Localisation of Partial Discharge in Power Cables Through Multi-Output Convolutional Recurrent Neural Network and Feature Extraction

Simple item page
dc.contributor.authorYeo, Joel
dc.contributor.authorJin, Huifei
dc.contributor.authorMor, Armando Rodrigo
dc.contributor.authorYuen, Chau
dc.contributor.authorPattanadech, Norasage
dc.contributor.authorTushar, Wayes
dc.contributor.authorSaha, Tapan K.
dc.contributor.authorNg, Chee Seng
dc.date.accessioned2026-08-06T10:41:00Z
dc.date.available2026-08-06T10:41:00Z
dc.date.issued2023-02-01
dc.description.abstractThis paper proposes an algorithmic approach constructed from a convolutional recurrent neural network (CRNN) iterated with examination of extracted features for partial discharge (PD) localisation; tests were conducted offline on medium voltage (MV) power cables. To evaluate the performance of the algorithm, a case study was performed on 7 cables deliberately selected to comprehensively illustrate the difficulties encountered in field testing. The experimental test results prove that the proposed concept is able to identify and localise discharges besmirched with significant quantities of noise. Main contribution of the methodology is the successful automated interpretation of measurements acquired under noisy challenging field constraints.
dc.identifier.citationIEEE Transactions on Power Delivery, 38(1), 177-188, 2023
dc.identifier.doi10.1109/TPWRD.2022.3183588
dc.identifier.issn08858977
dc.identifier.other2-s2.0-85132728249
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/14283
dc.sourceIEEE Transactions on Power Delivery
dc.subjectmedium voltage cables
dc.subjectneural networks
dc.subjectPartial discharge
dc.titleLocalisation of Partial Discharge in Power Cables Through Multi-Output Convolutional Recurrent Neural Network and Feature Extraction
dc.typeArticle

Files

Collections

Research