Signal-Aware Conditional Diffusion Surrogates for Transonic Wing Pressure Prediction

TL;DR

This paper introduces a signal-aware conditional diffusion model for predicting transonic wing pressure distributions, improving accuracy over deterministic models by capturing sharp nonlinear features and providing reliability diagnostics.

Contribution

It develops a novel diffusion-based surrogate model that operates on unstructured data with a principal component representation and a signal-aware training objective.

Findings

Reduces mean absolute error compared to deterministic baselines.

Improves reconstruction of shock structures and pressure peaks.

Provides diagnostic metrics correlating sampling spread with error.

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.