한국생산제조학회 학술지 영문 홈페이지

Current Issue

Journal of the Korean Society of Manufacturing Technology Engineers - Vol. 31 , No. 4

[ Papers ]
Journal of the Korean Society of Manufacturing Technology Engineers - Vol. 31, No. 4, pp. 240-246
Abbreviation: J. Korean Soc. Manuf. Technol. Eng.
ISSN: 2508-5107 (Online)
Print publication date 15 Aug 2022
Received 29 Jun 2022 Revised 01 Aug 2022 Accepted 02 Aug 2022
DOI: https://doi.org/10.7735/ksmte.2022.31.4.240

머신러닝을 활용한 사출성형 품질 예측에 관한 연구
김대호a ; 홍준희b, *

Prediction of Injection Molding Quality Using Machine Learning
Dae Ho Kima ; Jun Hee Hongb, *
aGraduate School of Mechanical Engineering, Chungnam National University
bDepartment of Mechanical Engineering, Chungnam National University
Correspondence to : *Tel.: +82-42-821-5642 E-mail address: hongjh@cnu.ac.kr (Jun Hee Hong).


Abstract

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.


Keywords: Quality prediction, Plastic injection molding, Machine learning, Support vector machine, Smart factory

References
1. Yeo, S. K., Park, D. W., 2021, Design of DNN-Based Injection Molded Product Defect Prediction System, The Journal of Korean Institute of Communications and Information Sciences, 46:10 1771-1777.
2. Song, K. H., Jeong, H. J., Lee, D. Y., Kim, B. H., 2020, Package Software Configuration and Cloud-Based Service System for Building a Smart Factory in the Root Industry, J. Korean Soc. Manuf. Technol. Eng., 29:4 323-330.
3. Sim, H. S., Kim, C. W., 2015, Process and Facility Analysis of PCB Manufacturing Lines Suspected of Defects using Data Mining Techniques, KIPS Transactions on Software and Data Engineering, 4:2 65-70.
4. Kang, D. H., Oh, S. G., Park, J. H., Seo, M. S., 2019, Prediction of Quality of Backplate Products Using Artificial Neural Network, 2019 Autumn Conf. of the Korea Society of Quality Management, 146.
5. Nam, J. I., Park, H. J., 2020, A Neural Network based Fault Detection and Classification System Using Acoustic Measurement, J. Korean Soc. Manuf. Technol. Eng., 29:3 210-215.
6. Kim, H. K., 2022, Wear Diagnostic System for End Mill based on Machine Learning, J. Korean Soc. Manuf. Technol. Eng., 31:1 37-40.
7. Cho, H. M., Shin, H. J., 2021, A Study on Deep Learning Models Application for Quality Prediction in Smart Factory - A Case for Plastic Injection Molding Process, Journal of the Korea Academia-Industrial cooperation Society, 22:10 411-420.
8. Silva, B., Sousa, J., Alenya, G., 2021, Machine Learning Methods for Quality Prediction in Thermoplastics Injection Molding, 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), 1-6.
9. Jung, H. I., Jeon, J. S., Choi, D. H., Park, J. Y., 2021, Application of Machine Learning Techniques in Injection Molding Quality Prediction, Implications on Sustainable Manufacturing Industry, Sustainability, 13:8 4120.
10. Ramana, E. V., 2017, Data Mining Based Approach for Quality Prediction of Injection Molding Process, Int. J. Eng. Technol., 9:3 2220-2224.
11. Kim, B. L., Lee, S. H., Kwon, H. H., 2021, Determination of Injection Conditions for ASTM Flexural Specimen Using Injection Molding Analysis, J. Korean Soc. Manuf. Technol. Eng., 30:3 212-217.

Dae Ho Kim

Ph.D. candidate in the Department of Mechanical Engineering, Chungnam National University. His research interest is PDM, CAD/CAM, and Injection Mold.

E-mail: scv3323@naver.com

Jun Hee Hong

Professor in the School of Mechanical Engineering, Chungnam National University. His research interest is Intelligent Measurement.

E-mail: hongjh@cnu.ac.kr