dc.contributor.author |
Miya, WS
|
|
dc.contributor.author |
Mpanza, LJ
|
|
dc.contributor.author |
Marwala, T
|
|
dc.contributor.author |
Nelwamondo, Fulufhelo V
|
|
dc.date.accessioned |
2010-02-01T08:23:15Z |
|
dc.date.available |
2010-02-01T08:23:15Z |
|
dc.date.issued |
2008-10 |
|
dc.identifier.citation |
Miya, WS, Mpanza, LJ et al. 2008. Condition monitoring of oil-impregnated paper bushings using extension neural network, Gaussian mixture and hidden Markov models. IEEE International Conference on Systems, Man and Cybernetics (SMC 2008), 12-15 Oct 2008, Singapore, pp 1954-1959 |
en |
dc.identifier.isbn |
978-1-4244-2384-2 |
|
dc.identifier.uri |
http://hdl.handle.net/10204/3924
|
|
dc.description |
Copyright: 2008 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. |
en |
dc.description.abstract |
In this paper, a comparison between Extension Neural Network (ENN), Gaussian Mixture Model (GMM) and Hidden Markov model (HMM) is conducted for bushing condition monitoring. The monitoring process is a two-stage implementation of a classification method. The first stage detects whether the bushing is faulty or normal while the second stage classifies the fault. Experimentation is conducted using dissolve gas-in-oil analysis (DGA) data collected from bushings based on IEEEc57.104; IEC60599 and IEEE production rates methods for oil-impregnated paper (OIP) bushings. It is observed from experimentation that there is no major classification discrepancy between ENN and GMM for the detection stage with classification rates at 87.93% and 87.94% respectively, outperforming HMM which achieved 85.6%. Moreover, HMM fault diagnosis surpasses those of ENN and GMM with a classification of 100%. However, for diagnosis stage HMM outperforms both ENN and GMM with 100% classification rate. ENN and GMM have considerably faster training and classification time whilst HMM's training is time-consuming for both detection and diagnosis stages. |
en |
dc.language.iso |
en |
en |
dc.publisher |
Institute of Electrical and Electronics Engineers (IEEE) |
en |
dc.subject |
Condition monitoring |
en |
dc.subject |
Hidden markov models |
en |
dc.subject |
Transformer bushings |
en |
dc.subject |
Gaussian mixture models |
en |
dc.subject |
Extension neural networks |
en |
dc.title |
Condition monitoring of oil-impregnated paper bushings using extension neural network, Gaussian mixture and hidden Markov models |
en |
dc.type |
Conference Presentation |
en |
dc.identifier.apacitation |
Miya, W., Mpanza, L., Marwala, T., & Nelwamondo, F. V. (2008). Condition monitoring of oil-impregnated paper bushings using extension neural network, Gaussian mixture and hidden Markov models. Institute of Electrical and Electronics Engineers (IEEE). http://hdl.handle.net/10204/3924 |
en_ZA |
dc.identifier.chicagocitation |
Miya, WS, LJ Mpanza, T Marwala, and Fulufhelo V Nelwamondo. "Condition monitoring of oil-impregnated paper bushings using extension neural network, Gaussian mixture and hidden Markov models." (2008): http://hdl.handle.net/10204/3924 |
en_ZA |
dc.identifier.vancouvercitation |
Miya W, Mpanza L, Marwala T, Nelwamondo FV, Condition monitoring of oil-impregnated paper bushings using extension neural network, Gaussian mixture and hidden Markov models; Institute of Electrical and Electronics Engineers (IEEE); 2008. http://hdl.handle.net/10204/3924 . |
en_ZA |
dc.identifier.ris |
TY - Conference Presentation
AU - Miya, WS
AU - Mpanza, LJ
AU - Marwala, T
AU - Nelwamondo, Fulufhelo V
AB - In this paper, a comparison between Extension Neural Network (ENN), Gaussian Mixture Model (GMM) and Hidden Markov model (HMM) is conducted for bushing condition monitoring. The monitoring process is a two-stage implementation of a classification method. The first stage detects whether the bushing is faulty or normal while the second stage classifies the fault. Experimentation is conducted using dissolve gas-in-oil analysis (DGA) data collected from bushings based on IEEEc57.104; IEC60599 and IEEE production rates methods for oil-impregnated paper (OIP) bushings. It is observed from experimentation that there is no major classification discrepancy between ENN and GMM for the detection stage with classification rates at 87.93% and 87.94% respectively, outperforming HMM which achieved 85.6%. Moreover, HMM fault diagnosis surpasses those of ENN and GMM with a classification of 100%. However, for diagnosis stage HMM outperforms both ENN and GMM with 100% classification rate. ENN and GMM have considerably faster training and classification time whilst HMM's training is time-consuming for both detection and diagnosis stages.
DA - 2008-10
DB - ResearchSpace
DP - CSIR
KW - Condition monitoring
KW - Hidden markov models
KW - Transformer bushings
KW - Gaussian mixture models
KW - Extension neural networks
LK - https://researchspace.csir.co.za
PY - 2008
SM - 978-1-4244-2384-2
T1 - Condition monitoring of oil-impregnated paper bushings using extension neural network, Gaussian mixture and hidden Markov models
TI - Condition monitoring of oil-impregnated paper bushings using extension neural network, Gaussian mixture and hidden Markov models
UR - http://hdl.handle.net/10204/3924
ER -
|
en_ZA |