Atjaunināt sīkdatņu piekrišanu

Neural Network Control of Nonlinear Discrete-Time Systems [Hardback]

4.00/5 (2 ratings by Goodreads)
(Missouri University of Science and Technology, Rolla, USA)
  • Formāts: Hardback, 622 pages, height x width: 229x152 mm, weight: 1310 g, 23 Tables, black and white; 171 Illustrations, black and white
  • Sērija : Automation and Control Engineering
  • Izdošanas datums: 24-Apr-2006
  • Izdevniecība: CRC Press Inc
  • ISBN-10: 0824726774
  • ISBN-13: 9780824726775
Citas grāmatas par šo tēmu:
  • Hardback
  • Cena: 288,80 €
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
  • Bibliotēkām
Neural Network Control of Nonlinear Discrete-Time SystemsPalielināt
  • Formāts: Hardback, 622 pages, height x width: 229x152 mm, weight: 1310 g, 23 Tables, black and white; 171 Illustrations, black and white
  • Sērija : Automation and Control Engineering
  • Izdošanas datums: 24-Apr-2006
  • Izdevniecība: CRC Press Inc
  • ISBN-10: 0824726774
  • ISBN-13: 9780824726775
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9780824726775.html
Keywords:
The increasing complexity of aerospace engineering, automotive technology, military, and industrial systems have rendered traditional feedback control systems increasingly less able to meet desired performance requirements, thus sparking interest in intelligent control systems using artificial neural networks, fuzzy logic, and genetic algorithms. In this book, Sarangapani (U. of Missouri) describes controller design in discrete-time using artificial neural networks (NN) since they "capture the parallel processing, adaptive, and learning capabilities of biological nervous systems." After providing the background on neural networks and discrete-time adaptive control, he presents chapters discussing neural network control of nonlinear systems and feedback linearization, neural network control of uncertain nonlinear discrete-time systems with actuator nonlinearities, output feedback control of strict feedback nonlinear multiple input/multiple output discrete-time systems, neural network control of nonstrict feedback nonlinear systems, system identification using discrete-time neural networks, discrete-time model reference adaptive control, neural network control in discrete-time using Hamilton-Jacobi-Bellman formulation, and neural network output feedback controller design and embedded hardware implementation. Annotation ©2007 Book News, Inc., Portland, OR (booknews.com)

Intelligent systems are a hallmark of modern feedback control systems. But as these systems mature, we have come to expect higher levels of performance in speed and accuracy in the face of severe nonlinearities, disturbances, unforeseen dynamics, and unstructured uncertainties. Artificial neural networks offer a combination of adaptability, parallel processing, and learning capabilities that outperform other intelligent control methods in more complex systems.

Borrowing from Biology
Examining neurocontroller design in discrete-time for the first time, Neural Network Control of Nonlinear Discrete-Time Systems presents powerful modern control techniques based on the parallelism and adaptive capabilities of biological nervous systems. At every step, the author derives rigorous stability proofs and presents simulation examples to demonstrate the concepts.

Progressive Development
After an introduction to neural networks, dynamical systems, control of nonlinear systems, and feedback linearization, the book builds systematically from actuator nonlinearities and strict feedback in nonlinear systems to nonstrict feedback, system identification, model reference adaptive control, and novel optimal control using the Hamilton-Jacobi-Bellman formulation. The author concludes by developing a framework for implementing intelligent control in actual industrial systems using embedded hardware.

Neural Network Control of Nonlinear Discrete-Time Systems fosters an understanding of neural network controllers and explains how to build them using detailed derivations, stability analysis, and computer simulations.
Chapter 1 Background on Neural Networks 1(74)
1.1 NN Topologies and Recall
2(22)
1.1.1 Neuron Mathematical Model
3(5)
1.1.2 Multilayer Perceptron
8(4)
1.1.3 Linear-in-the-Parameter NN
12(3)
1.1.3.1 Gaussian or Radial Basis Function Networks
12(1)
1.1.3.2 Cerebellar Model Articulation Controller Networks
13(2)
1.1.4 Dynamic NN
15(9)
1.1.4.1 Hopfield Network
15(4)
1.1.4.2 Generalized Recurrent NN
19(5)
1.2 Properties of NN
24(11)
1.2.1 Classification and Association
25(6)
1.2.1.1 Classification
25(3)
1.2.1.2 Association
28(3)
1.2.2 Function Approximation
31(4)
1.3 NN Weight Selection and Training
35(34)
1.3.1 Weight Computation
36(2)
1.3.2 Training the One-Layer NN — Gradient Descent
38(9)
1.3.2.1 Gradient Descent Tuning
39(3)
1.3.2.2 Epoch vs. Batch Updating
42(5)
1.3.3 Training the Multilayer NN — Backpropagation Tuning
47(20)
1.3.3.1 Background
49(2)
1.3.3.2 Derivation of the Backpropagation Algorithm
51(12)
1.3.3.3 Improvements on Gradient Descent
63(4)
1.3.4 Hebbian Tuning
67(2)
1.4 NN Learning and Control Architectures
69(2)
1.4.1 Unsupervised and Reinforcement Learning
69(1)
1.4.2 Comparison of the Two NN Control Architectures
70(1)
References
71(2)
Problems
73(2)
Chapter 2 Background and Discrete-Time Adaptive Control 75(64)
2.1 Dynamical Systems
75(4)
2.1.1 Discrete-Time Systems
75(1)
2.1.2 Brunovsky Canonical Form
76(1)
2.1.3 Linear Systems
77(2)
2.2 Mathematical Background
79(4)
2.2.1 Vector and Matrix Norms
79(3)
2.2.2 Continuity and Function Norms
82(1)
2.3 Properties of Dynamical Systems
83(5)
2.3.1 Stability
83(3)
2.3.2 Passivity
86(1)
2.3.3 Interconnections of Passive Systems
87(1)
2.4 Nonlinear Stability Analysis and Controls Design
88(14)
2.4.1 Lyapunov Analysis for Autonomous Systems
88(4)
2.4.2 Controller Design Using Lyapunov Techniques
92(5)
2.4.3 Lyapunov Analysis for Nonautonomous Systems
97(2)
2.4.4 Extensions of Lyapunov Techniques and Bounded Stability
99(3)
2.5 Robust Implicit STR
102(25)
2.5.1 Background
104(7)
2.5.1.1 Adaptive Control Formulation
105(1)
2.5.1.2 Stability of Dynamical Systems
106(5)
2.5.2 STR Design
111(5)
2.5.2.1 Structure of the STR and Error System Dynamics
111(1)
2.5.2.2 STR Parameter Updates
112(4)
2.5.3 Projection Algorithm
116(1)
2.5.4 Ideal Case: No Disturbances and No STR Reconstruction Errors
117(2)
2.5.5 Parameter-Tuning Modification for Relaxation of PE Condition
119(4)
2.5.6 Passivity Properties of the STR
123(4)
2.5.7 Conclusions
127(1)
References
127(2)
Problems
129(2)
Appendix 2.A
131(8)
Chapter 3 Neural Network Control of Nonlinear Systems and Feedback Linearization 139(126)
3.1 NN Control with Discrete-Time Tuning
142(55)
3.1.1 Dynamics of the mnth Order Multi-Input and Multi-Output Discrete-Time Nonlinear System
143(2)
3.1.2 One-Layer NN Controller Design
145(22)
3.1.2.1 NN Controller Design
146(1)
3.1.2.2 Structure of the NN and Error System Dynamics
147(1)
3.1.2.3 Weight Updates of the NN for Guaranteed Tracking Performance
148(7)
3.1.2.4 Projection Algorithm
155(1)
3.1.2.5 Ideal Case: No Disturbances and No NN Reconstruction Errors
156(4)
3.1.2.6 Parameter Tuning Modification for Relaxation of PE Condition
160(7)
3.1.3 Multilayer NN Controller Design
167(24)
3.1.3.1 Error Dynamics and NN Controller Structure
170(2)
3.1.3.2 Multilayer NN Weight Updates
172(7)
3.1.3.3 Projection Algorithm
179(6)
3.1.3.4 Multilayer NN Weight-Tuning Modification for Relaxation of PE Condition
185(6)
3.1.4 Passivity of the NN
191(6)
3.1.4.1 Passivity Properties of the Tracking Error System
191(1)
3.1.4.2 Passivity Properties of One-Layer NN
192(3)
3.1.4.3 Passivity of the Closed-Loop System
195(1)
3.1.4.4 Passivity of the Multilayer NN
196(1)
3.2 Feedback Linearization
197(3)
3.2.1 Input–Output Feedback Linearization Controllers
197(2)
3.2.1.1 Error Dynamics
198(1)
3.2.2 Controller Design
199(1)
3.3 NN Feedback Linearization
200(54)
3.3.1 System Dynamics and Tracking Problem
201(3)
3.3.2 NN Controller Design for Feedback Linearization
204(7)
3.3.2.1 NN Approximation of Unknown Functions
204(2)
3.3.2.2 Error System Dynamics
206(3)
3.3.2.3 Well-Defined Control Problem
209(1)
3.3.2.4 Controller Design
210(1)
3.3.3 One-Layer NN for Feedback Linearization
211(22)
3.3.3.1 Weight Updates Requiring PE
211(11)
3.3.3.2 Projection Algorithm
222(1)
3.3.3.3 Weight Updates not Requiring PE
223(10)
3.4 Multilayer NN for Feedback Linearization
233(21)
3.4.1 Weight Updates Requiring PE
234(2)
3.4.2 Weight Updates Not Requiring PE
236(18)
3.5 Passivity Properties of the NN
254(5)
3.5.1 Passivity Properties of the Tracking Error System
255(1)
3.5.2 Passivity Properties of One-Layer NN Controllers
256(1)
3.5.3 Passivity Properties of Multilayer NN Controllers
256(3)
3.6 Conclusions
259(1)
References
259(3)
Problems
262(3)
Chapter 4 Neural Network Control of Uncertain Nonlinear Discrete-Time Systems with Actuator Nonlinearities 265(78)
4.1 Background on Actuator Nonlinearities
266(8)
4.1.1 Friction
266(3)
4.1.1.1 Static Friction Models
267(1)
4.1.1.2 Dynamic Friction Models
268(1)
4.1.2 Deadzone
269(3)
4.1.3 Backlash
272(1)
4.1.4 Saturation
273(1)
4.2 Reinforcement NN Learning Control with Saturation
274(23)
4.2.1 Nonlinear System Description
276(1)
4.2.2 Controller Design Based on the Filtered Tracking Error
277(2)
4.2.3 One-Layer NN Controller Design
279(4)
4.2.3.1 The Strategic Utility Function
279(1)
4.2.3.2 Critic NN
280(1)
4.2.3.3 Action NN
281(2)
4.2.4 NN Controller without Saturation Nonlinearity
283(4)
4.2.5 Adaptive NN Controller Design with Saturation Nonlinearity
287(9)
4.2.5.1 Auxiliary System Design
287(1)
4.2.5.2 Adaptive NN Controller Structure with Saturation
288(1)
4.2.5.3 Closed-Loop System Stability Analysis
288(8)
4.2.6 Comparison of Tracking Error and Reinforcement Learning-Based Controls Design
296(1)
4.3 Uncertain Nonlinear System with Unknown Deadzone and Saturation Nonlinearities
297(12)
4.3.1 Nonlinear System Description and Error Dynamics
300(1)
4.3.2 Deadzone Compensation with Magnitude Constraints
300(4)
4.3.2.1 Deadzone Nonlinearity
300(1)
4.3.2.2 Compensation of Deadzone Nonlinearity
301(2)
4.3.2.3 Saturation Nonlinearities
303(1)
4.3.3 Reinforcement Learning NN Controller Design
304(5)
4.3.3.1 Error Dynamics
304(1)
4.3.3.2 Critic NN Design
305(1)
4.3.3.3 Main Result
306(3)
4.4 Adaptive NN Control of Nonlinear System with Unknown Backlash
309(10)
4.4.1 Nonlinear System Description
310(1)
4.4.2 Controller Design Using Filtered Tracking Error without Backlash Nonlinearity
311(1)
4.4.3 Backlash Compensation Using Dynamic Inversion
312(7)
4.5 Conclusions
319(1)
References
320(3)
Problems
323(2)
Appendix 4.A
325(4)
Appendix 4.B
329(1)
Appendix 4.C
330(8)
Appendix 4.D
338(5)
Chapter 5 Output Feedback Control of Strict Feedback Nonlinear MIMO Discrete-Time Systems 343(28)
5.1 Class of Nonlinear Discrete-Time Systems
345(1)
5.2 Output Feedback Controller Design
345(5)
5.2.1 Observer Design
346(1)
5.2.2 NN Controller Design
347(3)
5.2.2.1 Auxiliary Controller Design
348(1)
5.2.2.2 Controller Design with Magnitude Constraints
349(1)
5.3 Weight Updates for Guaranteed Performance
350(11)
5.3.1 Weights Updating Rule for the Observer NN
350(1)
5.3.2 Strategic Utility Function
351(1)
5.3.3 Critic NN Design
351(2)
5.3.4 Weight-Updating Rule for the Action NN
353(8)
5.4 Conclusions
361(1)
References
362(1)
Problems
363(1)
Appendix 5.A
364(2)
Appendix 5.B
366(5)
Chapter 6 Neural Network Control of Nonstrict Feedback Nonlinear Systems 371(52)
6.1 Introduction
371(3)
6.1.1 Nonlinear Discrete-Time Systems in Nonstrict Feedback Form
371(2)
6.1.2 Backstepping Design
373(1)
6.2 Adaptive NN Control Design Using State Measurements
374(18)
6.2.1 Tracking Error-Based Adaptive NN Controller Design
375(6)
6.2.1.1 Adaptive NN Backstepping Controller Design
375(3)
6.2.1.2 Weight Updates
378(3)
6.2.2 Adaptive Critic-Based NN Controller Design
381(11)
6.2.2.1 Critic NN Design
382(1)
6.2.2.2 Weight-Tuning Algorithms
383(9)
6.3 Output Feedback NN Controller Design
392(14)
6.3.1 NN Observer Design
394(2)
6.3.2 Adaptive NN Controller Design
396(4)
6.3.3 Weight Updates for the Output Feedback Controller
400(6)
6.4 Conclusions
406(1)
References
407(2)
Problems
409(2)
Appendix 6.A
411(8)
Appendix 6.B
419(4)
Chapter 7 System Identification Using Discrete-Time Neural Networks 423(24)
7.1 Identification of Nonlinear Dynamical Systems
425(1)
7.2 Identifier Dynamics for MIMO Systems
426(3)
7.3 NN Identifier Design
429(10)
7.3.1 Structure of the NN Identifier and Error System Dynamics
430(2)
7.3.2 Multilayer NN Weight Updates
432(7)
7.4 Passivity Properties of the NN
439(4)
7.5 Conclusions
443(1)
References
444(1)
Problems
444(3)
Chapter 8 Discrete-Time Model Reference Adaptive Control 447(26)
8.1 Dynamics of an mnth-Order Multi-Input and Multi-Output System
448(3)
8.2 NN Controller Design
451(9)
8.2.1 NN Controller Structure and Error System Dynamics
451(3)
8.2.2 Weight Updates for Guaranteed Tracking Performance
454(6)
8.3 Projection Algorithm
460(8)
8.4 Conclusions
468(1)
References
469(1)
Problems
470(3)
Chapter 9 Neural Network Control in Discrete-Time Using Hamilton–Jacobi–Bellman Formulation 473(38)
9.1 Optimal Control and Generalized HJB Equation in Discrete-Time
475(11)
9.2 NN Least-Squares Approach
486(4)
9.3 Numerical Examples
490(18)
9.4 Conclusions
508(1)
References
508(1)
Problems
509(2)
Chapter 10 Neural Network Output Feedback Controller Design and Embedded Hardware Implementation 511(84)
10.1 Embedded Hardware-PC Real-Time Digital Control System
512(2)
10.1.1 Hardware Description
512(2)
10.1.2 Software Description
514(1)
10.2 SI Engine Test Bed
514(9)
10.2.1 Engine-PC Interface Hardware Operation
516(2)
10.2.2 PC Operation
518(2)
10.2.3 Timing Specifications for Controller
520(1)
10.2.4 Software Implementation
521(2)
10.3 Lean Engine Controller Design and Implementation
523(24)
10.3.1 Engine Dynamics
526(2)
10.3.2 NN Observer Design
528(2)
10.3.3 Adaptive NN Output Feedback Controller Design
530(7)
10.3.3.1 Adaptive NN Backstepping Design
531(4)
10.3.3.2 Weight Updates for Guaranteed Performance
535(2)
10.3.4 Simulation of NN Controller C Implementation
537(2)
10.3.5 Experimental Results
539(8)
10.4 EGR Engine Controller Design and Implementation
547(16)
10.4.1 Engine Dynamics with EGR
549(2)
10.4.2 NN Observer Design
551(2)
10.4.3 Adaptive Output Feedback EGR Controller Design
553(6)
10.4.3.1 Error Dynamics
554(3)
10.4.3.2 Weight Updates for Guaranteed Performance
557(2)
10.4.4 Numerical Simulation on
559(4)
10.5 Conclusions
563(1)
References
564(1)
Problems
565(1)
Appendix 10.A
566(4)
Appendix 10.B
570(25)
Index 595


Sarangapani, Jagannathan