论文标题
基于残留的物理信息转移学习：通过深度学习加速长期CFD模拟的混合方法
Residual-based physics-informed transfer learning: A hybrid method for accelerating long-term CFD simulations via deep learning
论文作者
论文摘要
尽管大量人工智能（AI）已经传播到计算流体动力学（CFD）加速度研究的领域，但最近的研究强调，调和以下目标的AI技术的发展仍然是我们的主要任务：（1）在长期CFD模拟（2）中（2）在多个模拟中（2）量度（2）量度（2）的准确预测（2）量（2）（3）（3）的时间（3）（3）（3）（3）（3）（3）（3）（3）（3）（3）量（3）（3） 健康）状况。在这项研究中，我们提出了一种基于残留的物理信息传递学习（REPIT）策略，以使用ML-CFD混合计算实现这四个目标。我们的假设是，与混合方法相关的长期CFD模拟是可行的，其中CFD和AI在监测第一个原理的残差时交替地计算时间序列。通过关于自然对流的CFD案例研究，对重新策略的可行性进行了验证。在一种单一的训练方法中，残留量表发生在100个时间步长左右，导致预测的时间序列表现出非物理模式以及与地面真相的显着偏差。相反，REPIT策略将残差保持在定义范围内，并在整个模拟期间表现出良好的准确性。地面真相的最大误差在温度下低于0.4 K，X轴速度为0.024 m/s。此外，ML-GPU和CFD-CPU计算的平均时间分别为0.171 s和0.015 s。包括参数升级时间，模拟的加速度为1.9。总之，我们的重新策略是一种有希望的技术，可以降低行业中CFD模拟的成本。但是，仍然需要更有力的优化和改进研究。
While a big wave of artificial intelligence (AI) has propagated to the field of computational fluid dynamics (CFD) acceleration studies, recent research has highlighted that the development of AI techniques that reconciles the following goals remains our primary task: (1) accurate prediction of unseen (future) time series in long-term CFD simulations (2) acceleration of simulations (3) an acceptable amount of training data and time (4) within a multiple PDEs condition. In this study, we propose a residual-based physics-informed transfer learning (RePIT) strategy to achieve these four objectives using ML-CFD hybrid computation. Our hypothesis is that long-term CFD simulation is feasible with the hybrid method where CFD and AI alternately calculate time series while monitoring the first principle's residuals. The feasibility of RePIT strategy was verified through a CFD case study on natural convection. In a single training approach, a residual scale change occurred around 100th timestep, resulting in predicted time series exhibiting non-physical patterns as well as a significant deviations from the ground truth. Conversely, RePIT strategy maintained the residuals within the defined range and demonstrated good accuracy throughout the entire simulation period. The maximum error from the ground truth was below 0.4 K for temperature and 0.024 m/s for x-axis velocity. Furthermore, the average time for 1 timestep by the ML-GPU and CFD-CPU calculations was 0.171 s and 0.015 s, respectively. Including the parameter-updating time, the simulation was accelerated by a factor of 1.9. In conclusion, our RePIT strategy is a promising technique to reduce the cost of CFD simulations in industry. However, more vigorous optimization and improvement studies are still necessary.
