Pumped-storage hydroelectricity (PSH) is a facility that stores energy in the form of the gravitational potential energy of water by pumping water from a lower to a higher elevation reservoir in a hydroelectric power plant. The operation of PSH can be divided into two states: the turbine state, during which electric energy is generated, and the pump state, during which this generated electric energy is stored as potential energy. Additionally, the condition monitoring of PSH is generally challenging because the hydropower turbine, which is one of the primary components of PSH, is immersed in water and continuously rotates. This study presents a method that automatically detects new abnormal conditions in target structures without the intervention of experts. The proposed method automatically updates and optimizes existing abnormal condition classification models to accommodate new abnormal conditions. The performance of the proposed method was evaluated with sensor data obtained from on-site PSH. The test results show that the proposed method detects new abnormal PSH conditions with an 85.89% accuracy using fewer than three datapoints and classifies each condition with a 99.73% accuracy on average.
Keywords: condition monitoring; continuous learning; prognostics and health management; pumped-storage hydroelectricity.