PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection
The rapid development of the photovoltaic industry in recent years has made the efficient and accurate completion of photovoltaic operation and maintenance a major focus in recent studies. The key to photovoltaic operation and maintenance is the accurate multifault identification of photovoltaic pan...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10032147/ |
| _version_ | 1811169695119704064 |
|---|---|
| author | Wang Yin Shen Lingxin Li Maohuan Sun Qianlai Li Xiaosong |
| author_facet | Wang Yin Shen Lingxin Li Maohuan Sun Qianlai Li Xiaosong |
| author_sort | Wang Yin |
| collection | DOAJ |
| description | The rapid development of the photovoltaic industry in recent years has made the efficient and accurate completion of photovoltaic operation and maintenance a major focus in recent studies. The key to photovoltaic operation and maintenance is the accurate multifault identification of photovoltaic panel images collected using drones. In this paper, PV-YOLO is proposed to replace YOLOX’s backbone network, CSPDarknet53, with a transformer-based PVTv2 network to obtain local connections between images and feature maps to extract more edge-detail features of similar faults. The CBAM attention mechanism is added to enhance the effective features and improve the detection accuracy of small objects. The label assignment mechanism is optimized, and the SIoU loss functionis used to improve the uneven distribution of samples and accelerate network convergence. Experiments on the dataset prove that this method is superior to the existing technology, as the highest mAP value is 92.56%. This value is 10.46% higher than that of YOLOX, and the mAP is optimal under the same parameter magnitude,proving the model’s effectiveness.Moreover, mAP is increased by over 10%, especially for small targets. In this paper, we implemented a lightweight design for the model, and proposes four models of different sizes to be-sized models that are suitable for different detection scenarios. |
| first_indexed | 2024-04-10T16:46:31Z |
| format | Article |
| id | doaj.art-673c429341a34621b8ecdb93ad9253c1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T16:46:31Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-673c429341a34621b8ecdb93ad9253c12023-02-08T00:00:13ZengIEEEIEEE Access2169-35362023-01-0111109661097610.1109/ACCESS.2023.324089410032147PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault DetectionWang Yin0Shen Lingxin1https://orcid.org/0000-0002-0573-0286Li Maohuan2Sun Qianlai3https://orcid.org/0000-0001-6914-0587Li Xiaosong4https://orcid.org/0000-0002-8688-1333College of Electronic Information Engineering, Taiyuan University of Science and Technology, Shanxi, Taiyuan, ChinaCollege of Electronic Information Engineering, Taiyuan University of Science and Technology, Shanxi, Taiyuan, ChinaCollege of Electronic Information Engineering, Taiyuan University of Science and Technology, Shanxi, Taiyuan, ChinaCollege of Electronic Information Engineering, Taiyuan University of Science and Technology, Shanxi, Taiyuan, ChinaCollege of Electronic Information Engineering, Taiyuan University of Science and Technology, Shanxi, Taiyuan, ChinaThe rapid development of the photovoltaic industry in recent years has made the efficient and accurate completion of photovoltaic operation and maintenance a major focus in recent studies. The key to photovoltaic operation and maintenance is the accurate multifault identification of photovoltaic panel images collected using drones. In this paper, PV-YOLO is proposed to replace YOLOX’s backbone network, CSPDarknet53, with a transformer-based PVTv2 network to obtain local connections between images and feature maps to extract more edge-detail features of similar faults. The CBAM attention mechanism is added to enhance the effective features and improve the detection accuracy of small objects. The label assignment mechanism is optimized, and the SIoU loss functionis used to improve the uneven distribution of samples and accelerate network convergence. Experiments on the dataset prove that this method is superior to the existing technology, as the highest mAP value is 92.56%. This value is 10.46% higher than that of YOLOX, and the mAP is optimal under the same parameter magnitude,proving the model’s effectiveness.Moreover, mAP is increased by over 10%, especially for small targets. In this paper, we implemented a lightweight design for the model, and proposes four models of different sizes to be-sized models that are suitable for different detection scenarios.https://ieeexplore.ieee.org/document/10032147/Photovoltaic panel failuretarget detectionYOLOXtransformerlightweight |
| spellingShingle | Wang Yin Shen Lingxin Li Maohuan Sun Qianlai Li Xiaosong PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection IEEE Access Photovoltaic panel failure target detection YOLOX transformer lightweight |
| title | PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection |
| title_full | PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection |
| title_fullStr | PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection |
| title_full_unstemmed | PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection |
| title_short | PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection |
| title_sort | pv yolo lightweight yolo for photovoltaic panel fault detection |
| topic | Photovoltaic panel failure target detection YOLOX transformer lightweight |
| url | https://ieeexplore.ieee.org/document/10032147/ |
| work_keys_str_mv | AT wangyin pvyololightweightyoloforphotovoltaicpanelfaultdetection AT shenlingxin pvyololightweightyoloforphotovoltaicpanelfaultdetection AT limaohuan pvyololightweightyoloforphotovoltaicpanelfaultdetection AT sunqianlai pvyololightweightyoloforphotovoltaicpanelfaultdetection AT lixiaosong pvyololightweightyoloforphotovoltaicpanelfaultdetection |