主管:中华人民共和国应急管理部
主办:应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU

消防科学与技术 ›› 2024, Vol. 43 ›› Issue (8): 1111-1115.

• • 上一篇    下一篇

消防员多模体征传感器信息融合技术研究

屈天翊1, 洪赢政2   

  1. (1. 国家消防救援局,北京 100097;2. 应急管理部上海消防研究所,上海 200032)
  • 收稿日期:2024-05-21 修回日期:2024-06-13 出版日期:2024-08-19 发布日期:2024-08-15
  • 作者简介:屈天翊(1986- ),男,安徽合肥人,国家消防救援局应急通信和科技司高级专业技术职务,主要从事消防产品监督管理、消防科技管理等工作,北京市海淀区紫竹院路118号,100097。
  • 基金资助:
    基金项目:国家重点研发计划课题(2018YFC0807606)

Research on information fusion technology of multi-mode physical sign sensors for firefighters

Qu Tianyi1, Hong Yingzheng2   

  1. (1. National Fire and Rescue Administration, Beijing 100097, China;2. Shanghai Fire Science and Technology Research Institute of MEM, Shanghai 200032, China)
  • Received:2024-05-21 Revised:2024-06-13 Online:2024-08-19 Published:2024-08-15

摘要: 为保障消防员职业安全与健康、提升消防员身体素质和训练效果,开展消防员多体征传感器信息融合技术研究。针对生命体征监测设备易受消防实战训练中的恶劣环境、消防员的大幅度作业运动影响和消防员个人防护装备的干扰,造成采集数据的精度降低,导致采集数据无效或缺失的问题,本文采取多模传感器交叉采集消防员体征指标的设计,利用多模传感器从不同位置对消防员的心电波和脉搏波进行监测,并对采集信号进行小波阈值收缩法和快速滑动均值滤波去噪处理,然后基于数据的离散型和连续型分别开展特征识别和融合。经融合后,在功率自行车、大雨环境、消防员滚轮胎和拖拽假人训练等场景中开展测试,表明多模生命体征监测单元的监测精度和容错能力大幅提升。

关键词: 消防员职业安全与健康, 多传感器信息融合, 消防员生命体征, 体征监测

Abstract: To ensure the occupational safety and health of firefighters, improve their physical fitness and training effectiveness, research is being conducted on the fusion technology of multi sign sensor information for firefighters. In response to the problem that vital sign monitoring equipment is susceptible to harsh environments during firefighting training, significant work movements of firefighters, and interference from personal protective equipment of firefighters, resulting in reduced accuracy of data collection and ineffective or missing data collection, this article adopts the design of multi-mode sensor cross collection to monitor firefighter physical sign indicators. Multi-mode sensors are used to monitor firefighter's electrocardiogram and pulse waves from different positions, and the collected signals are denoised using wavelet threshold contraction method and fast sliding mean filtering. Then, feature recognition and fusion are carried out based on the discrete and continuous types of data. After integration, tests were conducted in several scenarios such as power bicycles, heavy rain environments, firefighter tire rolling, and drag dummy training, indicating a significant improvement in the monitoring accuracy and fault tolerance of the multi-mode vital sign monitoring unit.

Key words: firefighters occupational safety and health, multi-sensor information fusion, firefighter vital signs, signs monitoring