Missing Structural Health Monitoring Data Recovery Based on Bayesian Matrix Factorization

被引:3
|
作者
Sun, Shouwang [1 ]
Jiao, Sheng [1 ]
Hu, Qi [2 ]
Wang, Zhiwen [1 ]
Xia, Zili [3 ]
Ding, Youliang [4 ]
Yi, Letian [4 ]
机构
[1] YunJi Intelligent Engn Co Ltd, Shenzhen 518000, Peoples R China
[2] Zhongshan City Construct Grp Co Ltd, Zhongshan 528402, Peoples R China
[3] Hong Kong Zhuhai Macao Bridge Author, Zhuhai 519060, Peoples R China
[4] Southeast Univ, Key Lab C&PC Struct, Minist Educ, Nanjing 210096, Peoples R China
基金
中国国家自然科学基金;
关键词
matrix factorization; missing recovery; Bayesian inference; structural health monitoring; PREDICTION;
D O I
10.3390/su15042951
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The exposure of bridge health-monitoring systems to extreme conditions often results in missing data, which constrains the health monitoring system from working. Therefore, there is an urgent need for an efficient data cleaning method. With the development of big data and machine-learning techniques, several methods for missing-data recovery have emerged. However, optimization-based methods may experience overfitting and demand extensive tuning of parameters, and trained models may still have substantial errors when applied to unseen datasets. Furthermore, many methods can only process monitoring data from a single sensor at a time, so the spatiotemporal dependence among monitoring data from different sensors cannot be extracted to recover missing data. Monitoring data from multiple sensors can be organized in the form of matrix. Therefore, matrix factorization is an appropriate way to handle monitoring data. To this end, a hierarchical probabilistic model for matrix factorization is formulated under a fully Bayesian framework by incorporating a sparsity-inducing prior over spatiotemporal factors. The spatiotemporal dependence is modeled to reconstruct the monitoring data matrix to achieve the missing-data recovery. Through experiments using continuous monitoring data of an in-service bridge, the proposed method shows good performance of missing-data recovery. Furthermore, the effect of missing data on the preset rank of matrix is also investigated. The results show that the model can achieve higher accuracy of missing-data recovery with higher preset rank under the same case of missing data.
引用
收藏
页数:15
相关论文
共 50 条
  • [31] Bayesian nonnegative matrix factorization in an incremental manner for data representation
    Yang, Lijun
    Yan, Lulu
    Yang, Xiaohui
    Xin, Xin
    Xue, Liugen
    APPLIED INTELLIGENCE, 2023, 53 (08) : 9580 - 9597
  • [32] Bayesian dynamic forecasting of structural strain response using structural health monitoring data
    Wang, Y. W.
    Ni, Y. Q.
    STRUCTURAL CONTROL & HEALTH MONITORING, 2020, 27 (08):
  • [33] Missing data imputation framework for bridge structural health monitoring based on slim generative adversarial networks
    Gao, Shuai
    Zhao, Wenlong
    Wan, Chunfeng
    Jiang, Huachen
    Ding, Youliang
    Xue, Songtao
    MEASUREMENT, 2022, 204
  • [34] SGCast: A New Forecasting Framework for Multilocation Geomagnetic Data With Missing Traces Based on Matrix Factorization
    Liu, Huan
    Bin, Junchi
    Liu, Yihao
    Dong, Haobin
    Liu, Zheng
    Mrad, Nezih
    Blasch, Erik
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70
  • [35] Structural health monitoring by Bayesian updating
    Sibilio, Enrico
    Ciampoli, Marcello
    Beck, James L.
    COMPUTATIONAL STRUCTURAL DYNAMICS AND EARTHQUAKE ENGINEERING, 2009, 2 : 275 - +
  • [36] SGCast: A New Forecasting Framework for Multilocation Geomagnetic Data with Missing Traces Based on Matrix Factorization
    Liu, Huan
    Bin, Junchi
    Liu, Yihao
    Dong, Haobin
    Liu, Zheng
    Mrad, Nezih
    Blasch, Erik
    IEEE Transactions on Instrumentation and Measurement, 2021, 70
  • [37] Interpolation of Missing Data in Sensor Networks Using Nonnegative Matrix Factorization
    Suyama, Takayuki
    Kishino, Yasue
    Shirai, Yoshinari
    Mizutani, Shin
    Sawada, Hiroshi
    PROCEEDINGS OF THE 2018 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2018 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS (UBICOMP/ISWC'18 ADJUNCT), 2018, : 263 - 266
  • [38] NON-NEGATIVE MATRIX FACTORIZATION OF CLUSTERED DATA WITH MISSING VALUES
    Chen, Rebecca
    Varshney, Lav R.
    2019 IEEE DATA SCIENCE WORKSHOP (DSW), 2019, : 180 - 184
  • [39] A Deep Matrix Factorization Method with Missing Not at Random Data for Social Recommendation
    Wang, Weiye
    Yang, Ben
    Zhao, Wanting
    Xie, Jinkui
    NEURAL INFORMATION PROCESSING (ICONIP 2019), PT II, 2019, 11954 : 682 - 694
  • [40] Semi-Nonnegative Matrix Factorization for Motion Segmentation with Missing Data
    Mo, Quanyi
    Draper, Bruce A.
    COMPUTER VISION - ECCV 2012, PT VII, 2012, 7578 : 402 - 415