Discrete-Time High Order Neural Control: Trained with Kalman Filtering

摘要: The objective of this work is to present recent advances in the theory neural control for discrete-time nonlinear systems with multiple inputs and outputs. results that appear each chapter include rigorous mathematical analyses, based on Lyapunov approach, guarantee its properties; addition, chapter, simulation are included verify successful performance corresponding proposed schemes. In order complete treatment these schemes, final presents experimental related their application a electric three phase induction motor, which show applicability such designs. schemes could be employed different applications beyond ones presented book. book solutions output trajectory tracking problem unknown four For first one, direct design method considered: well known backstepping method, under assumption sate measurement; second one considers an indirect solved block sliding mode techniques, same assumption. third scheme, technique reconsidering including observer, finally techniques used again too, observer. All developed discrete-time. both mentioned methods as on-line training respective networks performed by Kalman Filtering.