An Intelligent Online Fault Diagnostic Scheme for Nonlinear Systems

An online fault diagnostic scheme for nonlinear systems based on neurofuzzy networks is proposed in this paper. The scheme involves two stages. In the first stage, the nonlinear system is approximated by a neurofuzzy network, which is trained offline from data obtained during the normal operation of the system. In the second stage, residual is generated online from this network, which is modelled by another neurofuzzy network trained online. From this network, fuzzy rules can be generated. Comparing these rules with those obtained under different faulty operations, fault can then be diagnosed. The proposed intelligent fault scheme is illustrated using a two-tank water level control system under various faulty conditions.