Sensor Fault Identification for a Class of Nonlinear Discrete-time System

This paper presents an adaptive neural network (ANN) observer based on deterministic learning (DL) theory for a class of discrete-time nonlinear system with sensor faults. The attractiveness is that the exponential stability of the state and parameter estimation error system is proved, and thus locally-accurate approximation of sensor faults is achieved. The simulation example shows the effectiveness of the proposed approach.