Designing phononic crystal with anticipated band gap through a deep learning based data-driven method

Abstract Phononic crystal is a type of artificial heterogeneous material constituted by a periodic repetition of cells. This characteristic provides a possible solution to the accurate manipulation of acoustic and elastic waves. For this reason, phononic crystal is of application potentials in vibration and noise reduction, filtering, acoustic lens, acoustic imaging, and acoustic stealth, etc. It is thus of significance in the fields of information, communication, and medical applications. To design phononic crystal with anticipated manipulation characteristic has become a research hotspot in recent years. However, how to accurately manipulate acoustic and mechanical wave is still a major challenge for existing designing approaches. Assisted by image-based finite element analysis and deep learning, a data-driven approach is proposed in this study for designing phononic crystals. An auto-encoder is trained to extract the topological features from sample images. Finite element analysis is employed to study the band gaps of samples. A multi-layer perceptron is trained to establish the inherent relation between band gaps and topological features. The trained models are ultimately employed to design phononic crystals with anticipated band gaps. Not limited to this material, the proposed method could be further extended to design various structured mechanical materials with specific functionalities.

[1]  Yukio Kosugi,et al.  Neural network representation of finite element method , 1994, Neural Networks.

[2]  Jan Sokolowski,et al.  On the Topological Derivative in Shape Optimization , 1999 .

[3]  Wei Chen,et al.  Microstructural Materials Design Via Deep Adversarial Learning Methodology , 2018, Journal of Mechanical Design.

[4]  O. Bou Matar,et al.  Band structures tunability of bulk 2D phononic crystals made of magneto-elastic materials , 2011 .

[5]  G. Allaire,et al.  Structural optimization using sensitivity analysis and a level-set method , 2004 .

[6]  O. V. Stryk,et al.  Modelling and simulation of electro- and magnetorheological fluid dampers , 2002 .

[7]  T. Rabczuk,et al.  A Deep Collocation Method for the Bending Analysis of Kirchhoff Plate , 2021, Computers, Materials & Continua.

[8]  Chuanzeng Zhang,et al.  Topological optimization of two-dimensional phononic crystals based on the finite element method and genetic algorithm , 2014 .

[9]  Y. L. Cun,et al.  Modèles connexionnistes de l'apprentissage , 1987 .

[10]  Genki Yagawa,et al.  Implicit constitutive modelling for viscoplasticity using neural networks , 1998 .

[11]  Masoud Rahimi,et al.  Prediction of heat transfer and flow characteristics in helically coiled tubes using artificial neural networks , 2012 .

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

[13]  Andres Tovar,et al.  An efficient 3D topology optimization code written in Matlab , 2014 .

[14]  Yunlian Qi,et al.  Development of constitutive relationship model of Ti600 alloy using artificial neural network , 2010 .

[15]  S. S. Nanthakumar,et al.  Inverse design of quantum spin hall-based phononic topological insulators , 2019, Journal of the Mechanics and Physics of Solids.

[16]  M. Bendsøe,et al.  A topological derivative method for topology optimization , 2007 .

[17]  Andrey Kazennov,et al.  The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology , 2016, Oncotarget.

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

[19]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[20]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[21]  Zongfu Yu,et al.  Training Deep Neural Networks for the Inverse Design of Nanophotonic Structures , 2017, 2019 Conference on Lasers and Electro-Optics (CLEO).

[22]  Yan Pennec,et al.  Two-dimensional phononic crystals: Examples and applications , 2010 .

[23]  Eleftherios N. Economou,et al.  Elastic and acoustic wave band structure , 1992 .

[24]  Raşit Köker,et al.  Neural network based prediction of mechanical properties of particulate reinforced metal matrix composites using various training algorithms , 2007 .

[25]  Eleftherios N. Economou,et al.  Classical vibrational modes in phononic lattices: theory and experiment , 2005 .

[26]  Li-Yang Zheng,et al.  Granular monolayers : wave dynamics and topological properties , 2017 .

[27]  Alán Aspuru-Guzik,et al.  Inverse molecular design using machine learning: Generative models for matter engineering , 2018, Science.

[28]  Kunihiko Fukushima,et al.  Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Visual Pattern Recognition , 1982 .

[29]  Chuanzeng Zhang,et al.  Topology optimization of two-dimensional asymmetrical phononic crystals , 2014 .

[30]  G. Allaire,et al.  A level-set method for shape optimization , 2002 .

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

[32]  M. Zhou,et al.  Generalized shape optimization without homogenization , 1992 .

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

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

[35]  Xiao-Xing Su,et al.  Multi-objective optimization of two-dimensional porous phononic crystals , 2014 .

[36]  Satish S. Udpa,et al.  Finite-element neural networks for solving differential equations , 2005, IEEE Transactions on Neural Networks.

[37]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[38]  P. Sheng,et al.  Locally resonant sonic materials , 2000, Science.

[39]  Thierry Kogej,et al.  Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks , 2017, ACS central science.

[40]  Xiang Li,et al.  Predicting the effective mechanical property of heterogeneous materials by image based modeling and deep learning , 2019, Computer Methods in Applied Mechanics and Engineering.

[41]  William E. Faller,et al.  Unsteady Fluid Mechanics Applications of Neural Networks , 1997 .

[42]  Zeng Yu-hong,et al.  Application of artificial neural network to predict the friction factor of open channel flow , 2009 .

[43]  E. Thomas,et al.  Micro‐/Nanostructured Mechanical Metamaterials , 2012, Advanced materials.

[44]  Yoshua Bengio,et al.  Generative Adversarial Networks , 2014, ArXiv.

[45]  Max Yi Ren,et al.  Microstructure Representation and Reconstruction of Heterogeneous Materials via Deep Belief Network for Computational Material Design , 2016, ArXiv.

[46]  Yoshua Bengio,et al.  Scaling learning algorithms towards AI , 2007 .

[47]  Debora S. Marks,et al.  Deep generative models of genetic variation capture mutation effects , 2017, bioRxiv.

[48]  Katia Bertoldi,et al.  Effects of geometric and material nonlinearities on tunable band gaps and low-frequency directionality of phononic crystals , 2013 .

[49]  Jamshid Ghaboussi,et al.  Neural network constitutive model for rate-dependent materials , 2006 .

[50]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

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

[52]  R. Martínez-Sala,et al.  Sound attenuation by sculpture , 1995, Nature.

[53]  B. Djafari-Rouhani,et al.  Theory of acoustic band structure of periodic elastic composites. , 1994, Physical review. B, Condensed matter.

[54]  M. Bendsøe.  Optimal shape design as a material distribution problem , 1989 .

[55]  N. Phan-Thien,et al.  Neural-network-based approximations for solving partial differential equations , 1994 .

[56]  Eleftherios N. Economou,et al.  Band structure of elastic waves in two dimensional systems , 1993 .

[57]  H. P. Mlejnek,et al.  Some aspects of the genesis of structures , 1992 .

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

[59]  Zhan Kang,et al.  Robust topology optimization of phononic crystals with random field uncertainty , 2018 .

[60]  Henry Schriemer,et al.  Energy Velocity of Diffusing Waves in Strongly Scattering Media , 1997 .

[61]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[62]  Anders Clausen,et al.  Efficient topology optimization in MATLAB using 88 lines of code , 2011 .

[63]  R. Asahi,et al.  Microstructure recognition using convolutional neural networks for prediction of ionic conductivity in ceramics , 2017 .

[64]  Ole Sigmund,et al.  Inverse design of phononic crystals by topology optimization , 2005 .

[65]  Jamshid Ghaboussi,et al.  Autoprogressive training of neural network constitutive models , 1998 .

[66]  O. Sigmund,et al.  Topology optimization approaches , 2013, Structural and Multidisciplinary Optimization.

[67]  Xiaodong Huang,et al.  Evolutionary topological design for phononic band gap crystals , 2016 .

[68]  Chiara Daraio,et al.  Wide band-gap seismic metastructures , 2015 .

[69]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[70]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[71]  B. Djafari-Rouhani,et al.  Acoustic band structure of periodic elastic composites. , 1993, Physical review letters.

[72]  Geoffrey E. Hinton.  Learning multiple layers of representation , 2007, Trends in Cognitive Sciences.

[73]  Yuebing Zheng,et al.  Intelligent nanophotonics: merging photonics and artificial intelligence at the nanoscale , 2018, Nanophotonics.

[74]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[75]  Thomas Blaschke,et al.  The rise of deep learning in drug discovery. , 2018, Drug discovery today.

[76]  Wei-Hsin Liao,et al.  Modeling and control of magnetorheological fluid dampers using neural networks , 2005 .

[77]  C. Mattheck,et al.  A new method of structural shape optimization based on biological growth , 1990 .

[78]  Henry Schriemer,et al.  Group Velocity in Strongly Scattering Media , 1996, Science.

[79]  Shinji Nishiwaki,et al.  Shape and topology optimization based on the phase field method and sensitivity analysis , 2010, J. Comput. Phys..

[80]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[81]  Bahram Djafari-Rouhani,et al.  Complete acoustic band gaps in periodic fibre reinforced composite materials : the carbon/epoxy composite and some metallic systems , 1994 .

[82]  Wei Chen,et al.  A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions , 2018, Scientific Reports.

[83]  Lefteri H. Tsoukalas,et al.  Flow regime identification methodology with neural networks and two-phase flow models , 2001 .

[84]  Dimitrios I. Fotiadis,et al.  Artificial neural networks for solving ordinary and partial differential equations , 1997, IEEE Trans. Neural Networks.

[85]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[86]  Y. Xie,et al.  A simple evolutionary procedure for structural optimization , 1993 .

[87]  R. Martínez-Sala,et al.  Refractive acoustic devices for airborne sound. , 2001 .

[88]  Dana H. Ballard,et al.  Modular Learning in Neural Networks , 1987, AAAI.

[89]  Fuguo Li,et al.  A comparative study on Arrhenius-type constitutive model and artificial neural network model to predict high-temperature deformation behaviour in Aermet100 steel , 2011 .

[90]  Fabian J Theis,et al.  Single-cell RNA-seq denoising using a deep count autoencoder , 2019, Nature Communications.

[91]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[92]  Xiaoming Wang,et al.  A level set method for structural topology optimization , 2003 .

[93]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[94]  A. Chambolle,et al.  Design-dependent loads in topology optimization , 2003 .

[95]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[96]  Yi Ren,et al.  Improving direct physical properties prediction of heterogeneous materials from imaging data via convolutional neural network and a morphology-aware generative model , 2017, Computational Materials Science.

[97]  Youssef M A Hashash,et al.  Numerical implementation of a neural network based material model in finite element analysis , 2004 .

[98]  Martin Burger,et al.  Phase-Field Relaxation of Topology Optimization with Local Stress Constraints , 2006, SIAM J. Control. Optim..

[99]  Xinhua Hu,et al.  Superlensing effect in liquid surface waves. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[100]  C. Sun,et al.  Continuum modeling of a composite material with internal resonators , 2012 .

[101]  Ole Sigmund,et al.  Systematic design of phononic band–gap materials and structures by topology optimization , 2003, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[102]  Naif Alajlan,et al.  Artificial Neural Network Methods for the Solution of Second Order Boundary Value Problems , 2019, Computers, Materials & Continua.

[103]  Kurt Maute,et al.  Design of phononic materials/structures for surface wave devices using topology optimization , 2007 .

[104]  Huanyang Chen,et al.  Wavefront modulation and subwavelength diffractive acoustics with an acoustic metasurface , 2014, Nature Communications.

[105]  B. H. Nguyen,et al.  Tunable topological bandgaps and frequencies in a pre-stressed soft phononic crystal , 2019, Journal of Applied Physics.

[106]  Toshiaki Koike-Akino,et al.  Deep Neural Network Inverse Design of Integrated Nanophotonic Devices. , 2018, 1809.03555.

[107]  G. P. Srivastava,et al.  The Physics of Phonons , 2019 .

[108]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.