Paper Contents
Abstract
Renewable energy sources now play a significant part in addressing the growing energy demand for the protection of the environment. The fast-growing innovation in eco-sustainable power is solar energy, supplied by huge solar fields. But, its productivity degrades from solar cell flaws that arise during deployment or are induced by weather occurrences. The images of electroluminescence (EL) can make these faults obvious. The manual categorization of these EL pictures takes an incredible amount of cost and time and is sensitive to subjective changes in the inter-examiner. To combat this problem, many deep learning algorithms have been developed in the past few centuries to identify and categorize the solar cell defects or failures in the EL images. This paper gives a complete review of the solar cell defect classification from several imaging methods. First, the diverse deep learning classifiers using EL images for the identification and categorization of solar cell abnormalities discovered by current researchers are briefly explored. A comparison analysis is then carried out to analyze the difficulties in those classification models and suggests a new approach that improves the precise categorization of flaws in the solar cell from EL images.
Copyright
Copyright © 2024 C. Daxayani. This is an open access article distributed under the Creative Commons Attribution License.
