Data-Driven Nonlinear Deformation Design of 3D-Printable Shells
This work addresses the problem of designing custom mechanical structures for applications requiring precise nonlinear deformations, representing an incremental advance by applying data-driven methods to a domain-specific challenge.
The authors tackled the challenge of designing 3D-printable shells with specific mechanical properties, particularly for nonlinear deformations like elastoplastic and hyperelastic behaviors, by training a neural network on thousands of physical experiments to learn the design-performance relationship, enabling both forward and inverse design and validating generated designs through fabrication and testing.
Designing and fabricating structures with specific mechanical properties requires understanding the intricate relationship between design parameters and performance. Understanding the design-performance relationship becomes increasingly complicated for nonlinear deformations. Though successful at modeling elastic deformations, simulation-based techniques struggle to model large elastoplastic deformations exhibiting plasticity and densification. We propose a neural network trained on experimental data to learn the design-performance relationship between 3D-printable shells and their compressive force-displacement behavior. Trained on thousands of physical experiments, our network aids in both forward and inverse design to generate shells exhibiting desired elastoplastic and hyperelastic deformations. We validate a subset of generated designs through fabrication and testing. Furthermore, we demonstrate the network's inverse design efficacy in generating custom shells for several applications.