T.H. Lee – författare

While neural network control has been successfully applied in various practical applications, many important issues, such as stability, robustness, and performance, have not been extensively researched for neural adaptive systems. This text offers a study of stable adaptive control designs using approximation-based techniques, and presents analysis for system stability and control performance. Both linearly parameterized and multi-layer neural networks (NN) are discussed and employed in the design of adaptive NN control systems for completeness. In addition, the developed design methodologies are not only applied to typical example systems, but also to real application-oriented systems, such as the variable length pendulum system, the underactuated inverted pendulum system and nonaffine nonlinear chemical processes (CSTR).

This volume contains the proceedings for the second annual Maple Summer Workshop and Symposium (MSWS '93) held at the University of Michigan, Ann Arbor, on June 28-30, 1993. The goal of this international conference was to encourage innovative applications of the Maple V mathematical computation system. Papers were presented on a wide range of application areas by authors from many countries including USA, Canada, France, and Japan.The papers in this collection are organized into four subject areas: Maple V in Education - innovative use of Maple V in mathematics, science, and engineering education; Maple V in Mathematics - methods to efficiently solve difficult mathematical problems, topics include polynomial theory, matrix operations, and statistics; Maple V in Science and Engineering, Part A, Modelling and simulation - using Maple V to derive, solve, and analyse equations that model complex physical systems, application areas include dynamical systems, molecular chemistry, and biostatistics; Maple V in Science and Engineering, Part B, Design - the development of systems and applications to assist in the design process, topics include Computer Aided Design (CAD), and Very Large Scale Integration (VLSI).

While neural network control has been successfully applied in various practical applications, many important issues, such as stability, robustness, and performance, have not been extensively researched for neural adaptive systems. Motivated by the need for systematic neural control strategies for nonlinear systems, Stable Adaptive Neural Network Control offers an in-depth study of stable adaptive control designs using approximation-based techniques, and presents rigorous analysis for system stability and control performance. Both linearly parameterized and multi-layer neural networks (NN) are discussed and employed in the design of adaptive NN control systems for completeness. Stable adaptive NN control has been thoroughly investigated for several classes of nonlinear systems, including nonlinear systems in Brunovsky form, nonlinear systems in strict-feedback and pure-feedback forms, nonaffine nonlinear systems, and a class of MIMO nonlinear systems.In addition, the developed design methodologies are not only applied to typical example systems, but also to real application-oriented systems, such as the variable length pendulum system, the underactuated inverted pendulum system and nonaffine nonlinear chemical processes (CSTR).

Recent years have seen a rapid development of neural network control tech­ niques and their successful applications. Numerous simulation studies and actual industrial implementations show that artificial neural network is a good candidate for function approximation and control system design in solving the control problems of complex nonlinear systems in the presence of different kinds of uncertainties. Many control approaches/methods, reporting inventions and control applications within the fields of adaptive control, neural control and fuzzy systems, have been published in various books, journals and conference proceedings. In spite of these remarkable advances in neural control field, due to the complexity of nonlinear systems, the present research on adaptive neural control is still focused on the development of fundamental methodologies. From a theoretical viewpoint, there is, in general, lack of a firmly mathematical basis in stability, robustness, and performance analysis of neural network adaptive control systems. This book is motivated by the need for systematic design approaches for stable adaptive control using approximation-based techniques. The main objec­ tives of the book are to develop stable adaptive neural control strategies, and to perform transient performance analysis of the resulted neural control systems analytically. Other linear-in-the-parameter function approximators can replace the linear-in-the-parameter neural networks in the controllers presented in the book without any difficulty, which include polynomials, splines, fuzzy systems, wavelet networks, among others. Stability is one of the most important issues being concerned if an adaptive neural network controller is to be used in practical applications.