The Sira-Kvina power company produces about 5% of Norway's power generation as renewable energy from seven hydro power plants. Sira-Kvina engaged Elder Research to build predictive models to determine hydro generator component failure risk to enable preemptive maintenance operations and system monitoring.
Elder Research built machine learning models using various operational and maintenance data sources. We developed an abstract model of the generator systems that could be linked to operational and sensor data. The generator risk and other relevant data were represented in a visual layer using our Risk Assessment Data Repository (RADR) as a prototype for the predictive maintenance tool.
The model identified that the generator had moved into a damaged state eight power cycles earlier than had previously been observed by the maintenance team. The model was trained on the SCADA sensor data and achieved a 5-times boost in predictive performance above the baseline. Using CEPtor, sensor metrics were reduced from hundreds to the ten that provided the best predictive performance, making the results easier to interpret.