High-performance real-time fire detection and forecasting framework for industrial cables

IF 3.4 3区 工程技术 Q2 ENGINEERING, CIVIL Fire Safety Journal Pub Date : 2024-07-16 DOI:10.1016/j.firesaf.2024.104228
Wanfeng Sun, Haibo Gao, Cheng Li
{"title":"High-performance real-time fire detection and forecasting framework for industrial cables","authors":"Wanfeng Sun,&nbsp;Haibo Gao,&nbsp;Cheng Li","doi":"10.1016/j.firesaf.2024.104228","DOIUrl":null,"url":null,"abstract":"<div><p>In industrial scenarios, cable fires have always been the most common threat, and traditional fire detection systems often rely on a large number of sensors, and the detection range is very limited, and it is impossible to effectively predict the fire situation in time. In this paper, we propose a detection and prediction scheme for industrial cable fire, which breaks the limitations of the previous research on multi-sensor signal input, and highly couples the detection and prediction modules to realize fire prediction based on video image input only. In fire detection, we design an object detection model using HSV for flame feature enhancement based on YOLOv8, and in fire prediction aspect, we use iTransformer as a time series prediction model to mine the correlation between various parameters to predict the spread of fire. In the experiments, the average absolute percentage error of the flame detection model for the detection of flame height, width and longitudinal position was 3.49%–10.64 %, 2.45%–8.89 % and 1.61%–9.31 %, respectively, and the MAPE of the time series prediction model for the above three parameters was 11.18%–15.06 % and 4.35%–8.18 %, 3.37%–6.62 %.The results of the above experiments verify that the proposed model has the ability to quantitatively analyze the fire spread trend in the actual fire and help firefighters make decisions.</p></div>","PeriodicalId":50445,"journal":{"name":"Fire Safety Journal","volume":"148 ","pages":"Article 104228"},"PeriodicalIF":3.4000,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fire Safety Journal","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0379711224001413","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0

Abstract

In industrial scenarios, cable fires have always been the most common threat, and traditional fire detection systems often rely on a large number of sensors, and the detection range is very limited, and it is impossible to effectively predict the fire situation in time. In this paper, we propose a detection and prediction scheme for industrial cable fire, which breaks the limitations of the previous research on multi-sensor signal input, and highly couples the detection and prediction modules to realize fire prediction based on video image input only. In fire detection, we design an object detection model using HSV for flame feature enhancement based on YOLOv8, and in fire prediction aspect, we use iTransformer as a time series prediction model to mine the correlation between various parameters to predict the spread of fire. In the experiments, the average absolute percentage error of the flame detection model for the detection of flame height, width and longitudinal position was 3.49%–10.64 %, 2.45%–8.89 % and 1.61%–9.31 %, respectively, and the MAPE of the time series prediction model for the above three parameters was 11.18%–15.06 % and 4.35%–8.18 %, 3.37%–6.62 %.The results of the above experiments verify that the proposed model has the ability to quantitatively analyze the fire spread trend in the actual fire and help firefighters make decisions.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
用于工业电缆的高性能实时火灾探测和预测框架
在工业场景中,电缆火灾一直是最常见的威胁,而传统的火灾探测系统往往依赖大量传感器,探测范围十分有限,无法及时有效地预测火情。本文提出了一种针对工业电缆火灾的检测和预测方案,打破了以往研究多传感器信号输入的局限性,将检测和预测模块高度耦合,实现了仅基于视频图像输入的火灾预测。在火灾检测方面,我们基于 YOLOv8 设计了使用 HSV 进行火焰特征增强的物体检测模型;在火灾预测方面,我们使用 iTransformer 作为时间序列预测模型,挖掘各种参数之间的相关性来预测火灾的蔓延。在实验中,火焰检测模型对火焰高度、宽度和纵向位置检测的平均绝对百分比误差分别为 3.49%-10.64 %、2.45%-8.89 % 和 1.61%-9.31 %,时间序列预测模型对上述三个参数的 MAPE 分别为 11.18%-15.06 %和4.35%-8.18 %、3.37%-6.62 %。上述实验结果验证了所提出的模型具有定量分析实际火灾中火势蔓延趋势的能力,有助于消防人员做出决策。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Fire Safety Journal
Fire Safety Journal 工程技术-材料科学:综合
CiteScore
5.70
自引率
9.70%
发文量
153
审稿时长
60 days
期刊介绍: Fire Safety Journal is the leading publication dealing with all aspects of fire safety engineering. Its scope is purposefully wide, as it is deemed important to encourage papers from all sources within this multidisciplinary subject, thus providing a forum for its further development as a distinct engineering discipline. This is an essential step towards gaining a status equal to that enjoyed by the other engineering disciplines.
期刊最新文献
Investigating the impact of iron oxide nanoparticles on the stability of class A foam for wildfire suppression Numerical investigation of the influence of thermal runaway modelling on car park fire hazard and application to a Lithium-ion Manganese Oxide battery Analysis of air consumption and moving speed by firefighters during full-scale search & rescue experiments in a tunnel Numerical simulation of fire spread in a large-scale open CLT compartment Soot modeling in the numerical simulation of buoyant diffusion flames and fires—A review
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1