Transfer Learning-Enhanced Prediction of Glass Transition Temperature in Bismaleimide-Based Polyimides

Abstract

The glass transition temperature (Tg) was a pivotal parameter governing the thermal and mechanical properties of bismaleimide-based polyimide (BMI) resins. However, limited experimental data for BMI systems posed significant challenges for predictive modeling. To address this gap, this study introduced a hybrid modeling framework leveraging transfer learning. Specifically, a multilayer perceptron (MLP) deep neural network was pre-trained on a large-scale polymer database and subsequently fine-tuned on a small-sample BMI dataset. Complementing this approach, six interpretable machine learning algorithms—random forest, ridge regression, k-nearest neighbors, Bayesian regression, support vector regression, and extreme gradient boosting—were employed to construct transparent predictive models. SHapley Additive exPlanations (SHAP) analysis was further utilized to quantify the relative contributions of molecular descriptors to Tg. Results demonstrated that the transfer learning strategy achieved superior predictive accuracy in data-scarce scenarios compared to direct training on the BMI dataset. SHAP analysis identified charge distribution inhomogeneity, molecular topology, and molecular surface area properties as the major influences on Tg. This integrated framework not only improved the prediction performance but also provided feasible insights into molecular structure design, laying a solid foundation for the rational engineering of high-performance BMI resins.