Evolutionary de-homogenization using a generative model for optimizing solid-porous infill structures considering the stress concentration issue

TL;DR

The paper tackles the challenge of designing porous infill structures that balance weight reduction with mechanical performance, particularly addressing stress concentration and geometric gaps between analysis models and manufacturable geometries. It introduces evolutionary de-homogenization, a data-driven multifidelity framework that links low-fidelity density-based design variables to high-fidelity CAD-compatible geometries via a wave-projection de-homogenization mapping, enabling accurate stress-aware optimization. The method combines NSGA-II-based multi-objective optimization with a VAE-driven crossover to evolve diverse, high-quality designs, and it demonstrates mesh-independent results and improved stress distribution in two 2D benchmarks. The approach provides a practical pathway toward manufacturable, stress-robust solid-porous infill designs suitable for additive manufacturing, while outlining limitations and directions for extension to 3D and experimental validation.

Abstract

The design of porous infill structures presents significant challenges due to their complex geometric configurations, such as the accurate representation of geometric boundaries and the control of localized maximum stress. In current mainstream design methods, such as topology optimization, the analysis is often performed using pixel or voxel-based element approximations. These approximations, constrained by the optimization framework, result in substantial geometric discrepancies between the analysis model and the final physical model. Such discrepancies can severely impact structural performance, particularly for localized properties like stress response, where accurate geometry is critical to mitigating stress concentration. To address these challenges, we propose evolutionary de-homogenization, which is a design framework based on the integration of de-homogenization and data-driven multifidelity optimization. This framework facilitates the hybrid solid-porous infill design by bridging the gap between low-fidelity analysis and high-fidelity physical realizations, ensuring both geometric accuracy and enhanced structural performance. The low-fidelity level utilizes commonly used density control variables, while the high-fidelity level involves stress analysis based on structures with precise geometric representations. By employing a de-homogenization-based mapping method, a side-by-side correspondence between low-fidelity and high-fidelity results is established. The low-fidelity control variables are iteratively adjusted to optimize the high-fidelity results by integrating deep generative model with multi-objective evolutionary algorithm. Finally, numerical experiments demonstrate the effectiveness of the proposed method.

Figures (21)

• Figure 1: The concept of decomposing the regions contained in a hybrid solid-porous infill structure.
• Figure 2: The basic idea of low-fidelity optimization method.
• Figure 3: The optimization process for low-fidelity optimization: (a) symmetric tension beam case, and (b) L-bracket beam case.
• Figure 4: Geometry pattern for rank-2 composite material.
• Figure 5: The schematic diagram for the phase field $\Phi(\bm{r})$, the wave function field $\Gamma(\bm{r})$, and their relationship