Korean Chemical Engineering Research

The Korean Institute of Chemical Engineers (한국화학공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Predictive Models based on the Machine Learning for Evaluating the Extent of Hazardous Zone of Explosive Gases

기계학습 기반의 가스폭발위험범위 예측모델에 관한 연구

  • Jung, Yong Jae (Department of Safety Engineering, Pukyong National University) ;
  • Lee, Chang Jun (Department of Safety Engineering, Pukyong National University)
  • 정용재 (부경대학교 안전공학과) ;
  • 이창준 (부경대학교 안전공학과)
  • Received : 2020.02.10
  • Accepted : 2020.03.23
  • Published : 2020.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, predictive models based on machine learning for evaluating the extent of hazardous zone of explosive gases are developed. They are able to provide important guidelines for installing the explosion proof apparatus. 1,200 research data sets including 12 combustible gases and their extents of hazardous zone are generated to train predictive models. The extent of hazardous zone is set to an output variable and 12 variables affecting an output are set as input variables. Multiple linear regression, principal component regression, and artificial neural network are employed to train predictive models. Mean absolute percentage errors of multiple linear regression, principal component regression, and artificial neural network are 44.2%, 49.3%, and 5.7% and root mean square errors are 1.389m, 1.602m, and 0.203 m respectively. Therefore, it can be concluded that the artificial neural network shows the best performance. This model can be easily used to evaluate the extent of hazardous zone for explosive gases.

본 연구에서는 폭발위험장소의 방폭설비 설치를 위해 필요한 가스폭발위험범위 예측모델 개발을 수행하였다. 이를 위해 12개의 가연성가스에 대한 1,200개의 폭발위험범위 데이터를 생성하였다. 가스폭발위험범위를 출력변수로 설정하였고 데이터 생성과정에서 필요한 12개의 변수를 입력변수로 설정하였다. 다중 회귀, 주성분 회귀, 인공신경망 기법을 이용해 예측모델을 개발하였다. 각각 모델의 예측 성능을 비교한 결과, 평균절대퍼센트오차(MAPE)는 각각 44.2%, 49.3%, 5.7%이고 평균제곱근오차(RMSE)는 1.389 m, 1.602 m, 0.203 m로 나타났다. 결과를 통해 인공신경망이 가장 우수한 성능을 보여주었고 가스폭발위험범위 예측을 위한 최적 모델이라는 것을 확인하였다.

Keywords

References

  1. Lee, H. S. and Yim, J. P., "A Study on Prevention Measure Establishment Through Cause Analysis of Chemical Accidents," Journal of the Korean Society of Safety, 32(3), 21-27(2017). https://doi.org/10.14346/JKOSOS.2017.32.3.21
  2. Lee, K. O., Park, J. Y. and Lee, C. J., "Evaluation of a Mitigation System for Leakage Accidents Using Mathematical Modeling," The Korean Institute of Chemical Engineers, 35(2), 348-354(2018).
  3. Crowl, D. A. and Louvar, J. F., Chemical Safety Process : Fundamentals with applications, 3rd ed., Prentice Hall, USA(2011).
  4. Byun, J. H., Lee, S. J. and Jeong, K, H., "A Study on the Technical and Institutional Management Plan to Maintain Explosion Proof Equipment and Apparatus," 2019-OSHRI-1648, Occupational Safety &Health Research Institute, Korea(2019).
  5. KS C IEC 60079-10-1 : "Explosive atmospheres Part 10-1 : Classification of Areas-Explosive Gas Atmospheres," Korean Industrial Standards, Korea(2017).
  6. Jung, Y. J. and Lee, C. J., "A Study on Gas Explosion Hazardous Ranges for International Electrotechnical Commission Technical Standards," Journal of the Korean Society of Safety, 33(3), 39-45 (2018). https://doi.org/10.14346/JKOSOS.2018.33.3.39
  7. Choi, J. Y., "An Analysis on the Main Amendment of Hazardous Area Classification in Korea and a Study on Its Limitation," Korean Journal of Hazardous Materials, 6(1), 8-17(2018). https://doi.org/10.31333/kihm.2018.6.1.8
  8. Bozek, A., "Application of IEC 60079-10-1 Edition 2.0 For Hazardous Area Classification," Petroleum and Chemical Industry Technical Conference, September, Calgary, AB(2017).
  9. Souza, A. O. and Luiz, A. M., "CFD Predictions for Hazardous Area Classification," Chinese Journal of Chemical Engineering, 27(1), 21-31(2019). https://doi.org/10.1016/j.cjche.2018.06.002
  10. Miranda, J. T. and Camacho, E. M., "Comparative Study of the Methodologies Based on Standard UNE 60079/10/1 and Computational Fluid Dynamics (CFD) to Determine Zonal Reach of Gas-generated Atex Explosive Atmospheres," Journal of Loss Prevention in the Process Industries, 26, 839-850(2013). https://doi.org/10.1016/j.jlp.2013.02.015
  11. Shrivastava, V. and Mohan, G., "An Innovative Approach to Hazardous Area Classification-Three Dimentional (3D) Modelling of Hazardous Area," Petroleum and Chemical Industry Technical Conference, September, Philadelphia(2016).
  12. Jung, Y. J. and Lee, C. J., "A Study on the Estimation Model of Liquid Evaporation Rate for Classification of Flammable Liquid Explosion Hazardous Area," Journal of the Korean Society of Safety, 33(4), 21-29(2018). https://doi.org/10.14346/JKOSOS.2018.33.4.21
  13. Zohdirad, H., Ebadi, T. and Givehchi, S., "Predictive Modeling of Hazard Radius for Refinery Predictive Modeling of Hazard Radius for Refinery," International Journal of Hydrogen Energy, 41(26), 11491-11496(2016). https://doi.org/10.1016/j.ijhydene.2016.04.005
  14. Cho, K. W., Kang, C. G. and Oh, C. H., "Conformity Assessment of Machine Learning Algorithm for Particulate Matter Prediction," Journal of the Korea Institute of Information and Communication Engineering, 23(1), 20-26(2019). https://doi.org/10.6109/JKIICE.2019.23.1.20
  15. Park, J. Y. and Lee, C. J., "Principal Component Analysis Based Method for Effective Fault Diagnosis," Journal of the Korean Society of Safety, 29(4), 73-77(2014). https://doi.org/10.14346/JKOSOS.2014.29.4.073
  16. Lee, C. J., Song, S. O. and Yoon, E. S., "The Monitoring of Chemical Process using The Support Vector Machine," Korean Chemical Engineering Research, 42(5), 538-544(2004).
  17. Park, J. H., Shin, S. W. and Kim, S. Y., "Traffic Volume Dependent Displacement Estimation Model for Gwangan Bridge Using Monitoring Big Data," Journal of the Korean Society of Civil Engineers, 38(2), 183-191(2018). https://doi.org/10.12652/Ksce.2018.38.2.0183
  18. Korea Petrochemical Industry Association, Petrochemical Handbook, Seoul(2019).
  19. Ministry of Environment, Chemical Statistics Survey, Sejong(2014).
  20. http://www.kgs.or.kr/kgsmain/SearchAction.do?method=mat1List&windowId=0305000101.html.
  21. https://cameochemicals.noaa.gov/search/simple.html.
  22. Yang, W. S. and Park, H. M., "Improving Polynomial Regression Using Principal Components Regression With the Example of the Numerical Inversion of Probability Generating Function," Journal of the Korea Contents Association, 15(1), 475-481(2015). https://doi.org/10.5392/JKCA.2015.15.01.475
  23. Lee, T. R., Koo, J. Y., Park, H. J., Lee, K. H. and Choi, D. W., Data mining, Korea National Open University, Seoul(2004).
  24. Park, J. H., Shin, S. W., and Kim, S. Y., "Modeling on Expansion Behavior of Gwangan Bridge using Machine Learning Techniques and Structural Monitoring Data," Journal of the Korean Society of Safety, 33(6), 42-49(2018). https://doi.org/10.14346/JKOSOS.2018.33.6.42
  25. Oh, C. S., Artificial Neural Networks for Deep Learnig, Naeha Inc., Korea(2016).
  26. Kwon, S. H., Lee, J. W. and Chung, G. H., "Snow Damages Estimation using Artificial Neural Network and Multiple Regression Analysis," Journal of the Korean Society of Hazard Mitigation, 17(2), 315-325(2017). https://doi.org/10.9798/KOSHAM.2017.17.2.315
  27. Kaiser, H. F., "An Index of Factorial Simplicity," Psychometrika, 39(1), 31-36(1974). https://doi.org/10.1007/BF02291575
  28. Kaiser, H. F., "The Application of Electronic Computers to Factor Analysis," Educational and Psychological Measurement, 20, 141-151(1960). https://doi.org/10.1177/001316446002000116
  29. Jolliffe, I. T., "Discarding Variables in a Principal Component Analysis. I: Artificial Data," Journal of the Royal Statistical Society Series C, Royal Statistical Society, 21(2), 160-173(1972).
  30. Catell, R. R., "The Scree Test for Number of Factors," Multivariate Behavioral Research, 1, 245-276(1966). https://doi.org/10.1207/s15327906mbr0102_10
  31. Hornik, K., "Multilayer Feedforward Networks are Universal Approximators," Neural Networks, 2, 359-366(1989). https://doi.org/10.1016/0893-6080(89)90020-8
  32. Cybenko, G., "Approximation by Superpositions of a Sigmoidal Function," Mathmatics of Control, Signals and Systems, 2, 303-314(1989). https://doi.org/10.1007/BF02551274
  33. Stephen, M., Machine Learning:An Algorithmic Perspective, 2nd ed., Jpub Inc., Korea(2018).
  34. Bengio, Y., "Practical Recommendations for Gradient-Based Training of Deep Architectures," Neural Networks:Tricks of the Trade 2nd ed., 437-478, Springer, Heidelberg(2012).
  35. Berry, M. J. A. and Linoff, G., Data mining technique, Wiley, New York(1997).
  36. Oh, I. S., Machine Learning, Hanbit Academy Inc., Seoul(2017).