Machine Learning Based Online Monitoring of Step-Up Transformer Assets in Electrical Generating Stations

Electric utilities undertake a significant cost to maintain the health of their assets every year. In recent years, in BC Hydro, one of the strategies in maintaining generating stations has been to shift burden from preventative maintenance to predictive maintenance when safely and reliably applicable. This approach could help utilities to reduce the cost of preventative maintenance programs and further rely on predictive measures to assess the health risk of assets and only execute physical interventions when the assessed risk compels. In this paper, the authors share BC Hydro's experience in using machine learning for predictive online monitoring of step-up transformers at electrical generating stations. In addition to high level statistics of the machine learning based predictive online monitoring program, the paper presents a detailed example where predictive monitoring prevented financial damage to a transformer and mitigated fast reduction of remaining life of the asset possibly saving the company millions of dollars.