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 | |
|
|
1 | (8) |
|
|
1 | (1) |
|
|
2 | (1) |
|
1.3 Neural identification |
|
|
2 | (1) |
|
1.4 Neural state observers |
|
|
2 | (1) |
|
|
3 | (1) |
|
1.5.1 Discrete sliding modes |
|
|
3 | (1) |
|
1.5.2 Inverse optimal control |
|
|
3 | (1) |
|
|
3 | (1) |
|
|
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) |
|
|
9 | (2) |
|
|
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) |
|
|
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) |
|
|
87 | (1) |
|
|
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) |
|
|
115 | (2) |
|
|
115 | (2) |
|
Appendix A Artificial neural networks |
|
|
117 | (8) |
|
A.1 Biological neural networks |
|
|
117 | (3) |
|
|
118 | (1) |
|
|
118 | (1) |
|
|
119 | (1) |
|
A.2 Artificial neural networks |
|
|
120 | (1) |
|
|
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) |
|
|
125 | (1) |
|
|
126 | (1) |
|
|
127 | (1) |
|
B.2 Linear induction motor prototype |
|
|
128 | (3) |
|
B.2.1 Electric drive by induction motor |
|
|
128 | (1) |
|
|
129 | (2) |
|
Appendix C Differential tracked robot prototype |
|
|
131 | (4) |
|
|
131 | (2) |
|
C.1.1 Tracked robot model |
|
|
132 | (1) |
|
|
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.