Deep learning-enhanced efficient seismic analysis of structures with multi-fidelity modeling strategies

被引:9
作者
Feng, De-Cheng [1 ]
Chen, Shi-Zhi [2 ]
Taciroglu, Ertugrul [3 ]
机构
[1] Southeast Univ, Minist Educ, Key Lab Concrete & Prestressed Concrete Struct, Nanjing 211189, Peoples R China
[2] Changan Univ, Sch Highway, Xian 710064, Peoples R China
[3] Univ Calif Los Angeles, Dept Civil & Environm Engn, Los Angeles, CA 90095 USA
基金
中国国家自然科学基金;
关键词
Seismic analysis; Fragility curve; Multi-fidelity modeling; Deep learning; Projection; FRAGILITY ANALYSIS; ELEMENTS; CURVES; STEEL;
D O I
10.1016/j.cma.2024.116775
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Seismic assessment and design of structures nominally require large numbers of analyses with high-fidelity models-e.g., to obtain fragility curves-especially for regional scale tasks. In this study, a deep learning -enhanced multi -fidelity modeling approach is devised that can dramatically increase the computational efficiency of such analyses. This approach uses highand low -fidelity numerical models for generating small and large sample responses first. Then, a deep learning -based projection model is trained with the limited high-fidelity data to learn the correlations within multi -fidelity results with the objective of having a trained model that can predict high-fidelity results from low -fidelity simulations. For validating this approach, a reinforced concrete frame and a high-rise shear -wall structure are used as validation and application examples, and the impacts of various key factors in training and model generation are examined. The results indicate that the proposed approach can effectively accelerate seismic analyses without compromising accuracy.
引用
收藏
页数:22
相关论文
共 41 条
  • [1] Efficient Analytical Fragility Function Fitting Using Dynamic Structural Analysis
    Baker, Jack W.
    [J]. EARTHQUAKE SPECTRA, 2015, 31 (01) : 579 - 599
  • [2] Assessment of various seismic fragility analysis approaches for structures excited by non-stationary stochastic ground motions
    Cao, Xu-Yang
    Feng, De-Cheng
    Li, Yue
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023, 186
  • [3] Dynamic and probabilistic seismic performance assessment of precast prestressed reinforced concrete frames incorporating slab influence through three-dimensional spatial model
    Cao, Xu-Yang
    Xiong, Cheng-Zhuo
    Feng, De-Cheng
    Wu, Gang
    [J]. BULLETIN OF EARTHQUAKE ENGINEERING, 2022, 20 (12) : 6705 - 6739
  • [4] Research on the seismic retrofitting performance of RC frames using SC-PBSPC BRBF substructures
    Cao, Xu-Yang
    Wu, Gang
    Feng, De-Cheng
    Wang, Zhun
    Cui, Hao-Ran
    [J]. EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS, 2020, 49 (08) : 794 - 816
  • [5] Multifidelity approach for data-driven prediction models of structural behaviors with limited data
    Chen, Shi-Zhi
    Feng, De-Cheng
    [J]. COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2022, 37 (12) : 1566 - 1581
  • [6] Probabilistic Machine-Learning Methods for Performance Prediction of Structure and Infrastructures through Natural Gradient Boosting
    Chen, Shi-Zhi
    Feng, De-Cheng
    Wang, Wen-Jie
    Taciroglu, Ertugrul
    [J]. JOURNAL OF STRUCTURAL ENGINEERING, 2022, 148 (08)
  • [7] An extended probabilistic demand model with optimal intensity measures for seismic performance characterization of isolated bridges under coupled horizontal and vertical motions
    Dehghanpoor, Ahmad
    Thambiratnam, David
    Zhang, Wenyang
    Chan, Tommy
    Taciroglu, Ertugrul
    [J]. BULLETIN OF EARTHQUAKE ENGINEERING, 2021, 19 (05) : 2291 - 2323
  • [8] Finite element modelling approach for precast reinforced concrete beam-to-column connections under cyclic loading
    Feng, De-Cheng
    Wu, Gang
    Lu, Yong
    [J]. ENGINEERING STRUCTURES, 2018, 174 : 49 - 66
  • [9] Filippou F.C., 1983, Effects of bond deterioration on hysteretic behavior of reinforced concrete joints"
  • [10] Multi-fidelity optimization via surrogate modelling
    Forrester, Alexander I. J.
    Sobester, Andras
    Keane, Andy J.
    [J]. PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2007, 463 (2088): : 3251 - 3269