Application of Neural Networks to Adaptive Control of Nonlinear Systems (Umist Control Systems Centre Series, 4) - Hardcover

Ng, G. W.

Hardcover

ISBN 10: 0471972630 ISBN 13: 9780471972631

Publisher: John Wiley & Sons Inc, 1997

Synopsis

This book investigates the ability of a neural network (NN) to learn how to control an unknown (nonlinear, in general) system, using data acquired on-line, that is during the process of attempting to exert control. Two algorithms are developed to train the neural network for real-time control applications. The first algorithm is known as Learning by Recursive Least Squares (LRLS) algorithm and the second algorithm is known as Integrated Gradient and Least Squares (IGLS) algorithm. The ability of these algorithms for training the NN controller for real-time control is demonstrated on practical applications and the local convergence and stability requirements of these algorithms are analysed. In addition, network topology, learning algorithms (particularly supervised learning) and neural network control strategies including a new classification system for them, are presented.

About this title

Synopsis

This text investigates the ability of a neural network (NN) to learn how to control an unknown - generally nonlinear - system using data acquired on-line. The work presents real-time control applications, together with the theoretical analysis of algorithms developed to train neural networks. It provides: an analysis of local convergence and stability requirements of the two fast-learning algorithms developed by the author; a comprehensive survey of network topology and learning algorithms - particularly supervised learning; and a classification for NN control strategies. The book also analyzes and discusses various control strategies.

Edition details

• Publisher: John Wiley & Sons Inc
• Publication date: 1997
• ISBN 10: 0471972630
• ISBN 13: 9780471972631
• Binding: Hardcover
• Language: English
• Number of pages: 198