EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-objective and cross-scale inverse design of temperature-control materials via physics-constrained machine learning

Dongliang Ding iD, Minhao Zou, Ruoyu Huang, Ting Liang, Hang Shi, Ke Xu, Chunyu Wong, Yanhui Chen, Meng Han, Linfeng Yu, Guoxian Zhang, Yangbo Chen und 9 weitere

National Science Review · 21.09.2026 · 13 (18)

DOI: 10.1093/nsr/nwag503 ↗

Kurz gefasst

Fachartikel in der Zeitschrift National Science Review, online erschienen am 22.08.2026. Verfasst von Dongliang Ding und 20 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics Engineering, The Chinese University of Hong Kong, Hong Kong 999077, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Research Grants Council General Research Fund, Chinese Academy of Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Temperature-control materials—notably composite phase-change materials (CPCMs)—show great potential for the thermal management of next-generation power electronics. However, the synergistic optimization of multiple performance metrics still relies heavily on Edisonian trial-and-error experimentation. Herein, we present an artificial intelligence framework that incorporates a physics-constrained inverse-design system (PHICS) built upon a directed acyclic graph (DAG) architecture for CPCMs, integrating interface, phase and carrier engineering. By encoding structural hierarchies and physical causality through a DAG, a PHICS framework couples forward predictive modeling with a diversity-enhanced NSGA-II optimizer to efficiently map Pareto-optimal design boundaries. Guided by these predictions, we successfully fabricate a high-performance CPCM composed of an oriented graphite fiber skeleton and an n-octacosane matrix with amorphous alumina (am-Al2O3) interfacial transition layers. Benefitting from the bifunctional role of the am-Al2O3 interlayer as both an interfacial phonon bridge and an electron barrier, the resulting CPCMs achieve a superior balance of thermal conduction, thermal storage and electrical insulation. These results demonstrate the accuracy of PHICS-guided multifunctional composite design, establishing a closed-loop platform that combines physics-constrained machine learning with experimental validation to solve key thermal–electrical trade-offs.

Schlagwörter

Stichwörter der Autor:innen

amorphous aluminacarrier engineeringcomposite phase-change materialsinterface engineeringphysics-constrained machine learning

Autor:innen und Institutionen

  • Department of Electronics Engineering, The Chinese University of Hong Kong, Hong Kong 999077, China.
  • School of Computer Science, Peking University, Beijing 100871, China.
  • Advanced Institute of Information Technology, Peking University, Hangzhou 311200, China.
  • College of Physical Science and Technology, Xiamen University, Xiamen 361000, China.
  • Shenzhen Institute of Advanced Electronic Materials, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.
  • Ningbo Institute of Northwestern Polytechnical University, Ningbo 315103, China.

ORCID-Profile: Dongliang Ding, Jianbin Xu

Förderung

  • National Key Research and Development Program of China
  • Research Grants Council General Research Fund
  • Chinese Academy of Sciences
  • Innovation and Technology Fund
  • National Natural Science Foundation of China
  • Guangdong Science and Technology Program

Zitieren

APA

Ding, D., Zou, M., Huang, R., Liang, T., Shi, H., Xu, K., Wong, C., Chen, Y., Han, M., Yu, L., Zhang, G., Chen, Y., Yao, Y., Zhang, X., Zhou, Y., Song, C., Zeng, X., Peng, Y., Deng, T., …, & Sun, R. (2026). Multi-objective and cross-scale inverse design of temperature-control materials via physics-constrained machine learning. National Science Review, 13(18). https://doi.org/10.1093/nsr/nwag503

Vancouver

Ding D, Zou M, Huang R, Liang T, Shi H, Xu K, et al. Multi-objective and cross-scale inverse design of temperature-control materials via physics-constrained machine learning. National Science Review. 2026;13(18). doi:10.1093/nsr/nwag503

BibTeX
@article{Ding2026,
  author = {Ding, Dongliang and Zou, Minhao and Huang, Ruoyu and Liang, Ting and Shi, Hang and Xu, Ke and Wong, Chunyu and Chen, Yanhui and Han, Meng and Yu, Linfeng and Zhang, Guoxian and Chen, Yangbo and Yao, Yimin and Zhang, Xueao and Zhou, Yanguang and Song, Chengyi and Zeng, Xiaoliang and Peng, Yijie and Deng, Tao and Xu, Jianbin and Sun, Rong},
  title = {Multi-objective and cross-scale inverse design of temperature-control materials via physics-constrained machine learning},
  journal = {National Science Review},
  year = {2026},
  volume = {13},
  number = {18},
  doi = {10.1093/nsr/nwag503}
}
Kostenlos starten →