Host: The Japanese Society for Artificial Intelligence
Name : 34th Annual Conference, 2020
Number : 34
Location : Online
Date : June 09, 2020 - June 12, 2020
In recent years, electric power companies collects different types of sensor data and weather information to maintain the safety of hydroelectric power plants while the plants are in operation. Although the power plant operation data is mostly normal state data, there is little accumulation of abnormal state data, and it is not easy to observe data related to abnormal states. Therefore, we have to identify malfunction signs from among the collected sensor data. In this paper, we detected outliers from hydropower plant operation data using five outlier detection methods including one-class SVM and compared the characteristics of each outlier.