An efficient application of Bayesian optimization to an industrial MDO framework for aircraft design

TL;DR

This paper demonstrates how a constrained Bayesian optimization method can significantly reduce computational effort in multi-disciplinary aircraft design optimization, outperforming traditional optimizers within an industrial framework.

Contribution

It introduces the application of a super efficient global optimization with mixture of experts to aircraft design, enhancing efficiency over existing Isight optimizers.

Findings

Significant reduction in computational effort achieved.

Outperforms two popular Isight optimizers.

Validated on Bombardier aircraft configuration cases.

Abstract

The multi-level, multi-disciplinary and multi-fidelity optimization framework developed at Bombardier Aviation has shown great results to explore efficient and competitive aircraft configurations. This optimization framework has been developed within the Isight software, the latter offers a set of ready-to-use optimizers. Unfortunately, the computational effort required by the Isight optimizers can be prohibitive with respect to the requirements of an industrial context. In this paper, a constrained Bayesian optimization optimizer, namely the super efficient global optimization with mixture of experts, is used to reduce the optimization computational effort. The obtained results showed significant improvements compared to two of the popular Isight optimizers. The capabilities of the tested constrained Bayesian optimization solver are demonstrated on Bombardier research aircraft configuration study cases.