Abstract
Despite the demonstrated utility of Reynolds-averaged Navier Stokes (RANS) calculations for many industrially-relevant problems, the method yields unsatisfactory representations of many flows of engineering interest, such as non-equilibrium turbulence, massive flow separation, coherent unsteadiness, and secondary flow features. Due to the Reynolds-averaging process, a turbulence model is required to close the RANS equations, and the simple physical approximations used in many turbulence models can cause erroneous results when applied to the flows that feature strong pressure gradients, sudden changes in mean-strain-rate, surface curvature, and turbulence anisotropy. Physics-informed neural networks (PINNs) offer a way to model aerodynamic problems without explicitly requiring a turbulence closure. The network can use sparse training data and the unclosed RANS equations to reconstruct the flow without a turbulence model. In this work, PINNs are applied to two problems of relevance in the turbomachinery community. Firstly, we consider a variable area channel known as the periodic hills, which features a shear layer, a separation bubble, as well as favourable and adverse-pressure-gradients. Secondly, a PINN is applied to the T106C low-pressure turbine blade featuring the additional challenges of transition and laminar separation. We demonstrate that PINNs are capable of capturing sensitive features such as separation length and kinetic wake loss. This paper undertakes a considered and pragmatic assessment of the state of PINNs when applied to complex high Reynolds number flows of industrial interest, and this work demonstrates the benefits and challenges of this data-assimilation methodology.
