한국가스학회지 (Journal of the Korean Institute of Gas)

  • 제23권4호
  • /
  • Pages.19-27
  • /
  • 2019
  • /
  • 1226-8402(pISSN)
  • /
  • 2713-6922(eISSN)
한국가스학회 (The Korean Institute of GAS)
권호 표지
DOI QR코드

DOI QR Code

다중모드 주성분분석에 기반한 천연가스 액화플랜트의 성분 분리공정 감시 시스템 개발

Development of Monitoring System for the LNG plant fractionation process based on Multi-mode Principal Component Analysis

  • 편하형 (서울대학교 화학생물공학부) ;
  • 이철진 (중앙대학교 화학신소재공학부) ;
  • 이원보 (서울대학교 화학생물공학부)
  • Pyun, Hahyung (School of chemical and Biological Engineering, Seoul National University) ;
  • Lee, Chul-Jin (School of Chemical Engineering and Materials Science, Chung-Ang University) ;
  • Lee, Won Bo (School of chemical and Biological Engineering, Seoul National University)
  • 투고 : 2019.06.11
  • 심사 : 2019.08.14
  • 발행 : 2019.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

세계 환경규제가 강화되면서 액화천연가스의 사용량이 지속해서 증가하고 있다. 안정적이고 효율적인 액화천연가스 생산을 위해서는 운전 조건을 세분화하여 감시하는 시스템 구축이 필수적이다. 본 연구에서는 천연가스 액화플랜트 성분 분리공정을 해석하여 구축한 동적 모델 데이터를 대상으로 다중 모드 감시시스템 개발 방법을 제안하였다. 먼저 전체 정상 데이터를 주성분분석과 k-평균 군집화 방법론을 사용하여 다중 정상 운전 모델로 구분하였다. 그 다음, 새로운 데이터 값을 k-최근접 알고리즘으로 구축된 다중 정상 모드와 매칭하였다. 마지막으로, 다중 모드 주성분분석 감시 기법을 통해 공정 데이터의 이상 여부를 판별하였다. 제시된 방법론은 45가지 이상경우에 적용하였고, 기본 주성분분석 방법론과 단변수 감시 방법론과의 비교를 통해 속도와 정확도 지표에서 평균 약 5~10%이상 우수함을 입증하였다.

The consumption of liquefied natural gas (LNG) has increased annually due to the strengthening of international environmental regulations. In order to produce stable and efficient LNG, it is essential to divide the global (overall) operating condition and construct a quick and accurate monitoring system for each operation condition. In this study, multi-mode monitoring system is proposed to the LNG plant fractionation process. First, global normal operation data is divided to local (subdivide) normal operation data using global principal component analysis (PCA) and k-means clustering method. And then, the data to be analyzed were matched with the local normal mode. Finally, it is determined the state of process abnormality through the local PCA. The proposed method is applied to 45 fault case and it proved to be more than 5~10% efficient compared to the global PCA and univariate monitoring.

키워드

참고문헌

  1. Cheong, H.Y. and Park, H.J., "Forecasting the Daily Demand of Natural Gas for Power Generation". Bulletin Korea Photovoltatic Soc, 4(2), 45-53, (2018)
  2. Lee, S.L., Lee, J.W. and Kim, G.W., "Forecasting the Medium Term Demand of LNG for Power Generation under the Energy Transition Policy in South Korea", Journal of Climate Chang Research, 10(1), 47-54, (2019) https://doi.org/10.15531/KSCCR.2019.10.1.47
  3. Xu, R. and WunschII, D., "Survey of Clustering Algorithms", IEEE Transactions on Neural Networks, 16(3), 645-678, (2005) https://doi.org/10.1109/TNN.2005.845141
  4. Geng, Z. and Zhu, Q., "Multiscale Nonlinear Principal Component Analysis(NLPCA) and Its Application for Chemical Process Monitoring", Industrial and Engineering Chemistry Research, 44(10), 3585-3593, (2005) https://doi.org/10.1021/ie0493107
  5. MacGregor, J. F. and Kourti, T., "Statistical Process Control of Multivariate Processes". Control Engineering Practice, 3(3), 403-414, (1995) https://doi.org/10.1016/0967-0661(95)00014-L
  6. Qin, S., "Statistical Process Monitoring: Basics and Beyond", Journal of Chemometrics, 17(8-9), 480-502, (2003) https://doi.org/10.1002/cem.800
  7. Dudzic, M., Vaculik, V. and Miletic. I., "Applications of Multivariate Statistics at Dofasco", In IEEE Industry Applications Society Advanced Process Control Applications for Industry Workshop, IEEE, 27-29. (1999)
  8. Dudzic, M., Vaculik, V. and Miletic, I., "On-Line Applications of Multivariate Statistics at Dofasco" IFAC Proceedings Volumes, 33(22), 425-430, (2000)
  9. Jeong, H., Cho, S., Kim, D., Pyun, H., Ha, D., Han, C., Kang, M., Jeong, M. and Lee, S., "A Heuristic Method of Variable Selection Based on Principal Component Analysis and Factor Analysis for Monitoring in a 300 KW MCFC Power Plant", International Journal of Hydrogen Energy, 37(15), 11394-11400, (2012) https://doi.org/10.1016/j.ijhydene.2012.04.135
  10. Lane, S., Martin, E. B., Morris, A. J. and Gower, P., "Application of Exponentially Weighted Principal Component Analysis for the Monitoring of a Polymer Film Manufacturing Process", Transactions of the Institute of Measurement and Control, 25(1), 17-35, (2003) https://doi.org/10.1191/0142331203tm071oa
  11. Garcia, M., Ruiz, M.; Colomer, J. and Melendez, J., "Multiway Principal Component Analysis and Case Base Reasoning Methodology for Abnormal Situation Detection in a Nutrient Removing SBR", In 2007 European Control Conference (ECC), IEEE, 5354-5360, (2007)
  12. Jang, Q. and Yan, X., "Monitoring Multi- Mode Plant-Wide Processes by Using Mutual Information-Based Multi-Block PCA, Joint Probability, and Bayesian Inference", Chemometrics and Intelligent Laboratory Systems, 136, 121-137, (2014) https://doi.org/10.1016/j.chemolab.2014.05.012
  13. Westerhuis, J. A., Kourti, T. and MacGregor, J. F., "Analysis of Multiblock and Hierarchical PCA and PLS Models", Journal of Chemometrics, 12(5), 301-321, (1998) https://doi.org/10.1002/(SICI)1099-128X(199809/10)12:5<301::AID-CEM515>3.0.CO;2-S
  14. Kim K.J., "Modeling and Simulation of a Fractionation Process in LNG Plant", Master thesis, Seoul National University, Seoul, Korea, (2011)
  15. Bahadori, A., Natural Gas Processing: Technology and Engineering Design, Elsevier, 2014