In this study, we utilize the emerging Physics Informed Neural Networks
(PINNs) approach for the first time to predict the flow field of a compressor
cascade. The approach is demonstrated on a two-dimensional problem,
incorporating Navier-Stokes equations in both the forward and inverse problems.
In the forward problem, PINNs effectively predict the flow field of the
compressor. The key advantage over Deep Neural Networks (DNNs) is that the
PINNs model incorporates a physical relationship between the relevant
quantities, resulting in more precise predictions. PINNs show obvious
advantages over the traditional CFD approaches when dealing with inverse
problems in the absence of partial boundary conditions. PINNs successfully
reconstruct the flow field of the compressor cascade solely based on partial
velocity vectors and wall pressure information. This research provides
compelling evidence that PINNs offer turbomachinery designers a promising
alternative to the current dominant CFD methods, delivering higher accuracy
compared to DNNs.

该研究首次利用物理信息神经网络（PINNs）方法预测压缩器叶片的流场，通过在正向和反向问题中融入 Navier-Stokes 方程，在正向问题中，相比深度神经网络（DNNs），PINNs 能更精确地预测流场，且在无部分边界条件的反向问题中，PINNs 比传统的 CFD 方法表现出明显优势，能仅依靠部分速度向量和壁压力信息成功重构压缩器叶片的流场，证明了 PINNs 作为一种有潜力的替代方法能提供给涡轮机械设计师更高的准确性。