Machine learning glass transition temperature of polymers

Yun Zhang,Xiaojie Xu

doi:10.1016/j.heliyon.2020.e05055

Yun Zhang, Xiaojie Xu

Open Access

https://doi.org/10.1016/j.heliyon.2020.e05055

Copy DOI

Journal: Heliyon	Publication Date: Oct 1, 2020
Citations: 57	License type: cc-by

Affiliation: North Carolina State University

Abstract

As an important thermophysical property, polymers' glass transition temperature, Tg, could sometimes be difficult to determine experimentally. Modeling methods, particularly data-driven approaches, are promising alternatives to predictions of Tg in a fast and robust way. The molecular traceless quadrupole moment and molecule average hexadecapole moment are closely correlated with polymers' Tg. In the current work, these two parameters are used as descriptors in the Gaussian process regression model to predict Tg. We investigate 60 samples with Tg values from 194 K to 440 K. The model provides rapid and low-cost Tg estimations with high accuracy and stability.

Highlights

Glass transition temperature, Tg, of polymeric materials is a complex parameter that depends on both intrinsic and extrinsic factors
The morphology, crystallinity, tacticity, molecular weight, and density are a few examples of intrinsic factors, while synthesis and characterization methods are examples of extrinsic ones
These factors determine transition temperature of the amorphous phase between glassy and rubbery states, which plays a critical role in the polymer characterization and application [1]

Summary

Introduction

Tg, of polymeric materials is a complex parameter that depends on both intrinsic and extrinsic factors. The morphology, crystallinity, tacticity, molecular weight, and density are a few examples of intrinsic factors, while synthesis and characterization methods are examples of extrinsic ones. These factors determine transition temperature of the amorphous phase between glassy and rubbery states, which plays a critical role in the polymer characterization and application [1]. During the synthesis of half-metallic CrO2/polystyrene composites with enhanced room-temperature magnetoresistance, Tg of polystyrene affects the thermal caloricity behavior of composites and performance [7, 8, 9, 10, 11, 12]. As for polymer semiconductors, Tg impacts the polymer solar cell stability as it governs molecular organization’s kinetics during the solidification [13, 14, 15, 16]

Methods

Findings

Discussion

Conclusion