Deep learning-based response spectrum analysis method for building structures

被引:5
|
作者
Kim, Taeyong [1 ]
Kwon, Oh-Sung [2 ]
Song, Junho [3 ]
机构
[1] Ajou Univ, Dept Civil Syst Engn, Suwon, South Korea
[2] Univ Toronto, Dept Civil & Mineral Engn, Toronto, ON, Canada
[3] Seoul Natl Univ, Dept Civil & Environm Engn, Seoul, South Korea
来源
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS | 2024年 / 53卷 / 04期
基金
新加坡国家研究基金会;
关键词
Complete Quadratic Combination; Deep learning-based modal Combination; multi-degree-of-freedom; response spectrum analysis; Square-Root-of-Sum-of-Squares; COMBINATION; EARTHQUAKE;
D O I
10.1002/eqe.4086
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The response spectrum method has gained widespread acceptance in practical applications owing to its favorable compromise between accuracy and practical efficiency. The method predicts the peak responses of multi-degree-of-freedom (MDOF) systems by combining modal responses. The Square Root of the Sum of Squares (SRSS) and Complete Quadratic Combination (CQC) rules are commonly used for modal combinations. However, it has been widely known that these rules have limitations in accurately predicting responses influenced by higher modes and cross-modal correlations. To improve the accuracy of the response spectrum analysis method for building structures, this paper proposes a Deep learning-based modal Combination (DC) rule by introducing modal contribution coefficients predicted by a deep neural network (DNN) model. The DC rule enhances prediction accuracy by considering the characteristics of ground motion and the dynamic properties of a structural system. The DC rule provides more accurate predictions than the conventional rules, particularly for irregular response spectra and responses affected by higher modes. The efficiency and applicability of the DC rule are demonstrated by numerical investigations of multistory shear buildings and steel frame structures with regular and irregular shapes. The source codes, data, and trained models are available for download at .
引用
收藏
页码:1638 / 1655
页数:18
相关论文
共 50 条
  • [31] A deep learning-based method for structural modal analysis using computer vision
    Liu, Yingkai
    Cao, Ran
    Xu, Shaopeng
    Deng, Lu
    ENGINEERING STRUCTURES, 2024, 301
  • [32] Deep Learning-Based Multidimensional Data Analysis Method for Athletes' Education Level
    He, Jun
    Zhang, Na
    ARCHIVES OF CLINICAL PSYCHIATRY, 2022, 49 (01) : 48 - 56
  • [33] Development of Deep Learning-based Analysis Method for Dynamic Stagger of the Contact Wires
    Kim D.
    Park C.
    Lee K.
    Transactions of the Korean Institute of Electrical Engineers, 2023, 72 (10): : 1285 - 1290
  • [34] Deep Learning-based Image Analysis Method for Estimation of Macroscopic Spray Parameters
    Fran Huzjan
    Filip Jurić
    Sven Lončarić
    Milan Vujanović
    Neural Computing and Applications, 2023, 35 : 9535 - 9548
  • [35] A deep learning-based constrained intelligent routing method
    Rao, Zheheng
    Xu, Yanyan
    Pan, Shaoming
    PEER-TO-PEER NETWORKING AND APPLICATIONS, 2021, 14 (04) : 2224 - 2235
  • [36] Deep Learning-Based Method for Classification of Sugarcane Varieties
    Kai, Priscila Marques
    de Oliveira, Bruna Mendes
    da Costa, Ronaldo Martins
    AGRONOMY-BASEL, 2022, 12 (11):
  • [37] A deep learning-based method for the design of microstructural materials
    Tan, Ren Kai
    Zhang, Nevin L.
    Ye, Wenjing
    STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2020, 61 (04) : 1417 - 1438
  • [38] A deep learning-based method for silkworm egg counting
    Shi, Hongkang
    Chen, Xiao
    Zhu, Minghui
    Li, Linbo
    Wu, Jianmei
    Zhang, Jianfei
    JOURNAL OF ASIA-PACIFIC ENTOMOLOGY, 2025, 28 (01)
  • [39] A Deep Learning-Based Innovative Points Extraction Method
    Yu, Tao
    Wang, Rui
    Zhan, Hongfei
    Lin, Yingjun
    Yu, Junhe
    ADVANCES IN NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY, ICNC-FSKD 2022, 2023, 153 : 130 - 138
  • [40] A deep learning-based constrained intelligent routing method
    Zheheng Rao
    Yanyan Xu
    Shaoming Pan
    Peer-to-Peer Networking and Applications, 2021, 14 : 2224 - 2235