Design space exploration and optimization using self-organizing maps

Identifying regions of interest (RoI) in the design space is extremely useful while building metamodels with limited computational budget. Self-organizing maps (SOM) are used as a visualization technique for design space exploration that permits identifying RoI. Conventional implementation of SOM is susceptible to folds or intersections that hinder visualizing the design space. This work proposes a modified SOM algorithm whose maps are interpretable and that does not fold and allows smoother input and performance space visualization. The modified algorithm enables identification of RoI and additional sampling in the identified RoI allows building accurate Kriging metamodel, which is then used for optimization. The proposed approach is demonstrated on benchmark nonlinear analytical examples and two practical engineering design examples. Results show that the proposed approach is highly efficient in identifying the RoI and in obtaining the optima with less samples.

[1]  Gregory T. Breard,et al.  Evaluating Self-Organizing Map Quality Measures as Convergence Criteria , 2017 .

[2]  D Deschrijver,et al.  Adaptive Sampling Algorithm for Macromodeling of Parameterized $S$ -Parameter Responses , 2011, IEEE Transactions on Microwave Theory and Techniques.

[3]  Qiqi Wang,et al.  Erratum: Active Subspace Methods in Theory and Practice: Applications to Kriging Surfaces , 2013, SIAM J. Sci. Comput..

[4]  Nianfei Gan,et al.  Hybrid meta-model-based design space exploration method for expensive problems , 2018, Structural and Multidisciplinary Optimization.

[5]  T. Simpson,et al.  Fuzzy clustering based hierarchical metamodeling for design space reduction and optimization , 2004 .

[6]  Farrokh Mistree,et al.  Design of multifunctional honeycomb materials , 2002 .

[7]  Harish Ganapathy,et al.  Alpha shape based design space decomposition for island failure regions in reliability based design , 2015 .

[8]  Feng Qian,et al.  Adaptive Sampling for Surrogate Modelling with Artificial Neural Network and its Application in an Industrial Cracking Furnace , 2016 .

[9]  Dimitri N. Mavris,et al.  Dimensionality Reduction Using Principal Component Analysis Applied to the Gradient , 2015 .

[10]  Sumeet Parashar,et al.  Self Organizing Maps (SOM) for Design Selection in Robust Multi-Objective Design of Aerofoil , 2008 .

[11]  M. Ashby.  MULTI-OBJECTIVE OPTIMIZATION IN MATERIAL DESIGN AND SELECTION , 2000 .

[12]  Raphael T. Haftka,et al.  A convex hull approach for the reliability-based design optimization of nonlinear transient dynamic problems , 2007 .

[13]  Wataru Yamazaki,et al.  A Dynamic Sampling Method for Kriging and Cokriging Surrogate Models , 2011 .

[14]  Naif Alajlan,et al.  Active learning for spectroscopic data regression , 2012 .

[15]  G. Belingardi,et al.  Surrogate modeling in design optimization of structures with discontinuous responses , 2018 .

[16]  Teuvo Kohonen,et al.  Exploration of very large databases by self-organizing maps , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[17]  Haitao Liu,et al.  A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering design , 2017, Structural and Multidisciplinary Optimization.

[18]  Shahryar Rahnamayan,et al.  3D-RadVis: Visualization of Pareto front in many-objective optimization , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[19]  V. Schulz,et al.  Comparing sampling strategies for aerodynamic Kriging surrogate models , 2012 .

[20]  Liang Gao,et al.  An expert system using rough sets theory and self-organizing maps to design space exploration of complex products , 2010, Expert Syst. Appl..

[21]  M. Diez,et al.  Design-space dimensionality reduction in shape optimization by Karhunen–Loève expansion , 2015 .

[22]  Ezequiel López-Rubio,et al.  Improving the Quality of Self-Organizing Maps by Self-Intersection Avoidance , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[23]  Carolyn Conner Seepersad,et al.  Building Surrogate Models Based on Detailed and Approximate , 2004, DAC 2004.

[24]  Farrokh Mistree,et al.  Statistical Experimentation Methods for Achieving Affordable Concurrent Systems Design , 1997 .

[25]  H. Sebastian Seung,et al.  Query by committee , 1992, COLT '92.

[26]  Adil Baykasoglu,et al.  Prediction and multi-objective optimization of high-strength concrete parameters via soft computing approaches , 2009, Expert Syst. Appl..

[27]  Reinhard Radermacher,et al.  Cross-validation based single response adaptive design of experiments for Kriging metamodeling of deterministic computer simulations , 2013 .

[28]  Andy J. Keane,et al.  Visualization methodologies in aircraft design , 2004 .

[29]  Xinyu Shao,et al.  A novel sequential exploration-exploitation sampling strategy for global metamodeling , 2015 .

[30]  Serge Guillas,et al.  Sequential Design with Mutual Information for Computer Experiments (MICE): Emulation of a Tsunami Model , 2014, SIAM/ASA J. Uncertain. Quantification.

[31]  Andy J. Keane,et al.  Engineering Design via Surrogate Modelling - A Practical Guide , 2008 .

[32]  Joong Hoon Kim,et al.  Genetic algorithm in mix proportioning of high-performance concrete , 2004 .

[33]  A. Meher Prasad,et al.  High‐dimensional model representation for structural reliability analysis , 2009 .

[34]  Liang Gao,et al.  Multi-stage design space reduction and metamodeling optimization method based on self-organizing maps and fuzzy clustering , 2016, Expert Syst. Appl..

[35]  Christian B Allen,et al.  Investigation of an adaptive sampling method for data interpolation using radial basis functions , 2010 .

[36]  G. G. Wang,et al.  Space exploration and global optimization for computationally intensive design problems: a rough set based approach , 2004 .

[37]  Chien-Nan Jimmy Liu,et al.  A novel design space reduction method for efficient simulation-based optimization , 2014, 2014 IEEE International Symposium on Circuits and Systems (ISCAS).

[38]  Joost Van de Peer,et al.  Self-organizing map based adaptive sampling , 2013 .

[39]  Kimmo Kiviluoto,et al.  Topology preservation in self-organizing maps , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[40]  J. P. Evans,et al.  Interdigitation for effective design space exploration using iSIGHT , 2002 .

[41]  G. G. Wang,et al.  Design Space Reduction for Multi-Objective Optimization and Robust Design Optimization Problems , 2004 .

[42]  Daisuke Sasaki,et al.  Visualization and Data Mining of Pareto Solutions Using Self-Organizing Map , 2003, EMO.

[43]  Christopher A. Mattson,et al.  Divergent exploration in design with a dynamic multiobjective optimization formulation , 2013 .

[44]  Jun Li,et al.  Optimization and Knowledge Discovery of a Three-Dimensional Parameterized Vane with Nonaxisymmetric Endwall , 2018 .

[45]  Songqing Shan,et al.  Introducing Rough Set for Design Space Exploration and Optimization , 2003, DAC 2003.