Residual learning-based robotic image analysis model for low-voltage distributed photovoltaic fault identification and positioning
With the fast development of large-scale Photovoltaic (PV) plants, the automatic PV fault identification and positioning have become an important task for the PV intelligent systems, aiming to guarantee the safety, reliability, and productivity of large-scale PV plants. In this paper, we propose a r...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2024.1396979/full |
| _version_ | 1827276703583436800 |
|---|---|
| author | Xudong Zhang Yunlong Ge Yifeng Wang Jun Wang Wenhao Wang Lijun Lu |
| author_facet | Xudong Zhang Yunlong Ge Yifeng Wang Jun Wang Wenhao Wang Lijun Lu |
| author_sort | Xudong Zhang |
| collection | DOAJ |
| description | With the fast development of large-scale Photovoltaic (PV) plants, the automatic PV fault identification and positioning have become an important task for the PV intelligent systems, aiming to guarantee the safety, reliability, and productivity of large-scale PV plants. In this paper, we propose a residual learning-based robotic (UAV) image analysis model for low-voltage distributed PV fault identification and positioning. In our target scenario, the unmanned aerial vehicles (UAVs) are deployed to acquire moving images of low-voltage distributed PV power plants. To get desired robustness and accuracy of PV image detection, we integrate residual learning with attention mechanism into the UAV image analysis model based on you only look once v4 (YOLOv4) network. Then, we design the sophisticated multi-scale spatial pyramid fusion and use it to optimize the YOLOv4 network for the nuanced task of fault localization within PV arrays, where the Complete-IOU loss is incorporated in the predictive modeling phase, significantly enhancing the accuracy and efficiency of fault detection. A series of experimental comparisons in terms of the accuracy of fault positioning are conducted, and the experimental results verify the feasibility and effectiveness of the proposed model in dealing with the safety and reliability maintenance of low-voltage distributed PV systems. |
| first_indexed | 2024-04-24T07:04:14Z |
| format | Article |
| id | doaj.art-5b96afe0ac574d9a8f7a2f5e150dc110 |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-04-24T07:04:14Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-5b96afe0ac574d9a8f7a2f5e150dc1102024-04-22T04:54:55ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182024-04-011810.3389/fnbot.2024.13969791396979Residual learning-based robotic image analysis model for low-voltage distributed photovoltaic fault identification and positioningXudong Zhang0Yunlong Ge1Yifeng Wang2Jun Wang3Wenhao Wang4Lijun Lu5State Grid Hebei Electric Power Company, Shijiazhuang, ChinaState Grid Hebei Electric Power Company, Shijiazhuang, ChinaState Grid Hebei Electric Power Company, Shijiazhuang, ChinaHenan XJ Metering Co., Ltd., Xuchang, ChinaHenan XJ Metering Co., Ltd., Xuchang, ChinaHenan XJ Metering Co., Ltd., Xuchang, ChinaWith the fast development of large-scale Photovoltaic (PV) plants, the automatic PV fault identification and positioning have become an important task for the PV intelligent systems, aiming to guarantee the safety, reliability, and productivity of large-scale PV plants. In this paper, we propose a residual learning-based robotic (UAV) image analysis model for low-voltage distributed PV fault identification and positioning. In our target scenario, the unmanned aerial vehicles (UAVs) are deployed to acquire moving images of low-voltage distributed PV power plants. To get desired robustness and accuracy of PV image detection, we integrate residual learning with attention mechanism into the UAV image analysis model based on you only look once v4 (YOLOv4) network. Then, we design the sophisticated multi-scale spatial pyramid fusion and use it to optimize the YOLOv4 network for the nuanced task of fault localization within PV arrays, where the Complete-IOU loss is incorporated in the predictive modeling phase, significantly enhancing the accuracy and efficiency of fault detection. A series of experimental comparisons in terms of the accuracy of fault positioning are conducted, and the experimental results verify the feasibility and effectiveness of the proposed model in dealing with the safety and reliability maintenance of low-voltage distributed PV systems.https://www.frontiersin.org/articles/10.3389/fnbot.2024.1396979/fulllow-voltage distributed photovoltaicsphotovoltaic identificationpositioning technologyunmanned aerial vehicle imageryhorizontal comparison experiment |
| spellingShingle | Xudong Zhang Yunlong Ge Yifeng Wang Jun Wang Wenhao Wang Lijun Lu Residual learning-based robotic image analysis model for low-voltage distributed photovoltaic fault identification and positioning Frontiers in Neurorobotics low-voltage distributed photovoltaics photovoltaic identification positioning technology unmanned aerial vehicle imagery horizontal comparison experiment |
| title | Residual learning-based robotic image analysis model for low-voltage distributed photovoltaic fault identification and positioning |
| title_full | Residual learning-based robotic image analysis model for low-voltage distributed photovoltaic fault identification and positioning |
| title_fullStr | Residual learning-based robotic image analysis model for low-voltage distributed photovoltaic fault identification and positioning |
| title_full_unstemmed | Residual learning-based robotic image analysis model for low-voltage distributed photovoltaic fault identification and positioning |
| title_short | Residual learning-based robotic image analysis model for low-voltage distributed photovoltaic fault identification and positioning |
| title_sort | residual learning based robotic image analysis model for low voltage distributed photovoltaic fault identification and positioning |
| topic | low-voltage distributed photovoltaics photovoltaic identification positioning technology unmanned aerial vehicle imagery horizontal comparison experiment |
| url | https://www.frontiersin.org/articles/10.3389/fnbot.2024.1396979/full |
| work_keys_str_mv | AT xudongzhang residuallearningbasedroboticimageanalysismodelforlowvoltagedistributedphotovoltaicfaultidentificationandpositioning AT yunlongge residuallearningbasedroboticimageanalysismodelforlowvoltagedistributedphotovoltaicfaultidentificationandpositioning AT yifengwang residuallearningbasedroboticimageanalysismodelforlowvoltagedistributedphotovoltaicfaultidentificationandpositioning AT junwang residuallearningbasedroboticimageanalysismodelforlowvoltagedistributedphotovoltaicfaultidentificationandpositioning AT wenhaowang residuallearningbasedroboticimageanalysismodelforlowvoltagedistributedphotovoltaicfaultidentificationandpositioning AT lijunlu residuallearningbasedroboticimageanalysismodelforlowvoltagedistributedphotovoltaicfaultidentificationandpositioning |