One-Class SVM based Unusual Condition Monitoring for Risk Management of Hydroelectric Power Plants

Abstract

Kyushu Electric Power Co., Inc. collects different sensor data and weather information to maintain the safety of hydroelectric power plants while the plants are running. However, it is very rare to occur abnormal condition and trouble condition in the power equipment. And in order to collect the abnormal and trouble condition data, it is hard to construct experimental power generation plant and hydroelectric power plant. Because its cost is very high. In this situation, we have to find abnormal condition sign as a risk management. In this paper, we consider that the abnormal condition sign may be unusual condition. This paper shows results of unusual condition patterns of bearing vibration detected from the collected different sensor data and weather information by using one class support vector machine. The result shows that our approach may be useful for unusual condition patterns detection in bearing vibration and maintaining hydroelectric power plants. Therefore, the proposed method is one method of risk management for hydroelectric power plants.