Reconstructing Missing Data Using a Bi-LSTM Model Based on VMD and SSA for Structural Health Monitoring

被引:3
|
作者
Zhu, Songlin [1 ]
Miao, Jijun [1 ]
Chen, Wei [2 ,3 ]
Liu, Caiwei [1 ]
Weng, Chengliang [4 ]
Luo, Yichun [4 ]
机构
[1] Qingdao Univ Technol, Sch Civil Engn, Qingdao 266520, Peoples R China
[2] China Univ Min & Technol, Jiangsu Key Lab Environm Impact & Struct Safety En, Xuzhou 221116, Peoples R China
[3] China Univ Min & Technol, Xuzhou Key Lab Fire Safety Engn Struct, Xuzhou 221116, Peoples R China
[4] Shandong Luqiao Grp Co Ltd, Jinan 250021, Peoples R China
基金
美国国家科学基金会;
关键词
data reconstruction; structural health monitoring; Bi-LSTM; VMD; SSA;
D O I
10.3390/buildings14010251
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
For structural health monitoring (SHM), a complete dataset is crucial for further modal identification analysis and risk warning. Unfortunately, data loss can occur due to sensor failure, transmission system interruption, or hardware failure, which can lead to missing data. Therefore, this study proposes a bidirectional long short-term memory neural network (Bi-LSTM) response recovery method based on variational mode decomposition (VMD) and sparrow search algorithm (SSA) optimization that utilizes the structural response data between multiple sensors and can simultaneously consider temporal and spatial correlations. A dataset containing approximately half a month of monitoring data was collected from a certain project for training, validation, and testing. A publicly available dataset was also referenced to validate the proposed method in this paper. Using the public dataset, under 13 different data loss rates, the VMD + SSA + Bi-LSTM model reduced the RMSE of data reconstruction by an average of 65.01% and 45.35% compared to the Bi-LSTM model and the VMD + Bi-LSTM models, respectively, while the coefficient of determination increased by 62.21% and 11.19%. The data reconstruction method proposed in this paper can accurately reconstruct the variation trends of missing data without the manual optimization of hyperparameters, and the reconstruction results are close to the real data.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] A structural health monitoring data reconstruction method based on VMD and SSA-optimized GRU model
    Jia, Xiaoliang
    Zhang, Guoyan
    Wang, Zhiqiang
    Li, Huacong
    Hu, Jing
    Zhu, Songlin
    Liu, Caiwei
    SCIENTIFIC REPORTS, 2025, 15 (01):
  • [2] Field Data Forecasting Using LSTM and Bi-LSTM Approaches
    Suebsombut, Paweena
    Sekhari, Aicha
    Sureephong, Pradorn
    Belhi, Abdelhak
    Bouras, Abdelaziz
    APPLIED SCIENCES-BASEL, 2021, 11 (24):
  • [3] Bus Load Forecasting Method of Power System Based on VMD and Bi-LSTM
    Tang, Jiajie
    Zhao, Jie
    Zou, Hongliang
    Ma, Gaoyuan
    Wu, Jun
    Jiang, Xu
    Zhang, Huaixun
    SUSTAINABILITY, 2021, 13 (19)
  • [4] Bayesian dynamic regression for reconstructing missing data in structural health monitoring
    Zhang, Yi-Ming
    Wang, Hao
    Bai, Yu
    Mao, Jian-Xiao
    Xu, Yi-Chao
    STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2022, 21 (05): : 2097 - 2115
  • [5] A Machine Learning Operations (MLOps) Monitoring Model Using BI-LSTM and SARSA Algorithms
    Elgamal, Zeinab Shoieb
    Elfangary, Laila
    Fahmy, Hanan
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (10) : 583 - 593
  • [6] Sentiment Analysis based on Bi-LSTM using Tone
    Li, Huakang
    Wang, Lei
    Wang, Yongchao
    Sun, Guozi
    2019 15TH INTERNATIONAL CONFERENCE ON SEMANTICS, KNOWLEDGE AND GRIDS (SKG 2019), 2019, : 30 - 35
  • [7] Hierarchical Bi-LSTM based emotion analysis of textual data
    Mahto, Dashrath
    Yadav, Subhash Chandra
    BULLETIN OF THE POLISH ACADEMY OF SCIENCES-TECHNICAL SCIENCES, 2022, 70 (03)
  • [8] Short-term industrial load forecasting based on Bi-LSTM optimized by SSA and Dropout
    Ying, Zhangchi
    Xu, Haiyang
    Zhou, Yang
    Wu, Xuan
    He, Dong
    2023 11TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY: IOT AND SMART CITY, ITIOTSC 2023, 2023, : 50 - 62
  • [9] Web Services Classification Based on Wide & Bi-LSTM Model
    Ye, Hongfan
    Cao, Buqing
    Peng, Zhenlian
    Chen, Ting
    Wen, Yiping
    Liu, Jianxun
    IEEE ACCESS, 2019, 7 : 43697 - 43706
  • [10] Trajectory outlier detection algorithm based on Bi-LSTM model
    Han Z.
    Huang T.
    Ren W.
    Xu G.
    Journal of Radars, 2019, 8 (01) : 36 - 43