Comparisons of Support Vector Regression and Neural Network in Modelling the Hydraulic Damper

Abstract:

Nonparametric models of hydraulic damper based on support vector regression (SVR) are developed. Then these models are compared with two kinds neural network models. One is backpropagation neural network (BPNN) model; another is radial basis function neural network (RBFNN) model. Comparisons are carried out both on virtual damper and actual damper. The force-velocity relation of a virtual damper is obtained based on a rheological model. Then these data are used to identify the characteristics of the virtual damper. The dynamometer measurements of an actual displacement-dependent damper are obtained by experiment. And these data are used to identify the characteristics of this actual damper. The comparisons show that BPNN model is best at identifying the characteristics of the virtual damper, but SVR model is best at identifying the characteristics of the actual damper. The reason is that all experimental data include noise more or less. When the amplitude of the noise is smaller than the parameter of SVR, the noise can not affect the construction of the resulting model. So when training a model based on the experimental data, SVR is superior to other neural networks methods.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 3805-3812
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.3805
• Online since: November 2011
• Authors: Kong Hui Guo, Xian Yun Wang
• Keywords: Hydraulic Damper, Neural Network (NN), Support Vector Regression (SVR), Vehicle Simulation

References

[1] H. Lang, A study of the characteristics of automotive hydraulic dampers at high stroking frequency, PH.D. thesis, University of Michigan, (1977).

[2] K. Reybrouck, A non linear parametric model of an automotive shock absorber, SAE Technical Papers, 940869 , (1994).

DOI: 10.4271/940869

[3] K. Lee, Numerical modelling for the hydraulic performance prediction of automotive monotube dampers, Veh. Syst. Dyn. 28 (1997), pp.25-39.

DOI: 10.1080/00423119708969347

[4] F.H. Besinger, D. Cebon, and D.J. Cole, Damper models for heavy vehicle ride dynamics, Veh. Syst. Dyn. 24 (1995), pp.35-64.

DOI: 10.1080/00423119508969081

[5] A. Lion, and S. Loose, A thermomechanically coupled model for automotive shock absorbers: theory, experiments and vehicle simulations on test tracks, Veh. Syst. Dyn. 37 (2002), pp.241-261.

DOI: 10.1076/vesd.37.4.241.3528

[6] S. Duym, R. Stiens, and K. Reybrouck, Evaluation of shock absorber models, Veh. Syst. Dyn. 27 (1997), pp.109-127.

DOI: 10.1080/00423119708969325

[7] A. Patel, and J.F. Dunne, NARX neural network modelling of hydraulic suspension dampers for steady-state and variable temperature operation, Veh. Syst. Dyn. 40 (2003), pp.285-328.

DOI: 10.1076/vesd.40.5.285.17911

[8] V.N. Vapnik, Statistical Learning Theory, Johnwiley & Sons. New York, (1998).

[9] B. Schölkopf, A.J. Smola, R.C. Williamson, and P.L. Bartlett, New support vector algorithms, Neural Comput., 12 (2000), pp.1207-1245.

DOI: 10.1162/089976600300015565

[10] G.W. Flake, and S. Lawrence, Efficient SVM regression training with SMO, Mach Learn., 46 (2002), pp.271-290.

[11] A.J. Smola, and B. Schölkopf, A tutorial on support vector regression, Stat Comput., 14 (2004), pp.199-222.

DOI: 10.1023/b:stco.0000035301.49549.88

[12] A.H. Marti, Support vector machines, IEEE Intell Syst., 13 (1998), pp.18-28.

[13] http: /www. mathworks. com/help.

[14] C.C. Chang, and C.J. Lin, LIBSVM: a library for support vector machines; Software available at http: /www. csie. ntu. edu. tw/~cjlin/libsvm.