EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Improved Physics-Informed Neural Network for Nonsmooth Stick–Slip Dynamic Analysis

Zilin Li, Feifan Zhang, Jinshuai Bai, Xinyuan Li, Wei Wang, Hongtao Wei, Pan Liu, Ming Zhai, Ronghan Wei

Journal of Computational and Nonlinear Dynamics · 01.09.2026 · 21 (9)

DOI: 10.1115/1.4071567 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational and Nonlinear Dynamics, online erschienen am 22.04.2026. Verfasst von Zilin Li und 8 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In complex frictional systems, friction-induced vibration (FIV) and noise are ubiquitous and intricate issues. Achieving high-precision simulation of the vibration response is crucial for the diagnosis of system dynamic properties and vibration control. However, frictional surfaces with multiple contact points introduce nonsmoothness, resulting in unpredictable vibration responses and posing significant challenges for numerical methods to maintain accuracy over long-term analyses. This study proposes a new physics-informed neural network (PINN) method designed to enhance the adaptability between physical constraints and neural network training. The method introduces loss functions with state transition boundary modification (STBM) derived from the physical governing equations. Additionally, a data expansion and regression (DER) strategy for processing linear complementarity problem (LCP) is implemented in the optimizer, significantly improving simulation accuracy for complex stick–slip vibration processes in multicontact frictional systems. By combining these two innovations, the proposed method, referred to as BMDER-PINN, was validated through simulations of stick–slip vibration in a two-degree-of-freedom (2DoF) frictional system. Compared with conventional time-stepping methods, this approach ensures higher accuracy in longer simulations while also enabling large time steps, thereby offering a promising calculation method for improving nonsmooth dynamics simulations.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, Z., Zhang, F., Bai, J., Li, X., Wang, W., Wei, H., Liu, P., Zhai, M., & Wei, R. (2026). An Improved Physics-Informed Neural Network for Nonsmooth Stick–Slip Dynamic Analysis. Journal of Computational and Nonlinear Dynamics, 21(9). https://doi.org/10.1115/1.4071567

Vancouver

Li Z, Zhang F, Bai J, Li X, Wang W, Wei H, et al. An Improved Physics-Informed Neural Network for Nonsmooth Stick–Slip Dynamic Analysis. Journal of Computational and Nonlinear Dynamics. 2026;21(9). doi:10.1115/1.4071567

BibTeX
@article{Li2026,
  author = {Li, Zilin and Zhang, Feifan and Bai, Jinshuai and Li, Xinyuan and Wang, Wei and Wei, Hongtao and Liu, Pan and Zhai, Ming and Wei, Ronghan},
  title = {An Improved Physics-Informed Neural Network for Nonsmooth Stick–Slip Dynamic Analysis},
  journal = {Journal of Computational and Nonlinear Dynamics},
  year = {2026},
  volume = {21},
  number = {9},
  doi = {10.1115/1.4071567}
}
Kostenlos starten →