Machine learning-based Optimization for Molten pool Dynamics in Laser Manufacturing

This study employs machine learning to analyze and predict the influence of process parameters on molten pool dynamics in hybrid Laser-MIG welding of aluminum alloys. A comprehensive numerical model simulates thermal dynamics, in corporating multiple reflection, Fresnel absorption, and laser-arc synergy. Key parameters such as temperature field, flow field, element distribution, and solidification behavior are evaluated. Results show that scanning speed significantly impacts molten pool dynamics, affecting temperature, liquid velocity, penetration, and magnesium distribution. Machine learning extracts patterns from simulations, enabling parameter optimization for improved weld quality.