A novel physics-informed machine learning strategy to accelerate unsteady heat and mass transfer simulations

Despite the rapid advancements in the performance of central processing units (CPUs), the simulation of unsteady heat and mass transfer is computationally very costly, particularly in large domains. While a big wave of machine learning (ML) has propagated in accelerating computational fluid dynamics (CFD) studies, recent research has revealed that it is unrealistic to completely suppress the error increase as the gap between the training and prediction times increases in single training approach. In this study, we propose a residual-based physics-informed transfer learning (RePIT) strategy to accelerate unsteady heat and mass transfer simulations using ML-CFD cross computation. Our hypothesis is that long-term CFD simulations become feasible if continuous ML-CFD cross computation is periodically carried out to not only reduce increased residuals but also update network parameters with the latest CFD time series data (transfer learning approach). The cross point of ML-CFD is determined using a method similar to residual monitoring methods of first principle solvers (physics-informed manner). The feasibility of the proposed strategy was evaluated based on natural convection simulation and compared to the single training approach. In the single training approach, a residual scale change occurred around 100 timesteps leading to predicted time series exhibiting non-physical pattern as well as a large difference from the ground truth. Conversely, it was confirmed that the RePIT strategy maintained the continuity residual within the set range and showed good agreement with the ground truth for all variables and locations. The simulation was accelerated by 1.9 times, including the parameter-updating time. In conclusion, this universal strategy has the potential to significantly reduce the computational cost of CFD simulations while maintaining high accuracy.