A Novel Wind Turbine Fault Detection Method Based on Fuzzy Logic System Using Neural Network Construction Method

Fuzzy logic system is commonly used in wind turbine fault detection. However, traditional fuzzy logic systems are built through human experience. The fuzzy logic system constructed in this way will have inaccurate problems. In order to solve this problem, this paper proposes a novel fuzzy logic system (FLS) based on neural network construction method to improve accuracy rate of wind turbine fault detection. First, a neural network construction method is proposed. Using this method, membership function can be constructed more accurately. Then, a FLS based on the extended data-driven membership function is proposed. When environment changes, such FLS can improve accuracy rate of wind turbine fault detection with the extended data-driven membership function. Finally, experiments using data from actual wind fields are performed, and the experimental results show that the method proposed in this paper is effective. Copyright (C) 2020 The Authors.