A novel SE-weighted multi-scale Hedging CNN approach for fault diagnosis of wind turbine

This paper proposes a novel weighted SE MSH CNNs approach to make full use of time-series data and solve the problem of low WT fault diagnosis accuracy. Firstly, the operating data of WTs are collected through the SCADA system and expanded by the SWM. Then, the SE network is constructed to adaptively determine the weights of each parameter to focus on the effective fault features, and the stacking layers are used to extract the multi-scale features. After that, the obtained features are hedged to get the differentiated features, and two global pooling layers are employed to extract further and fuse the multi-scale features. The proposed method is put into an application case to verify its superior effectiveness and generalization ability in WT fault diagnosis. Experimental results show that: (1) the proposed method effectively extracts multi-scale differentiated features, thereby improving the identifiability of WT faults; (2) the proposed model outperforms all the other considered models in terms of accuracy and other evaluation metrics, showing that it is more appropriate for WT fault diagnosis; (3) the superiority and generalization ability of the proposed method are further verified through various experimental strategies.