Benchmarking machine learning models for predicting aerofoil performance

2025-04-22

AI Summary

This study addresses the speed–accuracy trade-off inherent in conventional methods for airfoil aerodynamic performance prediction in wind and tidal energy applications. We introduce the first renewable-energy-specific airfoil benchmark—integrating NREL’s windAI_bench and AirfRANS—and systematically evaluate four model families—MLP, PointNet, GraphSAGE, and GUNet—for predicting flow fields and lift coefficients ($C_L$) across 25 angles of attack. Notably, this work presents the first comparative analysis of geometry-aware graph neural networks versus fully connected models in this domain. Results show PointNet achieves the highest $C_L$ prediction accuracy (mean relative error < 3.2%), while MLP exhibits superior generalization for flow-field modeling. Both models deliver over 100× faster inference than traditional CFD-based approaches, effectively breaking the long-standing accuracy–efficiency bottleneck in airfoil performance prediction for renewable energy systems.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

This paper investigates the capability of Neural Networks (NNs) as alternatives to the traditional methods to analyse the performance of aerofoils used in the wind and tidal energy industry. The current methods used to assess the characteristic lift and drag coefficients include Computational Fluid Dynamics (CFD), thin aerofoil and panel methods, all face trade-offs between computational speed and the accuracy of the results and as such NNs have been investigated as an alternative with the aim that it would perform both quickly and accurately. As such, this paper provides a benchmark for the windAI_bench dataset published by the National Renewable Energy Laboratory (NREL) in the USA. In order to validate the methodology of the benchmarking, the AirfRANS { t arXiv:2212.07564v3} dataset is used as both a starting point and a point of comparison. This study evaluates four neural networks (MLP, PointNet, GraphSAGE, GUNet) trained on a range aerofoils at 25 angles of attack (4$^circ$ to 20$^circ$). to predict fluid flow and calculate lift coefficients ($C_L$) via the panel method. GraphSAGE and GUNet performed well during the testing phase, but underperformed during validation. Accordingly, this paper has identified PointNet and MLP as the two strongest models tested, however whilst the results from MLP are more commonly correct for predicting the behaviour of the fluid, the results from PointNet provide the more accurate results for calculating $C_L$.

Problem

• Evaluating Neural Networks for aerofoil performance prediction
• Comparing NN models to traditional CFD methods for speed and accuracy
• Benchmarking windAI_bench dataset to identify optimal NN models

Innovation

• Neural Networks replace traditional aerofoil analysis methods
• Benchmarking windAI_bench dataset for performance prediction
• PointNet and MLP excel in fluid behavior prediction