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

Abstract

Affordable and clean energy is one of the Sustainable Development Goals (SDG). SDG compliance and economic crises have boosted investment in solar energy as an important source of renewable generation. Nevertheless, the complex maintenance of solar plants is behind the increasing trend to use advanced artificial intelligence techniques, which critically depend on big amounts of data. In this work, a model based on Deep Convolutional Generative Adversarial Neural Networks (DCGANs) was trained in order to generate a synthetic dataset made of 10,000 electroluminescence images of photovoltaic cells, which extends a smaller dataset of experimentally acquired images. The energy output of the virtual cells associated with the synthetic dataset is predicted using a Random Forest regression model trained from real IV curves measured on real cells during the image acquisition process. The assessment of the resulting synthetic dataset gives an Inception Score of 2.3 and a Fréchet Inception Distance of 15.8 to the real original images, which ensures the excellent quality of the generated images. The final dataset can thus be later used to improve machine learning algorithms or to analyze patterns of solar cell defects.

Defect detection of photovoltaic modules based on improved VarifocalNet

“…Besides, an intelligent algorithm based on the high-resolution network was also proposed for the defect detection of photovoltaic modules. Other EL image generation methods were also proposed 18 . To improve the defects classification and detection results in raw solar cell EL images, Su et al 19 proposed a novel complementary attention network and a region proposal attention network, and introduced the proposed networks into the Faster RCNN.…”

“… Higher detection accuracy Slower detection speed Based on the one-stage method Meng et al 24 , Tang et al 25 , Shen et al 26 , Jiang et al 28 , etc. Faster detection speed Lower detection accuracy Based on GAN and the two-stage method Tang et al 16 , Zhao et al 17 , Romero et al 18 Higher detection accuracy Fewer types of defects …”

Environmental Sustainability in the Age of Deep Learning: Balancing Technological Advancement with Ecological Responsibility

“…Pierdicca et al (2020) suggested a deep learning-based method for detecting anomalies in photovoltaic photos, demonstrating AI's effectiveness in maintaining renewable energy systems [12]. Deep convolutional generative adversarial networks (DCGANs) have been used to generate synthetic datasets for solar cell defect analysis, marking significant progress in the area [13].…”

Deep Learning and Artificial Intelligence in Sustainability: A Review of SDGs, Renewable Energy, and Environmental Health

“…For instance, a deep learning-based system proposed by Pierdicca et al (2020) for anomaly detection in photovoltaic images demonstrated the efficacy of AI in maintaining the health of renewable energy systems [4]. In addition, the generation of synthetic datasets for solar cell defect analysis using deep convolutional generative adversarial networks (DCGANs) represents a significant advancement in the field [5].…”