This study developed a new metallography–property relationship neural network (MPR-Net) to predict the relationship between the microstructure and mechanical properties of 316L stainless steel built by laser powder bed fusion (LPBF). The accuracy R² of MPR-Net was 0.96 and 0.91 for tensile strength and Vickers hardness predictions, respectively, based on optical metallurgy images. Feature visualisation methods, such as gradient-weighted class activation mapping (Grad-CAM) and clustering, were employed to interpret the abstract features within the MPR-Net, providing insights into the molten pool morphology and grain formation mechanisms during the LPBF process. Experimental results showed that the optimal process parameters—190 W laser power and 700 mm/s scanning speed—yielded a maximum tensile strength of 762.83 MPa and a Vickers hardness of 253.07 HV_0.2 with nearly full densification (99.97%). The study marks the first application of a convolutional neural network (MPR-Net) to predict the mechanical properties of 316L stainless steel samples manufactured through laser powder bed fusion (LPBF) based on metallography. It innovatively employs techniques such as gradient-weighted class activation mapping (Grad-CAM), spatial coherence testing, and clustering to provide deeper insights into the workings of the machine learning model, enhancing the interpretability of complex neural network decisions in material science.

Laser powder bed fusion (LPBF) is an advanced additive manufacturing technology that is gaining increasing interest for biomedical implants because it can produce dense, patient-specific metallic components with controlled microstructures. This study investigated the LPBF fabrication of 316L stainless steel, which is widely used in orthopedic and dental implants, and examined the effects of laser power and scanning speed on the microstructure and mechanical properties relevant to biomedical applications. The study achieved 99.97% density and refined columnar and cellular austenitic grains, with optimized molten pool morphology. The optimal LPBF parameters, 190 W laser power and 700 mm/s, produced a tensile strength of 762.83 MPa and hardness of 253.07 HV_0.2, which exceeded the values of conventional cast 316L stainless steel. These results demonstrated the potential of optimized LPBF 316L stainless steel for functional biomedical applications that require high mechanical integrity and biocompatibility.

The influence of organic solvents on the structural integrity and properties of activated kaolinite were compared and analyzed via characterization techniques and molecular dynamics (MD) simulation. The results revealed that the organic intercalators can be easily inserted into the interlayer spaces of activated kaolinite within a short time of the wet ball milling. The DMSO intercalated kaolinites maintained structural integrity due to the high intercalation rate and the excellent buffering effect against the crushing force of milling during the delamination/exfoliation process. The delaminated layers of the DMSO–kaolinite complex exhibited a high specific surface area of 99.12 m²/g and a low average thickness of 35.21 nm. The calculated elastic properties of the organo-kaolinite complex manifested the intercalation of DMSO into a kaolinite interlayer, which could improve the compressibility and structural integrity of kaolinite nanosheets. The DMSO–kaolinite complex was easier to peel off when compared to the other organic intercalators due to its more intercalated molecules.