基于多传感器信息融合的火灾探测和自动化预警系统设计
Design of Fire Detection and Automated Early Warning System Based on Multi Sensor Information Fusion
刘阔 1刘文元 1曾会彬 1宋岩1
作者信息
- 1. 福建宁德核电有限公司,宁德 355200
- 折叠
摘要
火灾探测和自动化预警,是保证火灾进行可靠应急救援的依据,因此,设计基于多传感器信息融合的火灾探测和自动化预警系统.采用自适应加权算法,以传感器的自相关函数和互相关函数为依据,融合温度传感器、一氧化碳传感器、烟雾传感器的感知数据,采用基于TOPSIS法优化的DKmeans算法,聚类融合后多传感数据,并计算火灾概率结果,依据概率计算结果判断火灾类别,并进行火灾预警.测试结果显示,该系统能够完成多传感器数据融合,获取可靠、全面的火灾数据;数据聚类效果良好,单点轮廓系数均在0.947以上,可依据火灾概率结果,判断火灾类别,并完成火灾预警.
Abstract
Fire detection and automated early warning are the basis for ensuring reliable emergency rescue of fires.Therefore,a fire detection and automated early warning system based on multi-sensor information fusion is designed.Using adaptive weighting algorithm,based on the autocorrelation and cross correlation functions of sensors,the sensing data of temperature sensors,carbon monoxide sensors,and smoke sensors are fused.The DKmeans algorithm optimized based on TOPSIS method is used to cluster the fused multi-sensor data and calculate the fire probability results.Based on the probability calculation results,the fire category is determined and fire warning is carried out.The test results show that the system can complete multi-sensor data fusion and obtain reliable and comprehensive fire data.The data clustering effect is good,with single point contour coefficients above 0.947.Based on the fire probability re-sults,the fire category can be determined and the fire warning can be completed.
关键词
多传感器/信息融合/火灾探测/自动化预警/数据聚类/火灾概率Key words
multiple sensors/information fusion/fire detection/automated early warning/data clustering/fire probability引用本文复制引用
出版年
2024
NETL
NSTL
维普
万方数据