[ Article ]

Journal of the Korean Society of Manufacturing Technology Engineers - Vol. 32, No. 2, pp.72-77

ISSN: 2508-5107 (Online)

Print publication date 15 Apr 2023

Received 01 Feb 2023 Revised 15 Feb 2023 Accepted 22 Mar 2023

DOI: https://doi.org/10.7735/ksmte.2023.32.2.72

Machine Learning을 이용한 LCD 3D프린터 공정조건 추천시스템 개발

성시헌^a ; 이성범^b^{, *} ; 김현수^c^{, *} ; 김현철^d^{, *}

Development of an LCD 3D Printer Process Parameter Recommendation System by Machine Learning

Siheon Seong^a ; Seongbeom Lee^b^{, *} ; Hyunsoo Kim^c^{, *} ; Hyunchul Kim^d^{, *}

aDepartment of Mechanical Engineering, Inje University
bDepartment of Electronic, Telecommunications, Mechanical and Automotive Engineering, High Safety Vehicle Core Technology Research Center, Inje University
cDepartment of Mechanical Engineering, Ulsan College
dDepartment of Future Automotive Engineering, Kongju National University

Correspondence to: ^*These authors contributed equally to this work. ^b*Tel.: +82-55-320-3667 E-mail address: mechlsb@inje.ac.kr (Seongbeom Lee). ^c*Tel.: +82-52-279-3122 E-mail address: hskim3@uc.ac.kr (Hyunsoo Kim). ^d*Tel.: +82-41-521-9273 E-mail address: khc@kongju.ac.kr (Hyunchul Kim).

Abstract

With the development of the fourth industry, production methods using 3D printers are increasingly being used to compensate for the limitations of mold processing. Under the existing mold method, the production time is slow and no fixed production process exists. These result in low product reliability and expensive equipment, making the existing mold method inefficient and limited in use. This study develops a liquid crystal display(LCD) 3D printer process parameter recommendation system that can solve the unspecified production processes . To indicate the stacking height and direction, the system is divided into X and Y axes, respectively , and each axis is raised from 0° to 90° in increments of 5° to test samples. After manufacture, a hardness test is performed, and the output accuracy and precision are measured. Using a Gaussian regression, we implement the system to recommend grade results from 1 to 9 to workers and verify performance.

Keywords:

Machine learning, LCD 3D printer, Process parameter, Gaussian linear regression

Acknowledgments

이 논문은 2022년도 정부(교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업 (NRF-2021R1I1A3048752)과 2021~2022년도 교육부의 재원으로 한국연구재단의 지원을 받아 수행된 지자체-대학 협력 기반 지역혁신 사업의 결과입니다. (2021RIS-003, 2021RIS-004) 또한, 본 연구는 2020년도 교육부의 재원으로 한국기초과학지원연구원 국가연구시설장비진흥센터의 지원을 받아 수행된 연구입니다. (2020R1A6C101A187)

References

Choi, B. J., Yang, J. Y., Lee, M. G., Jeon, Y. H., 2021, Defect Analysis of Metal 3D Printing Process, J. Korean Soc. Manuf. Technol. Eng., 30:1 92-98. [https://doi.org/10.7735/ksmte.2021.30.1.92]
Shin, G. S., Kweon, H. K., Kang, Y. G., 2017, The Influence of Experiment Variables on DLP 3D Printing using ART Resin, J. Korean Soc. Manuf. Proc. Eng., 16:6 101-108. [https://doi.org/10.14775/ksmpe.2017.16.6.101]
Jo, K. H., Lee, S. H., Jang, H. S., Ha, Y. M., 2015, Development of High-Performance, Low-Cost 3D Printer Using LCD and UV-LED, J. Korean Soc. Precis. Eng., 32:10 917-923. [https://doi.org/10.7736/KSPE.2015.32.10.917]
Park, C., Kim, M. H., Hong, S. M., Go, J. S., Shin, B. S., 2015, A Study on the Comparison Mechanical Properties of 3D Printing Prototypes with Laminating Direction, J. Korean Soc. Manuf. Technol. Eng., 24:3 334-341. [https://doi.org/10.7735/ksmte.2015.24.3.334]
Jung, S. J., Hur, J. W., 2020, Deep Learning Approaches to RUL Prediction of Lithium-ion Batteries, J. Korean Soc. Manuf. Proc. Eng., 19:12 21-27. [https://doi.org/10.14775/ksmpe.2020.19.12.021]
Choi, H., Kim, T. K., Heo, G. R., Choi, S. D., Hur, J. W., 2019, Study of Fuel Pump Failure Prognostic Based on Machine Learning using Artificial Neural Network,J. Korean Soc. Manuf. Proc. Eng., 18:9 52-57. [https://doi.org/10.14775/ksmpe.2019.18.9.052]
Rasmussen, C. E., Williams, C. K. I., 2006, Gaussian Processes for Machine Learning, The MIT Press, U.S.A. [https://doi.org/10.7551/mitpress/3206.001.0001]
Meng, L., Mcwilliams, B., Jarosinski, W., Park, H. Y., Jung, Y. G., Lee, J. U., Zhang, J., 2020, Machine Learning in Additive Manufacturing: A Review, J. Miner. Met. Mater. Soc., 72:6 2364-2375. [https://doi.org/10.1007/s11837-020-04155-y]
Koo, M. H., Park, E. Y., Jeong, J. A, Lee, H. M., Kim, H. G., Kwon, M. J., Kim, Y. S., Nam, S. W., Ko, J. Y., Choi, J. H., Kim, D. G., Jo, S. B., 2013, Applications of Gaussian Process Regression to Groundwater Quality Data, J. Soil Groundw. Environ., 21:6 67-79. [https://doi.org/10.7857/JSGE.2016.21.6.067]

Siheon Seong

Ma. D. Candidate in the School of Mechanical Engineering, Inje University. His research interest is Mechanical Engineering.

E-mail: ssh831@oasis.inje.ac.kr

Seongbeom Lee

Professor in the Department of Electronic, Teleco mmunications, Mechanical and Automotive Engineering, Inje University. His research interest is Structure Analysis.

E-mail: mechlsb@inje.ac.kr

Hyunsoo Kim

Professor in the Department of Mechanical Engineering, Ulsan College. His research interest is 3D Printing and Smart Manufacturing.

E-mail: hskim3@uc.ac.kr

Hyunchul Kim

Professor in the Department of Future Automotive Engineering, Kongju National University. His research interest is CAD/CAM and Precision Machining.

E-mail: khc@kongju.ac.kr