Series Arc Fault Identification Method Based on Multi-Feature Fusion
With the increase of various loads connected to the low-voltage distribution system, the difficulty of identifying low-voltage series fault arcs has greatly increased, which seriously threatens the electricity safety. Aiming at such problems, a neural network algorithm based on multi-feature fusion...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2021.824414/full |
| _version_ | 1798025515378933760 |
|---|---|
| author | Quanyi Gong Ke Peng Wei Wang Bingyin Xu Xinhui Zhang Yu Chen |
| author_facet | Quanyi Gong Ke Peng Wei Wang Bingyin Xu Xinhui Zhang Yu Chen |
| author_sort | Quanyi Gong |
| collection | DOAJ |
| description | With the increase of various loads connected to the low-voltage distribution system, the difficulty of identifying low-voltage series fault arcs has greatly increased, which seriously threatens the electricity safety. Aiming at such problems, a neural network algorithm based on multi-feature fusion is proposed. The fault current has the characteristics of randomness, high frequency noise, and singularity. A GA-BP neural network model is built, and the wavelet analysis method (based on singularity), Fourier transform method (based on high frequency noise), current cycle difference method (based on randomness), and current cycle similarity derivation method (based on randomness) are used for feature extraction and can more comprehensively reflect the characteristics of arc faults. Simulation results show that the multi-feature fusion algorithm has a higher recognition rate than other algorithms. Moreover, compared with the support vector machine model, logistic regression model, and AlexNet model, the GA-BP neural network model has a higher recognition accuracy than the other three models, which can reach 99%. |
| first_indexed | 2024-04-11T18:19:56Z |
| format | Article |
| id | doaj.art-87e3bd87397f4cd4814f58e1a6d68ed0 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-04-11T18:19:56Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-87e3bd87397f4cd4814f58e1a6d68ed02022-12-22T04:09:48ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2022-01-01910.3389/fenrg.2021.824414824414Series Arc Fault Identification Method Based on Multi-Feature FusionQuanyi GongKe PengWei WangBingyin XuXinhui ZhangYu ChenWith the increase of various loads connected to the low-voltage distribution system, the difficulty of identifying low-voltage series fault arcs has greatly increased, which seriously threatens the electricity safety. Aiming at such problems, a neural network algorithm based on multi-feature fusion is proposed. The fault current has the characteristics of randomness, high frequency noise, and singularity. A GA-BP neural network model is built, and the wavelet analysis method (based on singularity), Fourier transform method (based on high frequency noise), current cycle difference method (based on randomness), and current cycle similarity derivation method (based on randomness) are used for feature extraction and can more comprehensively reflect the characteristics of arc faults. Simulation results show that the multi-feature fusion algorithm has a higher recognition rate than other algorithms. Moreover, compared with the support vector machine model, logistic regression model, and AlexNet model, the GA-BP neural network model has a higher recognition accuracy than the other three models, which can reach 99%.https://www.frontiersin.org/articles/10.3389/fenrg.2021.824414/fulllow-voltage series arcneural networksfault identificationmulti-feature fusionarc fault characteristics |
| spellingShingle | Quanyi Gong Ke Peng Wei Wang Bingyin Xu Xinhui Zhang Yu Chen Series Arc Fault Identification Method Based on Multi-Feature Fusion Frontiers in Energy Research low-voltage series arc neural networks fault identification multi-feature fusion arc fault characteristics |
| title | Series Arc Fault Identification Method Based on Multi-Feature Fusion |
| title_full | Series Arc Fault Identification Method Based on Multi-Feature Fusion |
| title_fullStr | Series Arc Fault Identification Method Based on Multi-Feature Fusion |
| title_full_unstemmed | Series Arc Fault Identification Method Based on Multi-Feature Fusion |
| title_short | Series Arc Fault Identification Method Based on Multi-Feature Fusion |
| title_sort | series arc fault identification method based on multi feature fusion |
| topic | low-voltage series arc neural networks fault identification multi-feature fusion arc fault characteristics |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2021.824414/full |
| work_keys_str_mv | AT quanyigong seriesarcfaultidentificationmethodbasedonmultifeaturefusion AT kepeng seriesarcfaultidentificationmethodbasedonmultifeaturefusion AT weiwang seriesarcfaultidentificationmethodbasedonmultifeaturefusion AT bingyinxu seriesarcfaultidentificationmethodbasedonmultifeaturefusion AT xinhuizhang seriesarcfaultidentificationmethodbasedonmultifeaturefusion AT yuchen seriesarcfaultidentificationmethodbasedonmultifeaturefusion |