Articles & Issues

Language: korean

Conflict of Interest: In relation to this article, we declare that there is no conflict of interest.

Publication history: Received March 2, 2020
Accepted May 30, 2020

This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/bync/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

All issues

증류탑을 위한 머신러닝 기반 플랫폼 개발

Development of Machine Learning-Based Platform for Distillation Column

오광철¹ 권혁원^{1 2} 노지원^{1 3} 최영렬^{1 3} 박현도^{1 3} 조형태¹ 김정환^1†

Kwang Cheol Oh¹ Hyukwon Kwon^{1 2} Jiwon Roh^{1 3} Yeongryeol Choi^{1 3} Hyundo Park^{1 3} Hyungtae Cho¹ Junghwan Kim^1†

¹한국생산기술연구원 친환경재료공정연구그룹, 44413 울산광역시 중구 종가로 55 ²부산대학교 화공생명공학부, 46241 부산광역시 금정구 부산 대학로 63번길 2 ³연세대학교 화공생명공학과, 03722 서울특별시 서대문구 연세로 50

¹Green Materials and Processes R&D Group, Korea Institute of Industrial Technology, 55 Jongga-ro, Jung-gu, Ulsan, 44413, Korea ²School of Chemical & Biomoleular Engineering, Pusan National University, 2, Busandaehak-ro, 63beon-gil, Geumjeong-gu, Busan, 46241, Korea ³Department of Chemical and Biomolecular Engineering, Yonsei University, 50, Yensei-ro, Seodaemun-gu, Seoul, 03722, Korea

kjh31@kitech.re.kr

Korean Chemical Engineering Research, November 2020, 58(4), 565-572(8), 10.9713/kcer.2020.58.4.565 Epub 29 October 2020

Download PDF

Abstract

본 연구는 증류탑 분리공정 시스템 최적화를 위하여 인공지능 머신러닝이 적용된 소프트웨어 플랫폼을 개발하였다. 증류탑 분리공정은 석유화학 산업의 대표적이고 핵심적인 공정이다. 하지만 다양한 운전조건과 연속식공정 특성으로 인하여 안정적인 운전이 어려우며 운전자 숙련도에 의하여 공정효율에 차이가 발생된다. 이를 해결하기 위하여 이론적 시뮬레이션을 활용한 제어방법이 개발되어 사용되고 있지만 특수하거나 복잡한 반응이 포함된 공정에는 적용이 어려우며, 거대한 시스템에 대하여 분석이 이루어질 경우 계산비용 증대로 인하여 실시간 제어와 연동이 어려운 한계점을 지니고 있다. 따라서 본 연구에서는 이러한 문제점을 해결하기 위하여 머신러닝을 기반으로 한 경험적 시뮬레이션 모델을 개발하고 이를 통하여 최적의 공정운영방법을 제시하고자 한다. 경험적 시뮬레이션 개발은 실제 공정에서 수집된 빅 데이터, 데이터마이닝을 통한 특성추출, 공정을 대표하는 데이터 선별, 화학공정 특성에 맞는 모델 선정으로 이루어졌으며, 현장검증 및 테스트를 통하여 증류탑 분리공정 플랫폼이 개발되었다. 최종적으로 개발된 플랫폼을 통하여 운전 조작변수의 예측이 가능하며, 최적화된 운전조건을 제공하여 효율적인 공정운영을 달성할 수 있다. 본 논문은 머신러닝 기법을 화학공정에 적용한 기초연구로서 이후 다양한 공정에 적용하여 4차 산업의 스마트 팩토리의 초석이되어 널리 활용될 수 있을 것이라 판단된다.

This study developed a software platform using machine learning of artificial intelligence to optimize the distillation column system. The distillation column is representative and core process in the petrochemical industry. Process stabilization is difficult due to various operating conditions and continuous process characteristics, and differences in process efficiency occur depending on operator skill. The process control based on the theoretical simulation was used to overcome this problem, but it has a limitation which it can’t apply to complex processes and real-time systems. This study aims to develop an empirical simulation model based on machine learning and to suggest an optimal process operation method. The development of empirical simulations involves collecting big data from the actual process, feature extraction through data mining, and representative algorithm for the chemical process. Finally, the platform for the distillation column was developed with verification through a developed model and field tests. Through the developed platform, it is possible to predict the operating parameters and provided optimal operating conditions to achieve efficient process control. This study is the basic study applying the artificial intelligence machine learning technique for the chemical process. After application on a wide variety of processes and it can be utilized to the cornerstone of the smart factory of the industry 4.0.

Keywords

Big data Machine learning-based platform Empirical simulation Process optimization

References

Na JG, Lee U, NICE (News & Information for Chemical Engineers), 36(1), 4-8 (2018).
Cho YS, Hanyang university, GRADUATE SCHOOL(2018).
Cui Y, Matsubara T, Sugimoto K, Neural Networks, 94, 13 (2017)
Song YE, Moon AK, An SY, Jung HY, J. Korean Soc. Precis. Eng., 36(3), 239 (2019)
Lee DH, Lim MK, Park HS, Kim JH, Journal of Digital Contents Society, 18(1), 93-99(2017).
Song JH, Department of Software Convergence(2018).
Oh KC, Euh SH, Oh JH, Kim DH, J. Energy Engineering, 23(3), 213 (2014)
Francois C, “Deep learning with Python,” (2017).
Oh SM, Lee DS, Kim JS, Park JH, Journal of Digital Contents Society, 20(12), 2525-2533(2019).
Hope T, Resheff YS, Lieder I, O'Reilly Media(2017).
Muller AC, Guido S, O'Reilly Media(2017).
Ariga M, Nakayama S, Nishibayasi D, O’Reilly Media(2018).
Kim SY, Jung YJ, Hanbit Media(2017).
Seo TH, Byun MK, Lee HS, J. Digital Contents Society, 21(1), 165-172(2020).
Park KS, Hwang KS, Lee KM, J. Korean Institute of Intelligent Systems, 29(1), 23-29(2019).
Jo YH, Seo EG, Journal of Korean Society of Archives and Records Management, 16(3), 209-233(2016).
Jin JH, Journal of Korean Soc. of Mechanical Technology, 16(3), 1447-1453(2014).
Liu X, Ounifi HA, Gherbi A, Lemieux Y, Li W, Procedia Computer Science, 141, 104 (2018)
Kim MH, Joo SC, Journal of KIISE : Computing Practices and Letters, 7(6), 602-613(2001).
Kim J, Lim W, Lee Y, Kim S, Park SR, Suh SK, Moon I, Industrial & Engineering Chemistry Research, 50(13), 8272-8277(2011).
Lee KM, Yoo J, Kim SW, Lee JH, Hong J, International Journal of Information Management, 49, 491-501(2019).
Chang Z, Zhang Y, Chen W, Energy, 187, 115804 (2019)
Keshavarzian A, Sharifian S, Seyedin S, Future Generation Computer Systems, 101, 14 (2019)
Zhao H, Liu F, Zhang H, Liang Z, Neural Networks, 110, 225 (2019)
Seul MS, The Justice, 10, 269 (2016)