| Abstract Scope |
Laser powder bed fusion (L-PBF), which is one of the representative metal additive manufacturing, enables the fabrication of complex-shaped metallic part including lattice structures. The lattice structure can be applied for lightweight components, shock energy absorbers, and heat sinks. It is essential to design the lattice structures for each application. In addition, the microstructure and related properties of the L-PBF-built metallic components are significantly affected by the processing conditions including laser power, scan speed, and spot size. It is essential to efficiently optimize the process parameters for obtaining desired microstructures and properties. Machine-learning approaches are effective for the design of lattice structures and the optimization of the process parameters. In this presentation, the machine learning approaches to efficiently optimize the process parameters for controlling the microstructure of L-PBF-built WC/Co composites and to rapidly predict the heat transfer properties of lattice-structured heat sinks are introduced. |