A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality

A new data-driven computational framework is developed to assist in the design and modeling of new material systems and structures. The proposed framework integrates three general steps: (1) design of experiments, where the input variables describing material geometry (microstructure), phase properties and external conditions are sampled; (2) efficient computational analyses of each design sample, leading to the creation of a material response database; and (3) machine learning applied to this database to obtain a new design or response model. In addition, the authors address the longstanding challenge of developing a data-driven approach applicable to problems that involve unacceptable computational expense when solved by standard analysis methods – e.g. finite element analysis of representative volume elements involving plasticity and damage. In these cases the framework includes the recently developed “self-consistent clustering analysis” method in order to build large databases suitable for machine learning. The authors believe that this will open new avenues to finding innovative materials with new capabilities in an era of high-throughput computing (“big-data”).

[1]  Mustafa Sonmez,et al.  Discrete optimum design of truss structures using artificial bee colony algorithm , 2011 .

[2]  Ole Sigmund,et al.  A 99 line topology optimization code written in Matlab , 2001 .

[3]  Jonathan Levin,et al.  Economics in the age of big data , 2014, Science.

[4]  Wei Chen,et al.  Stochastic microstructure characterization and reconstruction via supervised learning , 2016 .

[5]  I. Sobol.  Uniformly distributed sequences with an additional uniform property , 1976 .

[6]  Julien Yvonnet,et al.  Numerically explicit potentials for the homogenization of nonlinear elastic heterogeneous materials , 2009 .

[7]  Sie Chin Tjong,et al.  Novel Nanoparticle‐Reinforced Metal Matrix Composites with Enhanced Mechanical Properties , 2007 .

[8]  Yasuaki Seki,et al.  Biological materials: Structure and mechanical properties , 2008 .

[9]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[10]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[11]  Iannis Aifantis,et al.  CCR7 signalling as an essential regulator of CNS infiltration in T-cell leukaemia , 2009, Nature.

[12]  Ted Belytschko,et al.  A meshfree unification: reproducing kernel peridynamics , 2014, Computational Mechanics.

[13]  Yentl Swolfs,et al.  Fibre hybridisation in polymer composites: a review , 2014 .

[14]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[15]  Zeliang Liu,et al.  An extended micromechanics method for probing interphase properties in polymer nanocomposites , 2016 .

[16]  C. Lynch.  Big data: How do your data grow? , 2008, Nature.

[17]  A. O'Hagan,et al.  Bayesian emulation of complex multi-output and dynamic computer models , 2010 .

[18]  Jeremy Staum,et al.  Better simulation metamodeling: The why, what, and how of stochastic kriging , 2009, Proceedings of the 2009 Winter Simulation Conference (WSC).

[19]  Timothy W. Simpson,et al.  Sampling Strategies for Computer Experiments: Design and Analysis , 2001 .

[20]  Marco Buongiorno Nardelli,et al.  The high-throughput highway to computational materials design. , 2013, Nature materials.

[21]  Timothy W. Simpson,et al.  Metamodels for Computer-based Engineering Design: Survey and recommendations , 2001, Engineering with Computers.

[22]  August G. Domel,et al.  An efficient multiscale model of damping properties for filled elastomers with complex microstructures , 2014 .

[23]  Maria F. Sassano,et al.  Automated design of ligands to polypharmacological profiles , 2012, Nature.

[24]  Albert A. Groenwold,et al.  Sizing design of truss structures using particle swarms , 2003 .

[25]  Paola Annoni,et al.  Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index , 2010, Comput. Phys. Commun..

[26]  H. Faure.  Discrépance de suites associées à un système de numération (en dimension s) , 1982 .

[27]  M. D. McKay,et al.  A comparison of three methods for selecting values of input variables in the analysis of output from a computer code , 2000 .

[28]  Clara E Yoon,et al.  Earthquake detection through computationally efficient similarity search , 2015, Science Advances.

[29]  Bertrand Iooss,et al.  Latin hypercube sampling with inequality constraints , 2009, 0909.0329.

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

[31]  R. Altman,et al.  Data-Driven Prediction of Drug Effects and Interactions , 2012, Science Translational Medicine.

[32]  M. Rietschel,et al.  Neuropsychosocial profiles of current and future adolescent alcohol misusers , 2014, Nature.

[33]  Tom M Mitchell,et al.  Mining Our Reality , 2009, Science.

[34]  J. Michel,et al.  Nonuniform transformation field analysis , 2003 .

[35]  Muratahan Aykol,et al.  Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) , 2013 .

[36]  Tony Reichhardt,et al.  NASA reworks its sums after Mars fiasco , 1999, Nature.

[37]  N. Perrimon,et al.  Protein Complex–Based Analysis Framework for High-Throughput Data Sets , 2013, Science Signaling.

[38]  Christian Soize,et al.  Computational nonlinear stochastic homogenization using a nonconcurrent multiscale approach for hyperelastic heterogeneous microstructures analysis , 2012, International Journal for Numerical Methods in Engineering.

[39]  Gerbrand Ceder,et al.  Predicting crystal structure by merging data mining with quantum mechanics , 2006, Nature materials.

[40]  Miguel A. Bessa,et al.  High-fidelity micro-scale modeling of the thermo-visco-plastic behavior of carbon fiber polymer matrix composites , 2015 .

[41]  A. Sudjianto,et al.  An Efficient Algorithm for Constructing Optimal Design of Computer Experiments , 2005, DAC 2003.

[42]  T Reichhardt,et al.  It's sink or swim as a tidal wave of data approaches , 1999, Nature.

[43]  David Amsallem,et al.  Automatised selection of load paths to construct reduced-order models in computational damage micromechanics: from dissipation-driven random selection to Bayesian optimization , 2016, Computational Mechanics.

[44]  Wing Kam Liu,et al.  Reproducing kernel particle methods , 1995 .

[45]  M. Daly,et al.  A map of human genome sequence variation containing 1.42 million single nucleotide polymorphisms , 2001, Nature.

[46]  Chris Mattmann,et al.  Computing: A vision for data science , 2013, Nature.

[47]  António R. Melro,et al.  Micromechanical analysis of polymer composites reinforced by unidirectional fibres: Part I – Constitutive modelling , 2013 .

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

[49]  Antoine Cully,et al.  Robots that can adapt like animals , 2014, Nature.

[50]  V. Kouznetsova,et al.  Multi‐scale constitutive modelling of heterogeneous materials with a gradient‐enhanced computational homogenization scheme , 2002 .

[51]  Pedro P. Camanho,et al.  Micromechanical analysis of polymer composites reinforced by unidirectional fibres: Part II – Micromechanical analyses , 2013 .

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

[53]  Pedro P. Camanho,et al.  Generation of random distribution of fibres in long-fibre reinforced composites , 2008 .

[54]  P. Holmes,et al.  The Proper Orthogonal Decomposition in the Analysis of Turbulent Flows , 1993 .

[55]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[56]  Hongyi Xu,et al.  A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures , 2015 .

[57]  Wei Chen,et al.  Microstructure reconstruction and structural equation modeling for computational design of nanodielectrics , 2015, Integrating Materials and Manufacturing Innovation.

[58]  J. Fröhlich,et al.  The effect of filler–filler and filler–elastomer interaction on rubber reinforcement , 2005 .

[59]  A. Ammar,et al.  PGD-Based Computational Vademecum for Efficient Design, Optimization and Control , 2013, Archives of Computational Methods in Engineering.

[60]  K. Deb,et al.  Design of truss-structures for minimum weight using genetic algorithms , 2001 .

[61]  Barry L. Nelson,et al.  Stochastic kriging for simulation metamodeling , 2008, 2008 Winter Simulation Conference.

[62]  Blaz Zupan,et al.  Predictive data mining in clinical medicine: Current issues and guidelines , 2008, Int. J. Medical Informatics.

[63]  J. Marsden,et al.  Dimensional model reduction in non‐linear finite element dynamics of solids and structures , 2001 .

[64]  G. Matheron.  Principles of geostatistics , 1963 .

[65]  Lincoln D. Stein,et al.  Identification of pre-leukemic hematopoietic stem cells in acute leukemia , 2014, Nature.

[66]  Paul Raccuglia,et al.  Machine-learning-assisted materials discovery using failed experiments , 2016, Nature.

[67]  M. Boyce,et al.  A three-dimensional constitutive model for the large stretch behavior of rubber elastic materials , 1993 .

[68]  Adrien Leygue,et al.  An overview of the proper generalized decomposition with applications in computational rheology , 2011 .

[69]  M. Claeys-Bruno,et al.  Construction of space-filling designs using WSP algorithm for high dimensional spaces , 2012 .

[70]  Runze Li,et al.  Design and Modeling for Computer Experiments , 2005 .

[71]  Mehdi Hojjati,et al.  Review article: Polymer-matrix Nanocomposites, Processing, Manufacturing, and Application: An Overview , 2006 .

[72]  António R. Melro,et al.  Mechanics of hybrid polymer composites: analytical and computational study , 2016 .

[73]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[74]  Kristin A. Persson,et al.  Predicting crystal structures with data mining of quantum calculations. , 2003, Physical review letters.

[75]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

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

[77]  N. Kikuchi,et al.  Simulation of the multi-scale convergence in computational homogenization approaches , 2000 .

[78]  Hervé Moulinec,et al.  A numerical method for computing the overall response of nonlinear composites with complex microstructure , 1998, ArXiv.

[79]  Geoffrey M. Laslett,et al.  Kriging and Splines: An Empirical Comparison of their Predictive Performance in Some Applications , 1994 .

[80]  D. V. van Essen,et al.  Challenges and Opportunities in Mining Neuroscience Data , 2011, Science.

[81]  Julien Yvonnet,et al.  The reduced model multiscale method (R3M) for the non-linear homogenization of hyperelastic media at finite strains , 2007, J. Comput. Phys..

[82]  Michael Ghil,et al.  An end-to-end assessment of extreme weather impacts on food security , 2015 .

[83]  S. Pellegrino,et al.  Imperfection-insensitive axially loaded thin cylindrical shells , 2015 .

[84]  G. Michel,et al.  Transfer of carbohydrate-active enzymes from marine bacteria to Japanese gut microbiota , 2010, Nature.

[85]  Natalia N. Ivanova,et al.  Metagenomic and functional analysis of hindgut microbiota of a wood-feeding higher termite , 2007, Nature.

[86]  Eva Riccomagno,et al.  Experimental Design and Observation for Large Systems , 1996, Journal of the Royal Statistical Society: Series B (Methodological).

[87]  Miguel A. Bessa,et al.  Self-consistent clustering analysis: An efficient multi-scale scheme for inelastic heterogeneous materials , 2016 .

[88]  P. Ladevèze,et al.  The LATIN multiscale computational method and the Proper Generalized Decomposition , 2010 .

[89]  Marco Buongiorno Nardelli,et al.  AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations , 2012 .

[90]  S. Hanash,et al.  Mining the plasma proteome for cancer biomarkers , 2008, Nature.

[91]  I. Sobol.  On the distribution of points in a cube and the approximate evaluation of integrals , 1967 .

[92]  Somnath Ghosh,et al.  Two scale analysis of heterogeneous elastic-plastic materials with asymptotic homogenization and Voronoi cell finite element model , 1996 .

[93]  Frank Greer,et al.  Fabrication and deformation of three-dimensional hollow ceramic nanostructures. , 2013, Nature materials.

[94]  Yang Li,et al.  A Descriptor-Based Design Methodology for Developing Heterogeneous Microstructural Materials System , 2014 .

[95]  Jean-Louis Chaboche,et al.  On the capabilities of mean-field approaches for the description of plasticity in metal matrix composites , 2005 .

[96]  J. Hammersley.  MONTE CARLO METHODS FOR SOLVING MULTIVARIABLE PROBLEMS , 1960 .

[97]  Jacob Fish,et al.  Eigendeformation-based reduced order homogenization for failure analysis of heterogeneous materials , 2007 .

[98]  O. Dubrule.  Comparing splines and kriging , 1984 .

[99]  Thomas A. Vilgis,et al.  Reinforcement of Elastomers , 2002 .

[100]  F. Feyel.  A multilevel finite element method (FE2) to describe the response of highly non-linear structures using generalized continua , 2003 .

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

[102]  K. Bertoldi,et al.  Harnessing buckling to design tunable locally resonant acoustic metamaterials. , 2014, Physical review letters.

[103]  J. Chaboche,et al.  FE2 multiscale approach for modelling the elastoviscoplastic behaviour of long fibre SiC/Ti composite materials , 2000 .

[104]  A. Jourdan,et al.  Optimal Latin hypercube designs for the Kullback–Leibler criterion , 2010 .

[105]  G. Dvorak.  Transformation field analysis of inelastic composite materials , 1992, Proceedings of the Royal Society of London. Series A: Mathematical and Physical Sciences.

[106]  John Wood,et al.  Dealing with data: upgrading infrastructure. , 2011, Science.

[107]  T. Belytschko,et al.  Element‐free Galerkin methods , 1994 .