VIBRATION BASED FAULT DETECTION OF ALTERNATOR BY FAST FOURIER TRANSFORM AND ADAPTIVE NEURO FUZZY INFERENCE SYSTEM

Alternators are used in modern automobiles to provide the electrical power. The electrical power requirements in automobiles have been rising rapidly for many years and are expected to continue to rise. Now the alternator is one of the critical components of an automobile. If the alternator does not work properly, the automobile cannot operate. Hence, the present study tries to introduce a technique for intelligent fault diagnosis of an alternator using acquired vibration signals and ANFIS. This paper presented an adaptive network fuzzy inference system to diagnose the fault type of the alternator. The alternator conditions to be considered were healthy alternator (HA), unbalancing in driven shaft (UDS), crack in rotor body (CRB) and wear in bearing (WB). These features are extracted from vibration signals using the FFT technique. The features were fed into an adaptive neuro fuzzy inference system as input vectors. Performance of the system was validated by applying the testing data set to the trained ANFIS model. According to the result, total classification accuracy was 86.67%.