Multi-objective Optimization of 316L Stainless Steel SLM Forming based on Genetic Algorithm

To address the multi-objective optimization of density and microhardness in 316L stainless steel formed parts produced by selective laser melting (SLM) technology, this study employs an orthogonal experiment combined with genetic algorithms. By designing a three-factor, three-level orthogonal experiment, the effects of laser power, scanning speed, and scanning spacing on the density and microhardness of the formed parts were analyzed. The significance of each parameter was determined using the range analysis method. Based on the experimental data, a cubic polynomial regression equation was established as the fitness function, and an optimization model aimed at achieving high density and high microhardness was constructed. The Pareto optimal solution set was found using genetic algorithms. The results indicate that laser power has the most significant impact on both indicators. The optimized parameter combination (scanning speed 640mm/s to 650mm/s, laser power 190 W, scanning spacing 0.08 mm) achieves a density of 97.26% to 97.78% and a microhardness of 250.6 HV to 251.6 HV, showing a significant improvement over the orthogonal experiment results. This validates the effectiveness of genetic algorithms in multi-objective optimization of SLM forming parameters.