Advanced Manufacturing Configuration by Sample-Efficient Batch Bayesian Optimization
Abstract
We propose a framework for the configuration and operation of expensive-to-evaluate advanced manufacturing methods, based on Bayesian optimization. The framework unifies a tailored acquisition function, a parallel acquisition procedure, and the integration of process information providing context to the optimization procedure. The novel acquisition function is demonstrated, analyzed and compared on state-of-the-art bench-marking problems. We apply the optimization approach to atmospheric plasma spraying and fused deposition modeling. Our results demonstrate that the proposed framework can efficiently find input parameters that produce the desired outcome and minimize the process cost. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000575936Publication status
publishedExternal links
Journal / series
IEEE Robotics and Automation LettersVolume
Pages / Article No.
Publisher
IEEESubject
Bayesian optimization; intelligent and flexible manufacturing; machine learning for control; probability and statistical methods; process controlOrganisational unit
03751 - Lygeros, John / Lygeros, John
Funding
180545 - NCCR Automation (phase I) (SNF)
More
Show all metadata