Premium
Determination of Ductile Material Properties by Means of the Small Punch Test and Neural Networks
Author(s) -
Abendroth M.,
Kuna M.
Publication year - 2004
Publication title -
advanced engineering materials
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.938
H-Index - 114
eISSN - 1527-2648
pISSN - 1438-1656
DOI - 10.1002/adem.200400405
Subject(s) - artificial neural network , materials science , hardening (computing) , displacement (psychology) , finite element method , structural engineering , measure (data warehouse) , material properties , base (topology) , test data , composite material , computer science , mathematical analysis , engineering , mathematics , psychology , layer (electronics) , database , machine learning , psychotherapist , programming language
This paper compares two different methods for the identification of ductile properties of materials using the small punch test to measure the material response under loading. The finite element method is used to calculate the load displacement curve of the punch depending on the parameters of a hardening law. Via systematical variation of the material parameters a data base is built up, which is used to train neural networks. The second method allows the indentification of material parameters by using a conjugate directions algorithm, which minimizes the error between an experimental load displacement curve and one calculated by the network function.