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
  • [41] Prediction of enthalpy of alkanes by the use of radial basis function neural networks
    Yao, XJ
    Zhang, XY
    Zhang, RS
    Liu, MC
    Hu, ZD
    Fan, BT
    COMPUTERS & CHEMISTRY, 2001, 25 (05): : 475 - 482
  • [42] Vessel Trajectory Prediction Using Radial Basis Function Neural Networks
    Stogiannos, Marios
    Papadimitrakis, Myron
    Sarimveis, Haralambos
    Alexandridis, Alex
    IEEE EUROCON 2021 - 19TH INTERNATIONAL CONFERENCE ON SMART TECHNOLOGIES, 2021, : 113 - 118
  • [43] Implicit surface reconstruction based on a new interpolation/approximation radial basis function
    Zeng, Yajun
    Zhu, Yuanpeng
    COMPUTER AIDED GEOMETRIC DESIGN, 2022, 92
  • [44] Hybrid training of radial basis function networks in a partitioning context of classification
    Oukhellou, L
    Aknin, P
    NEUROCOMPUTING, 1999, 28 : 165 - 175
  • [45] Probabilistic self-organizing map and radial basis function networks
    Anouar, F
    Badran, F
    Thiria, S
    NEUROCOMPUTING, 1998, 20 (1-3) : 83 - 96
  • [46] Applying Radial Basis Function Networks to Fault Diagnosis of Motorized Spindle
    Li, Zhe
    Wang, Kesheng
    Yang, Jinghui
    Stefanov, Yavor
    Proceedings of the 6th International Workshop of Advanced Manufacturing and Automation, 2016, 24 : 237 - 240
  • [47] Dynamic Higher Level Learning Radial Basis Function for Healthcare Application
    Chandrasekar, Jesintha Bala
    Ganapathy, Kirupa
    Vaidehi, V.
    2014 INTERNATIONAL CONFERENCE ON RECENT TRENDS IN INFORMATION TECHNOLOGY (ICRTIT), 2014,
  • [48] Application of a radial basis function neural network for diagnosis of diabetes mellitus
    Venkatesan, P.
    Anitha, S.
    CURRENT SCIENCE, 2006, 91 (09): : 1195 - 1199
  • [49] A multidomain integrated-radial-basis-function collocation method for elliptic problems
    Mai-Duy, N.
    Tran-Cong, T.
    NUMERICAL METHODS FOR PARTIAL DIFFERENTIAL EQUATIONS, 2008, 24 (05) : 1301 - 1320
  • [50] Radial basis function-based differential quadrature for dam break problems
    Behroozi, Abdol Mahdi
    Meier, Claudio I.
    Vaghefi, Mohammad
    ENGINEERING ANALYSIS WITH BOUNDARY ELEMENTS, 2023, 155 : 307 - 322