Fault diagnosis using neural-fuzzy technique based on the simulation results of stator faults for a three-phase induction motor drive system

Nowadays, induction machines are known as workhorse and play an important role in manufacturing environments mainly due to their low cost, reasonably small size, ruggedness, low maintenance, and operation with an easily available power supply. Therefore, the diagnostic technology of this type of machine is mainly considered and proposed from industry and scientist academia. Several studies show that approximately 30-40% of induction machine faults are stator faults. The fault diagnosis of electrical machines has progressed in recent years from traditional to artificial intelligence (Al) techniques. This paper presents a general review of the principle of AI-based diagnostic methods first. It covers the recent development and the system structure, about expert system (ES), artificial neural network (ANN), fuzzy logic system (FLS), and combined structure, like neural-fuzzy, based fault diagnostic strategies. Finally, a neural-fuzzy technique is used in this paper to perform the stator fault diagnosis for induction machine. The simulation results verified the technique proposed