Shell rolls out preventative maintenance tech
Shell has extended its use of a predictive maintenance technology that uses artificial intelligence to identify possible equipment failures ahead of time, allowing the operator to take precautionary actions.
The technology platform from enterprise AI software company C3 AI is now being used across 10,000 pieces of critical equipment across Shell's global upstream, manufacturing and integrated gas segments, C3 AI said on March 8.
Shell renewed its strategic agreement with C3 AI in June 2021. What's more, Shell is offering its version of the technology to the entire energy industry, having made it available through the open energy AI initiative (OAI). Shell and C3 AI are both founding members of OAI, alongside others including Microsoft and Baker Hughes.
Predictive maintenance technologies help energy firms rationalise the financial and operational costs of downtime, as well as countering risks to the environment and human safety.
They are set to replace ordinary maintenance schedules with updates that evolve to reflect the health status of every equipment node, using sensors connected to the internet.
Shell's deployment, for example, makes more than 15mn predictions each day, using data collected from 3mn sensors across its facilities.
The AI learns to recognise 11,000 machine learning models using algorithmic signals from the sensors. Shell plans to further accelerate the predictive maintenance deployment later this year, and will also explore new use cases such as production optimisation, asset integrity, safety and sustainability.
"Monitoring 10,000 pieces of critical equipment with AI-enabled predictive maintenance is an important milestone for Shell — an ambitious target we had set for 2021 and successfully achieved," said Dan Jeavons, Shell's vice president of computational science and digital innovation. "We have an exceptionally talented team to thank for this accomplishment, as well as partners like C3 AI, whose technology helped us reach this level of scale in our predictive maintenance programme."