基于物理信息神经网络求解电推进器放电腔中不可压缩气体弥散问题

Background]The advent of the Artificial Intelligence era has led to the application of neural networks and deep learning in different disciplines, and in this study, we propose a deep neural network-based approach to solve the two-dimensional Navier-Stokes equations solution problem with a physical information-driven neural network and to model the whole physical system. [Purpose] This study aims to facilitate the traditional CFD numerical calculations, the classical problem of propellant passing into a thin gas cavity is used to replace the incompressible gas flow problem in vacuum to satisfy the continuum medium assumption of the traditional CFD method. [Methods] In the method proposed in this paper, the NavierStokes equations were combined with Physics-Informed Neural Networks (PINNs), which embedded physical information into the networks to ensure that the results were more consistent with the laws of physics and that the modeling performance was enhanced. In addition, the study introduced the XPINN method, which was based on the idea of domain decomposition, in an attempt to improve the modeling effect of PINNs. [Results]The results show that the method proposed in this paper has the following advantages: (1) Compared with the traditional CFD method, the PINN-based gas diffusion field modeling method proposed in this study has less error with the FLUENT solution results, and more accurate numerical results can be obtained. (2) The PINN-based gas diffusion field modeling approach proposed in this study models the predictive accuracy and physical consistency over the purely data-driven neural network approach. (3) It can solve the PDEs inverse problem.(4) The modeling performance of XPINN based on the idea of domain decomposition is stronger than the performance of the ordinary PINN method. [Conclusions] In a nutshell, the PINN method obtains results close to those of traditional CFD methods, while the XPINN method based on the idea of domain decomposition improves the solution of the ordinary PINN.