Machine Learning Approaches for Predicting Aging Behavior in Polymer Nanocomposites

EasyChair Preprint 14592

Abstract

Predicting the aging behavior of polymer nanocomposites is crucial for ensuring their durability and reliability in various industrial applications. Machine learning approaches offer a promising solution for modeling the complex degradation processes that occur in these materials over time. This study explores the application of machine learning algorithms, including neural networks and decision trees, to predict the aging behavior of polymer nanocomposites. By leveraging experimental data on the physical and chemical properties of these materials, we develop predictive models that can forecast their mechanical and thermal properties after exposure to environmental stressors. Our results demonstrate the potential of machine learning to accurately predict the aging behavior of polymer nanocomposites, enabling the design of more robust and sustainable materials for advanced engineering applications.

Keyphrases: Aging behavior, Polymer nanocomposite, machine learning

@booklet{EasyChair:14592,
  author    = {Abi Cit},
  title     = {Machine Learning Approaches for Predicting Aging Behavior in Polymer Nanocomposites},
  howpublished = {EasyChair Preprint 14592},
  year      = {EasyChair, 2024}}