A Review on the Development of Data Driven Aerodynamic Optimization Design Technology for Airfoils
Traditional airfoil optimization generally relies on Computational Fluid Dynamics (CFD) simulations to build aerodynamic models for prediction and combines them with optimization algorithms. However, CFD computations are often computationally expensive and time-consuming, failing to meet the demands of modern aircraft design. In recent years, data-driven methods have gradually been introduced into aerodynamic design, offering new pathways to reduce dependence on expensive CFD calculations and improve airfoil optimization efficiency. This paper reviews research progress in data-driven airfoil aerodynamic optimization, focusing on applications of traditional surrogate models, deep learning models, and intelligent optimization algorithms for aerodynamic performance prediction and optimization. It also analyzes current challenges in data-driven airfoil optimization, including the high cost of acquiring training data, insufficient model interpretability, limited physical consistency constraints, and inadequate generalization across multiple operating conditions. On this basis, this paper discusses future development directions such as multi-fidelity data fusion, Physics-Informed Neural Networks (PINNs), and AI-CFD collaborative optimization, aiming to provide references for further application of data-driven methods in airfoil aerodynamic optimization design.
Authors
- Ziming Xu
Institutions
- University of Birmingham (GB)
Publication Details
- Journal
- Applied and Computational Engineering
- Published
- 2026-11-17
- DOI
- https://doi.org/10.54254/2755-2721/2026.39161
- Primary Topic
- Advanced Multi-Objective Optimization Algorithms
- Type
- article
- Field-Weighted Citation Impact
- 0.00