Self-Directed Online Machine Learning for Topology Optimization

Topology optimization by optimally distributing materials in a given domain requires stochastic optimizers to solve highly complicated problems. However, with hundreds of design variables or more involved, solving such problems would require millions of Finite Element Method (FEM) calculations whose computational cost is huge and impractical. Here we report a self-directed online learning method which integrates Deep Neural Network (DNN) with FEM calculations. A DNN learns and substitutes the objective as a function of design variables. A small amount of training data are generated dynamically around the DNN's prediction of the global optimum. The DNN adapts to the new training data and gives better prediction in the region of interest until convergence. Our algorithm was tested by compliance minimization problems and demonstrated a reduction of computational time by over two orders of magnitude than the current method. This approach enables solving very large multi-dimensional optimization problems.

[1]  K. Lee,et al.  A new structural optimization method based on the harmony search algorithm , 2004 .

[2]  Guan-Chun Luh,et al.  A binary particle swarm optimization for continuum structural topology optimization , 2011, Appl. Soft Comput..

[3]  Peter L. Bartlett,et al.  Rademacher and Gaussian Complexities: Risk Bounds and Structural Results , 2003, J. Mach. Learn. Res..

[4]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[5]  George I. N. Rozvany,et al.  A critical review of established methods of structural topology optimization , 2009 .

[6]  Tuo Zhao,et al.  On Computation and Generalization of Generative Adversarial Imitation Learning , 2020, ICLR.

[7]  Michael I. Jordan,et al.  On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems , 2019, ICML.

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

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

[10]  Ole Sigmund,et al.  On the usefulness of non-gradient approaches in topology optimization , 2011 .

[11]  P. Hajela,et al.  Genetic algorithms in truss topological optimization , 1995 .

[12]  Guan-Chun Luh,et al.  Structural topology optimization using ant colony optimization algorithm , 2009, Appl. Soft Comput..

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

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

[15]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[16]  Yang Xiang,et al.  Generalized Simulated Annealing for Global Optimization: The GenSA Package , 2013, R J..

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

[18]  Xin-She Yang,et al.  Binary bat algorithm , 2013, Neural Computing and Applications.

[19]  Rajalaxmi Ramasamy,et al.  Modified binary bat algorithm for feature selection in unsupervised learning , 2018, Int. Arab J. Inf. Technol..

[20]  Feng Liu,et al.  On Computation and Generalization of Generative Adversarial Networks under Spectrum Control , 2019, ICLR.

[21]  Ramana V. Grandhi,et al.  A survey of structural and multidisciplinary continuum topology optimization: post 2000 , 2014 .

[22]  Yang Xiang,et al.  Generalized Simulated Annealing , 2017 .

[23]  David A. McAllester,et al.  A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks , 2017, ICLR.

[24]  Tuo Zhao,et al.  On Generalization Bounds of a Family of Recurrent Neural Networks , 2018, AISTATS.

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

[26]  Saeed Shojaee,et al.  Structural topology optimization using ant colony methodology , 2008 .

[27]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.

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

[29]  Ikjin Lee,et al.  Deep Generative Design: Integration of Topology Optimization and Generative Models , 2019, Journal of Mechanical Design.

[30]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[31]  Matus Telgarsky,et al.  Spectrally-normalized margin bounds for neural networks , 2017, NIPS.

[32]  Jonathan E. Cooper,et al.  Aeroelastic tailoring and scaling using Bacterial Foraging Optimisation , 2014 .

[33]  Alexander Shapiro,et al.  Stochastic Approximation approach to Stochastic Programming , 2013 .

[34]  Ivan V. Oseledets,et al.  Neural networks for topology optimization , 2017, Russian Journal of Numerical Analysis and Mathematical Modelling.

[35]  C. Blair Problem Complexity and Method Efficiency in Optimization (A. S. Nemirovsky and D. B. Yudin) , 1985 .

[36]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.