Machine learning accelerated topology optimization of nonlinear structures

The field of optimal design of linear elastic structures has seen many exciting successes that resulted in new architected materials and designs. With the availability of cloud computing, including high-performance computing, machine learning, and simulation, searching for optimal nonlinear structures is now within reach. In this study, we develop two convolutional neural network models to predict optimized designs for a given set of boundary conditions, loads, and volume constraints. The first convolutional neural network model is for the case of materials with a linear elastic response while the second developed model is for hyperelastic response where material and geometric nonlinearities are involved. For the nonlinear elastic case, the neo-Hookean model is utilized. For this purpose, we generate datasets, composed of the optimized designs paired with the corresponding boundary conditions, loads, and constraints, using topology optimization framework to train and validate both models. The developed models are capable of accurately predicting the optimized designs without requiring an iterative scheme and with negligible computational time. The suggested pipeline can be generalized to other nonlinear mechanics scenarios and design domains.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Antonios Kontsos,et al.  Coupling In Situ Microstructure Observation with Machine Learning Algorithms for Damage Diagnostics and Prognostics , 2017 .

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

[4]  Kapil Khandelwal,et al.  Bi-material topology optimization for energy dissipation with inertia and material rate effects under finite deformations , 2019, Finite Elements in Analysis and Design.

[5]  Dongil Shin,et al.  Data-driven approach for a one-dimensional thin-walled beam analysis , 2020 .

[6]  Hajime Igarashi,et al.  Topology Optimization Accelerated by Deep Learning , 2019, IEEE Transactions on Magnetics.

[7]  Qingjie Liu,et al.  Road Extraction by Deep Residual U-Net , 2017, IEEE Geoscience and Remote Sensing Letters.

[8]  E. Ramm,et al.  Adaptive topology optimization of elastoplastic structures , 1998 .

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

[10]  Timon Rabczuk,et al.  An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications , 2019, Computer Methods in Applied Mechanics and Engineering.

[11]  Airong Chen,et al.  A deep Convolutional Neural Network for topology optimization with strong generalization ability , 2019, ArXiv.

[12]  L. Valdevit,et al.  Fabrication of 3D Micro-Architected/Nano-Architected Materials , 2016 .

[13]  Mattias Schevenels,et al.  The generation of hierarchic structures via robust 3D topology optimisation , 2017, Adv. Eng. Informatics.

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

[15]  T. E. Bruns,et al.  Topology optimization of non-linear elastic structures and compliant mechanisms , 2001 .

[16]  J. Petersson,et al.  Numerical instabilities in topology optimization: A survey on procedures dealing with checkerboards, mesh-dependencies and local minima , 1998 .

[17]  Rashid K. Abu Al-Rub,et al.  Design and prototyping soft–rigid tendon-driven modular grippers using interpenetrating phase composites materials , 2020, Int. J. Robotics Res..

[18]  Yeshern Maharaj,et al.  Metamaterial topology optimization of nonpneumatic tires with stress and buckling constraints , 2019, International Journal for Numerical Methods in Engineering.

[19]  Guido Morgenthal,et al.  Prediction of aeroelastic response of bridge decks using artificial neural networks , 2020 .

[20]  Joanna McKittrick,et al.  An Overview on Additive Manufacturing of Polymers , 2018 .

[21]  Umberto Ravaioli,et al.  Prediction and optimization of mechanical properties of composites using convolutional neural networks , 2019, Composite Structures.

[22]  Manolis Papadrakakis,et al.  Structural optimization using evolution strategies and neural networks , 1998 .

[23]  Sagar Patel,et al.  3D Topology Optimization using Convolutional Neural Networks , 2018, ArXiv.

[24]  M. Bendsøe,et al.  Topology Optimization: "Theory, Methods, And Applications" , 2011 .

[25]  Haim Waisman,et al.  Failure Mitigation in Optimal Topology Design Using a Coupled Nonlinear Continuum Damage Model , 2014 .

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

[27]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[28]  Charlie C. L. Wang,et al.  Current and future trends in topology optimization for additive manufacturing , 2018 .

[29]  Richard Leach,et al.  Multidimensional Phononic Bandgaps in Three-Dimensional Lattices for Additive Manufacturing , 2019, Materials.

[30]  K. Lee,et al.  A new meta-heuristic algorithm for continuous engineering optimization: harmony search theory and practice , 2005 .

[31]  David Cebon,et al.  Materials: Engineering, Science, Processing and Design , 2007 .

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

[33]  E. Sturler,et al.  Stochastic sampling for deterministic structural topology optimization with many load cases: Density-based and ground structure approaches , 2016, 1609.03099.

[34]  Hèrm Hofmeyer,et al.  Coevolutionary and genetic algorithm based building spatial and structural design , 2015, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[35]  Markus J. Buehler,et al.  Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment , 2018 .

[36]  James K. Guest,et al.  Topology Optimization for Architected Materials Design , 2016 .

[37]  Levent Burak Kara,et al.  A data-driven investigation and estimation of optimal topologies under variable loading configurations , 2014, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[38]  A. Klarbring,et al.  Topology optimization of hyperelastic bodies including non-zero prescribed displacements , 2013 .

[39]  Kapil Khandelwal,et al.  Design of energy dissipating elastoplastic structures under cyclic loads using topology optimization , 2017 .

[40]  K. Lee,et al.  A new metaheuristic algorithm for continuous engineering optimization : harmony search theory and practice , 2005 .

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

[42]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Y. Bréchet,et al.  Architectured materials: Expanding materials space , 2013 .

[44]  O. Sigmund,et al.  Stiffness design of geometrically nonlinear structures using topology optimization , 2000 .

[45]  Jonathan B. Russ,et al.  Topology optimization for brittle fracture resistance , 2019, Computer Methods in Applied Mechanics and Engineering.

[46]  Sharad Rawat,et al.  Application of Adversarial Networks for 3D Structural Topology Optimization , 2019, SAE technical paper series.

[47]  C.-Y. Lin,et al.  Artificial neural network based hole image interpretation techniques for integrated topology and shape optimization , 2005 .

[48]  Chang Su Woo,et al.  An experimental study and finite element analysis of weatherstrip , 2011 .

[49]  Diab W. Abueidda,et al.  Acoustic band gaps and elastic stiffness of PMMA cellular solids based on triply periodic minimal surfaces , 2018 .

[50]  D. Tortorelli,et al.  Tangent operators and design sensitivity formulations for transient non‐linear coupled problems with applications to elastoplasticity , 1994 .

[51]  Kai A. James,et al.  Optimal design of compliant mechanisms using functionally graded materials , 2017 .

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

[53]  Naif Alajlan,et al.  A novel deep learning based method for the computational material design of flexoelectric nanostructures with topology optimization , 2019, Finite Elements in Analysis and Design.

[54]  Daniel A. White,et al.  Simple, accurate surrogate models of the elastic response of three-dimensional open truss micro-architectures with applications to multiscale topology design , 2019, Structural and Multidisciplinary Optimization.

[55]  M. Aurangzeb Khan,et al.  Formulation and Execution of Structural Topology Optimization for Practical Design Solutions , 2012, J. Optim. Theory Appl..

[56]  M. Bendsøe,et al.  Generating optimal topologies in structural design using a homogenization method , 1988 .

[57]  Subra Suresh,et al.  Deep elastic strain engineering of bandgap through machine learning , 2019, Proceedings of the National Academy of Sciences.

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

[59]  In Gwun Jang,et al.  Deep learning for determining a near-optimal topological design without any iteration , 2018, Structural and Multidisciplinary Optimization.

[60]  Ruiyang Zhang,et al.  Deep long short-term memory networks for nonlinear structural seismic response prediction , 2019, Computers & Structures.

[61]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[62]  Joaquim R. R. A. Martins,et al.  Stress-based topology optimization using an isoparametric level set method , 2012 .

[63]  Huiyu Zhou,et al.  Using deep neural network with small dataset to predict material defects , 2019, Materials & Design.

[64]  Rahul,et al.  A deep learning-based hybrid approach for the solution of multiphysics problems in electrosurgery. , 2019, Computer methods in applied mechanics and engineering.

[65]  Jian-Ming Jin,et al.  Shielding effectiveness and bandgaps of interpenetrating phase composites based on the Schwarz Primitive surface , 2018, Journal of Applied Physics.

[66]  Daniel A. White,et al.  Multiscale topology optimization using neural network surrogate models , 2019, Computer Methods in Applied Mechanics and Engineering.

[67]  Richard M. Christensen,et al.  Mechanics of cellular and other low-density materials , 2000 .

[68]  Hassan A. Arafat,et al.  3D printed spacers for organic fouling mitigation in membrane distillation , 2019, Journal of Membrane Science.

[69]  Ole Sigmund,et al.  IUTAM Symposium on Topological Design Optimization of Structures, Machines and Materials , 2006 .

[70]  Ron Kikinis,et al.  Statistical validation of image segmentation quality based on a spatial overlap index. , 2004, Academic radiology.

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

[72]  William E. Frazier,et al.  Metal Additive Manufacturing: A Review , 2014, Journal of Materials Engineering and Performance.

[73]  M.-H. Herman Shen,et al.  A Novel Topology Optimization Approach using Conditional Deep Learning , 2019, ArXiv.

[74]  Seid Koric,et al.  Sparse matrix factorization in the implicit finite element method on petascale architecture , 2016 .

[75]  Rashid K. Abu Al-Rub,et al.  Mechanical properties of 3D printed polymeric Gyroid cellular structures: Experimental and finite element study , 2019, Materials & Design.

[76]  Mateo Valero,et al.  ALYA: MULTIPHYSICS ENGINEERING SIMULATION TOWARDS EXASCALE , 2014 .

[77]  Daniel A. Tortorelli,et al.  Topology optimization of finite strain viscoplastic systems under transient loads , 2018 .

[78]  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.

[79]  Rashid K. Abu Al-Rub,et al.  Viscoelastic properties of architected foams based on the Schoen IWP triply periodic minimal surface , 2018, Mechanics of Advanced Materials and Structures.

[80]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[81]  Oğuzhan Hasançebi,et al.  Linear and nonlinear model updating of reinforced concrete T-beam bridges using artificial neural networks , 2013 .

[82]  Baki Harish,et al.  Topology Optimization Using Convolutional Neural Network , 2020 .

[83]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[84]  Xianmin Zhang,et al.  A 213-line topology optimization code for geometrically nonlinear structures , 2018, Structural and Multidisciplinary Optimization.

[85]  Hua Bao,et al.  Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods , 2018, International Journal of Heat and Mass Transfer.

[86]  Rashid K. Abu Al-Rub,et al.  Mechanical Response of 3D Printed Bending-Dominated Ligament-Based Triply Periodic Cellular Polymeric Solids , 2019, Journal of Materials Engineering and Performance.

[87]  Xingyi Huang,et al.  Predicting the effective thermal conductivity of composites from cross sections images using deep learning methods , 2019, Composites Science and Technology.

[88]  T. Schaedler,et al.  Architected Cellular Materials , 2016 .

[89]  C. S. Jog,et al.  Stability of finite element models for distributed-parameter optimization and topology design , 1996 .

[90]  Naif Alajlan,et al.  Computational Machine Learning Representation for the Flexoelectricity Effect in Truncated Pyramid Structures , 2019, Computers, Materials & Continua.

[91]  J. Li,et al.  Elastic–plastic transition in three-dimensional random materials: massively parallel simulations, fractal morphogenesis and scaling functions , 2012 .

[92]  Liang Gao,et al.  Topological shape optimization of 3D micro-structured materials using energy-based homogenization method , 2018, Adv. Eng. Softw..

[93]  Shinji Nishiwaki,et al.  Topology Optimization with CAMD for Structures Undergoing Finite Deformation , 2006 .

[94]  Timon Rabczuk,et al.  Detection of material interfaces using a regularized level set method in piezoelectric structures , 2016 .

[95]  Julián A. Norato,et al.  Stress-based topology optimization for continua , 2010 .