A Study on the Fault Location of Secondary Equipment in Smart Substation Based on the Graph Attention Network
The inability to locate device faults quickly and accurately has become prominent due to the large number of communication devices and the complex structure of secondary circuit networks in smart substations. Traditional methods are less efficient when diagnosing secondary equipment faults in smart...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/23/9384 |
_version_ | 1797399573378891776 |
---|---|
author | Xian-Ming Xiang Xiu-Cheng Dong Jin-Qing He Yong-Kang Zheng Xin-Yang Li |
author_facet | Xian-Ming Xiang Xiu-Cheng Dong Jin-Qing He Yong-Kang Zheng Xin-Yang Li |
author_sort | Xian-Ming Xiang |
collection | DOAJ |
description | The inability to locate device faults quickly and accurately has become prominent due to the large number of communication devices and the complex structure of secondary circuit networks in smart substations. Traditional methods are less efficient when diagnosing secondary equipment faults in smart substations, and deep learning methods have poor portability, high learning sample costs, and often require retraining a model. Therefore, a secondary equipment fault diagnosis method based on a graph attention network is proposed in this paper. All fault events are automatically represented as graph-structured data based on the K-nearest neighbors (KNNs) algorithm in terms of the feature information exhibited by the corresponding detection nodes when equipment faults occur. Then, a fault diagnosis model is established based on the graph attention network. Finally, partial intervals of a 220 kV intelligent substation are taken as an example to compare the fault localization effect of different methods. The results show that the method proposed in this paper has the advantages of higher localization accuracy, lower learning cost, and better robustness than the traditional machine learning and deep learning methods. |
first_indexed | 2024-03-09T01:43:08Z |
format | Article |
id | doaj.art-84601234a21a4024bad3fee649bc6d98 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T01:43:08Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-84601234a21a4024bad3fee649bc6d982023-12-08T15:25:45ZengMDPI AGSensors1424-82202023-11-012323938410.3390/s23239384A Study on the Fault Location of Secondary Equipment in Smart Substation Based on the Graph Attention NetworkXian-Ming Xiang0Xiu-Cheng Dong1Jin-Qing He2Yong-Kang Zheng3Xin-Yang Li4Sichuan University Jinjiang College, Meishan 620860, ChinaSichuan University Jinjiang College, Meishan 620860, ChinaSichuan University Jinjiang College, Meishan 620860, ChinaState Grid Sichuan Electric Power Research Institute, Chengdu 610099, ChinaSichuan University Jinjiang College, Meishan 620860, ChinaThe inability to locate device faults quickly and accurately has become prominent due to the large number of communication devices and the complex structure of secondary circuit networks in smart substations. Traditional methods are less efficient when diagnosing secondary equipment faults in smart substations, and deep learning methods have poor portability, high learning sample costs, and often require retraining a model. Therefore, a secondary equipment fault diagnosis method based on a graph attention network is proposed in this paper. All fault events are automatically represented as graph-structured data based on the K-nearest neighbors (KNNs) algorithm in terms of the feature information exhibited by the corresponding detection nodes when equipment faults occur. Then, a fault diagnosis model is established based on the graph attention network. Finally, partial intervals of a 220 kV intelligent substation are taken as an example to compare the fault localization effect of different methods. The results show that the method proposed in this paper has the advantages of higher localization accuracy, lower learning cost, and better robustness than the traditional machine learning and deep learning methods.https://www.mdpi.com/1424-8220/23/23/9384smart substationsecondary equipmentfault diagnosisgraph attention network |
spellingShingle | Xian-Ming Xiang Xiu-Cheng Dong Jin-Qing He Yong-Kang Zheng Xin-Yang Li A Study on the Fault Location of Secondary Equipment in Smart Substation Based on the Graph Attention Network Sensors smart substation secondary equipment fault diagnosis graph attention network |
title | A Study on the Fault Location of Secondary Equipment in Smart Substation Based on the Graph Attention Network |
title_full | A Study on the Fault Location of Secondary Equipment in Smart Substation Based on the Graph Attention Network |
title_fullStr | A Study on the Fault Location of Secondary Equipment in Smart Substation Based on the Graph Attention Network |
title_full_unstemmed | A Study on the Fault Location of Secondary Equipment in Smart Substation Based on the Graph Attention Network |
title_short | A Study on the Fault Location of Secondary Equipment in Smart Substation Based on the Graph Attention Network |
title_sort | study on the fault location of secondary equipment in smart substation based on the graph attention network |
topic | smart substation secondary equipment fault diagnosis graph attention network |
url | https://www.mdpi.com/1424-8220/23/23/9384 |
work_keys_str_mv | AT xianmingxiang astudyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork AT xiuchengdong astudyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork AT jinqinghe astudyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork AT yongkangzheng astudyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork AT xinyangli astudyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork AT xianmingxiang studyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork AT xiuchengdong studyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork AT jinqinghe studyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork AT yongkangzheng studyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork AT xinyangli studyonthefaultlocationofsecondaryequipmentinsmartsubstationbasedonthegraphattentionnetwork |