Search

• Physics-Informed neural networks (PINNs) are used for single and two-phase flows. • The study investigates the rising bubble problem with and without heat transfer. • The pertinent physics of wake interaction and thermal boundary layer are discussed. • Physics-Informed neural networks are agnostic to geometry and fluid properties. • The maximum error in the position of the centre of mass by PINN is less than 2.8 %. This paper presents data-driven simulations of two-phase fluid processes with heat transfer. A Physics-Informed Neural Network (PINN) was applied to capture the behaviour of phase interfaces in two-phase flows and model the hydrodynamics and heat transfer of flow configurations representative of established numerical test cases. The developed PINN approach was trained on simulation data derived from physically based Computational Fluid Dynamics (CFD) simulations with interface capturing. The present study considers fundamental problems, including tracking the rise of a single gas bubble in a denser fluid and exploring the heat transfer in the wake of a bubble rising close to a heated wall. Tracking of a rising bubble phase interface of fluids with disparate properties was performed, revealing a maximum error of only 5.2% at the interface edge and a maximum error of 2.8% at the position of the centre of mass. Inferred (hidden variable) flows are studied in addition to a purely extrapolative inverse isothermal bubble case. When no velocity data was supplied, velocity field predictions remained accurate. Rise of an inferred isothermal bubble with unseen fluid properties was found to produce a maximum mean-squared error of 0.28 and centre of mass error of 1.25%. For the case of the rising bubble with a hot wall, the maximum error in the temperature domain using specified boundary conditions was 6.8%, while the bubble position analysis reveals a maximum positional error of 3.6%. These results demonstrate that PINN is agnostic to geometry and fluid properties when studying the combined effects of convection and buoyancy on two-phase flows for the first time. This work serves as a starting point for PINN in multiphase cases involving heat transfer over a range of geometries. Eventually, PINN will be used in such cases to provide solutions for forward, inverse, and extrapolative cases. Each of which represent a dramatic saving in computational cost compared to traditional CFD. Contours of volume fraction (α) and temperature (T*) predicted by the CFD (Top) and PINN (Bottom) for the evolution of flow showing how the rising bubble influences the thermal boundary layer on the wall. [Display omitted] [ABSTRACT FROM AUTHOR]

• 3D numerical simulation of flow boiling in diverging microchannel heat sink. • The effect of varying divergence angle, width, and wall contact angle has been studied. • Volume of fluid (VOF) along with phase change model is used for the numerical study. • Varying nucleation time and bubble patterns was observed for different channels. • Flow reversal was observed in the channel with divergence angle 0.38°. This paper presents a 3D conjugate numerical simulation of the diverging microchannel heat sink, which is performed using the Volume of Fluid (VOF) model coupled with the phase change model. The modeling approach and simulation results are validated with standard correlations and published experimental results. The model is used to analyze the flow boiling and transient heat transfer mechanism through simulation of bubble nucleation, bubble growth pattern, pressure, temperature, and vapor quality variations. Moreover, local and transient Heat Transfer Coefficient (HTC) is calculated and then correlated with the simulated bubble dynamics. Herein, simulations are performed on the expanding microchannel with a varying outlet to inlet width ratio for uniform heat flux 150 kW/m2 at two different mass fluxes 240 kg/m2s and 710 kg/m2s. Further, to understand the effect of wall contact angle, simulations are performed for two different values of wall contact angle of 140° and 65°. The results indicate that the channels with low divergence angle (θ) and low outlet to inlet width ratio (δ) have low nucleation time. Rapid bubble growth and elongated flow due to channel confinement were also observed. Higher values of the heat transfer coefficient are observed in the microchannels with small hydraulic diameter, and as the diameter is increased, a reduction in the HTC values is observed. The transient heat transfer coefficient fluctuation in the channel with time has been studied along with the corresponding flow pattern. Due to the smaller wall contact angle, the bubble separation rate from the wall is low, thereby creating localized hotspots. A comparative study between straight channel and diverging channel has showed that diverging microchannels have a better performance in terms of instability mitigated flow boiling. This study has considerable relevance in electronic chip cooling using expanding microchannel with instability mitigated two-phase flow. [ABSTRACT FROM AUTHOR]