A machine learning based global simulation data mining approach for efficient design changes

Abstract Historical simulation data reuse is crucial for helping the designer improve the product development process. Currently, simulation data mining has been brought into use to discover the underlying knowledge to support efficient design changes. However, most of the existing simulation data mining methods paid little attention to global performance evaluation, and thus causing it difficult for the designer to browse all the simulation results conveniently and accurately if it is without actual simulation performance verification. In this study, a machine learning based global simulation data mining approach is proposed to discover the interrelations between key design parameters and global performance parameters to realize the accurate prediction of all the simulation results, and thus supporting the decision-making in the development process. Firstly, an intermediate mesh model based cross-parameterization algorithm is adopted to construct global performance evaluation indicators. After that, two feature selection methods for design parameters are applied to select salient single parameter and their combinations to reduce the modeling complexity and improve the prediction accuracy. Finally, a machine learning based simulation data mining approach is developed and improved to realize global performance evaluation accurately and efficiently. Extensive experiments are conducted to demonstrate the feasibility, effectiveness and correctness of the proposed approach.

[1]  Jing Bai,et al.  Research on intelligent fault diagnosis of mechanical equipment based on sparse deep neural networks , 2017 .

[2]  Sidong Liu,et al.  An application of Takagi–Sugeno fuzzy system to the classification of cancer patients based on elemental contents in serum samples , 2006 .

[3]  J. Warren,et al.  Mean value coordinates for closed triangular meshes , 2005, SIGGRAPH 2005.

[4]  Martin Reimers,et al.  Mean value coordinates in 3D , 2005, Comput. Aided Geom. Des..

[5]  Guang-Bin Huang,et al.  Extreme Learning Machine for Multilayer Perceptron , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[6]  Chunguang Li,et al.  Intermediate model based efficient and integrated multidisciplinary simulation data visualization for simulation information reuse , 2015, Adv. Eng. Softw..

[7]  Gábor Szücs.  Decision Trees and Random Forest for Privacy-Preserving Data Mining , 2013 .

[8]  Ping Wang,et al.  An oscillation bound of the generalization performance of extreme learning machine and corresponding analysis , 2015, Neurocomputing.

[9]  Shuying Shen,et al.  Fine-grained leukocyte classification with deep residual learning for microscopic images , 2018, Comput. Methods Programs Biomed..

[10]  Sheridan J. Coakes,et al.  SPSS: Analysis Without Anguish Using Spss Version 14.0 for Windows , 1999 .

[11]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[12]  Florin Gorunescu,et al.  Data Mining - Concepts, Models and Techniques , 2011, Intelligent Systems Reference Library.

[13]  Vladislav Kraevoy,et al.  Cross-parameterization and compatible remeshing of 3D models , 2004, SIGGRAPH 2004.

[14]  Ying-Chung Wang,et al.  Knowledge discovery from finite element simulation data , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[15]  Yuan Lan,et al.  Random search enhancement of error minimized extreme learning machine , 2010, ESANN.

[16]  Jie Hu,et al.  Knowledge Discovery Based on Multidisciplinary Simulation Data , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[17]  Fred W. Glover,et al.  Advances in analytics: Integrating dynamic data mining with simulation optimization , 2007, IBM J. Res. Dev..

[18]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[19]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[20]  D. A. Adeniyi,et al.  Automated web usage data mining and recommendation system using K-Nearest Neighbor (KNN) classification method , 2016 .

[21]  Jin Xianlong.  Data mining on crashworthiness data of occupant restraint system , 2010 .

[22]  Dayong Li,et al.  Knowledge Discovery from Multidisciplinary Simulation to Support Concurrent and Collaborative Design , 2006, 2006 10th International Conference on Computer Supported Cooperative Work in Design.

[23]  Jianwei Wang,et al.  Data mining application on crash simulation data of occupant restraint system , 2010, Expert Syst. Appl..

[24]  Benno Stein,et al.  Simulation Data Mining for Supporting Bridge Design , 2011, AusDM.

[25]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[26]  Yusheng Liu,et al.  A uniform intermediate model for high-fidelity and efficient visualisation of multidisciplinary heterogeneous simulation data , 2016, Int. J. Comput. Integr. Manuf..

[27]  Nezih Mrad,et al.  Dynamic and static modelling of piezoelectric composite structures using a thermal analogy with MSC/NASTRAN , 2004 .

[28]  Nenad Filipovic,et al.  Mining data from CFD simulation for aneurysm and carotid bifurcation models , 2011, EMBC.

[29]  Paolo Cignoni,et al.  PolyCube-Maps , 2004, SIGGRAPH 2004.

[30]  Huan Liu,et al.  Toward integrating feature selection algorithms for classification and clustering , 2005, IEEE Transactions on Knowledge and Data Engineering.

[31]  Nenad Filipovic,et al.  Mining Data From Hemodynamic Simulations for Generating Prediction and Explanation Models , 2010, IEEE Transactions on Information Technology in Biomedicine.

[32]  Peter Schröder,et al.  Consistent mesh parameterizations , 2001, SIGGRAPH.

[33]  Richard Nock,et al.  A hybrid filter/wrapper approach of feature selection using information theory , 2002, Pattern Recognit..

[34]  M. Floater.  Mean value coordinates , 2003, Computer Aided Geometric Design.

[35]  Alla Sheffer,et al.  Cross-parameterization and compatible remeshing of 3D models , 2004, ACM Trans. Graph..

[36]  Robert K. L. Gay,et al.  Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning , 2009, IEEE Transactions on Neural Networks.

[37]  Liquan Mei,et al.  Data analysis for parallel car-crash simulation results and model optimization , 2008, Simul. Model. Pract. Theory.

[38]  Xevi Roca,et al.  Combining Size-Preserving and Smoothing Procedures for Adaptive Quadrilateral Mesh Generation , 2013, IMR.

[39]  Clemens-August Thole,et al.  Data Mining on Crash Simulation Data , 2005, MLDM.

[40]  Tobias Scheffer,et al.  Scalable look-ahead linear regression trees , 2007, KDD '07.