Optimization of density and surface morphology of SS 316L/IN718 functionally graded thin-walled structures using hybrid prediction-multi-objective optimization method

During the process of using directed energy deposition (DED) to prepare functionally graded material (FGM), there is a coupling problem involving multiple materials and parameters. The generation of intermetallic compounds and mismatched thermal property parameters often leads to the occurrence of defects such as pores and cracks at the microscopic level, as well as poor surface quality at the macroscopic level. In response to the issues, a hybrid prediction-multi-objective optimization method is proposed for the process parameter optimization of DED-fabricated thin-walled structures with SS 316 L/IN718 FGM. The aim is to achieve optimal density and surface morphology. The study investigates the influence of process parameters on the density and surface morphology of SS 316 L/IN718 functionally graded thin-walled structures during the preparation process and analyzes the reasons for defect generation and surface morphology changes. Based on the results, it can be inferred that interlayer lifting has the most prominent impact on density. The density first increases and then decreases as interlayer lifting increases. On the other hand, scan speed has a significant effect on surface morphology, with an increase leading to a decrease in surface roughness. The presence of ceramic oxides and intermetallic compounds in gradient materials induces cracking, and the accumulation of Nb- and Mo-rich phases, as well as columnar to equiaxed transition (CET), causes thermal stress and residual stress concentration, leading to the expansion of defects. Hybrid prediction-multi-objective optimization achieved optimal density and surface roughness of 8001 kg/m³ and 180.96 μm, respectively. The model's reliability was validated experimentally.