A data-driven impedance estimation and matching method for high impedance fault detection and location of distribution networks
High impedance fault (HIF) is the most difficult fault type to recognize in power systems because their fault currents are small and difficult to distinguish from normal load fluctuations. Currently, most HIF identification methods are based on transient measurement data, and their dependence on hig...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-04-01
|
| Series: | International Journal of Electrical Power & Energy Systems |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S014206152500050X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206952819425280 |
|---|---|
| author | Zhenyu Zhang Yong Li Zhiyu Wang Junle Liu An Chen Yijia Cao |
| author_facet | Zhenyu Zhang Yong Li Zhiyu Wang Junle Liu An Chen Yijia Cao |
| author_sort | Zhenyu Zhang |
| collection | DOAJ |
| description | High impedance fault (HIF) is the most difficult fault type to recognize in power systems because their fault currents are small and difficult to distinguish from normal load fluctuations. Currently, most HIF identification methods are based on transient measurement data, and their dependence on high-frequency measurements, communication and data processing capabilities increases the cost and limits the application of these methods. This paper proposes a novel, data-driven two-stage HIF identification method based on line impedance estimation, which matches the estimated results with fault location information. The approach treats each line as a target, allowing for precise HIF identification between specific measurement nodes rather than at percentage locations along the full length of the line. Experimental results conducted on the IEEE 33 bus system show that the proposed method can pinpoint the occurrence of HIFs with 99.85% accuracy in the absence of noise and an accuracy of 91.72% with a signal-to-noise ratio of 60 dB for load identification results, demonstrating its effectiveness. |
| format | Article |
| id | doaj-art-69c3f61152ce4a7caea0f1598b15549a |
| institution | Kabale University |
| issn | 0142-0615 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Electrical Power & Energy Systems |
| spelling | doaj-art-69c3f61152ce4a7caea0f1598b15549a2025-02-07T04:46:35ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-04-01165110499A data-driven impedance estimation and matching method for high impedance fault detection and location of distribution networksZhenyu Zhang0Yong Li1Zhiyu Wang2Junle Liu3An Chen4Yijia Cao5College of Electrical and Information Engineering, Hunan University, Changsha, 410000, Hunan Province, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha, 410000, Hunan Province, China; Corresponding author.College of Electrical and Information Engineering, Hunan University, Changsha, 410000, Hunan Province, ChinaCSG Guangdong Power Grid Corporation Zhongshan Power Supply Bureau, Zhongshan, 528400, Guangdong Province, ChinaCSG Guangdong Power Grid Corporation Zhongshan Power Supply Bureau, Zhongshan, 528400, Guangdong Province, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha, 410000, Hunan Province, ChinaHigh impedance fault (HIF) is the most difficult fault type to recognize in power systems because their fault currents are small and difficult to distinguish from normal load fluctuations. Currently, most HIF identification methods are based on transient measurement data, and their dependence on high-frequency measurements, communication and data processing capabilities increases the cost and limits the application of these methods. This paper proposes a novel, data-driven two-stage HIF identification method based on line impedance estimation, which matches the estimated results with fault location information. The approach treats each line as a target, allowing for precise HIF identification between specific measurement nodes rather than at percentage locations along the full length of the line. Experimental results conducted on the IEEE 33 bus system show that the proposed method can pinpoint the occurrence of HIFs with 99.85% accuracy in the absence of noise and an accuracy of 91.72% with a signal-to-noise ratio of 60 dB for load identification results, demonstrating its effectiveness.http://www.sciencedirect.com/science/article/pii/S014206152500050XHigh impedance fault detectionMachine learningPower systemDistribution network |
| spellingShingle | Zhenyu Zhang Yong Li Zhiyu Wang Junle Liu An Chen Yijia Cao A data-driven impedance estimation and matching method for high impedance fault detection and location of distribution networks International Journal of Electrical Power & Energy Systems High impedance fault detection Machine learning Power system Distribution network |
| title | A data-driven impedance estimation and matching method for high impedance fault detection and location of distribution networks |
| title_full | A data-driven impedance estimation and matching method for high impedance fault detection and location of distribution networks |
| title_fullStr | A data-driven impedance estimation and matching method for high impedance fault detection and location of distribution networks |
| title_full_unstemmed | A data-driven impedance estimation and matching method for high impedance fault detection and location of distribution networks |
| title_short | A data-driven impedance estimation and matching method for high impedance fault detection and location of distribution networks |
| title_sort | data driven impedance estimation and matching method for high impedance fault detection and location of distribution networks |
| topic | High impedance fault detection Machine learning Power system Distribution network |
| url | http://www.sciencedirect.com/science/article/pii/S014206152500050X |
| work_keys_str_mv | AT zhenyuzhang adatadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT yongli adatadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT zhiyuwang adatadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT junleliu adatadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT anchen adatadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT yijiacao adatadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT zhenyuzhang datadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT yongli datadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT zhiyuwang datadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT junleliu datadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT anchen datadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks AT yijiacao datadrivenimpedanceestimationandmatchingmethodforhighimpedancefaultdetectionandlocationofdistributionnetworks |