Characterization of Shape Memory Alloys Using Artificial Neural Networks
Conference Paper
Overview
Research
Identity
Other
View All
Overview
abstract
Shape memory alloys have in recent years been shown to be an attractive lightweight alternative to traditional actuators due to their unique ability to recover high levels of plastic strain. Practical implementation of shape memory alloys, however, is often complicated by their liysteretic, non-linear, thermo-mechanical behavior. Existing constitutive models, although largely accurate in predicting this liysteretic behavior, require thorough characterization of the material. The current characterization procedure requires an extensive experimentation process in which many parameters must be carefully identified. This paper develops a novel method in which an Artificial Neural Network is trained to identify transformation temperatures of a given shape memory alloy specimen using strain-temperature coordinates as inputs. The Hartl-Lagoudas model was implemented to generate temperature-strain plots for a number of theoretical shape memory alloys. This data was used to train an Artificial Neural Network, which was in turn used to identify parameters for a number of randomly generated theoretical shape memory alloys. Results presented in the paper show that a comparison of the transformation temperatures predicted by the Artificial Neural Network with the known target transformation temperatures found that the Artificial Neural Network was able to identify both transformation temperatures and stress influence coefficients with satisfactory accuracy. 2013 by the American Institute of Aeronautics and Astronautics, Inc. All rights reserved.
name of conference
51st AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition
