[1]刘罡,黄丽达,袁宏永,等.基于贝叶斯估计的多探测器火警判定方法研究*[J].中国安全生产科学技术,2021,17(1):12-18.[doi:10.11731/j.issn.1673-193x.2021.01.002]
LIU Gang,HUANG Lida,YUAN Hongyong,et al.Research on multi-detector fire alarm judgment method based on Bayesian estimation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(1):12-18.[doi:10.11731/j.issn.1673-193x.2021.01.002]
点击复制
基于贝叶斯估计的多探测器火警判定方法研究*
LIU Gang,HUANG Lida,YUAN Hongyong,et al.Research on multi-detector fire alarm judgment method based on Bayesian estimation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(1):12-18.[doi:10.11731/j.issn.1673-193x.2021.01.002]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 17
- 期数:
- 2021年1期
- 页码:
- 12-18
- 栏目:
- 特邀专栏
- 出版日期:
- 2021-01-31
文章信息/Info
- Title:
- Research on multi-detector fire alarm judgment method based on Bayesian estimation
- 文章编号:
- 1673-193X(2021)-01-0012-07
- Keywords:
- fire detector; Bayesian estimation; fire recognition; fire false alarm rate; multi-detector system
- 分类号:
- X932
- 文献标志码:
- A
- 摘要:
- 为应对感烟探测器的大量误报对消防应急响应带来的挑战，考虑目前以感烟探测器为主的火警设施误报率高且短期内难以全部更换的特点，提出基于贝叶斯估计的多探测器火警判定方法，通过多个探测器的报警时间间隔计算火源位置的后验概率分布，并提出火警真实度概念，为火警判定提供依据。结果表明：使用多探测器耦合模型时每增加1个探测器可将误报率降低约4个数量级，该方法在探测器正常、部分失效、误报的情景下均能有效判别火警。
- Abstract:
- In order to cope with the challenges caused by the large number of false alarms of smoke detectors to the fire emergency response,considering the high false alarm rate of current fire alarm facilities dominated by smoke detectors and the difficulty of all replacement in a short period of time,a multi-detector fire alarm judgment method based on the Bayesian Estimation was proposed.The posterior probability distribution of the fire source location was calculated through the alarm time intervals of multiple detectors,and the concept of fire alarm authenticity was proposed to provide a basis for the fire alarm judgment.The results showed that when the multi-detector coupling model was used,each additional detector could reduce the false alarm rate by about four orders of magnitude,and this method could effectively distinguish the fire alarms under the normal,partial failure and false alarm scenarios of detectors.
参考文献/References:
［1］陈涛,袁宏永,范维澄.火灾探测技术研究的展望［J］.火灾科学,2001(2):108-112.CHEN Tao,YUAN Hongyong,FAN Weicheng.The developing fire detection technology ［J］.Fire Safety Science,2001(2):108-112.
［2］许行宾,缪小平,江丰,等.火灾自动报警系统误报原因分析及对策［J］.洁净与空调技术,2011(3):28-31.XU Xingbin,MIU Xiaoping,JIANG Feng,et al.The reason analysis and measures of the false alarms of the automatic fire alarm system ［J］.Contamination Control & Air-conditioning Technology,2011(3):28-31.
［3］CARTER C F.Fire detector sensors:US10/071589 ［P］.2002-08-15.
［4］ZHANG J W,LI M B,LI W,et al.TDLAS based early-stage forest fire detection system ［C］//PIERS 2014 in Guangzhou Proceedings.Guangzhou:The Electromagnetics Academy,2014:171-175.
［5］LIU B F,ZHANG Y X,GAN F C,et al.Designintelligent multi-sensor fire monitoring based on DSP ［C］//Proceedings of 2007 8th International Conference on Electronic Measurement & Instruments.Xi’an:IEEE,2007:799-804.
［6］HOMEAG I L,PARLOG-CRISTIAN R,COVRIG M.Efficiency increase for electrical fire detection and alarm systems through implementation of fuzzy expert systems ［J］.Scientific Bulletin-“Politehnica” University of Bucharest.Series C,Electrical Engineering,2013,75(1):251-266.
［7］DING Q,PENG Z H,LIU T Z,et al.Multi-sensor building fire alarm system with information fusion technology based on D-S evidence theory ［J］.Algorithms,2014,7(4):523-537.
［8］HASHEMZADEH M,ZADEMEHDI A.Fire detection for video surveillance applications using ICA K-medoids-based color model and efficient spatio-temporal visual features ［J］.Expert Systems with Applications,2019,130:60-78.
［9］MUHAMMAD K,AHMAD J,LV Z,et al.Efficient deep CNN-based fire detection and localization in video surveillance applications ［J］.IEEE Transactions on Systems,Man,and Cybernetics:Systems,2019,49(7):1419-1434.
［10］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.
［11］陈希孺.概率论与数理统计［M］.北京:科学出版社,1992.
［12］郭少冬.基于贝叶斯理论与蒙特卡洛方法的扩散源反演研究［D］.北京:清华大学,2010.
［13］吴楠.基于分布式控制策略的建筑火灾参数反演与态势预测研究［D］.北京:清华大学,2014.
［14］王岩.危险物质大气扩散的源项估计方法研究［D］.北京:清华大学,2019.
［15］HU L H,HUO R,LI Y Z,et al.Full-scale burning tests on studying smoke temperature and velocity along a corridor ［J］.Tunneling and Underground Space Technology,2005,20(3):223-229.
［16］JI J,LI L J,SHI W X,et al.Experimental investigation on the rising characteristics of the fire-induced buoyant plume in stairwells ［J］.International Journal of Heat and Mass Transfer,2013,64:193-201.
相似文献/References:
[1]胡瑾秋,张来斌,伊岩,等.基于贝叶斯估计的炼化装置动态告警管理方法研究[J].中国安全生产科学技术,2016,12(10):81.[doi:10.11731/j.issn.1673-193x.2016.10.013]
HU Jinqiu,ZHANG Laibin,YI Yan,et al.Research on dynamic alarm management method of refining device based
on Bayesian estimation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2016,12(1):81.[doi:10.11731/j.issn.1673-193x.2016.10.013]
备注/Memo
- 备注/Memo:
-
收稿日期： 2021-01-21
* 基金项目： 国家重点研发计划项目（2018YFC0810200）；中国博士后科学基金面上项目（2019M660663）
作者简介： 刘罡,博士研究生,主要研究方向为安全科学与工程。
