International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 3, pp. 156-161, March 2026.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Enhancing Defect Classification in Solar Panels using Electroluminescence Imaging and Advanced Machine Learning Strategies
Renangi Sandeep
Tadipatri Reddi Kumari
Kopala Sahithi
Ashutosh Kumar
Chinnareddy Sai Teja
Maruboina Raja Sree
Department of CSE, Siddartha Institute of Science and Technology, Puttur, Andhra Pradesh, India
Abstract: Defects that may cause early degradation of modules can pose significant challenges to the long-term reliability and performance of solar panels. The use of EL imaging has made it possible to detect electrical and structural faults that are not easily detectable using conventional inspection methods. This technology is particularly useful in this area. The complexity and variability of EL image patterns necessitate intelligent analysis methods that can identify subtle defect characteristics with high consistency. The investigation presents an advanced defect classification model that combines EL imaging with cutting-edge machine learning techniques to optimize the precision, efficiency, and automation of solar panel inspection. Optimal classification models, along with image preprocessing techniques that extract features, are utilized in the approach to identify various types of defects under different imaging conditions. Through experiments, it is revealed that the proposed framework effectively captures intricate defect signatures and provides dependable guidance for measuring PVD quality.
Keywords: Electroluminescence imaging, solar panel defect detection, machine learning, deep learning, photovoltaic diagnostics.
References:
- A H. M. Al-Otum, “Defect classification of photovoltaic solar cells using electroluminescence imaging and enhanced deep learning approaches,” Solar Energy, vol. 303, p. 114085, Oct. 2025, doi: 10.1016/j.solener.2025.114085.
- S. Deitsch et al., “Automatic classification of defective photovoltaic module cells in electroluminescence images,” Solar Energy, vol. 185, pp. 455–468, May 2019, doi: 10.1016/j.solener.2019.02.067.
- W. Tang, Q. Yang, K. Xiong, and W. Yan, “Deep learning based automatic defect identification of photovoltaic module using electroluminescence images,” Solar Energy, vol. 201, pp. 453–460, Mar. 2020, doi: 10.1016/j.solener.2020.03.049.
- H. Tella, A. Hussein, S. Rehman, B. Liu, A. Balghonaim, and M. Mohandes, “Solar photovoltaic panel cells defects classification using deep learning ensemble methods,” Case Studies in Thermal Engineering, vol. 66, p. 105749, Jan. 2025, doi: 10.1016/j.csite.2025.105749.
- I. I. Malek and H. Imtiaz, “Advanced fault detection in PV panels using deep neural networks: leveraging transfer learning and electroluminescence image processing,” Energy Advances, vol. 5, no. 2, pp. 180–193, Dec. 2025, doi: 10.1039/d5ya00239g.
- A. S. Al‐Waisy et al., “Identifying defective solar cells in electroluminescence images using deep feature representations,” PeerJ Computer Science, vol. 8, p. e992, May 2022, doi: 10.7717/peerj-cs.992.
- M. W. Akram et al., “CNN based automatic detection of photovoltaic cell defects in electroluminescence images,” Energy, vol. 189, p. 116319, Oct. 2019, doi: 10.1016/j.energy.2019.116319.
- A.-K. Hamid, M. Alrahhal, K. Obaideen, T. Bonny, Y. C. Tan, and M. I. Hussein, “Artificial intelligence for smart solar energy monitoring: Genetic attention-based hybrid deep–handcrafted fusion for faulty solar panel image classification,” Results in Engineering, vol. 28, p. 107900, Oct. 2025, doi: 10.1016/j.rineng.2025.107900.
- K. Samrouth, S. Nazir, N. Bakir, and N. Khodor, “Dual CNN for photovoltaic electroluminescence images microcrack detection,” Array, vol. 27, p. 100442, Jul. 2025, doi: 10.1016/j.array.2025.100442.
- N. Drir, F. Chekired, A. Mellit, and N. Blasuttigh, “Hybrid CNN-EML model for fault diagnosis in electroluminescence images of photovoltaic cells,” Renewable Energy, vol. 250, p. 123343, May 2025, doi: 10.1016/j.renene.2025.123343.
- A. Jha, Y. Rawat, and S. Vyas, “Advancing automatic photovoltaic defect detection using semi-supervised semantic segmentation of electroluminescence images,” Engineering Applications of Artificial Intelligence, vol. 160, p. 111790, Jul. 2025, doi: 10.1016/j.engappai.2025.111790.
- U. Hijjawi, S. Lakshminarayana, T. Xu, and M. Rahman, “A benchmarking study of instance segmentation methods for photovoltaic cell defect detection using electroluminescence images,” Solar Energy, vol. 303, p. 114083, Oct. 2025, doi: 10.1016/j.solener.2025.114083.