Page 22 - IJAMD-2-2

International Journal of AI for
Materials and Design AI-driven material development for AM

Extending this approach to multi-material systems, In addition to mechanical performance, AI has been
He et al. integrated GA with multi-material-inkjet 3D applied to enhance the biofunctional properties of polymeric
91
printing (MM-IJ3DP) and voxel-level finite element AM materials. In bioprinting applications, optimizing
99
modeling. The GA served as a global search tool to explore process parameters can improve biocompatibility and
the vast design space, enabling customizable stiffness cell viability, while in medical implants and antimicrobial
gradients and improved biofilm resistance. As illustrated materials development, tailoring surface properties
in Figure 10, their framework integrates MM-IJ3DP with can reduce bacterial adhesion and mitigate infection
FEA and GA to tailor material properties at the voxel level. risks. Magennis et al. utilized high-throughput
100
Experimental validation confirmed that their approach screening to identify polymeric materials capable of
enables the fabrication of customizable polymer composites effectively resisting bacterial attachment, presenting
with tunable stiffness and enhanced biofilm resistance, new opportunities for biomedical AM. Figure 11 shows
demonstrating the potential of AI in multifunctional that their study systematically analyzed the relationship
material optimization. between polymer chemistry and bacterial adhesion by

Figure 9. Bayesian machine learning framework for the design of super-compressible metamaterials in brittle polymers. Reproduced from Bessa et al. 84
A B C

D

E F
G

Figure 10. Artificial intelligence-driven generative design framework for multi-material 3D-printed composites. Reproduced from He et al. 91
Abbreviation: FEA: Finite element analysis.

Volume 2 Issue 2 (2025) 16 doi: 10.36922/IJAMD025100007