Automated quality control of vacuum insulated glazing by convolutional neural network image classification

Abstract

Vacuum insulated glazing (VIG) is a highly thermally insulating window technology, which boasts an extremely thin profile and lower weight as compared to gas-filled insulated glazing units of equivalent performance. The VIG is a double-pane configuration with a submillimeter vacuum gap maintained by small pillars positioned in between the panes, which can damage the glass during manufacturing, transportation and installation. For the purpose of automatically classifying the damage, we have developed, trained, and tested a deep learning model using convolutional neural networks. We employ the state-of-the-art methods Grad-CAM and Score-CAM of explainable Artificial Intelligence (XAI) to provide an understanding of the internal mechanisms and were able to show that our classifier outperforms ResNet50V2 for identification of crack locations and geometry. Further analysis of our model's predictive capabilities demonstrates its superiority over state-of-the-art ResNet models in terms of convergence speed, accuracy, precision at 100% recall and AUC for ROC.