Random forest classifier for real-time chemical leak source tracking using fence-monitoring sensors

  • Hyunseung Kim
  • Addis Lulu Gebreselassie
  • Seungkyu Dan
  • Dongil Shin
Research papers

Abstract

Fast and reliable diagnosis of chemical leak and leak location(s) can save lives and reduce the damage from chemical accidents by enabling quick response. This paper presents a method that uses random forest (RF) classifier to track the location of chemical leak in real-time. A set of big data of leak accidents, which is needed to learn the RF classifier, is extracted by performing massive CFD simulations on a real chemical plant. The RF model is designed with optimal parameters and descriptors through parameter effect experiment. Feature ranking is also implemented to eliminate unnecessary attributes from the dataset. Using the pre-processed data, the optimal RF model achieved a test accuracy of 86.9% for the classification problem of predicting the leak location among 40-potential leak sources in the plant. Furthermore, when analyzing prediction errors by visualizing the classification boundary of RF model, most of the prediction errors are confirmed to be misclassification of adjacent leak locations. Considering the high prediction accuracy of the RF model, the RF-based leak source tracking model is expected to be effectively applied to industrial leak accidents.

Keywords

Chemical Leak Accident Source Tracking Inverse Problem Random Forest Artificial Intelligence 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    T. R. Chouhan, J. Loss Prevention in the Process Industries, 18, 205 (2004).CrossRefGoogle Scholar
  2. 2.
    E. Broughton, Environ. Health, 4, 1 (2005).CrossRefGoogle Scholar
  3. 3.
    I. Eckerman, The Bhopal saga: causes and consequences of the world's largest industrial disaster, Universities Press, Hyderabad, India (2005).Google Scholar
  4. 4.
    G. Arturson, Burns, 13, 87 (1987).CrossRefGoogle Scholar
  5. 5.
    J. Park, Y. Lee, Y. Yoon, S. Kim and I. Moon, Korean J. Chem. Eng., 28, 2110 (2011).CrossRefGoogle Scholar
  6. 6.
    H. Ishida, K. Yoshikawa and T. Moriizumi, Three-dimensional gas-plume tracking using gas sensors and ultrasonic anemometer, Proceedings of IEEE Sensors 2004, Vienna, Austria (2004).CrossRefGoogle Scholar
  7. 7.
    W. J. Pisano and D. A. Lawrence, Data Dependant Motion Planning for UAV Plume Localization, Proceedings of the AIAA Guidance, Navigation and Control Conference, Hilton Head, SC, U. S. A. (2007).CrossRefGoogle Scholar
  8. 8.
    X. Zheng and Z. Chen, J. Loss Prevention in the Process Industries, 24, 293 (2011).CrossRefGoogle Scholar
  9. 9.
    J. Cho, Placement Optimization and Reliability Analysis of Stationary and Mobile Sensors for Chemical Plant Fence Monitoring, M. S. Thesis, Myongji University, Yongin, Korea (2017).Google Scholar
  10. 10.
    L. Breiman, Machine Learning, 45(5), 5 (2001).CrossRefGoogle Scholar
  11. 11.
    F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot and E. Duchesnay, J. Machine Learning Res., 12, 2825 (2011).Google Scholar
  12. 12.
    A. Rubinsteyn, Training Random Forests in Python using the GPU, http://blog.explainmydata.com/2013/10/training-random-forests-inpython-using.html, Accessed on 15 Jul. 2017 (2013).Google Scholar

Copyright information

© Korean Institute of Chemical Engineers, Seoul, Korea 2018

Authors and Affiliations

  • Hyunseung Kim
    • 1
  • Addis Lulu Gebreselassie
    • 1
  • Seungkyu Dan
    • 2
  • Dongil Shin
    • 1
  1. 1.Department of Chemical EngineeringMyongji UniversityYongin, Gyeonggi-doKorea
  2. 2.Korean Gas CorporationAnsan, Gyeonggi-doKorea

Personalised recommendations