An Artificial Neural Network as a Tool for the Inversion of Ultrasonic Dispersion Data for Material Characterization
Date
Authors
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Authors
Research Projects
Organizational Units
Journal Issue
Is Version Of
Versions
Series
Begun in 1973, the Review of Progress in Quantitative Nondestructive Evaluation (QNDE) is the premier international NDE meeting designed to provide an interface between research and early engineering through the presentation of current ideas and results focused on facilitating a rapid transfer to engineering development.
This site provides free, public access to papers presented at the annual QNDE conference between 1983 and 1999, and abstracts for papers presented at the conference since 2001.
Department
Abstract
In this paper, efforts on the inversion of the ultrasonic oblique incidence data to obtain the stiffness constants of orthotropic symmetry material systems such as fiber reinforced composites will be discussed. Artificial Neural Network (ANN) and Hybrid Neural Net/Fuzzy Logic Architectures [1] were used in this effort and the performance will be compared to more traditional methods. This paper seeks to solve these inverse problems in a more general fashion using Artificial Neural Networks (ANN). The acoustical data domains used was the plate wave dispersion curves for unidirectional graphite epoxy composite laminate.