Fault detection of rotating machinery based on wavelet transform and improved deep neural network

In the operation of wind turbine, gearbox faults are very common. It is very important to detect the fault effectively to ensure the safe and reliable operation of wind turbine. In this study, the wavelet analysis method is combined with an improved convolutional neural network and support vector machine (CNN-SVM), and the proposed method is applied to the fault detection and classification of the gearbox in the wind power generation equipment in the laboratory. The experimental results show that the proposed method achieves super classification result.