Motor bearing fault diagnosis method based on artificial neural network

Abstract

The invention discloses a motor bearing fault diagnosis method based on an artificial neural network. Firstly the vibration signals of the internal circle, the external circle and the rolling body ofa motor bearing under different states are acquired to act as feature data by using a vibration sensor to form feature vectors and act as the input of the neural network; then the number of nodes of the artificial neural network is determined according to the number of dimensions of the extracted feature vectors; the artificial neural network is designed and then a part of the feature signals actas training samples, and the expected output is obtained by using the trained neural network; and finally the residual feature signals act as verification samples to diagnose the fault point of the motor bearing. Various types of faults of the motor bearing can be judged by using the artificial neural network. The artificial neural network can be used for identifying the complex or unknown system.The artificial neural network has high anti-interference capability, and identification of the neural network is not influenced even the system is under interference. Besides, the artificial neural network has high identification accuracy and high practicality.

Description

technical field [0001] The invention relates to the field of motor bearing faults, in particular to an artificial neural network-based fault diagnosis method for motor bearings. Background technique [0002] In modern production, the motor plays an irreplaceable role. If the motor fails, it will stop production and even endanger human life. Rolling bearing is the most important part of the motor, and its normal operation has an important impact on the mechanical properties of the motor. At present, the diagnosis method of motor bearing faults is mainly the vibration method. The vibration method can effectively detect various faults of the motor and is easy to operate. However, the vibration method can only detect signals and cannot accurately identify the fault type. Contents of the invention [0003] The purpose of the present invention is to provide a motor bearing fault diagnosis method based on artificial neural network, which can accurately identify the fault type of...

AI Technical Summary

Problems solved by technology

At present, the diagnosis method of motor bearing faults is mainly the vibration method. The vibration method can effectively detect various faults of the motor and is easy to operate. However, the vibration method can only detect signals and cannot accurately identify the type of fault.

Images