Wire-arc additive manufacturing (WAAM) is an advanced technique for fabricating large metal components through layer-by-layer material deposition using arc welding methods. This study focused on optimizing the WAAM process by employing machine learning models to predict and control bead geometries, specifically bead height (BH) and bead width (BW), while ensuring consistent height increments in multibead walls. Based on CMT technology in cold metal transfer experiments, linear regression models achieved high accuracy in predicting BH and BW. Analysis of variance results highlighted the considerable influence of voltage (V) and travel speed (TS) on bead geometries. For multibead wall characteristics, polynomial regression models incorporating non-linear terms, such as travel speed (TS²) and dwell time (Dt²), were developed to predict height (H) and waviness (W). Various optimization metrics were employed to balance the trade-offs between H and W for identifying optimal welding conditions that achieved the target H while minimizing W. A notable innovation of this research is the optimization of dwell time (Dt) for each layer to achieve a linear incremental H profile, minimizing W and ensuring consistent layer quality.

Additive manufacturing (AM) processes are now integrated in industry. Therefore, new methods to design AM parts taken into consideration capabilities and limitations are necessary. It is very difficult for teachers to effectively guide students with ideas emerging from generative design tools. AM requires significant preparation and compromises. Topological optimization is also used depending on requirements. A significant impact on the final part quality is related to the part orientation and geometric dimensions. Therefore, this white paper focuses on detailed design steps to prepare future technicians and engineers to design for additive manufacturing. Active teaching pedagogy guideline is proposed. Students have to think in 3D and use analysis tools to create and validate the optimised design. They use immersive tools to review constraints and model diagnostic algorithm to generate data. Present approaches with design guidelines and tools enable to create AM rules based on it. Questionnaire shows that students need explicit knowledge information. Features recognition and geometry diagnostic are mandatory for complex model. Immersive tool helps to evaluate post-processing. They can now relate AM product-process relationship.