Adaptive Neural Network Generalized Predictive Control for Unknown Nonlinear System

This paper presents an adaptive neural control design for a class of unknown nonlinear systems. Novel state variables and the corresponding transform are introduced, such that the statefeedback control of a pure-feedback system can be viewed as the output-feedback control of a canonical system. An adaptive predictor incorporated with a neural network observer is proposed to obtain the future system states predictions, which are used in the control design to circumvent the input delay and nonlinearities. The proposed predictor, observer and controller are all online implemented, and the closedloop system stability is guaranteed. The conventional backstepping design and analysis for pure-feedback systems are avoided, which renders the developed scheme simpler in its synthesis and application. Practical guidelines on the control implementation and the parameter design are provided. The applicability in nonlinear system is demonstrated by simulation experiments.