EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Ziqi Wang, Yu Liu, Xintong Xu, Jiale Zhang, Zhen Li iD, Lei Zheng, Peng Kang iD

Polymers · 30.06.2025 · 17 (13) · 1833

DOI: 10.3390/polym17131833 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Polymers, online erschienen am 30.06.2025. Verfasst von Ziqi Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Materials Science and Engineering, Beihang University, Beijing 100191, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

Tg predictionbismaleimide-based polyimidesglass transition temperaturemachine learningmolecular designtransfer learning

Autor:innen und Institutionen

  • School of Materials Science and Engineering, Beihang University, Beijing 100191, China.
  • State Key Laboratory of Artificial Intelligence for Material Science, Beihang University, Beijing 100191, China.
  • Tianmushan Laboratory, Yuhang District, Hangzhou 311115, China.

ORCID-Profile: Zhen Li, Peng Kang

Zitieren

APA

Wang, Z., Liu, Y., Xu, X., Zhang, J., Li, Z., Zheng, L., & Kang, P. (2025). Transfer Learning-Enhanced Prediction of Glass Transition Temperature in Bismaleimide-Based Polyimides. Polymers, 17(13), 1833. https://doi.org/10.3390/polym17131833

Vancouver

Wang Z, Liu Y, Xu X, Zhang J, Li Z, Zheng L, et al. Transfer Learning-Enhanced Prediction of Glass Transition Temperature in Bismaleimide-Based Polyimides. Polymers. 2025;17(13):1833. doi:10.3390/polym17131833

BibTeX
@article{Wang2025,
  author = {Wang, Ziqi and Liu, Yu and Xu, Xintong and Zhang, Jiale and Li, Zhen and Zheng, Lei and Kang, Peng},
  title = {Transfer Learning-Enhanced Prediction of Glass Transition Temperature in Bismaleimide-Based Polyimides},
  journal = {Polymers},
  year = {2025},
  volume = {17},
  number = {13},
  pages = {1833},
  doi = {10.3390/polym17131833}
}
Kostenlos starten →