Fault Diagnosis Method of Rolling Bearing Based on Equivalent LBP Texture Map

In order to diagnose the rolling bearing fault of the helicopter's automatic tilter, when the Convolution Neural Networks (CNN) directly extracts the fault features, the features of unfavorable factors such as noise can easily mislead the network learning, and there is a problem of ignoring local structural features, which affects the recognition To further improve the rate, a rolling bearing fault diagnosis method based on the combination of the equivalent local binary pattern (LBP) texture feature map and CNN is proposed. Firstly, the two-dimensional time-frequency image of rolling bearing vibration signal is obtained by using continuous wavelet transform, and the time-frequency image is preprocessed. Then, the uniform LBP algorithm is used to extract the texture features of gray time-frequency images to form the texture map. Finally, the convolution neural network model is built to train the texture map data set and achieve the optimal, so as to realize the diagnosis of the fault type of rolling bearing. Diagnostic experiments were carried out using the bearing fault data of the research team and Case Western Reserve University. The recognition accuracy is up to 99.23% and 100%, which is a maximum increase of 1.7% compared with the traditional method. The results show that the proposed method can effectively realize the accurate identification of fault diagnosis.