Many-objective optimization of build part orientation in additive manufacturing
Marina A. Matos, Ana Maria A. C. Rocha, Lino Costa
Abstract
Additive manufacturing is the process of building a three-dimensional object from a computer-aided design model, by successively adding material layer-by-layer. This technology allows to print complex shape objects and is being rapidly adopted throughout the aircraft industry, medical implants, jewelry, footwear industry, automotive industry, and fashion products. The build orientation of 3D objects has a strong influence on many quality characteristics. In this paper, a many-objective approach is applied to the Fin model, using the NSGA-II algorithm to optimize four conflicting objective functions regarding the need for support structures, the build time, the surface roughness, and the overall quality of the surface. First, a bi-objective optimization is performed for each couple of two objectives and some representative solutions are identified. However, when applying many-objective optimization to the four objective functions simultaneously, some more orientation angles are found as good optimal solutions. Visualization tools are used to inspect the relationships and the trade-offs between the objectives. Then, the decision-maker can choose which orientation angles are more favorable according to his/her preferences. The optimal solutions found confirmed the effectiveness of the proposed approach.