Cover Image

Improved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processing

Clustering algorithms; Conformal mapping; Data visualization; Power transformers; Self organizing maps; Support vector machines; Data normalization methods; Detection sensitivity; Dissolved gas analyses (DGA); Dissolved gas analysis; High dimensional data; Incipient fault detection; Interpretation m...

Full description

Saved in:
Bibliographic Details
Main Authors: Misbahulmunir S., Ramachandaramurthy V.K., Thayoob Y.H.M.D.
Other Authors: 57189044890
Format: Article
Published: Institute of Electrical and Electronics Engineers Inc. 2023
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-25738
record_format dspace
spelling my.uniten.dspace-257382023-05-29T16:13:38Z Improved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processing Misbahulmunir S. Ramachandaramurthy V.K. Thayoob Y.H.M.D. 57189044890 6602912020 6505876050 Clustering algorithms; Conformal mapping; Data visualization; Power transformers; Self organizing maps; Support vector machines; Data normalization methods; Detection sensitivity; Dissolved gas analyses (DGA); Dissolved gas analysis; High dimensional data; Incipient fault detection; Interpretation methods; Topological relations; Fault detection Ability to organize data spatially while conserving the topological relation between data features makes the Self Organizing Map (SOM) a very useful tool for analysis and visualization of high dimensional data such as a power transformer's Dissolved Gas Analysis (DGA). Past SOM application required large historical data for its training and has limited fault detection sensitivity. In this paper, the effects of input features and data normalization are studied to enhance SOM's clustering. SOM is trained using DGA results extracted from actual faulted transformers. Combination of input features and data normalization methods are tested on SOM before the best SOM is identified. Validation is conducted using several datasets i.e. the IEC Technical Committee 10 database. Compared with past SOM applications, the proposed SOM required lesser training data, improved SOM's sensitivity in incipient fault detection and has good diagnosis accuracy. The proposed SOM is also compared with other AI-based DGA interpretation method i.e. Support Vector Machine (SVM) for benchmarking. � 2013 IEEE. Final 2023-05-29T08:13:38Z 2023-05-29T08:13:38Z 2020 Article 10.1109/ACCESS.2020.2986726 2-s2.0-85084192701 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85084192701&doi=10.1109%2fACCESS.2020.2986726&partnerID=40&md5=e7c2a4e7a15f18624ed274a34efe65ba https://irepository.uniten.edu.my/handle/123456789/25738 8 9061160 71798 71811 All Open Access, Gold Institute of Electrical and Electronics Engineers Inc. Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
description Clustering algorithms; Conformal mapping; Data visualization; Power transformers; Self organizing maps; Support vector machines; Data normalization methods; Detection sensitivity; Dissolved gas analyses (DGA); Dissolved gas analysis; High dimensional data; Incipient fault detection; Interpretation methods; Topological relations; Fault detection
author2 57189044890
author_facet 57189044890
Misbahulmunir S.
Ramachandaramurthy V.K.
Thayoob Y.H.M.D.
format Article
author Misbahulmunir S.
Ramachandaramurthy V.K.
Thayoob Y.H.M.D.
spellingShingle Misbahulmunir S.
Ramachandaramurthy V.K.
Thayoob Y.H.M.D.
Improved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processing
author_sort Misbahulmunir S.
title Improved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processing
title_short Improved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processing
title_full Improved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processing
title_fullStr Improved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processing
title_full_unstemmed Improved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processing
title_sort improved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processing
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2023
_version_ 1806428365847003136
score 13.211869

Similar Items