Vector-level Feedforward Control of LPBF Melt Pool Area Using a Physics-Based Thermal Model

2025-07-16

AI Summary

Dynamic melt pool fluctuations during laser powder bed fusion (LPBF) induce defects such as porosity and geometric deviations. This work proposes a physics-informed, vector-level feedforward control framework that, for the first time, decouples macroscopic heat conduction—modeled via a lightweight finite-difference scheme—from microscopic melt pool dynamics—captured by an analytical reduced-order model. The resulting framework enables calibration-free, cross-scale, cross-material, and cross-platform melt pool regulation. Model parameters are calibrated using single-track and 2D scanning experiments, enabling high-accuracy melt pool area prediction and real-time laser power scheduling. Experimental validation on 3D components fabricated from Inconel 718 and 316L stainless steel demonstrates a 62% reduction in critical dimensional deviations, a 16.5% decrease in overall porosity, and a 6.8% reduction in the mean fluctuation of photodiode signals—directly reflecting improved melt pool stability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Low Level & Physics-based Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Laser powder bed fusion (LPBF) is an additive manufacturing technique that has gained popularity thanks to its ability to produce geometrically complex, fully dense metal parts. However, these parts are prone to internal defects and geometric inaccuracies, stemming in part from variations in the melt pool. This paper proposes a novel vector-level feedforward control framework for regulating melt pool area in LPBF. By decoupling part-scale thermal behavior from small-scale melt pool physics, the controller provides a scale-agnostic prediction of melt pool area and efficient optimization over it. This is done by operating on two coupled lightweight models: a finite-difference thermal model that efficiently captures vector-level temperature fields and a reduced-order, analytical melt pool model. Each model is calibrated separately with minimal single-track and 2D experiments, and the framework is validated on a complex 3D geometry in both Inconel 718 and 316L stainless steel. Results showed that feedforward vector-level laser power scheduling reduced geometric inaccuracy in key dimensions by 62%, overall porosity by 16.5%, and photodiode variation by 6.8% on average. Overall, this modular, data-efficient approach demonstrates that proactively compensating for known thermal effects can significantly improve part quality while remaining computationally efficient and readily extensible to other materials and machines.

Problem

• Control melt pool area in LPBF to reduce defects
• Decouple thermal behavior from melt pool physics
• Improve part quality with feedforward laser power

Innovation

• Vector-level feedforward control for LPBF
• Coupled lightweight thermal and melt models
• Data-efficient calibration with minimal experiments