微观结构
财产(哲学)
卷积神经网络
材料科学
特征(语言学)
涂层
人工神经网络
人工智能
计算机科学
算法
深度学习
模式识别(心理学)
特征提取
特征向量
均方预测误差
计算机模拟
作者
Tianchuang Gao,Yehao Long,Tongdi Zhang,Jing Zhong,Lijun Zhang
出处
期刊:Microstructures
[OAE Publishing Inc.]
日期:2026-03-13
卷期号:6 (2)
被引量:1
标识
DOI:10.20517/microstructures.2025.107
摘要
Microstructure evolution in service significantly influences the properties of advanced materials. Numerical simulation can effectively capture microstructure development and provide abundant high-fidelity data. However, effective 3D microstructure-informed property prediction methods are lacking due to the complexity and richness of 3D microstructural data. In this work, a novel approach combining phase-field simulation and a 3D convolutional neural network is proposed to explore the composition-process-structure-property relationship in Ti1-xAlxN coatings. A large dataset of 4,962 simulated 3D microstructures under various heat treatment conditions was first generated using phase-field simulations. Then, a reconstructible feature extraction model was trained to compress each 48 × 48 × 48-grid microstructure into a 128-dimensional latent vector with a reconstruction accuracy of up to 99%. Using the extracted features, a microstructure-based hardness prediction model was constructed, achieving a low prediction error of 1.6 GPa (ca. 5.3% error for an average hardness of 30.8 GPa). The results demonstrate the effectiveness of 3D microstructure-informed deep learning for accurate property prediction, providing a promising tool for the data-driven design of high-performance materials.
科研通智能强力驱动
Strongly Powered by AbleSci AI