Data-Driven Structural Design Optimization for Petal-Shaped Auxetics Using Isogeometric Analysis

Focusing on the structural optimization of auxetic materials using data-driven methods, a back-propagation neural network (BPNN) based design framework is developed for petal-shaped auxetics using isogeometric analysis. Adopting a NURBSbased parametric modelling scheme with a small number of design variables, the highly nonlinear relation between the input geometry variables and the effective material properties is obtained using BPNN-based fitting method, and demonstrated in this work to give high accuracy and efficiency. Such BPNN-based fitting functions also enable an easy analytical sensitivity analysis, in contrast to the generally complex procedures of typical shape and size sensitivity approaches.

[1]  Martin van Hecke,et al.  Combinatorial design of textured mechanical metamaterials , 2016, Nature.

[2]  Yi Min Xie,et al.  Auxetic metamaterials and structures: a review , 2018 .

[3]  Xiaoping Qian,et al.  Isogeometric Shape Optimization on Triangulations , 2016, DAC 2016.

[4]  O. Sigmund.  Tailoring materials with prescribed elastic properties , 1995 .

[5]  Damiano Pasini,et al.  Multiscale isogeometric topology optimization for lattice materials , 2017 .

[6]  W. Wall,et al.  Isogeometric structural shape optimization , 2008 .

[7]  Shan Tang,et al.  Clustering discretization methods for generation of material performance databases in machine learning and design optimization , 2019, Computational Mechanics.

[8]  Yingjun Wang,et al.  Structural Design Optimization Using Isogeometric Analysis: A Comprehensive Review , 2018, Computer Modeling in Engineering & Sciences.

[9]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[10]  Yilin Zhu,et al.  Systematic design of tetra-petals auxetic structures with stiffness constraint , 2019, Materials & Design.

[11]  Guangyao Li,et al.  Topology optimization of periodic lattice structures taking into account strain gradient , 2018, Computers & Structures.

[12]  Xiang Zhang,et al.  Negative refractive index in chiral metamaterials. , 2009, Physical review letters.

[13]  J. Bonache,et al.  Babinet principle applied to the design of metasurfaces and metamaterials. , 2004, Physical review letters.

[14]  Trenton Kirchdoerfer,et al.  Data Driven Computing with Noisy Material Data Sets , 2017, 1702.01574.

[15]  Fengwen Wang,et al.  Systematic design of 3D auxetic lattice materials with programmable Poisson’s ratio for finite strains , 2018 .

[16]  T. Shi,et al.  Stable hole nucleation in level set based topology optimization by using the material removal scheme of BESO , 2019, Computer Methods in Applied Mechanics and Engineering.

[17]  Liang Gao,et al.  Robust topology optimization for periodic structures by combining sensitivity averaging with a semianalytical method , 2018, International Journal for Numerical Methods in Engineering.

[18]  Georgios E. Stavroulakis,et al.  Topology optimization for compliant mechanisms, using evolutionary-hybrid algorithms and application to the design of auxetic materials , 2012 .

[19]  Ameet Talwalkar,et al.  Foundations of Machine Learning , 2012, Adaptive computation and machine learning.

[20]  Xiangyang Cui,et al.  Concurrent topological design of composite structures and the underlying multi-phase materials , 2017 .

[21]  Hua Xu,et al.  Graphics processing unit (GPU) accelerated fast multipole BEM with level-skip M2L for 3D elasticity problems , 2015, Adv. Eng. Softw..

[22]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[23]  R. Lakes,et al.  Poisson's ratio and modern materials , 2011, Nature Materials.

[24]  T. Hughes,et al.  Isogeometric analysis : CAD, finite elements, NURBS, exact geometry and mesh refinement , 2005 .

[25]  Damiano Pasini,et al.  Hip Implant Design With Three-Dimensional Porous Architecture of Optimized Graded Density , 2018, Journal of Mechanical Design.

[26]  P. Breitkopf,et al.  Concurrent topology optimization design of material and structure within FE2 nonlinear multiscale analysis framework , 2014 .

[27]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[28]  Zeliang Liu,et al.  Exploring the 3D architectures of deep material network in data-driven multiscale mechanics , 2019, Journal of the Mechanics and Physics of Solids.

[29]  T. Shi,et al.  Optimization of composite structures with continuous spatial variation of fiber angle through Shepard interpolation , 2017 .

[30]  Marc-André Keip,et al.  A data-driven approach to nonlinear elasticity , 2018 .

[31]  Roderic S. Lakes,et al.  Negative-Poisson's-Ratio Materials: Auxetic Solids , 2017 .

[32]  Zhen-Pei Wang,et al.  Optimal form and size characterization of planar isotropic petal-shaped auxetics with tunable effective properties using IGA , 2018, Composite Structures.

[33]  Yongmin Liu,et al.  Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials. , 2018, ACS nano.

[34]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[35]  Markus J. Buehler,et al.  De novo composite design based on machine learning algorithm , 2018 .

[36]  Chenglie Du,et al.  An integrated micromechanical model and BP neural network for predicting elastic modulus of 3-D multi-phase and multi-layer braided composite , 2015 .

[37]  Gang Wang,et al.  An adaptive dual-information FMBEM for 3D elasticity and its GPU implementation , 2013 .

[38]  Mohamed Rachik,et al.  Micromechanical modeling of the effect of phase distribution topology on the plastic behavior of dual-phase steels , 2019, Computational Materials Science.

[39]  Jakob S. Jensen,et al.  Topology Optimized Architectures with Programmable Poisson's Ratio over Large Deformations , 2015, Advanced materials.

[40]  Zeliang Liu,et al.  A Deep Material Network for Multiscale Topology Learning and Accelerated Nonlinear Modeling of Heterogeneous Materials , 2018, Computer Methods in Applied Mechanics and Engineering.

[41]  Ajmal Mian,et al.  Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey , 2018, IEEE Access.

[42]  Jakob S. Jensen,et al.  Design of materials with prescribed nonlinear properties , 2014 .

[43]  O. Sigmund.  Materials with prescribed constitutive parameters: An inverse homogenization problem , 1994 .

[44]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[45]  Wei Chen,et al.  A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality , 2017 .

[46]  Nong Zhang,et al.  Level-set topology optimization for multimaterial and multifunctional mechanical metamaterials , 2017 .

[47]  Justin Dirrenberger,et al.  Isogeometric shape optimization of smoothed petal auxetic structures via computational periodic homogenization , 2017 .

[48]  Matej Vesenjak,et al.  Auxetic Cellular Materials - a Review , 2016 .

[49]  Thomas J. R. Hughes,et al.  Isogeometric shell analysis: The Reissner-Mindlin shell , 2010 .

[50]  Julien Yvonnet,et al.  COMPUTATIONAL HOMOGENIZATION METHOD AND REDUCED DATABASE MODEL FOR HYPERELASTIC HETEROGENEOUS STRUCTURES , 2013 .

[51]  Piotr Breitkopf,et al.  Recent Advances on Topology Optimization of Multiscale Nonlinear Structures , 2017 .

[52]  Chang Liu,et al.  Machine Learning-Driven Real-Time Topology Optimization Under Moving Morphable Component-Based Framework , 2018, Journal of Applied Mechanics.

[53]  Xianda Xie,et al.  A new isogeometric topology optimization using moving morphable components based on R-functions and collocation schemes , 2018, Computer Methods in Applied Mechanics and Engineering.

[54]  Hong Hu,et al.  Auxetic materials and their potential applications in textiles , 2014 .

[55]  R. Lakes.  Foam Structures with a Negative Poisson's Ratio , 1987, Science.

[56]  B. A. Le,et al.  Computational homogenization of nonlinear elastic materials using neural networks , 2015 .

[57]  Xiaoping Qian,et al.  Full analytical sensitivities in NURBS based isogeometric shape optimization , 2010 .

[58]  Martin L. Dunn,et al.  Isogeometric shape optimization of nonlinear, curved 3D beams and beam structures , 2019, Computer Methods in Applied Mechanics and Engineering.

[59]  Chao Mei,et al.  GPU parallel strategy for parameterized LSM-based topology optimization using isogeometric analysis , 2017 .

[60]  Terry Senior,et al.  Quasi-static characterisation and impact testing of auxetic foam for sports safety applications , 2016 .

[61]  Dan Wang,et al.  Streamline stiffener path optimization (SSPO) for embedded stiffener layout design of non-uniform curved grid-stiffened composite (NCGC) structures , 2019, Computer Methods in Applied Mechanics and Engineering.

[62]  Z. Kang,et al.  Topological shape optimization of microstructural metamaterials using a level set method , 2014 .

[63]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[64]  Tao Chen,et al.  Back propagation neural network with adaptive differential evolution algorithm for time series forecasting , 2015, Expert Syst. Appl..

[65]  Yilin Zhu,et al.  Auxetic hexachiral structures with wavy ligaments for large elasto-plastic deformation , 2018 .

[66]  R. Singer,et al.  Design of Auxetic Structures via Mathematical Optimization , 2011, Advanced materials.

[67]  Yingjun Wang,et al.  A triple acceleration method for topology optimization , 2019, Structural and Multidisciplinary Optimization.

[68]  Tielin Shi,et al.  A cascadic multilevel optimization algorithm for the design of composite structures with curvilinear fiber based on Shepard interpolation , 2018 .

[69]  Ser Tong Quek,et al.  Isogeometric shape optimization of smoothed petal auxetics with prescribed nonlinear deformation , 2019, Computer Methods in Applied Mechanics and Engineering.

[70]  Keith Winwood,et al.  Review of Auxetic Materials for Sports Applications: Expanding Options in Comfort and Protection , 2018, Applied Sciences.

[71]  Seonho Cho,et al.  Isogeometric configuration design optimization of shape memory polymer curved beam structures for extremal negative Poisson’s ratio , 2018, Structural and Multidisciplinary Optimization.

[72]  C. D. Boor,et al.  On Calculating B-splines , 1972 .

[73]  Trenton Kirchdoerfer,et al.  Data-driven computational mechanics , 2015, 1510.04232.

[74]  Raj Das,et al.  Three Decades of Auxetics Research − Materials with Negative Poisson's Ratio: A Review , 2016 .

[75]  Pineda,et al.  Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[76]  D. Benson,et al.  Isogeometric analysis for parameterized LSM-based structural topology optimization , 2016 .

[77]  M. Kafesaki,et al.  Chiral metamaterials: simulations and experiments , 2009 .