A self-adaptive RBF neural network classifier for transformer fault analysis

Ke Meng; Zhao Yang Dong; Dian Hui Wang; Kit Po Wong

doi:10.1109/TPWRS.2010.2040491

A self-adaptive RBF neural network classifier for transformer fault analysis

Ke Meng
, Zhao Yang Dong
, Dian Hui Wang
, Kit Po Wong

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

138 Citations (Scopus)

Abstract

A new hybrid self-adaptive training approach-based radial basis function (RBF) neural network for power transformer fault diagnosis is presented in this paper. The proposed method is able to generate RBF neural network models based on fuzzy c-means (FCM) and quantum-inspired particle swarm optimization (QPSO), which can automatically configure network structure and obtain model parameters. With these methods, the number of neuron, centers and radii of hidden layer activated functions, as well as output connection weights can be automatically calculated. This learning method is proved to be effective by applying the RBF neural network in the classification of five benchmark testing data sets, and power transformer fault data set. The results clearly demonstrated the improved classification accuracy compared with other alternatives and showed that it can be used as a reliable tool for power transformer fault analysis. © 2010 IEEE.

Original language	English
Article number	5418850
Pages (from-to)	1350-1360
Journal	IEEE Transactions on Power Systems
Volume	25
Issue number	3
DOIs	https://doi.org/10.1109/TPWRS.2010.2040491
Publication status	Published - Aug 2010
Externally published	Yes

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

Computational methods
particle swarm optimization
power transformer fault diagnosis
radial basis function (RBF) neural network

Access Output

10.1109/TPWRS.2010.2040491

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{456c528d41564d37b0beeb1e24d767c6,

title = "A self-adaptive RBF neural network classifier for transformer fault analysis",

abstract = "A new hybrid self-adaptive training approach-based radial basis function (RBF) neural network for power transformer fault diagnosis is presented in this paper. The proposed method is able to generate RBF neural network models based on fuzzy c-means (FCM) and quantum-inspired particle swarm optimization (QPSO), which can automatically configure network structure and obtain model parameters. With these methods, the number of neuron, centers and radii of hidden layer activated functions, as well as output connection weights can be automatically calculated. This learning method is proved to be effective by applying the RBF neural network in the classification of five benchmark testing data sets, and power transformer fault data set. The results clearly demonstrated the improved classification accuracy compared with other alternatives and showed that it can be used as a reliable tool for power transformer fault analysis. {\textcopyright} 2010 IEEE.",

keywords = "Computational methods, particle swarm optimization, power transformer fault diagnosis, radial basis function (RBF) neural network",

author = "Ke Meng and Dong, \{Zhao Yang\} and Wang, \{Dian Hui\} and Wong, \{Kit Po\}",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].",

year = "2010",

month = aug,

doi = "10.1109/TPWRS.2010.2040491",

language = "English",

volume = "25",

pages = "1350--1360",

journal = "IEEE Transactions on Power Systems",

issn = "0885-8950",

publisher = "IEEE",

number = "3",

}

TY - JOUR

T1 - A self-adaptive RBF neural network classifier for transformer fault analysis

AU - Meng, Ke

AU - Dong, Zhao Yang

AU - Wang, Dian Hui

AU - Wong, Kit Po

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2010/8

Y1 - 2010/8

N2 - A new hybrid self-adaptive training approach-based radial basis function (RBF) neural network for power transformer fault diagnosis is presented in this paper. The proposed method is able to generate RBF neural network models based on fuzzy c-means (FCM) and quantum-inspired particle swarm optimization (QPSO), which can automatically configure network structure and obtain model parameters. With these methods, the number of neuron, centers and radii of hidden layer activated functions, as well as output connection weights can be automatically calculated. This learning method is proved to be effective by applying the RBF neural network in the classification of five benchmark testing data sets, and power transformer fault data set. The results clearly demonstrated the improved classification accuracy compared with other alternatives and showed that it can be used as a reliable tool for power transformer fault analysis. © 2010 IEEE.

AB - A new hybrid self-adaptive training approach-based radial basis function (RBF) neural network for power transformer fault diagnosis is presented in this paper. The proposed method is able to generate RBF neural network models based on fuzzy c-means (FCM) and quantum-inspired particle swarm optimization (QPSO), which can automatically configure network structure and obtain model parameters. With these methods, the number of neuron, centers and radii of hidden layer activated functions, as well as output connection weights can be automatically calculated. This learning method is proved to be effective by applying the RBF neural network in the classification of five benchmark testing data sets, and power transformer fault data set. The results clearly demonstrated the improved classification accuracy compared with other alternatives and showed that it can be used as a reliable tool for power transformer fault analysis. © 2010 IEEE.

KW - Computational methods

KW - particle swarm optimization

KW - power transformer fault diagnosis

KW - radial basis function (RBF) neural network

UR - https://www.scopus.com/pages/publications/77954834842

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-77954834842&origin=recordpage

U2 - 10.1109/TPWRS.2010.2040491

DO - 10.1109/TPWRS.2010.2040491

M3 - RGC 21 - Publication in refereed journal

SN - 0885-8950

VL - 25

SP - 1350

EP - 1360

JO - IEEE Transactions on Power Systems

JF - IEEE Transactions on Power Systems

IS - 3

M1 - 5418850

ER -

A self-adaptive RBF neural network classifier for transformer fault analysis

Abstract

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this