Development of a Neural Network Simulator for Studying the Constitutive Behavior of Structural Composite Materials

This paper introduces a recent development and application of a noncommercial artificial neural network (ANN) simulator with graphical user interface (GUI) to assist in rapid data modeling and analysis in the engineering diffraction field. The real-time network training/simulation monitoring tool has been customized for the study of constitutive behavior of engineering materials, and it has improved data mining and forecasting capabilities of neural networks. This software has been used to train and simulate the finite element modeling (FEM) data for a fiber composite system, both forward and inverse. The forward neural network simulation precisely reduplicates FEM results several orders of magnitude faster than the slow original FEM. The inverse simulation is more challenging; yet, material parameters can be meaningfully determined with the aid of parameter sensitivity information. The simulator GUI also reveals that output node size for materials parameter and input normalization method for strain data are critical train conditions in inverse network. The successful use of ANN modeling and simulator GUI has been validated through engineering neutron diffraction experimental data by determining constitutive laws of the real fiber composite materials via a mathematically rigorous and physically meaningful parameter search process, once the networks are successfully trained from the FEM database.

[1]  C. Tomé.  Self-consistent polycrystal models: a directional compliance criterion to describe grain interactions , 1999 .

[2]  Teuvo Kohonen,et al.  An introduction to neural computing , 1988, Neural Networks.

[3]  Alexandru Dan Stoica,et al.  VULCAN—The engineering diffractometer at the SNS , 2006 .

[4]  B. Clausen,et al.  Investigation of thermal residual stresses in tungsten-fiber/bulk metallic glass matrix composites , 2001 .

[5]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[6]  Kevin Swingler,et al.  Applying neural networks - a practical guide , 1996 .

[7]  Bjørn Clausen,et al.  Compressive yielding of tungsten fiber reinforced bulk metallic glass composites , 2003 .

[8]  D. C. Dunand,et al.  SMARTS – a spectrometer for strain measurement in engineering materials , 2002 .

[9]  Halil Ceylan,et al.  Engineering Neutron Diffraction Data Analysis with Inverse Neural Network Modeling , 2013 .

[10]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[12]  Halil Ceylan.  Analysis and Design of Concrete Pavement Systems Using Artificial Neural Networks , 2002 .

[13]  Rodney Hill,et al.  The essential structure of constitutive laws for metal composites and polycrystals , 1967 .

[14]  Igor Aleksander,et al.  Introduction to Neural Computing , 1990 .