Performance Analysis of SVM and CNN Networks for Defect Detection in Solar Panel

Open Access

Year : 2023 | Volume :7 | Issue : 1 | Page : 15-24

    Vishakha Yadav

  1. Om Dev Singh

  2. Shubham Singh

  3. Shailender Gupta

  1. Ph.D. Scholar, Department of Electronics & Communication Engineering, Mizoram University, Mizoram, India
  2. Research Scholar, Department of Electronics Engineering, J.C. Bose University of Science & Technology, YMCA, Faridabad, Haryana, India


Use of solar panel in generating electricity is increasing globally day by day to meet the increase in demand of power. Many developments have been made in order to achieve higher efficiency of the system. But efficiency of the system may still decrease due to harsh environmental conditions or poor handling of the. These factors highly contribute in the performance degradation of the system. For detection of these irregularities, human level inspections to advance level methods are available in order to enhance the performance metrics. This paper focuses on performance evaluation and comparison of Support Vector Machines (SVM) and Convolution Neural Network (CNN), to find their effectiveness in detection of the defect in Photo-Voltaic cell. To achieve this both SVM and CNN models are trained and tested with the electroluminescence dataset. The simulation results depicts that CNN achieves higher accuracy than SVM on grounds of accuracy (87.97%) and error rate (1.7%)

Keywords: Convolution Neural Network, Support Vector Machine, Photo-Voltaic, Electroluminescence.

[This article belongs to International Journal of Analog Integrated Circuits(ijaic)]

How to cite this article: Vishakha Yadav, Om Dev Singh, Shubham Singh, Shailender Gupta , Performance Analysis of SVM and CNN Networks for Defect Detection in Solar Panel ijaic 2023; 7:15-24
How to cite this URL: Vishakha Yadav, Om Dev Singh, Shubham Singh, Shailender Gupta , Performance Analysis of SVM and CNN Networks for Defect Detection in Solar Panel ijaic 2023 {cited 2023 Jan 17};7:15-24. Available from:

Full Text PDF Download

Browse Figures


1. R.W. Birkmire and E. Eser. “Polycrystalline Thin Film Solar Cells: Present Status and Future Potential,” Annual Review of Material Science; August 1997: 27(1): 625–653.
2. A. Goetzberger, J. Luther, and G. Willeke. “Solar cells: past, present, future,” Solar Energy Materials and Solar Cells. October 2002; 74(1): 1–11. DOI: 10.1016/S0927-0248(02)00042-9.
3. M.A. Green. “Photovoltaic principles,” Physica E: Low-dimensional Systems and Nanostructures. April 2002; 14(1): 11–17. DOI: 10.1016/S1386-9477(02)00354-5.
4. M.A. Green. “Corrigendum to ‘Solar cell efficiency tables (version 49)’ [Prog. Photovolt: Res. Appl. 2017; 25:3–13],” Progress in Photovoltaics: Research and Applications. 2017. 25(4):333– 334. DOI: 10.1002/pip.2876.
5. D.M. Chapin, C.S. Fuller, and G.L. Pearson. “A New Silicon p‐n Junction Photocell for Converting Solar Radiation into Electrical Power. Journal of Applied Physics. May 1954; 25(5):
676–677. DOI: 10.1063/1.1721711.
6. M. Abdelhamid, R. Singh, and M. Omar. “Review of Microcrack Detection Techniques for Silicon Solar Cells”. IEEE Journal of Photovoltaics. January 2014; 4(1): 514–524. DOI: 10.1109/JPHOTOV.2013.2285622.
7. S. Deitsch et al. “Automatic classification of defective photovoltaic module cells in electroluminescence images,” Solar Energy. June 2019; 185: 455–468. DOI: 10.1016/j.solener.2019.02.067.
8. M. Dhimish and V. Holmes. “Solar cells micro crack detection technique using state-of-the-art electroluminescence imaging,” Journal of Science: Advanced Materials and Devices. December 2019; 4(4): 499–508. DOI: 10.1016/j.jsamd.2019.10.004.
9. Y. Shi, L. Cui, Z. Qi, F. Meng, and Z. Chen, “Automatic Road Crack Detection Using Random Structured Forests. IEEE Transactions on Intelligent Transportation Systems. December 2016; 17(12): 3434–3445. DOI: 10.1109/TITS.2016.2552248.
10. P. Wang and H. Huang. “Comparison analysis on present image-based crack detection methods in concrete structures. 2010 3rd International Congress on Image and Signal Processing; October 2010 16-18; Yantai, China. US: IEEE; 2010. 2530–2533p. DOI: 10.1109/CISP.2010.5647496.
11. S.A. Anwar and M.Z. Abdullah. Micro-crack detection of multicrystalline solar cells featuring an improved anisotropic diffusion filter and image segmentation technique. EURASIP Journal on Image and Video Processing. Mar. 2014; 2014(1): 15. DOI: 10.1186/1687-5281-2014-15.
12. C. Cortes and V. Vapnik. Support-vector networks. Machine Learning. September 1995; 20(3): 273–297. DOI: 10.1007/BF00994018.
13. G. Huang, H. Zhou, X. Ding, and R. Zhang, “Extreme Learning Machine for Regression and Multiclass Classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).April 2012; 42(2): 513–529. doi: 10.1109/TSMCB.2011.2168604.
14. Guang-Bin Huang, K.Z. Mao, Chee-Kheong Siew, and De-Shuang Huang. Fast Modular network implementation for support vector machines. IEEE Transactions on Neural Networks. November 2005; 16(6): 1651–1663., DOI: 10.1109/TNN.2005.857952.
15. W.S. Noble. What is a support vector machine?, Nature Biotechnology. December 2006; 24(12):1565–1567.doi: 10.1038/nbt1206-1565.
16. Cadence (2015).Using convolutional neural networks for image recognition. [Online]. Available from
17. R. Yamashita, M. Nishio, R.K.G. Do, and K. Togashi. Convolutional neural networks: an overview and application in radiology. Insights into Imaging. August 2018. 9(4):611–629. DOI: 10.1007/s13244-018-0639-9.
18. S. Karamizadeh, S.M. Abdullah, M. Halimi, J. Shayan, and M.j. Rajabi. Advantage and drawback of support vector machine functionality. 2014 International Conference on Computer, Communications, and Control Technology (I4CT), 2-4 September. 2014. Langkawi, Malaysia. US: IEEE. 63–65p. DOI: 10.1109/I4CT.2014.6914146.

Regular Issue Open Access Article
Volume 7
Issue 1
Received August 10, 2021
Accepted September 17, 2021
Published January 17, 2023