(Gunadarma University, Indonesia)(2) Sarifuddin Madenda
(Gunadarma University, Indonesia)(3) Bertalya Bertalya
(Gunadarma University, Indonesia)(4) Dina Indarti
(Gunadarma University, Indonesia)*corresponding author
AbstractSolar modules are essential components of a solar power plant, that are designed to withstand scorching heat, storms, strong winds, and other natural influences. However, continuous usage can cause defects in solar modules, preventing them from producing electrical energy optimally. This paper proposes the development of a deep learning-based system for identifying and classifying solar module surface defects in solar power plants. Module surface condition are classified into five categories: clean, dirt, burn, crack, and snail track. The dataset used consists of 8,370 images, including primary image data acquired directly from the mini solar power plant at the Renewable Energy Laboratory of PLN Institute of Technology, and secondary image data obtained from public repositories. The limitation in the number of images in each category was overcome using data augmentation techniques. The proposed classification model combines Deep Convolutional Neural Networks (DCNN) with transfer learning models (DenseNet201, MobileNetV2, and EfficientNetB0) to perform supervised image classification. Training and testing results on the three models demonstrated that the combination of DCNN + DenseNet201 provided the best performance, with a classification accuracy of 97.85%, compared to 97.25% accuracy for DCNN + EfficientNetB0 and 94.98% for DCNN + MobileNetV2. This research shows that DCNN-based image classification reliably diagnoses solar module defects and supports using RGB images for surface defect classification. Applying the developed system to solar power plant maintenance management can help in accelerating the process of identifying panel defects, determining defect types, and performing panel maintenance or repairs, while ensuring optimal power production.
KeywordsClassification, Deep Convolutional neural network, Solar module, Transfer learning, The failure types
|
DOIhttps://doi.org/10.26555/ijain.v11i3.1818 |
Article metricsAbstract views : 292 | PDF views : 34 |
Cite |
Full Text Download
|
References
[1] U. Kumar, S. Mishra, and K. Dash, “An IoT and Semi-Supervised Learning-Based Sensorless Technique for Panel Level Solar Photovoltaic Array Fault Diagnosis,” IEEE Trans. Instrum. Meas., vol. 72, pp. 1–12, 2023, doi: 10.1109/TIM.2023.3287247.
[2] K. Z. Mostofa and M. A. Islam, “Creation of an Internet of Things (IoT) system for the live and remote monitoring of solar photovoltaic facilities,” Energy Reports, vol. 9, pp. 422–427, Oct. 2023, doi: 10.1016/j.egyr.2023.09.060.
[3] N. El Yanboiy et al., “Mejora de la detección de defectos superficiales en paneles solares con modelos VGG basados en IA,” Data Metadata, vol. 2, p. 81, Dec. 2023, doi: 10.56294/dm202381.
[4] R. B. Patil, A. Khalkar, S. Al-Dahidi, R. S. Pimpalkar, S. Bhandari, and M. Pecht, “A Reliability and Risk Assessment of Solar Photovoltaic Panels Using a Failure Mode and Effects Analysis Approach: A Case Study,” Sustainability, vol. 16, no. 10, p. 4183, May 2024, doi: 10.3390/su16104183.
[5] L. Alhmoud, “Why Does the PV Solar Power Plant Operate Ineffectively?,” Energies, vol. 16, no. 10, p. 4074, May 2023, doi: 10.3390/en16104074.
[6] M. L. Katche, A. B. Makokha, S. O. Zachary, and M. S. Adaramola, “A Comprehensive Review of Maximum Power Point Tracking (MPPT) Techniques Used in Solar PV Systems,” Energies, vol. 16, no. 5, p. 2206, Feb. 2023, doi: 10.3390/en16052206.
[7] S. Mamykin, R. Z. Shneck, B. Dzundza, F. Gao, and Z. Dashevsky, “A Novel Solar System of Electricity and Heat,” Energies, vol. 16, no. 7, p. 3036, Mar. 2023, doi: 10.3390/en16073036.
[8] K. Barbusiński et al., “Influence of Environmental Conditions on the Electrical Parameters of Side Connectors in Glass–Glass Photovoltaic Modules,” Energies, vol. 17, no. 3, p. 680, Jan. 2024, doi: 10.3390/en17030680.
[9] A. K. Schnatmann et al., “Investigating the Technical Reuse Potential of Crystalline Photovoltaic Modules with Regard to a Recycling Alternative,” Sustainability, vol. 16, no. 3, p. 958, Jan. 2024, doi: 10.3390/su16030958.
[10] I. Gunes, “Comparison of PV Panels and Non-Planar PV Surfaces in Terms of Pollution,” in 2025 IEEE Texas Power and Energy Conference (TPEC), Feb. 2025, pp. 1–5, doi: 10.1109/TPEC63981.2025.10906853.
[11] S. Hassan and M. Dhimish, “A Survey of CNN-Based Approaches for Crack Detection in Solar PV Modules: Current Trends and Future Directions,” Solar, vol. 3, no. 4, pp. 663–683, Dec. 2023, doi: 10.3390/solar3040036.
[12] H. Al Mahdi, P. G. Leahy, M. Alghoul, and A. P. Morrison, “A Review of Photovoltaic Module Failure and Degradation Mechanisms: Causes and Detection Techniques,” Solar, vol. 4, no. 1, pp. 43–82, Jan. 2024, doi: 10.3390/solar4010003.
[13] J. Yang, M. Xin, and Q. Feng, “Automatic hot spot edge-detection method for photovoltaic aerial infrared image,” in Third International Conference on Artificial Intelligence, Virtual Reality, and Visualization (AIVRV 2023), Nov. 2023, vol. 12923, p. 24, doi: 10.1117/12.3011341.
[14] M. U. Ali, H. F. Khan, M. Masud, K. D. Kallu, and A. Zafar, “A machine learning framework to identify the hotspot in photovoltaic module using infrared thermography,” Sol. Energy, vol. 208, pp. 643–651, Sep. 2020, doi: 10.1016/j.solener.2020.08.027.
[15] A. Singh Chaudhary and D. K. Chaturvedi, “Analyzing Defects of Solar Panels under Natural Atmospheric Conditions with Thermal Image Processing,” Int. J. Image, Graph. Signal Process., vol. 10, no. 6, pp. 10–21, Jun. 2018, doi: 10.5815/ijigsp.2018.06.02.
[16] S. Djordjevic, D. Parlevliet, and P. Jennings, “Detectable faults on recently installed solar modules in Western Australia,” Renew. Energy, vol. 67, pp. 215–221, Jul. 2014, doi: 10.1016/j.renene.2013.11.036.
[17] M. Dhimish and V. Holmes, “Solar cells micro crack detection technique using state-of-the-art electroluminescence imaging,” J. Sci. Adv. Mater. Devices, vol. 4, no. 4, pp. 499–508, Dec. 2019, doi: 10.1016/j.jsamd.2019.10.004.
[18] J. P. C. Barnabé, L. P. Jiménez, G. Fraidenraich, E. R. De Lima, and H. F. Dos Santos, “Quantification of Damages and Classification of Flaws in Mono-Crystalline Photovoltaic Cells Through the Application of Vision Transformers,” IEEE Access, vol. 11, pp. 112334–112347, 2023, doi: 10.1109/ACCESS.2023.3322653.
[19] M. S. H. Onim et al., “SolNet: A Convolutional Neural Network for Detecting Dust on Solar Panels,” Energies, vol. 16, no. 1, p. 155, Dec. 2022, doi: 10.3390/en16010155.
[20] I. Bodnár, D. Matusz-Kalász, and R. R. Boros, “Exploration of Solar Panel Damage and Service Life Reduction Using Condition Assessment, Dust Accumulation, and Material Testing,” Sustainability, vol. 15, no. 12, p. 9615, Jun. 2023, doi: 10.3390/su15129615.
[21] A. Ghahremani, S. D. Adams, M. Norton, S. Y. Khoo, and A. Z. Kouzani, “Delamination Techniques of Waste Solar Panels: A Review,” Clean Technol., vol. 6, no. 1, pp. 280–298, Feb. 2024, doi: 10.3390/cleantechnol6010014.
[22] U. Hijjawi, S. Lakshminarayana, T. Xu, G. Piero Malfense Fierro, and M. Rahman, “A review of automated solar photovoltaic defect detection systems: Approaches, challenges, and future orientations,” Sol. Energy, vol. 266, p. 112186, Dec. 2023, doi: 10.1016/j.solener.2023.112186.
[23] S. A. Memon, Q. Javed, W.-G. Kim, Z. Mahmood, U. Khan, and M. Shahzad, “A Machine-Learning-Based Robust Classification Method for PV Panel Faults,” Sensors, vol. 22, no. 21, p. 8515, Nov. 2022, doi: 10.3390/s22218515.
[24] H. Munawer Al-Otum, “Deep learning-based automated defect classification in Electroluminescence images of solar panels,” Adv. Eng. Informatics, vol. 58, p. 102147, Oct. 2023, doi: 10.1016/j.aei.2023.102147.
[25] N. A. M. Roslan, N. M. Diah, Z. Ibrahim, Y. Munarko, and A. E. Minarno, “Automatic plant recognition using convolutional neural network on Malaysian medicinal herbs: the value of data augmentation,” Int. J. Adv. Intell. Informatics, vol. 9, no. 1, pp. 136–147, 2023, doi: 10.26555/ijain.v9i1.1076.
[26] H. Haviluddin and R. Alfred, “Multi-step CNN forecasting for COVID-19 multivariate time-series,” Int. J. Adv. Intell. Informatics, vol. 9, no. 2, p. 176, Jul. 2023, doi: 10.26555/ijain.v9i2.1080.
[27] X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif. Intell. Rev., vol. 57, no. 4, p. 99, Mar. 2024, doi: 10.1007/s10462-024-10721-6.
[28] A. Serikbay, M. Bagheri, A. Zollanvari, and B. T. Phung, “Ensemble Pretrained Convolutional Neural Networks for the Classification of Insulator Surface Conditions,” Energies, vol. 17, no. 22, p. 5595, Nov. 2024, doi: 10.3390/en17225595.
[29] A. Younesi, M. Ansari, M. Fazli, A. Ejlali, M. Shafique, and J. Henkel, “A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends,” IEEE Access, vol. 12, pp. 41180–41218, 2024, doi: 10.1109/ACCESS.2024.3376441.
[30] S. Y. Prasetyo, G. Z. Nabiilah, Z. N. Izdihar, and S. M. Isa, “Pneumonia Detection on X-Ray Imaging using Softmax Output in Multilevel Meta Ensemble Algorithm of Deep Convolutional Neural Network Transfer Learning Models,” Int. J. Adv. Intell. Informatics, vol. 9, no. 2, p. 319, Jul. 2023, doi: 10.26555/ijain.v9i2.884.
[31] S. Hassan and M. Dhimish, “Dual spin max pooling convolutional neural network for solar cell crack detection,” Sci. Rep., vol. 13, no. 1, p. 11099, Jul. 2023, doi: 10.1038/s41598-023-38177-8.
[32] A. Shihavuddin et al., “Image based surface damage detection of renewable energy installations using a unified deep learning approach,” Energy Reports, vol. 7, pp. 4566–4576, Nov. 2021, doi: 10.1016/j.egyr.2021.07.045.
[33] Z. Zha, D. Shi, X. Chen, H. Shi, and J. Wu, “Classification of Appearance Quality of Red Grape Based on Transfer Learning of Convolution Neural Network,” Agronomy, vol. 13, no. 8, p. 2015, Jul. 2023, doi: 10.3390/agronomy13082015.
[34] M. Hasanat, W. Khan, N. Minallah, N. Aziz, and A.-U.-R. Durrani, “Performance evaluation of transfer learning based deep convolutional neural network with limited fused spectro-temporal data for land cover classification,” Int. J. Electr. Comput. Eng., vol. 13, no. 6, p. 6882, Dec. 2023, doi: 10.11591/ijece.v13i6.pp6882-6890.
[35] X. Song and Y. Liu, “Defect Detection of Solar Panel Based on DenseNet Network,” in Advances in Transdisciplinary Engineering, vol. 35, IOS Press, 2023, pp. 661–669, doi: 10.3233/ATDE230093.
[36] S. Matarneh, F. Elghaish, F. Pour Rahimian, E. Abdellatef, and S. Abrishami, “Evaluation and optimisation of pre-trained CNN models for asphalt pavement crack detection and classification,” Autom. Constr., vol. 160, p. 105297, Apr. 2024, doi: 10.1016/j.autcon.2024.105297.
[37] M. A. El-Rashidy, “An efficient and portable solar cell defect detection system,” Neural Comput. Appl., vol. 34, no. 21, pp. 18497–18509, Nov. 2022, doi: 10.1007/s00521-022-07464-2.
[38] Y. Zou, L. Wu, C. Zuo, L. Chen, B. Zhou, and H. Zhang, “White blood cell classification network using MobileNetv2 with multiscale feature extraction module and attention mechanism,” Biomed. Signal Process. Control, vol. 99, p. 106820, Jan. 2025, doi: 10.1016/j.bspc.2024.106820.
[39] Z. Zhao, E. B. A. Bakar, N. B. A. Razak, and M. N. Akhtar, “Corrosion image classification method based on EfficientNetV2,” Heliyon, vol. 10, no. 17, p. e36754, Sep. 2024, doi: 10.1016/j.heliyon.2024.e36754.
[40] Z. B. Duranay, “Fault Detection in Solar Energy Systems: A Deep Learning Approach,” Electronics, vol. 12, no. 21, p. 4397, Oct. 2023, doi: 10.3390/electronics12214397.
[41] M. Gao, Y. Xie, P. Song, J. Qian, X. Sun, and J. Liu, “A Definition Rule for Defect Classification and Grading of Solar Cells Photoluminescence Feature Images and Estimation of CNN-Based Automatic Defect Detection Method,” Crystals, vol. 13, no. 5, p. 819, May 2023, doi: 10.3390/cryst13050819.
[42] M. W. Akram et al., “CNN based automatic detection of photovoltaic cell defects in electroluminescence images,” Energy, vol. 189, p. 116319, Dec. 2019, doi: 10.1016/j.energy.2019.116319.
[43] M. R. Rahman, S. Tabassum, E. Haque, M. M. Nishat, F. Faisal, and E. Hossain, “CNN-based Deep Learning Approach for Micro-crack Detection of Solar Panels,” in 2021 3rd International Conference on Sustainable Technologies for Industry 4.0 (STI), Dec. 2021, pp. 1–6, doi: 10.1109/STI53101.2021.9732592.
[44] C. Bu, T. Liu, T. Wang, H. Zhang, and S. Sfarra, “A CNN-Architecture-Based Photovoltaic Cell Fault Classification Method Using Thermographic Images,” Energies, vol. 16, no. 9, p. 3749, Apr. 2023, doi: 10.3390/en16093749.
[45] H. Chen, Y. Pang, Q. Hu, and K. Liu, “Solar cell surface defect inspection based on multispectral convolutional neural network,” J. Intell. Manuf., vol. 31, no. 2, pp. 453–468, Feb. 2020, doi: 10.1007/s10845-018-1458-z.
[46] T. Rahman et al., “Investigation of Degradation of Solar Photovoltaics: A Review of Aging Factors, Impacts, and Future Directions toward Sustainable Energy Management,” Energies, vol. 16, no. 9, p. 3706, Apr. 2023, doi: 10.3390/en16093706.
[47] A. S. Al-Waisy et al., “Identifying defective solar cells in electroluminescence images using deep feature representations,” PeerJ Computer Science, vol. 8. PeerJ Inc., p. e992, May 19, 2022, doi: 10.7717/peerj-cs.992/table-9.
[48] Afroz, “Solar Panel Images Clean and Faulty Images,” Kaggle, 2023. [Online]. Available at: https://www.kaggle.com/datasets/pythonafroz/solar-panel-images.
[49] “solar panels fault,” Roboflow Universe Search, 2025. [Online]. Available at: https://universe.roboflow.com/search?q=solar+panels+fault.
[50] A. Pendota and S. S. Channappayya, “Are Deep Learning Models Pre-trained on RGB Data Good Enough for RGB-Thermal Image Retrieval?,” in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun. 2024, pp. 4287–4296, doi: 10.1109/CVPRW63382.2024.00432.
[51] P. Purnawansyah, A. Adnan, H. Darwis, A. P. Wibawa, T. Widyaningtyas, and H. Haviluddin, “Ensemble semi-supervised learning in facial expression recognition,” Int. J. Adv. Intell. Informatics, vol. 11, no. 1, p. 1, Feb. 2025, doi: 10.26555/ijain.v11i1.1880.
[52] D. Sathya, S. B. Jeniffer, R. S. J, L. M, and R. R. G, “Efficient Traffic Sign Detection Using CNNs: A Scalable Deep Learning Model,” in 2024 Eighth International Conference on Parallel, Distributed and Grid Computing (PDGC), Dec. 2024, pp. 693–699, doi: 10.1109/PDGC64653.2024.10984039.
[53] E. Jain and A. Singh, “Efficient Handwritten Digit Classification using Convolutional Neural Networks: A Robust Approach with Data Augmentation,” in 2024 3rd International Conference on Automation, Computing and Renewable Systems (ICACRS), Dec. 2024, pp. 1234–1239, doi: 10.1109/ICACRS62842.2024.10841545.
[54] L. Menglin, X. Qiang, Z. Peng, Z. Dahua, H. Lizhi, and H. Baiji, “Encrypted Traffic Identification in Power IoT based on CNN with Batch Normalization,” in 2024 6th International Conference on Electrical Engineering and Control Technologies (CEECT), Dec. 2024, pp. 136–142, doi: 10.1109/CEECT63656.2024.10898407.
[55] E. Pintelas, I. E. Livieris, S. Kotsiantis, and P. Pintelas, “A multi-view-CNN framework for deep representation learning in image classification,” Comput. Vis. Image Underst., vol. 232, p. 103687, Jul. 2023, doi: 10.1016/j.cviu.2023.103687.
[56] J. Jerome Vasanth, S. Naveen Venkatesh, V. Sugumaran, and V. S. Mahamuni, “Enhancing Photovoltaic Module Fault Diagnosis with Unmanned Aerial Vehicles and Deep Learning-Based Image Analysis,” Int. J. Photoenergy, vol. 2023, no. 1, pp. 1–17, Jul. 2023, doi: 10.1155/2023/8665729.
[57] J. Lee, J. Park, and Y. Lee, “Toward Efficient Cancer Detection on Mobile Devices,” IEEE Access, vol. 13, pp. 34613–34626, 2025, doi: 10.1109/ACCESS.2025.3543838.
[58] M. R. M. Kamal, S. Shahbudin, and F. Y. A. Rahman, “Photovoltaic (PV) Module Defect Image Classification Analysis Using EfficientNetV2 Architectures,” in 2023 IEEE 14th Control and System Graduate Research Colloquium (ICSGRC), Aug. 2023, pp. 236–241, doi: 10.1109/ICSGRC57744.2023.10215491.
[59] I. Markoulidakis, I. Rallis, I. Georgoulas, G. Kopsiaftis, A. Doulamis, and N. Doulamis, “Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem,” Technologies, vol. 9, no. 4, p. 81, Nov. 2021, doi: 10.3390/technologies9040081.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0