A study on the stress gradient reconstruction in finite elements problems with application of radial basis function networks

被引:0
|
作者
Giorgio Previati
Massimiliano Gobbi
Federico Ballo
机构
[1] Politecnico di Milano,Department of Mechanical Engineering
来源
Meccanica | 2019年 / 54卷
关键词
Stress recovery; Gradient recovery; Hessian recovery; Radial basis function;
D O I
暂无
中图分类号
学科分类号
摘要
The recovery of the stress gradient in finite elements problems is a widely discussed topic with many applications in the design process. The stress gradient is related to the second derivative (Hessian) of the nodal displacements and numerical techniques are required for its calculation. Particular difficulties are encountered in the reconstruction of the stress gradient in the boundary regions of the domain. This is of particular concern in most applications, especially in mechanical components, where the maximum values of stresses are often located in these regions and the stress gradient has a strong influence on the fatigue life of the component. This paper presents a comparison between some already published, partially modified, recovery techniques and a different approach based on radial basis function networks. The aim of the paper is to compare the performances of the different approaches for a number of element types with particular focus on the boundary regions. Some examples of mechanical interest are considered.
引用
收藏
页码:47 / 70
页数:23
相关论文
共 50 条
  • [31] Radial basis function based finite element method: Formulation and applications
    Kien, Dung Nguyen
    Zhuang, Xiaoying
    ENGINEERING ANALYSIS WITH BOUNDARY ELEMENTS, 2023, 152 : 455 - 472
  • [32] Application of Radial Basis Function for Concurrency Control in CAD with KBMS
    Raviram, P.
    Umarani, S. D.
    Wahidabanu, R. S. D.
    IAMA: 2009 INTERNATIONAL CONFERENCE ON INTELLIGENT AGENT & MULTI-AGENT SYSTEMS, 2009, : 338 - +
  • [33] On a high-order Gaussian radial basis function generated Hermite finite difference method and its application
    Fazlollah Soleymani
    Shengfeng Zhu
    Calcolo, 2021, 58
  • [34] On a high-order Gaussian radial basis function generated Hermite finite difference method and its application
    Soleymani, Fazlollah
    Zhu, Shengfeng
    CALCOLO, 2021, 58 (04)
  • [35] Damage localization on composite structures: radial basis function application
    Cuomo, Stefano
    Fierro, Gian Piero M.
    Meo, Michele
    NONDESTRUCTIVE CHARACTERIZATION AND MONITORING OF ADVANCED MATERIALS, AEROSPACE, CIVIL INFRASTRUCTURE, AND TRANSPORTATION VIX, 2020, 11380
  • [36] Radial basis function regularization for linear inverse problems with random noise
    Valencia, Carlos
    Yuan, Ming
    JOURNAL OF MULTIVARIATE ANALYSIS, 2013, 116 : 92 - 108
  • [37] SPEAKER IDENTIFICATION USING MULTILAYER PERCEPTRONS AND RADIAL BASIS FUNCTION NETWORKS
    MAK, MW
    ALLEN, WG
    SEXTON, GG
    NEUROCOMPUTING, 1994, 6 (01) : 99 - 117
  • [38] Control for nonlinear chaos based on radial basis function neural networks
    Wen, T
    Nan, WY
    Wu, ZS
    Nian, WJ
    PROCEEDINGS OF THE 4TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-4, 2002, : 1505 - 1508
  • [39] A review of genetic algorithms applied to training radial basis function networks
    C. Harpham
    C. W. Dawson
    M. R. Brown
    Neural Computing & Applications, 2004, 13 : 193 - 201
  • [40] A review of genetic algorithms applied to training radial basis function networks
    Harpham, C
    Dawson, CW
    Brown, MR
    NEURAL COMPUTING & APPLICATIONS, 2004, 13 (03) : 193 - 201