Vision-based real-time molten pool monitoring for Electron Beam Freeform Fabrication.

In the additive manufacturing process, the molten pool contains abundant information related to the deposition quality and stability. Real-time monitoring and feature extraction of the molten pool is of great significance for closed-loop control of molten pool and guarantee of consistency and stability of the deposition process. In this study, we develop a visual monitoring system of molten pool for electron beam freeform fabrication(EBF ³ ) and propose corresponding digital image processing algorithms to extract molten pool geometric and identify the wire position and metal transfer state of the deposition. The effectiveness of the proposed algorithm is verified by deposition experiments under different beam currents and different metal transfer states, and the transfer function model between the molten pool feature and the energy input is established by step response experiments. The proposed molten pool visual monitoring method and model identification work provide the foundation for the closed-loop control of the molten pool.