摘要：With the advent of the 4th Industrial Revolution, research on anomaly detection in the manufacturing process using deep learning and machine vision is being actively conducted. There have been various attempts to innovate the manufacturing site by adopting advance information technologies such as machine vision, machine learning, and deep learning in many manufacturing processes. However, there have been no cases of designing and implementing these technologies at the mask manufacturing site, which is essential to tackle COVID-19 pandemic. The originality of this paper is to implement sustainability in the mask manufacturing environment and industrial eco-system by introducing the latest computer technology into the manufacturing process essential for pandemic-related disasters. In this study, the intention is to establish a machine vision-based quality inspection system in actual manufacturing process to improve sustainable productivity in the mask manufacturing process and try a new technical application that can contribute to the overall manufacturing process industry in Korea in the future. Therefore, the purpose of this paper is to specifically present hardware and software system construction and implementation procedures for inspection process automation, control automation, POP (Point Of Production) manufacturing monitoring system construction, smart factory implementation, and solutions. This paper is an application study applied to an actual mask manufacturing plant, and is a qualitative analysis study focused on improving mask productivity. “Company A” is a mask manufacturing company that produces tons of masks everyday located in Korea. This company planned to automate the identification of good and defective products in the mask manufacturing process by utilizing machine vision technology. To this end, a deep learning and machine vision-based anomaly detection manufacturing environment is implemented using the LAON PEOPLE NAVI AI Toolkit. As a result, the productivity of “Company A”’s mask defect detection process can be dramatically improved, and this technology is expected to be applied to similar mask manufacturing processes in the future to make similar manufacturing sites more sustainable.
