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
  • [1] A study on the stress gradient reconstruction in finite elements problems with application of radial basis function networks
    Previati, Giorgio
    Gobbi, Massimiliano
    Ballo, Federico
    MECCANICA, 2019, 54 (1-2) : 47 - 70
  • [2] Finite integration method with radial basis function for solving stiff problems
    Li, Y.
    Hon, Y. C.
    ENGINEERING ANALYSIS WITH BOUNDARY ELEMENTS, 2017, 82 : 32 - 42
  • [3] Performance Evaluation of PET Image Reconstruction Using Radial Basis Function Networks
    Arunprasath, T.
    Rajasekaran, M. Pallikonda
    Kannan, S.
    George, Shaeba Mariam
    ARTIFICIAL INTELLIGENCE AND EVOLUTIONARY ALGORITHMS IN ENGINEERING SYSTEMS, VOL 1, 2015, 324 : 481 - 489
  • [4] A new radial basis function for Helmholtz problems
    Lin, J.
    Chen, W.
    Sze, K. Y.
    ENGINEERING ANALYSIS WITH BOUNDARY ELEMENTS, 2012, 36 (12) : 1923 - 1930
  • [5] Robust radial basis function neural networks
    Lee, CC
    Chung, PC
    Tsai, JR
    Chang, CI
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1999, 29 (06): : 674 - 685
  • [6] Radial Basis Function Cascade Correlation Networks
    Lu, Weiying
    Harrington, Peter de B.
    ALGORITHMS, 2009, 2 (03) : 1045 - 1068
  • [7] Reformulated radial basis neural networks trained by gradient descent
    Karayiannis, NB
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (03): : 657 - 671
  • [8] Neural Networks with Radial Basis Function and NARX Structure for Material Lifetime Assessment Application
    Hidayat, Mas Irfan P.
    Berata, Wajan
    ADVANCED MATERIALS RESEARCH QIR 12, 2011, 277 : 143 - +
  • [9] A radial basis function method for fractional Darboux problems
    Chandhini, G.
    Prashanthi, K. S.
    Vijesh, V. Antony
    ENGINEERING ANALYSIS WITH BOUNDARY ELEMENTS, 2018, 86 : 1 - 18
  • [10] Study on the Evaluation of Phase Space Reconstruction Based on Radial Basis Function Network Prediction
    Liu, Shuyong
    Yang, Qingchao
    Wei, Xiulei
    Yang, Aibo
    COMMUNICATIONS AND INFORMATION PROCESSING, PT 1, 2012, 288 : 30 - 36