A Real Data-Driven Fault Diagnosing Method for Distribution Networks Based on ResBlock-CBAM-CNN
Power distribution systems frequently encounter various fault-causing events. Thus, prompt and accurate fault diagnosis is crucial for maintaining system stability and safety. This study presents an innovative residual block-convolutional block attention module-convolutional neural network (ResBlock...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Electricity |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4826/6/2/19 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849472477771595776 |
|---|---|
| author | Yuhai Yao Hao Ma Cheng Gong Yifei Li Qiao Zhao Ning Wei Bin Yang |
| author_facet | Yuhai Yao Hao Ma Cheng Gong Yifei Li Qiao Zhao Ning Wei Bin Yang |
| author_sort | Yuhai Yao |
| collection | DOAJ |
| description | Power distribution systems frequently encounter various fault-causing events. Thus, prompt and accurate fault diagnosis is crucial for maintaining system stability and safety. This study presents an innovative residual block-convolutional block attention module-convolutional neural network (ResBlock-CBAM-CNN)-based method for fault cause diagnosis. To enhance diagnostic precision further, the proposed approach incorporates a multimodal data fusion model. This model combines raw on-site measurements, processed data, and external environmental information to extract relevant fault-related details. Empirical results show that the ResBlock-CBAM-CNN method, with data fusion, outperforms existing techniques significantly in fault identification accuracy. Additionally, t-SNE visualization of fault data validates the effectiveness of this approach. Unlike studies that rely on simulated datasets, this research uses real-world measurements, highlighting the practical applicability and value of the proposed model for fault cause diagnosis in power distribution systems. |
| format | Article |
| id | doaj-art-9609629d88d041a18686d96d77aebefd |
| institution | Kabale University |
| issn | 2673-4826 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electricity |
| spelling | doaj-art-9609629d88d041a18686d96d77aebefd2025-08-20T03:24:32ZengMDPI AGElectricity2673-48262025-04-01621910.3390/electricity6020019A Real Data-Driven Fault Diagnosing Method for Distribution Networks Based on ResBlock-CBAM-CNNYuhai Yao0Hao Ma1Cheng Gong2Yifei Li3Qiao Zhao4Ning Wei5Bin Yang6State Grid Beijing Electric Power Research Institute, Beijing 100075, ChinaState Grid Beijing Electric Power Research Institute, Beijing 100075, ChinaState Grid Beijing Electric Power Research Institute, Beijing 100075, ChinaState Grid Beijing Electric Power Research Institute, Beijing 100075, ChinaState Grid Beijing Electric Power Research Institute, Beijing 100075, ChinaState Key Laboratory of Intelligent Power Distribution Equipment and System, Hebei University of Technology, Tianjin 300401, ChinaState Key Laboratory of Intelligent Power Distribution Equipment and System, Hebei University of Technology, Tianjin 300401, ChinaPower distribution systems frequently encounter various fault-causing events. Thus, prompt and accurate fault diagnosis is crucial for maintaining system stability and safety. This study presents an innovative residual block-convolutional block attention module-convolutional neural network (ResBlock-CBAM-CNN)-based method for fault cause diagnosis. To enhance diagnostic precision further, the proposed approach incorporates a multimodal data fusion model. This model combines raw on-site measurements, processed data, and external environmental information to extract relevant fault-related details. Empirical results show that the ResBlock-CBAM-CNN method, with data fusion, outperforms existing techniques significantly in fault identification accuracy. Additionally, t-SNE visualization of fault data validates the effectiveness of this approach. Unlike studies that rely on simulated datasets, this research uses real-world measurements, highlighting the practical applicability and value of the proposed model for fault cause diagnosis in power distribution systems.https://www.mdpi.com/2673-4826/6/2/19convolutional block attention modulepower distribution networkfault cause diagnosismachine learning |
| spellingShingle | Yuhai Yao Hao Ma Cheng Gong Yifei Li Qiao Zhao Ning Wei Bin Yang A Real Data-Driven Fault Diagnosing Method for Distribution Networks Based on ResBlock-CBAM-CNN Electricity convolutional block attention module power distribution network fault cause diagnosis machine learning |
| title | A Real Data-Driven Fault Diagnosing Method for Distribution Networks Based on ResBlock-CBAM-CNN |
| title_full | A Real Data-Driven Fault Diagnosing Method for Distribution Networks Based on ResBlock-CBAM-CNN |
| title_fullStr | A Real Data-Driven Fault Diagnosing Method for Distribution Networks Based on ResBlock-CBAM-CNN |
| title_full_unstemmed | A Real Data-Driven Fault Diagnosing Method for Distribution Networks Based on ResBlock-CBAM-CNN |
| title_short | A Real Data-Driven Fault Diagnosing Method for Distribution Networks Based on ResBlock-CBAM-CNN |
| title_sort | real data driven fault diagnosing method for distribution networks based on resblock cbam cnn |
| topic | convolutional block attention module power distribution network fault cause diagnosis machine learning |
| url | https://www.mdpi.com/2673-4826/6/2/19 |
| work_keys_str_mv | AT yuhaiyao arealdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT haoma arealdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT chenggong arealdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT yifeili arealdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT qiaozhao arealdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT ningwei arealdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT binyang arealdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT yuhaiyao realdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT haoma realdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT chenggong realdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT yifeili realdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT qiaozhao realdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT ningwei realdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn AT binyang realdatadrivenfaultdiagnosingmethodfordistributionnetworksbasedonresblockcbamcnn |