Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment

Biomimicry, adapting and implementing nature's designs provides an adequate first-order solution to achieving superior mechanical properties. However, the design space is too vast even using biomimetic designs as prototypes for optimization. Here, we propose a new approach to design hierarchical materials using machine learning, trained with a database of hundreds of thousands of structures from finite element analysis, together with a self-learning algorithm for discovering high-performing materials where inferior designs are phased out for superior candidates. Results show that our approach can create microstructural patterns that lead to tougher and stronger materials, which are validated through additive manufacturing and testing. We further show that machine learning can be used as an alternative method of coarse-graining – analyzing and designing materials without the use of full microstructural data. This novel paradigm of smart additive manufacturing can aid in the discovery and fabrication of new material designs boasting orders of magnitude increase in computational efficacy over conventional methods.

[1]  Marian Stewart Bartlett,et al.  Face recognition by independent component analysis , 2002, IEEE Trans. Neural Networks.

[2]  Chiara Bisagni,et al.  Post-buckling optimisation of composite stiffened panels using neural networks , 2002 .

[3]  Richard Weinkamer,et al.  Nature’s hierarchical materials , 2007 .

[4]  Sanguthevar Rajasekaran,et al.  Accelerating materials property predictions using machine learning , 2013, Scientific Reports.

[5]  Nicola Pugno,et al.  Hierarchical Fibers with a Negative Poisson’s Ratio for Tougher Composites , 2013, Materials.

[6]  Christopher B. Williams,et al.  Multiple-Material Topology Optimization of Compliant Mechanisms Created Via PolyJet Three-Dimensional Printing , 2014 .

[7]  Markus J. Buehler,et al.  Optimization of Composite Fracture Properties: Method, Validation, and Applications , 2016 .

[8]  Grace X. Gu,et al.  Bone‐Inspired Materials by Design: Toughness Amplification Observed Using 3D Printing and Testing   , 2016 .

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

[10]  Ian H. Witten,et al.  Data Mining, Fourth Edition: Practical Machine Learning Tools and Techniques , 2016 .

[11]  Mary C. Boyce,et al.  3D printed, bio-inspired prototypes and analytical models for structured suture interfaces with geometrically-tuned deformation and failure behavior , 2014 .

[12]  Markus J. Buehler,et al.  Nacre-inspired design of graphene oxide–polydopamine nanocomposites for enhanced mechanical properties and multi-functionalities , 2017, Nano Futures.

[13]  Shiwei Zhou,et al.  Simple cubic three‐dimensional auxetic metamaterials , 2014 .

[14]  Grace X. Gu,et al.  Biomimetic additive manufactured polymer composites for improved impact resistance , 2016 .

[15]  Charlie C. L. Wang,et al.  The status, challenges, and future of additive manufacturing in engineering , 2015, Comput. Aided Des..

[16]  John R. Anderson,et al.  Machine learning - an artificial intelligence approach , 1982, Symbolic computation.

[17]  Ann B. Lee,et al.  Diffusion maps and coarse-graining: a unified framework for dimensionality reduction, graph partitioning, and data set parameterization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Markus J Buehler,et al.  Three-Dimensional-Printing of Bio-Inspired Composites. , 2016, Journal of biomechanical engineering.

[19]  R. Ritchie The conflicts between strength and toughness. , 2011, Nature materials.

[20]  Nicholas Lubbers,et al.  Inferring low-dimensional microstructure representations using convolutional neural networks , 2016, Physical review. E.

[21]  Abhinav Vishnu,et al.  Deep learning for computational chemistry , 2017, J. Comput. Chem..

[22]  Grace X. Gu,et al.  Algorithm-driven design of fracture resistant composite materials realized through additive manufacturing , 2017 .

[23]  Clément Sanchez,et al.  Biomimetism and bioinspiration as tools for the design of innovative materials and systems , 2005, Nature materials.

[24]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[25]  Yi Min Xie,et al.  Experiments and parametric studies on 3D metallic auxetic metamaterials with tuneable mechanical properties , 2015 .

[26]  Grace X. Gu,et al.  Hierarchically Enhanced Impact Resistance of Bioinspired Composites , 2017, Advanced materials.

[27]  Beom Jun Kim Geographical coarse graining of complex networks. , 2004, Physical review letters.

[28]  R. Ritchie,et al.  Bioinspired structural materials. , 2014, Nature materials.

[29]  G. Lauder,et al.  Biomimetic shark skin: design, fabrication and hydrodynamic function , 2014, Journal of Experimental Biology.

[30]  Grace X. Gu,et al.  Printing nature: Unraveling the role of nacre's mineral bridges. , 2017, Journal of the mechanical behavior of biomedical materials.

[31]  Zhongya Zhang,et al.  Artificial neural networks applied to polymer composites: a review , 2003 .

[32]  A. Choudhary,et al.  Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science , 2016 .

[33]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[34]  J. Lewis,et al.  3D‐Printing of Lightweight Cellular Composites , 2014, Advanced materials.