Inter-Turn Fault Detection of PMSM Based on Fuzzy Logic and Discrete Wavelet Transform Using Unsupervised Clustering

The idea of this paper is designing an automatic fault detection system based onfuzzy logic, therefore two signals of PMSM in fault condition are analyzed for interturn fault detection: current and torque. In this fault type there is some distortion inthese signals, but it is not good enough to detecting with fuzzy logic solely, so withcombination of wavelet transform and FCM a new method for fault detection isintroduced. In this method one detail signal of wavelet transform is chosen and thenwith FCM it is divided into 6 clusters, these clusters describe the situation of signaltruly. Using FCM has two advantages: first in some clusters there had been faulttherefore fault was detected, and second it is used for fuzzy logic system to decidingamount and intensity of fault of PMSM. By applying combination of wavelettransform and FCM, designing of fuzzy logic has been more effective, the MFs aredirectly come from output of FCM, therefore fuzzy logic system have more accurateanswer. The output of fuzzy logic that is showed in surface view is based on treesituation that is defined in output MF, and describes whole conditions of PMSM andshows the amount of inter turn fault.

کلیدواژه ها:

Fault Detection ، FCM ، Turn to Turn Fault ، PMSM ، Wavelet Transform