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:王巍 余军波 邓涛 李镇 尹保国 WANG Wei;YU Junbo;DENG Tao;LI Zhen;YIN Baoguo(Zhejiang Huadong Engineering Consulting Co.Ltd,Hangzhou 310014,China;College of Environment and Civil Engineering,Chengdu University of Technology,Chengdu 610059,China)
机构地区:[1]浙江华东工程咨询有限公司,杭州310014 [2]成都理工大学环境与土木工程学院,成都610059
出 处:《自动化与仪器仪表》2021年第11期27-31,共5页Automation & Instrumentation
基 金:国家自然科学基金面上项目,基于细观结构的砂卵石隧道围岩力学行为及拱效应机理研究(51978088,2020/01-2023/12)。
摘 要:传统桥梁支撑节点故障检测方法,为控制桥梁支撑节点图像集采集成本,所建立的桥梁支撑节点图像集数量有限,导致桥梁支撑节点故障程度、数量的正确率及位置重合度低,为此提出基于多传感融合的桥梁支撑节点故障检测方法研究。选择位移传感器、倾角传感器、光敏传感器和激光传感器组成多传感融合装置,采集桥梁支撑节点图像,并针对采集到的图像进行图像灰度、滤波和均衡处理;将桥梁支撑节点标准图像分为三部分增强图像集,后进行归一化处理;采用U-net卷积神经网络结构,建立桥梁支撑节点故障检测模型,检测桥梁支撑节点故障。实验结果:确定桥梁支撑节点故障程度、位置和数量,研究方法相较两组传统方法,与设计故障程度、位置和数量完全一致,检测桥梁支撑节点故障程度和数量的正确率为100%,故障位置的交并比为1。in order to control the acquisition cost of bridge support node image set,the number of traditional bridge support node fault detection methods is limited,which leads to the low accuracy and position coincidence of the degree and number of bridge support node fault.Therefore,a bridge support node fault detection method based on multi-sensor fusion is proposed.The multi-sensor fusion device is composed of displacement sensor,inclination sensor,photosensitive sensor and laser sensor.The image of bridge support node is collected,and the gray level,filtering and equalization of the image are carried out.The standard image of bridge support node is divided into three parts,and the enhanced image set is normalized.The u-net convolution neural network structure is used to build the bridge support node Beam support node fault detection model is used to detect bridge support node fault.Experimental results:compared with the two traditional methods,the research method is completely consistent with the design fault degree,location and number.The accuracy rate of detecting the fault degree and number of bridge support nodes is 100%,and the intersection ratio of fault location is 1.
分 类 号:TP391[自动化与计算机技术—计算机应用技术]
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:216.73.216.38