Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures

Messner, Mark C.

doi:10.1115/1.4045040

Title: Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures

Abstract

The work in this paper describes neural network surrogate models for calculating the effective mechanical properties of a periodic composites. The models achieve good accuracy even when only provided with training data sampling a small portion of the design space. As an example, the surrogate models are applied to solving the inverse design problem of finding structures with optimal mechanical properties. The surrogate models are sufficiently accurate to recover optimal solutions in general agreement with established topology optimization methods. However, improvements will be required to develop robust, efficient neural network-based surrogate models and several directions for future research are highlighted here.

Authors:

Messner, Mark C. ^[1]

Argonne National Lab. (ANL), Lemont, IL (United States)

Publication Date:: Thu Oct 17 00:00:00 EDT 2019

Research Org.:: Argonne National Lab. (ANL), Argonne, IL (United States)

Sponsoring Org.:: USDOE Office of Nuclear Energy (NE)

OSTI Identifier:: 1632185

Grant/Contract Number:: AC02-06CH11357

Resource Type:: Accepted Manuscript

Journal Name:: Journal of Mechanical Design

Additional Journal Information:: Journal Volume: 142; Journal Issue: 2; Journal ID: ISSN 1050-0472

Publisher:: ASME

Country of Publication:: United States

Language:: English

Subject:: 42 ENGINEERING; design optimization; metamodeling; simulation-based design

Citation Formats


                    Messner, Mark C. Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures.  United States: N. p., 2019. 
Web.  doi:10.1115/1.4045040.

Copy to clipboard


                    Messner, Mark C. Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures.  United States.  https://doi.org/10.1115/1.4045040

Copy to clipboard


                    Messner, Mark C. Thu .  
"Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures".  United States.  https://doi.org/10.1115/1.4045040.  https://www.osti.gov/servlets/purl/1632185.

Copy to clipboard


                    
@article{osti_1632185,

  title        = {Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures},

  author       = {Messner, Mark C.},

  abstractNote = {The work in this paper describes neural network surrogate models for calculating the effective mechanical properties of a periodic composites. The models achieve good accuracy even when only provided with training data sampling a small portion of the design space. As an example, the surrogate models are applied to solving the inverse design problem of finding structures with optimal mechanical properties. The surrogate models are sufficiently accurate to recover optimal solutions in general agreement with established topology optimization methods. However, improvements will be required to develop robust, efficient neural network-based surrogate models and several directions for future research are highlighted here.},

  doi          = {10.1115/1.4045040},

  journal      = {Journal of Mechanical Design},

  number       = 2,

  volume       = 142,

  place        = {United States},

  year         = {Thu Oct 17 00:00:00 EDT 2019},

  month        = {Thu Oct 17 00:00:00 EDT 2019}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1115/1.4045040

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 10 works

Citation information provided by
Web of Science

Figures / Tables:

Fig. 1: Problem geometry. The one-eighth section marked out with bold lines describes the entire, square-symmetric, periodic structure.

All figures and tables (6 total)

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Optimal shape design as a material distribution problem
journal, December 1989

Bendsøe, M. P.
Structural Optimization, Vol. 1, Issue 4
DOI: 10.1007/BF01650949

Review of Metamodeling Techniques in Support of Engineering Design Optimization
journal, May 2006

Wang, G. Gary; Shan, S.
Journal of Mechanical Design, Vol. 129, Issue 4
DOI: 10.1115/1.2429697

Computational homogenization of nonlinear elastic materials using neural networks: NEURAL NETWORKS-BASED COMPUTATIONAL HOMOGENIZATION
journal, June 2015

Le, B. A.; Yvonnet, J.; He, Q. -C.
International Journal for Numerical Methods in Engineering, Vol. 104, Issue 12
DOI: 10.1002/nme.4953

Efficient topology optimization in MATLAB using 88 lines of code
journal, November 2010

Andreassen, Erik; Clausen, Anders; Schevenels, Mattias
Structural and Multidisciplinary Optimization, Vol. 43, Issue 1
DOI: 10.1007/s00158-010-0594-7

Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
journal, January 1962

Hubel, D. H.; Wiesel, T. N.
The Journal of Physiology, Vol. 160, Issue 1
DOI: 10.1113/jphysiol.1962.sp006837

Face recognition: a convolutional neural-network approach
journal, January 1997

Lawrence, S.; Giles, C. L.
IEEE Transactions on Neural Networks, Vol. 8, Issue 1
DOI: 10.1109/72.554195

An integrated approach for optimum design of bridge decks using genetic algorithms and artificial neural networks
journal, July 2007

Srinivas, V.; Ramanjaneyulu, K.
Advances in Engineering Software, Vol. 38, Issue 7
DOI: 10.1016/j.advengsoft.2006.09.016

Optimization of Large-Scale 3-D Trusses Using Evolution Strategies and Neural Networks
journal, September 1999

Papadrakakis, Manolis; Lagaros, Nikos D.; Tsompanakis, Yiannis
International Journal of Space Structures, Vol. 14, Issue 3
DOI: 10.1260/0266351991494830

Integral equation of the inverse problem of the plane theory of elasticity
journal, January 1976

Vigdergauz, S. B.
Journal of Applied Mathematics and Mechanics, Vol. 40, Issue 3
DOI: 10.1016/0021-8928(76)90046-0

A New Design Approach for Rapid Evaluation of Structural Modifications Using Neural Networks
journal, January 2013

Demirkan, O.; Olceroglu, E.; Basdogan, I.
Journal of Mechanical Design, Vol. 135, Issue 2
DOI: 10.1115/1.4023156

Structural optimization using evolution strategies and neural networks
journal, April 1998

Papadrakakis, Manolis; Lagaros, Nikos D.; Tsompanakis, Yiannis
Computer Methods in Applied Mechanics and Engineering, Vol. 156, Issue 1-4
DOI: 10.1016/S0045-7825(97)00215-6

Soft computing methodologies for structural optimization
journal, November 2003

Papadrakakis, Manolis; Lagaros, Nikos D.
Applied Soft Computing, Vol. 3, Issue 3
DOI: 10.1016/S1568-4946(03)00040-1

Optimum design of high-rise steel buildings using an evolution strategy integrated parallel algorithm
journal, November 2011

Hasançebi, O.; Bahçecioğlu, T.; Kurç, Ö.
Computers & Structures, Vol. 89, Issue 21-22
DOI: 10.1016/j.compstruc.2011.05.019

Coupling of scales in a multiscale simulation using neural networks
journal, November 2008

Unger, Jörg F.; Könke, Carsten
Computers & Structures, Vol. 86, Issue 21-22
DOI: 10.1016/j.compstruc.2008.05.004

Aims, scope, methods, history and unified terminology of computer-aided topology optimization in structural mechanics
journal, April 2001

Rozvany, G. I. N.
Structural and Multidisciplinary Optimization, Vol. 21, Issue 2
DOI: 10.1007/s001580050174

Subject independent facial expression recognition with robust face detection using a convolutional neural network
journal, June 2003

Matsugu, Masakazu; Mori, Katsuhiko; Mitari, Yusuke
Neural Networks, Vol. 16, Issue 5-6
DOI: 10.1016/S0893-6080(03)00115-1

Figures / Tables found in this record:

Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.

Similar Records in DOE PAGES and OSTI.GOV collections:

Improving surrogate model accuracy for the LCLS-II injector frontend using convolutional neural networks and transfer learning

Journal Article Gupta, Lipi ; Edelen, Auralee ; Neveu, Nicole ; ... - Machine Learning: Science and Technology

Machine learning (ML) models of accelerator systems ('surrogate models') are able to provide fast, accurate predictions of accelerator physics phenomena. However, approaches to date typically do not include measured input diagnostics, such as the initial beam distributions, which are critical for accurately representing the beam evolution through the system. In addition, these inputs often vary over time, and models that can account for these changing conditions are needed. As beam time for measurements is often limited, simulations are in some cases needed to provide sufficient training data. These typically represent the designed machine before construction; however, the behavior of themore »« less
https://doi.org/10.1088/2632-2153/ac27ff
A Look Inside the Black Box: Using graph-theoretical descriptors to interpret a Continuous-Filter Convolutional Neural Network (CF-CNN) trained on the global and local minimum energy structures of neutral water clusters

Journal Article Bilbrey, Jenna A. ; Heindel, Joseph ; Schram, Malachi ; ... - Journal of Chemical Physics

A Continuous Filter Convolutional Neural Network (CF-CNN) was trained to predict the potential energy of water cluster networks \ce{(H2O)_{\textit{N}}}, \textit{N}=10--30, corresponding to local minima lying within 5 kcal/mol from the putative minima taken from a newly published database containing over 5 million unique networks. The chemical sampling space of the database was characterized using chemical descriptors derived from graph theory, which led to the identification of important trends in the topology, connectivity, polygon structures associated with the various networks as a function of cluster size. The resulting graphs are available alongside the original database at \url{https://sites.uw.edu/wdbase/}. The CF-CNN trained on a subset of 500,000 networks for (\textit{N}=10, 30) yielded a mean absolute error of 0.002more »« less
https://doi.org/10.1063/5.0009933
Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules

Journal Article Choi, Jong Youl ; Zhang, Pei ; Mehta, Kshitij ; ... - Journal of Cheminformatics

Abstract Graph Convolutional Neural Network (GCNN) is a popular class of deep learning (DL) models in material science to predict material properties from the graph representation of molecular structures. Training an accurate and comprehensive GCNN surrogate for molecular design requires large-scale graph datasets and is usually a time-consuming process. Recent advances in GPUs and distributed computing open a path to reduce the computational cost for GCNN training effectively. However, efficient utilization of high performance computing (HPC) resources for training requires simultaneously optimizing large-scale data management and scalable stochastic batched optimization techniques. In this work, we focus on building GCNN modelsmore »« less
https://doi.org/10.1186/s13321-022-00652-1
Multiscale topology optimization using neural network surrogate models

Journal Article White, Daniel A. ; Arrighi, William J. ; Kudo, Jun ; ... - Computer Methods in Applied Mechanics and Engineering

In this study, we are concerned with optimization of macroscale elastic structures that are designed utilizing spatially varying microscale metamaterials. The macroscale optimization is accomplished using gradient-based nonlinear topological optimization. But instead of using density as the optimization decision variable, the decision variables are the multiple parameters that define the local microscale metamaterial. This is accomplished using single layer feedforward Gaussian basis function networks as a surrogate models of the elastic response of the microscale metamaterial. The surrogate models are trained using highly resolved continuum finite element simulations of the microscale metamaterials and hence are significantly more accurate than analyticalmore »« less
Cited by 81
https://doi.org/10.1016/j.cma.2018.09.007

Full Text Available
Designing Ti-6Al-4V microstructure for strain delocalization using neural networks

Journal Article Ahmadikia, Behnam ; Beyerlein, Adolph L. ; Hestroffer, Jonathan M. ; ... - Journal of Materials Science: Materials Theory

Abstract The deformation behavior of Ti-6Al-4V titanium alloy is significantly influenced by slip localized within crystallographic slip bands. Experimental observations reveal that intense slip bands in Ti-6Al-4V form at strains well below the macroscopic yield strain and may serially propagate across grain boundaries, resulting in long-range localization that percolates through the microstructure. These connected, localized slip bands serve as potential sites for crack initiation. Although slip localization in Ti-6Al-4V is known to be influenced by various factors, an investigation of optimal microstructures that limit localization remains lacking. In this work, we develop a novel strategy that integrates an explicit slipmore »« less
https://doi.org/10.1186/s41313-024-00055-9

Similar Records

Title: Convolutional Neural Network Surrogate Models for the Mechanical Properties of Periodic Structures

Abstract

Citation Formats

Figures / Tables:

Optimal shape design as a material distribution problem journal, December 1989

Review of Metamodeling Techniques in Support of Engineering Design Optimization journal, May 2006

Computational homogenization of nonlinear elastic materials using neural networks: NEURAL NETWORKS-BASED COMPUTATIONAL HOMOGENIZATION journal, June 2015

Efficient topology optimization in MATLAB using 88 lines of code journal, November 2010

Receptive fields, binocular interaction and functional architecture in the cat's visual cortex journal, January 1962

Face recognition: a convolutional neural-network approach journal, January 1997

An integrated approach for optimum design of bridge decks using genetic algorithms and artificial neural networks journal, July 2007

Optimization of Large-Scale 3-D Trusses Using Evolution Strategies and Neural Networks journal, September 1999

Integral equation of the inverse problem of the plane theory of elasticity journal, January 1976

A New Design Approach for Rapid Evaluation of Structural Modifications Using Neural Networks journal, January 2013

Structural optimization using evolution strategies and neural networks journal, April 1998

Soft computing methodologies for structural optimization journal, November 2003

Optimum design of high-rise steel buildings using an evolution strategy integrated parallel algorithm journal, November 2011

Coupling of scales in a multiscale simulation using neural networks journal, November 2008

Aims, scope, methods, history and unified terminology of computer-aided topology optimization in structural mechanics journal, April 2001

Subject independent facial expression recognition with robust face detection using a convolutional neural network journal, June 2003

Optimal shape design as a material distribution problem
journal, December 1989

Review of Metamodeling Techniques in Support of Engineering Design Optimization
journal, May 2006

Computational homogenization of nonlinear elastic materials using neural networks: NEURAL NETWORKS-BASED COMPUTATIONAL HOMOGENIZATION
journal, June 2015

Efficient topology optimization in MATLAB using 88 lines of code
journal, November 2010

Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
journal, January 1962

Face recognition: a convolutional neural-network approach
journal, January 1997

An integrated approach for optimum design of bridge decks using genetic algorithms and artificial neural networks
journal, July 2007

Optimization of Large-Scale 3-D Trusses Using Evolution Strategies and Neural Networks
journal, September 1999

Integral equation of the inverse problem of the plane theory of elasticity
journal, January 1976

A New Design Approach for Rapid Evaluation of Structural Modifications Using Neural Networks
journal, January 2013

Structural optimization using evolution strategies and neural networks
journal, April 1998

Soft computing methodologies for structural optimization
journal, November 2003

Optimum design of high-rise steel buildings using an evolution strategy integrated parallel algorithm
journal, November 2011

Coupling of scales in a multiscale simulation using neural networks
journal, November 2008

Aims, scope, methods, history and unified terminology of computer-aided topology optimization in structural mechanics
journal, April 2001

Subject independent facial expression recognition with robust face detection using a convolutional neural network
journal, June 2003