Recurrent Neural Network for End-to-End Modeling of Laminar-Turbulent Transition

TL;DR

This paper introduces a recurrent neural network model that directly predicts laminar-turbulent transition locations on airfoils from boundary-layer profiles, improving accuracy and efficiency over previous methods that predicted instability growth rates.

Contribution

The paper presents an end-to-end RNN-based transition prediction model that directly estimates transition points, offering a more straightforward and accurate approach compared to prior neural network methods.

Findings

Successfully trained on 53 airfoils across various conditions.

Achieved more accurate transition location predictions than previous models.

Provided insights on selecting training datasets from large data pools.

Abstract

Accurate prediction of laminar-turbulent transition is a critical element of computational fluid dynamics simulations for aerodynamic design across multiple flow regimes. Traditional methods of transition prediction cannot be easily extended to flow configurations where the transition process depends on a large set of parameters. In comparison, neural network methods allow higher dimensional input features to be considered without compromising the efficiency and accuracy of the traditional data driven models. Neural network methods proposed earlier follow a cumbersome methodology of predicting instability growth rates over a broad range of frequencies, which are then processed to obtain the N-factor envelope, and then, the transition location based on the correlating N-factor. This paper presents an end-to-end transition model based on a recurrent neural network, which sequentially processes the mean boundary-layer profiles along the surface of the aerodynamic body to directly predict the N-factor envelope and the transition locations over a two-dimensional airfoil. The proposed transition model has been developed and assessed using a large database of 53 airfoils over a wide range of chord Reynolds numbers and angles of attack. The sequence-to-sequence transduction model proposed herein provides a more direct approach for accurate predictions of the transition location than the earlier neural network methods, which predict the local amplification rate of a single instability mode at a fixed location along the airfoil. The large universe of airfoils encountered in various applications causes additional difficulties. As such, we provide further insights on selecting training datasets from large amounts of available data.