Machine learning enabled autonomous microstructural characterization in 3D samples
Автономная характеристика микроструктуры трехмерных образцов с использованием машинного обучения
2020-01-06
SCID: 54.1/aasw8dsr
Discuss with AI
3D microstructural characterizationmicrostructure segmentationpolycrystalline grain analysistopology classificationunsupervised machine learning
Figures from the paper
Abstract (AI)
Abstract We introduce an unsupervised machine learning (ML) based technique for the identification and characterization of microstructures in three-dimensional (3D) samples obtained from molecular dynamics simulations, particle tracking data, or experiments. Our technique combines topology classification, image processing, and clustering algorithms, and can handle a wide range of microstructure types including grains in polycrystalline materials, voids in porous systems, and structures from self/directed assembly in soft-matter complex solutions. Our technique does not require a priori microstructure description of the target system and is insensitive to disorder such as extended defects in polycrystals arising from line and plane defects. We demonstrate quantitively that our technique provides unbiased microstructural information such as precise quantification of grains and their size distributions in 3D polycrystalline samples, characterizes features such as voids and porosity in 3D polymeric samples and micellar size distribution in 3D complex fluids. To demonstrate the efficacy of our ML approach, we benchmark it against a diverse set of synthetic data samples representing nanocrystalline metals, polymers and complex fluids as well as experimentally published characterization data. Our technique is computationally efficient and provides a way to quickly identify, track, and quantify complex microstructural features that impact the observed material behavior.
Key Findings
1
Benchmarking on synthetic nanocrystalline metals, polymers, complex fluids, and published experimental data demonstrates computationally efficient identification, tracking, and quantification of microstructural features.
2
Combines topology classification, image processing, and clustering without requiring an a priori description of the target microstructure.
3
Handles disorder, including extended line and plane defects in polycrystals, while providing unbiased grain counts and precise three-dimensional grain-size distributions.
4
Introduces an unsupervised machine-learning technique for autonomous identification and characterization of diverse microstructures in three-dimensional samples.
5
Quantitatively characterizes voids and porosity in 3D polymeric samples and micellar size distributions in 3D complex fluids.
Research Object
Three-dimensional samples containing complex microstructures, including polycrystalline materials, porous polymers, and soft-matter complex fluids
Research Subject
Identification, tracking, and quantitative characterization of 3D microstructural features, including grain and void morphology, porosity, and micellar size distributions, without a priori structural descriptions
Publication Details
Publication Date
2020-01-06
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest