A back-stepping neural network control scheme for PM synchronous motors

J. Wang; K. M. Tsang; Chow Norbert Cheung

doi:10.1109/PEDS.2003.1282975

A back-stepping neural network control scheme for PM synchronous motors

J. Wang, K. M. Tsang, Chow Norbert Cheung

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

Focusing on the seriously nonlinear problem and unknown or uncertain parameters, a backstepping control method based on neural networks is proposed to realize the multi-object position control of PM synchronous motors. Neural networks in the scheme are used to solve the contradiction between backstepping control and unmatched conditions of systems. A special weight online tuning method is proposed in this paper, and an off-line training phase is not required. The method does not require the system parameters to be exactly known, and the system is robust. The simulation results show that, the proposed method is effective.

Original language	English
Title of host publication	5th International Conference on Power Electronics and Drive Systems, PEDS 2003 - Proceedings
Publisher	IEEE
Pages	728-732
Number of pages	5
Volume	1
ISBN (Electronic)	0780378857
DOIs	https://doi.org/10.1109/PEDS.2003.1282975
Publication status	Published - 1 Jan 2003
Event	5th International Conference on Power Electronics and Drive Systems, PEDS 2003 - Novotel Apollo Hotel, Singapore, Singapore Duration: 17 Nov 2003 → 20 Nov 2003

Conference

Conference	5th International Conference on Power Electronics and Drive Systems, PEDS 2003
Country/Territory	Singapore
City	Singapore
Period	17/11/03 → 20/11/03

Keywords

Backstepping
Neural Networks
PMSM Position control

ASJC Scopus subject areas

Electrical and Electronic Engineering

More information

10.1109/PEDS.2003.1282975

Cite this

@inproceedings{c1bc837f941a48649a7cf4c102d28b1f,

title = "A back-stepping neural network control scheme for PM synchronous motors",

abstract = "Focusing on the seriously nonlinear problem and unknown or uncertain parameters, a backstepping control method based on neural networks is proposed to realize the multi-object position control of PM synchronous motors. Neural networks in the scheme are used to solve the contradiction between backstepping control and unmatched conditions of systems. A special weight online tuning method is proposed in this paper, and an off-line training phase is not required. The method does not require the system parameters to be exactly known, and the system is robust. The simulation results show that, the proposed method is effective.",

keywords = "Backstepping, Neural Networks, PMSM Position control",

author = "J. Wang and Tsang, {K. M.} and Cheung, {Chow Norbert}",

year = "2003",

month = jan,

day = "1",

doi = "10.1109/PEDS.2003.1282975",

language = "English",

volume = "1",

pages = "728--732",

booktitle = "5th International Conference on Power Electronics and Drive Systems, PEDS 2003 - Proceedings",

publisher = "IEEE",

address = "United States",

note = "5th International Conference on Power Electronics and Drive Systems, PEDS 2003 ; Conference date: 17-11-2003 Through 20-11-2003",

}

Wang, J, Tsang, KM & Cheung, CN 2003, A back-stepping neural network control scheme for PM synchronous motors. in 5th International Conference on Power Electronics and Drive Systems, PEDS 2003 - Proceedings. vol. 1, 1282975, IEEE, pp. 728-732, 5th International Conference on Power Electronics and Drive Systems, PEDS 2003, Singapore, Singapore, 17/11/03. https://doi.org/10.1109/PEDS.2003.1282975

A back-stepping neural network control scheme for PM synchronous motors. / Wang, J.; Tsang, K. M.; Cheung, Chow Norbert.
5th International Conference on Power Electronics and Drive Systems, PEDS 2003 - Proceedings. Vol. 1 IEEE, 2003. p. 728-732 1282975.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A back-stepping neural network control scheme for PM synchronous motors

AU - Wang, J.

AU - Tsang, K. M.

AU - Cheung, Chow Norbert

PY - 2003/1/1

Y1 - 2003/1/1

N2 - Focusing on the seriously nonlinear problem and unknown or uncertain parameters, a backstepping control method based on neural networks is proposed to realize the multi-object position control of PM synchronous motors. Neural networks in the scheme are used to solve the contradiction between backstepping control and unmatched conditions of systems. A special weight online tuning method is proposed in this paper, and an off-line training phase is not required. The method does not require the system parameters to be exactly known, and the system is robust. The simulation results show that, the proposed method is effective.

AB - Focusing on the seriously nonlinear problem and unknown or uncertain parameters, a backstepping control method based on neural networks is proposed to realize the multi-object position control of PM synchronous motors. Neural networks in the scheme are used to solve the contradiction between backstepping control and unmatched conditions of systems. A special weight online tuning method is proposed in this paper, and an off-line training phase is not required. The method does not require the system parameters to be exactly known, and the system is robust. The simulation results show that, the proposed method is effective.

KW - Backstepping

KW - Neural Networks

KW - PMSM Position control

UR - http://www.scopus.com/inward/record.url?scp=84961637020&partnerID=8YFLogxK

U2 - 10.1109/PEDS.2003.1282975

DO - 10.1109/PEDS.2003.1282975

M3 - Conference article published in proceeding or book

VL - 1

SP - 728

EP - 732

BT - 5th International Conference on Power Electronics and Drive Systems, PEDS 2003 - Proceedings

PB - IEEE

T2 - 5th International Conference on Power Electronics and Drive Systems, PEDS 2003

Y2 - 17 November 2003 through 20 November 2003

ER -

A back-stepping neural network control scheme for PM synchronous motors

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this