Integrating Machine Learning Algorithms for Nanofiller Selection in Polymer Nanocomposites

EasyChair Preprint 14574

Abstract

The selection of suitable nanofillers for polymer nanocomposites is crucial for optimizing their mechanical, thermal, and electrical properties. This study explores the integration of machine learning algorithms to predict and select optimal nanofillers for polymer nanocomposites. By leveraging a dataset of nanofiller properties and corresponding composite performance, we trained and validated several machine learning models, including decision trees, random forests, and neural networks. Our results show that these models can accurately predict composite properties based on nanofiller characteristics, enabling the rapid identification of optimal nanofiller candidates. This approach streamlines the nanofiller selection process, reducing experimental trial and error, and accelerating the development of high-performance polymer nanocomposites for various applications.

Keyphrases: Nanofiller selection, machine learning, polymer nanocomposites

@booklet{EasyChair:14574,
  author    = {Abey Litty},
  title     = {Integrating Machine Learning Algorithms for Nanofiller Selection in Polymer Nanocomposites},
  howpublished = {EasyChair Preprint 14574},
  year      = {EasyChair, 2024}}