首页|结合逆非线性主成分分析和极值理论的桥梁损伤检测

结合逆非线性主成分分析和极值理论的桥梁损伤检测

扫码查看
原文链接
  • 万方数据
  • 维普
为提高环境和运营变化(environmental and operational variations,EOV)影响下的桥梁损伤检测可靠性,结合逆非线性主成分分析(inverse nonlinear principal component analysis,INLPCA)和极值理论,提出一种新的桥梁损伤检测方法.该方法采用INLPCA对桥梁损伤特征进行建模,利用不完备健康监测数据的估计均方误差和添加神经网络训练惩罚项控制 INLPCA的非线性程度.采用 INLPCA对损伤特征的重构误差和马氏平方距离(Mahalanobis squared distance,MSD)建立损伤指标(ID),最后基于 ID 的广义极值(generalized extreme value,GEV)分布建立损伤检测阈值.以比利时KW51 铁路桥和天津永和斜拉桥为例,验证所提方法的有效性.结果表明,所提方法能准确检测EOV影响下的桥梁损伤,且对不同桥型和不同损伤特征均有良好的适用性.
Bridge damage detection based on INLPCA and extreme value theory
To improve the reliability of bridge damage detection under the influence of environmental and operational variations(EOV),a new bridge damage detection method is proposed by combining inverse nonlinear principal component analysis(INLPCA)and extreme value theory.This method uses INLPCA to model the damage features of bridges.The estimation mean square error of incomplete health monitoring data and the addition of neural network training penalty terms are used to adjust the nonlinearity of INLPCA.Damage indicator(ID)is established using INLPCA reconstruction error of damage features and Mahalanobis squared distance(MSD).Finally,a damage detection threshold is established based on the generalized extreme value(GEV)distribution of ID.Taking the KW51 railway bridge in Belgium and the Yonghe cable-stayed bridge in Tianjin as examples,the effectiveness of the proposed method was verified.The results indicate that the proposed method can accurately detect bridge damage under the influence of EOV and has good applicability to different bridge types and damage features.

bridge structuredamage detectionhealth monitoringenvironmental and operational variations(EVO)inverse nonlinear principal component analysis(INLPCA)extreme value theory

刘迅、卓卫东、林楷奇

展开 >

福州大学土木工程学院,福建 福州 350108

桥梁结构 损伤检测 健康监测 环境和运营变化(EVO) 逆非线性主成分分析(INLPCA) 极值理论

福建省科技引导性计划福建省高等学校产学合作项目福建省交通运输科技资助项目

2023H00492019Y4003ZH202305

2024

10.7631/issn.1000-2243.23174

福州大学学报(自然科学版)
福州大学

福州大学学报(自然科学版)

CSTPCD北大核心
影响因子：0.35
ISSN：1000-2243
年,卷(期)：2024.52(3)
  • 2