Stereo garage motor fault diagnosis method using DBN multi-domain feature extraction

Abstract

The invention discloses a stereo garage motor fault diagnosis method using DBN multi-domain feature extraction. The method comprises the following steps: carrying out time-frequency domain feature extraction on a vibration signal of a stereo garage gear reduction motor; carrying out further depth feature extraction on the time-frequency domain feature indexes by utilizing a DBN model; and inputting the deeply extracted features into a trained OnClass SVM model for fault diagnosis to obtain a diagnosis result of whether the motor has a fault or not, judging whether the motor has a fault or not,and then notifying a garage administrator to carry out corresponding processing. The DBN is used for multi-domain depth feature extraction, so that deeper vibration signal features can be extracted,the accuracy of motor fault diagnosis is improved, and meanwhile, the maintenance efficiency of the stereo garage motor is improved.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis, and relates to a fault diagnosis method for a three-dimensional garage motor using DBN multi-domain feature extraction. Background technique [0002] The rapid development of the three-dimensional garage will bring more operational safety problems. Since the three-dimensional garage works in an outdoor environment for a long time, various factors such as weather may cause the garage motor to run over temperature, over-rotation and other faults, so as to improve the safety of the garage operation. become a key issue of concern. As an important part of the three-dimensional garage, the motor may fail at any time due to insulation aging, long-term overload operation, surrounding environmental factors, etc., and a part of the motor failure will often cause the entire system to fail, resulting in a series of safety issues and problems. Economic losses. [0003] At present, the management per...

AI Technical Summary

Problems solved by technology

As an important part of the three-dimensional garage, the motor may fail at any time due to insulation aging, long-term overload operation, surrounding environmental factors, etc., and a part of the motor failure will often cause the entire system to fail, resulting in a series of safety issues and problems. Economic losses

[0003] At present, the management personnel of the three-dimensional garage mostly use the method of manual periodic inspection to maintain the motor. This maintenance method is not only inefficient, but also cannot guarantee the safe operation of the garage. At the same time, in the field of motor fault diagnosis, most fault diagnosis methods only use the time domain Indicators or frequency domain indicators to diagnose the motor vibration signal, without combining the characteristic indicators of the time domain and frequency domain to comprehensively judge the motor vibration signal, which affects the accuracy of the fault diagnosis model of the three-dimensional garage motor to a certain extent Sexuality and Generalization

Images