Automated visual inspection system for ATLAS strip hybrid

A method of automating the visual inspection of ATLAS upgrade strip modules is shown. The visual inspection of the hybrids is a time consuming part of the quality control during module production. A method of detecting and classifying (an object detection method) the SMD (surface mount devices) components on the hybrids using an object detection neural network (YOLO) ~\cite{yolo} was investigated. Another system using a computer vision method was also used to check the hybrids for solder splash. These methods were tested on a pre-production batch of 150 hybrids. The results show that the amount of hybrids that needed to be check by a human operator was reduced to around 10$\%$ of the batch. This hugely reduced the amount of time needed for human inspection and did find real mistakes done during the production of the hybrids.