Using Genetic Algorithm to Optimize Parameters of Support Vector Machine and Its Application in Material Fatigue Life Prediction

Lanlan ZHANG, Juyang LEI, Juyang LEI, Qilin ZHOU, Qilin ZHOU, Yudong WANG, Yudong WANG

Abstract


Support vector machine is a new kind of learning method based on solid theoretical foundation, but this method has the characteristic of sensitivity to parameter. According to this characteristic, this paper use genetic algorithm to optimize the parameters of SVM and cross validation is introduced to reduce the dependence of the parameters on the training samples. Through the analysis of fatigue data for the relevant literature, take the parameters of the best generalization ability as the final parameters and apply the obtained model (GA-SVR) in material fatigue life prediction. Compared with the conventional SVR model and PSO-SVR model, the mean square error and the square of correlation coefficient are used to verify the reliability and accuracy of the three models. The results show that, the GA-SVR model can predict the fatigue life of materials with high
accuracy.


Keywords


Support vector machine; Genetic algorithm; Parameter optimization; Material fatigue life prediction; Application

Full Text:

PDF

References


Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers (pp.144-152). In D. Haussler (Ed.). Proceeding of the 5th Annual ACM Workshop on Computational Learning Theory. ACM Press.

Chen, Y. Y., & Xiong, Q. F. (2011). Application of support vector machine method tutorial (pp.1-83). China Meteorological Press.

Deng, N. Y., & Tian, Y. J. (2009). Support vector machine-theory, algorithm and expand (pp.63-111). Beijing, China: Science Press.

Gu, J. Y., Liu, J. F., & Chen, M. (2014). A modified regression prediction algorithm of large sample data based on SVM. Computer Engineering, 40(1), 161-166.

Jamal, A. Abdalla, R. H. (2011). Modeling and simulation of low-cycle fatigue life of steel reinforcing bars using artificial neural network. Journal of the Franklin Institute, 348,1393-1403.

Ji, D. M. (2011). Study on the fatigue life of P91 steel creep based on support vector machine. Pressure Vessel, 28(15), 15-21.

Li, J., Ping, A., & Wang, D. J. (2001). The intelligent simulation method of the reliability analysis based on the fatigue damage process with non steady state. Chinese Journal of Mechanical Engineering, 37(1), 1-5.

Lotfia, B., & Beissb, P. (2013).Application of neural networking for fatigue limit prediction of powder metallurgy steel parts. Materials & Design, 50, 440-445.

Mathew, M. D., Kim, D., & Ryu, W.-S. (2008).A Neural network model to predict low cycle fatigue life of nitrogen-alloyed 316L stainless steel. Material Science and Engineer A 474,247-253 .

Wang, J., Jing, Q. B., & Cao, L. L. (2007). Support vector regression facing multi input and multi output system. Journal of Tsinghua University, 47(S2), 1737-1741.

Zuo, J. W. (2011). The application of MATLAB in mathematical modeling (pp.37-82). China: Beijing University of Aeronautics and Astronautics Press.




DOI: http://dx.doi.org/10.3968/6404

DOI (PDF): http://dx.doi.org/10.3968/g7135

Refbacks

  • There are currently no refbacks.


Copyright (c)



Share us to:   

Reminder

We are currently accepting submissions via email only.

The registration and online submission functions have been disabled.

Please send your manuscripts to ans@cscanada.net，or  ans@cscanada.org  for consideration. We look forward to receiving your work.

 

 Articles published in Advances in Natural Science are licensed under Creative Commons Attribution 4.0 (CC-BY).

 ADVANCES IN NATURAL SCIENCE Editorial Office

Address: 1055 Rue Lucien-L'Allier, Unit #772, Montreal, QC H3G 3C4, Canada.

Telephone: 1-514-558 6138
Website: Http://www.cscanada.net; Http://www.cscanada.org
E-mail:caooc@hotmail.com; office@cscanada.net

Copyright © 2010 Canadian Research & Development Centre of Sciences and Cultures