Plasma Spray Process Parameters Configuration using Sample-efficient Batch Bayesian Optimization

TL;DR

This paper presents a sample-efficient batch Bayesian optimization method tailored for industrial plasma spray process parameter tuning, incorporating parallel acquisition and equipment-adaptive algorithms to improve efficiency and reproducibility.

Contribution

It introduces a novel parallel acquisition procedure and an adaptive algorithm for process optimization, enhancing efficiency and reproducibility in complex manufacturing settings.

Findings

Efficiently finds process parameters that meet desired outcomes.

Reduces process cost through optimized parameter selection.

Validated both numerically and experimentally.

Abstract

Recent work has shown constrained Bayesian optimization to be a powerful technique for the optimization of industrial processes. In complex manufacturing processes, the possibility to run extensive sequences of experiments with the goal of finding good process parameters is severely limited by the time required for quality evaluation of the produced parts. To accelerate the process parameter optimization, we introduce a parallel acquisition procedure tailored on the process characteristics. We further propose an algorithm that adapts to equipment status to improve run-to-run reproducibility. We validate our optimization method numerically and experimentally, and demonstrate that it can efficiently find input parameters that produce the desired outcome and minimize the process cost.