Fault Diagnosis For A Class Of Nonlinear Systems Via Deterministic Learning

With the development of science and technology,the needs of production and life have been constantly improved,which makes the engineering system more and more complex,such as aeroengine,vehicle dynamics,power network,motor and other safety critical systems.These systems are very important,and if they have a fault,it will greatly damage the interests of society and property safety,affect the normal operation of society,or cause major safety accidents.Fault detection methods can effectively ensure the safe operation of these systems,which is of great significance in actual production.In this paper,through a combination of the deterministic learning(DL)method and the adaptive high gain observer(AHGO)technology,a fault identification approach for a class of input-output nonlinear systems is proposed.By using the DL method,the partial PE condition of the identification system is satisfied,and then the AHGO technology is exploited to estimate the states and the NN weights simultaneously.To analyze the convergence of the proposed method,we first analyze the uniformed completely observability(UCO)property of the linear part of the nonlinear identification system.Then by using the Lipschitz property of the nonlinear item and the Bellman-Gronwall lemma,we show that the UCO property of the nonlinear identification system is depended on the UCO property of the linear part when the observer gain is chosen large.Therefore,by using the UCO property of the nonlinear identification system and the Lyapunov stability theorem,the convergence of the proposed learning observer is proven.The attraction of this paper is based on the analysis of the UCO property of the identification system,the convergence of the proposed learning observer can be directly proven.And it is proved that this method is also suitable for sensor fault detection.The effectiveness of this method is proved by a van der Pol system and a single link manipulator system.