Application of Neural Networks to Adaptive Control of Nonlinear Systems (Hardcover) by G W Ng

9780863802140. New condition. Hard cover. Language: English. Pages: 224. Sewn binding. Cloth over boards. 224 p. Contains: Illustrations. Umist Control Systems Centre Series, 4. 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 Algorithm (IGLS). The ability of these algorithms for training the NN controller for real-time control is demonstrated on practical applications; the local convergence and stability requirements of the 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.