Fault diagnosis system for rotary machines based on fuzzy neural networks

This paper is concerned with the application of fuzzy neural networks to a fault diagnosis system of a rotary machine. The fault diagnosis system is based on a series of standard fault pattern pairs between fault symptoms and fault. Fuzzy neural networks are trained to memorize these standard pattern pairs. When an unknown sample is input into the trained fault diagnosis system, the fault diagnosis system can make a fault diagnosis by bi-directional association of fuzzy neural networks. Through experiment on a rotor testing table and application in monitoring and fault diagnosis of water pumps of an oil plant, it is verified that fuzzy neural networks have good discrimination ability and are effective for making fault diagnosis of a rotary machine.