Development of a Neural Network Simulator for Studying the Constitutive Behavior of Structural Composite Materials. (7th March 2013)

• Record Type: Journal Article
• Authors: Na, Hyuntae; Lee, Seung-Yub; Üstündag, Ersan; Ross, Sarah L.; Ceylan, Halil; Gopalakrishnan, Kasthurirangan
• Other Names: Afzaal M. Academic Editor.; Ein-Mozaffari F. Academic Editor.; Hermann H. Academic Editor.; Labajos F. M. Academic Editor.; Yoshihara H. Academic Editor.
• Is Part Of: ISRN materials science. Volume 2013(2013)
• Publication Date: 2013-03-07
• Subjects: Materials science -- Periodicals; Materials science; Periodicals; 620.11
• DOI: 10.1155/2013/147086
• Languages: English
• ISSNs: 2090-6080

Abstract

Abstract : 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.