An incremental high impedance fault detection method under non-stationary environments in distribution networks
In the non-stationary environments of distribution networks, where operating conditions continually evolve, maintaining reliable high impedance faults (HIF) detection is a significant challenge due to the frequent changes in data distribution caused by environmental variations. In this paper, we pro...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | International Journal of Electrical Power & Energy Systems |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0142061523007627 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846157851477671936 |
|---|---|
| author | Mou-Fa Guo Meitao Yao Jian-Hong Gao Wen-Li Liu Shuyue Lin |
| author_facet | Mou-Fa Guo Meitao Yao Jian-Hong Gao Wen-Li Liu Shuyue Lin |
| author_sort | Mou-Fa Guo |
| collection | DOAJ |
| description | In the non-stationary environments of distribution networks, where operating conditions continually evolve, maintaining reliable high impedance faults (HIF) detection is a significant challenge due to the frequent changes in data distribution caused by environmental variations. In this paper, we propose a novel HIF detection method based on incremental learning to handle non-stationary data stream with changing distributions. The proposed method utilizes stationary wavelet transform (SWT) to extract fault characteristics in different frequency domains from zero-sequence current data. Subsequently, a complex mapping from signal features to operational conditions is established using backpropagation neural network (BPNN) to achieve online detection of HIF. Additionally, signal features are analyzed using density-based spatial clustering of applications with noise (DBSCAN) to monitor the distribution of data. After encountering multiple distribution changes, an incremental learning process based on data replay is initiated to evolve the BPNN model for adapting to the changing data distribution. It is worth noting that the data replay mechanism ensures that the model retains previously acquired knowledge while learning from newly encountered data distributions. The proposed method was implemented in a prototype of a designed edge intelligent terminal and validated using a 10 kV testing system data. The experimental results indicate that the proposed method is capable of identifying and learning new distribution data information within non-stationary data stream. This enables the classifier model to maintain a high level of detection accuracy for the current cycle data, effectively enhancing the reliability of HIF detection. |
| format | Article |
| id | doaj-art-f6b6570aa2a74b26b038b7c0d6a001b8 |
| institution | Kabale University |
| issn | 0142-0615 |
| language | English |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Electrical Power & Energy Systems |
| spelling | doaj-art-f6b6570aa2a74b26b038b7c0d6a001b82024-11-25T04:40:33ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152024-02-01156109705An incremental high impedance fault detection method under non-stationary environments in distribution networksMou-Fa Guo0Meitao Yao1Jian-Hong Gao2Wen-Li Liu3Shuyue Lin4College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China; Engineering Research Center of Smart Distribution Grid Equipment, Fujian Province University, Fuzhou 350108, ChinaCollege of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China; Engineering Research Center of Smart Distribution Grid Equipment, Fujian Province University, Fuzhou 350108, ChinaCollege of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China; School of Engineering, University of Hull, Hull HU67RX, UK; Department of Electrical Engineering, Yuan Ze University, Taoyuan 32003, Taiwan; Engineering Research Center of Smart Distribution Grid Equipment, Fujian Province University, Fuzhou 350108, China; Corresponding author.College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China; Engineering Research Center of Smart Distribution Grid Equipment, Fujian Province University, Fuzhou 350108, ChinaSchool of Engineering, University of Hull, Hull HU67RX, UKIn the non-stationary environments of distribution networks, where operating conditions continually evolve, maintaining reliable high impedance faults (HIF) detection is a significant challenge due to the frequent changes in data distribution caused by environmental variations. In this paper, we propose a novel HIF detection method based on incremental learning to handle non-stationary data stream with changing distributions. The proposed method utilizes stationary wavelet transform (SWT) to extract fault characteristics in different frequency domains from zero-sequence current data. Subsequently, a complex mapping from signal features to operational conditions is established using backpropagation neural network (BPNN) to achieve online detection of HIF. Additionally, signal features are analyzed using density-based spatial clustering of applications with noise (DBSCAN) to monitor the distribution of data. After encountering multiple distribution changes, an incremental learning process based on data replay is initiated to evolve the BPNN model for adapting to the changing data distribution. It is worth noting that the data replay mechanism ensures that the model retains previously acquired knowledge while learning from newly encountered data distributions. The proposed method was implemented in a prototype of a designed edge intelligent terminal and validated using a 10 kV testing system data. The experimental results indicate that the proposed method is capable of identifying and learning new distribution data information within non-stationary data stream. This enables the classifier model to maintain a high level of detection accuracy for the current cycle data, effectively enhancing the reliability of HIF detection.http://www.sciencedirect.com/science/article/pii/S0142061523007627High impedance faultIncremental learningData replayDistribution network |
| spellingShingle | Mou-Fa Guo Meitao Yao Jian-Hong Gao Wen-Li Liu Shuyue Lin An incremental high impedance fault detection method under non-stationary environments in distribution networks International Journal of Electrical Power & Energy Systems High impedance fault Incremental learning Data replay Distribution network |
| title | An incremental high impedance fault detection method under non-stationary environments in distribution networks |
| title_full | An incremental high impedance fault detection method under non-stationary environments in distribution networks |
| title_fullStr | An incremental high impedance fault detection method under non-stationary environments in distribution networks |
| title_full_unstemmed | An incremental high impedance fault detection method under non-stationary environments in distribution networks |
| title_short | An incremental high impedance fault detection method under non-stationary environments in distribution networks |
| title_sort | incremental high impedance fault detection method under non stationary environments in distribution networks |
| topic | High impedance fault Incremental learning Data replay Distribution network |
| url | http://www.sciencedirect.com/science/article/pii/S0142061523007627 |
| work_keys_str_mv | AT moufaguo anincrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks AT meitaoyao anincrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks AT jianhonggao anincrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks AT wenliliu anincrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks AT shuyuelin anincrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks AT moufaguo incrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks AT meitaoyao incrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks AT jianhonggao incrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks AT wenliliu incrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks AT shuyuelin incrementalhighimpedancefaultdetectionmethodundernonstationaryenvironmentsindistributionnetworks |