Simulation of multi-species flow and heat transfer using physics-informed neural networks
Simulation of multi-species flow and heat transfer using physics-informed neural networks
复制标题
DOI：
10.1063/5.0058529
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
R. Laubscher
中科院分区：
文献类型：
--
作者：
R. Laubscher
在目前的工作中，单网络和分离网络的PINN架构被应用于预测一个简单的二维矩形区域内干燥空气加湿问题的动量、物质和温度分布。所创建的PINN模型考虑了可变流体性质、种类、热扩散和对流。使用不同的超参数设置（如网络宽度和深度）来训练上述两种PINN架构，以找到性能最佳的配置。结果表明，对于给定问题，与单网络PINN体系结构相比，隔离网络PINN方法的平均损失降低了62%。此外，单网络变体难以确保物种在计算域的不同区域的质量守恒，而分离方法则成功地保持了物种守恒。在给定的一组边界条件下，PINN预测的速度、温度和物种分布与使用OpenFOAM软件生成的结果进行了比较。单网络和分离网络的PINN模型对温度和速度剖面都能得出准确的结果，相对于CFD结果，速度和温度的平均百分比差异约为7.5%和8%。单网络模型的物种质量分数的平均误差百分比为9%，隔离网络方法的平均误差百分比为1.5%。到1 ar X iv:2 10 5。14 90 7 v 1 (ph值y ic s fl 21 n] 3 1 M ay 2 02 1展示的适用性PINNs multispecies代理模型问题,parameterised版本的segregated-network PINN训练可能产生的结果不同水蒸汽入口速度。相对于OpenFOAM结果，在三种预测情况下，速度和温度的标准化平均绝对百分比误差约为7.5%，水蒸气质量分数的标准化平均绝对百分比误差约为2.4%。
In the present work, singleand segregated-network PINN architectures are applied to predict momentum, species and temperature distributions of a dry air humidification problem in a simple 2D rectangular domain. The created PINN models account for variable fluid properties, speciesand heat-diffusion and convection. Both the mentioned PINN architectures were trained using different hyperparameter settings, such as network width and depth to find the best-performing configuration. It is shown that the segregated-network PINN approach results in on-average 62% lower losses when compared to the singlenetwork PINN architecture for the given problem. Furthermore, the single-network variant struggled to ensure species mass conservation in different areas of the computational domain, whereas, the segregated approach successfully maintained species conservation. The PINN predicted velocity, temperature and species profiles for a given set of boundary conditions were compared to results generated using OpenFOAM software. Both the singleand segregated-network PINN models produced accurate results for temperature and velocity profiles, with average percentage difference relative to the CFD results of approximately 7.5% for velocity and 8% for temperature. The mean error percentages for the species mass fractions are 9% for the singlenetwork model and 1.5% for the segregated-network approach. To 1 ar X iv :2 10 5. 14 90 7v 1 [ ph ys ic s. fl udy n] 3 1 M ay 2 02 1 showcase the applicability of PINNs for surrogate modelling of multispecies problems, a parameterised version of the segregated-network PINN is trained which could produce results for different water vapour inlet velocities. The normalised mean absolute percentage errors, relative to the OpenFOAM results, across three predicted cases for velocity and temperature are approximately 7.5% and 2.4% for water vapour mass fraction.