Solar Panel Defect Detection using FOMO on Edge Impulse

Authors

  • Muhammad Nabil Aiman Baderul Hisham Electrical Engineering Studies, College of Engineering, Universiti Teknologi MARA,Cawangan Pulau Pinang, Permatang Pauh, Malaysia.
  • Roslan Seman Electrical Engineering Studies, College of Engineering, Universiti Teknologi MARA,Cawangan Pulau Pinang, Permatang Pauh, Malaysia.
  • Zuraidi Saad Electrical Engineering Studies, College of Engineering, Universiti Teknologi MARA,Cawangan Pulau Pinang, Permatang Pauh, Malaysia.
  • Zainal Hisham Che Soh Electrical Engineering Studies, College of Engineering, Universiti Teknologi MARA,Cawangan Pulau Pinang, Permatang Pauh, Malaysia.

DOI:

https://doi.org/10.21834/e-bpj.v10iSI27.6822

Keywords:

Solar Panel Defect Detection, Hotspots and Crack Defect, Faster Object More Object (FOMO), Edge Impulse

Abstract

A machine learning model is developed for detecting defects in solar panels, focusing on hotspot detection. The project was created on Edge Impulse with images of solar panels in normal and defective states. The trained model with appropriate training accuracy was then deployed on a smartphone for real-time defect detection, utilizing a camera to capture and process image frames, overlaying results on a smartphone screen for immediate inspection. The evaluation revealed an F1 score of 80.5% for hotspot detection with an accuracy of over 95% for the model-detecting hotspots. This demonstrates the model’s practical application and effectiveness for solar panel hotspot detection.

References

B. Sandeep, D. S. Reddy, R. Aswin & R. Mahalakshmi, (2022). "Monitoring of PV Modules and Hotspot Detection using TensorFlow," Proc. Int. Conf. Electron. Renew. Syst. ICEARS 2022, no. Icears, pp. 155–160, 2022, doi: 10.1109/ICEARS53579.2022.9752346. DOI: https://doi.org/10.1109/ICEARS53579.2022.9752346

D. P. Winston et al., (2021), “Solar PV’s Micro Crack and Hotspots Detection Technique Using NN and SVM,” IEEE Access, vol. 9, pp. 127259–127269, doi:10.1109/ACCESS.2021.3111904. DOI: https://doi.org/10.1109/ACCESS.2021.3111904

F. Wang, Z. Wang, Z. Chen, D. Zhu, X. Gong & W. Cong, (2023). "An Edge-Guided Deep Learning Solar Panel Hotspot Thermal Image Segmentation Algorithm," Appl. Sci., vol. 13, no. 19, doi: 10.3390/app131911031. DOI: https://doi.org/10.3390/app131911031

G. Terzoglou, M. Loufakis, P. Symeonidis, D. Ioannidis & D. Tzovaras, (2023). "Employing deep learning framework for improving solar panel defects using drone imagery," Int. Conf. Digit. Signal Process. DSP, vol. 2023-June, pp. 1–5, doi: 10.1109/DSP58604.2023.10167960. DOI: https://doi.org/10.1109/DSP58604.2023.10167960

I. N. Mihigo, M. Zennaro, A. Uwitonze, J. Rwigema, & M. Rovai, (2022), “On-Device IoT-Based Predictive Maintenance Analytics Model: Comparing TinyLSTM and TinyModel from Edge Impulse,” Sensors, vol. 22, no. 14, pp. 1–20, doi: 10.3390/s22145174. DOI: https://doi.org/10.3390/s22145174

J. A. Dhanraj et al., “An effective evaluation on fault detection in solar panels, (2021),” Energies, vol. 14, no. 22. MDPI, Nov. 01. doi: 10.3390/en14227770. DOI: https://doi.org/10.3390/en14227770

K. A. K. Niazi, W. Akhtar, H. A. Khan, Y. Yang, & S. Athar (2019). "Hotspot diagnosis for solar photovoltaic modules using a Naive Bayes classifier," Sol. Energy, vol. 190, no. August, pp. 34–43, doi: 10.1016/j.solener.2019.07.063. DOI: https://doi.org/10.1016/j.solener.2019.07.063

M. Karimi, H. Samet, T. Ghanbari & E. Moshksar, (2020). "A current based approach for hotspot detection in photovoltaic strings," Int. Trans. Electr. Energy Syst., vol. 30, no. 9, pp. 1–18, doi: 10.1002/2050-7038.12517. DOI: https://doi.org/10.1002/2050-7038.12517

M. U. Ali et al., (2022), “Early hotspot detection in photovoltaic modules using color image descriptors: An infrared thermography study,” Int. J. Energy Res., vol. 46, no. 2, pp. 774–785, doi: 10.1002/er.7201. DOI: https://doi.org/10.1002/er.7201

S. P. Pathak & S. A. Patil, (2023). "Evaluation of Effect of Preprocessing Techniques in Solar Panel Fault Detection," IEEE Access, vol. 11, no. May, pp. 72848–72860, doi: 10.1109/ACCESS.2023.3293756. DOI: https://doi.org/10.1109/ACCESS.2023.3293756

Soh Z.H.C., Kamarulazizi K., Daud K., Hamzah I.H., Saad Z. & Abdullah S.A.C.(2020). "Abandoned Baggage Detection & Alert System Via AI and IoT" ACM International Conference Proceeding Series, art. no. 3384614, pp. 205 - 209, DOI: 10.1145/3384613.3384614. DOI: https://doi.org/10.1145/3384613.3384614

Soh, Zainal Hisham Che, Muhammad Shafiq Abd Razak, Irni Hamiza Hamzah, Mohd Nizar Zainol, Siti Noraini Sulaiman, Saiful Zaimy Yahaya, & Syahrul Afzal Che Abdullah.(2022), "Riverbank Monitoring using Image Processing for Early Flood Warning System via IoT." International Journal of Integrated Engineering 14, no. 3, 166-174. https://doi.org/10.30880/ijie.2022.14.03.018. DOI: https://doi.org/10.30880/ijie.2022.14.03.018

U. Pruthviraj, Y. Kashyap, E. Baxevanaki, & P. Kosmopoulos (2023). "Solar Photovoltaic Hotspot Inspection Using Unmanned Aerial Vehicle Thermal Images at a Solar Field in South India," Remote Sens., vol. 15, no. 7, doi: 10.3390/rs15071914. DOI: https://doi.org/10.3390/rs15071914

Z. B. Duranay, (2023). "Fault Detection in Solar Energy Systems: A Deep Learning Approach," Electron., vol. 12, no. 21, doi: 10.3390/electronics12214397[ DOI: https://doi.org/10.3390/electronics12214397

Downloads

Published

2025-04-15

How to Cite

Baderul Hisham, M. N. A., Seman, R., Saad, Z., & Che Soh, Z. H. (2025). Solar Panel Defect Detection using FOMO on Edge Impulse. Environment-Behaviour Proceedings Journal, 10(SI27), 89–95. https://doi.org/10.21834/e-bpj.v10iSI27.6822

Issue

Vol. 10 No. SI27 (2025): Apr. The 6th International Conference of Information Science, ICIS2025PortDickson, 27-28 Jan 2025

Section

Energy Environment

License

Copyright (c) 2025 Muhammad Nabil Aiman Baderul Hisham, Roslan Seman, Zuraidi Saad, Zainal Hisham Che Soh

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Crossref
Scopus
Google Scholar
Europe PMC