Motor Fault Diagnosis Based on Short-time Fourier Transform and Convolutional Neural Network  

作　　者：Li-Hua Wang Xiao-Ping Zhao Jia-Xin Wu Yang-Yang Xie Yong-Hong Zhang 

机构地区：[1]School of Information and Control, Nanjing University ofInformation Science and Technology, Nanjing 210044, China [2]School of Computer and Software, Nanjing University ofInformation Science and Technology, Nanjing 210044, China [3]Network Monitoring Center of Jiangsu Province, NanjingUniversity of Information Science and Technology,Nanjing 210044, China

出　　处：《Chinese Journal of Mechanical Engineering》2017年第6期1357-1368,共12页中国机械工程学报（英文版）

基　　金：Supported by National Natural Science Foundation of China(Grant No.51405241,51505234,51575283)

摘　　要：With the rapid development of mechanical equipment, the mechanical health monitoring field has entered the era of big data. However, the method of manual feature extraction has the disadvantages of low efficiency and poor accuracy, when handling big data. In this study, the research object was the asynchronous motor in the drivetrain diagnostics simulator system. The vibration signals of different fault motors were collected. The raw signal was pretreated using short time Fourier transform （STFT） to obtain the corresponding time-frequency map. Then, the feature of the time-frequency map was adap- tively extracted by using a convolutional neural network （CNN）. The effects of the pretreatment method, and the hyper parameters of network diagnostic accuracy, were investigated experimentally. The experimental results showed that the influence of the preprocessing method is small, and that the batch-size is the main factor affecting accuracy and training efficiency. By investigating feature visualization, it was shown that, in the case of big data, the extracted CNN features can represent complex mapping relationships between signal and health status, and can also overcome the prior knowledge and engineering experience requirement for feature extraction, which is used by tra- ditional diagnosis methods. This paper proposes a new method, based on STFT and CNN, which can complete motor fault diagnosis tasks more intelligently and accurately.With the rapid development of mechanical equipment, the mechanical health monitoring field has entered the era of big data. However, the method of manual feature extraction has the disadvantages of low efficiency and poor accuracy, when handling big data. In this study, the research object was the asynchronous motor in the drivetrain diagnostics simulator system. The vibration signals of different fault motors were collected. The raw signal was pretreated using short time Fourier transform （STFT） to obtain the corresponding time-frequency map. Then, the feature of the time-frequency map was adap- tively extracted by using a convolutional neural network （CNN）. The effects of the pretreatment method, and the hyper parameters of network diagnostic accuracy, were investigated experimentally. The experimental results showed that the influence of the preprocessing method is small, and that the batch-size is the main factor affecting accuracy and training efficiency. By investigating feature visualization, it was shown that, in the case of big data, the extracted CNN features can represent complex mapping relationships between signal and health status, and can also overcome the prior knowledge and engineering experience requirement for feature extraction, which is used by tra- ditional diagnosis methods. This paper proposes a new method, based on STFT and CNN, which can complete motor fault diagnosis tasks more intelligently and accurately.

关 键 词：Big data Deep learning Short-time Fouriertransform Convolutional neural network MOTOR 

分 类 号：TM307[电气工程—电机]