Predictive modeling of dynamic fracture growth in brittle materials with machine learning

Abstract We use simulation data from a high fidelity Finite-Discrete Element Model to build an efficient Machine Learning (ML) approach to predict fracture growth and coalescence. Our goal is for the ML approach to be used as an emulator in place of the computationally intensive high fidelity models in an uncertainty quantification framework where thousands of forward runs are required. The failure of materials with various fracture configurations (size, orientation and the number of initial cracks) are explored and used as data to train our ML model. This novel approach has shown promise in predicting spatial (path to failure) and temporal (time to failure) aspects of brittle material failure. Predictions of where dominant fracture paths formed within a material were ∼85% accurate and the time of material failure deviated from the actual failure time by an average of ∼16%. Additionally, the ML model achieves a reduction in computational cost by multiple orders of magnitude.

[1]  José L. Zapico,et al.  Finite element model updating of a small steel frame using neural networks , 2008 .

[2]  W. C. Cooley,et al.  Mechanics of Brittle Fracture , 1982 .

[3]  M. Ortiz,et al.  Computational modelling of impact damage in brittle materials , 1996 .

[4]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[5]  Tshilidzi Marwala,et al.  Finite Element Model Updating Using Computational Intelligence Techniques: Applications to Structural Dynamics , 2010 .

[6]  Jiann-Wen Ju,et al.  Effective Elastic Moduli of Two-Dimensional Brittle Solids With Interacting Microcracks, Part I: Basic Formulations , 1994 .

[7]  S Karra,et al.  Where Does Water Go During Hydraulic Fracturing? , 2016, Ground water.

[8]  A. Needleman Computational mechanics at the mesoscale , 2000 .

[9]  Taiwo Oladipupo Ayodele,et al.  Machine Learning Overview , 2010 .

[10]  Huajian Gao,et al.  Modern topics and challenges in dynamic fracture , 2005 .

[11]  H. Saunders,et al.  Introduction to fracture mechanics , 1984 .

[12]  Antonio Munjiza,et al.  A generalized anisotropic deformation formulation for geomaterials , 2016, 1805.06024.

[13]  D. Owen,et al.  A combined finite‐discrete element method in transient dynamics of fracturing solids , 1995 .

[14]  L. J. Sluys,et al.  Coupled-volume multi-scale modelling of quasi-brittle material , 2008 .

[15]  Gerhard Weikum Foundations of Statistical Natural Language Processing - Book Review , 2002, SIGMOD Rec..

[16]  L. G. Margolin,et al.  Elastic moduli of a cracked body , 1983 .

[17]  Ronald Davis,et al.  Neural networks and deep learning , 2017 .

[18]  Adnan Ibrahimbegovic,et al.  Microscale and mesoscale discrete models for dynamic fracture of structures built of brittle material , 2003 .

[19]  Gregory M. Odegard,et al.  Computational materials: Multi-scale modeling and simulation of nanostructured materials , 2005 .

[20]  Jay Fineberg,et al.  The dynamics of rapid fracture: instabilities, nonlinearities and length scales , 2013, Reports on progress in physics. Physical Society.

[21]  Jian-Fu Shao,et al.  Experimental investigation and poroplastic modelling of saturated porous geomaterials , 2012 .

[22]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[23]  G. I. Barenblatt THE MATHEMATICAL THEORY OF EQUILIBRIUM CRACKS IN BRITTLE FRACTURE , 1962 .

[24]  D. Opitz,et al.  Popular Ensemble Methods: An Empirical Study , 1999, J. Artif. Intell. Res..

[25]  A. Munjiza The Combined Finite-Discrete Element Method , 2004 .

[26]  Lior Rokach,et al.  Data Mining with Decision Trees - Theory and Applications , 2007, Series in Machine Perception and Artificial Intelligence.

[27]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[28]  A. A. Griffith The Phenomena of Rupture and Flow in Solids , 1921 .

[29]  Michael P Marder,et al.  Particle methods in the study of fracture , 2015, International Journal of Fracture.

[30]  Victor S. Sheng,et al.  Class Imbalance Problem , 2010, Encyclopedia of Machine Learning.

[31]  Antonio Munjiza,et al.  Validation of a three-dimensional Finite-Discrete Element Method using experimental results of the Split Hopkinson Pressure Bar test , 2014 .

[32]  P. C. Paris,et al.  A Critical Analysis of Crack Propagation Laws , 1963 .

[33]  Dennis M. Dimiduk,et al.  Development of intermetallic materials for aerospace systems , 1992 .

[34]  A. Hillerborg,et al.  Analysis of crack formation and crack growth in concrete by means of fracture mechanics and finite elements , 1976 .

[35]  Concha Bielza,et al.  Machine Learning in Bioinformatics , 2008, Encyclopedia of Database Systems.