基于CNN和Transformer结合的电机故障诊断方法研究

In order to improve the accuracy and efficiency of motor fault diagnosis, the extraction of fault features in traditional diagnosis methods is not comprehensive. This paper presents a motor fault diagnosis method that combines Convolutional Neural Network (CNN) with Transformer. Firstly, the main faults of asynchronous motor and the fault diagnosis algorithm of current motor are analyzed. Then, through the analysis of convolutional neural network structure, combined with the encoder module of transformer, a fault diagnosis model for asynchronous motor is proposed. Finally, a data set is constructed based on the data of five common fault conditions and normal conditions of the motor, and experiments are carried out on the motor fault data set. The experimental results show that the model proposed in this paper has a high accuracy in the test set.