Recurrent Graph Transformer Network for Multiple Fault Localization in Naval Shipboard Systems

The integration of power electronics building blocks in modern MVDC 12kV Naval ship systems enhances energy management and functionality but also introduces complex fault detection and control challenges. These challenges strain traditional fault diagnostic methods, making it difficult to detect and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ngo, Quang-Ha, Barnola, Isabel, Vu, Tuyen, Zhang, Jianhua, Ravindra, Harsha, Schoder, Karl, Ginn, Herbert
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Ngo, Quang-Ha
Barnola, Isabel
Vu, Tuyen
Zhang, Jianhua
Ravindra, Harsha
Schoder, Karl
Ginn, Herbert
description The integration of power electronics building blocks in modern MVDC 12kV Naval ship systems enhances energy management and functionality but also introduces complex fault detection and control challenges. These challenges strain traditional fault diagnostic methods, making it difficult to detect and manage faults across multiple locations while maintaining system stability and performance. This paper proposes a temporal recurrent graph transformer network for fault diagnosis in naval MVDC 12kV shipboard systems. The deep graph neural network uses gated recurrent units to capture temporal features and a multi-head attention mechanism to extract spatial features, enhancing diagnostic accuracy. The approach effectively identifies and evaluates successive multiple faults with high precision. The method is implemented and validated on the MVDC 12kV shipboard system designed by the ESDRC team, incorporating all key components. Results show significant improvements in fault localization accuracy, with a 1-4% increase in performance metrics compared to other machine learning methods.
doi_str_mv 10.48550/arxiv.2409.10792
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2409_10792</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2409_10792</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2409_107923</originalsourceid><addsrcrecordid>eNqFzjEOgkAUBNBtLIx6ACv_BURAiFIb0UIphFryxSVsXFjyd0Hx9CKxt5qZZIrH2NyxLW_r-_YK6SVay_XswHLsTeCO2fXCs4aIVwYOhHUBCWGlc0UlJ4i4eSp6QD_h3EgjaskhxL7BSWUoxRuNUBWICiJsUUJciPqmkO4Qd9rwUk_ZKEep-eyXE7YI98nuuBwkaU2iROrSrygdROv_jw8exUJW</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Recurrent Graph Transformer Network for Multiple Fault Localization in Naval Shipboard Systems</title><source>arXiv.org</source><creator>Ngo, Quang-Ha ; Barnola, Isabel ; Vu, Tuyen ; Zhang, Jianhua ; Ravindra, Harsha ; Schoder, Karl ; Ginn, Herbert</creator><creatorcontrib>Ngo, Quang-Ha ; Barnola, Isabel ; Vu, Tuyen ; Zhang, Jianhua ; Ravindra, Harsha ; Schoder, Karl ; Ginn, Herbert</creatorcontrib><description>The integration of power electronics building blocks in modern MVDC 12kV Naval ship systems enhances energy management and functionality but also introduces complex fault detection and control challenges. These challenges strain traditional fault diagnostic methods, making it difficult to detect and manage faults across multiple locations while maintaining system stability and performance. This paper proposes a temporal recurrent graph transformer network for fault diagnosis in naval MVDC 12kV shipboard systems. The deep graph neural network uses gated recurrent units to capture temporal features and a multi-head attention mechanism to extract spatial features, enhancing diagnostic accuracy. The approach effectively identifies and evaluates successive multiple faults with high precision. The method is implemented and validated on the MVDC 12kV shipboard system designed by the ESDRC team, incorporating all key components. Results show significant improvements in fault localization accuracy, with a 1-4% increase in performance metrics compared to other machine learning methods.</description><identifier>DOI: 10.48550/arxiv.2409.10792</identifier><language>eng</language><subject>Computer Science - Systems and Control</subject><creationdate>2024-09</creationdate><rights>http://creativecommons.org/licenses/by-nc-nd/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2409.10792$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2409.10792$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ngo, Quang-Ha</creatorcontrib><creatorcontrib>Barnola, Isabel</creatorcontrib><creatorcontrib>Vu, Tuyen</creatorcontrib><creatorcontrib>Zhang, Jianhua</creatorcontrib><creatorcontrib>Ravindra, Harsha</creatorcontrib><creatorcontrib>Schoder, Karl</creatorcontrib><creatorcontrib>Ginn, Herbert</creatorcontrib><title>Recurrent Graph Transformer Network for Multiple Fault Localization in Naval Shipboard Systems</title><description>The integration of power electronics building blocks in modern MVDC 12kV Naval ship systems enhances energy management and functionality but also introduces complex fault detection and control challenges. These challenges strain traditional fault diagnostic methods, making it difficult to detect and manage faults across multiple locations while maintaining system stability and performance. This paper proposes a temporal recurrent graph transformer network for fault diagnosis in naval MVDC 12kV shipboard systems. The deep graph neural network uses gated recurrent units to capture temporal features and a multi-head attention mechanism to extract spatial features, enhancing diagnostic accuracy. The approach effectively identifies and evaluates successive multiple faults with high precision. The method is implemented and validated on the MVDC 12kV shipboard system designed by the ESDRC team, incorporating all key components. Results show significant improvements in fault localization accuracy, with a 1-4% increase in performance metrics compared to other machine learning methods.</description><subject>Computer Science - Systems and Control</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFzjEOgkAUBNBtLIx6ACv_BURAiFIb0UIphFryxSVsXFjyd0Hx9CKxt5qZZIrH2NyxLW_r-_YK6SVay_XswHLsTeCO2fXCs4aIVwYOhHUBCWGlc0UlJ4i4eSp6QD_h3EgjaskhxL7BSWUoxRuNUBWICiJsUUJciPqmkO4Qd9rwUk_ZKEep-eyXE7YI98nuuBwkaU2iROrSrygdROv_jw8exUJW</recordid><startdate>20240916</startdate><enddate>20240916</enddate><creator>Ngo, Quang-Ha</creator><creator>Barnola, Isabel</creator><creator>Vu, Tuyen</creator><creator>Zhang, Jianhua</creator><creator>Ravindra, Harsha</creator><creator>Schoder, Karl</creator><creator>Ginn, Herbert</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240916</creationdate><title>Recurrent Graph Transformer Network for Multiple Fault Localization in Naval Shipboard Systems</title><author>Ngo, Quang-Ha ; Barnola, Isabel ; Vu, Tuyen ; Zhang, Jianhua ; Ravindra, Harsha ; Schoder, Karl ; Ginn, Herbert</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2409_107923</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Systems and Control</topic><toplevel>online_resources</toplevel><creatorcontrib>Ngo, Quang-Ha</creatorcontrib><creatorcontrib>Barnola, Isabel</creatorcontrib><creatorcontrib>Vu, Tuyen</creatorcontrib><creatorcontrib>Zhang, Jianhua</creatorcontrib><creatorcontrib>Ravindra, Harsha</creatorcontrib><creatorcontrib>Schoder, Karl</creatorcontrib><creatorcontrib>Ginn, Herbert</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ngo, Quang-Ha</au><au>Barnola, Isabel</au><au>Vu, Tuyen</au><au>Zhang, Jianhua</au><au>Ravindra, Harsha</au><au>Schoder, Karl</au><au>Ginn, Herbert</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Recurrent Graph Transformer Network for Multiple Fault Localization in Naval Shipboard Systems</atitle><date>2024-09-16</date><risdate>2024</risdate><abstract>The integration of power electronics building blocks in modern MVDC 12kV Naval ship systems enhances energy management and functionality but also introduces complex fault detection and control challenges. These challenges strain traditional fault diagnostic methods, making it difficult to detect and manage faults across multiple locations while maintaining system stability and performance. This paper proposes a temporal recurrent graph transformer network for fault diagnosis in naval MVDC 12kV shipboard systems. The deep graph neural network uses gated recurrent units to capture temporal features and a multi-head attention mechanism to extract spatial features, enhancing diagnostic accuracy. The approach effectively identifies and evaluates successive multiple faults with high precision. The method is implemented and validated on the MVDC 12kV shipboard system designed by the ESDRC team, incorporating all key components. Results show significant improvements in fault localization accuracy, with a 1-4% increase in performance metrics compared to other machine learning methods.</abstract><doi>10.48550/arxiv.2409.10792</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2409.10792
ispartof
issn
language eng
recordid cdi_arxiv_primary_2409_10792
source arXiv.org
subjects Computer Science - Systems and Control
title Recurrent Graph Transformer Network for Multiple Fault Localization in Naval Shipboard Systems
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-18T22%3A55%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Recurrent%20Graph%20Transformer%20Network%20for%20Multiple%20Fault%20Localization%20in%20Naval%20Shipboard%20Systems&rft.au=Ngo,%20Quang-Ha&rft.date=2024-09-16&rft_id=info:doi/10.48550/arxiv.2409.10792&rft_dat=%3Carxiv_GOX%3E2409_10792%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true