Research on Operation Condition Classification Method for Vibration Monitoring of Wind Turbine

Previous condition monitoring products classify the wind turbine operation condition based on one operation parameter. And a series of monitoring alarm thresholds are defined for each one of the classified wind turbine operation conditions. This leads to a lot of false alarms during the application of condition monitoring system of wind turbine. This paper uses multiple operation parameters to classify the complex and non-stationary wind turbine operation conditions related to vibration. In this paper, after preprocessing the actual operation data of a wind turbine, the false alarm rate is defined as a rationality evaluation index of operation condition classification methods. Afterwards, this paper proposes respectively two multiple parameters classification methods based on rough sets and support vector machine to classify the normal operation condition of wind turbine and calculates the false alarm rate based on testing different operation condition classification methods. The test results show that the two intelligent methods can decrease the false alarm rate obviously. Finally, the test results of different operation condition classification methods are compared and analyzed.