Research On Gearbox Fault Diagnosis Of Wind Turbine Based On Vibration Signal Analysis

Since the implementation of sustainable development strategy in China,renewable energy has played a more and more important role in social and economic development.As a kind of clean and renewable energy with wide distribution and huge reserves,wind energy plays an important role in the energy supply of our country.Wind turbine’s gearbox is an important component of the turbine transmission system,Its working state is closely related to the operating condition of the turbine.If the gearbox fails,there is a high probability that it will lead to the downtime of the wind turbine.In this paper,the fault diagnosis model of wind turbine’s gearbox is established by processing the vibration signal of wind turbine’s gearbox,extracting its fault features,constructing appropriate feature vectors and combining with intelligent algorithm.The main contents are as follows:(1)The background and significance of fault diagnosis of fan gearbox are introduced,and the structure and fault mechanism of wind turbine gearbox are analyzed.According to the current research situation at home and abroad,the main contents of gearbox fault diagnosis are summarized.(2)In view of the non-linearity and non-stationarity of the wind turbine’s gearbox signal,the improved overall empirical mode decomposition algorithm(MEEMD),is adopted to process the wind turbine’s gearbox vibration signal,which is convenient for the feature extraction of the gearbox fault signal.The effectiveness of the signal processing method is verified by experimental comparison.(3)The vibration signal of wind turbine’s gearbox is decomposed by MEEMD signal processing algorithm,and the first few intrinsic modal function components which are highly related to the original signal are selected,then the sample entropy of each intrinsic modal function component is calculated,the eigenvector of wind turbine’s gearbox fault identification is constructed,and finally the sample set is formed.(4)Aiming at the problem that the fuzzy C-means clustering(FCM)algorithm can not consider the difference of each feature in the sample vector,the weighted fuzzy clustering algorithm(WFCM)is used to cluster the fault feature vector,and the fault diagnosis model of MEEMD-WFCM wind turbine’s gearbox is established,and the effectiveness of the model is verified by simulation experiments.(5)In view of the deficiency of the stability of the fault diagnosis model of MEEMD-WFCM wind turbine’s gearbox,the least square support vector machine(WOA-LSSVM)classification algorithm based on whale optimization algorithm is proposed,and the fault diagnosis model of WOA-LSSVM fan gearbox is established.On the basis of ensuring the accuracy of fault identification,the model further improves the stability of the fault diagnosis model and can achieve better fault diagnosis results.