Process–Design Co-Optimisation of Laser Powder Bed Fusion Titanium Gyroid Lattices via Deep Learning

Laser powder bed fusion (LPBF) enables controlled gyroid lattices, but mapping process and design together to performance remains challenging when datasets are small and interactions are nonlinear. In this study, data-driven models that link energy density and lattice geometry to Young’s modulus and yield strength were established for sheet and network gyroid architectures. To stabilise small-data learning, stacked-autoencoder pretraining was benchmarked against greedy layer-wise pretraining. Compression characterisation data at under-represented energy-density conditions were added to fill data gaps and validate predictions. The models support property-driven design in which given modulus and yield strength targets the method returns feasible combinations of laser powder bed fusion settings and gyroid density and size. Pretrained models reduced error and captured the relationship between stiffness and density and between strength and density, with yield strength prediction errors of 3.51 % for sheet architectures and 8.76 % for network architectures. Young’s modulus showed higher variability that is consistent with sensitivities in LPBF such as surface roughness and thin walls. This work contributes an artificial intelligence method for manufacturing datasets using stacked autoencoder pretraining with fine-tuning, and an inverse design workflow that maps energy density and gyroid geometry to Young’s modulus and yield strength in titanium lattices.