EUVIMEDEUVIMED entdecken
Crossref

An adaptive method of fundamental solutions driven by physics-informed neural networks for acoustic problems

Zhanpeng Yan, Fajie Wang, Xin Li, Xingxing Yue, Lin Qiu

Journal of Applied Physics · 21.11.2026 · 140 (19)

DOI: 10.1063/5.0349841 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Physics, online erschienen am 19.11.2026. Verfasst von Zhanpeng Yan und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Selecting appropriate source points remains a significant challenge in the method of fundamental solutions (MFS), particularly for acoustic problems involving geometrically complex domains and multiple types of boundary conditions. Building upon the existing adaptive MFS framework developed using physics-informed neural networks, this study extends the approach to Helmholtz acoustic problems in two- and three-dimensional domains, including both interior and exterior fields. Unlike the Laplace and biharmonic problems considered in the previous framework, Helmholtz problems involve complex-valued acoustic fields. To address this issue, the real and imaginary components are separated in the loss formulation and jointly used for neural network training. Source-point locations are represented in polar coordinates with uniformly distributed angular coordinates. For a prescribed number of source points, the angular coordinates are used as neural network inputs to predict the corresponding radial coordinates, while the loss is constructed from the MFS boundary residuals and prescribed boundary conditions to adaptively optimize source-point locations within a prescribed radial range. Numerical experiments demonstrate that conventional MFS accuracy is sensitive to the manually selected source-point distance, whereas the proposed adaptive MFS reduces the dependence on empirical source-point placement. Under the test conditions considered, it achieves comparable accuracy to conventional MFS with fewer source points. In the two-dimensional cases, it requires approximately half the time of physics-informed neural networks, while in the three-dimensional cases, it shows relatively small variations in accuracy and time across the tested network configurations and requires substantially less time than physics-informed neural networks.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province

Zitieren

APA

Yan, Z., Wang, F., Li, X., Yue, X., & Qiu, L. (2026). An adaptive method of fundamental solutions driven by physics-informed neural networks for acoustic problems. Journal of Applied Physics, 140(19). https://doi.org/10.1063/5.0349841

Vancouver

Yan Z, Wang F, Li X, Yue X, Qiu L. An adaptive method of fundamental solutions driven by physics-informed neural networks for acoustic problems. Journal of Applied Physics. 2026;140(19). doi:10.1063/5.0349841

BibTeX
@article{Yan2026,
  author = {Yan, Zhanpeng and Wang, Fajie and Li, Xin and Yue, Xingxing and Qiu, Lin},
  title = {An adaptive method of fundamental solutions driven by physics-informed neural networks for acoustic problems},
  journal = {Journal of Applied Physics},
  year = {2026},
  volume = {140},
  number = {19},
  doi = {10.1063/5.0349841}
}
Kostenlos starten →