Compared with the space on the ground,if there is a fire in the urban complex underground space,the loss will be greatly harmful.In addition,the complex underground space is usually connected with other large space ar...Compared with the space on the ground,if there is a fire in the urban complex underground space,the loss will be greatly harmful.In addition,the complex underground space is usually connected with other large space areas and densely populated.Once a fire occurs in the complex underground space,it will cause huge property losses and casualties.In order to reduce the risk of fire,it is necessary to deeply understand the development rules and characteristics of fire in the complex underground space of the city.This article has mainly carried on the following work:(I)A particularly complex model of the multi‐storey subway station was built.On this basis,three groups of comparative experiments were conducted to study the effects of fire power,fire location and smoke control system on fire development,and the conclusion that fire location is the most important factor for fire development was obtained;(II)In order to explore the entire space fire and the local space fire,CFD(Computational Fluid Dynamics)is used to build a large‐size fire model and a small‐size fire model respectively;(III)Multiple detector data as temperature slices were built,and it is expected to make full use of the simulation data to deduce the important index of fire location in the early stage of fire.All of the works in this paper will provide reference experimental data for the prevention and firefighting of a sudden fire in the complex underground space.展开更多
同时定位与建图(simultaneous localization and mapping,SLAM)是地下空间自主探测、自动巡检和应急救援的关键。然而,地下空间巷道狭长、地形复杂、光照不均等使得激光点云和视觉图像匹配极易发生退化,进而导致多源传感器数据融合SLAM...同时定位与建图(simultaneous localization and mapping,SLAM)是地下空间自主探测、自动巡检和应急救援的关键。然而,地下空间巷道狭长、地形复杂、光照不均等使得激光点云和视觉图像匹配极易发生退化,进而导致多源传感器数据融合SLAM精度不足,甚至失效。为此,本文提出一种增强稳健性的多源传感器数据动态加权融合SLAM方法。首先,在视觉图像预处理阶段,采用了一种基于色调、饱和度、亮度(hue,stauration,value,HSV)空间的图像增强技术,结合单参数同态滤波和对比度受限的自适应直方图均衡化(contrast limited adaptive histogram equalization,CLAHE)算法,有效提升了地下空间图像的亮度和对比度,从而增强了视觉里程计的稳健性。然后,通过马氏距离一致性检验方法对各传感器的数据质量进行评估,分析数据退化情况,并自适应地选择适合当前场景的传感器数据进行融合。最后,在综合考虑各传感器关键参数的基础上,构建了多源传感器因子图模型,并根据数据质量动态调整各传感器数据融合因子的权重,形成多源传感器数据权重动态组合模型。为验证本文方法的有效性,使用自主设计集成的移动机器人在地下走廊、开挖的地铁隧道和煤矿巷道等典型地下空间中分别进行了试验,并与多种主流SLAM方法进行定性、定量对比分析。结果表明:本文方法最大轨迹均方根误差(root mean square error,RMSE)仅为0.19 m,以高精度地面三维激光扫描获取的点云为参考,平均点云直接距离比较(cloud to cloud,C2C)小于0.13 m,所构建的点云地图具有较好的全局一致性和几何结构真实性,验证了本文方法在复杂地下空间具有更高的精度和稳健性。展开更多
基金supported by Shenzhen Science and Technology Innovation Commission(NO.KCXFZ20211020163402004).
文摘Compared with the space on the ground,if there is a fire in the urban complex underground space,the loss will be greatly harmful.In addition,the complex underground space is usually connected with other large space areas and densely populated.Once a fire occurs in the complex underground space,it will cause huge property losses and casualties.In order to reduce the risk of fire,it is necessary to deeply understand the development rules and characteristics of fire in the complex underground space of the city.This article has mainly carried on the following work:(I)A particularly complex model of the multi‐storey subway station was built.On this basis,three groups of comparative experiments were conducted to study the effects of fire power,fire location and smoke control system on fire development,and the conclusion that fire location is the most important factor for fire development was obtained;(II)In order to explore the entire space fire and the local space fire,CFD(Computational Fluid Dynamics)is used to build a large‐size fire model and a small‐size fire model respectively;(III)Multiple detector data as temperature slices were built,and it is expected to make full use of the simulation data to deduce the important index of fire location in the early stage of fire.All of the works in this paper will provide reference experimental data for the prevention and firefighting of a sudden fire in the complex underground space.
文摘同时定位与建图(simultaneous localization and mapping,SLAM)是地下空间自主探测、自动巡检和应急救援的关键。然而,地下空间巷道狭长、地形复杂、光照不均等使得激光点云和视觉图像匹配极易发生退化,进而导致多源传感器数据融合SLAM精度不足,甚至失效。为此,本文提出一种增强稳健性的多源传感器数据动态加权融合SLAM方法。首先,在视觉图像预处理阶段,采用了一种基于色调、饱和度、亮度(hue,stauration,value,HSV)空间的图像增强技术,结合单参数同态滤波和对比度受限的自适应直方图均衡化(contrast limited adaptive histogram equalization,CLAHE)算法,有效提升了地下空间图像的亮度和对比度,从而增强了视觉里程计的稳健性。然后,通过马氏距离一致性检验方法对各传感器的数据质量进行评估,分析数据退化情况,并自适应地选择适合当前场景的传感器数据进行融合。最后,在综合考虑各传感器关键参数的基础上,构建了多源传感器因子图模型,并根据数据质量动态调整各传感器数据融合因子的权重,形成多源传感器数据权重动态组合模型。为验证本文方法的有效性,使用自主设计集成的移动机器人在地下走廊、开挖的地铁隧道和煤矿巷道等典型地下空间中分别进行了试验,并与多种主流SLAM方法进行定性、定量对比分析。结果表明:本文方法最大轨迹均方根误差(root mean square error,RMSE)仅为0.19 m,以高精度地面三维激光扫描获取的点云为参考,平均点云直接距离比较(cloud to cloud,C2C)小于0.13 m,所构建的点云地图具有较好的全局一致性和几何结构真实性,验证了本文方法在复杂地下空间具有更高的精度和稳健性。
