Neural Network Based Adaptive Control Of Uncertain And Unknown Nonlinear Systems

The focus of this book is the application of artificial neural networks in uncertain dynamical systems. It explains how to use neural networks in concert with adaptive techniques for system identification, state estimation, and control problems. The authors begin with a brief historical overview of adaptive control, followed by a review of mathematical preliminaries. In the subsequent chapters, they present several neural network-based control schemes. Each chapter starts with a concise introduction to the problem under study, and a neural network-based control strategy is designed for the simplest case scenario. After these designs are discussed, different practical limitations (i.e., saturation constraints and unavailability of all system states) are gradually added, and other control schemes are developed based on the primary scenario. Through these exercises, the authors present structures that not only provide mathematical tools for navigating control problems, but also supply solutions that are pertinent to real-life systems.

The objectives of this research effort were to exploit recent advances in neural network (NN) based adaptive control, with the goal of being able to treat a very general class of nonlinear system, for which the dynamics are not only uncertain, but may in fact be unknown except for minimal structural information, such as the relative degree of the regulated output variables. We were particularly interested in designing adaptive control systems that are robust with respect to both parametric uncertainty and unmodeled dynamics. Extensions to decentralized control were also of interest. In addition, we placed a high priority on transition opportunities in aircraft flight control, control of flows, control of flexible space structures, and control of aeroelastic wings.

Our main accomplishment this past year has been to finalize and apply two approaches to output feedback adaptive control. The first is a direct adaptive approach, while the second uses a new error state observe. Both approaches overcome the limitation of earlier adaptive state observer based methods, which require that the order of the plant be known, and impose severe restrictions on the relative degree of regulated output variables. Within this context, we also have continued to exploit our approach for adaptive hedging' of actuator limits, which was the highlight of last year's report. We have also made some progress in the area of decentralized adaptive control. Our most significant interactions have been with NASA Marshall, NASA Ames, Wright Patterson AFB, Eglin AFB, Boeing and Lockheed.

Adaptive Identification and Control of Uncertain Systems with Nonsmooth Dynamics reports some of the latest research on modeling, identification and adaptive control for systems with nonsmooth dynamics (e.g., backlash, dead zone, friction, saturation, etc). The authors present recent research results for the modelling and control designs of uncertain systems with nonsmooth dynamics, such as friction, dead-zone, saturation and hysteresis, etc., with particular applications in servo systems. The book is organized into 19 chapters, distributed in five parts concerning the four types of nonsmooth characteristics, namely friction, dead-zone, saturation and hysteresis, respectively. Practical experiments are also included to validate and exemplify the proposed approaches. This valuable resource can help both researchers and practitioners to learn and understand nonlinear adaptive control designs. Academics, engineers and graduate students in the fields of electrical engineering, control systems, mechanical engineering, applied mathematics and computer science can benefit from the book. It can be also used as a reference book on adaptive control for servo systems for students with some background in control engineering. Explains the latest research outputs on modeling, identification and adaptive control for systems with nonsmooth dynamics Provides practical application and experimental results for robotic systems, and servo motors

Thema dieses Buches ist die Anwendung neuronaler Netze und Fuzzy-Logic-Methoden zur Identifikation und Steuerung nichtlinear-dynamischer Systeme. Dabei werden fortgeschrittene Konzepte der herkömmlichen Steuerungstheorie mit den intuitiven Eigenschaften intelligenter Systeme kombiniert, um praxisrelevante Steuerungsaufgaben zu lösen. Die Autoren bieten viel Hintergrundmaterial; ausgearbeitete Beispiele und Übungsaufgaben helfen Studenten und Praktikern beim Vertiefen des Stoffes. Lösungen zu den Aufgaben sowie MATLAB-Codebeispiele sind ebenfalls enthalten.

This book presents the results of the second workshop on Neural Adaptive Control Technology, NACT II, held on September 9-10, 1996, in Berlin. The workshop was organised in connection with a three-year European-Union-funded Basic Research Project in the ESPRIT framework, called NACT, a collaboration between Daimler-Benz (Germany) and the University of Glasgow (Scotland).The NACT project, which began on 1 April 1994, is a study of the fundamental properties of neural-network-based adaptive control systems. Where possible, links with traditional adaptive control systems are exploited. A major aim is to develop a systematic engineering procedure for designing neural controllers for nonlinear dynamic systems. The techniques developed are being evaluated on concrete industrial problems from within the Daimler-Benz group of companies.The aim of the workshop was to bring together selected invited specialists in the fields of adaptive control, nonlinear systems and neural networks. The first workshop (NACT I) took place in Glasgow in May 1995 and was mainly devoted to theoretical issues of neural adaptive control. Besides monitoring further development of theory, the NACT II workshop was focused on industrial applications and software tools. This context dictated the focus of the book and guided the editors in the choice of the papers and their subsequent reshaping into substantive book chapters. Thus, with the project having progressed into its applications stage, emphasis is put on the transfer of theory of neural adaptive engineering into industrial practice. The contributors are therefore both renowned academics and practitioners from major industrial users of neurocontrol.

The authors here provide a detailed treatment of the design of robust adaptive controllers for nonlinear systems with uncertainties. They employ a new tool based on the ideas of system immersion and manifold invariance. New algorithms are delivered for the construction of robust asymptotically-stabilizing and adaptive control laws for nonlinear systems. The methods proposed lead to modular schemes that are easier to tune than their counterparts obtained from Lyapunov redesign.

Hybrid dynamical systems exhibit continuous and instantaneous changes, having features of continuous-time and discrete-time dynamical systems. Filled with a wealth of examples to illustrate concepts, this book presents a complete theory of robust asymptotic stability for hybrid dynamical systems that is applicable to the design of hybrid control algorithms--algorithms that feature logic, timers, or combinations of digital and analog components. With the tools of modern mathematical analysis, Hybrid Dynamical Systems unifies and generalizes earlier developments in continuous-time and discrete-time nonlinear systems. It presents hybrid system versions of the necessary and sufficient Lyapunov conditions for asymptotic stability, invariance principles, and approximation techniques, and examines the robustness of asymptotic stability, motivated by the goal of designing robust hybrid control algorithms. This self-contained and classroom-tested book requires standard background in mathematical analysis and differential equations or nonlinear systems. It will interest graduate students in engineering as well as students and researchers in control, computer science, and mathematics.

This book discusses methods and algorithms for the near-optimal adaptive control of nonlinear systems, including the corresponding theoretical analysis and simulative examples, and presents two innovative methods for the redundancy resolution of redundant manipulators with consideration of parameter uncertainty and periodic disturbances. It also reports on a series of systematic investigations on a near-optimal adaptive control method based on the Taylor expansion, neural networks, estimator design approaches, and the idea of sliding mode control, focusing on the tracking control problem of nonlinear systems under different scenarios. The book culminates with a presentation of two new redundancy resolution methods; one addresses adaptive kinematic control of redundant manipulators, and the other centers on the effect of periodic input disturbance on redundancy resolution. Each self-contained chapter is clearly written, making the book accessible to graduate students as well as academic and industrial researchers in the fields of adaptive and optimal control, robotics, and dynamic neural networks.