Muutke küpsiste eelistusi

Adaptive Neural Network Control Of Robotic Manipulators [Kõva köide]

(Nus, S'pore), (Nus, S'pore), (Univ Of Southampton, Uk)
Teised raamatud teemal:
Adaptive Neural Network Control Of Robotic ManipulatorsSuurem pilt
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9789810234522.html
Recently, there has been considerable research interest in neural network control of robots, and satisfactory results have been obtained in solving some of the special issues associated with the problems of robot control in an on-and-off fashion. This book is dedicated to issues on adaptive control of robots based on neural networks. The text has been carefully tailored to (i) give a comprehensive study of robot dynamics, (ii) present structured network models for robots, and (iii) provide systematic approaches for neural network based adaptive controller design for rigid robots, flexible joint robots, and robots in constraint motion. Rigorous proof of the stability properties of adaptive neural network controllers is provided. Simulation examples are also presented to verify the effectiveness of the controllers, and practical implementation issues associated with the controllers are also discussed.
1 Introduction
1(8)
1.1 Introduction
1(4)
1.2 Notation
5(1)
1.3 Outline of the Book
6(3)
2 Mathematical Background
9(28)
2.1 Introduction
9(1)
2.2 Mathematical Preliminaries
9(5)
2.2.1 Norms for Vectors and Signals
10(1)
2.2.2 Norms for Functions
11(3)
2.3 Norms for Operators and Systems
14(3)
2.4 Properties of Matrix
17(2)
2.5 Properties of Sign Functions
19(3)
2.5.1 Discontinuous Functions
19(1)
2.5.2 Gains of Switching Functions
20(1)
2.5.3 Symmetric Positive Definite Matrix
21(1)
2.6 Concepts of Stability
22(5)
2.6.1 Autonomous Systems
25(1)
2.6.2 Non-Autonomous Systems
26(1)
2.7 Lyapunov Stability Theorem
27(2)
2.8 Invariant Set Theorems
29(1)
2.9 Useful Stability Results
30(7)
2.9.1 BIBO Stability
30(1)
2.9.2 Linear Systems
30(3)
2.9.3 Non-linear Systems
33(2)
2.9.4 Feedback Linearisation
35(1)
2.9.5 Singular Perturbation
35(2)
3 Dynamic Modelling of Robots
37(28)
3.1 Introduction
37(1)
3.2 Lagrange-Euler Equations
38(4)
3.2.1 Method of Virtual Displacement
38(4)
3.3 Lagrange-Euler Formulation of Robots
42(7)
3.3.1 Denavit-Hartenberg Convention
43(1)
3.3.2 Kinetic Energy of Robots
43(3)
3.3.3 Potential Energy of Robots
46(1)
3.3.4 Lagrangian Equations of Robots
46(2)
3.3.5 Hamiltonian Formulation
48(1)
3.4 Properties of Dynamic Equations
49(6)
3.5 Cartesian Space Dynamics
55(1)
3.6 Dynamics of Example Robots
56(8)
3.6.1 Planar Two-Link Manipulator
56(3)
3.6.2 Five-Bar Linkage Robot
59(3)
3.6.3 Three DOF robot
62(2)
3.7 Conclusion
64(1)
4 Structured Network Modelling of Robots
65(40)
4.1 Introduction
65(2)
4.2 Neural Network Approximations
67(12)
4.2.1 GL Matrix and Operator
75(3)
4.2.2 Permutation Operator "XXX"
78(1)
4.2.3 Validity of NN Modelling
78(1)
4.3 Dynamic Neural Network Modelling
79(6)
4.4 Dynamic Modelling Based on Static Neural Networks
85(6)
4.5 Neural Network Modelling of Task Space Dynamics
91(1)
4.6 Parametric Network Modelling
92(10)
4.7 Conclusion
102(3)
5 Adaptive Neural Network Control of Robots
105(78)
5.1 Introduction
105(1)
5.2 Dynamic Compensator Design
106(3)
5.3 Unified Adaptive Controller Based on Passivity
109(12)
5.3.1 Different Control Laws
113(4)
5.3.2 Passive Parameter Estimators
117(3)
5.3.3 Robust Parameter Adaptation
120(1)
5.4 Dynamic NN Based Adaptive Control
121(26)
5.4.1 Issues of Bounded Neural Network Errors
126(2)
5.4.2 Simulation Study
128(3)
5.4.3 Experiments on a Gyro-Mirror System
131(16)
5.5 Static NN Based Adaptive Control
147(14)
5.5.1 Simulation Example
155(6)
5.6 Parametric Network Based Adaptive Control
161(21)
5.6.1 Simulation Example
166(6)
5.6.2 Experimental Study
172(10)
5.7 Conclusion
182(1)
6 Neural Network Model Reference Adaptive Control
183(46)
6.1 Introduction
183(3)
6.2 Neural Network MRAC for Feedback Linearisable Systems
186(11)
6.2.1 Feedback Linearisation Control
186(3)
6.2.2 Robust Adaptive Neural Network FLC
189(8)
6.3 Application to Rigid Body Robots
197(7)
6.4 MRAC Based on Passivity
204(13)
6.5 Adaptive NN Model Matching Control
217(9)
6.6 Conclusion
226(3)
7 Flexible Joint Robots
229(38)
7.1 Introduction
229(2)
7.2 Dynamic model of Flexible Joint Robots
231(4)
7.3 Singularly Perturbed Model
235(8)
7.3.1 Singularly Perturbed Model I
235(3)
7.3.2 Singularly Perturbed Model II
238(5)
7.4 Adaptive Neural Network Composite Control
243(8)
7.4.1 Adaptive Neural Network Control I
244(1)
7.4.2 Adaptive Neural Network Control II
245(1)
7.4.3 Simulation Study
246(5)
7.5 Adaptive NN Feedback Linearization Control
251(14)
7.5.1 Control Formulation
251(7)
7.5.2 Simulation Study
258(7)
7.6 Conclusion
265(2)
8 Task Space and Force Control
267(60)
8.1 Introduction
267(3)
8.2 Task Space Position Control
270(10)
8.3 Impedance Control
280(7)
8.3.1 Problem Formulation
281(1)
8.3.2 Adaptive NN Impedance Control
282(2)
8.3.3 Simulation Example
284(3)
8.4 Constrained Motion Control
287(12)
8.4.1 Constrained Dynamics
291(2)
8.4.2 Applications of Adaptive Neural Networks
293(4)
8.4.3 Simulation Example
297(2)
8.5 Co-ordinated Control of Multiple Robots
299(18)
8.5.1 Dynamics of Co-ordinated Manipulators
304(4)
8.5.2 Controller Formulation
308(5)
8.5.3 Simulation Example
313(4)
8.6 Conclusion
317(10)
Bibliography 327(18)
A Computer Simulation 345(8)
A.1 State-Space Representation 346(2)
A.2 Adaptive Runge-Kutta-Merson Method 348(5)
B Simulation Software in C 353(26)
B.1 Main File: main.c 354(4)
B.2 Control Law File: control.c 358(10)
B.3 Desired Trajectory File: path.c 368(1)
B.4 Adaptive RKM File: adapRKM.c 369(3)
B.5 Dynamic Equation File: robot.c 372(2)
B.6 Utility File: util.c 374(3)
B.7 User Header File: user.h 377(1)
B.8 Input Data File: init.dat 378(1)
Index 379