Detection and diagnosis of broken rotor bars and eccentricity faults in induction motors using the Fuzzy Min-Max neural network

Fault detection and diagnosis of electrical machines is gaining importance in regards to machine downtimes, where an unpredicted shutdown of operations owing to unavailability of machines can be very costly. As such, an early warning system for incipient machine faults using condition monitoring is of significance in practical applications. In this paper, we propose a fault detection and diagnosis system to detect and classify broken rotor bars and eccentricity faults of induction motors using the Fuzzy MinMax (FMM) neural network. A series of real experiments is conducted, where the acquired current signals under various motor conditions is used to build a database. The Power Spectral Density is then used to extract the discriminative input features for fault detection and classification with FMM. The results are comparable, if not better, than those from the MultiLayer Perceptron neural network and other methods reported in the literature.