Transformer hot spot temperature prediction using a hybrid algorithm of support vector regression and information granulation

Cui, Yi, Ma, Hui and Saha, Tapan (2015). Transformer hot spot temperature prediction using a hybrid algorithm of support vector regression and information granulation. In: Proceedings of the 2015 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC). IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), Brisbane, Australia, (). 15-18 November 2015. doi:10.1109/APPEEC.2015.7381066

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Cui, Yi
Ma, Hui
Saha, Tapan
Title of paper Transformer hot spot temperature prediction using a hybrid algorithm of support vector regression and information granulation
Conference name IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC)
Conference location Brisbane, Australia
Conference dates 15-18 November 2015
Convener IEEE
Proceedings title Proceedings of the 2015 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC)
Journal name Asia-Pacific Power and Energy Engineering Conference, APPEEC
Series Asia-Pacific Power and Energy Engineering Conference, APPEEC
Place of Publication Piscataway, NJ, United States
Publisher Institute of Electrical and Electronic Engineers (IEEE)
Publication Year 2015
Sub-type Fully published paper
DOI 10.1109/APPEEC.2015.7381066
Open Access Status Not Open Access
ISBN 9781467381321
ISSN 2157-4847
Volume 2016-January
Total pages 5
Collection year 2016
Language eng
Formatted Abstract/Summary
A novel algorithm for transformer hot spot temperature prediction is proposed and presented in this paper. The algorithm is an integration of Support Vector Regression (SVR) and Information Granulation (IG), which is based on the principle of time series regression. The historical records consisting of measured hot spot temperature, top oil temperature, road current and ambient temperature of a transformer are used for verifying the proposed hybrid algorithm. The results show that the algorithm consistently outperforms a number of existing thermal modelling based methods (IEEE model, Swift’s model and Susa’s model) in estimating transformer’s hot spot temperature.
Keyword Hot spot temperature
Information granulation
Support vector regression
Top oil temperature
Transformer
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Fri, 20 Nov 2015, 12:01:24 EST by Yi Cui on behalf of School of Information Technol and Elec Engineering