Research on Fault Diagnosis Algorithm Based on Convolutional Neural Network

Most of the traditional fault diagnosis methods rely on the expert knowledge of artificial extraction features and related fields, and these algorithms are not accurate, and the robustness and generalization ability are poor. Convolutional neural network is one of the most widely used deep learning models. Based on its unique convolution-pooling network structure, convolutional neural network has powerful feature extraction and expression capabilities. In this paper, based on the characteristics of one-dimensional vibration signals, a fault diagnosis algorithm model based on one-dimensional convolutional neural network is proposed. Through the experiment of the bearing fault public data set, the proposed algorithm has more than 99% fault recognition rate.