Metamodell of optimized Prognosis (MoP) - an Auto- matic Approach for User Friendly Parameter Optimization

Summary In real case applications of CAE-based optimization tasks within the virtual prototyping process, it is not always possible to reduce the complexity of the physical models and to obtain numerical models which can be solved quickly. Usually, every single numerical simulation takes hours or even days. Although the progresses in numerical methods and high performance computing, in such cases, it is not possible to perform CAE-based optimization, hence efficient surrogate models to replace the costly design runs are would be an interesting alterative. Generally the available meta-model techniques show several advantages and disadvantages depending on the investigated problem. Usually they are limited to a small number of optimization variables and the quality of prognosis is not known. In this paper we present an automatic approach for the selection of the optimal suitable meta-model for the actual problem as well as test the prognosis quality of the metamodel with an independent test data set. Therefore we call the selected metamodel with the best prognosis quality the meta-model of optimized prognosis (MoP). Together with an automatic reduction of the variable space using advanced filter techniques an efficient approximation is enabled also for high dimensional problems. After the generation of MoP the prognosis quality of important responses can be investigated and the MoP can be used for optimization purpose.

[1]  George E. P. Box,et al.  Empirical Model‐Building and Response Surfaces , 1988 .

[2]  T. W. Layne,et al.  A Comparison of Approximation Modeling Techniques: Polynomial Versus Interpolating Models , 1998 .

[3]  Douglas C. Montgomery,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[4]  Thomas Most,et al.  A Moving Least Squares weighting function for the Element-free Galerkin Method which almost fulfills essential boundary conditions , 2005 .

[5]  Thomas J. Santner,et al.  The Design and Analysis of Computer Experiments , 2003, Springer Series in Statistics.

[6]  D. Cox,et al.  An Analysis of Transformations , 1964 .

[7]  P. Lancaster,et al.  Surfaces generated by moving least squares methods , 1981 .

[8]  Harvey M. Wagner,et al.  Global Sensitivity Analysis , 1995, Oper. Res..

[9]  Ren-Jye Yang,et al.  Approximation methods in multidisciplinary analysis and optimization: a panel discussion , 2004 .

[10]  R. Gunst.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[11]  Saltelli Andrea,et al.  Global Sensitivity Analysis: The Primer , 2008 .

[12]  J. Will,et al.  Advanced surrogate models within the robustness evaluation , 2008 .

[13]  Xiaobo Zhou,et al.  Global Sensitivity Analysis , 2017, Encyclopedia of GIS.

[14]  A. Handler.  Basic concepts for robustness evaluation using stochastic analysis , 2008 .

[15]  Timothy W. Simpson,et al.  Metamodels for Computer-based Engineering Design: Survey and recommendations , 2001, Engineering with Computers.

[16]  André I. Khuri,et al.  Response surface methodology , 2010 .

[17]  A. J. Booker,et al.  A rigorous framework for optimization of expensive functions by surrogates , 1998 .

[18]  Sonja Kuhnt,et al.  Design and analysis of computer experiments , 2010 .