主管：中华人民共和国应急管理部
主办：应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU
消防科学与技术

消防科学与技术 ›› 2024, Vol. 43 ›› Issue (1): 56-64.

• • 上一篇    下一篇

基于BP神经网络及烟尘沉积特征的单隔间内起火点预测

牛甜辉1,2, 耿佃桥1,2, 苑轶2, 董辉2   

  1. （1. 东北大学 材料电磁过程研究教育部重点实验室，辽宁 沈阳 110819；2. 东北大学 冶金学院，辽宁 沈阳 110819）
  • 出版日期:2024-01-15 发布日期:2024-01-15
  • 作者简介:牛甜辉（1997- ），男，东北大学冶金学院硕士研究生，主要从事火灾烟尘沉积数值模拟等方面的研究，辽宁省沈阳市和平区文化路3号巷11号东北大学，110819。
  • 基金资助:
    基金项目：沈阳市科技计划项目（21-108-9-16）；应急管理部消防救援局科技计划重点项目(2021XFZD13)

Fire origin prediction in single compartment based on BP neural network and soot deposition characteristics

Niu Tianhui1,2, Geng Dianqiao1,2, Yuan Yi2, Dong Hui2   

  1. (1. The Key Laboratory of Electromagnetic Processing of Materials, Ministry of Education, Northeastern University,Liaoning Shenyang 110819, China; 2. School of Metallurgy, Northeastern University, Liaoning Shenyang 110819, China)
  • Online:2024-01-15 Published:2024-01-15

摘要： 为帮助火灾调查人员更准确、高效地判定起火点，提出了一种基于BP神经网络的起火点预测模型。通过对单隔间火灾烟尘沉积进行数值模拟，构建了59种不同起火点场景下壁面烟尘沉积数据库，并分析了典型起火点场景下的壁面烟尘沉积特征，发现起火点位置与壁面沉积总量及最大浓度平均值之间具有强关联性。选取上述两个参数作为输入，起火点位置作为输出进行神经网络训练，并利用新数据进行预测。结果表明起火点位置预测值的最大绝对误差为0.65 m，最小绝对误差为0.03 m，平均绝对误差为0.37 m，说明本文提出的模型能以较高精度预测起火点位置，是一种较好的火灾调查替代方法。

关键词: BP神经网络, 烟尘沉积, 数值模拟, 单隔间, 起火点

Abstract: In order to help fire investigators to determine the fire origin more accurately and efficiently, a BP neural network-based fire point prediction model is proposed in this paper. The soot deposition database of wall soot deposition under 59 different fire origin scenarios is constructed by numerical simulation of single compartment fire, and the wall soot deposition characteristics under representative fire origin scenarios are analyzed, which indicates a strong correlation of the fire origin location with the mass of wall deposition and the average value of the maximum concentration. The above two parameters are selected as input, and the fire origin location is used as output for network training. And the new data is used for prediction. The results show that the maximum absolute error of the predicted value is 0.65 m, the minimum absolute error is 0.03 m, and the average absolute error is 0.37 m, indicating that the proposed model can achieve the prediction of fire source location with relatively high accuracy and is a good alternative method for fire investigation.

Key words: BP neural network, soot deposition, numerical simulation, single compartment, fire origin