Control co-design of a slender structure in high-speed flow via fast multiobjective Bayesian optimization

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The control co-design of a slender structure in high-speed (supersonic to hypersonic) flows involves the simultaneous optimization of multiple objectives, namely, structural mass and control effort. To make this optimization sample-efficient, we consider multiobjective Bayesian optimization (MOBO) which places a Gaussian process prior on the objectives followed by sequentially updating the posterior GP in a goal-oriented fashion via Bayesian decision theory. Conventional MOBO, however, involves an "inner" optimization of an intractable "acquisition" function, which can in some cases be a non-trivial computational overhead, in addition to being hard to solve. Inability to solve this inner optimization accurately causes MOBO to be not sample efficient. In this work, we solve the control co-design problem, via a novel, "acquisition-free", MOBO approach called Pareto optimal Thompson sampling (qPOTS). qPOTS is revolutionary in the sense that new candidate(s) are chosen from the Pareto frontier of random GP posterior sample paths obtained by solving a much cheaper multiobjective optimization problem, instead of solving a potentially nonconvex, nonsmooth, and/or stochastic inner optimization. We demonstrate the superior performance of qPOTS compared to the state-of-the-art on several synthetic test functions as well as the control co-design problem.

Original languageEnglish (US)
Title of host publicationAIAA Aviation Forum and ASCEND, 2024
PublisherAmerican Institute of Aeronautics and Astronautics Inc, AIAA
ISBN (Print)9781624107160
DOIs
StatePublished - 2024
EventAIAA Aviation Forum and ASCEND, 2024 - Las Vegas, United States
Duration: Jul 29 2024Aug 2 2024

Publication series

NameAIAA Aviation Forum and ASCEND, 2024

Conference

ConferenceAIAA Aviation Forum and ASCEND, 2024
Country/TerritoryUnited States
CityLas Vegas
Period7/29/248/2/24

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Nuclear Energy and Engineering
  • Aerospace Engineering
  • Space and Planetary Science

Fingerprint

Dive into the research topics of 'Control co-design of a slender structure in high-speed flow via fast multiobjective Bayesian optimization'. Together they form a unique fingerprint.

Cite this