Research Papers

Integrating Least Square Support Vector Regression and Mode Pursuing Sampling Optimization for Crashworthiness Design

[+] Author and Article Information
Hu Wang

The State Key Laboratory of Advanced Technology for Vehicle Design and Manufacture, College of Mechanical and Vehicle Engineering,  Hunan University, Changsha, Hunan, P. R. Chinawanghuenying@hotmail.com

Songqing Shan

Department of Mechanical and Manufacturing Engineering,  University of Manitoba, Winnipeg, MB, R3T 5V6, Canadashans@cc.umanitoba.ca

G. Gary Wang

School of Engineering Science,  Simon Fraser University, Surrey, BC, V3T 0A3, Canadagary_wang@sfu.ca

Guangyao Li

The State Key Laboratory of Advanced Technology for Vehicle Design and Manufacture, College of Mechanical and Vehicle Engineering,  Hunan University, Changsha, Hunan, P. R. Chinagyli@hnu.cn

FE simulations in this study are performed on this workstation.

J. Mech. Des 133(4), 041002 (May 09, 2011) (10 pages) doi:10.1115/1.4003840 History: Received September 22, 2009; Revised February 24, 2011; Accepted March 16, 2011; Published May 09, 2011; Online May 09, 2011

Many metamodeling techniques have been developed in the past two decades to reduce the computational cost of design evaluation. With the increasing scale and complexity of engineering problems, popular metamodeling techniques including artificial neural network (ANN), Polynomial regression (PR), Kriging (KG), radial basis functions (RBF), and multivariate adaptive regression splines (MARS) face difficulties in solving highly nonlinear problems, such as the crashworthiness design. Therefore, in this work, we integrate the least support vector regression (LSSVR) with the mode pursuing sampling (MPS) optimization method and applied the integrated approach for crashworthiness design. The MPS is used for generating new samples which are concentrated near the current local minima at each iteration and yet still statistically cover the entire design space. The LSSVR is used for establishing a more robust metamodel from noisy data. Therefore, the proposed method integrates the advantages of both the LSSVR and MPS to more efficiently achieve reasonably accurate results. In order to verify the proposed method, well-known highly nonlinear functions are used for testing. Finally, the proposed method is applied to three typical crashworthiness optimization cases. The results demonstrate the potential capability of this method in the crashworthiness design of vehicles.

Copyright © 2011 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Relative performance of metamodeling approaches with respect to LSSVR. (a) Mean of relative metrics; (b) STD of relative metrics.

Grahic Jump Location
Figure 2

Efficiency comparison of optimization approaches

Grahic Jump Location
Figure 3

FE model of the vehicle frontal member under impact

Grahic Jump Location
Figure 4

Change in the rigid wall force with respect to time for the initial and optimum design variables of case I

Grahic Jump Location
Figure 5

Crash simulation result with optimum design variables for case II

Grahic Jump Location
Figure 6

Change of internal energy of initial and optimum designs of case II

Grahic Jump Location
Figure 7

FE model of side impact for case III

Grahic Jump Location
Figure 8

Location of test points (P1 are P2 locate on the B-pillar; P3 locates on the floor)

Grahic Jump Location
Figure 9

Selected components that need optimization

Grahic Jump Location
Figure 10

Change of deflection of B pillar with initial and optimum designs of case III




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In