Quality control using artificial intelligence (AI) has led to considerable improvements in the manufacturing industry. However, trimming die design inspection to minimize potential failures is still done manually by engineers. The inspection is labor-intensive, time-consuming, and prone to human error. In this study, we developed an automatic design inspection system for automobile trimming dies by integrating AI modules and computer-aided design (CAD) software. The AI modules replace the engineers' judgment, and the CAD software performs the operations requested by the AI modules. The design inspection is completed through a zigzag interaction between the AI modules and CAD software by a one-click operation without the intervention of experts. In the zigzag interaction process, 3D CAD files are converted to 2D images for interaction from the CAD software to the AI modules, and the output of the AI modules is transferred to the CAD software through VBA macros.The AI modules are designed to be CAD-independent and data-efficient; therefore, they can be easily adapted to other CAD software and achieve a high performance, even when trained with only a few trimming dies. The length measurement error is only 2.4 % on an average, which is at the 14th place out of 18 grades according to ISO 286-1:1988 standard tolerance. In addition, the inspection time is reduced to approximately one-fifth of the manual inspection time by experts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.