Physics-Informed Neural Networks for the Reynolds Equation with Transient Cavitation Modeling

被引:1
|
作者
Brumand-Poor, Faras [1 ]
Barlog, Florian [1 ]
Plueckhahn, Nils [1 ]
Thebelt, Matteo [1 ]
Bauer, Niklas [1 ]
Schmitz, Katharina [1 ]
机构
[1] Rhein Westfal TH Aachen, Inst Fluid Power Drives & Syst IFAS, D-52074 Aachen, Germany
关键词
hydrodynamic lubrication; physics-informed neural networks; average Reynolds equation with transient cavitation; physics-informed machine learning; elastohydrodynamic; machine learning; AVERAGE FLOW MODEL;
D O I
10.3390/lubricants12110365
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Gaining insight into tribological systems is crucial for optimizing efficiency and prolonging operational lifespans in technical systems. Experimental investigations are time-consuming and costly, especially for reciprocating seals in fluid power systems. Elastohydrodynamic lubrication (EHL) simulations offer an alternative but demand significant computational resources. Physics-informed neural networks (PINNs) provide a promising solution using physics-based approaches to solve partial differential equations. While PINNs have successfully modeled hydrodynamics with stationary cavitation, they have yet to address transient cavitation with dynamic geometry changes. This contribution applies a PINN framework to predict pressure build-up and transient cavitation in sealing contacts with dynamic geometry changes. The results demonstrate the potential of PINNs for modeling tribological systems and highlight their significance in enhancing computational efficiency.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Physics-informed neural networks for the Reynolds equation with cavitation modeling
    Rom, Michael
    TRIBOLOGY INTERNATIONAL, 2023, 179
  • [2] Evaluation of physics-informed neural networks (PINN) in the solution of the Reynolds equation
    Douglas Jhon Ramos
    Barbara Zaparoli Cunha
    Gregory Bregion Daniel
    Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2023, 45
  • [3] Evaluation of physics-informed neural networks (PINN) in the solution of the Reynolds equation
    Ramos, Douglas Jhon
    Cunha, Barbara Zaparoli
    Daniel, Gregory Bregion
    JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING, 2023, 45 (11)
  • [4] Analysis on Strategies for Modeling the Wave Equation with Physics-Informed Neural Networks
    Cho, Sangin
    Choi, Woochang
    Ji, Jun
    Pyun, Sukjoon
    GEOPHYSICS AND GEOPHYSICAL EXPLORATION, 2023, 26 (03): : 114 - 125
  • [5] Optimizing a Physics-Informed Neural Network to solve the Reynolds Equation
    Lopez, Z. Sanchez
    Cortes, G. Berenice Diaz
    REVISTA MEXICANA DE FISICA, 2025, 71 (02)
  • [6] Boussinesq equation solved by the physics-informed neural networks
    Ruozhou Gao
    Wei Hu
    Jinxi Fei
    Hongyu Wu
    Nonlinear Dynamics, 2023, 111 : 15279 - 15291
  • [7] Boussinesq equation solved by the physics-informed neural networks
    Gao, Ruozhou
    Hu, Wei
    Fei, Jinxi
    Wu, Hongyu
    NONLINEAR DYNAMICS, 2023, 111 (16) : 15279 - 15291
  • [8] Solving the Teukolsky equation with physics-informed neural networks
    Luna, Raimon
    Bustillo, Juan Calderon
    Martinez, Juan Jose Seoane
    Torres-Forne, Alejandro
    Font, Jose A.
    PHYSICAL REVIEW D, 2023, 107 (06)
  • [9] PHYSICS-INFORMED NEURAL NETWORKS FOR MODELING LINEAR WAVES
    Sheikholeslami, Mohammad
    Salehi, Saeed
    Mao, Wengang
    Eslamdoost, Arash
    Nilsson, Hakan
    PROCEEDINGS OF ASME 2024 43RD INTERNATIONAL CONFERENCE ON OCEAN, OFFSHORE AND ARCTIC ENGINEERING, OMAE2024, VOL 9, 2024,
  • [10] Multifidelity modeling for Physics-Informed Neural Networks (PINNs)
    Penwarden, Michael
    Zhe, Shandian
    Narayan, Akil
    Kirby, Robert M.
    JOURNAL OF COMPUTATIONAL PHYSICS, 2022, 451