检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:郭超 闫治国[1,2] GUO Chao;YAN Zhiguo(State Key Laboratory for Disaster Reduction in Civil Engineering,Tongji University,Shanghai 200092;Department of Geotechnical Engineering,Tongji University,Shanghai 200092)
机构地区:[1]同济大学土木工程防灾国家重点实验室,上海200092 [2]同济大学地下建筑与工程系,上海200092
出 处:《现代隧道技术》2020年第S01期13-23,共11页Modern Tunnelling Technology
基 金:国家重点研发计划项目(2018YFB2101001);上海市“科技创新行动计划”项目(16DZ1200600).
摘 要:本文基于应急韧性防灾理念,结合地下基础设施智慧防灾决策需求,提出了一种基于多源数据深度学习的智慧防灾系统框架,建立了基于地下空间火灾事故案例库、防灾专家知识库、多源数据深度学习融合库和灾害救援与恢复联动策略库的功能架构。根据火灾领域知识和历史灾害案例制定防灾标准,对多传感器监测数据运用多尺度方法分析与表达,为深度学习方法奠定数据基础。以多源数据融合预警、智能通风控制和图像识别辅助救援为例,介绍了智慧防灾系统深度学习模型在上海多个服役隧道和运营地下综合体中的应用。结果显示,该模型相比传统方法可提前发出火灾预警,降低运营通风能耗,在火灾紧急通风和人员自救疏散等方面提供辅助决策支持。智慧防灾系统对于突发灾害时地下空间决策支持体系的数字化、信息化和智慧化建设具有重要意义。In light of the concept of resilient emergency disaster prevention and the decision-making requirements of intelligent disaster prevention in tunnels,this paper proposes a framework of intelligent disaster prevention system based on multi-source deep learning algorithm,introduces an architecture of intelligent disaster prevention system and the collaborative method and application cases of each sub-module.According to the knowledge in the field of fire disaster and case histories,disaster prevention standards are formulated,and multi-sensor monitoring data of tunnels are analyzed and presented by multi-scale method,which provides the dataset for the deep learning.Taking multi-source data fusion early warning,intelligent risk control system and image recognition aid rescue as examples,the application of deep learning in intelligent disaster prevention system is introduced.Compared with the traditional tunnel methods,the deep learning-based system can give fire early warning in advance,reduce the energy consumption of operation ventilation,and provide auxiliary decision support in fire emergency ventilation and personnel self-rescue evacuation.The intelligent disaster prevention system is of great significance to the digitization,informatization and intelligent construction of the tunnel decision support system under the sudden-onset disaster.
分 类 号:U458.1[建筑科学—桥梁与隧道工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.254