Application of the Least Squares Support Vector Machine for Life Prediction of Vital Parts

Abstract:

In order to better study the wear state of vital parts of the large scale equipment, and overcoming the disadvantage of small sample of vital parts, we use the least squares support vector machine (LS_SVM) algorithm to predict the wear state of vital parts. Using of quantum particle swarm optimization (QPSO) to optimize parameters least squares support vector machine, and achieved good results. Compared those with the method that use of curve fitting to predict the data development trend, show that this method is superior to the curve fitting method, and has good application value.

• Periodical: Applied Mechanics and Materials (Volumes 584-586)
• Pages: 2129-2132
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.584-586.2129
• Online since: July 2014
• Authors: Hong Kai Wang, Ji Sheng Ma, Li Qing Fang, Da Lin Wu, Yan Feng Yang
• Keywords: Curve Fitting, Least Squares Support Vector Machine, Quantum Particle Swarm Optimization, Small Sample, Vital Part

References

[1] Vapnik Vladimir N. 2000 The Nature of Statistical Learning Theory, M. Springer -Verlag, New York, Inc.

[2] Burges J C. 1999 A Tutorial on Support Vector Machines for Pattern Recognition, M. Kluwer Academic Publishers, Boston.

[3] Yan Weiwu, Shao Huihe. 2003 Application of support vector machines and least squares support vector machines to heart disease diagnose, J. Control and Decision. 3(18): 358－360.

DOI: 10.1109/acc.2003.1239851

[4] SHAN Yan, Xu Wenbo, SUN Ju. 2006 Application of quantum-behaved particle swarm optimization in training support vector machine, J. Computer Application. 26(11): 2645－2647, 2677.