ONLINE FAULT DIAGNOSIS OF NONLINEAR SYSTEMS BASED ON NEUROFUZZY NETWORKS

Abstract Artificial intelligence techniques such as neural networks and fuzzy logic have been widely used in fault detection and diagnosis. Combining these two techniques, referred to as neurofuzzy networks, provides a powerful tool for modelling. B-spline neurofuzzy networks are used to model the residuals. The weights of the networks are trained online using recursive least squares method. Fuzzy rules are extracted from the networks and they provide linguistic description of the residuals. The qualitative information of the residuals facilitates isolation of the system faults. The proposed scheme is illustrated using a simulation example of a DC motor.