Small sample fault diagnosis for wind turbine gearbox based on lightweight multiscale convolutional neural network
Yuan Wang, Junnian Wang, Pengcheng Tong
Abstract
Abstract The maintenance and diagnosis of wind turbine gearboxes are crucial for enhancing the stability and operational efficiency of wind power systems. However, there are still two challenges in gearbox fault diagnosis methods based on deep learning: (1) limited failure sample; (2) interference of strong noise. To solve the above issues, a lightweight multiscale convolutional neural network (LMSCNN) based fault diagnosis method is proposed in this paper. Among them, a large kernel convolution is used to denoise the original vibration signal. A lightweight multiscale architecture is constructed using depthwise separable convolutional blocks, which mine fault features at different scales and improve the operational efficiency of the model. Moreover, a parallel global pooling block is designed to provide a more comprehensive feature for the fusion layer, enabling the effective diagnosis of vibration signals. Experiments are conducted on the datasets of two different gearboxes, which prove that LMSCNN has excellent generalization capability and diagnostic speed.