Fault Feature Parameter Extraction Method for Wind Turbine Based on Relief Algorithm

Abstract

With the rapid development of wind power technology, the capacity of wind power is growing rapidly and monitoring data of SCADA system is also becoming more comprehensive. Faults of wind turbine components are closely related to work condition, so the overall availability of whole wind farm could be improved by focusing on the wind turbines operating in harsh condition. In this paper, a method based on SCADA data to judge harsh condition is proposed. According to historical data of SCADA and fault record, the fault characteristic parameters are selected by Relief algorithm, as the characteristic quantity of failure rate of wind turbine. Taking pitch fault and yaw fault as example, the SCADA data of the actual wind farm are simulated and the effectiveness of the method is verified.