Multiclass Solar Panel Classification based on Surface Anomalies using VGG16

Authors

  • Vijayshri Khedkar, Kalyani Kadam, Ananya Shetty, Utkarsh Rastogi, Pranali G. Chavhan

Keywords:

Solar panel anomaly detection, VGG16, Transfer learning, Computer vision, Sustainable energy maintenance, Global solar energy systems, Solar panel monitoring.

Abstract

This study fills a crucial research gap in understanding solar panel efficiency by focusing on quantifying the impact of surface anomalies. Employing machine learning, computer vision, and transfer learning, our solar panel classification model, based on the VGG16 architecture, accurately identifies surface issues. A comprehensive literature review underscores the importance of anomaly assessment. The methodology involves meticulous data preprocessing, architectural modifications, and parameter optimization. Evaluation results show a significant accuracy improvement for both training (65.25% to 98.16%) and validation (75.14% to 83.62%) datasets, with robust precision, recall, and F1-score metrics. Implementing an early stopping mechanism prevents overfitting, ensuring a balanced, high-accuracy, and generalizable model. The study culminates in a powerful tool for global solar energy systems, enhancing efficiency and viability. It advocates for advanced technology integration with environmental consciousness, contributing to a cleaner and greener energy future. By addressing the critical gap in anomaly assessment, this research provides a reliable, eco-friendly solution for solar panel monitoring and maintenance, supporting sustainable growth in the solar power industry.

Downloads

Download data is not yet available.

References

J. Zhang et al., "Automated Solar Panel Classification Using Deep Learning Techniques," IEEE Transactions on Sustainable Energy, vol. 10, no. 4, pp. 1850-1858, 2019.

A. Smith et al., "Applications of Solar Energy and the Importance of Advanced Classification Techniques," IEEE Journal of Photovoltaics, vol. 8, no. 2, pp. 520-527, 2018.

Q. Wang and L. Chen, "Deep Learning-Based Solar Panel Classification: A Comparative Study," IEEE Transactions on Industrial Electronics, vol. 66, no. 10, pp. 7892-7900, 2019.

R. Jones and M. Brown, "Impact of Misclassification on Solar Panel Maintenance," IEEE Transactions on Sustainable Energy, vol. 11, no. 1, pp. 350-358, 2020.

Y. Liu et al., "Fault Diagnosis System for Solar Panels Using Machine Learning," IEEE Transactions on Power Systems, vol. 35, no. 2, pp. 1023-1031, 2020.

A. Garcia and P. Rodriguez, "Effects of Shading on Solar Panel Classification Accuracy," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 4178-4187, 2020.

H. Li and S. Wang, "Impact of Environmental Factors on Solar Panel Classification Performance," IEEE Transactions on Sustainable Energy, vol. 9, no. 3, pp. 1322-1329, 2018.

X. Chen et al., "Adaptive Techniques for Solar Panel Classification Under Varying Lighting Conditions," IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 5, pp. 1551-1559, 2019.

J. Kim et al., "Effects of Image Quality on Solar Panel Classification Accuracy," IEEE Journal of Photovoltaics, vol. 7, no. 4, pp. 1132- 1139, 2017.

S. Sharma et al., "Enhancing VGG16 for Solar Panel Classification: A Modification Approach," IEEE Access, vol. 8, pp. 187240-187251, 2020.

X. Zhao and H. Li, "Improved Feature Extraction for Solar Panel Classification with Spatial Information," IEEE Transactions on Industrial Informatics, vol. 16, no. 3, pp. 1654-1661, 2020.

R. Patel et al., "Comparative Analysis of Deep Learning Models for Solar Panel Classification," IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 7, pp. 2452-2464, 2020.

Q. Wang et al., "Transfer Learning and Fine-Tuning for Solar Panel Classification," IEEE Access, vol. 9, pp. 31550-31559, 2021.

Downloads

Published

24.03.2024

How to Cite

Vijayshri Khedkar. (2024). Multiclass Solar Panel Classification based on Surface Anomalies using VGG16. International Journal of Intelligent Systems and Applications in Engineering, 12(3), 3833–3842. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/6067

Issue

Vol. 12 No. 3 (2024)

Section

Research Article

License

Creative Commons License

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

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.