Hopfield/ART-1 neural network-based fault detection and isolation

A new approach to detect and isolate faults in linear dynamic systems is proposed. System parameters are estimated by Hopfield type neural network, while the system is in certain operating mode. When the system dynamics changes, estimated parameters go through a transition period and this period is used to detect faults. These estimates, however, are not reliable enough to be used for isolating faults. The judgment on the instance at which the estimates move out of the transition zone is made through a set of statistical tests performed on the residuals in a moving window. Once the system is out of the transition zone and settles to a new operating level, the estimated parameters are classified using an ART-1 based neural network. The proposed scheme is implemented to detect and isolate faults in a position servo system.