Anomaly detection in electroluminescence images of heterojunction solar cells

Abstract

Efficient defect detection in solar cell manufacturing is crucial for stable green energy technology manufacturing. This paper presents a deep-learning-based automatic detection model SeMaCNN for classification and anomaly detection of electroluminescent images for solar cell quality evaluation. The core of the model is an anomaly detection algorithm based on Mahalanobis distance that can be trained in a semi-supervised manner on imbalanced data with a small number of digital electroluminescence images with relevant defects. This is particularly valuable for prompt model integration into the industrial landscape. The model has been trained with the dataset collected at the manufacturing plant consisting of 68 748 electroluminescent images of heterojunction solar cells with a busbar grid. Our model achieves the accuracy of 92.5%, F1 score 95.8%, recall 94.8%, and precision 96.9% within the validation subset consisting of 1049 manually annotated images. The model was also tested on the open ELPV dataset and demonstrates stable performance with accuracy 94.6% and F1 score 91.1%. The SeMaCNN model demonstrates a good balance between its performance and computational complexity, which make it applicable for integrating into quality control systems of solar cell manufacturing.