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

Simple item page
dc.citedby15
dc.contributor.authorMisbahulmunir S.en_US
dc.contributor.authorRamachandaramurthy V.K.en_US
dc.contributor.authorThayoob Y.H.M.D.en_US
dc.contributor.authorid57189044890en_US
dc.contributor.authorid6602912020en_US
dc.contributor.authorid6505876050en_US
dc.date.accessioned2023-05-29T08:13:38Z
dc.date.available2023-05-29T08:13:38Z
dc.date.issued2020
dc.descriptionClustering 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 detectionen_US
dc.description.abstractAbility 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.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo9061160
dc.identifier.doi10.1109/ACCESS.2020.2986726
dc.identifier.epage71811
dc.identifier.scopus2-s2.0-85084192701
dc.identifier.spage71798
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85084192701&doi=10.1109%2fACCESS.2020.2986726&partnerID=40&md5=e7c2a4e7a15f18624ed274a34efe65ba
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/25738
dc.identifier.volume8
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofAll Open Access, Gold
dc.sourceScopus
dc.sourcetitleIEEE Access
dc.titleImproved self-organizing map clustering of power transformer dissolved gas analysis using inputs pre-processingen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS