|Table of Contents|

Prediction of vertical stiffness of rubber isolation bearings by BP neural network(PDF)

《建筑科学与工程学报》[ISSN:1673-2049/CN:61-1442/TU]

Issue:
2023年06期
Page:
83-90
Research Field:
建筑结构
Publishing date:

Info

Title:
Prediction of vertical stiffness of rubber isolation bearings by BP neural network
Author(s):
CHEN Lingyang1;  CUI Langlang2;  CHEN Yonghui1;  WANG Yuhang3;  KE Ke1; 3
(1. College of Civil Engineering, Hunan University, Changsha 410082, Hunan, China; 2. Citic Heavy Industries Co., Ltd., Luoyang 471039, Henan, China; 3. School of Civil Engineering, Chongqing University, Chongqing 400045, China)
Keywords:
rubber isolation bearing;  vertical stiffness;  parametric modeling;  BP neural network
PACS:
TU352.12
DOI:
10.19815/j.jace.2022.03092
Abstract:
Aiming at the problem that the vertical stiffness of rubber isolation bearings can not be accurately calculated by the theoretical formula at present, a refined ABAQUS finite element model verified by tests was established. On the basis, the common geometric dimensions(inner and outer diameters), the thickness of single-layer rubber and the number of rubber layers were selected to construct parameter matrices, and the BP neural network prediction model of vertical stiffness of rubber isolation bearings was obtained based on a large quantity of finite element analysis data. Finally, based on the finite element analysis results, the BP neural network model, China's rubber isolation bearing specifications and the vertical stiffness calculation formula proposed in literature were evaluated. The results show that the established BP neural network prediction model of vertical stiffness of rubber isolation bearings based on inner diameter, outer diameter, thickness of single rubber layer and number of rubber layers has high accuracy. The correlation coefficient between the predicted results of the BP neural network and the experimental results approaches 1, and it is completely feasible to calculate and estimate the vertical stiffness of rubber isolation bearings based on the BP neural network. The BP neural network model can better solve multivariable linear coupling relationships compared to traditional fitting methods.

References:

[1] 建筑隔震橡胶支座:JG 118—2000[S].北京:中国建筑工业出版社,2000.
Rubber isolation bearings for buildings:JG 118—2000[S].Beijing:China Architecture & Building Press,2000.
[2]肖 畅,盛 涛,金红亮.橡胶隔震支座竖向刚度有限元模拟与试验研究[J].空间结构,2019,25(3):67-71.
XIAO Chang,SHENG Tao,JIN Hongliang.Finite element simulation and experimental study on vertical stiffness of rubber isolation bearings[J].Spatial Structures,2019,25(3):67-71.
[3]徐永秋,刘文光.厚层橡胶隔震支座的竖向力学性能与试验分析[J].浙江建筑,2008,25(6):30-32.
XU Yongqiu,LIU Wenguang.Vertical mechanical property and experimental analysis of thick bedded rubber vibration isolation bearing[J].Zhejiang Construction,2008,25(6):30-32.
[4]何文福,刘文光,杨彦飞,等.厚层橡胶隔震支座基本力学性能试验[J].解放军理工大学学报(自然科学版),2011,12(3):258-263.
HE Wenfu,LIU Wenguang,YANG Yanfei,et al.Basic mechanical properties of thick rubber isolators[J].Journal of PLA University of Science and Technology(Natural Science Edition),2011,12(3):258-263.
[5]陈浩文.厚肉型橡胶隔振支座在地铁周边建筑物隔振中的应用[D].北京:清华大学,2014.
CHEN Haowen.Application of thick rubber bearing in vibration isolation for metro surrounding building structures[D].Beijing:Tsinghua University,2014.
[6]FUKASAWA T,OKAMURA S,YAMAMOTO T,et al.Development on rubber bearings for sodium-cooled fast reactor:part 2 — fundamental characteristics of half-scale rubber bearings based on static test[C]//ASME.Proceedings of ASME 2015 Pressure Vessels and Piping Conference.Boston:ASME,2015:1-10.
[7]刘文光,三山刚史,冯德民,等.橡胶隔震支座竖向刚度简化计算法[J].地震工程与工程振动,2001,21(4):111-116.
LIU Wenguang,MIYAMA Takafumi,FENG Demin,et al.A Simple method for computing vertical stiffness of rubber bearings[J].Earthquake Engineering and Engineering Vibration,2001,21(4):111-116.
[8]邹立华,饶 宇,黄 凯,等.预应力厚层橡胶支座隔震性能研究[J].建筑结构学报,2013,34(2):76-82.
ZOU Lihua,RAO Yu,HUANG Kai,et al.Research on isolating property of prestressed thick rubber bearings[J].Journal of Building Structures,2013,34(2):76-82.
[9]LINDLEY P B.Natural rubber structural bearings[C]//American Concrete Institute.Joint Sealing and Bearing System for Concrete Structures.Detroit:American Concrete Institute,1981:353-378.
[10]王奕可,谢壮宁,黄用军.矩形平面超高层建筑横风向气动力谱的神经网络预测[J].振动工程学报,2023,36(2):326-333.
WANG Yike,XIE Zhuangning,HUANG Yongjun.Neural network prediction of across-wind aerodynamic spectrum of rectangular plane super high-rise buildings[J].Journal of Vibration Engineering,2023,36(2):326-333.
[11]刘 鸣.TRC加固RC柱抗震性能的有限元分析[D].徐州:中国矿业大学,2019.
LIU Ming.Finite element analysis of seismic performance of RC columns strengthened with TRC[D].Xuzhou:China University of Mining and Technology,2019.
[12]HORTON T A,HAJIRASOULIHA I,DAVISON B,et al.Accurate prediction of cyclic hysteresis behaviour of RBS connections using Deep Learning Neural Networks[J].Engineering Structures,2021,247:113156.
[13]橡胶支座 第3部分:建筑隔震橡胶支座:GB 20688.3—2006[S].北京:中国标准出版社,2006.
Rubber bearing — Part 3:elastomeric seismic-protection isolators for buildings:GB 20688.3—2006[S].Beijing:Standards Press of China,2006.
[14]王靖雯.厚叠层橡胶隔震支座力学性能研究及稳定性分析[D].广州:广州大学,2020.
WANG Jingwen.Research on mechanical performance and stability analysis of thick laminated rubber bearing[D].Guangzhou:Guangzhou University,2020.
[15]Dassault Systemes.ABAQUS 6.12 analysis users manual volume IIE[M].Paris:Dassault Systemes,2012.
[16]王小莉.橡胶隔振器多轴疲劳寿命预测方法研究[D].广州:华南理工大学,2014.
WANG Xiaoli.Studies on life prediction of multiaxial fatigue for rubber isolators[D].Guangzhou:South China University of Technology,2014.
[17]SOZEN A,ARCAKLOGLU E,OZALP M,et al.Forecasting based on neural network approach of solar potential in Turkey[J].Renewable Energy,2005,30(7):1075-1090.
[18]KERMANSHAHI B.Recurrent neural network for forecasting next 10 years loads of nine Japanese utilities[J].Neurocomputing,1998,23(1/2/3):125-133.
[19]HAGAN M T,MENHAJ M B.Training feedforward networks with the Marquardt algorithm[J].IEEE Transactions on Neural Networks,1994,5(6):989-993.

Memo

Memo:
-
Last Update: 2023-12-01