Regularized Artificial Neural Networks for Predicting the Strain of Traction-Aged Polymer Systems Part II - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Regularized Artificial Neural Networks for Predicting the Strain of Traction-Aged Polymer Systems Part II

Philippe Durand
Emmanuel Frenod
  • Function : Author
Bouchera Hassoune-Rhabbour
  • Function : Author
Valerie Nassiet

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.
Fichier principal
Vignette du fichier
rann_strain_polymer2.pdf (632.47 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03650872 , version 1 (25-04-2022)

Identifiers

  • HAL Id : hal-03650872 , version 1

Cite

Helene Canot, Philippe Durand, Emmanuel Frenod, Bouchera Hassoune-Rhabbour, Valerie Nassiet. Regularized Artificial Neural Networks for Predicting the Strain of Traction-Aged Polymer Systems Part II. WCE 2022 International Conference Engineering of Applied Mathematics, Jul 2022, Londres, Unknown Region. ⟨hal-03650872⟩
69 View
62 Download

Share

Gmail Facebook X LinkedIn More