Robust fault diagnosis for a class of nonlinear systems using fuzzy-neural and sliding mode approaches

A robust fault diagnosis (FD) scheme integrating Takagi-Sugeno (T-S) fuzzy-neural models and sliding mode technique is presented for a class of nonlinear systems that can be described by T-S fuzzy models. A fuzzy-neural observer and a fuzzy-neural sliding mode observer are constructed respectively. A modified back-propagation (BP) algorithm is used to update the parameters of these two observers. Finally, the proposed FD scheme is applied to a satellite orbital control system. Simulation results show that this robust fault diagnosis strategy is effective for a class of nonlinear systems.