A short review on machine learning for the purpose of optimizing and predicting the properties of polymeric nanocomposites

Abstract

The mechanical, electrical, and thermal properties of nanocomposite materials are vastly superior to those of their bulk counterparts. Adding nanoparticles (sometimes called nanofillers or nano reinforcing) to a material is a common way to make the polymeric matrix more robust. The automobile, aviation, aerospace, maritime, and municipal industries can all benefit greatly from these materials. Common types of carbon-based nanomaterials include graphene sheets and carbon nanotubes. Their mechanical, electrical, and optical qualities are unparalleled.This material has the potential to be used in the development of synthetic scaffolding. According to their properties, nanofillers can be broken down into one of three broad categories. In this paper, we provide an overview of recent advances in the application of machine learning (ML)-driven approaches for the logical design of polymer nanocomposite materials. It has been found that nanocomposites in this setting can take on one of three distinct morphologies: phase separated, intercalated, or exfoliated. This is because the resulting mechanical and thermal properties are intimately tied to the particular morphologies that are developed. Melt mixing, compression moulding, and in-situ polymerization are common techniques for creating polymeric nanocomposites. When it comes to the toughness and rigidity of composites, stress transfer from the continuous phase to the dispersed phase is a crucial occurrence. Polymer nanocomposites are a class of nanomaterials that have the potential to be used in a variety of applications such as tissue engineering.