Bead Geometry Prediction in Laser-Wire Additive Manufacturing Process Using Machine Learning: Case of Study

In Laser Wire Additive Manufacturing (LWAM), the final geometry is produced using layer-by-layer deposition (beads principle). To achieve good geometrical accuracy in product, proper implementation of bead essential. For this reason, paper focuses on process and proposes a layer (width height) prediction model to improve accuracy. More specifically, machine learning regression algorithm applied several experimental data predict across layers. Furthermore, neural network-based approach was used study influence different parameters, namely laser power, wire-feed rate travel speed geometry. validate effectiveness proposed approach, test split validation strategy train models. The results show particular evolutionary trend confirm that parameters have direct geometry, so, too, part. Several been found obtain an accurate with low errors deposition. Finally, indicates can efficiently be could help later designing controller LWAM process.