Document Type
Article
Publication Date
6-18-2026
Abstract
This research proposes an acquisition function for constraint boundary identification, with applications to hypersonic air vehicles. Hypersonic vehicles endure extreme thermal loads caused by aerodynamic heating, resulting in a strong coupling between structural performance and aerothermodynamics. However, modeling coupled system behaviors requires simultaneous consideration of both aerodynamic and structural design variables, increasing the dimensionality of the design trade space and the difficulty of accurately modeling the constraints. Several active learning schemes have been proposed to accelerate identification of the composite feasible region that satisfies all constraints. Some of these require integrating the surrogate model over the entire design space with each acquisition function evaluation, but this scales poorly to high-dimensional spaces. Others require only the information at the candidate sample point. In this work, we propose an acquisition function based on the Expected Magnitude of Incorrectness at the sample point. Each constraint is modeled with either Gaussian Process Regression or an ensemble of neural networks, either of which can provide the uncertainty information needed by the proposed acquisition function. Our approach performs well on analytical functions when compared to current point-based acquisition functions. Additionally, we demonstrate our method on a lift constraint problem for a hypersonic vehicle wing.
Source Publication
Structural and Multidisciplinary Optimization (ISSN 1615-147X | eISSN 1615-1488)
Recommended Citation
Beachy, A., Grandhi, R. Active learning of constraint boundaries using expected magnitude of incorrectness and neural networks. Struct Multidisc Optim 69, 165 (2026). https://doi.org/10.1007/s00158-026-04352-4
Comments
© 2026 The Authors.
This article is published by Springer, licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Sourced from the published version of record cited below.
Open Access funding provided by Air Force Research Laboratory (AFRL) Technical Libraries Consortia. This project was supported in part by an appointment to the NRC Research Associateship Program at the Air Force Institute of Technology, administered by the Fellowships Office of the National Academies of Sciences, Engineering, and Medicine. The contract number for the program is FA955024CB001.