Multiphase Reconstruction of Heterogeneous Materials Using Machine Learning and Quality of Connection Function.

基于机器学习和连接函数质量的异质材料多相重构 [J].

• 影响指数: 3.748
• 发表时间: 2024 Jun 21
• 来源期刊: Materials (Basel)
• DOI: 10.3390/ma17133049
• PMID: 38998131
• 文章类型: Journal Article
• 作者列表: Hamidpour P,Araee A,Baniassadi M,Garmestani H

关键词: 3D microstructure reconstruction; convolutional occupancy networks; multi-phase heterogeneous materials; point cloud data; quality of connection function; serial-section stitching; statistical function; transfer learning

Abstract

Establishing accurate structure-property linkages and precise phase volume accuracy in 3D microstructure reconstruction of materials remains challenging, particularly with limited samples. This paper presents an optimized method for reconstructing 3D microstructures of various materials, including isotropic and anisotropic types with two and three phases, using convolutional occupancy networks and point clouds from inner layers of the microstructure. The method emphasizes precise phase representation and compatibility with point cloud data. A stage within the Quality of Connection Function (QCF) repetition loop optimizes the weights of the convolutional occupancy networks model to minimize error between the microstructure\'s statistical properties and the reconstructive model. This model successfully reconstructs 3D representations from initial 2D serial images. Comparisons with screened Poisson surface reconstruction and local implicit grid methods demonstrate the model\'s efficacy. The developed model proves suitable for high-quality 3D microstructure reconstruction, aiding in structure-property linkages and finite element analysis.

摘要

在材料的三维微观结构重建中建立精确的结构-性能联系和精确的相体积精度仍然具有挑战性，特别是有限的样本。本文提出了一种用于重建各种材料的3D微结构的优化方法。包括具有两相和三相的各向同性和各向异性类型，使用卷积占用网络和来自微观结构内层的点云。该方法强调精确的相位表示和与点云数据的兼容性。连接质量函数（QCF）重复循环中的一个阶段优化了卷积占用网络模型的权重，以最小化微观结构的统计属性与重建模型之间的误差。该模型成功地从初始2D系列图像重建3D表示。与筛选的泊松表面重建和局部隐式网格方法的比较证明了模型的有效性。所开发的模型证明适用于高质量的三维微结构重建，有助于结构-性能联系和有限元分析。