Hybrid LSTM+CNN architecture for unsteady flow prediction

Data-driven methods are increasingly used for modeling fluid dynamic systems, since traditional numerical methods, such as Computational Fluid Dynamics (CFD), have certain limitations, including the required computational resources and user influence. There are many Deep Learning based methods capable of providing very accurate results for stationary problems. However, the prediction of unsteady flows remains being a challenge, since with the addition of the time component, these methods lose reliability. This paper aims to design a hybrid neural network for unsteady flow prediction, which combines a Long-Short Term Memory (LSTM) and a Convolutional Neural Network (CNN). Unsteady-state RANS-based CFD simulations are conducted to obtain data of flows around cylinders. In these simulations different inlet velocities and cylinder diameters are considered, to ensure diversity in the dataset. A hybrid neural network is designed, in which a LSTM predicts the Lift Coefficient for each time step and then, based on those predictions, a CNN predicts the velocity and pressure fields. For training and testing the proposed net the conducted CFD simulations are used. Even if there is a small mismatch between the ground-truth vortex shedding frequency and the predicted one, the proposed network is able to accurately predict the vortex shedding behind the cylinders, with very low errors throughout the whole studied range.