Aerodynamic force reconstruction using physics-informed Gaussian processes

2026-05-21

AI Summary

Accurately modeling aerodynamic loads is crucial for reliable structural response prediction, yet conventional approaches rely on simplifying assumptions and struggle to validate effectively under noisy or incomplete data conditions. This work proposes a probabilistic physics-informed machine learning framework that embeds the linear unsteady aerodynamic hypothesis as a prior within a Gaussian process, enabling robust reconstruction of true aerodynamic loads directly from noisy structural responses—without requiring explicit regularization and inherently supporting heterogeneous multi-fidelity data fusion. Validated on the Great Belt East Bridge case study, the reconstructed loads exhibit excellent agreement with ground-truth measurements in terms of root-mean-square error, amplitude, phase, and peak values, demonstrating the method’s accuracy, robustness, and generalization capability.

Abstract

Accurate modeling of aerodynamic loads is essential for understanding and predicting the responses of complex structural systems. However, these models often rely on simplifications of the true physical forces, introducing assumptions that can limit their accuracy. Validating such models becomes particularly challenging in the presence of noisy or incomplete data. To address this, we introduce a probabilistic physics-informed machine learning approach designed to reconstruct the underlying aerodynamic loads from noisy measurements of structural dynamic responses. The model avoids overfitting, eliminates the need for regularization schemes, and allows for the use of heterogeneous and multi-fidelity data during the training process. The efficacy of the approach is demonstrated through the reconstruction of aerodynamic loads on the Great Belt East Bridge, simulated under a linear unsteady assumption. Results show a strong agreement between true and predicted loads, particularly related to root mean squared errors, magnitude, phase angle and peak values of the signals. The method for load reconstructing holds broad applicability, such as modeling validation, future load estimation, and structural damage prognosis.

Problem

• aerodynamic force reconstruction
• noisy data
• structural dynamic responses
• model validation
• multi-fidelity data

Innovation

• physics-informed machine learning
• Gaussian processes
• aerodynamic force reconstruction
• multi-fidelity data
• structural dynamics