2. Home
  3. ARCHIVE
  4. 2023
  5. VOL 45, NO 5 (2023)
  6. pp. 39-53

A TWO-LEVEL METHOD FOR MODELING FLUID MOVEMENT USING A LATTICE BOLTZMANN MODEL AND A CONVOLUTIONAL NEURAL NETWORK

M. A. Novotarskyi, V.A. Kuzmych

Èlektron. model. 2023, 45(5):39-53

https://doi.org/10.15407/emodel.45.05.039

ABSTRACT

A new two-level method for modeling fluid movement in closed surfaces is proposed. The metod simulates an unsteady hydrodynamic process and includes two levels of description of the modeling process. The first level supports the development of the process over time and is implemented based on the Boltzmann lattice model. At the second level, for each time layer, based on the obtained velocity field, the pressure distribution is refined by modeling the solution of the Poisson equation in the working area using a convolutional neural network, which is pre-trained on a training data set formed for a given set of typical problems. A method combi­ning both technologies is proposed, taking into account the compensation of the compressibi­lity characteristic. The structure and features of neural network training are described. Experiments were conducted on models simulating the human digestive tract in various states. The performance of the developed method is compared with the numerical way of solving the Poisson equation.

KEYWORDS

hydrodynamics, lattice Boltzmann model, Poisson equation, convolutional neural network.

REFERENCES

  1. Bristeau M.O., Glowinski R., & Periaux J. (1987). Numerical methods of the Navier-Stokes equations. Applications to the simulation of compressible and incompressible viscous flows. Computer Physics Reports, 6(1-6), 73-187. 
    https://doi.org/10.1016/0167-7977(87)90011-6
  2. Dissanayake M., Phan-Thien N. (1994). Neural-network-based approximations for solving partial differential equations. Communications in Numerical Methods in Engineering, 10(3), 195-201. 
    https://doi.org/10.1002/cnm.1640100303
  3. Mc-Fall K.S., Mahan J.R. (2009). Artificial Neural Network Method for Solution of Boundary Value Problems with Exact Satisfaction of Arbitrary Boundary Conditions. IEEE Transactions on Neural Networks, 20(8), 1221-1233. 
    https://doi.org/10.1109/TNN.2009.2020735
  4. Lagaris I., Likas A. (2000). Neural-network methods for boundary value problems with irregular boundaries. IEEE Transactions on Neural Networks, 11(5), 1041-1049. https:// org/ 10.1109/72.870037 (date of access: 12.05.2023).
    https://doi.org/10.1109/72.870037
  5. Vovk O.V. (2016). Numerical modeling of nonlinear evolution problems of diffusion-advection-reaction [Diss. PhD phys.-math. Sciences, Lviv National University named after Ivan Franko]. Institutional repository Lviv National University named after Ivan Franko. https://www.lnu.edu.ua/wp-content/uploads/2016/05/dis_vovk.pdf
  6. Doolen G. (1991). Lattice Gas MIT Press. (date of access: 24.06.2023).
  7. Kruger T., Kusumaatmaja H., Kuzmin A., Shardt O. (2017). The Lattice Boltzmann Me­thod: Principles and Practice. Springer.
    https://doi.org/10.1007/978-3-319-44649-3
  8. Sterling J.D., Chen S. (1996). Stability analysis of lattice Boltzmann methods. Journal of Computational Physics, 123(1), 196-206. 
    https://doi.org/10.1006/jcph.1996.0016
  9. Koelman J. (1991). A simple lattice Boltzmann scheme for Navier-Stokes fluid flow. Europhysics Letters, 15(6), 603-607. 
    https://doi.org/10.1209/0295-5075/15/6/007
  10. Chen S., Doolen G.D. (1998). Lattice Boltzmann Method for Fluid Flows. Annual Review of Fluid Mechanics, 30, 329-364. 
    https://doi.org/10.1146/annurev.fluid.30.1.329
  11. Horwitz J.A., Vanka S.P., Kumar P. (2019). LBM simulations of dispersed multiphase flows in a channel: role of a pressure Poisson equation. Fluids Engineering Division Summer Meeting, Published Online: November 20, 2019. https://doi.org/10.1115/AJKFluids 2019-4943 (date of access: 11.06.2023).
  12. Schofield S.P., Christon M.A., Dyadechko V. (2010). Multi-material incompressible flow simulation using the moment-of-fluid-method. International Journal for Numerical Me­thods in Fluids, 931-952. 
    https://doi.org/10.1002/fld.2108 (date of access: 12.06.2023)
  13. Chitode J.S. (2011). Numerical Methods. Technical Publications.
  14. Kuzmych V., Novotarskyi M. (2022). Accelerating simulation of the PDE solution by the structure of the convolutional neural network modifying. The 2nd International Conference on Artificial Intelligence and Logistics Engineering (ICAILE2022). Lecture Notes on Data Engineering and Communications, pр. 3-15. 
    https://doi.org/10.1007/978-3-031-04809-8_1
  15. Duchi J., Hazan E., Singer Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research. 12. 2121-2159. https://dl.acm.org/doi/10.5555/1953048.2021068 (date of access: 02.06.2023)

Full text: PDF