Structural Health Monitoring Using Machine Learning and Cumulative Absolute Velocity Features

被引:14
作者
Muin, Sifat [1 ]
Mosalam, Khalid M. [1 ,2 ]
机构
[1] Univ Calif Berkeley, Dept Civil & Environm Engn, Berkeley, CA 94720 USA
[2] Univ Calif Berkeley, Pacific Earthquake Engn Res PEER Ctr, 723 Davis Hall, Berkeley, CA 94720 USA
来源
APPLIED SCIENCES-BASEL | 2021年 / 11卷 / 12期
关键词
cumulative absolute velocity; earthquake damage assessment; machine learning; structural health monitoring; SUPPORT VECTOR MACHINE; DAMAGE DETECTION; MODAL PARAMETERS; IDENTIFICATION; BUILDINGS; CRITERION; MODEL;
D O I
10.3390/app11125727
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Machine learning (ML)-aided structural health monitoring (SHM) can rapidly evaluate the safety and integrity of the aging infrastructure following an earthquake. The conventional damage features used in ML-based SHM methodologies face the curse of dimensionality. This paper introduces low dimensional, namely, cumulative absolute velocity (CAV)-based features, to enable the use of ML for rapid damage assessment. A computer experiment is performed to identify the appropriate features and the ML algorithm using data from a simulated single-degree-of-freedom system. A comparative analysis of five ML models (logistic regression (LR), ordinal logistic regression (OLR), artificial neural networks with 10 and 100 neurons (ANN(10) and ANN(100)), and support vector machines (SVM)) is performed. Two test sets were used where Set-1 originated from the same distribution as the training set and Set-2 came from a different distribution. The results showed that the combination of the CAV and the relative CAV with respect to the linear response, i.e., RCAV, performed the best among the different feature combinations. Among the ML models, OLR showed good generalization capabilities when compared to SVM and ANN models. Subsequently, OLR is successfully applied to assess the damage of two numerical multi-degree of freedom (MDOF) models and an instrumented building with CAV and RCAV as features. For the MDOF models, the damage state was identified with accuracy ranging from 84% to 97% and the damage location was identified with accuracy ranging from 93% to 97.5%. The features and the OLR models successfully captured the damage information for the instrumented structure as well. The proposed methodology is capable of ensuring rapid decision-making and improving community resiliency.
引用
收藏
页数:18
相关论文
共 48 条
  • [1] 1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data
    Abdeljaber, Osama
    Avci, Onur
    Kiranyaz, Mustafa Serkan
    Boashash, Boualem
    Sodano, Henry
    Inman, Daniel J.
    [J]. NEUROCOMPUTING, 2018, 275 : 1308 - 1317
  • [2] Rotor health monitoring combining spin tests and data-driven anomaly detection methods
    Abdul-Aziz, Ali
    Woike, Mark R.
    Oza, Nikunj C.
    Matthews, Bryan L.
    Iekki, John D.
    [J]. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2012, 11 (01): : 3 - 12
  • [3] Alibrandi U, 2015, 2015 IEEE INTERNATIONAL CONFERENCE ON BUILDING ENERGY EFFICIENCY AND SUSTAINABLE TECHNOLOGIES (ICBEST), P101, DOI 10.1109/ICBEST.2015.7435873
  • [4] American Society of Civil Engineers, 2016, MIN LOADS ASS CRIT B
  • [5] [Anonymous], 2012, Seismic Performance Assessment of Buildings
  • [6] [Anonymous], 2011, Technical report 2011/03
  • [7] [Anonymous], 2012, International Building Code
  • [8] Modal identification of bridge systems using state-space methods
    Arici, Y
    Mosalam, KM
    [J]. STRUCTURAL CONTROL & HEALTH MONITORING, 2005, 12 (3-4) : 381 - 404
  • [9] Statistical significance of modal parameters of bridge systems identified from strong motion data
    Arici, Y
    Mosalam, KM
    [J]. EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS, 2005, 34 (10) : 1323 - 1341
  • [10] System identification of instrumented bridge systems
    Arici, Y
    Mosalam, KM
    [J]. EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS, 2003, 32 (07) : 999 - 1020