Muutke küpsiste eelistusi

Neural Networks Modeling and Control: Applications for Unknown Nonlinear Delayed Systems in Discrete Time [Pehme köide]

(University of Guadalajara, Guadalajara, Jalisco, Mexico), Series edited by , (Dean of Technologies for Cyber-Human Interaction Division (CUCEI), Universidad de Guadalajara, Mexico), (University of Guadalajara, Guadal), (University of Guadalajara, Mexico)
  • Formaat: Paperback / softback, 158 pages, kõrgus x laius: 235x191 mm, kaal: 340 g, Approx. 240 illustrations; Illustrations, unspecified
  • Ilmumisaeg: 20-Jan-2020
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0128170786
  • ISBN-13: 9780128170786
  • Formaat: Paperback / softback, 158 pages, kõrgus x laius: 235x191 mm, kaal: 340 g, Approx. 240 illustrations; Illustrations, unspecified
  • Ilmumisaeg: 20-Jan-2020
  • Kirjastus: Academic Press Inc
  • ISBN-10: 0128170786
  • ISBN-13: 9780128170786

Neural Networks Modelling and Control: Applications for Unknown Nonlinear Delayed Systems in Discrete Time focuses on modeling and control of discrete-time unknown nonlinear delayed systems under uncertainties based on Artificial Neural Networks. First, a Recurrent High Order Neural Network (RHONN) is used to identify discrete-time unknown nonlinear delayed systems under uncertainties, then a RHONN is used to design neural observers for the same class of systems. Therefore, both neural models are used to synthesize controllers for trajectory tracking based on two methodologies: sliding mode control and Inverse Optimal Neural Control.

As well as considering the different neural control models and complications that are associated with them, this book also analyzes potential applications, prototypes and future trends.

  • Provide in-depth analysis of neural control models and methodologies
  • Presents a comprehensive review of common problems in real-life neural network systems
  • Includes an analysis of potential applications, prototypes and future trends
Dedication v
About the authors xi
Preface xiii
Acknowledgments xv
Chapter 1 Introduction
1(8)
1.1 Systems with delay
1(1)
1.2 System model
2(1)
1.3 Neural identification
2(1)
1.4 Neural state observers
2(1)
1.5 Neural block control
3(1)
1.5.1 Discrete sliding modes
3(1)
1.5.2 Inverse optimal control
3(1)
1.6 Problem statement
3(1)
1.7 Background
4(5)
1.7.1 Previous work on systems with time delay
4(2)
1.7.2 Advantages of our schemes
6(3)
Chapter 2 Mathematical preliminaries
9(8)
2.1 Time delay systems
9(2)
2.1.1 Delay
10(1)
2.1.2 System with time delay
10(1)
2.1.3 Nonlinear discrete system with time delays
11(1)
2.2 Recurrent high-order neural networks
11(6)
2.2.1 Discrete high-order recurrent neural networks
12(2)
2.2.2 Extended Kalman filter training
14(3)
Chapter 3 Neural identification using recurrent high-order neural networks for discrete nonlinear systems with unknown time delays
17(18)
3.1 Identification of the system
17(2)
3.2 Neural identification
19(1)
3.3 Identifier design based on recurrent high-order neural networks for uncertain nonlinear systems with delay
20(4)
3.4 Results of RHONN identifier
24(11)
3.4.1 Simulation results: Van der Pol oscillator
24(5)
3.4.2 Simulation results: differential robot
29(6)
Chapter 4 Identifier-controller scheme for uncertain nonlinear discrete systems with unknown time delays
35(36)
4.1 Identifier-controller scheme, sliding modes
35(8)
4.1.1 Block control with sliding modes
35(8)
4.2 Results of identifier-controller scheme, sliding modes
43(12)
4.2.1 Real-time results: linear induction motor with variant delays Test 4.1
44(4)
4.2.2 Real-time results: linear induction motor with variants delays Test 4.2
48(4)
4.2.3 Real-time results: linear induction motor with varying delays Test 4.3
52(3)
4.3 Identifier-controller scheme, inverse optimal control
55(2)
4.3.1 Inverse optimal control
56(1)
4.4 Results of identifier-controller scheme, inverse optimal control
57(14)
4.4.1 Application to a tank differential robot
57(3)
4.4.2 Real-time results: differential robot Test 4.4
60(3)
4.4.3 Real-time results: differential robot Test 4.5
63(8)
Chapter 5 Neural observer based on a RHONN for uncertain nonlinear discrete systems with unknown time delays
71(24)
5.1 Neural observer
71(1)
5.2 Full-order neural observer design based on a RHONN for discrete-time nonlinear systems with unknown delays
72(14)
5.2.1 Results of full-order RHONN observer
77(9)
5.3 Reduced-order neural observer design based on RHONNs for discrete-time nonlinear systems with unknown delays
86(1)
5.4 Results of reduced-order neural observer
87(8)
5.4.1 Simulation results
87(1)
5.4.2 Real-time results
88(7)
Chapter 6 Observer-controller scheme for uncertain nonlinear discrete systems with unknown delays
95(20)
6.1 RHONN observer-controller scheme for uncertain nonlinear discrete systems with unknown delays
95(20)
6.1.1 Simulation results: reduced-order RHONN observer-controller
104(5)
6.1.2 Real-time results: reduced RHONN observer-controller
109(6)
Chapter 7 Conclusions
115(2)
7.1 Conclusions
115(2)
Appendix A Artificial neural networks
117(8)
A.1 Biological neural networks
117(3)
A.1.1 Biological neuron
118(1)
A.1.2 Biological synapse
118(1)
A.1.3 Types of neurons
119(1)
A.2 Artificial neural networks
120(1)
A.3 Activation functions
121(1)
A.4 Classification of neural networks
121(2)
A.4.1 Single-layer neural networks
122(1)
A.4.2 Multilayer neural networks
122(1)
A.4.3 Recurrent neural networks
122(1)
A.5 Neural network training
123(2)
Appendix B Linear induction motor prototype
125(6)
B.1 Linear induction motor
125(3)
B.1.1 How a LIM works
125(1)
B.1.2 Model of a LIM
126(1)
B.1.3 Flux observer
127(1)
B.2 Linear induction motor prototype
128(3)
B.2.1 Electric drive by induction motor
128(1)
B.2.2 LIM prototype
129(2)
Appendix C Differential tracked robot prototype
131(4)
C.1 Tracked robot
131(2)
C.1.1 Tracked robot model
132(1)
C.2 Prototype
133(2)
Bibliography 135(4)
Index 139
Jorge D. Rios, was born in Guadalajara, Jalisco, Mexico, in 1985. He received the B.Sc. degree in Computer Engineering, in 2009, the M.Sc. and Ph. D. degrees in Electronics and Computer Engineering, in 2014 and 2017, respectively, from University of Guadalajara. He is in a Postdoctoral position at University of Guadalajara. His research interests center on neural control, nonlinear time-delay systems and their applications to electrical machines and robotics. Dr. Alma Y. Alanis received her M.Sc. and Ph.D. degrees in electrical engineering from the Advanced Studies and Research Center of the National Polytechnic Institute (CINVESTAV-IPN), Guadalajara, Mexico. Since 2008 she has been with University of Guadalajara, where she is currently a Dean of the Technologies for Cyber-Human Interaction Division, CUCEI. She is also member of the Mexican National Research System (SNI-2) and member of the Mexican Academy of Sciences. She has published papers in recognized International Journals and Conferences, besides eight international books. Dr. Alanis is a Senior Member of the IEEE and Subject Editor of the Journal of Franklin Institute, Section Editor at Open Franklin, Technical Editor at ASME/IEEE Transactions on Mechatronics, and Associate Editor at IEEE Transactions on Cybernetics, Intelligent Automation & Soft Computing and Engeenering Applications of Artifical Intelligence. Moreover, Dr. Alanis is currently serving on a number of IEEE and IFAC Conference Organizing Committees. In 2013 Dr. Alanis received the grant for women in science by L'Oreal-UNESCO-AMC-CONACYT-CONALMEX. In 2015, she received the Marcos Moshinsky Research Award. Her research interest centers on artificial neural networks, learning systems, intelligent control, and intelligent systems. Nancy Arana-Daniel received her B. Sc. Degree from the University of Guadalajara in 2000, and her M. Sc. And Ph.D. degrees in electric engineering with the special field in computer sicence from Research Center of the National Polytechnic Institute and Advanced Studies, CINVESTAV, in 2003 and 2007 respectively. She is currently a research fellow at the University of Guadalajara, in the Department of Computer Science Mxico, where she is working at the Laboratory of Intelligent Systems and the Research Center for Control Systems and Artificial Intelligence. She is IEEE Senior member and a member of National System of Researchers (SNI-1). She has published several papers in International Journals and Conferences and she has been technical manager of several projects that have been granted by the Nacional Council of Science and Technology (CONACYT). Also, se has collaborated in an international project granted by OPTREAT), She is Associated Editor of the Journal of Franklin Institute (Elsevier). Her research interests focus on applications of geometric algebra, geometric computing, machine learning, bio-inspired optimization, pattern recognition and robot navigation. Carlos Lpez-Franco received the Ph.D. degree in Computer Science in 2007 from the Center of Research and Advanced Studies, CINVESTAV, Mexico. He is currently a professor at the University of Guadalajara, Mexico, Computer Science Department, and member of the Intelligent Systems group. He is IEEE Senior member and a member of National System of Researchers) or SNI, level 1. His research interests include geometric algebra, computer vision, robotics and intelligent systems. Edgar N. Sanchez was born in 1949, in Sardinata, Colombia, South America. He obtained his BSEE major in Power Systems from Universidad Industrial de Santander (UIS, Bucaramanga, Colombia) in 1971, his MSEE from CINVESTAV-IPN (Advanced Studies and Research Center of the National Polytechnic Institute), his major in Automatic Control (Mexico City, Mexico) in 1974, and his Docteur Ingenieur degree in Automatic Control from Institut Nationale Polytechnique de Grenoble, France in 1980. In 1971, 1972, 1975 and 1976, he worked for different electrical engineering consulting companies in Bogota, Colombia. In 1974 he was a professor in the Electrical Engineering Department of UIS, Colombia. From January 1981 to November 1990, he worked as a researcher at the Electrical Research Institute, Cuernavaca, Mexico. He was a professor of the graduate program in electrical engineering at the Universidad Autonoma de Nuevo Leon (UANL), Monterrey, Mexico, from December 1990 to December 1996. Since January 1997, he has been with CINVESTAV-IPN (Guadalajara Campus, Mexico) as a Professor of Electrical Engineering in their graduate programs. His research interests are in neural networks and fuzzy logic as applied to automatic control systems. He has been the advisor of 21 Ph. D. theses and 40 M. Sc theses. He was granted a USA National Research Council Award as a research associate at NASA Langley Research Center, Hampton, Virginia, USA (January 1985 to March 1987). He is also a member of the Mexican National Research System (promoted to highest rank, III, in 2005), the Mexican Academy of Science and the Mexican Academy of Engineering. He has published four books, more than 150 technical papers in international journals and conferences, and has served as a reviewer for different international journals and conferences. He has also been a member of many international conferences, both IEEE and IFAC.