Synthetic Dataset of Electroluminescence Images of Photovoltaic Cells by Deep Convolutional Generative Adversarial Networks

This article presents a different way of obtaining images of solar cells using Artificial Intelligence techniques such as Generative Adversarial Neural Networks (GANs). This will improve the maintenance of Photovoltaic Systems in different places like Smart Cities. The original data has been obtained manually and preprocessed to create better images. The GAN architecture used is known as Deep Convolutional GAN since it performs better than other GANs. The synthetic images were labeled and analyzed to ensure their quality.