Additive manufacturing, a key enabler of Industry 4.0, is revolutionizing the automatic landscape in manufacturing. The primary challenge in manufacturing innovation centers on the implementation of smart factories characterized by unmanned production facilities and automated management systems. To overcome this challenge, the adoption of 3D printing technologies, which offer significant advantages in standardizing production processes, is crucial. However, a major obstacle in complete automation of additive manufacturing is an inadequate placement of support structures at critical locations, which remains the leading cause of print failures. This study proposed a novel algorithm for accurate detection of island regions known to be critical areas requiring support structures. The algorithm can compare loops on two consecutive layers derived from STL files. In contrast to conventional GPU-based image comparison methods, our proposed CPU-based algorithm enables high-precision detection independent of image resolution. Experimental results demonstrated the algorithm's efficacy in enhancing the reliability of 3D printing processes and optimizing automated workflows. This research contributes to the advancement of smart manufacturing by addressing a critical challenge in the automation of additive manufacturing processes.
The goal of this research is to develop intelligence data analytics system for quality enhancement of die-casting process. Targeting a die-casting factory in Korea, we first constructed an edge device-based infrastructure with wireless communication environment for data collection and a processing infrastructure to support the intelligence data analytics system. Using the real quality regarding data of the target factory, we developed two data analytics models for defect prediction and defect cause diagnosis using AdaBoostC2 algorithm. Accuracy of the developed data analytics model for defect prediction was verified as 86%. To use the developed data analytics model efficiently and produce a sequential process of data analytics model generation, execution, and update were conducted automatically. The edge device and integrated server-based dualized analysis system was proposed. The developed intelligence data analytics system was applied to the target factory, and the effectiveness was demonstrated.
Citations
Citations to this article as recorded by
Development of AI-based Bearing Machining Process Defect Monitoring System Dae-Youn Kim, Dongwoo Go, Seunghoon Lee Journal of Society of Korea Industrial and Systems Engineering.2025; 48(3): 112. CrossRef
Development of a Quality Prediction Algorithm for an Injection Molding Process Considering Cavity Sensor and Vibration Data Jun Kim, Ju Yeon Lee International Journal of Precision Engineering and Manufacturing.2023; 24(6): 901. CrossRef
Data-analytics-based factory operation strategies for die-casting quality enhancement Jun Kim, Ju Yeon Lee The International Journal of Advanced Manufacturing Technology.2022; 119(5-6): 3865. CrossRef
Development of a cost analysis-based defect-prediction system with a type error-weighted deep neural network algorithm Jun Kim, Ju Yeon Lee Journal of Computational Design and Engineering.2022; 9(2): 380. CrossRef
Development of Prognostics and Health Management System for Rotating Machine and Application to Rotary Table Mingyu Kang, Chibum Lee Journal of the Korean Society for Precision Engineering.2022; 39(5): 337. CrossRef
Server-Edge dualized closed-loop data analytics system for cyber-physical system application Jun Kim, Ju Yeon Lee Robotics and Computer-Integrated Manufacturing.2021; 67: 102040. CrossRef
Die-Casting Defect Prediction and Diagnosis System using Process Condition Data Ji Soo Kim, Jun Kim, Ju Yeon Lee Procedia Manufacturing.2020; 51: 359. CrossRef
Development of Fault Diagnosis Models Based on Predicting Energy Consumption of a Machine Tool Spindle Won Hwa Choi, Jun Kim, Ju Yeon Lee Procedia Manufacturing.2020; 51: 353. CrossRef
First
Prev
