Optimization-Embedded Active Multi-Fidelity Surrogate Learning for Multi-Condition Airfoil Shape Optimization

2026-03-17

AI Summary

This work addresses the high computational cost of high-fidelity CFD simulations in multi-condition airfoil optimization by proposing an active multi-fidelity surrogate modeling framework. The approach integrates low-fidelity XFOIL and high-fidelity RANS data within a hybrid genetic algorithm, employing uncertainty-triggered sampling and a synchronous elite validation mechanism to dynamically re-evaluate population fitness. This strategy mitigates erroneous selections caused by overreliance on outdated surrogates and enables independent refinement of surrogates for each operating condition. Coupled with CST parameterization and transfer Gaussian process regression, the method achieves a 41.05% improvement in cruise efficiency and a 20.75% increase in takeoff lift coefficient while requiring only 14.78% (cruise) and 9.5% (takeoff) of the high-fidelity evaluations typically needed, thereby striking an effective balance between optimization efficiency and accuracy.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Constraint Optimization
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Active multi-fidelity surrogate modeling is developed for multi-condition airfoil shape optimization to reduce high-fidelity CFD cost while retaining RANS-level accuracy. The framework couples a low-fidelity-informed Gaussian process regression transfer model with uncertainty-triggered sampling and a synchronized elitism rule embedded in a hybrid genetic algorithm. Low-fidelity XFOIL evaluations provide inexpensive features, while sparse RANS simulations are adaptively allocated when predictive uncertainty exceeds a threshold; elite candidates are mandatorily validated at high fidelity, and the population is re-evaluated to prevent evolutionary selection based on outdated fitness values produced by earlier surrogate states. The method is demonstrated for a two-point problem at $Re=6\times10^6$ with cruise at $α=2^\circ$ (maximize $E=L/D$) and take-off at $α=10^\circ$ (maximize $C_L$) using a 12-parameter CST representation. Independent multi-fidelity surrogates per flight condition enable decoupled refinement. The optimized design improves cruise efficiency by 41.05% and take-off lift by 20.75% relative to the best first-generation individual. Over the full campaign, only 14.78% (cruise) and 9.5% (take-off) of evaluated individuals require RANS, indicating a substantial reduction in high-fidelity usage while maintaining consistent multi-point performance.

Problem

• multi-fidelity surrogate
• airfoil shape optimization
• high-fidelity CFD cost
• multi-condition optimization
• computational efficiency

Innovation

• multi-fidelity surrogate
• active learning
• airfoil optimization
• uncertainty-triggered sampling
• embedded elitism