Transformer incipient fault prediction using combined artificial neural network and various particle swarm optimisation techniques

Illias, H.A. and Chai, X.R. and Abu Bakar, A.H. and Mokhlis, H. (2015) Transformer incipient fault prediction using combined artificial neural network and various particle swarm optimisation techniques. PLoS ONE, 10 (6). p. 16. ISSN 1932-6203

[img]
Preview
PDF (Transformer Incipient Fault Prediction Using Combined Artificial Neural Network and Various Particle Swarm Optimisation Techniques)
Transformer_Incipient_Fault_Prediction_Using_Combined_Artificial_Neural_Network.pdf - Published Version

Download (526kB)
Official URL: http://www.ncbi.nlm.nih.gov/pubmed/26103634

Abstract

It is important to predict the incipient fault in transformer oil accurately so that the maintenance of transformer oil can be performed correctly, reducing the cost of maintenance and minimise the error. Dissolved gas analysis (DGA) has been widely used to predict the incipient fault in power transformers. However, sometimes the existing DGA methods yield inaccurate prediction of the incipient fault in transformer oil because each method is only suitable for certain conditions. Many previous works have reported on the use of intelligence methods to predict the transformer faults. However, it is believed that the accuracy of the previously proposed methods can still be improved. Since artificial neural network (ANN) and particle swarm optimisation (PSO) techniques have never been used in the previously reported work, this work proposes a combination of ANN and various PSO techniques to predict the transformer incipient fault. The advantages of PSO are simplicity and easy implementation. The effectiveness of various PSO techniques in combination with ANN is validated by comparison with the results from the actual fault diagnosis, an existing diagnosis method and ANN alone. Comparison of the results from the proposed methods with the previously reported work was also performed to show the improvement of the proposed methods. It was found that the proposed ANN-Evolutionary PSO method yields the highest percentage of correct identification for transformer fault type than the existing diagnosis method and previously reported works.

Item Type: Article
Additional Information: ISI Document Delivery No.: CL4DD Times Cited: 0 Cited Reference Count: 32 Cited References: Abdullah MN, 2012, INT U POW ENG C UPEC, P1 Ahmed MR, 2013, MED C CONTR AUTOMAT, P584, DOI 10.1109/MED.2013.6608781 Andras P, 2012, PLOS ONE, V7, DOI 10.1371/journal.pone.0048710 Anonymous, C571042008 IEEE Bhattacharya SK, 1993, N AM POW S Changxin L, 2010, INT C GEN EV COMP, P8 Ding X, 1994, N AM POW S Garg H, 2013, ISA T, V52, P701, DOI 10.1016/j.isatra.2013.06.010 Gracia J, 2005, IEEE T POWER DELIVER, V20, P2389, DOI 10.1109/TPWRD.2005.855482 Guardado JL, 2001, IEEE T POWER DELIVER, V16, P643, DOI 10.1109/61.956751 Hamadneh N, 2013, PLOS ONE, V8, DOI 10.1371/journal.pone.0066080 Hammestrom P, 1993, IEEE SPECTRUM Hong-Tzer Yang, 1998, IEEE Transactions on Power Systems, V13, DOI 10.1109/59.708845 Hsu CC, 2009, ISA T, V48, P264, DOI 10.1016/j.isatra.2009.01.008 Huang YC, 2003, IEE P-SCI MEAS TECH, V150, P25, DOI 10.1049/ip-smt:20020454 Liu C, 2014, PLOS ONE, V9, DOI 10.1371/journal.pone.0097822 Malabanan DR, 2014, IEEE REG 10 C, P1 Mehta AK, 2013, 2013 INTERNATIONAL CONFERENCE ON POWER, ENERGY AND CONTROL (ICPEC), P181 Miranda V., 2002, IEEE PES TRANSM DIST, V2, P745, DOI DOI 10.1109/TDC.2002.1177567 Poultangari I, 2012, ISA T, V51, P641, DOI 10.1016/j.isatra.2012.06.001 Seifeddine S, 2012, INT C REN EN VEH TEC, P230 Setiawan NA, 2012, PROCEEDINGS OF 2012 IEEE INTERNATIONAL CONFERENCE ON CONDITION MONITORING AND DIAGNOSIS (IEEE CMD 2012), P950 Shintemirov A, 2009, IEEE T SYST MAN CY C, V39, P69, DOI 10.1109/TSMCC.2008.2007253 Siva Sarma D. V. S., 2004, IEEE T POWER SYST, V3, P444 Weidong J, 2011, INT C COMP SCI NETW, P585 Wu PF, 2011, ISA T, V50, P71, DOI 10.1016/j.isatra.2010.08.005 Xiaoxia Wang, 2008, 2008 Second International Symposium on Intelligent Information Technology Application, DOI 10.1109/IITA.2008.381 Yang HT, 1998, IEEE T POWER SYST, V13, P946 Zakaria F, 2014, 2014 IEEE 8TH INTERNATIONAL POWER ENGINEERING AND OPTIMIZATION CONFERENCE (PEOCO), P635, DOI 10.1109/PEOCO.2014.6814505 Zhang JL, 2011, PLOS ONE, V6, DOI 10.1371/journal.pone.0021787 Zhang Y, 1996, IEEE T POWER DELIVER, V11, P1836, DOI 10.1109/61.544265 Zhenyuan W, 2000, IEEE POW ENG SOC WIN, V2, P1261 Illias, Hazlee Azil Chai, Xin Rui Abu Bakar, Ab Halim Mokhlis, Hazlie Engineering, Faculty /I-7935-2015 Engineering, Faculty /0000-0002-4848-7052 High Impact Research (HIR), Malaysian Ministry of Higher Education, HAI H-16001-D00048; Fundamental Research Grant Scheme (FRGS), Malaysian Ministry of Higher Education, HAI FP026-2012A This work was supported by a High Impact Research (HIR) grant: H-16001-D00048, Malaysian Ministry of Higher Education, HAI. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Fundamental Research Grant Scheme (FRGS) grant: FP026-2012A, Malaysian Ministry of Higher Education, HAI, "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript." 0 PUBLIC LIBRARY SCIENCE SAN FRANCISCO PLOS ONE
Uncontrolled Keywords: Dissolved-gas analysis, diagnosis, algorithm,
Subjects: T Technology > T Technology (General)
T Technology > TA Engineering (General). Civil engineering (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Engineering
Depositing User: Mr Jenal S
Date Deposited: 17 Mar 2016 01:32
Last Modified: 13 Nov 2017 08:24
URI: http://eprints.um.edu.my/id/eprint/15704

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year