MIND: Microstructure INverse Design with Generative Hybrid Neural Representation

2025-02-01

AI Summary

Microstructural inverse design faces challenges—including low accuracy and poor diversity—stemming from strong coupling between geometric configuration and physical properties. To address this, we propose the first end-to-end inverse design framework integrating a latent diffusion model with Holoplane—a hybrid neural representation jointly encoding implicit geometric and physical property fields. Our method enables generalized generation across diverse microstructure classes (e.g., trusses, shells, tubes, plates), cross-class interpolation, and heterogeneous infilling—overcoming representational limitations of conventional voxel-based or parametric approaches. Experiments demonstrate that our generated structures consistently outperform state-of-the-art methods in physical property fidelity, geometric validity, and tessellability. Furthermore, we validate efficacy in complex assembly tasks. This work establishes a new paradigm for intelligent metamaterial design.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Structured Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

The inverse design of microstructures plays a pivotal role in optimizing metamaterials with specific, targeted physical properties. While traditional forward design methods are constrained by their inability to explore the vast combinatorial design space, inverse design offers a compelling alternative by directly generating structures that fulfill predefined performance criteria. However, achieving precise control over both geometry and material properties remains a significant challenge due to their intricate interdependence. Existing approaches, which typically rely on voxel or parametric representations, often limit design flexibility and structural diversity. In this work, we present a novel generative model that integrates latent diffusion with Holoplane, an advanced hybrid neural representation that simultaneously encodes both geometric and physical properties. This combination ensures superior alignment between geometry and properties. Our approach generalizes across multiple microstructure classes, enabling the generation of diverse, tileable microstructures with significantly improved property accuracy and enhanced control over geometric validity, surpassing the performance of existing methods. We introduce a multi-class dataset encompassing a variety of geometric morphologies, including truss, shell, tube, and plate structures, to train and validate our model. Experimental results demonstrate the model's ability to generate microstructures that meet target properties, maintain geometric validity, and integrate seamlessly into complex assemblies. Additionally, we explore the potential of our framework through the generation of new microstructures, cross-class interpolation, and the infilling of heterogeneous microstructures. The dataset and source code will be open-sourced upon publication.

Problem

• Inverse design of microstructures
• Control over geometry and material properties
• Generative model with hybrid neural representation

Innovation

• Generative model with latent diffusion
• Holoplane hybrid neural representation
• Multi-class dataset for training