As one of the largest clean power producers in North America, Ontario Power Generation (OPG) is responsible for approximately 50% of the electricity generation in the Province of Ontario. OPG has installed the PI System and AVEVA™ Predictive Analytics across its renewable and nuclear fleet, thereby enabling AI-infused condition-based maintenance.
“We’ve just deployed the first set of online pattern recognition monitoring on our large transformers, so we can predict degradation while optimizing performance and maintenance programs. In the past, engineers would need to walk around to each transformer to manually download and analyze this data. These data sets are piped directly into our PI System network, so that we can build models using the information. We’ve also incorporated our own auto-diagnostic calculations using AVEVA Predictive Analytics. This enables us to better understand and predict which failure mechanisms are occurring, which enables true condition-based maintenance. This is just the beginning, as we look forward to the integration of monitoring and diagnostics and more advanced analytics in future fleets of small modular reactors.”
Nazgol Shahbandi, Data Scientist, OPG’s Monitoring & Diagnostic Center
Goals
- Ontario Power Generation (OPG) has a mission to provide low-cost power in a safe, clean, reliable, and sustainable manner for customers across Ontario
- The company is constantly pursuing innovations, and the team wanted to use digital transformation to boost efficiency and sustainability throughout their operations
- In line with this vision, OPG’s leadership wished to move from reactive to predictive and prescriptive operating and maintenance models for their power generation fleet to improve plant uptime, increase reliability, and enhance safety performance
Challenges
- Need to optimize operations and maintenance of critical nuclear facilities
- High-risk operating environment makes changes to operating procedures fraught with risk – OPG sought a trusted and expert partner with whom to embark on their digital transformation journey
- Shifting from reactive to predictive operating models requires behavioral change – OPG needed to find a partner who could support it in the transition
Solutions
Results
- Up to $4 million (USD) efficiency savings achieved within the first 24 months of implementation and value accelerating
- Over 1,200 predictive and prescriptive maintenance operating models were established, which harness data from thousands of sensors throughout OPG’s nuclear operating teams and HEP power plants
- Cloud-based systems connect the monitoring and diagnostic team with operational teams on site, enabling live collaboration and facilitating the move to condition-based maintenance
- Reduced risk and increased operational efficiency throughout the fleet – reduction of 3,000 annual maintenance hours can be redirected to higher value corrective tasks
- $400,000 (USD) saved in a single nuclear predictive analytics catch; $200,000 (USD) saved in a single HydroElectric (HEP) early warning catch
