PCG-Informed Neural Solvers for High-Resolution Homogenization of Periodic Microstructures

TL;DR

This paper introduces CGINS, a neural network-based homogenization solver that combines preconditioned conjugate gradient methods with deep learning to achieve high accuracy and speed in predicting properties of complex microstructures.

Contribution

The paper presents a novel neural network architecture that integrates PCG iterations and multi-scale learning for efficient, accurate homogenization of high-resolution microstructures.

Findings

Achieves less than 1% relative error in predictions.

Delivers 2 to 10 times speedup over traditional solvers.

Maintains physical consistency at resolutions up to 512^3.

Abstract

The mechanical properties of periodic microstructures are pivotal in various engineering applications. Homogenization theory is a powerful tool for predicting these properties by averaging the behavior of complex microstructures over a representative volume element. However, traditional numerical solvers for homogenization problems can be computationally expensive, especially for high-resolution and complicated topology and geometry. Existing learning-based methods, while promising, often struggle with accuracy and generalization in such scenarios. To address these challenges, we present CGINS, a preconditioned-conjugate-gradient-solver-informed neural network for solving homogenization problems. CGINS leverages sparse and periodic 3D convolution to enable high-resolution learning while ensuring structural periodicity. It features a multi-level network architecture that facilitates effective learning across different scales and employs minimum potential energy as label-free loss functions for self-supervised learning. The integrated preconditioned conjugate gradient iterations ensure that the network provides PCG-friendly initial solutions for fast convergence and high accuracy. Additionally, CGINS imposes a global displacement constraint to ensure physical consistency, addressing a key limitation in prior methods that rely on Dirichlet anchors. Evaluated on large-scale datasets with diverse topologies and material configurations, CGINS achieves state-of-the-art accuracy (relative error below 1%) and outperforms both learning-based baselines and GPU-accelerated numerical solvers. Notably, it delivers 2 times to 10 times speedups over traditional methods while maintaining physically reliable predictions at resolutions up to $512^3$.