钢筋混凝土剪力墙抗震滞回性能的多元时序深度神经网络预测

MULTIVARIATE TIME SERIES DEEP NEURAL NETWORK PREDICTION OF SEISMIC HYSTERETIC PERFORMANCE OF REINFORCED CONCRETE SHEAR WALLS

在线阅读下载PDF

导出

摘要钢筋混凝土剪力墙结构抗震性能优越且造价合理,广泛用于抗震烈度较高的地区。准确地预测剪力墙的滞回性能与骨架曲线,直接决定了结构设计与分析的准确度与可靠性。该文提出了一种基于深度学习的剪力墙结构滞回性能预测方法,可以根据结构的基本设计参数(如材料属性、几何尺寸、荷载工况等),直接预测出其承载力。通过3组剪力墙的滞回试验预测1组结构的滞回曲线,结果表明:通过比较时域的特征,深度学习方法具有较高的预测精度。通过与有限元仿真结果对比,深度学习仅需输入不同参数就能够快速预测滞回曲线,其优势还在于具有较高的计算效率,而有限元仿真需要几何建模、本构模型选取、材料属性输入和荷载工况定义,整个过程相较于深度学习耗时耗力。 The reinforced concrete shear wall structure has superior seismic performance and reasonable cost,and is widely used in regions with high seismic intensity.Accurately predicting the hysteretic performance and skeleton curve of shear walls directly determines the accuracy and reliability of structural design and analysis.A deep learning-based prediction method for the hysteretic performance of shear wall structures is proposed,which can directly predict the bearing capacity index according to the basic design parameters of the structure(such as material properties,geometric dimensions,load conditions,etc.).The hysteresis curves of one group of structures are predicted by the hysteresis tests of three groups of shear walls.The results show that the deep learning method has high prediction accuracy by comparing the characteristics of the time domain.Compared with the finite element simulation results,deep learning can quickly predict the hysteresis curve only by inputting different parameters,which has the advantage of high computational efficiency;while the finite element simulation requires geometric modeling,constitutive model selection,material property input and load case definition,and is time-consuming and labor-intensive compared with deep learning.

作者袁程熊青松孔庆钊 YUAN Cheng;XIONG Qing-song;KONG Qing-zhao(State Key Laboratory for Disaster Reduction in Civil Engineering,Tongji University,Shanghai 200092,China)

机构地区同济大学土木工程防灾国家重点实验室

出处《工程力学》 EI CSCD 北大核心 2024年第6期66-76,共11页 Engineering Mechanics

基金国家自然科学基金项目(52108470,2020YFC1512504,2022T150485,SSOP202104)。

关键词钢筋混凝土剪力墙多元时序深度神经网络滞回曲线抗震性能骨架曲线 reinforced concrete shear wall multivariate time sequential deep neural network hysteresis curve seismic performance backbone curve

分类号 TP183 [自动化与计算机技术—控制理论与控制工程] TU398.2 [建筑科学—结构工程]

作者简介通信作者:孔庆钊(1988−),男,上海人,教授,博士,博导,主要从事结构健康监测与数字孪生研究(E-mail:qkong@tongji.edu.cn);袁程(1989-),男,山东人,博士,主要从事结构加固与智能运维研究(E-mail:20310146@tongji.edu.cn);熊青松(1997-),男,湖北人,博士生,主要从事结构健康监测研究(E-mail:2011158@tongji.edu.cn).