Robust fault detection and diagnosis in a class of nonlinear systems using a neural sliding mode observer

This article presents a robust fault detection and diagnosis scheme for any abrupt and incipient class of faults that can affect the state of a class of nonlinear systems. A nonlinear observer which synthesizes sliding mode techniques and neural state space models is proposed for the purpose of online health monitoring. The sliding mode term is utilized to eliminate the effect of system uncertainties on the state observation. The switching gain of the sliding mode is updated via an iterative learning algorithm and an iterative fuzzy model, respectively. Moreover, a bank of neural state space models is adopted to estimate various state faults. Robustness with respect to modeling uncertainties, fault sensitivity, and stability of this neural sliding mode observer-based fault diagnosis scheme are rigorously investigated in theory. Moreover, the proposed fault detection and diagnosis scheme is applied to the model of a fourth-order satellite dynamic system, and the simulation results illustrate the effectiveness of the proposed approach.