Neural Systems For Control.pdf

(2456 KB) Pobierz
Tbook.dvi
Neural Systems for Control
1
Omid M. Omidvar and David L. Elliott, Editors
February, 1997
1 This the complete book (but with different pagination) Neural Systems
for Control ,O.M.Omidvar and D. L. Elliott, editors, Copyright 1997 by
Academic Press, ISBN: 0125264305 and is posted with permission from Elsevier.
http://www.isr.umd.edu/ ∼ delliott/NeuralSystemsForControl.pdf
ii
Contents
Contributors
vii
Preface
xi
1Introduction: Neural Networks and Automatic Control 1
1 Control Systems ........................ 1
2WhatisaNeural Network? .................. 3
2Rein orcement Learning 7
1Introduction ........................... 7
2 on-Associative Reinforcement Learning ........... 8
3 ssociative Reinforcement Learning ............. 12
4 Sequential Reinforcement Learning .............. 20
5 Conclusion ........................... 26
6 eferences ............................ 27
3Neurocontrol in Sequence Recognition 31
1Introduction ........................... 31
2 MM Source Models ...................... 32
3 ecognition: Finding the Best Hidden Sequence ....... 33
4 Controlled Sequence Recognition ............... 34
5ASequential Event Dynamic Neural Network . ....... 42
6 eurocontrol in sequence recognition ............. 49
7 Observations and Speculations ................ 52
8 eferences ............................ 56
4ALearning Sensorimotor Map of Arm Movements: a Step
Toward Biological Arm Control 61
1Introduction ........................... 61
2Methods ............................. 63
3 imulation Results ....................... 71
4 iscussion ............................ 85
5 eferences ............................ 86
5Neuronal Modeling of the Baroreceptor Reflex with Appli-
cations in Process Modeling and Control 89
1Motivation ........................... 89
2 he Baroreceptor Vagal Reflex ................ 90
iv
3ANeuronal Model of the Baroreflex ............. 95
4 arallel Control Structures in the Baroreflex . . ....... 103
5 eural Computational Mechanisms for Process Modeling . . 116
6 Conclusionsand Future Work ................. 120
7 eferences ............................ 123
6Iden ification of Nonlinear Dynamical Systems Using Neu-
ral Networks 127
1Introduction ........................... 127
2Mathematical Preliminaries .................. 129
3 tate space models for identification ............. 136
4Identification using Input-Output Models . . . ....... 139
5 Conclusion ........................... 150
6 eferences ............................ 153
7N ural Network Control of Robot Arms and Nonlinear
Systems 157
1Introduction ........................... 157
2 ackground in Neural Networks, Stability, and Passivity . . 159
3 ynamics of Rigid Robot Arms ................ 162
4 NController for Robot Arms ................ 164
5 ssivity andStructurePropertiesofthe NN ........ 177
6 eural Networksfor Control of NonlinearSystems ..... 183
7 eural Network Control with Discrete-Time Tuning .... 188
8 Conclusion ........................... 203
9 eferences ............................ 203
8Neural Networks for Intelligent Sensors and Control —
Practical Issues and Some Solutions 207
1Introduction ........................... 207
2 haracteristicsofProcessData ................ 209
3 ata Pre-processing ...................... 211
4 ariable Selection ....................... 213
5 ffect of Collinearity on Neural Network Training ...... 215
6Integrating Neural Nets with Statistical Approaches .... 218
7 pplication to a Refinery Process ............... 221
8 Conclusions and Recommendations .............. 222
9 eferences ............................ 223
9Approximation of Time–Optimal Control for an Industrial
Production Plant with General Regression Neural Net-
work 227
1Introduction ........................... 227
2 escription of the Plant .................... 228
3M del of the Induction Motor Drive ............. 230
v
4 eneral Regression Neural Network .............. 231
5 Control Concept ........................ 234
6 Conclusion ........................... 241
7 eferences ............................ 242
10 Neuro-Control Design: Optimization Aspects 251
1Introduction ........................... 251
2 euro-Control Systems ..................... 252
3 Optimization Aspects ..................... 264
4 NC Design and Evolutionary Algorithm . . . ....... 268
5 Conclusions ........................... 270
6 eferences ............................ 272
11 Reconfigurable Neural Control in Precision Space Struc-
tural Platforms 279
1 Connectionist Learning System ................ 279
2 econfigurable Control ..................... 282
3 daptive Time-Delay Radial Basis Function Network .... 284
4 igenstructure Bidirectional Associative Memory ...... 287
5 ault Detection and Identification .............. 291
6 imulation Studies ....................... 293
7 Conclusion ........................... 297
8 eferences ............................ 297
12 Neural Approximations for Finite- and Infinite-Horizon Op-
timal Control 307
1Introduction ........................... 307
2 tatement of the finite–horizon optimal control problem . . 309
3 eduction of the functional optimization Problem 1 to a
nonlinear programming problem ............... 310
4 pproximating properties of the neural control law ..... 313
5 olution of the nonlinear programming problem by the gra-
dientmethod .......................... 316
6 imulation results ....................... 319
7 tatements of the infinite-horizon optimal control problem
and of its receding-horizon approximation . . . ....... 324
8 tabilizing properties of the receding–horizon regulator . . . 327
9 he neural approximation for the receding–horizon regulator 330
10 A gradient algorithm for deriving the RH neural regulator
and simulation results ..................... 333
11 Conclusions ........................... 335
12 References ............................ 337
Index
341

Plik z chomika:

Inne pliki z tego folderu:

Inne foldery tego chomika:

Zgłoś jeśli naruszono regulamin