AI-assisted design of 3D NPR lattice materials with programmable mechanical properties using irregular unit cells

Area of Science:

• Materials Science and Engineering
• Computational Materials Design
• Metamaterials

Background:

• Lattice materials with negative Poisson's ratios (NPR) offer unique mechanical properties.
• Traditional periodic lattice designs limit anisotropic potential; irregular architectures present design challenges.
• Optimizing irregular lattice cell geometry for specific metamaterial properties is complex.

Purpose of the Study:

• To develop an AI-driven framework for optimizing anisotropic negative Poisson's ratio (NPR) and energy absorption in irregular 3D lattice cells.
• To enable the inverse design of 3D lattice metamaterials with tailored mechanical responses.

Main Methods:

• Utilized a hybrid AI approach combining deep neural networks and genetic algorithms for parametric optimization.
• Fabricated optimized irregular 3D lattice cells using microscale and macroscale 3D printing.
• Conducted in situ and quasi-static compression tests, alongside micro-Digital Image Correlation (DIC) analysis.

Main Results:

• Successfully validated programmable negative Poisson's ratio (NPR) effects across diverse materials and scales.
• Identified strain localization patterns and critical buckling instabilities governing deformation in compressed architectures.
• Demonstrated inverse design capability for irregular unit cell-based metamaterials.

Conclusions:

• The AI framework effectively optimizes anisotropic NPR and energy absorption in irregular 3D lattice metamaterials.
• Experimental validation confirms the programmable mechanical properties and provides insights into deformation mechanisms.
• This approach opens new avenues for designing advanced materials for lightweight structures and energy absorption applications.