Intelligent Fault Diagnosis Of Brushless Direct Current Motor Research Based On Wavelet Transform

With the development of modern science and technology,brushless direct current motor play a more and more important role in modern industrial,commercial,aviation,military and other fields.The risk of machine failing can be remarkably reduced if normal service conditions can be arranged in advance.In other words,one may avoid very costly expensive downtime of plant by proper time scheduling of machine replacement or repair if warning of impeding failure can be obtained in advance.As the fault signals are non-stationary transient ones,the traditional signal analysis methods,such as Fourier Transform,are not so efficient and for the fault signal detection.However,Wavelet Analysis has the excellent time-frequency local performance,it can detect the different frequency components of the fault signals by its adjustable time-frequency window.In view of the superiority of Wavelet Transform to non-stationary signals,this paper focuses on how to detect and analyze the fault signals by Wavelet Transform.This paper gives a new fault diagnosis method for inverter main circuits:using current waveforms of inverter circuit as fault information,analyzing the fault cases,and drawing out the fault characteristics as the inputs of neural network to realize fault diagnosis.The main works and conclusions in this paper are as following:(1)Short-circuit fault of transistors in the inverter is taken to give fault waveforms.The analysis shows that:The classifiable fault styles are mainly two types:one is fault occurs in single bridge arm,the other one is fault occurs in two bridge arms.Every type of fault can be classified into several classes.(2)According to the multi-scale analysis theory,fault information's wavelet coefficient energy in five decomposition details of signal is changed into vector form as the input of neural network after normalized.(3)BP neural network classifier is trained by the feature vector sets,and then the new fault datas are collected to inspect and verify BP neural network in order to achieve the positioning of fault components.The experimental results show that: Diagnosis effect is well.