MalaysiaEnergy and utilities2019 – ongoingPETRONAS
Cloud-based early warnings for rotating equipment
PETRONAS avoided US$17.4 million in equipment-related losses in its first deployment year, according to AVEVA
Problem
Equipment failures could shut down plants, while fragmented operating data slowed engineers' responses.
Approach
PETRONAS combined AVEVA PI System data with predictive models running in Microsoft Azure. The models detected departures from learned normal equipment behavior and warned maintenance engineers. Integrator Trisystem Engineering helped deploy the system.
Results
Takeaway
Maintenance engineers used early warnings to repair equipment before failure. AVEVA attributed US$17.4 million in avoided losses and 14x ROI to the first deployment year.
Categories
- Size
- Large enterprise
- Industry
- Energy and utilities
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Vendor solution
- Evidence
- Vendor case study
Sources
Source summaries
AVEVA described models trained on normal equipment behavior and maintenance responses to early warnings. It assigned US$17.4 million in avoided losses and 14x ROI to the first deployment year, 2020.
The presentation described PETRONAS integrating predictive analytics with its PI-based monitoring platform. It confirmed continuing use to improve equipment alerts and reduce unplanned downtime.
Full details are in the original sources.
