The development of building fires was divided into four stages for risk assessment as fire initiation, fire alarm, fire behavior, and fire spreading based on fire engineering theory with analyses of the main risk assessment parameters of each stage. The dynamic risk assessment model was based on a Bayesian network. A sensitivity analysis was then used to evaluate the influences of key parameters on the fire risk. Two typical buildings were then used as examples to evaluate the risk at each fire stage and the overall risk. The results illustrate how the building fire risk is a dynamic process with different risk and impact parameters in each stage. The model nodes and dependencies constitute a causal network. The evaluation model can effectively combine large amounts of fire data collected by a building fire monitoring terminal using artificial intelligence analyses. This research can effectively improve building fire safety management.
[1] WEI Y Y, ZHANG J Y, WANG J. Research on building fire risk fast assessment method based on fuzzy comprehensive evaluation and SVM[J]. Procedia Engineering, 2018, 211:1141-1150.
[2] DONG X M, LI Y, PAN Y L, et al. Study on urban fire station planning based on fire risk assessment and GIS technology[J]. Procedia Engineering, 2018, 211:124-130.
[3] USFA. Information on the risk, hazard and value evaluation[R]. USA:United States Fire Administration, 1999.
[4] FERREIRA T M, VICENTE R, DA SILVA J A R M, et al. Urban fire risk:Evaluation and emergency planning[J]. Journal of Cultural Heritage, 2016, 20:739-745.
[5] XIN J, HUANG C F. Fire risk analysis of residential buildings based on scenario clusters and its application in fire risk management[J]. Fire Safety Journal, 2013, 62:72-78.
[6] LI S Y, TAO G, ZHANG L J. Fire risk assessment of high-rise buildings based on Gray-FAHP mathematical model[J]. Procedia Engineering, 2018, 211:395-402.
[7] SFPE Risk Task Group. SFPE engineering guide to application of risk assessment in fire protection design[R]. Bethesda:Society of Fire Protection Engineers, 2005.
[8] CODE L S. NFPA 101®[J]. National Fire Protection Assn, Quincy, 2009, 2(1):1-34.
[9] NIMLYAT P S, AUDU A U, OLA-ADISA E O, et al. An evaluation of fire safety measures in high-rise buildings in Nigeria[J]. Sustainable Cities and Society, 2017, 35:774-785.
[10] HANSEN N D, STEFFENSEN F B, VALKVIST M, et al. A fire risk assessment model for residential high-rises with a single stairwell[J]. Fire Safety Journal, 2018, 95:160-169.
[11] ZHANG X, LI X, MEHAFFEY J, et al. A probability-based Monte Carlo life-risk analysis model for fire emergencies[J]. Fire Safety Journal, 2017, 89:51-62.
[12] MATELLINI D B, WALL A D, JENKINSON I D, et al. Modelling dwelling fire development and occupancy escape using Bayesian network[J]. Reliability Engineering & System Safety, 2013, 114:75-91.
[13] GIACHETTI B, COUTON D, PLOURDE F. Smoke spreading analyses in a subway fire scale model[J]. Tunnelling and Underground Space Technology, 2017, 70:233-239.
[14] JIN Y L, JANG B S. Probabilistic fire risk analysis and structural safety assessment of FPSO topside module[J]. Ocean Engineering, 2015, 104:725-737.
[15] LIU F, ZHAO S Z, WENG M C, et al. Fire risk assessment for large-scale commercial buildings based on structure entropy weight method[J]. Safety Science, 2017, 94:26-40.
[16] YI G W, QIN H L. Fuzzy comprehensive evaluation of fire risk on high-rise buildings[J]. Procedia Engineering, 2011, 11:620-624.
[17] WANG Y F, QIN T, LI B, et al. Fire probability prediction of offshore platform based on dynamic Bayesian network[J]. Ocean Engineering, 2017, 145:112-123.
[18] 马德仲, 丁文飞, 刘圣楠, 等. 基于贝叶斯网络的地下空间火灾风险评估方法研究[J]. 中国安全科学学报, 2013, 23(11):151-156. MA D Z, DING W F, LIU S N, et al. Risk assessment method for fire in underground space based on Bayesian network[J]. China Safety Science Journal, 2013, 23(11):151-156. (in Chinese)
[19] 方鸿强, 陈潇, 陆守香. 基于贝叶斯网络的城市火灾风险分析研究[C]//第30届全国高校安全科学与工程学术年会暨第12届全国安全工程领域专业学位研究生教育研讨会论文集. 合肥, 中国:中国科学技术大学, 2018. FANG H Q, CHEN X, LU S X. Urban fire risk analysisbased on Bayesian networks[C]//Proceedings of the 30th National Conference on Safety Science and Engineering in Universities. Hefei, China:University of Science and Technology of China, 2018. (in Chinese)
[20] 中华人民共和国建设部. 城市消防远程监控系统技术规范:GB50440-2007[S]. 北京:中国计划出版社, 2008. Ministry of Construction of the People's Republic of China. Technical code for remote-monitoring system of urban fire protection:GB50440-2007[S]. Beijing:China Planning Publishing House, 2008. (in Chinese)
[21] 虞利强, 杨琦, 黄鹏, 等. 基于物联网技术的消防给水监测系统构建[J]. 消防科学与技术, 2017, 36(7):971-973. YU L Q, YANG Q, HUANG P, et al. Construction of fire water supply monitoring system based on Internet of Things technology[J]. Fire Science and Technology, 2017, 36(7):971-973. (in Chinese)
[22] 范维澄, 孙金华, 陆守香, 等. 火灾风险评估方法学[M]. 北京:科学出版社, 2004. FAN W C, SUN J H, LU S X, et al. Methodology of fire risk assessment[M]. Beijing:Science Press, 2004. (in Chinese)
[23] 张连文, 郭海鹏. 贝叶斯网引论[M]. 北京:科学出版社, 2006. ZHANG L W, GUO H P. Introduction to Bayesian networks[M]. Beijing:Science Press, 2006. (in Chinese)
[24] NORSYS. Netica's help system[R/OL].(2012-12-15).[2019-05-01]. https://www.norsys.com/WebHelp/NETICA.htm.
[25] 范维澄, 王清安, 张人杰, 等. 火灾科学导论[M]. 武汉:湖北科学技术出版社, 1993. FAN W C, WANG Q A, ZHANG R J, et al. Introduction to fire science[M]. Wuhan:Hubei Science and Technology Press, 1993. (in Chinese)
[26] MATHESON J E. Using influence diagrams to value information and control[M]//OLIVER R M, SMITH J Q. Influence Diagrams, Belief Nets and Decision Analysis. New York:John Wiley & Sons, 1990:25-63.
