Smooth Like Butter: Evaluating Multi-Lattice Transitions in Property-Augmented Latent Spaces

TL;DR

This paper evaluates a hybrid geometry/property Variational Autoencoder for designing multi-lattice transition regions, showing improved stiffness continuity and potential for better structural optimization in additive manufacturing.

Contribution

It introduces and assesses a hybrid VAE that incorporates mechanical properties into the design process, enhancing the generation of smooth transition regions in multi-lattice structures.

Findings

Hybrid VAEs improve stiffness continuity in transition regions

Mechanical property integration benefits multi-lattice design

Enhanced performance over geometry-only models

Abstract

Additive manufacturing has revolutionized structural optimization by enhancing component strength and reducing material requirements. One approach used to achieve these improvements is the application of multi-lattice structures, where the macro-scale performance relies on the detailed design of mesostructural lattice elements. Many current approaches to designing such structures use data-driven design to generate multi-lattice transition regions, making use of machine learning models that are informed solely by the geometry of the mesostructures. However, it remains unclear if the integration of mechanical properties into the dataset used to train such machine learning models would be beneficial beyond using geometric data alone. To address this issue, this work implements and evaluates a hybrid geometry/property Variational Autoencoder (VAE) for generating multi-lattice transition regions. In our study, we found that hybrid VAEs demonstrate enhanced performance in maintaining stiffness continuity through transition regions, indicating their suitability for design tasks requiring smooth mechanical properties.