Publication:
Identification of transient overvoltage using discrete wavelet transform with minimised border distortion effect and support vector machine

Simple item page
dc.citedby2
dc.contributor.authorAsman S.H.en_US
dc.contributor.authorAbidin A.F.en_US
dc.contributor.authorYusoh M.A.T.M.en_US
dc.contributor.authorSubiyanto S.en_US
dc.contributor.authorid57194493395en_US
dc.contributor.authorid26666522700en_US
dc.contributor.authorid56453466100en_US
dc.contributor.authorid57224199114en_US
dc.date.accessioned2023-05-29T09:38:09Z
dc.date.available2023-05-29T09:38:09Z
dc.date.issued2022
dc.descriptionDiscrete wavelet transforms; Electrolysis; Power quality; Signal reconstruction; Border distortion; Discrete-wavelet-transform; Distortion effects; Sliding Window; Support vector machine classification; Support vectors machine; Transient disturbances; Transient overvoltages; Transient signal; Window techniques; Support vector machinesen_US
dc.description.abstractThe existing border distortion effect at signal edges can produce inaccurate detection of transient signals when deploying signal processing method. Therefore, there is a need to develop a technique to minimise this border distortion effect through the use of Discrete Wavelet Transform (DWT). In this study, the extension mode has been proposed to minimise border distortion effect. DWT based on one-cycle window technique is used to extract the features of transient disturbances signal. The disturbances contain imprecision of data and provide insufficient information, thereby leading to the failure of the conventional method to identify any power quality (PQ) problems. Thus, the detection and classification method using Support Vector Machine (SVM) is deployed to acquire reliable and accurate classification technique. The novel approached of one-cycle sliding window with the association of extension mode are validated through the SVM classification. From the results obtained, the performance of absolute reconstructed signal after threshold technique shows that smooth padding is the most effective extension mode to reduce the border distortion effect using one-cycle sliding window. Overall, the SVM classification performance based on one-versus-one (OVO) coding design can detect transient and non-transient events subsequent to undergoing all subsequent processes. � 2021 The Authorsen_US
dc.description.natureFinalen_US
dc.identifier.ArtNo100311
dc.identifier.doi10.1016/j.rineng.2021.100311
dc.identifier.scopus2-s2.0-85121208348
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85121208348&doi=10.1016%2fj.rineng.2021.100311&partnerID=40&md5=5ecaa2761272c0a76fc51ca32f735321
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/26958
dc.identifier.volume13
dc.publisherElsevier B.V.en_US
dc.relation.ispartofAll Open Access, Gold
dc.sourceScopus
dc.sourcetitleResults in Engineering
dc.titleIdentification of transient overvoltage using discrete wavelet transform with minimised border distortion effect and support vector machineen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS