A Hybrid Feature Selection Based on Ant Colony Optimization and Probabilistic Neural Networks for Bearing Fault Diagnostics

Abstract:

Article Preview

This paper presents a novel hybrid feature selection algorithm based on Ant Colony Optimization (ACO) and Probabilistic Neural Networks (PNN). The wavelet packet transform (WPT) was used to process the bearing vibration signals and to generate vibration signal features. Then the hybrid feature selection algorithm was used to select the most relevant features for diagnostic purpose. Experimental results for bearing fault diagnosis have shown that the proposed hybrid feature selection method has greatly improved the diagnostic performance.

Info:

Periodical:

Edited by:

Kai Cheng, Yingxue Yao and Liang Zhou

Pages:

573-577

Citation:

Y.H. Gai and G. Yu, "A Hybrid Feature Selection Based on Ant Colony Optimization and Probabilistic Neural Networks for Bearing Fault Diagnostics", Applied Mechanics and Materials, Vols. 10-12, pp. 573-577, 2008

Online since:

December 2007

Authors:

Export:

Price:

$38.00

[1] H.Y. Yang, Joseph Mathew and L. Ma: Mechanical System and Signal Processing, Vol. 19 (2005), pp.341-356.

[2] R.X. Gao and R. Yan: Int. J. Manufacturing Research, Vol. 1 (2006), pp.18-40.

[3] J. Yang and V. Honavar: IEEE Transactions on Intelligent System, Vol. 13 (1998), pp.44-49.

[4] M. Dorigo, V. Maniezzo, A. Colorni: IEEE Tans. Syst. Man Cybern, Vol. 26 (1996) No. 1, pp.29-41.

[5] M. Dorigo, G. Di Caro and LM. Gambardella: Artificial Life, Vol. 5 (1999) No. 2, pp.137-172.

[6] D.F. Specht: Neural Networks, Vol. 3 (1990), pp.109-118.

[7] D. Merkle, M. Middendorf and H. Schmeck: Proc. of the genetic and evolutionary computation conference, (2000), pp.893-900.

[8] Information on http: /www. eecs. case. edu/laboratory/bearing/download. htm.