Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Gaussian Process Regression-based Knowledge Distillation Framework for Simultaneous Prediction of Physical and Mechanical Properties of Epoxy Polymers

Sindu B. S., Jan Hamaekers

Abstract

Epoxy polymers are widely used due to their multifunctional properties, but machine learning (ML) applications remain limited owing to their complex 3D molecular structure, multi-component nature, and lack of curated datasets. Existing ML studies are largely restricted to simulation data, specific properties, or narrow constituent ranges. To address these limitations, we developed an informed Gaussian Process Regression-based Knowledge Distillation (GPR-KD) framework for predicting multiple physical (glass transition temperature, density) and mechanical properties (elastic modulus, tensile strength, compressive strength, flexural strength, fracture energy, adhesive strength) of thermoset epoxy polymers. The model was trained on experimental literature data covering diverse monomer classes (9 resins, 40 hardeners). Individual GPR models serve as teacher models capturing nonlinear feature-property relationships, while a unified neural network student model learns distilled knowledge across all properties simultaneously. By encoding the target property as an input feature, the student model leverages cross-property correlations. Molecular-level descriptors extracted from SMILES representations using RDKit create a physics-informed model. The framework combines GPR interpretability and robustness with deep learning scalability and generalization. Comparative analysis demonstrates superior prediction accuracy over conventional ML models. Simultaneous multi-property prediction further improves accuracy through information sharing across correlated properties. The proposed framework enables accelerated design of novel epoxy polymers with tailored properties.

Gaussian Process Regression-based Knowledge Distillation Framework for Simultaneous Prediction of Physical and Mechanical Properties of Epoxy Polymers

Abstract

Epoxy polymers are widely used due to their multifunctional properties, but machine learning (ML) applications remain limited owing to their complex 3D molecular structure, multi-component nature, and lack of curated datasets. Existing ML studies are largely restricted to simulation data, specific properties, or narrow constituent ranges. To address these limitations, we developed an informed Gaussian Process Regression-based Knowledge Distillation (GPR-KD) framework for predicting multiple physical (glass transition temperature, density) and mechanical properties (elastic modulus, tensile strength, compressive strength, flexural strength, fracture energy, adhesive strength) of thermoset epoxy polymers. The model was trained on experimental literature data covering diverse monomer classes (9 resins, 40 hardeners). Individual GPR models serve as teacher models capturing nonlinear feature-property relationships, while a unified neural network student model learns distilled knowledge across all properties simultaneously. By encoding the target property as an input feature, the student model leverages cross-property correlations. Molecular-level descriptors extracted from SMILES representations using RDKit create a physics-informed model. The framework combines GPR interpretability and robustness with deep learning scalability and generalization. Comparative analysis demonstrates superior prediction accuracy over conventional ML models. Simultaneous multi-property prediction further improves accuracy through information sharing across correlated properties. The proposed framework enables accelerated design of novel epoxy polymers with tailored properties.
Paper Structure (8 sections, 1 equation, 6 figures, 1 table)

This paper contains 8 sections, 1 equation, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. ML model for prediction of properties
  3. Basic architecture of the model
  4. Informed GPR-KD framework
  5. Performance of the informed GPR-KD framework
  6. Comparison with conventional methods
  7. Informed GPR-KD framework for simultaneous prediction of physical and mechanical properties
  8. Conclusions

Figures (6)

  • Figure 1: Data collected from literature (used for training the ML model): (\ref{['fig:1a']}) Distribution of datapoints for each property across different epoxy combinations (236 combinations in total); Distribution of data across individual (\ref{['fig:1b']}) resin classes and (\ref{['fig:1c']}) hardener classes; (\ref{['fig:1d']}) Range of individual physical and mechanical properties.
  • Figure 2: Architecture of the GPR-KD framework used in this study.
  • Figure 3: Prediction accuracy of the proposed (\ref{['fig:3a']}) Knowledge Distillation Framework; (\ref{['fig:3b']}) Informed Knowledge Distillation Framework.
  • Figure 4: Prediction accuracy (in terms of $R^2$ score) of different physical and mechanical properties using proposed GPR-based knowledge distillation framework and conventional models.
  • Figure 5: Prediction accuracy (in terms of $R^2$ Score) during simultaneous prediction of multiple properties.
  • ...and 1 more figures