Abnormal Data Recovery of Structural Health Monitoring for Ancient City Wall Using Deep Learning Neural Network

被引:10
作者
Deng, Yang [1 ]
Ju, Hanwen [1 ,3 ]
Li, Yuhang [2 ]
Hu, Yungang [1 ]
Li, Aiqun [1 ,2 ]
机构
[1] Beijing Univ Civil Engn & Architecture, Beijing Adv Innovat Ctr Future Urban Design, Beijing Key Lab Funct Mat Bldg Struct & Environm R, Beijing, Peoples R China
[2] Southeast Univ, Sch Civil Engn, Nanjing, Peoples R China
[3] Beijing Univ Civil Engn & Architecture, Sch Civil & Transportat Engn, 1, Zhanlanguan Rd, Beijing 100044, Peoples R China
基金
中国国家自然科学基金;
关键词
Abnormal data recovery; ancient city wall; deep learning; neural network; structural health monitoring (SHM); DAMAGE DETECTION; MISSING DATA; TOWER;
D O I
10.1080/15583058.2022.2153234
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Continuous structural health monitoring is of great importance to preventive conservation for ancient architectural heritages. However, abnormal monitoring data may trigger false alarming of structural damages. SHM of ancient buildings also needs abnormal data recovering. Most of the existing studies used the neural network with single input dimension and forward prediction to recover abnormal data, which is difficult to accurately predict long data sequences. This study developed a novel abnormal data recovery framework. The main novelty of the proposed framework is that the input and output configurations of the GRU model are optimized. Meanwhile, to make full use of the forward and backward information of the abnormal data sequence, bidirectional prediction is used to improve the prediction accuracy. The framework is implemented in the abnormal monitoring data recovering for an ancient city wall built 600 years ago in Beijing. Three types of abnormal data, including outlier, drift, and missing, are considered in this study. The results reveal that the proposed framework has high accuracy in abnormal data recovering of strain and crack width. The recovered data has the same regular diurnal variation as the normal monitoring data. The linear correlation between the structural responses and wall temperature gets obviously improved after data recovering. The proposed framework shows great capacity of abnormal data recovery for structural static responses of ancient buildings, which are usually influenced by environmental temperature variation.
引用
收藏
页码:389 / 407
页数:19
相关论文
共 37 条
  • [1] Computer vision and deep learning-based data anomaly detection method for structural health monitoring
    Bao, Yuequan
    Tang, Zhiyi
    Li, Hui
    Zhang, Yufeng
    [J]. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2019, 18 (02): : 401 - 421
  • [2] Wireless Sensor Networks for Continuous Structural Health Monitoring of Historic Masonry Towers
    Barsocchi, Paolo
    Bartoli, Gianni
    Betti, Michele
    Girardi, Maria
    Mammolito, Stefano
    Pellegrini, Daniele
    Zini, Giacomo
    [J]. INTERNATIONAL JOURNAL OF ARCHITECTURAL HERITAGE, 2021, 15 (01) : 22 - 44
  • [3] Failure modes classification and failure mechanism research of ancient city wall
    Chen, Guoqing
    Li, Le
    Li, GuangMing
    Pei, XiangJun
    [J]. ENVIRONMENTAL EARTH SCIENCES, 2017, 76 (23)
  • [4] Baseline Correction of Acceleration Data Based on a Hybrid EMD-DNN Method
    Chen, Zengshun
    Fu, Jun
    Peng, Yanjian
    Chen, Tuanhai
    Zhang, LiKai
    Yuan, Chenfeng
    [J]. SENSORS, 2021, 21 (18)
  • [5] Sequence-based modeling of deep learning with LSTM and GRU networks for structural damage detection of floating offshore wind turbine blades
    Choe, Do-Eun
    Kim, Hyoung-Chul
    Kim, Moo-Hyun
    [J]. RENEWABLE ENERGY, 2021, 174 : 218 - 235
  • [6] Experimental Research on Material Properties of Ancient White Bricks in the Yichun Region, China
    Chun, Qing
    Dong, Yunhong
    van Balen, Koenraad
    Xu, Xianbao
    [J]. INTERNATIONAL JOURNAL OF ARCHITECTURAL HERITAGE, 2017, 11 (04) : 554 - 565
  • [7] The roles of nearest neighbor methods in imputing missing data in forest inventory and monitoring databases
    Eskelson, Bianca N. I.
    Temesgen, Hailemariam
    Lemay, Valerie
    Barrett, Tara M.
    Crookston, Nicholas L.
    Hudak, Andrew T.
    [J]. SCANDINAVIAN JOURNAL OF FOREST RESEARCH, 2009, 24 (03) : 235 - 246
  • [8] Lost data recovery for structural health monitoring based on convolutional neural networks
    Fan, Gao
    Li, Jun
    Hao, Hong
    [J]. STRUCTURAL CONTROL & HEALTH MONITORING, 2019, 26 (10)
  • [9] Regression models for structural health monitoring of welded bridge joints based on temperature, traffic and strain measurements
    Farreras-Alcover, Isaac
    Chryssanthopoulos, Marios K.
    Andersen, Jacob Egede
    [J]. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2015, 14 (06): : 648 - 662
  • [10] Acceleration sensor placement technique for vibration test in structural health monitoring using microhabitat frog-leaping algorithm
    Feng, Shuo
    Jia, Jinqing
    [J]. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2018, 17 (02): : 169 - 184