Edge-Focused WAAM for Optimizing the Bending Strength of 3D-Printed Metal Parts: Experiments, Neural Network Prediction, and Genetic Optimization

This research presents edge-focused wire arc additive manufacturing (edge-focused WAAM), a new method for optimizing the bending strength of 3D-printed metal parts through joining layers along the edge of preformed metal plates. The test samples were manufactured and tested via the Taguchi L25 design, achieving a maximum bending strength of 3338.11 MPa, which was 171% greater than that of the original CT38 steel (1231.5 MPa). An artificial neural network (ANN) was deployed to predict the entire stress‒strain curve, and it reached a correlation coefficient R > 0.95, which is better than methods that predict only the maximum stress. The welding parameters, including the current intensity, path offset, moving angle, traveling speed, and layer thickness, were optimized via the Taguchi method and genetic algorithm (GA), identifying ideal conditions for enhancing the mechanical performance. The results show that edge-focused WAAM reduces thermal distortion and improves strength because of the plate structure, opening potential applications in the aviation, automotive, and energy sectors, with the ability to produce durable, light, and precise components