Article: A machine learning-based image classification of silicon solar cells Journal: International Journal of Hydromechatronics (IJHM) 2024 Vol.7 No.1 pp.49 - 66 Abstract: Silicon-based solar cells are a popular choice to generate electricity from sunlight. Micro-cracks are inherent in brittle silicon cells, which propagate during their service and hence impacts the efficiency. This study is focused on classifying micro-crack patterns in silicon-based solar cells with the help of convolutional neural network (CNN)-based models. A dataset comprising 3,651 electroluminescence images is categorised into five groups: poly-good, poly-cracked, poly-corroded, mono-good, and mono-cracked. Four pre-trained convolutional neural networks, namely: ResNet50, VGG-16, VGG-19, and DenseNet are employed to classify the images, where 80% of the data is used for training and the remaining 20% for testing. Results reveal that the VGG-19 network is able to categorise the images with 100% accuracy in distinguishing poly and mono-crystalline silicon cells, with an overall accuracy of 98.44%, thereby outperforming other models. Thus, a VGG-19-based CNN is recommended for classification of electroluminescence images of silicon solar cells. Such image classification helps for health monitoring and hence, a better maintenance of the PV modules. Inderscience Publishers - linking academia, business and industry through research

Title: A machine learning-based image classification of silicon solar cells

Authors: H. Verma; S.D.V.S.S. Varma Siruvuri; P.R. Budarapu

Addresses: School of Mechanical Sciences, Indian Institute of Technology Bhubaneswar, Bhubaneswar, 752050, India ' School of Mechanical Sciences, Indian Institute of Technology Bhubaneswar, Bhubaneswar, 752050, India ' School of Mechanical Sciences, Indian Institute of Technology Bhubaneswar, Bhubaneswar, 752050, India

Abstract: Silicon-based solar cells are a popular choice to generate electricity from sunlight. Micro-cracks are inherent in brittle silicon cells, which propagate during their service and hence impacts the efficiency. This study is focused on classifying micro-crack patterns in silicon-based solar cells with the help of convolutional neural network (CNN)-based models. A dataset comprising 3,651 electroluminescence images is categorised into five groups: poly-good, poly-cracked, poly-corroded, mono-good, and mono-cracked. Four pre-trained convolutional neural networks, namely: ResNet50, VGG-16, VGG-19, and DenseNet are employed to classify the images, where 80% of the data is used for training and the remaining 20% for testing. Results reveal that the VGG-19 network is able to categorise the images with 100% accuracy in distinguishing poly and mono-crystalline silicon cells, with an overall accuracy of 98.44%, thereby outperforming other models. Thus, a VGG-19-based CNN is recommended for classification of electroluminescence images of silicon solar cells. Such image classification helps for health monitoring and hence, a better maintenance of the PV modules.

Keywords: silicon solar cells; electroluminescence images; deep machine learning; convolutional neural network; CNN; image classification; health monitoring of PV modules.

DOI: 10.1504/IJHM.2024.135990

International Journal of Hydromechatronics, 2024 Vol.7 No.1, pp.49 - 66

Received: 23 Feb 2023
Accepted: 03 Jul 2023
Published online: 11 Jan 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A machine learning-based image classification of silicon solar cells

Keep up-to-date