Neural Network Control of Nonlinear Discrete-Time Systems

TL;DR: This paper presents a meta-modelling architecture for adaptive control of Nonlinear Discrete-Time Systems using a model called Adaptive NN Control Design using State Measurements Output Feedback NN Controller Design.

Abstract: BACKGROUND ON NEURAL NETWORKS NN Topologies and Recall Properties of NN NN Weight Selection and Training NN Learning and Control Architectures References Problems BACKGROUND AND DISCRETE-TIME ADAPTIVE CONTROL Dynamical Systems Mathematical Background Properties of Dynamical Systems Nonlinear Stability Analysis and Controls Design Robust Implicit STR References Problems Appendix 2.A NEURAL NETWORK CONTROL OF NONLINEAR SYSTEMS AND FEEDBACK LINEARIZATION NN Control with Discrete-Time Tuning Feedback Linearization NN Feedback Linearization Multilayer NN for Feedback Linearization Passivity Properties of the NN Conclusions References Problems NEURAL NETWORK CONTROL OF UNCERTAIN NONLINEAR DISCRETE-TIME SYSTEMS WITH ACTUATOR NONLINEARITIES Background on Actuator Nonlinearities Reinforcement NN Learning Control with Saturation Uncertain Nonlinear System with Unknown Deadzone and Saturation Nonlinearities Adaptive NN Control of Nonlinear System with Unknown Backlash Conclusions References Problems Appendix 4.A Appendix 4.B Appendix 4.C Appendix 4.D OUTPUT FEEDBACK CONTROL OF STRICT FEEDBACK NONLINEAR MIMO DISCRETE-TIME SYSTEMS Class of Nonlinear Discrete-Time Systems Output Feedback Controller Design Weight Updates for Guaranteed Performance Conclusions References Problems Appendix 5.A Appendix 5.B NEURAL NETWORK CONTROL OF NONSTRICT FEEDBACK NONLINEAR SYSTEMS Introduction Adaptive NN Control Design Using State Measurements Output Feedback NN Controller Design Conclusions References Problems Appendix 6.A Appendix 6.B SYSTEM IDENTIFICATION USING DISCRETE-TIME NEURAL NETWORKS Identification of Nonlinear Dynamical Systems Identifier Dynamics for MIMO Systems NN Identifier Design Passivity Properties of the NN Conclusions References Problems DISCRETE-TIME MODEL REFERENCE ADAPTIVE CONTROL Dynamics of an mnth-Order Multi-Input and Multi-Output System NN Controller Design Projection Algorithm Conclusions References Problems NEURAL NETWORK CONTROL IN DISCRETE-TIME USING HAMILTON-JACOBI-BELLMAN FORMULATION Optimal Control and Generalized HJB Equation in Discrete-Time NN Least-Squares Approach Numerical Examples Conclusions References Problems NEURAL NETWORK OUTPUT FEEDBACK CONTROLLER DESIGN AND EMBEDDED HARDWARE IMPLEMENTATION Embedded Hardware-PC Real-Time Digital Control System SI Engine Test Bed Lean Engine Controller Design and Implementation EGR Engine Controller Design and Implementation Conclusions References Problems Appendix 10.A Appendix 10.B INDEX