|本期目录/Table of Contents|

[1]李伟,胡淋翔,杨满江,等.基于人工神经网络的烟气及温度实时预测模型*[J].中国安全生产科学技术,2023,19(3):5-12.[doi:10.11731/j.issn.1673-193x.2023.03.001]
　LI Wei,HU Linxiang,YANG Manjiang,et al.Real-time prediction model of smoke and temperature based on artificial neural network[J].Journal of Safety Science and Technology,2023,19(3):5-12.[doi:10.11731/j.issn.1673-193x.2023.03.001]
点击复制

基于人工神经网络的烟气及温度实时预测模型*()

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
19
期数:
2023年3期
页码:
5-12
栏目:
学术论著
出版日期:
2023-03-31

文章信息/Info

Title:
Real-time prediction model of smoke and temperature based on artificial neural network
文章编号:
1673-193X(2023)-03-0005-08
作者:
李伟; 胡淋翔; 杨满江; 刘晓平
（1.合肥工业大学 土木与水利工程学院，安徽 合肥 230041；
2.中国舰船研究设计中心，湖北 武汉 430070)
Author(s):
LI Wei;  HU Linxiang;  YANG Manjiang;  LIU Xiaoping
(1.College of Civil Engineering,Hefei University of Technology,Hefei Anhui 230041,China;
2.China Ship Development and Design Center,Wuhan Hubei 430070,China)
关键词:
消防安全; 转置卷积神经网络(TCNN); 数值模拟; 烟气扩散; 温度分布; 实时预测
Keywords:
fire safety;  transposed convolution neural network (TCNN);  numerical simulation;  smoke diffusion;  temperature distribution;  real-time prediction
分类号:
X932
DOI:
10.11731/j.issn.1673-193x.2023.03.001
文献标志码:
A
摘要:
为监测建筑火灾事故区域的危险程度，实现更加安全、高效的火灾应急救援，以通廊式建筑为研究对象，基于转置卷积神经网络及数值模拟方法开发1种可实时预测走廊位置处烟气扩散和温度分布的神经网络模型。首先，依托Python建立包含全连接、转置卷积、反池化等在内的19层神经网络模型的整体架构；其次，建立包含99个火灾场景，共7 920组图像数据的火场信息数据库用于模型训练；最后，使用测试集对模型进行可靠性验证。研究结果表明：烟气（温度）预测模型在不同火灾场景下的预测精度达到95%，训练完成后模型的预测时间一般为1~2 s。研究结果可为应急策略的快速制定提供数据参考。
Abstract:
In order to monitor the degree of danger in the area of building fire accidents and realize the safer and more efficient fire emergency rescue,taking the gallery building as the research object,a neural network model for the real-time prediction of smoke diffusion and temperature distribution at the corridor location was developed based on the transposed convolution neural network (TCNN) and numerical simulation method.Firstly,the overall architecture of a 19-layer neural network model including full connection,transposed convolution and inverse pooling was established based on Python.Secondly,a fire scene information database containing 99 fire scenarios and a total of 7 920 sets of image data was established for model training.Finally,the reliability of the model was verified by an independent test set.The results showed that the prediction accuracy of smoke prediction model and temperature prediction model reached 95% in different fire scenes,and the prediction time of the model after training was generally 1~2 seconds,which can provide data reference for the rapid formulation of emergency strategies.

参考文献/References:

［1］肖方.近10年全国发生居住场所火灾132.4万起造成11 634人遇难6 738人受伤直接财产损失77.7亿元［J］.中国消防,2022(2):10-11.
［2］FRIZZI S,KAABI R,BOUCHOUICHA M,et al.Convolutional neural network for video fire and smoke detection ［C］//IECON 2016-42nd Annual Conference of the IEEE Industrial Electronics Society.Florence,IEEE：2016:877-882.
［3］LI P，ZHAO W D.Image fire detection algorithms based on convolutional neural networks ［J］.Case Studies in Thermal Engineering,2020,19:100625.
［4］LI M J，JIANG Y，WU Z，et al.Real-time prediction of smoke spread affected by multiple factors in subway tunnel using CAERES-DNN model ［J］.Fire Technology,2021,57(4):2025-2059.
［5］HODGES J L,LATTIMER B Y,LUXBACHER K D.Compartment fire predictions using transpose convolutional neural networks［J］.Fire Safety Journal,2019,108:102854.
［6］SU L C,WU X Q,ZHANG X N,et al.Smart performance-based design for building fire safety:prediction of smoke motion via AI［J］.Journal of Building Engineering,2021,43:102529.
［7］颜峻,孟燕华,左哲.基于Bayesian网络的建筑火灾疏散条件安全性评估方法［J］.中国安全生产科学技术,2020,16(12):116-121.YAN Jun,MENG Yanhua,ZUO Zhe.Study on assessment method for safety of evacuation conditions in building fire based on Bayesian network［J］.Journal of Safety Science and Technology,2020,16(12):116-121.
［8］王悦,薛伟.基于BP神经网络的东北贮木场火灾危险等级评定［J］.中国安全生产科学技术,2013,9(2):173-176.WANG Yue，XUE Wei.Evaluation of fire danger rating of northeast lumberyard based on BP neural network［J］.Journal of Safety Science and Technology,2013,9(2):173-176.
［9］张健飞,蔡东成.基于多尺度卷积神经网络的结构损伤识别研究［J］.地震工程与工程振动,2022,42(1):132-142.ZHANG Jianfei,CAI Dongcheng.Research on structural damage identification based on multi-scale convolutional neural networks［J］.Earthquake Engineering and Engineering Dynamics,2022,42(1):132-142.
［10］QASSIM H,VERMA A,FEINZIMER D.Compressed residual-VGG16 CNN model for big data places image recognition［C］//2018 IEEE 8th annual computing and communication workshop and conference (CCWC).Las Vegas,NV：IEEE,2018:169-175.
［11］HUA J,WANG J,KUMAR K.Development of a hybrid field and zone model for fire smoke propagation simulation in buildings［J］.Fire Safety Journal,2005,40(2):99-119.
［12］范维澄,火灾学简明教程［M］.合肥:中国科学技术大学出版社,1995.
［13］马砺,刘顺,李超华,等.巷道火灾密闭过程中烟气温度及流动特性研究［J］.中国安全生产科学技术,2021,17(2):46-52.MA Li,LIU Shun,LI Chaohua,et al.Study on temperature and flow characteristics of smoke during sealing process of roadway fire［J］.Journal of Safety Science and Technology,2021,17(2):46-52.
［14］HADJISOPHOCLEOUS G,JIA Q.Comparison of FDS prediction of smoke movement in a 10-storey building with experimental data［J］.Fire Technology,2009,45(2):163-177.
［15］SHEN T S,HUANG Y H,CHEN S W.Using fire dynamic simulation (FDS) to reconstruct an arson fire scene［J］.Building and Environment,2008,43(6):1036-1045.
［16］WU X Q,ZHANG X M,HUANG X Y,et al.A real-time forecast of tunnel fire based on numerical database and artificial intelligence［J］.Building Simulation,2022,15:511-524.
［17］WANG Z L,ZHANG T H,WU X Q,et al.Predicting transient building fire based on external smoke images and deep learning［J］.Journal of Building Engineering,2022,47:103823.
［18］FRANCOIS C.Python深度学习［M］.张亮，译.北京：人民邮电出版社，2018.

相似文献/References:

[1]郝爱玲,王宗存,石宗维,等.大空间内封闭喷漆作业的火灾危险性及消防安全对策研究[J].中国安全生产科学技术,2011,7(5):72.
　HAO Ai-ling,Wang Zong-cun,SHI Zong-wei,et al.Research on fire hazard?analysis and fire safety measures of a large paint shop with enclosed paint-spraying operation[J].Journal of Safety Science and Technology,2011,7(3):72.
[2]李清江.建筑工地消防安全问题分析与对策[J].中国安全生产科学技术,2012,8(7):229.
　LI Qing jiang.Construction site fire safety analysis and countermeasures[J].Journal of Safety Science and Technology,2012,8(3):229.
[3]陈海涛,仇九子,杨〓鹏,等.一种高层建筑楼、电梯疏散模型的模拟研究[J].中国安全生产科学技术,2012,8(10):48.
　CHEN Hai tao,QIU Jiu zi,YANG Peng,et al.Simulation study on the novel stairs and elevator evacuation model in the highrise building[J].Journal of Safety Science and Technology,2012,8(3):48.
[4]张立红,陈海涛,杨鹏,等.心理迫切因素对行人疏散动力学的影响研究[J].中国安全生产科学技术,2013,9(6):79.[doi:10.11731/j.issn.1673-193x.2013.06.015]
　ZHANG Li hong,CHEN Hai tao,YANG Peng,et al.Study on influence of psychological urgency parameter on pedestrian evacuation dynamics[J].Journal of Safety Science and Technology,2013,9(3):79.[doi:10.11731/j.issn.1673-193x.2013.06.015]
[5]谭伟峰.城市公共消防安全风险预警评价体系构建研究[J].中国安全生产科学技术,2014,10(5):120.[doi:10.11731/j.issn.1673-193x.2014.05.021]
　TAN Weifeng.Study on construction of early-warning and evaluation system for public fire safety risk in city[J].Journal of Safety Science and Technology,2014,10(3):120.[doi:10.11731/j.issn.1673-193x.2014.05.021]
[6]赵青华,杨匀波.贵州黔南州高层建筑消防安全调研与防火策略[J].中国安全生产科学技术,2011,7(7):125.
　ZHAO qing-hua YANG yun-bo.Study of fire safety and fire prevention strategy in high-rise buildings which in Guizhou Qiannan[J].Journal of Safety Science and Technology,2011,7(3):125.
[7]张立红,王策源,杨光,等.基于行人疏散模型的建筑出口设计优化研究[J].中国安全生产科学技术,2014,10(10):100.[doi:10.11731/j.issn.1673-193x.2014.10.017]
　ZHANG Li-hong,WANG Ce-yuan,YANG Guang,et al.Study on optimization of building exits design based on pedestrian evacuation model[J].Journal of Safety Science and Technology,2014,10(3):100.[doi:10.11731/j.issn.1673-193x.2014.10.017]
[8]刘勇,徐志胜,赵望达.商业综合体人员密度调查与分析[J].中国安全生产科学技术,2015,11(5):175.[doi:10.11731/j.issn.1673-193x.2015.05.028]
　LIU Yong,XU Zhi-sheng,ZHAO Wang-da.Investigation and analysis on personnel density in commercial complex[J].Journal of Safety Science and Technology,2015,11(3):175.[doi:10.11731/j.issn.1673-193x.2015.05.028]
[9]王雅妮,叶宽,王云鹏,等.受限空间变压器火灾燃烧特性实验研究*[J].中国安全生产科学技术,2025,21(9):117.[doi:10.11731/j.issn.1673-193x.2025.09.015]
　WANG Yani,YE Kuan,WANG Yunpeng,et al.Experimental study on combustion characteristics of transformer fires in confined spaces[J].Journal of Safety Science and Technology,2025,21(3):117.[doi:10.11731/j.issn.1673-193x.2025.09.015]
[10]黄鹏,房志明,朱曼,等.基于SSD网络的电梯内电动自行车检测研究*[J].中国安全生产科学技术,2023,19(2):167.[doi:10.11731/j.issn.1673-193x.2023.02.023]
　HUANG Peng,FANG Zhiming,ZHU Man,et al.Research on detection of electric bicycles in elevator based on SSD network[J].Journal of Safety Science and Technology,2023,19(3):167.[doi:10.11731/j.issn.1673-193x.2023.02.023]

备注/Memo

备注/Memo:
收稿日期： 2022-09-22
* 基金项目： 国家重点研发计划项目（2018YFC0810600）
作者简介： 李伟，硕士研究生，主要研究方向为神经网络在建筑火灾方面的应用。
通信作者： 刘晓平，博士，教授，主要研究方向为建筑环境、污染物扩散及后果评估和建筑火灾等。
更新日期/Last Update: 2023-04-12