EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-enabled high-throughput characterization of material properties based on indentation response

Lizichen Chen, Gengxuan Zhu, Yuanhao Chen, C. W. Lim, Weiqiu Chen

MechanoEngineering · 2026

DOI: 10.1063/5.0284635 ↗

Kurz gefasst

Fachartikel in der Zeitschrift MechanoEngineering, 2026. Verfasst von Lizichen Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, 111 Project, Specialized research projects of Huanjiang Laboratory, Zhuji, Zhejiang Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-throughput characterization (HTC) is a highly time-efficient and spatially compact approach for materials testing. It enables acquisition of comprehensive material properties in a single experiment. Among the associated testing techniques, indentation-based materials characterization is of significant importance. Given the mappings of modulus distribution on indentation responses derived by symplectic contact analysis, as well as finite element simulations, a physics-informed U-net enhanced Fourier Kolmogorov–Arnold neural operator (PIU-FKANO) is established as a surrogate model to carry out inverse contact analysis. Displacement and curve measurement techniques are applied to facilitate integration of the neural operator with experiments. Predicted and true modulus fields demonstrate a high consistency in four representative numerical examples. Different architectures of PIU-FKANO are analyzed to explore a model that excels in terms of the relative L2 error. Furthermore, the proposed model also shows more stable performance than other models, thus offering robust support for HTC techniques.

Förderung

  • National Natural Science Foundation of China
  • 111 Project
  • Specialized research projects of Huanjiang Laboratory, Zhuji, Zhejiang Province

Zitieren

APA

Chen, L., Zhu, G., Chen, Y., Lim, C. W., & Chen, W. (2026). AI-enabled high-throughput characterization of material properties based on indentation response. MechanoEngineering. https://doi.org/10.1063/5.0284635

Vancouver

Chen L, Zhu G, Chen Y, Lim CW, Chen W. AI-enabled high-throughput characterization of material properties based on indentation response. MechanoEngineering. 2026. doi:10.1063/5.0284635

BibTeX
@article{Chen2026,
  author = {Chen, Lizichen and Zhu, Gengxuan and Chen, Yuanhao and Lim, C. W. and Chen, Weiqiu},
  title = {AI-enabled high-throughput characterization of material properties based on indentation response},
  journal = {MechanoEngineering},
  year = {2026},
  doi = {10.1063/5.0284635}
}
Kostenlos starten →