High-fidelity Grain Growth Modeling: Leveraging Deep Learning for Fast Computations

2025-05-08

AI Summary

To address the high computational cost of PDE-based grain growth simulation in metal annealing—which hinders efficient materials design—this study proposes an end-to-end deep learning framework for high-fidelity, ultra-fast microstructural evolution prediction. We innovatively integrate ConvLSTM with an autoencoder to construct a spatiotemporal joint modeling architecture and design a composite loss function incorporating SSIM, MSE, and a grain-boundary preservation term to enhance topological consistency. Experiments demonstrate an 89× speedup over conventional methods (from 10 minutes to 10 seconds), a structural similarity index of 86.71%, and a mean grain size error of only 0.07%. The model accurately reproduces grain boundary morphology and size distribution. This work establishes an efficient, data-driven paradigm for microstructure-aware materials design and control.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

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: Models for Web evolution
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Grain growth simulation is crucial for predicting metallic material microstructure evolution during annealing and resulting final mechanical properties, but traditional partial differential equation-based methods are computationally expensive, creating bottlenecks in materials design and manufacturing. In this work, we introduce a machine learning framework that combines a Convolutional Long Short-Term Memory networks with an Autoencoder to efficiently predict grain growth evolution. Our approach captures both spatial and temporal aspects of grain evolution while encoding high-dimensional grain structure data into a compact latent space for pattern learning, enhanced by a novel composite loss function combining Mean Squared Error, Structural Similarity Index Measurement, and Boundary Preservation to maintain structural integrity of grain boundary topology of the prediction. Results demonstrated that our machine learning approach accelerates grain growth prediction by up to SI{89}{ imes} faster, reducing computation time from SI{10}{minute} to approximately SI{10}{second} while maintaining high-fidelity predictions. The best model (S-30-30) achieving a structural similarity score of SI{86.71}{percent} and mean grain size error of just SI{0.07}{percent}. All models accurately captured grain boundary topology, morphology, and size distributions. This approach enables rapid microstructural prediction for applications where conventional simulations are prohibitively time-consuming, potentially accelerating innovation in materials science and manufacturing.

Problem

• Accelerate grain growth simulation using deep learning
• Reduce computational cost of microstructure evolution prediction
• Maintain high-fidelity grain boundary topology in predictions

Innovation

• Combines Convolutional LSTM with Autoencoder for grain growth
• Uses composite loss for structural integrity preservation
• Achieves 89x faster prediction with high fidelity