Data-Driven Multiscale Topology Optimization of Spinodoid Architected Materials with Controllable Anisotropy

2025-06-29

AI Summary

Spiral (gyroid) structure design confronts dual challenges: a high-dimensional parameter space—including material type, density, orientation, continuity, and anisotropy—and computational complexity in gradient evaluation. Conventional genetic algorithms suffer from low efficiency, while gradient-based topology optimization is hindered by the intractability of analytically deriving homogenized effective property gradients. This work proposes a data-driven multiscale topology optimization framework: design variables are implicitly parameterized via neural networks, enabling efficient gradient computation through automatic differentiation; Gaussian process surrogate models replace repetitive homogenization analyses, balancing computational efficiency and physical interpretability. Crucially, this approach establishes, for the first time, causal mappings between spatially varying anisotropic/isotropic regions in gyroid structures and their macroscopic mechanical responses. The method significantly improves optimization efficiency and scalability, successfully generating functionally graded, defect-robust designs with superior mechanical performance.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Spinodoid architected materials have drawn significant attention due to their unique nature in stochasticity, aperiodicity, and bi-continuity. Compared to classic periodic truss-, beam- and plate-based lattice architectures, spinodoids are insensitive to manufacturing defects, scalable for high throughput production, functionally graded by tunable local properties, and material failure resistant due to low-curvature morphology. However, the design of spinodoids is often hindered by the curse of dimensionality with extremely large design space of spinodoid types, material density, orientation, continuity, and anisotropy. From a design optimization perspective, while genetic algorithms are often beyond the reach of computing capacity, gradient-based topology optimization is challenged by the intricate mathematical derivation of gradient fields with respect to various spinodoid parameters. To address such challenges, we propose a data-driven multiscale topology optimization framework. Our framework reformulates the design variables of spinodoid materials as the parameters of neural networks, enabling automated computation of topological gradients. Additionally, it incorporates a Gaussian Process surrogate for spinodoid constitutive models, eliminating the need for repeated computational homogenization and enhancing the scalability of multiscale topology optimization. Compared to 'black-box' deep learning approaches, the proposed framework provides clear physical insights into material distribution. It explicitly reveals why anisotropic spinodoids with tailored orientations are favored in certain regions, while isotropic spinodoids are more suitable elsewhere. This interpretability helps to bridge the gap between data-driven design with mechanistic understanding.

Problem

• Design spinodoid materials with controllable anisotropy efficiently
• Overcome high dimensionality and gradient computation challenges in optimization
• Provide interpretable data-driven design insights for material distribution

Innovation

• Neural networks parameterize spinodoid design variables
• Gaussian Process surrogate for constitutive models
• Data-driven multiscale topology optimization framework