论文标题：Investigation on identification of structural anomalies from polluted data sets using an unsupervised learning method

期刊：Frontiers of Structural and Civil Engineering

作者：Junchen YE, Zhixin ZHANG, Ke CHENG, Xuyan TAN, Bowen DU, Weizhong CHEN

发表时间：15 Oct 2024

DOI：10.1007/s11709-024-1065-3

微信链接：点击此处阅读微信文章

爱思唯尔2024中国高被引作者

陈卫忠

特聘研究员

中国科学院武汉岩土力学研究所

引用格式

Junchen YE, Zhixin ZHANG, Ke CHENG, Xuyan TAN, Bowen DU, Weizhong CHEN. Investigation on identification of structural anomalies from polluted data sets using an unsupervised learning method.Front. Struct. Civ. Eng., 2024, 18(10): 1479-1491.

摘要

土木基础设施容易因高地应力和其他自然灾害而遭受结构损坏。结构健康监测（SHM）系统收集的数据容易受到温度、传感器波动、传感器故障等多种因素的影响，引入大量噪声，增加结构异常识别难度。为解决这一问题，本文设计了在噪声条件下进行结构异常识别的全新流程，提出了基于去噪自编码器的深度学习模型——土木基础设施去噪自编码器（CIDAE），并将之用于土木基础设施的结构健康监测。以武汉长江隧道变形应力数据为例，通过有限元数值模拟实验验证了所提模型的有效性，并对案例中的环向焊缝和纵向焊缝数据进行了分析。研究结论表明，CIDAE在性能上优于传统方法。

异常检测的流程图：(a) 训练过程；(b) 测试过程

Abstract

Civil infrastructure is prone to structural damage due to high geo-stress and other natural disasters, so monitoring is required. Data collected by structural health monitoring (SHM) systems are easily affected by many factors, such as temperature, sensor fluctuation, sensor failure, which can introduce a lot of noise, increasing the difficulty of structural anomaly identification. To address this problem, this paper designs a new process of structural anomaly identification under noisy conditions and offers Civil Infrastructure Denoising Autoencoder (CIDAE), a denoising autoencoder-based deep learning model for SHM of civil infrastructure. As a case study, the effectiveness of the proposed model is verified by experiments on deformation stress data of the Wuhan Yangtze River Tunnel based on finite element simulation. Investigation of the circumferential weld and longitudinal weld data of the case study is also conducted. It is concluded that CIDAE is superior to traditional methods.

扫描二维码阅读原文

https://link.springer.com/article/10.1007/s11709-024-1065-3

《前沿》系列英文学术期刊

由教育部主管、高等教育出版社主办的《前沿》（Frontiers）系列英文学术期刊，于2006年正式创刊，以网络版和印刷版向全球发行。系列期刊包括基础科学、生命科学、工程技术和人文社会科学四个主题，是我国覆盖学科最广泛的英文学术期刊群，其中12种被SCI收录，其他也被A&HCI、Ei、MEDLINE或相应学科国际权威检索系统收录，具有一定的国际学术影响力。系列期刊采用在线优先出版方式，保证文章以最快速度发表。

中国学术前沿期刊网

http://journal.hep.com.cn