Identification of Partial Discharge Source based on PLC Data using Support Vector Machine

カテゴリ: 研究会(論文単位)

論文No: DEI25020,EPP25020,HV25020

グループ名: 【A】基礎・材料・共通部門 誘電・絶縁材料/【A】基礎・材料・共通部門 放電・プラズマ・パルスパワー/【B】電力・エネルギー部門 高電圧合同研究会

発行日: 2025/01/19

タイトル(英語): Identification of Partial Discharge Source based on PLC Data using Support Vector Machine

著者名: Lumba Lunnetta Safura(九州工業大学),寳代 彬人(九州工業大学),木本 涼太(九州工業大学), 匹田 政幸(九州工業大学),小迫 雅裕(九州工業大学)

著者名(英語): Lunnetta Safura Lumba(Electrical Engineering - Kyushu Institute of Technology),Akito Houdai(Electrical Engineering - Kyushu Institute of Technology),Ryota Kimoto(Electrical Engineering - Kyushu Institute of Technology),Masayuki Hikita(Electrical Engineering - Kyushu Institute of Technology),Masahiro Kozako(Electrical Engineering - Kyushu Institute of Technology)

キーワード: Partial discharge|Condition Monitoring|Machine learning|Power line communication|Feature extraction|PRPD pattern

要約(日本語): This study employs a machine learning (ML) approach to classify three types of PD defects based on Power Line Communication ? Partial Discharge Monitoring System (PDMS) data in the format of PHY rate (Mbps). To achieve this, a modified IEC-60270 experimen

要約(英語): This study employs a machine learning (ML) approach to classify three types of PD defects based on Power Line Communication ? Partial Discharge Monitoring System (PDMS) data in the format of PHY rate (Mbps). To achieve this, a modified IEC-60270 experimental setup was developed, incorporating ferrite core (FC) sensors for PLC-PDMS.

本誌: 2025年1月22日-2025年1月23日誘電・絶縁材料/放電・プラズマ・パルスパワー/高電圧合同研究会-1

本誌掲載ページ: 87-91 p

原稿種別: 英語