Architecture of cyberphysical systems for UAV-based late-fusion defect detection in photovoltaic modules
DOI:
https://doi.org/10.30837/2522-9818.2026.1.079Keywords:
cyber-physical systems; photovoltaic modules; unmanned aerial vehicles; infrared thermography; edge computing; deep learning.Abstract
The subject of research is the architectural advancement of inspection systems for large-scale solar power plants. As global solar infrastructure expands, reliance on manual or offline analytical methods creates significant operational bottlenecks. The goal of research is to improve the operational utility of unmanned aerial vehicle (UAV)-based photovoltaic module inspection by developing a cyber-physical system (CPS) architecture. It integrates onboard deep learning, edge nodes, cloud analytics, and Supervisory Control and Data Acquisition (SCADA)-aware decision-making into a single coordinated workflow. The tasks of research: 1) formalise a multi-tiered CPS architecture (UAV-edge-cloud) and define interfaces for data, geo-tags, and alarms; 2) develop and validate an onboard thermographic detection pipeline with palette-aware fusion; and 3) integrate detection results with a SCADA-aware logic layer for hazard inference and fire risk mitigation. The methods of research: Computer vision and deep learning (YOLOv11) are used for onboard defect segmentation. Model ensembling via a late-fusion strategy for M2 and M3 thermal palettes mitigates domain shift. RTK-supported spatial clustering algorithms ensure precise geo-indexing and deduplication, and deterministic Boolean logic assesses fire risks based on bypass diode states. The results obtained with five-fold cross-validation shows the proposed architecture significantly outperforms single-modality baselines. The onboard YOLOv11 model achieved a macro mAP@0.5 of 0.91 and 0.90 for M2 and M3 palettes, respectively. The late-fusion ensemble elevated mAP@0.5 for cracks to 0.96 and delamination to 0.95. It reduced end-to-end per-frame processing latency from 4.235 s to 2.858 s. Field validation demonstrated an error of 0.71 defects per inspected string compared to manual counts. Sensitivity analysis highlighted that a 10 m flight altitude provides an optimal balance, yielding 93% precision and 90% recall. Conclusions: Treating UAV inspection as an integrated cyber-physical service improves defect detection. This offers a scalable, real-time solution for preventive maintenance and automated fire-risk mitigation in renewable energy.
References
References
Sun, L., Sun, Y. (2022), "Photovoltaic power forecasting based on artificial neural network and ultraviolet index", International Journal of Computing, Vol. 21, No. 2, 1531158 р. DOI: https://doi.org/10.47839/ijc.21.2.2583
Sinha, A., Sulas-Kern, D. B., Owen-Bellini, M., Spinella, L., Uličná, Š., Ayala, R., Murphy, R., Walker, C., Hacke, P. (2024), "A review of degradation and reliability analysis of a solar PV module", IEEE Access, Vol. 12, рр. 185036-185056. DOI: https://doi.org/10.1109/ACCESS.2024.3432394
Lynnyk, R., Vysotska, V., Matseliukh, Y., Burov, Y., Demkiv, L., Sachenko, A., Shylinska, I., Yevseyeva, I., Bihun, O. (2020), "DDoS attacks analysis based on machine learning in challenges of global changes", Proceedings of the 2nd International Workshop on Modern Machine Learning Technologies and Data Science (MoMLeT+DS 2020), Volume 2631, CEUR.org, Aachen, рр. 159-171, available at: https://ceur-ws.org/Vol-2631/paper12.pdf (last accessed 16.01.2025).
Aghaei, M., Kolahi, M., Nedaei, A., Venkatesh, N. S., Esmailifar, S. M. (2025), "Autonomous intelligent monitoring of photovoltaic systems: An in-depth multidisciplinary review", Progress in Photovoltaics: Research and Applications, Vol. 33, No. 3, рр. 381-409. DOI: https://doi.org/10.1002/pip.3859
Khatri, A., Khadka, S., Lamichhane, N., Shrestha, R. (2025), "A comprehensive review of infrared thermography and deep learning applications for solar photovoltaic systems", Infrared Physics & Technology, Vol. 148, 105878 р. DOI: https://doi.org/10.1016/j.infrared.2025.105878
Gallardo-Saavedra, S., Hernández-Callejo, L., Alonso-García, M. d. C., Muñoz-Cruzado-Alba, J., Ballestín-Fuertes, J. (2020), "Infrared thermography for the detection and characterization of photovoltaic defects: Comparison between illumination and dark conditions", Sensors, Vol. 20, No. 16, 4395 р. DOI: https://doi.org/10.3390/s20164395
Prasshanth, C. V., Deepak, B. B. V. L., Vijayakumar, N., Prabadevi, B., Alhussen, F. A. (2025), "Fault detection in photovoltaic systems using unmanned aerial vehicle-captured images and rough set theory", Solar Energy, Vol. 290, 113348 р. DOI: https://doi.org/10.1016/j.solener.2025.113348
Moctezuma, D., Valentín-Coronado, L. M. (2025), "Deep-learning-based electrical fault detection in photovoltaic modules through aerial infrared imaging: Addressing data complexity", Computación y Sistemas, Vol. 29, No. 1, рр. 65-75. DOI: https://doi.org/10.13053/cys-29-1-5531
Svystun, S., Scislo, L., Pawlik, M., Melnychenko, O., Radiuk, P., Savenko, O., Sachenko, A. (2025), "DyTAM: Accelerating wind turbine inspections with dynamic UAV trajectory adaptation", Energies, Vol. 18, No. 7, 1823 р. DOI: https://doi.org/10.3390/en18071823
Rouibah, N., El Hammoumi, A., Bouttout, A., Haddad, S., Oukaci, S., Limam, A., Benghanem, M. (2025), "Smart monitoring of photovoltaic energy systems: An IoT-based prototype approach", Scientific African, Vol. 30, e02973 р. DOI: https://doi.org/10.1016/j.sciaf.2025.e02973
Rodriguez-Vazquez, J., Prieto-Centeno, I., Fernandez-Cortizas, M., Pérez-Saura, D., Molina, M., Campoy, P. (2024), "Real-time object detection for autonomous solar farm inspection via UAVs", Sensors, Vol. 24, No. 3, 777 р. DOI: https://doi.org/10.3390/s24030777
Noura, H., Sun, Y., Taghezouit, B., Dairi, A. (2024), "Explainable artificial intelligence of tree-based algorithms for fault detection and diagnosis in grid-connected photovoltaic systems". Engineering Applications of Artificial Intelligence, Vol. 139, 109503 р. DOI: https://doi.org/10.1016/j.engappai.2024.109503
Bodyanskiy, Y., Deineko, A., Skorik, V., Brodetskyi, F. (2022), "Deep neural network with adaptive parametric rectified linear units and its fast learning", International Journal of Computing, Vol. 21, No. 1, рр. 11-18. DOI: https://doi.org/10.47839/ijc.21.1.2512
Di Tommaso, A., Betti, A., Fontanelli, G., Michelozzi, B. (2022), "A multi-stage model based on YOLOv3 for defect detection in PV panels based on IR and visible imaging by unmanned aerial vehicle", Renewable Energy, Vol. 193, рр. 941-962. DOI: https://doi.org/10.1016/j.renene.2022.04.046
Melnychenko, O., Scislo, L., Savenko, O., Sachenko, A., Radiuk, P. (2024), "Intelligent integrated system for fruit detection using multi-UAV imaging and deep learning", Sensors, Vol. 24, No. 6, 1913 р. DOI ttps://doi.org/10.3390/s24061913
Aljafari, B., Satpathy, P. R., Thanikanti, S. B., Nwulu, N. (2024), "Supervised classification and fault detection in grid-connected PV systems using 1D-CNN: Simulation and real-time validation", Energy Reports, Vol. 12, рр. 2156-2178. DOI: https://doi.org/10.1016/j.egyr.2024.08.008
Setiawan, E. A., Fathurrahman, M. (2025), "Exploring insights on deep learning-based photovoltaic fault detection for monofacial and bifacial modules using thermography", International Journal of Cognitive Computing in Engineering, Vol. 6, рр. 495-507. DOI: https://doi.org/10.1016/j.ijcce.2025.04.001
Xie, H., Yuan, B., Hu, C., Gao, Y., Wang, F., Wang, C., Wang, Y., Chu, P. (2024), "ST-YOLO: A defect detection method for photovoltaic modules based on infrared thermal imaging and machine vision technology", PLOS ONE, Vol. 19, No. 12, рр. 1-19. DOI: https://doi.org/10.1371/journal.pone.0310742
Carnì, D. L., Grimaldi, D., Lamonaca, F., Nigro, L., Sciammarella, P. F. (2017), "From distributed measurement systems to cyber-physical systems: A design approach", International Journal of Computing, Vol. 16, No. 2, рр. 66-73. DOI: https://doi.org/10.47839/ijc.16.2.882
Boucif, O. H., Toral-Cruz, H. (2025), "Artificial intelligence of things for solar energy monitoring and control", Applied Sciences, Vol. 15, No. 11, 6019 р. DOI: https://doi.org/10.3390/app15116019
Lysyi, A., Sachenko, A., Radiuk, P., Lysyi, M., Melnychenko, O., Ishchuk, O., Savenko, O. (2025), "Enhanced fire hazard detection in solar power plants: An integrated UAV, AI, and SCADA-based approach", Radioelectronic and Computer Systems, Vol. 2025, No. 2, рр. 99-117. DOI: https://doi.org/10.32620/reks.2025.2.06
Tang, W., Xu, J., Wang, X., Li, H., Chen, J., Zhang, Y. (2022), "Deep learning-based detection of linear defects in large-scale photovoltaic plants using an edge-cloud architecture", Solar Energy, Vol. 237, рр. 144-161. DOI: https://doi.org/10.1016/j.solener.2021.11.016
Ferlito, S., Ippolito, S., Santagata, C., Schiattarella, P., Di Francia, G. (2024), "A study on an IoT-based SCADA system for photovoltaic utility plants", Electronics, Vol. 13, No. 11, 2065 р. DOI: https://doi.org/10.3390/electronics13112065
Masita, K., Hasan, A., Shongwe, T., Abu Hilal, H. (2025), "Deep learning in defects detection of PV modules: A review", Solar Energy Advances, Vol. 5, 100090 р. DOI: https://doi.org/10.1016/j.seja.2025.100090
Dotenco, S., Dalsass, M., Winkler, L., Würzner, T., Brabec, C., Maier, A., Gallwitz, F. (2016), "Automatic detection and analysis of photovoltaic modules in aerial infrared imagery", Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, New York, NY, USA, рр. 1-9. DOI: https://doi.org/10.1109/WACV.2016.7477658
Ebied, M. A., Munshi, A., Alhuzali, S. A., El-sotouhy, M. M., Shehta, A. I., Elborlsy, M. S. (2025), "Advanced deep learning modeling to enhance detection of defective photovoltaic cells in electroluminescence images", Scientific Reports, Vol. 15, 31640 р. DOI: https://doi.org/10.1038/s41598-025-14478-y
Barraz, Z., Sebari, I., Lamrini, N., Ait El Kadi, K., Ait Abdelmoula, I. (2025), "Fast and automatic solar module geo-labeling for optimized large-scale photovoltaic systems inspection from UAV thermal imagery using deep learning segmentation", Cleaner Engineering and Technology, Vol. 28, 101048 р. DOI: https://doi.org/10.1016/j.clet.2025.101048
Abdelsattar, M., AbdelMoety, A., Emad-Eldeen, A. (2025), "ResNet-based image processing approach for precise detection of cracks in photovoltaic panels", Scientific Reports, Vol. 15, 24356 р. DOI: https://doi.org/10.1038/s41598-025-09101-z
Svystun, S., Melnychenko, O., Radiuk, P., Savenko, O., Sachenko, A., Lysyi, A. (2024), "Thermal and RGB images work better together in wind turbine damage detection", International Journal of Computing, Vol. 23, No. 4, рр. 526-535. DOI: https://doi.org/10.47839/ijc.23.4.3752
Zheng, Y., Shcherbakova, G., Rusyn, B., Sachenko, A., Volkova, N., Kliushnikov, I., Antoshchuk, S. (2025), "Wavelet transform cluster analysis of UAV images for sustainable development of smart regions due to inspecting transport infrastructure", Sustainability, Vol. 17, No. 3, 927 р. DOI: https://doi.org/10.3390/su17030927
Alfaro-Mejía, E., Loaiza-Correa, H., Franco-Mejía, E., Restrepo-Girón, A. D., Nope-Rodríguez, S. E. (2019), "Dataset for recognition of snail trails and hot spot failures in monocrystalline Si solar panels", Data in Brief, Vol. 26, 104441 р. DOI: https://doi.org/10.1016/j.dib.2019.104441
Wang, B., Chen, Q., Wang, M., Chen, Y., Zhang, Z., Liu, X., Gao, W., Zhang, Y., Zhang, H. (2024), "PVF-10: A high-resolution unmanned aerial vehicle thermal infrared image dataset for fine-grained photovoltaic fault classification", Applied Energy, Vol. 376, 124187 р. DOI: https://doi.org/10.1016/j.apenergy.2024.124187
CVAT.ai Corporation, (2024), "CVAT: Computer vision annotation tool (Version 2.16.1)", DOI: https://doi.org/10.5281/zenodo.12771595
Jocher, G., Qiu, J., Chaurasia, A. (2025), "Ultralytics YOLO", available at: https://github.com/ultralytics/ultralytics (last accessed 16.01.2026).
European Commission, (2018), "Standards for the assessment of the environmental performance of photovoltaic modules, power conversion equipment and photovoltaic systems", Publications Office of the European Union, Luxembourg, available at: 10.2760/89830
Ambarella, Inc. (2016), "Ambarella introduces low power 4K ultra HD SoCs for sports and flying cameras", available at: https://www.ambarella.com/news/ambarella-introduces-low-power-4k-ultra-hd-socs-for-sports-and-flying-cameras/ (last accessed 16.01.2026).
Bradski, G. (2000), "The OpenCV library", Dr. Dobb’s Journal: Software Tools for the Professional Programmer, Vol. 25, No. 11, рр. 120-123.
Paszke, A. et al. (2019), "PyTorch: An imperative style, high-performance deep learning library", Advances in Neural Information Processing Systems, Volume 32, Curran Associates, Inc., рр. 8024-8035, available at: https://proceedings.neurips.cc/paper_files/paper/2019/file/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf (last accessed 16.01.2026).
Qualcomm Technologies, Inc. (2020), "Qualcomm QCS603/QCS605 SoCs for IoT: Product brief", available at: https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/documents/qcs603.605-socs-product-brief_87-pg764-1-c.pdf (last accessed 16.01.2026).
NVIDIA Corporation, (2024), "Jetson AGX Orin: Technical brief", available at: https://www.nvidia.com/en-us/lp/embedded-computing/robotics-edge-ai-tech-brief/ (last accessed 16.01.2026).
Robustelli, U., Cutugno, M., Pugliano, G. (2023), "Low-cost GNSS and PPP-RTK: Investigating the capabilities of the u-blox ZED-F9P module", Sensors, Vol. 23, No. 13, 6074 р. DOI: https://doi.org/10.3390/s23136074
NVIDIA Corporation, (2024), "NVIDIA TensorRT documentation", available at: https://docs.nvidia.com/deeplearning/tensorrt/10.9.0/getting-started/release-notes.html (last accessed 16.01.2026).
Rainio, O., Teuho, J., Klén, R. (2024), "Evaluation metrics and statistical tests for machine learning", Scientific Reports, Vol. 14, No. 1, 6086 р. DOI: https://doi.org/10.1038/s41598-024-56706-x
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Our journal abides by the Creative Commons copyright rights and permissions for open access journals.
Authors who publish with this journal agree to the following terms:
Authors hold the copyright without restrictions and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-commercial and non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
Authors are permitted and encouraged to post their published work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
