Signal-Aware Conditional Diffusion Surrogates for Transonic Wing Pressure Prediction

2026-04-13

AI Summary

This work addresses the challenge that conventional deterministic surrogate models struggle to accurately capture strong nonlinear features—such as shock waves, suction peaks, and control surface discontinuities—in transonic wing pressure fields. To overcome this limitation, the authors propose a conditional denoising diffusion probabilistic model conditioned on Mach number, angle of attack, and four control surface deflection angles. The method employs principal component analysis to reversibly reparameterize unstructured surface pressure data into a linear latent space and introduces a signal-aware training objective that dynamically assigns timestep-dependent weights based on reconstruction loss, thereby enhancing fidelity in high-pressure-gradient regions. Additionally, local and global reliability indices are incorporated to qualitatively assess uncertainty by correlating sampling dispersion with reconstruction error. Experiments demonstrate that the proposed approach significantly reduces mean absolute error compared to deterministic baselines, more accurately reconstructs critical flow structures, and exhibits a strong correlation between sampling dispersion and surrogate error, effectively indicating prediction reliability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Computer Vision: Diffusion Models for Vision

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• 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
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Accurate and efficient surrogate models for aerodynamic surface pressure fields are essential for accelerating aircraft design and analysis, yet deterministic regressors trained with pointwise losses often smooth sharp nonlinear features. This work presents a conditional denoising diffusion probabilistic model for predicting surface pressure distributions on the NASA Common Research Model wing under varying conditions of Mach number, angle of attack, and four control surface deflections. The framework operates on unstructured surface data through a principal component representation used as a non-truncated, reversible linear reparameterization of the pressure field, enabling a fully connected architecture. A signal-aware training objective is derived by propagating a reconstruction loss through the diffusion process, yielding a timestep-dependent weighting that improves fidelity in regions with strong pressure gradients. The stochastic sampling process is analyzed through repeated conditional generations, and two diagnostic metrics are introduced, the Local Reliability Index and Global Reliability Index, to relate sampling-induced spread to reconstruction error. Relative to the considered deterministic baselines, the proposed formulation reduces mean absolute error and improves the reconstruction of suction peaks, shock structures, and control surface discontinuities. The sampling-induced spread exhibits strong correspondence with surrogate error, supporting its interpretation as a qualitative reliability indicator rather than calibrated uncertainty quantification.

Problem

• transonic wing
• pressure prediction
• surrogate modeling
• nonlinear features
• aerodynamic surface pressure

Innovation

• conditional diffusion model
• signal-aware training
• pressure field surrogate
• reliability index
• unstructured surface data