Application of neural networks to adaptive control of nonlinear systems
This book investigates the ability of a neural network (NN) to learn how to control an unknown (nonlinear, in general) system, using data acquired on-line, that is during the process of attempting to exert control. Two algorithms are developed to train the neural network for real-time control applic...
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Taunton, Somerset, England New York
Research Studies Press J. Wiley
1997.
|
| Series: | UMIST Control Systems Centre series
4. |
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
MARC
| LEADER | 00000nam a2200000 a 4500 | ||
|---|---|---|---|
| 001 | 2862 | ||
| 003 | MY-KLNDU | ||
| 005 | 20241218051255.0 | ||
| 008 | s1997 enka bi 000 0 eng d | ||
| 020 | |a 0471972630 (Research Studies Press : hardback) | ||
| 020 | |a 0863802141 (J. Wiley : hardback) | ||
| 039 | 9 | |a 201407141746 |b zul |c 201403131128 |d shahrim |c 201403131124 |d shahrim |c 200910081316 |d VLOAD |y 200910081159 |z VLOAD | |
| 040 | |a UPNM | ||
| 090 | |a QA 76.87 |b .N49 1997 | ||
| 100 | 1 | |a Ng, G. W. |q (Gee Wah), | |
| 245 | 1 | 0 | |a Application of neural networks to adaptive control of nonlinear systems |c G.W. NG |
| 260 | |a Taunton, Somerset, England |b Research Studies Press |a New York |b J. Wiley |c 1997. | ||
| 300 | |a xxv, 198 p. |b ill. |c 24 cm | ||
| 490 | 1 | |a UMIST Control Systems Centre series |v 4. | |
| 504 | |a Includes bibliographical references and index | ||
| 505 | 0 | |a 1. Introduction -- 2. Network Structures and Learning Algorithms -- 3. Neural Networks Control Strategies -- 4. On-line BPM and LRLS Control Algorithms -- 5. Local Convergence and Stability Analysis -- 6. On-line IGLS Control Algorithm -- 7. Systems with Unknown and Varying Time-delays -- 8. Conclusions. | |
| 520 | |a This book investigates the ability of a neural network (NN) to learn how to control an unknown (nonlinear, in general) system, using data acquired on-line, that is during the process of attempting to exert control. Two algorithms are developed to train the neural network for real-time control applications. The first algorithm is known as Learning by Recursive Least Squares (LRLS) algorithm and the second algorithm is known as Integrated Gradient and Least Squares (IGLS) algorithm. The ability of these algorithms to train the NN controller for real-time control is demonstrated on practical applications and the local convergence and stability requirements of these algorithms are analysed. In addition, network topology, learning algorithms (particularly supervised learning) and neural network control strategies are presented. | ||
| 650 | 0 | |a Neural networks (Computer science). | |
| 650 | 0 | |a Adaptive control systems. | |
| 650 | 0 | |a Nonlinear control theory. | |
| 830 | 0 | |a UMIST Control Systems Centre series |v 4. | |
| 999 | |a vtls000002661 |c 2862 |d 2862 | ||