DOI QR코드

DOI QR Code

주성분분석(PCA) 기법에 기반한 CNG 충전소의 이상감지 모니터링 및 진단 시스템 연구

A Study on Fault Detection Monitoring and Diagnosis System of CNG Stations based on Principal Component Analysis(PCA)

  • Lee, Kijun (Korea Institute of Fire Industry & Technology) ;
  • Lee, Bong Woo (Korea Institute of Fire Industry & Technology) ;
  • Choi, Dong-Hwang (Korea Institute of Fire Industry & Technology) ;
  • Kim, Tae-Ok (Department of Chemical Engineering, Myongji University) ;
  • Shin, Dongil (Department of Chemical Engineering, Myongji University)
  • 투고 : 2014.05.11
  • 심사 : 2014.06.23
  • 발행 : 2014.06.30

초록

본 연구에서는 비정상상태 운전을 기본으로 하는 CNG 충전소를 대상으로 다변량 통계분석방법 중의 하나인 다차원의 대용량 데이터 처리에 적합한 주성분분석(PCA) 기법을 사용하여 실시간 이상감지 및 진단이 가능한 모니터링 시스템을 제안하였다. CNG 충전소로부터 매초 간격으로 수집되는 7개의 압력센서 데이터와 5개의 온도센서 데이터의 주요 경향을 나타내는 변수들의 조합으로 주성분이라 불리는 새로운 특성변수들을 산출하고, 분산의 분포를 통해 특성변수의 계산으로부터 모델을 구축하였다. 모니터링은 구축된 모델을 통해 운전 중의 실시간 데이터를 반영하여 진행된다. 시스템 검증 및 정확성을 개선하기 위해 모니터링 테스트를 수행한 결과, 정상상태의 모든 데이터를 정상으로 판단하였고, 이상 데이터의 성공적인 검출 시 관련 변수를 추적하여 비정상 원인을 찾아낼 수 있었다.

In this study, we suggest a system to build the monitoring model for compressed natural gas (CNG) stations, operated in only non-stationary modes, and perform the real-time monitoring and the abnormality diagnosis using principal component analysis (PCA) that is suitable for processing large amounts of multi-dimensional data among multivariate statistical analysis methods. We build the model by the calculation of the new characteristic variables, called as the major components, finding the factors representing the trend of process operation, or a combination of variables among 7 pressure sensor data and 5 temperature sensor data collected from a CNG station at every second. The real-time monitoring is performed reflecting the data of process operation measured in real-time against the built model. As a result of conducting the test of monitoring in order to improve the accuracy of the system and verification, all data in the normal operation were distinguished as normal. The cause of abnormality could be refined, when abnormality was detected successfully, by tracking the variables out of the score plot.

키워드

참고문헌

  1. Himmelblau, D. M., Fault Detection and Diagnosis in Chemical and Petrochemical Processes, Elsevier, (1978)
  2. Kourti, T. and MacGregor, J. F., "Process Analysis, Monitoring and Diagnosis Using Multivariate Projection Methods", Chemometrics and Intelligent Laboratory System, 28(1), 3-21, (1995) https://doi.org/10.1016/0169-7439(95)80036-9
  3. Eastment, H. T. and Krzanowski, W. J., "Cross- Validatory Choice of the Number of Components from a Principal Component Analysis", Technometrics, 24(2), 73-77, (1982) https://doi.org/10.1080/00401706.1982.10487712
  4. Wise, B. M., PLS_Toolbox 3.5 Manual, Eigenvector Research, (2004)
  5. Wise, B. M. and Gallagher, N. B., "The Process Chemometrics Approach to Process Monitoring and Fault Detection", J. Process Control, 6(6), 329-348, (1996) https://doi.org/10.1016/0959-1524(96)00009-1
  6. Yoo, C. K., Choi, S. W., and Lee, I. B., "Recent Research Trends of Process Monitoring Technology: State-of-the Art", Korean J. Chem. Eng., 46(2), 233-247, (2008)
  7. Yang, J. M., Kim, B. S., Yong, J. W., Ko, B. S., Lee, D. H., and Ko, J. W., "A Study on Safety and Operational Management System for CNG Filling Stations", Journal of the Korean Institute of Gas, 15(6), 8-13, (2011) https://doi.org/10.7842/kigas.2011.15.6.008
  8. Lee, H. S., Lee, D. H., Yang, J. M., and Ko, J. W., "A Study on Application of USN in CNG Station", Journal of the Korean Institute of Gas, 15(4), 56-61, (2011) https://doi.org/10.7842/kigas.2011.15.4.056
  9. Hyosung Corporation, CNG compressor package manual, System Ver. 1.0
  10. Manabu, K., Shinji, H., and Iori, H., "A New Multivariate Statistical Process Monitoring Method Using Principal Component Analysis", Computers and Chemical Engineering, 25, 1103-1113, (2001) https://doi.org/10.1016/S0098-1354(01)00683-4
  11. Lee, Y. T., Monitoring and Diagnosis of Non- Steady Transient Process Operations, M.S. Thesis, Myongji University, (2011).
  12. Lee, K. J., Quantitative Simulation-based Safety Analysis of Energy-filling Facilities for Improved Sustainability, M.S. Thesis, Myongji University, (2014)
  13. Dan, S., Moon, D. J., Yoon, E. S., and Shin, D., "Analysis of Gas Explosion Consequence Models for the Explosion Risk Control in the New Gas Energy Filling Stations", Journal of Industrial & Engineering Chemistry Research, 52, 7265-7273, (2013) https://doi.org/10.1021/ie302511d

피인용 문헌

  1. Bioclimatic Classification of Northeast Asia Reflecting Social Factors: Development and Characterization vol.9, pp.7, 2017, https://doi.org/10.3390/su9071137
  2. Principal Component Analysis Based Method for a Fault Diagnosis Model DAMADICS Process vol.31, pp.4, 2016, https://doi.org/10.14346/JKOSOS.2016.31.4.35
  3. WILLINGNESS TO PAY FOR ACCESSIBLE ELDERLY HOUSING IN KOREA vol.24, pp.1, 2014, https://doi.org/10.3846/ijspm.2019.11095
  4. 온실 내 환경데이터 분석을 통한 파프리카 온실의 식별 vol.30, pp.1, 2014, https://doi.org/10.12791/ksbec.2021.30.1.019