United StatesChemicals and materials2008 – ongoingAir Products and Chemicals
ProcessMD predictive plant monitoring
Air Products used machine learning to monitor more than 400 industrial gas facilities
Problem
Equipment faults and process deviations could cause plant shutdowns. Operating teams needed earlier warnings and help diagnosing problems.
Approach
Air Products began developing ProcessMD in 2008 and deployed it at operating plants in 2009. Adaptive models detected departures from expected equipment and process behavior. Alerts went to engineers who diagnosed problems and recommended actions to plant teams.
Results
Takeaway
The monitoring system connected model alerts to a dedicated engineering team that could turn warnings into maintenance actions.
Categories
- Size
- Large enterprise
- Industry
- Chemicals and materials
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
Conference coverage reported Air Products manager Will Hanlon's account of ProcessMD. It described the deployment footprint and company-reported equipment savings.
Full details are in the original sources.
