多传感器融合的火灾监测机器人设计  

Design of fire monitoring robot based on multi - sensor fusion

作　　者：朱颖[1] 邹绮琦 ZHU Ying;ZOU Qi-qi(Huali College Guangdong University of Technology,Guangzhou 511325,China)

机构地区：[1]广东工业大学华立学院,广州511325

出　　处：《信息技术》2024年第5期133-137,143,共6页Information Technology

基　　金：2020年国家级大学生创新训练计划项目(2020-13656055)。

摘　　要：针对目前火灾报警系统不能应用在城市中非密闭空间的问题,提出一种适用于非密闭空间的多传感器融合的火灾监测机器人。该机器人采用履带式结构适应多地形移动,根据城市内非密闭下空间火势初期主要特征参数确定采集模块的搭建;利用D-S证据理论对多传感器火灾数据进行融合检测,以降低单个传感器的误报率,来提高对非密闭空间火灾事故的精确判定,并对火灾进行现场警报与远程回传。实验表明,与单一传感器判断相比,引入D-S证据理论的火灾监测机器人的火灾检测不确定性下降,检测精度得到了提高。To solve the problem that the current fire alarm system cannot be applied to the non-enclosed space in cities,a multi-sensor fusion fire monitoring robot is proposed.The robot adopts crawler structure to adapt to multi-terrain movement,and determines the construction of acquisition module according to the main characteristic parameters in the initial stage of fire in the unsealed space in the city.D-S evidence theory is used to fuse and detect the fire data of multiple sensors,so as to reduce the false alarm rate of a single sensor and improve the accurate judgment of fire accidents in non-enclosed spaces.Besides,the robot also carries out on-site alarm and remote return of fire.The experiment shows that compared with the single sensor judgment,the fire detection uncertainty of the fire monitoring robot with D-S evidence theory is reduced,and the detection accuracy is improved.

关 键 词：多传感器数据融合 火灾监测 DEMPSTER-SHAFER证据理论 非密闭空间 火灾仿真 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]