Multi-Fidelity Bayesian Neural Network for Uncertainty Quantification in Transonic Aerodynamic Loads

TL;DR

This paper introduces a multi-fidelity Bayesian neural network that effectively combines low- and high-fidelity data for uncertainty quantification in transonic aerodynamic load predictions, outperforming traditional methods.

Contribution

It presents a novel transfer learning approach within Bayesian neural networks to fuse multi-fidelity data, enhancing accuracy and uncertainty estimation in aerospace applications.

Findings

Outperforms Co-Kriging in accuracy and robustness

Provides reliable uncertainty estimates

Efficiently fuses multi-fidelity data

Abstract

Multi-fidelity models are becoming more prevalent in engineering, particularly in aerospace, as they combine both the computational efficiency of low-fidelity models with the high accuracy of higher-fidelity simulations. Various state-of-the-art techniques exist for fusing data from different fidelity sources, including Co-Kriging and transfer learning in neural networks. This paper aims to implement a multi-fidelity Bayesian neural network model that applies transfer learning to fuse data generated by models at different fidelities. Bayesian neural networks use probability distributions over network weights, enabling them to provide predictions along with estimates of their confidence. This approach harnesses the predictive and data fusion capabilities of neural networks while also quantifying uncertainty. The results demonstrate that the multi-fidelity Bayesian model outperforms the state-of-the-art Co-Kriging in terms of overall accuracy and robustness on unseen data.