Research on fault diagnosis method of rolling bearing based on 2DCNN

The traditional fault diagnosis method of rolling bearing relies on signal analysis and processing technology, and the accuracy of fault identification is low; artificial neural network(ANN) and support vector machine(SVM) need to extract features manually, and the accuracy rate can't meet people's needs. With the arrival of the era of big data, those methods more and more can not meet the needs of practical problems, and deep learning plays an increasingly important role in the field of fault diagnosis. In this study, a method of rolling bearing fault diagnosis based on Two-Dimensional Convolutional Neural Network(2DCNN) is proposed, 2DCNN architecture model is established, the network parameters are optimized, the experimental scheme is designed, and the classification accuracy of 2DCNN for rolling bearing fault is explored. The experimental results show that in the process of identifying the fault mode of rolling bearing, the 2DCNN can distinguish the fault and normal state of rolling bearing accurately and classify the fault accurately.