Abstract
This paper presents an adaptive neural net controller for controlling given plants which are unknown. In the neural net structure, a two-layered network is used to emulate the unknown plant dynamics, and another two-layer neural network, which is the inverse of the estimator, is used to generate the control action on-line. A modified Widrow-Hoff delta rule is adopted as a learning algorithm to minimize the error between the real plant response and the output of the estimator. An effective learning method which is based on sliding motions is provided to tune the control action to improve the system performance and convergence. The major advantage of the proposed approach is that the lengthy training of the controller might be eliminated. The effectiveness of the proposed approach is illustrated through simulations of controlling a unstable plant and a normalized motor model with noise disturbances.
| Original language | English |
|---|---|
| Title of host publication | International IEEE/IAS Conference on Industrial Automation and Control: Emerging Technologies, Proceedings |
| Publisher | IEEE |
| Pages | 335-341 |
| Number of pages | 7 |
| Publication status | Published - 1995 |
| Event | Proceedings of the 1995 International IEEE/IAS Conference on Industrial Automation and Control: Emerging Technologies - Taipei, Taiwan Duration: 1995 May 22 → 1995 May 27 |
Other
| Other | Proceedings of the 1995 International IEEE/IAS Conference on Industrial Automation and Control: Emerging Technologies |
|---|---|
| City | Taipei, Taiwan |
| Period | 95/5/22 → 95/5/27 |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
Design of adaptive neural net controller. / Yeh, Zong Mu.
International IEEE/IAS Conference on Industrial Automation and Control: Emerging Technologies, Proceedings. IEEE, 1995. p. 335-341.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Design of adaptive neural net controller
AU - Yeh, Zong Mu
PY - 1995
Y1 - 1995
N2 - This paper presents an adaptive neural net controller for controlling given plants which are unknown. In the neural net structure, a two-layered network is used to emulate the unknown plant dynamics, and another two-layer neural network, which is the inverse of the estimator, is used to generate the control action on-line. A modified Widrow-Hoff delta rule is adopted as a learning algorithm to minimize the error between the real plant response and the output of the estimator. An effective learning method which is based on sliding motions is provided to tune the control action to improve the system performance and convergence. The major advantage of the proposed approach is that the lengthy training of the controller might be eliminated. The effectiveness of the proposed approach is illustrated through simulations of controlling a unstable plant and a normalized motor model with noise disturbances.
AB - This paper presents an adaptive neural net controller for controlling given plants which are unknown. In the neural net structure, a two-layered network is used to emulate the unknown plant dynamics, and another two-layer neural network, which is the inverse of the estimator, is used to generate the control action on-line. A modified Widrow-Hoff delta rule is adopted as a learning algorithm to minimize the error between the real plant response and the output of the estimator. An effective learning method which is based on sliding motions is provided to tune the control action to improve the system performance and convergence. The major advantage of the proposed approach is that the lengthy training of the controller might be eliminated. The effectiveness of the proposed approach is illustrated through simulations of controlling a unstable plant and a normalized motor model with noise disturbances.
UR - http://www.scopus.com/inward/record.url?scp=0029477360&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029477360&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0029477360
SP - 335
EP - 341
BT - International IEEE/IAS Conference on Industrial Automation and Control: Emerging Technologies, Proceedings
PB - IEEE
ER -