Anomaly Detection for PV Modules Using Multi-Modal Data Fusion in Aerial Inspections
Solar energy is a compelling and growing avenue for transitioning towards reliance on sustainable and environmentally friendly energy sources. However, the performance of individual photovoltaic (PV) panels is vulnerable to defects inflicted by weather exposure. The industry currently addresses thes...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11006036/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849714368503087104 |
|---|---|
| author | Lourenco Sousa Pinho Tiago Daniel Sousa Celso D. Pereira Andry M. Pinto |
| author_facet | Lourenco Sousa Pinho Tiago Daniel Sousa Celso D. Pereira Andry M. Pinto |
| author_sort | Lourenco Sousa Pinho |
| collection | DOAJ |
| description | Solar energy is a compelling and growing avenue for transitioning towards reliance on sustainable and environmentally friendly energy sources. However, the performance of individual photovoltaic (PV) panels is vulnerable to defects inflicted by weather exposure. The industry currently addresses these challenges by conducting manual inspections at each PV installation, a process that is highly time-consuming, financially burdensome, difficult to scale, prone to human error, and sometimes unfeasible due to topographical constraints. This study aims to develop a solution that detects these defects in real time resorting to an Autonomous Aerial Vehicle (AAV) equipped with for a thermal and a visual sensor. This paper contributes three major advancements to PV defect detection: a robust, standardized dataset built following IEC TS 62446-3 specifications with annotations from a real PV power plant, a novel multi-spectral approach that leverages early fusion of visual and thermal data captured via an AAV, and benchmark performance metrics for defect detection using state-of-the-art AI models. Our implementation uses Real-Time DEtection TRansformer (RT-DETR) and You Only Look Once (YOLO) models, achieving a mean Average Precision@50 (mAP) of 94% for RT-DETR and a mAP@50 of nearly 95% for YOLOv11. These results demonstrate the effectiveness of our approach in real-world settings, addressing a significant operational challenge in PV plant maintenance while establishing new performance benchmarks for automated defect detection in industrial solar installations. |
| format | Article |
| id | doaj-art-3bc3a98a897f48b291ee3b704f27c0dd |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-3bc3a98a897f48b291ee3b704f27c0dd2025-08-20T03:13:43ZengIEEEIEEE Access2169-35362025-01-0113887628877910.1109/ACCESS.2025.357081511006036Anomaly Detection for PV Modules Using Multi-Modal Data Fusion in Aerial InspectionsLourenco Sousa Pinho0https://orcid.org/0009-0007-5607-9749Tiago Daniel Sousa1https://orcid.org/0009-0009-3975-9835Celso D. Pereira2https://orcid.org/0000-0003-4797-696XAndry M. Pinto3https://orcid.org/0000-0003-2465-5813Department of Electrical and Computer Engineering, Faculty of Engineering, University of Porto, Porto, PortugalDepartment of Electrical and Computer Engineering, Faculty of Engineering, University of Porto, Porto, PortugalDepartment of Electrical and Computer Engineering, Faculty of Engineering, University of Porto, Porto, PortugalDepartment of Electrical and Computer Engineering, Faculty of Engineering, University of Porto, Porto, PortugalSolar energy is a compelling and growing avenue for transitioning towards reliance on sustainable and environmentally friendly energy sources. However, the performance of individual photovoltaic (PV) panels is vulnerable to defects inflicted by weather exposure. The industry currently addresses these challenges by conducting manual inspections at each PV installation, a process that is highly time-consuming, financially burdensome, difficult to scale, prone to human error, and sometimes unfeasible due to topographical constraints. This study aims to develop a solution that detects these defects in real time resorting to an Autonomous Aerial Vehicle (AAV) equipped with for a thermal and a visual sensor. This paper contributes three major advancements to PV defect detection: a robust, standardized dataset built following IEC TS 62446-3 specifications with annotations from a real PV power plant, a novel multi-spectral approach that leverages early fusion of visual and thermal data captured via an AAV, and benchmark performance metrics for defect detection using state-of-the-art AI models. Our implementation uses Real-Time DEtection TRansformer (RT-DETR) and You Only Look Once (YOLO) models, achieving a mean Average Precision@50 (mAP) of 94% for RT-DETR and a mAP@50 of nearly 95% for YOLOv11. These results demonstrate the effectiveness of our approach in real-world settings, addressing a significant operational challenge in PV plant maintenance while establishing new performance benchmarks for automated defect detection in industrial solar installations.https://ieeexplore.ieee.org/document/11006036/Deep learningdefect detectionphotovoltaic panelsAAVs |
| spellingShingle | Lourenco Sousa Pinho Tiago Daniel Sousa Celso D. Pereira Andry M. Pinto Anomaly Detection for PV Modules Using Multi-Modal Data Fusion in Aerial Inspections IEEE Access Deep learning defect detection photovoltaic panels AAVs |
| title | Anomaly Detection for PV Modules Using Multi-Modal Data Fusion in Aerial Inspections |
| title_full | Anomaly Detection for PV Modules Using Multi-Modal Data Fusion in Aerial Inspections |
| title_fullStr | Anomaly Detection for PV Modules Using Multi-Modal Data Fusion in Aerial Inspections |
| title_full_unstemmed | Anomaly Detection for PV Modules Using Multi-Modal Data Fusion in Aerial Inspections |
| title_short | Anomaly Detection for PV Modules Using Multi-Modal Data Fusion in Aerial Inspections |
| title_sort | anomaly detection for pv modules using multi modal data fusion in aerial inspections |
| topic | Deep learning defect detection photovoltaic panels AAVs |
| url | https://ieeexplore.ieee.org/document/11006036/ |
| work_keys_str_mv | AT lourencosousapinho anomalydetectionforpvmodulesusingmultimodaldatafusioninaerialinspections AT tiagodanielsousa anomalydetectionforpvmodulesusingmultimodaldatafusioninaerialinspections AT celsodpereira anomalydetectionforpvmodulesusingmultimodaldatafusioninaerialinspections AT andrympinto anomalydetectionforpvmodulesusingmultimodaldatafusioninaerialinspections |