An enhanced semi-supervised learning method with self-supervised and adaptive threshold for fault detection and classification in urban power grids

With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle to address the complexities of diagnosing faults in intricate power grid systems. Although artificial intelligence technologies offer new so...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy and AI Jg. 17; S. 100377
Hauptverfasser: Zhang, Jiahao, Cheng, Lan, Yang, Zhile, Xiao, Qinge, Khan, Sohail, Liang, Rui, Wu, Xinyu, Guo, Yuanjun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.09.2024
Elsevier
Schlagworte:
ISSN:2666-5468, 2666-5468
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle to address the complexities of diagnosing faults in intricate power grid systems. Although artificial intelligence technologies offer new solutions for power grid fault diagnosis, the difficulty in acquiring labeled grid data limits the development of AI technologies in this area. In response to these challenges, this study proposes a semi-supervised learning framework with self-supervised and adaptive threshold (SAT-SSL) for fault detection and classification in power grids. Compared to other methods, our method reduces the dependence on labeling data while maintaining high recognition accuracy. First, we utilize frequency domain analysis on power grid data to filter abnormal events, then classify and label these events based on visual features, to creating a power grid dataset. Subsequently, we employ the Yule–Walker algorithm extract features from the power grid data. Then we construct a semi-supervised learning framework, incorporating self-supervised loss and dynamic threshold to enhance information extraction capabilities and adaptability across different scenarios of the model. Finally, the power grid dataset along with two benchmark datasets are used to validate the model’s functionality. The results indicate that our model achieves a low error rate across various scenarios and different amounts of labels. In power grid dataset, When retaining just 5% of the labels, the error rate is only 6.15%, which proves that this method can achieve accurate grid fault detection and classification with a limited amount of labeled data. [Display omitted] •Employed Yule–Walker for grid data spectral analysis to unveil distinct time-frequency characteristics•Merged self-supervised learning with dynamic thresholds (SAT-SSL) for high efficiency and accuracy•Validated SAT-SSL has better fault diagnosis performance on both benchmark and real-world datasets•Enhanced power grid fault detection and classification accuracy for intelligent monitoring and maintenance
AbstractList With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle to address the complexities of diagnosing faults in intricate power grid systems. Although artificial intelligence technologies offer new solutions for power grid fault diagnosis, the difficulty in acquiring labeled grid data limits the development of AI technologies in this area. In response to these challenges, this study proposes a semi-supervised learning framework with self-supervised and adaptive threshold (SAT-SSL) for fault detection and classification in power grids. Compared to other methods, our method reduces the dependence on labeling data while maintaining high recognition accuracy. First, we utilize frequency domain analysis on power grid data to filter abnormal events, then classify and label these events based on visual features, to creating a power grid dataset. Subsequently, we employ the Yule–Walker algorithm extract features from the power grid data. Then we construct a semi-supervised learning framework, incorporating self-supervised loss and dynamic threshold to enhance information extraction capabilities and adaptability across different scenarios of the model. Finally, the power grid dataset along with two benchmark datasets are used to validate the model’s functionality. The results indicate that our model achieves a low error rate across various scenarios and different amounts of labels. In power grid dataset, When retaining just 5% of the labels, the error rate is only 6.15%, which proves that this method can achieve accurate grid fault detection and classification with a limited amount of labeled data. [Display omitted] •Employed Yule–Walker for grid data spectral analysis to unveil distinct time-frequency characteristics•Merged self-supervised learning with dynamic thresholds (SAT-SSL) for high efficiency and accuracy•Validated SAT-SSL has better fault diagnosis performance on both benchmark and real-world datasets•Enhanced power grid fault detection and classification accuracy for intelligent monitoring and maintenance
With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle to address the complexities of diagnosing faults in intricate power grid systems. Although artificial intelligence technologies offer new solutions for power grid fault diagnosis, the difficulty in acquiring labeled grid data limits the development of AI technologies in this area. In response to these challenges, this study proposes a semi-supervised learning framework with self-supervised and adaptive threshold (SAT-SSL) for fault detection and classification in power grids. Compared to other methods, our method reduces the dependence on labeling data while maintaining high recognition accuracy. First, we utilize frequency domain analysis on power grid data to filter abnormal events, then classify and label these events based on visual features, to creating a power grid dataset. Subsequently, we employ the Yule–Walker algorithm extract features from the power grid data. Then we construct a semi-supervised learning framework, incorporating self-supervised loss and dynamic threshold to enhance information extraction capabilities and adaptability across different scenarios of the model. Finally, the power grid dataset along with two benchmark datasets are used to validate the model’s functionality. The results indicate that our model achieves a low error rate across various scenarios and different amounts of labels. In power grid dataset, When retaining just 5% of the labels, the error rate is only 6.15%, which proves that this method can achieve accurate grid fault detection and classification with a limited amount of labeled data.
ArticleNumber 100377
Author Xiao, Qinge
Guo, Yuanjun
Cheng, Lan
Zhang, Jiahao
Yang, Zhile
Wu, Xinyu
Liang, Rui
Khan, Sohail
Author_xml – sequence: 1
  givenname: Jiahao
  surname: Zhang
  fullname: Zhang, Jiahao
  organization: Taiyuan University of Technology, Taiyuan, Shanxi, China
– sequence: 2
  givenname: Lan
  surname: Cheng
  fullname: Cheng, Lan
  organization: Taiyuan University of Technology, Taiyuan, Shanxi, China
– sequence: 3
  givenname: Zhile
  surname: Yang
  fullname: Yang, Zhile
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
– sequence: 4
  givenname: Qinge
  surname: Xiao
  fullname: Xiao, Qinge
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
– sequence: 5
  givenname: Sohail
  surname: Khan
  fullname: Khan, Sohail
  organization: Sino-Pak Center for Artificial Intelligence, Pak-Austria Fachhochschule – Institute of Applied Sciences and Technology, Haripur, Khyber Pakhtunkhwa, Pakistan
– sequence: 6
  givenname: Rui
  surname: Liang
  fullname: Liang, Rui
  organization: Chengxi Company, State Grid Tianjin Electric Power Company, Tianjin, China
– sequence: 7
  givenname: Xinyu
  surname: Wu
  fullname: Wu, Xinyu
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
– sequence: 8
  givenname: Yuanjun
  orcidid: 0000-0002-2213-5489
  surname: Guo
  fullname: Guo, Yuanjun
  email: yj.guo@siat.ac.cn
  organization: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
BookMark eNqFUcuK3DAQNGED2Wz2C3LRD3iihy3ZhxyWJY-FhVySs2hb7XEPHmmQNLPsd-SHo_GEsOSQHBq1iqqCrnpbXfngsareC74RXOgPuw1un4E2ksumIFwZ86q6llrrum10d_Vif1PdprTjnMtWiN6Y6-rnnWfoZ_AjOpZwT3U6HjCeKJX_ghA9-S3bY56DY0-U50Jappck8GUcHDKdkOU5YprD4tgUIpvguGTmMOOYKfiVOi6QEk00wgqRZ8c4gGeH8ISRbSO59K56PcGS8Pb3e1P9-Pzp-_3X-vHbl4f7u8d6bEST615p1XEU0A-DaYRE7ibBpR4UoBBTA52SsneuHaaCKdCt0bKDXhsA1eCkbqqHi68LsLOHSHuIzzYA2RUIcWshZhoXtFx3sjfFvR1k0xrVD51ynXaDMVJz6IuXuniNMaQUcfrjJ7g912R3dq3Jnmuyl5qKqv9LNVJeg8kRaPmP9uNFiyWiE2G0aSQ890ix5F1uoH_qfwECDLM7
CitedBy_id crossref_primary_10_1016_j_egyai_2025_100550
crossref_primary_10_1016_j_autcon_2025_106228
Cites_doi 10.1016/j.epsr.2020.106437
10.1016/j.measurement.2021.109330
10.3390/s22124470
10.1609/aaai.v30i1.10179
10.1016/j.ijepes.2021.107399
10.1109/TIT.1970.1054472
10.1016/j.engappai.2021.104504
10.1109/TKDE.2022.3220219
10.1109/TPAMI.2021.3127558
10.1016/j.rser.2017.04.121
10.1016/j.epsr.2020.106914
10.1109/TIM.2013.2240920
10.1016/j.engappai.2020.103680
10.1049/iet-gtd.2011.0703
10.1016/j.engappai.2023.106592
10.1016/j.egyai.2023.100262
10.1016/j.neucom.2009.11.008
10.1016/j.ymssp.2020.107327
10.1109/TPWRD.2010.2079337
10.1016/j.ijepes.2023.109267
10.1016/j.egyai.2021.100133
10.1109/TPWRD.2015.2435158
10.1016/j.egyai.2023.100271
10.1080/00207543.2022.2032860
10.1016/j.egyai.2023.100322
10.24963/ijcai.2018/278
10.1109/JSEN.2020.2987321
10.1109/TPWRS.2016.2632156
10.1016/j.egyai.2023.100301
10.1109/ACCESS.2019.2960512
10.1109/TPAS.1983.318102
10.1007/s40565-018-0423-3
ContentType Journal Article
Copyright 2024 The Author(s)
Copyright_xml – notice: 2024 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.egyai.2024.100377
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2666-5468
ExternalDocumentID oai_doaj_org_article_0682971025b245739b83d86db77260a9
10_1016_j_egyai_2024_100377
S2666546824000430
GroupedDBID 0R~
0SF
6I.
AAEDW
AAFTH
AALRI
AAXUO
ADVLN
AITUG
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
EBS
FDB
GROUPED_DOAJ
M41
M~E
NCXOZ
OK1
ROL
AAYWO
AAYXX
ACVFH
ADCNI
AEUPX
AFJKZ
AFPUW
AIGII
AKBMS
AKYEP
APXCP
CITATION
ID FETCH-LOGICAL-c414t-936380e1a9bb7412e0df1026b3ae11f4a83229dd5bf6b33a657628a967aa34ef3
IEDL.DBID DOA
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001264977600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2666-5468
IngestDate Fri Oct 03 12:44:18 EDT 2025
Tue Nov 18 22:29:22 EST 2025
Sat Nov 29 03:06:01 EST 2025
Sat Aug 31 16:02:20 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Data driven
Power grid fault detection
Semi-supervised learning
Smart grid
Language English
License This is an open access article under the CC BY-NC license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c414t-936380e1a9bb7412e0df1026b3ae11f4a83229dd5bf6b33a657628a967aa34ef3
ORCID 0000-0002-2213-5489
OpenAccessLink https://doaj.org/article/0682971025b245739b83d86db77260a9
ParticipantIDs doaj_primary_oai_doaj_org_article_0682971025b245739b83d86db77260a9
crossref_primary_10_1016_j_egyai_2024_100377
crossref_citationtrail_10_1016_j_egyai_2024_100377
elsevier_sciencedirect_doi_10_1016_j_egyai_2024_100377
PublicationCentury 2000
PublicationDate September 2024
2024-09-00
2024-09-01
PublicationDateYYYYMMDD 2024-09-01
PublicationDate_xml – month: 09
  year: 2024
  text: September 2024
PublicationDecade 2020
PublicationTitle Energy and AI
PublicationYear 2024
Publisher Elsevier Ltd
Elsevier
Publisher_xml – name: Elsevier Ltd
– name: Elsevier
References Wei, Gong, Liu, Lu, Wang (b31) 2018
Phadke, Bi (b12) 2018; 6
Jayasree, Devaraj, Sukanesh (b2) 2010; 73
Cao S, Lu W, Xu Q. Deep neural networks for learning graph representations. In: Proceedings of the AAAI conference on artificial intelligence. Vol. 30, 2016.
Fahim, Sarker, Sarker, Sheikh, Das (b24) 2020; 187
Rasmus, Berglund, Honkala, Valpola, Raiko (b33) 2015; 28
Sajjadi, Javanmardi, Tasdizen (b34) 2016; 29
Kalair, Abas, Kalair, Saleem, Khan (b8) 2017; 78
Long, Chen, Yang, Huang, Li (b42) 2023; 61
Agrawala (b29) 1970; 16
Beinert, Holzhüter, Thomas, Vogt (b19) 2023; 14
Kingma, Mohamed, Jimenez Rezende, Welling (b32) 2014; 27
Dong-DongChen W, WeiGao Z. Tri-net for semi-supervised deep learning. In: Proceedings of twenty-seventh international joint conference on artificial intelligence. 2018, p. 2014–20.
Allen, Santoso, Muljadi (b11) 2013
Shadi, Ameli, Azad (b15) 2022; 134
Fan, Liu, Tian (b7) 2010; 26
Harish, Asok, Jayan (b21) 2023; 14
Yang, Song, King, Xu (b28) 2022; 35
Belagoune, Bali, Bakdi, Baadji, Atif (b26) 2021; 177
Zhang, Wang, Hou, Wu, Wang, Okumura, Shinozaki (b45) 2021; 34
Lee D-H, et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on challenges in representation learning, ICML. Vol. 3, Atlanta; 2013, p. 896.
Wallin, Svensson, Kahl, Hammarstrand (b44) 2022
Karić, Konjić, Jahić (b22) 2018
Kipf, Welling (b36) 2016
Buryanina, Korolyuk, Koryakina, Lesnykh, Suslov (b3) 2019
Rai, Londhe, Raj (b25) 2021; 192
Li, Xu, Zhu, Liu, Zhang (b30) 2021; 44
Mao, Wei, Xu, Chen, Wu, Peng, Ren (b43) 2022; 22
Qu, Zuo, Chen, Li (b23) 2019; 7
Crossley, McLaren (b4) 1983
Luo, Yan, Saha, Sharma (b5) 2023; 152
Vaish, Dwivedi, Tewari, Tripathi (b18) 2021; 106
Wu, Zhang, Cheng, Peng (b41) 2021; 149
Laverty, Best, Brogan, Al Khatib, Vanfretti, Morrow (b13) 2013; 62
Wang, Menke, Schäfer, Braun, Scheidler (b10) 2022; 7
Furse, Kafal, Razzaghi, Shin (b1) 2020; 21
Yu, Du, Li, Zhang, Hu (b16) 2023; 124
Lin, He, Li, Qian (b6) 2012; 6
Guo, Li, Laverty, Xue (b14) 2015; 30
Berthelot, Carlini, Goodfellow, Papernot, Oliver, Raffel (b39) 2019; 32
Sohn, Berthelot, Carlini, Zhang, Zhang, Raffel, Cubuk, Kurakin, Li (b40) 2020; 33
Heymann, Quest, Garcia, Ballif, Galus (b17) 2024; 15
Primadianto, Lu (b9) 2016; 32
Husnoo, Anwar, Reda, Hosseinzadeh, Islam, Mahmood, Doss (b20) 2023; 14
Wang, Wei, Wang, Huang, Peng, Song, Cabrera, Pérez-Jiménez (b27) 2020; 92
Wang (10.1016/j.egyai.2024.100377_b27) 2020; 92
Mao (10.1016/j.egyai.2024.100377_b43) 2022; 22
Agrawala (10.1016/j.egyai.2024.100377_b29) 1970; 16
Buryanina (10.1016/j.egyai.2024.100377_b3) 2019
Shadi (10.1016/j.egyai.2024.100377_b15) 2022; 134
Kingma (10.1016/j.egyai.2024.100377_b32) 2014; 27
Fan (10.1016/j.egyai.2024.100377_b7) 2010; 26
Laverty (10.1016/j.egyai.2024.100377_b13) 2013; 62
Jayasree (10.1016/j.egyai.2024.100377_b2) 2010; 73
Husnoo (10.1016/j.egyai.2024.100377_b20) 2023; 14
Sohn (10.1016/j.egyai.2024.100377_b40) 2020; 33
Allen (10.1016/j.egyai.2024.100377_b11) 2013
Qu (10.1016/j.egyai.2024.100377_b23) 2019; 7
Wallin (10.1016/j.egyai.2024.100377_b44) 2022
Kipf (10.1016/j.egyai.2024.100377_b36) 2016
Lin (10.1016/j.egyai.2024.100377_b6) 2012; 6
Rasmus (10.1016/j.egyai.2024.100377_b33) 2015; 28
Beinert (10.1016/j.egyai.2024.100377_b19) 2023; 14
Harish (10.1016/j.egyai.2024.100377_b21) 2023; 14
Luo (10.1016/j.egyai.2024.100377_b5) 2023; 152
Primadianto (10.1016/j.egyai.2024.100377_b9) 2016; 32
Wei (10.1016/j.egyai.2024.100377_b31) 2018
Yang (10.1016/j.egyai.2024.100377_b28) 2022; 35
Zhang (10.1016/j.egyai.2024.100377_b45) 2021; 34
Wang (10.1016/j.egyai.2024.100377_b10) 2022; 7
Vaish (10.1016/j.egyai.2024.100377_b18) 2021; 106
Wu (10.1016/j.egyai.2024.100377_b41) 2021; 149
Karić (10.1016/j.egyai.2024.100377_b22) 2018
10.1016/j.egyai.2024.100377_b35
Heymann (10.1016/j.egyai.2024.100377_b17) 2024; 15
Li (10.1016/j.egyai.2024.100377_b30) 2021; 44
Fahim (10.1016/j.egyai.2024.100377_b24) 2020; 187
Sajjadi (10.1016/j.egyai.2024.100377_b34) 2016; 29
Rai (10.1016/j.egyai.2024.100377_b25) 2021; 192
10.1016/j.egyai.2024.100377_b37
Berthelot (10.1016/j.egyai.2024.100377_b39) 2019; 32
Crossley (10.1016/j.egyai.2024.100377_b4) 1983
Kalair (10.1016/j.egyai.2024.100377_b8) 2017; 78
10.1016/j.egyai.2024.100377_b38
Phadke (10.1016/j.egyai.2024.100377_b12) 2018; 6
Yu (10.1016/j.egyai.2024.100377_b16) 2023; 124
Belagoune (10.1016/j.egyai.2024.100377_b26) 2021; 177
Furse (10.1016/j.egyai.2024.100377_b1) 2020; 21
Guo (10.1016/j.egyai.2024.100377_b14) 2015; 30
Long (10.1016/j.egyai.2024.100377_b42) 2023; 61
References_xml – volume: 44
  start-page: 9629
  year: 2021
  end-page: 9640
  ident: b30
  article-title: Triple generative adversarial networks
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 21
  start-page: 888
  year: 2020
  end-page: 906
  ident: b1
  article-title: Fault diagnosis for electrical systems and power networks: A review
  publication-title: IEEE Sens J
– volume: 6
  start-page: 764
  year: 2012
  end-page: 772
  ident: b6
  article-title: Travelling wave time–frequency characteristic-based fault location method for transmission lines
  publication-title: IET Gener Transm Distrib
– volume: 152
  year: 2023
  ident: b5
  article-title: Waveform abnormality detection method for distribution system equipment condition monitoring
  publication-title: Int J Electr Power Energy Syst
– volume: 29
  year: 2016
  ident: b34
  article-title: Regularization with stochastic transformations and perturbations for deep semi-supervised learning
  publication-title: Adv Neural Inf Process Syst
– year: 2016
  ident: b36
  article-title: Semi-supervised classification with graph convolutional networks
– volume: 14
  year: 2023
  ident: b20
  article-title: FedDiSC: A computation-efficient federated learning framework for power systems disturbance and cyber attack discrimination
  publication-title: Energy AI
– volume: 187
  year: 2020
  ident: b24
  article-title: Self attention convolutional neural network with time series imaging based feature extraction for transmission line fault detection and classification
  publication-title: Electr Power Syst Res
– start-page: 89
  year: 2018
  end-page: 101
  ident: b22
  article-title: Power system fault detection, classification and location using artificial neural networks
  publication-title: Advanced technologies, systems, and applications II: proceedings of the international symposium on innovative and interdisciplinary applications of advanced technologies
– volume: 134
  year: 2022
  ident: b15
  article-title: A real-time hierarchical framework for fault detection, classification, and location in power systems using PMUs data and deep learning
  publication-title: Int J Electr Power Energy Syst
– start-page: 2871
  year: 2022
  end-page: 2877
  ident: b44
  article-title: Doublematch: Improving semi-supervised learning with self-supervision
  publication-title: 2022 26th international conference on pattern recognition
– volume: 14
  year: 2023
  ident: b21
  article-title: A comparative evaluation of Stacked Auto-Encoder neural network and Multi-Layer Extreme Learning Machine for detection and classification of faults in transmission lines using WAMS data
  publication-title: Energy AI
– volume: 177
  year: 2021
  ident: b26
  article-title: Deep learning through LSTM classification and regression for transmission line fault detection, diagnosis and location in large-scale multi-machine power systems
  publication-title: Measurement
– volume: 32
  year: 2019
  ident: b39
  article-title: Mixmatch: A holistic approach to semi-supervised learning
  publication-title: Adv Neural Inf Process Syst
– reference: Lee D-H, et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on challenges in representation learning, ICML. Vol. 3, Atlanta; 2013, p. 896.
– reference: Cao S, Lu W, Xu Q. Deep neural networks for learning graph representations. In: Proceedings of the AAAI conference on artificial intelligence. Vol. 30, 2016.
– volume: 14
  year: 2023
  ident: b19
  article-title: Power flow forecasts at transmission grid nodes using Graph Neural Networks
  publication-title: Energy AI
– volume: 34
  start-page: 18408
  year: 2021
  end-page: 18419
  ident: b45
  article-title: Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling
  publication-title: Adv Neural Inf Process Syst
– start-page: 2971
  year: 1983
  end-page: 2983
  ident: b4
  article-title: Distance protection based on travelling waves
  publication-title: IEEE Trans Power Appar Syst
– year: 2018
  ident: b31
  article-title: Improving the improved training of wasserstein gans: A consistency term and its dual effect
– volume: 26
  start-page: 135
  year: 2010
  end-page: 142
  ident: b7
  article-title: A fault-location method for 12-phase transmission lines based on twelve-sequence-component method
  publication-title: IEEE Trans Power Deliv
– volume: 78
  start-page: 1152
  year: 2017
  end-page: 1187
  ident: b8
  article-title: Review of harmonic analysis, modeling and mitigation techniques
  publication-title: Renew Sustain Energy Rev
– year: 2013
  ident: b11
  article-title: Algorithm for screening phasor measurement unit data for power system events and categories and common characteristics for events seen in phasor measurement unit relative phase-angle differences and frequency signals
– volume: 33
  start-page: 596
  year: 2020
  end-page: 608
  ident: b40
  article-title: Fixmatch: Simplifying semi-supervised learning with consistency and confidence
  publication-title: Adv Neural Inf Process Syst
– volume: 27
  year: 2014
  ident: b32
  article-title: Semi-supervised learning with deep generative models
  publication-title: Adv Neural Inf Process Syst
– volume: 192
  year: 2021
  ident: b25
  article-title: Fault classification in power system distribution network integrated with distributed generators using CNN
  publication-title: Electr Power Syst Res
– volume: 16
  start-page: 373
  year: 1970
  end-page: 379
  ident: b29
  article-title: Learning with a probabilistic teacher
  publication-title: IEEE Trans Inform Theory
– volume: 149
  year: 2021
  ident: b41
  article-title: A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery
  publication-title: Mech Syst Signal Process
– volume: 61
  start-page: 8238
  year: 2023
  end-page: 8251
  ident: b42
  article-title: A novel self-training semi-supervised deep learning approach for machinery fault diagnosis
  publication-title: Int J Prod Res
– volume: 62
  start-page: 701
  year: 2013
  end-page: 709
  ident: b13
  article-title: The OpenPMU platform for open-source phasor measurements
  publication-title: IEEE Trans Instrum Meas
– volume: 30
  start-page: 2544
  year: 2015
  end-page: 2552
  ident: b14
  article-title: Synchrophasor-based islanding detection for distributed generation systems using systematic principal component analysis approaches
  publication-title: IEEE Trans Power Deliv
– volume: 92
  year: 2020
  ident: b27
  article-title: A weighted corrective fuzzy reasoning spiking neural P system for fault diagnosis in power systems with variable topologies
  publication-title: Eng Appl Artif Intell
– volume: 7
  year: 2022
  ident: b10
  article-title: Approximating multi-purpose AC optimal power flow with reinforcement trained artificial neural network
  publication-title: Energy AI
– volume: 6
  start-page: 619
  year: 2018
  end-page: 629
  ident: b12
  article-title: Phasor measurement units, WAMS, and their applications in protection and control of power systems
  publication-title: J Mod Power Syst Clean Energy
– reference: Dong-DongChen W, WeiGao Z. Tri-net for semi-supervised deep learning. In: Proceedings of twenty-seventh international joint conference on artificial intelligence. 2018, p. 2014–20.
– volume: 124
  year: 2023
  ident: b16
  article-title: Study on a comprehensive indicator and online classification of early warning of low frequency oscillation in power system
  publication-title: Eng Appl Artif Intell
– volume: 7
  start-page: 184020
  year: 2019
  end-page: 184028
  ident: b23
  article-title: Series arc fault detection of indoor power distribution system based on LVQ-NN and PSO-SVM
  publication-title: IEEE Access
– volume: 35
  start-page: 8934
  year: 2022
  end-page: 8954
  ident: b28
  article-title: A survey on deep semi-supervised learning
  publication-title: IEEE Trans Knowl Data Eng
– volume: 73
  start-page: 1451
  year: 2010
  end-page: 1456
  ident: b2
  article-title: Power quality disturbance classification using Hilbert transform and RBF networks
  publication-title: Neurocomputing
– volume: 22
  start-page: 4470
  year: 2022
  ident: b43
  article-title: Fault diagnosis for power transformers through semi-supervised transfer learning
  publication-title: Sensors
– start-page: 1
  year: 2019
  end-page: 5
  ident: b3
  article-title: Algoritm of current protection based on three instantaneous-value samples
  publication-title: 2019 IEEE PES innovative smart grid technologies europe
– volume: 106
  year: 2021
  ident: b18
  article-title: Machine learning applications in power system fault diagnosis: Research advancements and perspectives
  publication-title: Eng Appl Artif Intell
– volume: 15
  year: 2024
  ident: b17
  article-title: Reviewing 40 years of artificial intelligence applied to power systems–A taxonomic perspective
  publication-title: Energy AI
– volume: 32
  start-page: 3875
  year: 2016
  end-page: 3883
  ident: b9
  article-title: A review on distribution system state estimation
  publication-title: IEEE Trans Power Syst
– volume: 28
  year: 2015
  ident: b33
  article-title: Semi-supervised learning with ladder networks
  publication-title: Adv Neural Inf Process Syst
– volume: 187
  year: 2020
  ident: 10.1016/j.egyai.2024.100377_b24
  article-title: Self attention convolutional neural network with time series imaging based feature extraction for transmission line fault detection and classification
  publication-title: Electr Power Syst Res
  doi: 10.1016/j.epsr.2020.106437
– volume: 177
  year: 2021
  ident: 10.1016/j.egyai.2024.100377_b26
  article-title: Deep learning through LSTM classification and regression for transmission line fault detection, diagnosis and location in large-scale multi-machine power systems
  publication-title: Measurement
  doi: 10.1016/j.measurement.2021.109330
– volume: 22
  start-page: 4470
  issue: 12
  year: 2022
  ident: 10.1016/j.egyai.2024.100377_b43
  article-title: Fault diagnosis for power transformers through semi-supervised transfer learning
  publication-title: Sensors
  doi: 10.3390/s22124470
– start-page: 2871
  year: 2022
  ident: 10.1016/j.egyai.2024.100377_b44
  article-title: Doublematch: Improving semi-supervised learning with self-supervision
– ident: 10.1016/j.egyai.2024.100377_b35
  doi: 10.1609/aaai.v30i1.10179
– volume: 134
  year: 2022
  ident: 10.1016/j.egyai.2024.100377_b15
  article-title: A real-time hierarchical framework for fault detection, classification, and location in power systems using PMUs data and deep learning
  publication-title: Int J Electr Power Energy Syst
  doi: 10.1016/j.ijepes.2021.107399
– volume: 16
  start-page: 373
  issue: 4
  year: 1970
  ident: 10.1016/j.egyai.2024.100377_b29
  article-title: Learning with a probabilistic teacher
  publication-title: IEEE Trans Inform Theory
  doi: 10.1109/TIT.1970.1054472
– volume: 106
  year: 2021
  ident: 10.1016/j.egyai.2024.100377_b18
  article-title: Machine learning applications in power system fault diagnosis: Research advancements and perspectives
  publication-title: Eng Appl Artif Intell
  doi: 10.1016/j.engappai.2021.104504
– volume: 35
  start-page: 8934
  issue: 9
  year: 2022
  ident: 10.1016/j.egyai.2024.100377_b28
  article-title: A survey on deep semi-supervised learning
  publication-title: IEEE Trans Knowl Data Eng
  doi: 10.1109/TKDE.2022.3220219
– volume: 44
  start-page: 9629
  issue: 12
  year: 2021
  ident: 10.1016/j.egyai.2024.100377_b30
  article-title: Triple generative adversarial networks
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2021.3127558
– volume: 33
  start-page: 596
  year: 2020
  ident: 10.1016/j.egyai.2024.100377_b40
  article-title: Fixmatch: Simplifying semi-supervised learning with consistency and confidence
  publication-title: Adv Neural Inf Process Syst
– volume: 78
  start-page: 1152
  year: 2017
  ident: 10.1016/j.egyai.2024.100377_b8
  article-title: Review of harmonic analysis, modeling and mitigation techniques
  publication-title: Renew Sustain Energy Rev
  doi: 10.1016/j.rser.2017.04.121
– volume: 32
  year: 2019
  ident: 10.1016/j.egyai.2024.100377_b39
  article-title: Mixmatch: A holistic approach to semi-supervised learning
  publication-title: Adv Neural Inf Process Syst
– start-page: 1
  year: 2019
  ident: 10.1016/j.egyai.2024.100377_b3
  article-title: Algoritm of current protection based on three instantaneous-value samples
– volume: 192
  year: 2021
  ident: 10.1016/j.egyai.2024.100377_b25
  article-title: Fault classification in power system distribution network integrated with distributed generators using CNN
  publication-title: Electr Power Syst Res
  doi: 10.1016/j.epsr.2020.106914
– volume: 62
  start-page: 701
  issue: 4
  year: 2013
  ident: 10.1016/j.egyai.2024.100377_b13
  article-title: The OpenPMU platform for open-source phasor measurements
  publication-title: IEEE Trans Instrum Meas
  doi: 10.1109/TIM.2013.2240920
– volume: 27
  year: 2014
  ident: 10.1016/j.egyai.2024.100377_b32
  article-title: Semi-supervised learning with deep generative models
  publication-title: Adv Neural Inf Process Syst
– year: 2018
  ident: 10.1016/j.egyai.2024.100377_b31
– volume: 92
  year: 2020
  ident: 10.1016/j.egyai.2024.100377_b27
  article-title: A weighted corrective fuzzy reasoning spiking neural P system for fault diagnosis in power systems with variable topologies
  publication-title: Eng Appl Artif Intell
  doi: 10.1016/j.engappai.2020.103680
– ident: 10.1016/j.egyai.2024.100377_b38
– volume: 6
  start-page: 764
  issue: 8
  year: 2012
  ident: 10.1016/j.egyai.2024.100377_b6
  article-title: Travelling wave time–frequency characteristic-based fault location method for transmission lines
  publication-title: IET Gener Transm Distrib
  doi: 10.1049/iet-gtd.2011.0703
– volume: 124
  year: 2023
  ident: 10.1016/j.egyai.2024.100377_b16
  article-title: Study on a comprehensive indicator and online classification of early warning of low frequency oscillation in power system
  publication-title: Eng Appl Artif Intell
  doi: 10.1016/j.engappai.2023.106592
– volume: 14
  year: 2023
  ident: 10.1016/j.egyai.2024.100377_b19
  article-title: Power flow forecasts at transmission grid nodes using Graph Neural Networks
  publication-title: Energy AI
  doi: 10.1016/j.egyai.2023.100262
– volume: 73
  start-page: 1451
  issue: 7–9
  year: 2010
  ident: 10.1016/j.egyai.2024.100377_b2
  article-title: Power quality disturbance classification using Hilbert transform and RBF networks
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2009.11.008
– volume: 149
  year: 2021
  ident: 10.1016/j.egyai.2024.100377_b41
  article-title: A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery
  publication-title: Mech Syst Signal Process
  doi: 10.1016/j.ymssp.2020.107327
– volume: 26
  start-page: 135
  issue: 1
  year: 2010
  ident: 10.1016/j.egyai.2024.100377_b7
  article-title: A fault-location method for 12-phase transmission lines based on twelve-sequence-component method
  publication-title: IEEE Trans Power Deliv
  doi: 10.1109/TPWRD.2010.2079337
– volume: 34
  start-page: 18408
  year: 2021
  ident: 10.1016/j.egyai.2024.100377_b45
  article-title: Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling
  publication-title: Adv Neural Inf Process Syst
– volume: 29
  year: 2016
  ident: 10.1016/j.egyai.2024.100377_b34
  article-title: Regularization with stochastic transformations and perturbations for deep semi-supervised learning
  publication-title: Adv Neural Inf Process Syst
– volume: 152
  year: 2023
  ident: 10.1016/j.egyai.2024.100377_b5
  article-title: Waveform abnormality detection method for distribution system equipment condition monitoring
  publication-title: Int J Electr Power Energy Syst
  doi: 10.1016/j.ijepes.2023.109267
– volume: 28
  year: 2015
  ident: 10.1016/j.egyai.2024.100377_b33
  article-title: Semi-supervised learning with ladder networks
  publication-title: Adv Neural Inf Process Syst
– volume: 7
  year: 2022
  ident: 10.1016/j.egyai.2024.100377_b10
  article-title: Approximating multi-purpose AC optimal power flow with reinforcement trained artificial neural network
  publication-title: Energy AI
  doi: 10.1016/j.egyai.2021.100133
– volume: 30
  start-page: 2544
  issue: 6
  year: 2015
  ident: 10.1016/j.egyai.2024.100377_b14
  article-title: Synchrophasor-based islanding detection for distributed generation systems using systematic principal component analysis approaches
  publication-title: IEEE Trans Power Deliv
  doi: 10.1109/TPWRD.2015.2435158
– volume: 14
  year: 2023
  ident: 10.1016/j.egyai.2024.100377_b20
  article-title: FedDiSC: A computation-efficient federated learning framework for power systems disturbance and cyber attack discrimination
  publication-title: Energy AI
  doi: 10.1016/j.egyai.2023.100271
– year: 2016
  ident: 10.1016/j.egyai.2024.100377_b36
– volume: 61
  start-page: 8238
  issue: 23
  year: 2023
  ident: 10.1016/j.egyai.2024.100377_b42
  article-title: A novel self-training semi-supervised deep learning approach for machinery fault diagnosis
  publication-title: Int J Prod Res
  doi: 10.1080/00207543.2022.2032860
– volume: 15
  year: 2024
  ident: 10.1016/j.egyai.2024.100377_b17
  article-title: Reviewing 40 years of artificial intelligence applied to power systems–A taxonomic perspective
  publication-title: Energy AI
  doi: 10.1016/j.egyai.2023.100322
– ident: 10.1016/j.egyai.2024.100377_b37
  doi: 10.24963/ijcai.2018/278
– volume: 21
  start-page: 888
  issue: 2
  year: 2020
  ident: 10.1016/j.egyai.2024.100377_b1
  article-title: Fault diagnosis for electrical systems and power networks: A review
  publication-title: IEEE Sens J
  doi: 10.1109/JSEN.2020.2987321
– start-page: 89
  year: 2018
  ident: 10.1016/j.egyai.2024.100377_b22
  article-title: Power system fault detection, classification and location using artificial neural networks
– volume: 32
  start-page: 3875
  issue: 5
  year: 2016
  ident: 10.1016/j.egyai.2024.100377_b9
  article-title: A review on distribution system state estimation
  publication-title: IEEE Trans Power Syst
  doi: 10.1109/TPWRS.2016.2632156
– year: 2013
  ident: 10.1016/j.egyai.2024.100377_b11
– volume: 14
  year: 2023
  ident: 10.1016/j.egyai.2024.100377_b21
  article-title: A comparative evaluation of Stacked Auto-Encoder neural network and Multi-Layer Extreme Learning Machine for detection and classification of faults in transmission lines using WAMS data
  publication-title: Energy AI
  doi: 10.1016/j.egyai.2023.100301
– volume: 7
  start-page: 184020
  year: 2019
  ident: 10.1016/j.egyai.2024.100377_b23
  article-title: Series arc fault detection of indoor power distribution system based on LVQ-NN and PSO-SVM
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2960512
– start-page: 2971
  issue: 9
  year: 1983
  ident: 10.1016/j.egyai.2024.100377_b4
  article-title: Distance protection based on travelling waves
  publication-title: IEEE Trans Power Appar Syst
  doi: 10.1109/TPAS.1983.318102
– volume: 6
  start-page: 619
  issue: 4
  year: 2018
  ident: 10.1016/j.egyai.2024.100377_b12
  article-title: Phasor measurement units, WAMS, and their applications in protection and control of power systems
  publication-title: J Mod Power Syst Clean Energy
  doi: 10.1007/s40565-018-0423-3
SSID ssj0002511977
Score 2.300503
Snippet With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle...
SourceID doaj
crossref
elsevier
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 100377
SubjectTerms Data driven
Deep learning
Power grid fault detection
Semi-supervised learning
Smart grid
Title An enhanced semi-supervised learning method with self-supervised and adaptive threshold for fault detection and classification in urban power grids
URI https://dx.doi.org/10.1016/j.egyai.2024.100377
https://doaj.org/article/0682971025b245739b83d86db77260a9
Volume 17
WOSCitedRecordID wos001264977600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2666-5468
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511977
  issn: 2666-5468
  databaseCode: DOA
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2666-5468
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511977
  issn: 2666-5468
  databaseCode: M~E
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwELYqxIEeKh6tuuUhHzg2amJ77fgICMShRRyoxC3yK9ugrVltspW48Cf4w8w4WRQucOkhkTKa2JFn7JmJx98Qcmwl2CjPRea84pkoapfZ2pWZY6bIrReM2XRQ-Ke6uipvb_X1qNQX5oT18MD9wP3IJR7-BDM4tUxMFde25L6U3oJbKHOTju7lSo-CKVyDWdoeU2uYoZTQFWYPpoGIkAlMDeBKvTJFCbF_ZJFGVuZim3wa3EN60n_WDvkQ4i75OAIN3CNPJ5GG-Cft3NM2_G2ydrXAGd_C81AEYkb7ytAUf7MC07weM5kIlzcLXOloB8JscQ-KgvtKa7Oad9SHLmVoxcTq0MHGjKIkRNpEulpaE-kCC6zR2bLx7Wfy--L85uwyG0orZE4Uoss0h3mXh8Joa8GnYCH3NYyxtNyEoqiFwYmuvZ_aGmjcSAhLWGm0VMZwEWr-hWzE-xi-EupVKfPSB6YZhFZalAaCOAZUxw2ii00IW49y5QbccSx_Ma_WCWZ3VRJNhaKpetFMyPeXlxY97Mbb7KcovhdWxMxOBNCkatCk6j1NmhC5Fn41uB-9WwFNNW_1_u1_9L5PtrDJPn3tgGx0y1U4JJvuX9e0y6Ok3XD_9Xj-DI5a_64
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=An+enhanced+semi-supervised+learning+method+with+self-supervised+and+adaptive+threshold+for+fault+detection+and+classification+in+urban+power+grids&rft.jtitle=Energy+and+AI&rft.au=Zhang%2C+Jiahao&rft.au=Cheng%2C+Lan&rft.au=Yang%2C+Zhile&rft.au=Xiao%2C+Qinge&rft.date=2024-09-01&rft.issn=2666-5468&rft.eissn=2666-5468&rft.volume=17&rft.spage=100377&rft_id=info:doi/10.1016%2Fj.egyai.2024.100377&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_egyai_2024_100377
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2666-5468&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2666-5468&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2666-5468&client=summon