Fault conditions classification of automotive generator using an adaptive neuro-fuzzy inference system

In this paper, an adaptive neuro-fuzzy inference system (ANFIS) was proposed for condition monitoring and fault diagnosis of an automotive generator. Conventional fault indication of an automotive generator generally uses an indicator to inform the driver when the charging system is malfunctioning. Unfortunately, the charge indicator only shows if the generator is normal or in a fault condition. In the present study, an automotive generator fault diagnosis system was developed for fault classification of different fault conditions. The condition monitoring system consists of feature extraction using discrete wavelet analysis to reduce the complexity of the feature vectors with classification using the artificial neural network technique. In the generator output signal classification, the ANFIS is used to classify and compare the synthetic fault types in an experimental engine platform under various engine operating conditions. The experimental results pointed out the proposed condition monitoring and fault diagnosis system has potential in fault diagnosis of the automotive generator.