Fault Diagnosis algorithm of Wind Power Gearbox Based on Fuzzy Neural Network

Abstract

To improve the accuracy of fault diagnosis in wind power gearbox system, a fault diagnosis method based on the fuzzy neural network is proposed in this paper. Due to multiple working conditions of gearbox, the accuracy of fault diagnosis is easily affected by working environment and vibration signal of gearbox. Moreover, the vibration signals of the gearbox have the characteristics of non-linearity, non-stationarity and complexity. In this paper, the fault features of vibration signals are extracted from the perspective of information fusion. Based on the data obtained from the signals analysis, the fuzzy network is employed to establish the fault diagnosis model, and the parameter learning algorithm of network is also provided. Simulation results show that the feature extraction method adopted can well reflect the fault features of gear box, and the fault diagnosis system established by fuzzy neural network also has relatively accurate fault recognition capability.