A neural network approach to simultaneous state and actuator fault estimation under unknown input decoupling

The paper deals with the problem of a neural network-based robust state and actuator fault estimator design for non-linear discrete-time systems. It starts from a review of recent developments in the area of robust estimators and observers for non-linear discrete-time systems and proposes less restrictive procedure for designing a neural network-based H observer. The proposed approach guaranties a predefined disturbance attenuation level and convergence of the observer, as well as unknown input decoupling and state and actuator fault estimation. The main advantage of the design procedure is its simplicity. The paper presents an observer design procedure that is reduced to solving a set of linear matrix inequalities. The final part of the paper presents an illustrative example concerning an application of the proposed approach to the multi-tank system benchmark.