Dataset for: "Predictive Modeling for Low-Power Direct Energy Deposition of 316L Stainless Steel

This is the dataset for the paper, we present an in-depth investigation into the optimization of processing and geometric parameters in low-power laser-directed energy deposition (DED) of 316L stainless steel, with a particular focus on achieving high structural reliability, minimal porosity, and enhanced deposition quality. Our research demonstrates how key parameters—laser power, traversing speed, powder feed rate, hatch spacing, and interlayer height—can be systematically optimized to ensure repeatability in production cycles, efficiency, and a well-characterized microstructure with microhardness comparable to or superior to forged counterparts.

Through iterative adjustments and statistical analyses, we developed predictive mathematical models that incorporate specific energy and mass per unit length, offering a robust framework for process optimization. Notably, our findings identify five optimal parameter configurations across different power levels, validated through over 150 experiments, and introduce ten equations that accurately predict bead and structural geometry in layer-by-layer fabrication.