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 benchmarking 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.

Stress Flow Guided Non-Planar Print Trajectory Optimization for Additive Manufacturing of Anisotropic Polymers

“…It is best suited for optimization over continuous domains and tolerates stochastic noise in function evaluations [17], [18]. BO has been successfully used in a variety of applications such as machine learning [19], robotics [20], control [21], manufacturing [22], and more; [11] uses BO to tune the printing process parameters of FFF.…”

Generative and Contrastive Combined Support Sample Synthesis Model for Few-/Zero-Shot Surface Defect Recognition

“…Automated industrial production can reduce labor costs and increase productivity. Recent research has used Bayesian techniques for manufacturing methods [1] to significantly reduce the production process cost by producing input parameters for the desired outcome. Similarly, collective robotic systems for constructing multi-story buildings [2] reach state-of-theart construction speeds.…”