Automated visual inspection of silicon detectors in CMS experiment
This work addresses a domain-specific challenge in high-energy physics manufacturing by automating visual inspection, but it appears incremental as it applies existing deep learning methods to a new dataset.
The paper tackled the problem of manually inspecting numerous checkpoints in silicon detector modules for the CMS experiment by proposing a deep learning-based object detection approach to automate defect detection, though no concrete performance numbers were provided.
In the CMS experiment at CERN, Geneva, a large number of HGCAL sensor modules are fabricated in advanced laboratories around the world. Each sensor module contains about 700 checkpoints for visual inspection thus making it almost impossible to carry out such inspection manually. As artificial intelligence is more and more widely used in manufacturing, traditional detection technologies are gradually being intelligent. In order to more accurately evaluate the checkpoints, we propose to use deep learning-based object detection techniques to detect manufacturing defects in testing large numbers of modules automatically.