Abstract: The back-propagation neural network is applied to the state estimation of nonlinear time-varying system. An adaptive state estimator based on the neural network is proposed,and the structure and characteristics of the observer are discussed,The results of estimation show that the proposed nonlinear state observer can deal with a large unknown nonlinearity and track the real system state satisfactorily.

Key words: state estimation, neural nets, nonlinear systems-time dependance