A scalable composite Bayesian optimization framework for engineering design using deep learning reduced-order models

doi:10.1016/j.jocs.2025.102722

A scalable composite Bayesian optimization framework for engineering design using deep learning reduced-order models

2025-10-04

0

PRE

AI

DOI：10.1016/j.jocs.2025.102722

Original

Original request for help

Save

Abstract

En 中文

• Novel Bayesian optimization method using deep learning reduced-order models. • Method demonstrated on complex airfoil design problem and synthetic problems. • Neural network-based methods provide significant improvement in performance. • Extended to high-dimensional design spaces for complex engineering design.

A scalable composite Bayesian optimization framework for engineering design using deep learning reduced-order models

Abstract

Journal

Organization