Machine Learning Models of Plastic Flow Based on Representation Theory

doi:10.31614/cmes.2018.04285

This content will become publicly available on December 29, 2019

Title: Machine Learning Models of Plastic Flow Based on Representation Theory

Full Record
Other Related Research

Abstract

We use machine learning (ML) to infer stress and plastic flow rules using data from representative polycrystalline simulations. In particular, we use so-called deep (multilayer) neural networks (NN) to represent the two response functions. The ML process does not choose appropriate inputs or outputs, rather it is trained on selected inputs and output. Likewise, its discrimination of features is crucially connected to the chosen input-output map. Furthermore, we draw upon classical constitutive modeling to select inputs and enforce well-accepted symmetries and other properties. With these developments, we enable rapid model building in real-time with experiments, and guide data collection and feature discovery.

Authors:

Jones, R. E. ^[1]; Templeton, J. A. ^[2]; Sanders, C. M. ^[2]; Ostien, J. T. ^[1]

Sandia National Lab. (SNL-CA), Livermore, CA (United States). Mechanics of Materials Dept.
Sandia National Lab. (SNL-CA), Livermore, CA (United States). Thermal/Fluid Science and Engineering Dept.

Publication Date:: 2018-12-29

Research Org.:: Sandia National Lab. (SNL-CA), Livermore, CA (United States)

Sponsoring Org.:: USDOE National Nuclear Security Administration (NNSA); SNL Laboratory Directed Research and Development (LDRD) Program

OSTI Identifier:: 1502970

Report Number(s):: SAND-2019-2905J
Journal ID: ISSN 1526-1492; 673466

Grant/Contract Number:: NA0003525

Resource Type:: Accepted Manuscript

Journal Name:: Computer Modeling in Engineering & Sciences

Additional Journal Information:: Journal Volume: 117; Journal Issue: 3; Journal ID: ISSN 1526-1492

Publisher:: Tech Science Press

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; 42 ENGINEERING; machine learning; neural network; plasticity

Citation Formats


                    Jones, R. E., Templeton, J. A., Sanders, C. M., and Ostien, J. T. Machine Learning Models of Plastic Flow Based on Representation Theory.  United States: N. p., 2018. 
        Web.  doi:10.31614/cmes.2018.04285.

Copy to clipboard


                    Jones, R. E., Templeton, J. A., Sanders, C. M., & Ostien, J. T. Machine Learning Models of Plastic Flow Based on Representation Theory.  United States.  doi:10.31614/cmes.2018.04285.

Copy to clipboard


                    Jones, R. E., Templeton, J. A., Sanders, C. M., and Ostien, J. T. Sat .  
        "Machine Learning Models of Plastic Flow Based on Representation Theory".  United States.  doi:10.31614/cmes.2018.04285.

Copy to clipboard


                    
@article{osti_1502970,

  title        = {Machine Learning Models of Plastic Flow Based on Representation Theory},

  author       = {Jones, R. E. and Templeton, J. A. and Sanders, C. M. and Ostien, J. T.},

  abstractNote = {We use machine learning (ML) to infer stress and plastic flow rules using data from representative polycrystalline simulations. In particular, we use so-called deep (multilayer) neural networks (NN) to represent the two response functions. The ML process does not choose appropriate inputs or outputs, rather it is trained on selected inputs and output. Likewise, its discrimination of features is crucially connected to the chosen input-output map. Furthermore, we draw upon classical constitutive modeling to select inputs and enforce well-accepted symmetries and other properties. With these developments, we enable rapid model building in real-time with experiments, and guide data collection and feature discovery.},

  doi          = {10.31614/cmes.2018.04285},

  journal      = {Computer Modeling in Engineering & Sciences},

  number       = 3,

  volume       = 117,

  place        = {United States},

  year         = {2018},

  month        = {12}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

This content will become publicly available on December 29, 2019

Publisher's Version of Record

DOI: 10.31614/cmes.2018.04285

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

A mathematical discussion concerning the performance of multilayer perceptron-type artificial neural networks through use of orthogonal bipolar vectors

Journal Article Manzan, José Ricardo Gonçalves, E-mail: josericardo@iftm.edu.br ; Yamanaka, Keiji ; Peretta, Igor Santos, E-mail: iperetta@gmail.com ; ... - Computational and Applied Mathematics

This work proposes the use of orthogonal bipolar vectors (OBV) as targets for multilayer perceptron (MLP) Artificial neural networks pertaining to the pattern recognition field. Implications involving this proposal are supported by a proper mathematical discussion. This study shows that the use of OBV as targets improves the class identification performance of MLP networks for pattern recognition with more than two classes when compared to the widely used conventional target bipolar vector (CBV). In addition to the overall performance improvement, it is possible to obtain high recognition rates with fewer training epochs, while keeping a feasible generalization with other data.more »« less
DOI: 10.1007/S40314-016-0377-X
Machine learning strategies for systems with invariance properties

Journal Article Ling, Julia ; Jones, Reese E. ; Templeton, Jeremy Alan - Journal of Computational Physics

Here, in many scientific fields, empirical models are employed to facilitate computational simulations of engineering systems. For example, in fluid mechanics, empirical Reynolds stress closures enable computationally-efficient Reynolds-Averaged Navier-Stokes simulations. Likewise, in solid mechanics, constitutive relations between the stress and strain in a material are required in deformation analysis. Traditional methods for developing and tuning empirical models usually combine physical intuition with simple regression techniques on limited data sets. The rise of high-performance computing has led to a growing availability of high-fidelity simulation data, which open up the possibility of using machine learning algorithms, such as random forests or neuralmore »« less
Cited by 10
DOI: 10.1016/j.jcp.2016.05.003

Full Text Available
Computationally Efficient Training of Deep Neural Networks via Transfer Learning

Journal Article Oyen, Diane - Proceedings of SPIE - The International Society for Optical Engineering

Transfer learning is a highly successful approach to train deep neural networks for customized image recognition tasks. Transfer learning leverages deep learning models that are previously trained on massive datasets and re-trains the network for a novel image recognition dataset. Typically, the advantage of transfer learning has been measured in sample efficiency, but instead, we investigate the computational efficiency of transfer learning. A good pre-trained model provides features that can be used as input to a new classifier (usually the top layers of a neural network). We show that if a good pre-trained model is selected, that training a newmore »« less
DOI: 10.1117/12.2519097
Development of Ensemble Neural Network Convection Parameterizations for Climate Models

Technical Report Fox-Rabinovitz, M. S. ; Krasnopolsky, V. M.

The novel neural network (NN) approach has been formulated and used for development of a NN ensemble stochastic convection parametrization for climate models. This fast parametrization is built based on data from Cloud Resolving Model (CRM) simulations initialized with and forced by TOGA-COARE data. The SAM (System for Atmospheric Modeling), developed by D. Randall, M. Khairoutdinov, and their collaborators, has been used for CRM simulations. The observational data are also used for validation of model simulations. The SAM-simulated data have been averaged and projected onto the GCM space of atmospheric states to implicitly define a stochastic convection parametrization. This parametrizationmore »« less
DOI: 10.2172/1039344

Full Text Available
Classification of Local Seismic Events in the Utah Region: A Comparison of Amplitude Ratio Methods with a Spectrogram-Based Machine Learning Approach

Journal Article Tibi, Rigobert ; Linville, Lisa ; Young, Christopher ; ... - Bulletin of the Seismological Society of America

Abstract The capability to discriminate low-magnitude earthquakes from low-yield anthropogenic sources, both detectable only at local distances, is of increasing interest to the event monitoring community. Here, we used a dataset of seismic events in Utah recorded during a 14-day period (1–14 January 2011) by the University of Utah Seismic Stations network to perform a comparative study of event classification at local scale using amplitude ratio (AR) methods and a machine learning (ML) approach. The event catalog consists of 7377 events with magnitudes M _C ranging from –2 and lower up to 5.8. Events were subdivided into six populations basedmore »« less
DOI: 10.1785/0120190150

Similar Records