Abstract
Currently, the development of automated quality inspection is drawing attention as a major component of the smart factory. However, injection molding processes have not received much attention in this area of research because of product diversity, difficulty in obtaining uniform quality product images, and short cycle times. In this study, we proposed a defect inspection system for injection molding in edge intelligence. Using data augmentation, we solved the data shortage and imbalance problem of small and medium-sized enterprises (SMEs), introduced the actual smart factory method of the injection process, and measured the performance of the developed artificial intelligence model. The accuracy of the proposed model was more than 90%, proving that the system can be applied in the field.
Highlights
Injection molding has been widely used in the manufacturing industry, from small companies to major companies
The early detection of injection molding defects plays an important role in identifying failures in the equipment
We proposed a defect inspection system for injection molding in edge intelligence
Summary
Injection molding has been widely used in the manufacturing industry, from small companies to major companies. Continuous training of field professionals in reproducibility verification to bring each person to the same level is essential Repeating this process is so costly that the risk of financial losses throughout the industry has increased the urgency of automating surface defect detection and expanding it to manufacturing. In this paper, we present a novel method called a defect inspection framework based on deep neural networks for injection molding in IoT Systems with Edge. When the object produced by the sub-motor rotates, it is shot through the vision camera and to the edge box, which presents a quality check automation model that detects faults in the Edge Box and transfers the index of product-fault data to the programmable logic controller (PLC).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
