Populating cellular metamaterials on the extrema of attainable elasticity through neuroevolution

2024-12-15

AI Summary

To address the challenge of concurrently optimizing multiple elastic properties (e.g., stiffness, toughness, energy absorption) in metamaterials, this paper proposes the first neural evolutionary framework integrating Compositional Pattern-Producing Networks (CPPNs) with an enhanced Neuroevolution of Augmenting Topologies (NEAT) algorithm. The method overcomes fundamental limitations of gradient-based and data-driven paradigms—namely, poor design-space coverage and limited extrapolation capability—enabling efficient, large-scale, multi-objective topological search. By employing precise elastic tensor modeling and Pareto front analysis, we systematically characterize the empirical performance limits of multidimensional elastic property combinations and identify their attainable boundaries. Experimental results demonstrate high structural diversity and uniform distribution across the Pareto-optimal set. This work establishes a customizable, physics-informed design paradigm for metamaterials, with broad applicability in robotics, biomedical engineering, and photonics.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Evolutionary Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

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

Abstract

The trade-offs between different mechanical properties of materials pose fundamental challenges in engineering material design, such as balancing stiffness versus toughness, weight versus energy-absorbing capacity, and among the various elastic coefficients. Although gradient-based topology optimization approaches have been effective in finding specific designs and properties, they are not efficient tools for surveying the vast design space of metamaterials, and thus unable to reveal the attainable bound of interdependent material properties. Other common methods, such as parametric design or data-driven approaches, are limited by either the lack of diversity in geometry or the difficulty to extrapolate from known data, respectively. In this work, we formulate the simultaneous exploration of multiple competing material properties as a multi-objective optimization (MOO) problem and employ a neuroevolution algorithm to efficiently solve it. The Compositional Pattern-Producing Networks (CPPNs) is used as the generative model for unit cell designs, which provide very compact yet lossless encoding of geometry. A modified Neuroevolution of Augmenting Topologies (NEAT) algorithm is employed to evolve the CPPNs such that they create metamaterial designs on the Pareto front of the MOO problem, revealing empirical bounds of different combinations of elastic properties. Looking ahead, our method serves as a universal framework for the computational discovery of diverse metamaterials across a range of fields, including robotics, biomedicine, thermal engineering, and photonics.

Problem

• Material Design
• Optimal Balance
• Metamaterials

Innovation

• Neural Evolution
• Multi-Objective Optimization
• Compressed CPPNs