Open AccessConstruction of True Stress-Strain Curve of Metallic Material by Artificial Neural Network and Small Punch Test
Author(s) -
Ming Song,
Xuyang Li,
Yuguang Cao,
Shuai Ma
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1676/1/012130
Subject(s) - backpropagation , artificial neural network , structural engineering , stress–strain curve , displacement (psychology) , stress (linguistics) , materials science , curve fitting , ultimate tensile strength , finite element method , tensile testing , composite material , engineering , artificial intelligence , computer science , machine learning , psychology , linguistics , philosophy , psychotherapist
Small punch test (SPT) is used to evaluate mechanical properties of metallic materials by a miniature specimen. A method combining SPT and artificial backpropagation neural network for determining the true stress-strain curve of metallic materials is proposed. The load-displacement curves of different hypothetical materials were obtained by the finite element model of SPT with considering Gurson-Tvergaard-Needleman (GTN) damage parameters and used to train a backpropagation neural network. The relationship between the load-displacement curve of SPT and the true stress-strain curve of the conventional uniaxial tensile test was established based on the trained neural network, which is validated by the experimental results of X80 pipeline steel. The results demonstrate that the established relationship can be used to predict the true stress-strain curve of the metallic materials and then to determine their elastoplastic properties by SPT.