Differential neural networks for robust nonlinear control : identification, state estimation and trajectory tracking / / Alexander S. Poznyak, Edgar N. Sanchez, Wen Yu

• Autore: Poznyak Alexander S
• Pubblicazione: Singapore ; ; River Edge NJ, : World Scientific, c2001
• Edizione: 1st ed.
• Descrizione fisica: 1 online resource (455 p.)
• Disciplina: 006.32
• Soggetto topico: Neural networks (Computer science); Nonlinear control theory
• Altri autori: YuWen, profesor titular SanchezEdgar N
• Note generali: Includes index.
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Contents ; 0.1 Abstract ; 0.2 Preface ; 0.3 Acknowledgments ; 0.4 Introduction ; 0.4.1 Guide for the Readers ; 0.5 Notations ; I Theoretical Study ; 1 Neural Networks Structures ; 1.1 Introduction ; 1.2 Biological Neural Networks ; 1.3 Neuron Model ; 1.4 Neural Networks Structures 1.4.1 Single-Layer Feedforward Networks ; 1.4.2 Multilayer Feedforward Neural Networks ; 1.4.3 Radial Basis Function Neural Networks ; 1.4.4 Recurrent Neural Networks ; 1.4.5 Differential Neural Networks ; 1.5 Neural Networks in Control ; 1.5.1 Identification 1.5.2 Control ; 1.6 Conclusions ; 1.7 References ; 2 Nonlinear System Identification: Differential Learning ; 2.1 Introduction ; 2.2 Identification Error Stability Analysis for Simplest Differential Neural Networks without Hidden Layers ; 2.2.1 Nonlinear System and Differential Neural Network Model 2.2.2 Exact Neural Network Matching with Known Linear Part ; 2.2.3 Non-exact Neural Networks Modelling: Bounded Unmodelled Dynamics Case ; 2.2.4 Estimation of Maximum Value of Identification Error for Nonlinear Systems with Bounded Unmodelled Dynamics 2.3 Multilayer Differential Neural Networks for Nonlinear System On-line Identification ; 2.3.1 Multilayer Structure of Differential Neural Networks ; 2.3.2 Complete Model Matching Case
• Sommario/riassunto: This book deals with continuous time dynamic neural networks theory applied to the solution of basic problems in robust control theory, including identification, state space estimation (based on neuro-observers) and trajectory tracking. The plants to be identified and controlled are assumed to be <i>a priori</i> unknown but belonging to a given class containing internal unmodelled dynamics and external perturbations as well. The error stability analysis and the corresponding error bounds for different problems are presented. The effectiveness of the suggested approach is illustrated by its ap
• Titolo autorizzato: Differential neural networks for robust nonlinear control
• ISBN: 1-281-95673-2; 9786611956738; 981-281-129-X
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910816004603321
• Lo trovi qui: Univ. Federico II