Extracting Fundamental Parameters of 2-D Natural Thermal Convection Using Machine Learning

The Lattice Boltzmann Method (LBM) is an approach for modeling mesoscopic fluid flow and heat transfer, based on modelling distributions of particles moving and colliding on a lattice, which scales to macroscopic flow, as perturbation of the Boltzmann Equation from equilibrium¹. We simulate the natural thermal convection of a fluid via LBM in a 2-D rectangular box being heated from below, cooled from above, and use the results as a training dataset to build a deep learning model. A convolutional neural network (CNN) is used to extrapolate the Rayleigh (Ra) and the Prandtl (Pr) numbers used to generate the simulation. The model has a great potential for industrial application like electronic equipment cooling or scientific research such as thermal convection of the Earth’s mantle.



References

[1] Sharma, K. V., Straka, R., & Tavares, F. W. (2020). Current status of Lattice Boltzmann Methods applied to aerodynamic, aeroacoustic, and thermal flows. Progress in Aerospace Sciences, 115, 100616.