In-situ Controller Autotuning by Bayesian Optimization for Closed-loop Feedback Control of Laser Powder Bed Fusion Process
Baris Kavas, Efe C. Balta, Michael R. Tucker, Raamadaas Krishnadas, Alisa Rupenyan, John Lygeros, Markus Bambach
TL;DR
This work tackles how to stabilize the LPBF melt pool under layer-wise heating disturbances by automating in-layer PI control parameter tuning. It applies Bayesian Optimization, modeling a composite cost function that combines pyrometer tracking error, rise time, and laser power variability, using Gaussian Processes and a Lower Confidence Bound acquisition. The approach is demonstrated in online (powder) and offline (plate) settings on wedge geometries, showing that BO can efficiently converge to effective $K_p$ and $K_i$ values, significantly reducing overheating compared with uncontrolled prints. A key finding is that maintaining the laser within the process window is essential to avoid porosity, emphasizing the need for adaptable reference values and potential enhancements (e.g., D-term, cooling strategies) for robust, region-specific in-layer control in LPBF.
Abstract
Open-loop control of laser powder bed fusion (LPBF) additive manufacturing (AM) has enabled the production of complex, high-criticality parts for various industries. This method relies on static parameter sets from extensive experimentation and simulations, hoping they remain stable and defect-free in production. Closed-loop control of LPBF can further enhance process stability and reduce defects despite complex thermal histories, process noise, hardware drift, and unexpected perturbations. Controller performance depends on parameter tuning, traditionally a manual, expertise-driven process with no guarantee of optimal performance and limited transferability between systems. This study proposes Bayesian Optimization (BO) to automate in-layer controller tuning by leveraging LPBF's layer-to-layer repetitive nature. Two approaches are introduced: online tuning, adjusting parameters iteratively during the process, and offline tuning, conducted in a setup such as laser exposures on a bare metal plate. These methods are experimentally implemented on an in-layer PI controller, and the performance is investigated on two wedge geometries prone to overheating. Results show that BO effectively tunes controllers using either method, significantly reducing overheating in controlled wedge specimens compared to uncontrolled ones. This study presents the first printed parts controlled by an in-layer controller subjected to microstructural analysis. Findings reveal partial presence of lack-of-fusion porosities due to insufficient laser power assigned by the controller, highlighting a significant challenge for utilizing laser power controllers. In summary, BO presents a promising method for automatic in-layer controller tuning in LPBF, enhancing control precision and mitigating overheating in production parts.