Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)

Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)

Taking into account the chaotic characteristic of gas production within power transformers, a Least Square Support Vector Machine (LSSVM) model is implemented to forecast dissolved gas content based on historical chromatography samples. Additionally, an extending approach is developed with a correla...

Full description

Bibliographic Details
Main Author: Roberto Fiallos
Format: Article
Language:English
Published: Escuela Politécnica Nacional (EPN) 2017-11-01
Series:Latin-American Journal of Computing
Subjects:
dissolved gas analysis (dga)
gas chromatography
machine learning
least square support vector machine (lssvm).
Online Access:https://lajc.epn.edu.ec/index.php/LAJC/article/view/131
id doaj-5ea90f08c6ff4cf1ab99108fd0b856b5
record_format Article
spelling doaj-5ea90f08c6ff4cf1ab99108fd0b856b52021-04-20T14:56:46ZengEscuela Politécnica Nacional (EPN)Latin-American Journal of Computing1390-92661390-91342017-11-01435560131Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)Roberto Fiallos0Escuela Politécnica NacionalTaking into account the chaotic characteristic of gas production within power transformers, a Least Square Support Vector Machine (LSSVM) model is implemented to forecast dissolved gas content based on historical chromatography samples. Additionally, an extending approach is developed with a correlation between oil temperature and Dissolved Gas Analysis (DGA), where a multi-input LSSVM is trained with the utilization of DGA and temperature datasets. The obtained DGA prediction from the extending model illustrates more accurate results, and the previous algorithm uncertainties are reduced.A favourable correlation between hydrogen, methane, ethane, ethylene, and acetylene and oil temperature is achieved by the application of the proposed multi-input model.https://lajc.epn.edu.ec/index.php/LAJC/article/view/131dissolved gas analysis (dga)gas chromatographymachine learningleast square support vector machine (lssvm).
collection DOAJ
language English
format Article
sources DOAJ
author Roberto Fiallos
spellingShingle Roberto Fiallos
Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)
Latin-American Journal of Computing
dissolved gas analysis (dga)
gas chromatography
machine learning
least square support vector machine (lssvm).
author_facet Roberto Fiallos
author_sort Roberto Fiallos
title Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)
title_short Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)
title_full Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)
title_fullStr Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)
title_full_unstemmed Dissolved gas content forecasting in power transformers based on Least Square Support Vector Machine (LSSVM)
title_sort dissolved gas content forecasting in power transformers based on least square support vector machine (lssvm)
publisher Escuela Politécnica Nacional (EPN)
series Latin-American Journal of Computing
issn 1390-9266
1390-9134
publishDate 2017-11-01
description Taking into account the chaotic characteristic of gas production within power transformers, a Least Square Support Vector Machine (LSSVM) model is implemented to forecast dissolved gas content based on historical chromatography samples. Additionally, an extending approach is developed with a correlation between oil temperature and Dissolved Gas Analysis (DGA), where a multi-input LSSVM is trained with the utilization of DGA and temperature datasets. The obtained DGA prediction from the extending model illustrates more accurate results, and the previous algorithm uncertainties are reduced.A favourable correlation between hydrogen, methane, ethane, ethylene, and acetylene and oil temperature is achieved by the application of the proposed multi-input model.
topic dissolved gas analysis (dga)
gas chromatography
machine learning
least square support vector machine (lssvm).
url https://lajc.epn.edu.ec/index.php/LAJC/article/view/131
work_keys_str_mv AT robertofiallos dissolvedgascontentforecastinginpowertransformersbasedonleastsquaresupportvectormachinelssvm
_version_ 1721517725213261824

Similar Items