Physics-informed Kolmogorov–Arnold network with Chebyshev polynomials for fluid mechanics
Physics of Fluids · 01.09.2025 · 37 (9)
DOI: 10.1063/5.0284999 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 03.09.2025. Verfasst von Chunyu Guo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hainan Province, Shandong Province Youth Fund Project.
Abstract (Originalsprache)
Solving partial differential equations (PDEs) is essential in scientific forecasting and fluid dynamics. Traditional approaches often incur expensive computational costs and tradeoffs in efficiency and accuracy. Recent deep neural networks have improved the accuracy but require high-quality training data. Physics-informed neural networks effectively integrate physical laws to reduce the data reliance in limited sample scenarios. A novel machine-learning framework, Chebyshev physics-informed Kolmogorov–Arnold network (ChebPIKAN), is proposed to integrate the robust architectures of KAN with physical constraints to enhance the calculation accuracy of PDEs for fluid mechanics. We study the fundamentals of KAN, take advantage of the orthogonality of Chebyshev polynomial basis functions in spline fitting, and integrate physics-informed loss functions that are tailored to specific PDEs in fluid dynamics, including Allen–Cahn equation, nonlinear Burgers equation, Helmholtz equations, Kovasznay flow, cylinder wake flow, and cavity flow. Extensive experiments demonstrate that the proposed ChebPIKAN model significantly outperforms the standard KAN architecture in solving various PDEs by effectively embedding essential physical information. These results indicate that augmenting KAN with physical constraints can alleviate the overfitting issues of KAN and improve the extrapolation performance. Consequently, this study highlights the potential of ChebPIKAN as a powerful tool in computational fluid dynamics and proposes a path toward fast and reliable predictions in fluid mechanics and beyond.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hainan Province
- Shandong Province Youth Fund Project
- International Science and Technology Cooperation Project under the Fundamental Research Funds for the Central Universities of Harbin Engineering Univsity
Zitieren
APA
Guo, C., Sun, L., Li, S., Yuan, Z., & Wang, C. (2025). Physics-informed Kolmogorov–Arnold network with Chebyshev polynomials for fluid mechanics. Physics of Fluids, 37(9). https://doi.org/10.1063/5.0284999
Vancouver
Guo C, Sun L, Li S, Yuan Z, Wang C. Physics-informed Kolmogorov–Arnold network with Chebyshev polynomials for fluid mechanics. Physics of Fluids. 2025;37(9). doi:10.1063/5.0284999
BibTeX
@article{Guo2025,
author = {Guo, Chunyu and Sun, Lucheng and Li, Shilong and Yuan, Zelong and Wang, Chao},
title = {Physics-informed Kolmogorov–Arnold network with Chebyshev polynomials for fluid mechanics},
journal = {Physics of Fluids},
year = {2025},
volume = {37},
number = {9},
doi = {10.1063/5.0284999}
}
EUVIMED