Table of Content

Open AccessOpen Access


Global Approximation for a Simulation Model Based on the RBF Response Surface Set

Yin Xiao-Liang1, Wu Yi-Zhong1,2, Wan Li1, Xiong Hui-Yuan3

National CAD supported software engineering centre in Huazhong University of Science and Technology, Wuhan, P.R.China, 430074.
Corresponding author. E-mail: cad.wyz
Institute of Dongguan-Sun Yat-Sen University.

Computer Modeling in Engineering & Sciences 2014, 103(6), 429-462.


The use of multi-dimensional global approximation for a complex black-box function (such as a simulation or an analysis model) is steadily growing in the past decade. It can be applied in many fields such as parameter experiment, sensibility analyses real-time simulation, and design/control optimization. However, the widespread use of approximation methods is hampered by the lack of the ability to approximate a complex simulation model which characterizes the dynamic feature with multiple inputs and multiple outputs (MIMO) in a large domain. In this paper, a novel global approximation method for simulation models based on the RBF response surface set is proposed. Firstly, incremental building technique of RBF response surface set was studied, and was applied to approximate MIMO models. Several mathematical tests were presented to demonstrate the feasibility and effectiveness of the technique. Secondly, the approximation for complex simulation models, especially for dynamic models with state variables, was addressed. A simple test was given to illustrate the approximation process and effectiveness of a simulation model. Lastly, as an engineering application, the proposed method was utilized to approximate the power-train of a pure electric vehicle, and the approximation model was successfully applied in real-time simulation platform.


Cite This Article

Xiao-Liang, Y., Yi-Zhong, W., Li, W., Hui-Yuan, X. (2014). Global Approximation for a Simulation Model Based on the RBF Response Surface Set. CMES-Computer Modeling in Engineering & Sciences, 103(6), 429–462.

This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1022


  • 778


  • 0


Share Link