Fire Science and Engineering (한국화재소방학회논문지)

Korean Institute of Fire Science and Engineering (한국화재소방학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Fire Sources Analysis Using the Optical Characteristics of Smoke Particles and Neural Networks

연기입자의 광학적 특성과 신경망을 이용한 화원분석에 대한 연구

  • Received : 2014.07.28
  • Accepted : 2014.10.17
  • Published : 2014.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

The neural networks were able to be used by analyze fire source with the optical characteristics of smoke particles. The neural networks were learned the optical characteristics for three types test fire (paper, wood, flammable liquid). These test fires which were adopted in this study were also used to performance test of smoke detector according to UL268. A smoke chamber which was able to detect light extinction and scattering simultaneously was created. The optical characteristics of smoke particles were measured by the smoke chamber. And the results were used to input data for the neural networks. The neural networks distinguished the fire source accurately for paper fire, wood fire or flammable liquid fire. The neural networks distinguished accurately the combined fire source such as paper-wood fire, paper-flammable liquid fire or wood-flammable liquid fire.

신경망은 연기입자의 광학적 특징으로부터 화원을 분석할 수 있는 유용한 도구가 될 수 있다. UL268에서 연기감지기 시험에 사용되는 세 가지 화원(종이화원, 목재화원, 인화성 액체화원)들의 광학적 특징으로 신경망을 훈련시켰다. 또한, 소광과 산란을 동시에 측정할 수 있는 연기챔버를 제작하여 연기의 광학적 특징을 얻고 그 결과를 신경망에 입력하였다. 종이화원, 목재화원, 인화성 액체화원을 대상으로 한 실험에서 신경망은 화원을 정확하게 구별하였다. 또한, 종이-목재화원, 종이-인화성 액체화원, 목재-인화성 액체화원과 같은 복합화원을 대상으로 한 실험에서도 화원을 모두 구별하였다.

Keywords

References

  1. National Emergency Management Agency, "Safety Guides for the Automatic Fire Alarm System (NFSC 203)", Notification No. 2012-91 (2012).
  2. S. W. Jee, C. H. Lee, S. K. Kim, J. J. Lee and P. Y. Kim, "Development of a Traceable Fire Alarm System Basedon the Conventional Fire Alarm System", Fire Technology (DOI:10.1007/s10694-012-0299-0), pp.1-18 (2012).
  3. R. W. Bukowski and Wayne D. Moore, "Fire Alarm Signaling Systems 3 Edition", NFPA Inc., pp. 84-176 (2003).
  4. G. T. Jung, "A Study on Design of a Fire Smoke Detector with Auto-trning Sensitivity for Prevention of False Alarm", MS Thesis, Univ. of Seoul, Korea (2003).
  5. F. Derbel, "Performance Improvement of Fire Detectors by Means of Gas Sensors and Neural Networks", Vol. 39, Issues 5, pp. 383-398 (2004). https://doi.org/10.1016/j.firesaf.2004.03.001
  6. R. Siebel, "Test of Fire Detection Algorithms Using Artificially Generated Events", Fire Safety Journal, Vol. 41, Issues 4, pp. 258-265 (2006). https://doi.org/10.1016/j.firesaf.2006.01.004
  7. S. W. Jee, S. K. Kim, J. J. Lee, P. Y. Kim and C. H. Lee, "Development of the Low Power Stand-Alone Smoke and Heat Detector for the Reliability Improvement", Journal of Korean Institute of Fire Science & Engineering, Vol. 26, No. 1, pp. 62-68 (2011).
  8. M. Loepfe, P. Ryser, C. Tompkin and D. Wieser, "Optical Properties of Fire and Non-fire Aerosols", Fire Safety Journal, Vol. 29, Issues 2-3, pp. 185-194 (1997). https://doi.org/10.1016/S0379-7112(96)00048-3
  9. S. W. Jee and J. H. Lee, "Optical Properties for Smoke Particles of Fire Sources According to UL 268", Journal of Korean Institute of Fire Science & Engineering, Vol. 28, No. 2, pp. 1-5 (2014).
  10. William C. Hinds, "Aerosol Technology", Translation of Korean Language, ShinKwang MunHwa Publishing Co., pp. 379-412 (1995).
  11. R. W. Bukowski, "Smoke Measurements in Large- and Small-Scale Fire Testing - Part I", Fire Technology, Vol. 15, Issue 3, pp. 173-179 (1979). https://doi.org/10.1007/BF01983195
  12. Bart Kosko, "Neural Networks and Fuzzy Systems", Prentice-Hall, Englewood Cliffs, pp. 38-261 (1992).