skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Multiscale topology optimization using neural network surrogate models

Journal Article · · Computer Methods in Applied Mechanics and Engineering
 [1];  [1];  [1];  [1]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
+ Show Author Affiliations

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 analytical models e.g. classical beam theory. Because the derivative of the surrogate model is important for sensitivity analysis of the macroscale topology optimization, a neural network training procedure based on the Sobolev norm is described. Since the SIMP method is not appropriate for spatially varying lattices, an alternative method is developed to enable creation of void regions. Lastly, the efficacy of this approach is demonstrated via several examples in which the optimal graded metamaterial outperforms a traditional solid structure.

Research Organization:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
AC52-07NA27344
OSTI ID:
1557076
Alternate ID(s):
OSTI ID: 1636038
Report Number(s):
LLNL-JRNL-760619; 948858
Journal Information:
Computer Methods in Applied Mechanics and Engineering, Vol. 346, Issue C; ISSN 0045-7825
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 81 works
Citation information provided by
Web of Science

References (30)

Optimal shape design as a material distribution problem journal December 1989
Aims, scope, methods, history and unified terminology of computer-aided topology optimization in structural mechanics journal April 2001
Sufficiency of a finite exponent in SIMP (power law) methods journal April 2001
Topology optimization of non-linear elastic structures and compliant mechanisms journal March 2001
An element removal and reintroduction strategy for the topology optimization of structures and compliant mechanisms journal January 2003
Filters in topology optimization based on Helmholtz-type differential equations journal December 2010
Free material optimization via mathematical programming journal October 1997
Free material optimization: recent progress† journal February 2008
Shape optimization by the homogenization method journal March 1997
A geometric projection method for designing three-dimensional open lattices with inverse homogenization: A geometric projection method journal July 2017
Error estimates and condition numbers for radial basis function interpolation journal April 1995
Universal Approximation Using Radial-Basis-Function Networks journal June 1991
Multilayer feedforward networks are universal approximators journal January 1989
Interpolation and rates of convergence for a class of neural networks journal March 2009
Approximation capability of interpolation neural networks journal December 2010
On learning the derivatives of an unknown mapping with multilayer feedforward networks journal January 1992
Neural networks as material models within a multiscale approach journal October 2009
Accurate cyclic plastic analysis using a neural network material model journal March 2004
Artificial Neural Networks in numerical modelling of composites journal May 2009
Neural network constitutive modelling for non-linear characterization of anisotropic materials journal August 2010
Neural network based constitutive model for elastomeric foams journal July 2008
A neural network-based surrogate model for carbon nanotubes with geometric nonlinearities journal January 2018
On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming journal April 2005
Optimal lattice-structured materials journal November 2016
Approximation of a function and its derivative with a neural network journal January 1992
Approximation of function and its derivatives using radial basis function networks journal March 2003
On the limited memory BFGS method for large scale optimization journal August 1989
Data dimensionality estimation methods: a survey journal December 2003
Polynomial Bounds for VC Dimension of Sigmoidal and General Pfaffian Neural Networks journal February 1997
Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks journal November 1998

Cited By (1)

Simple, accurate surrogate models of the elastic response of three-dimensional open truss micro-architectures with applications to multiscale topology design journal May 2019

Figures / Tables (17)

Figure 1(p. 13)figure Figure 1
Figure 2(p. 15)figure Figure 2
Table 1(p. 20)table Table 1
Table 2(p. 20)table Table 2
Figure 3(p. 21)figure Figure 3
Figure 4(p. 22)figure Figure 4
Figure 5(p. 23)figure Figure 5
Figure 6(p. 24)figure Figure 6
Figure 7(p. 25)figure Figure 7
Figure 8(p. 26)figure Figure 8
Table 3(p. 27)table Table 3
Figure 9(p. 28)figure Figure 9
Figure 10(p. 29)figure Figure 10
Figure 11(p. 30)figure Figure 11
Figure 12(p. 31)figure Figure 12
Figure 13(p. 31)figure Figure 13
Table 4(p. 31)table Table 4

Similar Records

Simple, accurate surrogate models of the elastic response of three-dimensional open truss micro-architectures with applications to multiscale topology design
Journal Article · Sat May 25 00:00:00 EDT 2019 · Structural and Multidisciplinary Optimization · OSTI ID:1557076
+2 more
Operator learning for predicting multiscale bubble growth dynamics
Journal Article · Wed Mar 10 00:00:00 EST 2021 · Journal of Chemical Physics · OSTI ID:1557076
+3 more
Explicit physics-informed neural networks for nonlinear closure: The case of transport in tissues
Journal Article · Fri Oct 29 00:00:00 EDT 2021 · Journal of Computational Physics · OSTI ID:1557076

Related Subjects

42 ENGINEERING
97 MATHEMATICS AND COMPUTING
Topology optimization
Multiscale analysis
Neural networks
Material models