머신러닝을 활용한 사출성형 품질 예측에 관한 연구

• Published in: 한국생산제조학회지 Vol. 31; no. 4; pp. 240 - 246
• Main Authors: 김대호(Dae Ho Kim), 홍준희(Jun Hee Hong)
• Format: Journal Article
• Language: Korean
• Published: 한국생산제조학회 01.08.2022
• Subjects: 기계공학; Support vector machine; Quality prediction; Plastic injection molding; Smart factory; Machine learning
• ISSN: 2508-5093; 2508-5107
• DOI: 10.7735/ksmte.2022.31.4.240

The injection molding process is a process in which products, such as plastics and rubber, are mass-produced. It is essential in industry, from high-tech industries such as automobiles and aerospace parts, to daily necessities. The quality control of injection molding is based on the operator's experience or involves measurements and evaluations of some first products; hence, real-time process monitoring and data-based quality control are required. In this study, an autoencoder and a support vector machine were used to predict quality, and the learning dataset was collected using a sensor attached to the injection molding machine. Next, good and bad products were labeled, and hyperparameters were changed for each model. By learning, the performance of each model was evaluated. Reliability improvement is expected through data-based quality management using the machine learning model proposed in this study to predict the quality based on changes under process conditions. KCI Citation Count: 0