{"title":"High-performance real-time fire detection and forecasting framework for industrial cables","authors":"Wanfeng Sun, Haibo Gao, 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":null,"pages":null},"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.
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.