Maximum-Projection-Based Bayesian Optimization Utilizing Sensitivity Analysis for High-Efficiency Radial Turbine Design with Scarce Data
This work addresses data-efficient design optimization for high-cost engineering applications like turbines, though it is incremental in combining existing methods.
The authors tackled the problem of optimizing radial turbine efficiency under a limited budget of high-fidelity simulations, achieving an increase from 85.77% to 91.77% using only 330 simulations.
We propose a data-efficient workflow to optimize the efficiency of a radial turbine design under a strict budget of high-fidelity computational fluid dynamics simulations. Assuming anisotropic parameter impact, we use a maximum-projection initial experimental design to ensure space-filling and strong projection properties on low-dimensional subspaces. Bayesian optimization is performed using Gaussian process surrogates with an upper confidence bound acquisition function. In parallel, polynomial chaos expansions provide variance-based global sensitivity analysis metrics, which allow to identify a reduced subspace with the most influential parameters, wherein the optimization is continued. Turbine efficiency is increased from 85.77% initially to 91.77% at the end of the workflow, with a total budget of 330 simulations.