AC motor bearing fault diagnosis method adopting convolutional neural network and bidirectional long-short term memory network

Abstract

The invention discloses an AC motor bearing fault diagnosis method adopting a convolutional neural network and a bidirectional long-short term memory network. According to the method, the advantages of parameter sharing, local sensing, downsampling and the like of the convolutional neural network are fully utilized, corresponding spatial features are effectively extracted from original current data, and a complex feature extraction process is avoided. And then the extracted current data spatial features are input into a bidirectional long-short-term memory network, time sequence information of the current data spatial features is captured, and the rolling bearing fault diagnosis accuracy is further improved. According to the invention, the stator current obtained in the motor driving process is used as a fault signal, a non-intrusive fusion system which is easy to form a closed-loop'driving-diagnosis' is provided, and the monitoring cost can be effectively reduced; the bearing fault diagnosis method combines the characteristics of the convolutional neural network and the bidirectional long and short time memory neural network, has good performance in depth and complexity of feature extraction, and can realize accurate and effective extraction of fault features.

Description

technical field [0001] The invention relates to the field of state monitoring of AC motors, in particular to a method for diagnosing bearing faults of AC motors using current signal analysis. Background technique [0002] Compared with the traditional bearing fault diagnosis method using vibration signal analysis, due to cost and space constraints, some working environments cannot install additional hardware systems to meet the needs of AC motor bearing fault diagnosis. In addition, there are many other vibration and noise interference sources around the motor, which seriously affect the effect of vibration signal analysis and diagnosis of bearing faults. It is an important way to solve this problem by obtaining the fault signal through the motor drive control system and realizing the bearing condition monitoring. [0003] The bearing fault diagnosis method using the drive control system uses different signals such as current, voltage, torque and speed as the basis for faul...

AI Technical Summary

Problems solved by technology

Although the convolutional neural network application has achieved good results in bearing fault identification, it is not good at processing time series data samples.

Images