Discrete-Time Recurrent Neural Control

The book presents recent advances in the theory of neural control for discrete-time nonlinear systems with multiple inputs and multiple outputs. It provides solutions for the output trajectory tracking problem of unknown nonlinear systems based on sliding modes and inverse optimal control scheme.

Section I Analyses Chapter 1 Introduction 1.1 Preliminaries 1.2 Motivation 1.3 Objectives 1.4 Book Structure 1.5 Notation 1.6 Acronyms Chapter 2 Mathematical Preliminaries 2.1 Optimal Control 2.2 Lyapunov Stability 2.3 Robust Stability Analysis 2.4 Passivity 2.5 Discrete-time High Order Neural Networks 2.6 The EKF Training Algorithm 2.7 Separation Principle for Discrete-time Nonlinear Systems Chapter 3 Discrete Time Neural Block Control 3.1 Identification 3.2 Illustrative example 3.3 Neural Block Controller Design 3.4 Applications 3.5 Conclusions Chapter 4 Neural Optimal Control 4.1 Inverse Optimal Control via CLF 4.2 Robust Inverse Optimal Control 4.3 Trajectory Tracking Inverse Optimal Control 4.4 CLF-based Inverse Optimal Control for a Class of Nonlinear Positive Systems 4.5 Speed-Gradient for the Inverse Optimal Control 4.6 Speed-Gradient Algorithm for Trajectory Tracking 4.7 Trajectory Tracking for Systems in Block-Control Form 4.8 Neural Inverse Optimal Control 4.9 Block-Control Form: A Nonlinear Systems Particular Class 4.10 Conclusions Section II Real-time Applications Chapter 5 Induction motors 5.1 Neural Identifier 5.2 Discrete-time super-twisting observer 5.3 Neural Sliding Modes Block Control 5.4 Neural Inverse Optimal Control 5.5 Real time Implementation 5.6 Prototype 5.7 Conclusions Chapter 6 Doubly Fed Induction Generator 6.1 Neural Identifiers 6.2 Neural Sliding Modes Block Control 6.3 Neural Inverse Optimal Control 6.4 Implementation on a Wind Energy Testbed 6.5 Conclusions Chapter 7 Conclusions