Regularized Artificial Neural Networks for Predicting the Strain of Traction-Aged Polymer Systems Part II
Abstract
In this paper, we study the aging factor of a new polymer B and second time on A-150, A-185 polymer systems already certified for use in the aircraft and aerospace industry and we formulate a predictive model of sustainability thanks to artificial neural networks. It is the continuation of the paper [] in which we approach the experimental problem and the the theoretical part concerning Bayesian regularization and the BFGS algorithm. In this paper, an initial small experimental dataset of 33 samples is used to analyze the strain of polymers systems as a function of aging time, temperature, Young modulus and the breaking stress. In the view of the very small dataset, the strain of polymers systems is predicted by training Levenberg-Marquardt (LM), Bayesian regularization (BR), and Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm with a regularized cost function algorithms. The best results have been obtained with the two regularized artificial neural network from very small data set.
Origin : Publisher files allowed on an open archive