Data-informed lifting line theory

TL;DR

This paper introduces a neural network-enhanced lifting-line theory that incorporates high-fidelity aerodynamic data to improve predictions across a broader range of wing configurations while maintaining computational efficiency.

Contribution

It develops a data-driven framework that extends classical lifting-line theory with neural networks, capturing complex aerodynamic effects beyond traditional limits.

Findings

The neural network model accurately predicts spanwise lift and drag in regimes where LLT fails.

The approach generalizes well to unseen wing configurations outside the training data.

The method retains LLT's efficiency, suitable for optimization and early design stages.

Abstract

We present a data-driven framework that extends the predictive capability of classical lifting-line theory (LLT) to a wider aerodynamic regime by incorporating higher-fidelity aerodynamic data from panel method simulations. A neural network architecture with a convolutional layer followed by fully connected layers is developed, comprising two parallel subnetworks to separately process spanwise collocation points and global geometric/aerodynamic inputs such as angle of attack, chord, twist, airfoil distribution, and sweep. Among several configurations tested, this architecture is most effective in learning corrections to LLT outputs. The trained model captures higher-order three-dimensional effects in spanwise lift and drag distributions in regimes where LLT is inaccurate, such as low aspect ratios and high sweep, and generalizes well to wing configurations outside both the LLT regime and the training data range. The method retains LLT's computational efficiency, enabling integration into aerodynamic optimization loops and early-stage aircraft design studies. This approach offers a practical path for embedding high-fidelity corrections into low-order methods and may be extended to other aerodynamic prediction tasks, such as propeller performance.