Fault Diagnosis System for Machines Using Neural Networks

This research is concerned with the fault diagnosis for machines using neural networks. Generally, it is difficult to diagnose machine's fault by the conventional technique. In this research, two new fault diagnosis systems are proposed which one diagnoses a fault based on behavior of the object system, and another diagnoses a fault based on power spectrum of the object system. In the former, when an object system is a normal state, the system identification is performed by the neural networks. The diagnosis system detects a fault by finding the behavior's gap between the state of the real system and the identified normal one, and also the fault part is specified by fault diagnosis neural network. In the latter, neural network learns power spectrum of both the normal and fault states for the object. When a fault occurs, fault part is diagrnosed by fault diagnosis neural network based on power spectrum. Finally, through simulation and experiment, the effectiveness of proposed fault diagnosis systems is verified.