Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive

Faa Jeng Lin; Chih Hong Lin; Po Hung Shen

doi:10.1109/91.963761

Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive

Faa Jeng Lin, Chih Hong Lin, Po Hung Shen

Department of Electrical Engineering

Research output: Contribution to journal › Article › peer-review

248 Scopus citations

Abstract

A self-constructing fuzzy neural network (SCFNN) which is suitable for practical implementation is proposed in this study. The structure and the parameter learning phases are performed concurrently and online in the SCFNN. The structure learning is based on the partition of input space and the parameter learning is based on the supervised gradient decent method using a delta adaptation law. Several simulation and experimental results are provided to demonstrate the effectiveness of the proposed SCFNN control stratagem with the implementation of a permanent-magnet synchronous motor (PMSM) speed drive. Moreover, the simulation results of time varying and nonlinear disturbances are given to show the dynamic characteristics of the proposed controller over a broad range of operating conditions.

Original language	English
Pages (from-to)	751-759
Number of pages	9
Journal	IEEE Transactions on Fuzzy Systems
Volume	9
Issue number	5
DOIs	https://doi.org/10.1109/91.963761
State	Published - Oct 2001

Keywords

Fuzzy neural network
Gradient decent method
Self-constructing
Synchronous motor

Access to Document

10.1109/91.963761

Cite this

@article{ad0dae219b7f4f29905436b67deabb6c,

title = "Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive",

abstract = "A self-constructing fuzzy neural network (SCFNN) which is suitable for practical implementation is proposed in this study. The structure and the parameter learning phases are performed concurrently and online in the SCFNN. The structure learning is based on the partition of input space and the parameter learning is based on the supervised gradient decent method using a delta adaptation law. Several simulation and experimental results are provided to demonstrate the effectiveness of the proposed SCFNN control stratagem with the implementation of a permanent-magnet synchronous motor (PMSM) speed drive. Moreover, the simulation results of time varying and nonlinear disturbances are given to show the dynamic characteristics of the proposed controller over a broad range of operating conditions.",

keywords = "Fuzzy neural network, Gradient decent method, Self-constructing, Synchronous motor",

author = "Lin, {Faa Jeng} and Lin, {Chih Hong} and Shen, {Po Hung}",

note = "Funding Information: Manuscript received March 19, 2001; revised June 11, 2001. This work was supported by the National Science Council of Taiwan, R.O.C. under Grant NSC 89-2213-E-033-048. F.-J. Lin and P.-H. Shen are with the Department of Electrical Engineering, National Dong Hwa University, Hualien 974, Taiwan. C.-H. Lin is with the Department of Electrical Engineering, National Lien-Ho Institute of Technology, Miao Li 360, Taiwan. Publisher Item Identifier S 1063-6706(01)09625-4.",

year = "2001",

month = oct,

doi = "10.1109/91.963761",

language = "???core.languages.en_GB???",

volume = "9",

pages = "751--759",

journal = "IEEE Transactions on Fuzzy Systems",

issn = "1063-6706",

number = "5",

}

TY - JOUR

T1 - Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive

AU - Lin, Faa Jeng

AU - Lin, Chih Hong

AU - Shen, Po Hung

N1 - Funding Information: Manuscript received March 19, 2001; revised June 11, 2001. This work was supported by the National Science Council of Taiwan, R.O.C. under Grant NSC 89-2213-E-033-048. F.-J. Lin and P.-H. Shen are with the Department of Electrical Engineering, National Dong Hwa University, Hualien 974, Taiwan. C.-H. Lin is with the Department of Electrical Engineering, National Lien-Ho Institute of Technology, Miao Li 360, Taiwan. Publisher Item Identifier S 1063-6706(01)09625-4.

PY - 2001/10

Y1 - 2001/10

N2 - A self-constructing fuzzy neural network (SCFNN) which is suitable for practical implementation is proposed in this study. The structure and the parameter learning phases are performed concurrently and online in the SCFNN. The structure learning is based on the partition of input space and the parameter learning is based on the supervised gradient decent method using a delta adaptation law. Several simulation and experimental results are provided to demonstrate the effectiveness of the proposed SCFNN control stratagem with the implementation of a permanent-magnet synchronous motor (PMSM) speed drive. Moreover, the simulation results of time varying and nonlinear disturbances are given to show the dynamic characteristics of the proposed controller over a broad range of operating conditions.

AB - A self-constructing fuzzy neural network (SCFNN) which is suitable for practical implementation is proposed in this study. The structure and the parameter learning phases are performed concurrently and online in the SCFNN. The structure learning is based on the partition of input space and the parameter learning is based on the supervised gradient decent method using a delta adaptation law. Several simulation and experimental results are provided to demonstrate the effectiveness of the proposed SCFNN control stratagem with the implementation of a permanent-magnet synchronous motor (PMSM) speed drive. Moreover, the simulation results of time varying and nonlinear disturbances are given to show the dynamic characteristics of the proposed controller over a broad range of operating conditions.

KW - Fuzzy neural network

KW - Gradient decent method

KW - Self-constructing

KW - Synchronous motor

UR - http://www.scopus.com/inward/record.url?scp=0035483867&partnerID=8YFLogxK

U2 - 10.1109/91.963761

DO - 10.1109/91.963761

M3 - 期刊論文

AN - SCOPUS:0035483867

SN - 1063-6706

VL - 9

SP - 751

EP - 759

JO - IEEE Transactions on Fuzzy Systems

JF - IEEE Transactions on Fuzzy Systems

IS - 5

ER -

Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive

Abstract

Keywords

Access to Document

Fingerprint

Cite this