Machine learning approaches for elastic localization linkages in high-contrast composite materials
- 2.4k Downloads
There has been a growing recognition of the opportunities afforded by advanced data science and informatics approaches in addressing the computational demands of modeling and simulation of multiscale materials science phenomena. More specifically, the mining of microstructure–property relationships by various methods in machine learning and data mining opens exciting new opportunities that can potentially result in a fast and efficient material design. This work explores and presents multiple viable approaches for computationally efficient predictions of the microscale elastic strain fields in a three-dimensional (3-D) voxel-based microstructure volume element (MVE). Advanced concepts in machine learning and data mining, including feature extraction, feature ranking and selection, and regression modeling, are explored as data experiments. Improvements are demonstrated in a gradually escalated fashion achieved by (1) feature descriptors introduced to represent voxel neighborhood characteristics, (2) a reduced set of descriptors with top importance, and (3) an ensemble-based regression technique.
KeywordsMaterials informatics Data mining Elastic localization linkages Structure feature selection Structure feature ranking Ensemble-based regression
All authors gratefully acknowledge primary funding support from AFOSR award FA9550-12-1-0458 for this work. RL, AA, and AC also acknowledge partial support from NIST award 70NANB14H012 and DARPA award N66001-15-C-4036.
- 3.Kalidindi SR (2015) Data science and cyberinfrastructure: critical enablers for accelerated development of hierarchical materials. Int Mark Rev 60(3): 150–168.Google Scholar
- 6.Ferris KF, Peurrung LM, Marder JM (2007) Materials informatics: fast track to new materials. Adv Mater Process1: 50–51. 165(PNNL-SA-52427).Google Scholar
- 14.Warren J (2012) Materials genome initiative In: AIP Conference Proceedings.. American Institute of Physics, Ste. 1 NO 1 Melville NY 11747-4502 United States.Google Scholar
- 16.Landi G, Kalidindi SR (2010) Thermo-elastic localization relationships for multi-phase composites. Comput Mater Continua 16(3): 273–293.Google Scholar
- 19.Kalidindi SR, Niezgoda SR, Landi G, Vachhani S, Fast T (2010) A novel framework for building materials knowledge systems. Comput Mater Continua 17(2): 103–125.Google Scholar
- 25.Adams BL, Kalidindi SR, Fullwood DT (2012) Microstructure sensitive design for performance optimization. Butterworth-Heinemann, Boston.Google Scholar
- 39.Tezaki A, Mineta T, Egawa H, Noguchi T (1990) Measurement of three dimensional stress and modeling of stress induced migration failure in aluminium interconnects In: Reliability Physics Symposium, 1990. 28th Annual Proceedings., International, 221–229.. IEEE.Google Scholar
- 40.ABAQUS (2000) ABAQUS/standard user’s manual vol. 1. Hibbitt, Karlsson & Sorensen, Pawtucket, RI.Google Scholar
- 41.scikit-learn: machine learning in Python. http://scikit-learn.github.io/. [Online; accessed August 2015].
- 48.Quinlan JR (1992) Learning with continuous classes In: Proceedings of the 5th Australian Joint Conference on Artificial Intelligence, 343–348.. World Scientific, Singapore.Google Scholar
- 49.Wang Y, Witten IH (1996) Induction of model trees for predicting continuous classes. (Working paper 96/23), Hamilton, New Zealand. University of Waikato, Department of Computer Science.Google Scholar
Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.