploying around 50 active AI agents in production to support its industrial
Key takeaways
- Woodside Energy has around 50 AI agents in production supporting operating assets and enterprise workflows.
- The company's maintenance intelligence solution has the opportunity to reduce maintenance hours by up to 15% over five years on a pilot asset.
- Woodside utilizes an AI copilot called Startup Advisor to help panel operators manage the complex process of starting LNG plants.
- The company has been applying traditional AI, analytics, and predictive models to its business since around 2015.
Woodside Energy has transitioned from traditional predictive analytics to deploying around 50 active AI agents in production to support its industrial workflows and enterprise systems. According to Andrew Melouney, the company's vice president for digital, these tools include a "Startup Advisor" copilot to assist operators with complex liquefied natural gas (LNG) plant startups, and a maintenance intelligence system that has the potential to reduce maintenance hours by up to 15% over five years on a piloted asset.
In their words
“We've always had very large volumes of operational data coming from the equipment and the plants and the assets that we operate.”
“We started with a very bold vision of, how do we start up all of our LNG plants in a much more structured and optimized fashion?”
By the numbers
- 2015
- Year Woodside started applying traditional AI and analytics
- -15%
- Reduction in maintenance hours over five years
- 50
- AI agents currently in production at Woodside
How it unfolded
- Woodside begins applying traditional AI and predictive models
- Woodside operates around 50 AI agents in production
Turn stories like this into views
Ravenclip finds the AI news, makes the video, and posts it before attention moves on.
Common questions
- What happened with Woodside Energy?
- Woodside Energy has around 50 AI agents in production supporting operating assets and enterprise workflows.
- Where can I read the original report?
- Read the full report at mit_tech_review.
