Automated, strain-based, output-only bridge damage detection
Automated, strain-based, output-only bridge damage detection
复制标题
基于应变、仅输出的自动化电桥损伤检测
DOI：
10.1007/s13349-018-0311-6
复制
发表时间：
2018
影响因子：
4.4
通讯作者：
Eftekhar Azam, Saeed
中科院分区：
文献类型：
--
作者：
Rageh, Ahmed;Linzell, Daniel G.;Eftekhar Azam, Saeed
本文提出了一个框架，自动损伤检测使用连续流的结构健康监测数据。该研究利用了部署在双轨，钢，铁路，桁架桥上的优化传感器组测量的应变。纵梁-楼板梁连接恶化是一种常见的缺陷，是本研究的重点;然而，所提出的方法可用于评估各种结构元件和细节的状况。该框架利用适当的正交模式（POM）的损伤特征和人工神经网络（ANN）作为一种自动化的方法来推断损伤的位置和强度从POM。传统上依赖于输入（负载）的POM变化最终被用作损坏指标。输入可变性需要实现人工神经网络，以帮助解耦POM的变化，由于负载变化所造成的缺陷，变化，这将使所提出的框架输入独立，一个显着的进步。为了开发一个自动化和高效的输出损伤检测框架，在ANN训练之前进行了数据清洗和准备。在监测火车通过选定桥梁时记录的选定输出（应变）数据集中，人为地引入了损坏“场景”。反过来，这些信息又被用来使用MATLAB神经网络训练ANN。训练的人工神经网络进行了测试，对监测加载事件和人工破坏的情况。建议的，只输出框架的适用性进行了调查，通过研究的桥梁在操作条件下。为了考虑纵梁-地板梁连接处潜在缺陷的影响，在选定位置人为地减小了测量信号幅度。得出的结论是，所提出的框架可以成功地检测在操作条件下施加在测量信号上的人为缺陷。
This paper presents a framework for automated damage detection using a continuous stream of structural health monitoring data. The study utilized measured strains from an optimized sensor set deployed on a double track, steel, railway, truss bridge. Stringer–floor beam connection deterioration, a common deficiency, was the focus of this study; however, the proposed methodology could be used to assess the condition of a wide range of structural elements and details. The framework utilized Proper Orthogonal Modes (POMs) as damage features and Artificial Neural Networks (ANNs) as an automated approach to infer damage location and intensity from the POMs. POM variations, which are traditionally input (load) dependent, were ultimately utilized as damage indicators. Input variability necessitated implementing ANNs to help decouple POM changes due to load variations from those caused by deficiencies, changes that would render the proposed framework input independent, a significant advancement. To develop an automated and efficient output-only damage detection framework, data cleansing and preparation were conducted prior to ANN training. Damage “scenarios” were artificially introduced into select output (strain) datasets recorded while monitoring train passes across the selected bridge. This information, in turn, was used to train ANNs using MATLABs Neural Net Toolbox. Trained ANNs were tested against monitored loading events and artificial damage scenarios. Applicability of the proposed, output-only framework was investigated via studies of the bridge under operational conditions. To account for the effects of potential deficiencies at the stringer–floor beam connections, measured signal amplitudes were artificially decreased at select locations. It was concluded that the proposed framework could successfully detect artificial deficiencies imposed on measured signals under operational conditions.
登录
查看更多内容
影响因子：
3.7
作者：
S. O'connor;Yilan Zhang;J. Lynch;M. Ettouney;P. O. Jansson
通讯作者：
S. O'connor;Yilan Zhang;J. Lynch;M. Ettouney;P. O. Jansson
影响因子：
1.3
作者：
Glisic, Branko;Hubbell, David;Yao, Yao
通讯作者：
Yao, Yao
影响因子：
3.5
作者：
Chul‐Woo Kim;T. Morita;Y. Oshima;K. Sugiura
通讯作者：
Chul‐Woo Kim;T. Morita;Y. Oshima;K. Sugiura
DOI：
10.1007/978-3-7091-2484-0_2
发表时间：
1999
期刊：
--
影响因子：
--
作者：
W. M. Jenkins
通讯作者：
W. M. Jenkins
铆接铁路桥梁的疲劳评估
DOI：
--
发表时间：
2005
期刊：
影响因子：
--
作者：
B. Imam;T. D. Righiniotis;M. Chryssanthopoulos
通讯作者：
M. Chryssanthopoulos