基于车桥耦合振动和深度学习的悬索桥损伤识别分析  

Damage identification analysis of suspension bridge based on vehicle-bridge coupled vibration and deep learning

作　　者：李整[1] 李奥利 陈代海[1] 许世展 张宇 Li Zheng;Li Aoli;Chen Daihai;Xu Shizhan;Zhang Yu(School of Civil Engineering,Zhengzhou University,Zhengzhou 450001,China;Henan Transportation Investment Group Co.,Ltd.,Zhengzhou 450016,China)

机构地区：[1]郑州大学土木工程学院,郑州450001 [2]河南交通投资集团有限公司,郑州450016

出　　处：《国外电子测量技术》2024年第10期26-35,共10页Foreign Electronic Measurement Technology

基　　金：国家自然科学基金(51408557);中国博士后科学基金(2013M541995);河南省交通运输厅计划项目(2020J-2-6)资助。

摘　　要：针对现有通过车辆响应识别桥梁损伤方法的不足,提出结合车桥耦合振动和深度学习理论的桥梁结构损伤识别方法。以郑州桃花峪自锚式悬索桥为例,建立桥梁和车辆的有限元分析模型,开展大跨度自锚式悬索桥的车桥耦合振动分析,获取车辆的加速度响应。以车辆加速度响应作为网络输入参数,分别构建一维卷积神经网络(one dimensional convolutional neural network,1D-CNN)和二维卷积神经网络(two dimensional convolutional neural network,2D-CNN)两种深度学习模型,对二者的识别效果进行对比分析。探讨信号噪音、低损工况等因素对桥梁结构损伤识别效果的影响规律。结果表明,2DCNN对桥梁结构的损伤识别准确率和训练效率要优于1D-CNN;1D-CNN实现了端对端智能损伤识别,2D-CNN在识别准确率和对外界干扰因素的鲁棒性上表现更好。研究结果为进一步优化桥梁结构损伤识别方法提供参考。To address the deficiencies in existing methods for bridge damage identification using vehicle response,a new approach integrating vehicle-bridge coupled vibration and deep learning theory is proposed.Taking the self-anchored suspension bridge of Zhengzhou Taohuayu as an example,finite element analysis models of the bridge and vehicles are established.A vehicle-bridge coupled vibration analysis is conducted on the large-span self-anchored suspension bridge to obtain vehicle acceleration responses.Using these acceleration responses as input parameters,two deep learning models—one-dimensional convolutional neural network(1D-CNN)and two-dimensional convolutional neural network(2D-CNN)—are constructed and their identification effectiveness is compared.The influence of factors such as signal noise and low damage conditions on the bridge structure damage identification effectiveness is explored.Results indicate that the 2D-CNN surpasses the 1D-CNN in terms of accuracy and training efficiency for bridge damage identification;the 1D-CNN achieves end-to-end intelligent damage identification,while the 2D-CNN demonstrates superior performance in accuracy and robustness against external interference.The research results provide a reference for further optimization of bridge structure damage identification methods.

关 键 词：公路桥梁 车桥耦合振动 损伤识别 深度学习 卷积神经网络 

分 类 号：U441.4[建筑科学—桥梁与隧道工程] TN911.71[交通运输工程—道路与铁道工程]