Material structure-property linkages using three-dimensional convolutional neural networks
| Autor: | Yuksel C. Yabansu, Ahmet Cecen, Hanjun Dai, Le Song, Surya R. Kalidindi |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
010302 applied physics
Physics Polymers and Plastics Property (programming) Computation ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Metals and Alloys Estimator 02 engineering and technology 021001 nanoscience & nanotechnology computer.software_genre 01 natural sciences Convolutional neural network Electronic Optical and Magnetic Materials Reduction (complexity) Salient 0103 physical sciences Principal component analysis Ceramics and Composites Benchmark (computing) Data mining 0210 nano-technology computer |
| Zdroj: | Acta Materialia. 146:76-84 |
| ISSN: | 1359-6454 |
| Popis: | The core materials knowledge needed in the accelerated design, development, and deployment of new and improved materials is most accessible when cast in the form of computationally low cost (reduced-order) and reliable process-structure-property (PSP) linkages. Quantification of the material structure (also referred as microstructure) is the core challenge in this task. Conventionally, microstructure quantification has been addressed using highly simplified measures suggested by the governing physics, with the list of measures often suitably augmented by the intuition of the materials expert. In this paper, we develop an objective (data-driven) approach to efficiently and accurately link a three-dimensional (3-D) microstructure to its effective (homogenized) properties. Our method employs a 3-D convolutional neural network (CNN) to learn the salient features of the material microstructures that lead to good predictive performance for the effective property of interest. We then utilize 3-D CNN learned features as estimators of higher-order spatial correlations, and formulate an integrated framework combining 3-D CNN features with 2-point spatial correlations. In this work, we created an extremely large microstructure-property benchmark dataset of 5900 microstructures, and demonstrated that our CNN based approach not only learns interpretable microstructure features, but also leads to improved accuracy in property predictions for new microstructures, while achieving a dramatic reduction in the computation time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect