Artificial Neural Network Approach to Determine Elastic Modulus of Carbon Fiber-Reinforced Laminates

Recognized as a prominent material for engineering applications, carbon fiber-reinforced laminated composites require significant effort to characterize due to their anisotropic structure and viscoelastic nature. Dynamic mechanical analysis has been used to accelerate the testing process by transfor...

Full description

Saved in:
Bibliographic Details
Published in:JOM (1989) 2019-11, Vol.71 (11), p.4015-4023
Main Authors: Xu, Xianbo, Gupta, Nikhil
Format: Article
Language:English
Subjects:
Artificial neural networks
Behavior
Carbon fiber reinforcement
Carbon fibers
Chemistry/Food Science
Composite materials
Dynamic mechanical analysis
Earth Sciences
Elastic anisotropy
Elastic properties
Engineering
Environment
Fiber reinforced materials
Laminar composites
Laminates
Mathematical functions
Modeling and Simulation of Composite Materials
Modulus of elasticity
Neural networks
Optimization
Physics
Polymers
Stiffness
Storage modulus
Strain
Temperature
Tensors
Transformations (mathematics)
Viscoelasticity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recognized as a prominent material for engineering applications, carbon fiber-reinforced laminated composites require significant effort to characterize due to their anisotropic structure and viscoelastic nature. Dynamic mechanical analysis has been used to accelerate the testing process by transforming the measured viscoelastic properties to elastic modulus. To expand the transformation to anisotropic materials, artificial neural network approach is used to build the master relationship of the storage modulus in three in-plane directions. Using rotation transformation, the stiffness tensor can be calculated to extrapolate the frequency domain viscoelastic properties in any orientation with respect to the fiber direction. The viscoelastic properties are transformed to time domain relaxation function using the linear relationship of viscoelasticity. Stress response with a certain strain history is predicted and the elastic modulus is extracted. Compared to the experimental flexural test results, the artificial neural network-based method achieved an error of less than 7.3%. The results show that the transformation can predict the anisotropic material behavior at a wide range of temperatures and strain rates.
ISSN:1047-4838
1543-1851
DOI:10.1007/s11837-019-03666-7