DOI QR코드

DOI QR Code

Evaluation on Fire Available Safe Egress Time of Commercial Buildings based on Artificial Neural Network

인공신경망 기반 상업용 건축물의 화재 피난허용시간 평가

  • 할리오나 (서울시립대학교, 건축공학과 스마트시티융합전공) ;
  • 허인욱 (서울시립대학교, 건축공학과) ;
  • 최승호 (서울시립대학교, 건축공학과) ;
  • 김재현 (서울시립대학교, 건축공학과) ;
  • 김강수 (서울시립대학교, 건축공학과 스마트시티융합전공)
  • Received : 2021.10.18
  • Accepted : 2021.11.29
  • Published : 2021.12.31

Abstract

When a fire occurs in a commercial building, the evacuation route is complicated and the direction of smoke and flame is similar to that of the egress route of occupants, resulting in many casualties. Performance-based evacuation design for buildings is essential to minimize human casualties. In order to apply the performance-based evacuation design to buildings, it requires a complex fire simulation for each building, demanding a large amount of time and manpower. In order to supplement this, it would be very useful to develop an Available Safe Egress Time (ASET) prediction model that can rationally derive the ASET without performing a fire simulation. In this study, the correlations between fire temperature with visibility and toxic gas concentration were investigated through a fire simulation on a commercial building, from which databases for the training of artificial neural networks (ANN) were created. Based on this, an ANN model that can predict the available safe egress time was developed. In order to examine whether the proposed ANN model can be applied to other commercial buildings, it was applied to another commercial building, and the proposed model was found to estimate the available safe egress time of the commercial building very accurately.

상업용 건축물에서 화재가 발생하는 경우에는 피난경로가 복잡하고 연기 및 화염의 진행방향이 재실자의 피난방향과 비슷하기 때문에 많은 인명피해가 발생하고 있다. 인명피해를 최소화하기 위해서는 건축물에 대한 성능기반 피난설계가 필수적으로 요구된다. 성능기반 피난설계를 건축물에 적용하기 위해서는 각 건축물에 대한 복잡한 화재 시뮬레이션을 필요로 하기 때문에 많은 인력과 시간이 소요된다. 이를 보완하기 위하여, 화재 시뮬레이션을 수행하지 않고도 합리적으로 피난허용시간을 도출할 수 있는 피난허용시간 예측 모델을 개발한다면 매우 유용하게 활용될 수 있을 것이다. 이 연구에서는 상업용 건축물에 대한 화재 시뮬레이션을 수행하여 온도와 가시거리, 온도와 유독가스 농도의 상관관계를 규명하였으며, 이에 대한 데이터베이스를 구축하였다. 또한, 이를 기반으로 피난허용시간을 예측할 수 있는 인공신경망(ANN) 모델을 개발하였다. 제안된 인공신경망 모델이 다른 상업용 건축물에도 적용될 수 있는지를 검토하기 위하여 다른 상업용 건축물에 대한 검증을 수행하였으며, 제안모델은 이 상업용 건축물의 화재 시 피난허용시간을 매우 우수한 정확도로 추정하는 것으로 나타났다.

Keywords

Acknowledgement

본 연구는 국토교통부 국토교통기술촉진연구사업(과제번호: 21CTAP-C163892-01)의 연구비 지원으로 수행되었으며, 이에 감사드립니다.

References

  1. Goran, S., Stojan, P., Mitja, R. K., and Marko, P. P. V. (2013), Evacuation model managed through fuzzy logic during an accident in a LNG terminal, Scientific Journals, 36(108), 131-137.
  2. Shin, D.C. (2014), Development of an Artificial Neural Networks Model for the Required Safety Egress Time of an Office Room, J. Korean Soc. Hazard Mitig, (14), 27-33. https://doi.org/10.9798/KOSHAM.2014.14.6.27
  3. Oh, H. J., Baek, S. T., Kim, W. S., and Lee, S. K. (2003), A study on the Evacuation Performance Review for the Office Buildings, T. of Korean Institute of Fire Sci. & Eng , (17), 1- 6.
  4. Park, Y. J., Sung, W. K., and Kim, H. G. (2011), Developing Fire Scenario of High-Rise Buildings, Korean Institute of Fire Science and Engineering , 262-265.
  5. Han, H. S., Hwang, C. H. (2019), Study on the Available Safe Egress Time (ASET) Considering the Input Parameters and Model Uncertainties in Fire Simulation, Fire Sci. Eng., (33), 112-120. https://doi.org/10.7731/KIFSE.2019.33.3.112
  6. Jang, J. S., Kong, I. C., and Rie, D. H. (2019), A Study of Optimal Evacuation Simulation by Artificial Intelligence Evacuation Guidance Application, Journal of the Korean Society of Safety, (28), 118-122. https://doi.org/10.14346/JKOSOS.2013.28.3.118
  7. Kim, J. H., Joo, S. Y., and Lee, J. J. (2007), An Evaluation on Evacuation Safety in Multiplex Cinema based on Fire & Evacuation Simulation, Korean Institute of architectural sustainable environment and building system , (1), 7-13.
  8. Nimlyat, P. S., Audu, A. U., Ola-Adisa, E. O., and Gwatau, D. (2017), An evaluation of the fire safety measures in high-rise buildings in Nigeria, Sust. Cities Soc., (35), 774-785. https://doi.org/10.1016/j.scs.2017.08.035
  9. Baek, E. S., Baek, G. J., Shin, H., Song, M. J., Kook, Ch., and Kim, S.W. (2010), "A study on the awareness of fire safety and evacuation guide system" J. of Korean Institute of Fire Sci. & Eng. (24), 45-53.
  10. Stankovi, G., Petelin, S., Vidmar, P., and Perkovi. M., (2018), Impact of LNG Vapor Dispersion on Evacuation Routes inside LNG Terminals, Strojniski Vestn.-J. Mech. Eng. (64), 176-184.
  11. Popescu, I., Nikitopoulos, D., Constantinou, P., and Nafornita, I. (2006), Comparison of ANN Based Models for Path Loss Prediction in Indoor Environment, IEEE Veh. Technol.
  12. Saadatseresht, M., Varshosaz, M. (2007), Visibility prediction based on artificial neural networks used in automatic network design, Photogramm. Rec., (22), 336-355. https://doi.org/10.1111/j.1477-9730.2007.00454.x
  13. Kim, D, E., Kim, Ch, B., Lee, H, J. and Kwon, Y, J., (2012) ,A Relability Analysis on FDS through Full Scaled Fire Experiment of a Sing Fire Area, 한국화재소방학회.
  14. Kim, H. Yeul., Yoo, Y. H., and Ahn, C. S. (2007), Fire Safety Assessment of Full Scale Construction according to Large Scale Fire Test and Computer Simulation Analysis, Korea Institute for Structural Maintenance and Inspection, (11), 6.
  15. Kim, J. B., Lee, J. M., and Min, S. H. (2019), Study of the Reliability of the FDS Fire Model by Verification Experiments, J. Korean Soc. Hazard Mitig, (19), No. 1, 197-203. https://doi.org/10.9798/kosham.2019.19.1.197
  16. McGrattan, K., Simo, H., Randall, M., Jason, F., Craig, W., and Kristopher, O. (2013), Fire Dynamics Simulator - User's Guide;
  17. McGrattan, K., Hostikka, S., McDermott, R., Floyd J., Weinschenk, C., and Overholt, K. (2016), Fire Dynamics Simulator, Technical Reference Guide, National Institute of Standards and Technology Special Publication 1018-1: Maryland, USA.
  18. National Institute of Standards and Technology Special Publication 1019: Maryland, USA.
  19. DiNenno, P. J. (2002), SFPE Handbook of Fire Protection Engineering, National Fire Protection Association: Massachusetts, USA.
  20. Kim, H. J., David, G. L. (2000), Heat Release Rates of Burning Items in Fires, 38th Aerospace Sciences Meeting & Exhibit .
  21. NFPA 92B, (2005), Standard for Smoke Management Systems in Malls, Atria and Large Spaces, National Fire Protection Association.
  22. Buchanan, A. H., Abu, A. K. (2001), Structural Design for Fire Safety.
  23. Russell, S., Norvig, P. (2010), Artificial Intelligence A Modern Approach.
  24. Cho, H. Ch., Lee, D. H., Ju, H. J., Kim, K. S., Kim, K. H., and Paulo, J. M. (2015), Monteiro. Remaining Service Life Estimation of Reinforced Concrete Buildings based on Fuzzy Approach, Comput. Concr. (15), 879-902. https://doi.org/10.12989/cac.2015.15.6.879
  25. Cho, H. Ch., Lee, D. H., Ju, H. J., Park, H. Ch., Kim, H. Y., and Kim, K.S. (2017), Fire Damage Assessment of Reinforced Concrete Structures Using Fuzzy Theory, Appl. Sci.-Basel, (7), 1-16.
  26. Kang, H., Cho, H. Ch., Choi, S. H., Heo, I. W., Kim, H. Y., and Kim, K. S. (2019), Estimation of Heating Temperature for Fire-Damaged Concrete Structures Using Adaptive Neuro-Fuzzy Inference System, Materials, (12), 1-17. https://doi.org/10.3390/ma12010001
  27. Goodfellow, I., Y. Bengio., A. Courville., (2016), Deep Learning: MIT press.
  28. Hagan, M. T., Menhaj, M. (1994), Training feedforward networks with the Marquardt algorithm, IEEE Trans. Neural Netw., (5).
  29. Lee, J. S., Suh, K. D. (2016), Calculation of Stability Number of Tetrapods Using Weight and Biases of ANN Model, J Korean Soc Coast Ocean Eng, (28), 277-283. https://doi.org/10.9765/KSCOE.2016.28.5.277
  30. Nielsen, R. H. (1989), Theory of the Backpropagation Neural Network, IEEE IJCNN, 1593-1605.