Research On Motor Fault Diagnose Method Based On Condition Monitoring And Health Assessment

Motor fault diagnosis has always been a research hotspot in the field of equipment diagnosis.Due to the complex structure of the motor and the harsh operating environment,the fault features are subject to many interference factors.Based on the traditional method,the fault characteristics cannot be accurately obtained from the original data,resulting in fault diagnosis results less accurate.With the maturity of signal processing technology and the rapid development of artificial intelligence methods,fault information that was difficult to obtain can be effectively extracted using signal processing advanced methods.In this paper,based on the characteristics of motor fault data,The key research contents are as follows:First,the motor fault is modeled,and the mechanical and electrical fault characteristics are analyzed through the mechanism.For mechanical faults,the vibration signal mainly generates harmonic components,and the electrical fault mainly causes the current signal to change.Then the variational mode decomposition method is studied.For the rotor breaking fault of the motor,the characteristic frequency and the fundamental frequency of the power supply are very close.Based on Fourier transform and empirical mode decomposition,the two frequencies cannot be effectively separated.This article uses the variational mode.Decomposing the original signal can accurately separate the two.When the running state of the motor is stable,the fault characteristics can be effectively identified by using the mechanism characteristics;however,the motor is often in an unstable state of the speed fluctuation.Aiming at the problem of variable operating conditions,this article proposes an energy characteristic entropy analysis method based on variable mode decomposition to realize the effective estimation of the health coefficient of motor bearing.Taking the rolling bearing of the test bench of Case Western Reserve University as the experimental object,the wear condition of the inner ring of the bearing under the operating condition of the variable working condition is studied,and the analysis results of the wavelet packet Renyi entropy and the frequency domain feature are compared to verify the validity of the VMD-Renyi entropy under the variable working condition.Electrical faults are often judged by 0-1 and there is no intermediate state.While the motor components such as bearings wear out during operation,a health factor can be used to characterize the degree of failure of the bearing.Secondly,the support vector machine(SVM)information fusion multi-class classifier is constructed,and the fault state of the motor bearing is identified.Then the SVM classifiers with dimensionless time domain features and wavelet packet energy features are selected as references.The correctness of test sample classification is used to analyze and compare,and the effectiveness of information fusion SVM classifier is verified.Finally,the Whale Optimization Algorithm(WOA)improved by von Neumann structure optimizes the parameters of the classifier,which further enhances the generalization ability of the classifier.Finally,the fault diagnosis system platform was designed using MFC.This study provides technical support and theoretical guidance for motor fault detection in practical industrial environments.