A material description based on recurrent neural networks for fuzzy data and its application within the finite element method

被引：24
|
作者：
Freitag, S. [1 ]
Graf, W. [2 ]
Kaliske, M. [2 ]
机构：
[1] Ruhr Univ Bochum, Inst Struct Mech, D-44780 Bochum, Germany
[2] Tech Univ Dresden, Inst Struct Anal, D-01062 Dresden, Germany
来源：
COMPUTERS & STRUCTURES | 2013年 / 124卷
关键词：
Recurrent neural networks; Fuzzy data; Model-free material description; Fuzzy structural analysis; Finite element method; alpha-Level optimization; DEPENDENT STRUCTURAL BEHAVIOR; UNCERTAINTY TREATMENT; MODELS; MECHANICS;
D O I：
10.1016/j.compstruc.2012.11.011
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
A new soft computing approach is presented for structural analysis. Instead of material models, an artificial neural network concept is applied to describe time-dependent material behaviour within the finite element method. In order to consider imprecise data for the identification of dependencies between strain and stress processes from uncertain results of experimental investigations, recurrent neural networks for fuzzy data are used. An algorithm for the signal computation of recurrent neural networks is developed utilizing an alpha-level optimization. The approach is verified by a model based solution. Application capabilities are demonstrated by means of numerical examples. (C) 2012 Elsevier Ltd. All rights reserved.
引用
收藏
页码：29 / 37
页数：9
相关论文
共 50 条
  • [1] Fuzzy finite element method and its application
    Möller, B
    Beer, M
    Graf, W
    Sickert, JU
    TRENDS IN COMPUTATIONAL STRUCTURAL MECHANICS, 2001, : 529 - 538
  • [2] Recurrent neural networks for fuzzy data
    Freitag, Steffen
    Graf, Wolfgang
    Kaliske, Michael
    INTEGRATED COMPUTER-AIDED ENGINEERING, 2011, 18 (03) : 265 - 280
  • [3] Nonlinear dynamic data reconciliation based on recurrent neural networks and its application
    2000, East China Univ of Sci and Technology, China (26):
  • [4] A description of carbon monoxide dispersion by the finite element method and artificial neural networks
    Kucharski, M
    Kaminski, W
    Petera, J
    INZYNIERIA CHEMICZNA I PROCESOWA, 2004, 25 (03): : 1207 - 1212
  • [5] Finite element modeling of reinforced material based on dynamic relaxation method and its application
    Peng, F.-L. (pengfangle@tongji.edu.cn), 1600, Academia Sinica (34):
  • [6] Finite element modeling of reinforced material based on dynamic relaxation method and its application
    Peng Fang-le
    Hua Zhen
    Cao Yan-bo
    ROCK AND SOIL MECHANICS, 2013, 34 (11) : 3277 - 3283
  • [7] Structural Analysis with Fuzzy Data and Neural Network Based Material Description
    Graf, W.
    Freitag, S.
    Sickert, J. -U.
    Kaliske, M.
    COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2012, 27 (09) : 640 - 654
  • [8] NEURAL NETWORK BASED MATERIAL DESCRIPTION OF UNCURED RUBBER FOR USE IN FINITE ELEMENT SIMULATION
    Zopf, C.
    Freitag, S.
    Kaliske, M.
    COMPUTATIONAL PLASTICITY XI: FUNDAMENTALS AND APPLICATIONS, 2011, : 676 - 687
  • [9] Study of Neural Networks and Its Application based on Fuzzy Adjustment
    Xie, Cong
    PROCEEDINGS OF THE 2016 2ND WORKSHOP ON ADVANCED RESEARCH AND TECHNOLOGY IN INDUSTRY APPLICATIONS, 2016, 81 : 293 - 296
  • [10] Application of Fuzzy Decision Making to the Fuzzy Finite Element Method
    Ovaere, Koen
    Deschrijver, Glad
    Kerre, Etienne E.
    FUZZY INFORMATION AND ENGINEERING, 2009, 1 (01) : 27 - 36
12345