This book will sell because it presents interesting theoretical results to the academic control researcher and it shows those practising in the field of industrial control how to create better and cheaper models of the processes and systems with which they are concerned.

COMPLEX NONLINEAR SYSTEMS ARE WIDESPREAD - THE READER WILL BE ABLE TO TREAT THEM AS SIMPLER LINEAR SYSTEMS. THESE ARE EASIER AND LESS EXPENSIVE TO DEAL WITH. THE READER WILL BE MADE AWARE OF THE MOST UP-TO-DATE RESEARCH IN THE APPLICATION OF NEURAL NETWORKS TO NONLINEAR CONTROL SYSTEMS. Includes supplementary material: sn.pub/extras

Klappentext

Using relevant mathematical proofs and case studies illustrating design and application issues, this book demonstrates this powerful technique in the light of research on neural networks, which allow the identification of nonlinear models without the complicated and costly development of models based on physical laws.

Inhalt

1. Introduction.- 2. Fundamental Concepts.- 3. Introduction to Feedback Linearisation.- 4. Dynamic Neural Networks.- 5. Nonlinear System Approximation Using Dynamic Neural Networks.- 6. Feedback Linearisation Using Dynamic Neural Networks.- 7. Case Studies.- References.