RBF Neural Network Model Training by Unscented Kalman Filter and its Application in Mechanical Fault Diagnosis

Xu Sheng Gan; Hua Ping Li; Hai Long Gao

doi:10.4028/www.scientific.net/AMM.602-605.2383

Paper Titles

Development of Response Time Tester
p.2366

Research on Rolling Bearing Fault Monitoring System Based on LabVIEW
p.2370

Monitor Design of Hydraulic Experimental System for Electric Submersible Pump
p.2375

Potential of Photoionization Detector for Organic Compounds Analysis at a Brownfield Site Investigation
p.2379

RBF Neural Network Model Training by Unscented Kalman Filter and its Application in Mechanical Fault Diagnosis
p.2383

A Novel Vehicle Type Recognition Based on Hierarchical Matching
p.2387

Application of Factor Analysis in Measurement and Assessment of Corporate Governance System
p.2391

Spectrophotometric Method in the Determination of Aminophylline Content
p.2395

A Near-Infrared Starry Image Stars Identifying Method Based on Star Magnitude Differ and Star Point Pairs
p.2399

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 602-605RBF Neural Network Model Training by Unscented...

RBF Neural Network Model Training by Unscented Kalman Filter and its Application in Mechanical Fault Diagnosis

Abstract:

To improve the ability of fault diagnosis for mechanical equipment, a Radial Basis Function Neural Network (RBFNN) diagnosis method based on Unscented Kalman Filter (UKF) algorithm is proposed. In the algorithm, at first, UKF algorithm is used to estimate the parameters of RBFNN, and then the proposed method is introduced into the fault diagnosis of mechanical equipment. The simulation indicates that the established model has a good diagnosis performance for mechanical fault diagnosis.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 602-605)

Pages:

2383-2386

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.602-605.2383

Citation:

Cite this paper

Online since:

August 2014

Authors:

Xu Sheng Gan*, Hua Ping Li, Hai Long Gao

Keywords:

Fault Diagnosis, Mechanical Equipment, Neural Network (NN), Unscented Kalman Filter

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] J. Moody, C. Darken. Fast learning in networks of locally-tuned processing units. Neural Computation, 1(2), (1989), 281-294.

DOI: 10.1162/neco.1989.1.2.281

Google Scholar

[2] S. J. Hanson, D. J. Burr. Minkowski-r back-propagation: learning in connectionist models with non-euclidean error signals. Neural Information Processing Systems, (1987), 348-357.

Google Scholar

[3] S. Chert, P. M. Crant, C. F. N. Cown. Orthogonal least square algorithm for radial basis function networks. IEEE Transaction on Neural Networks, 2(2), (1991), 302-309.

DOI: 10.1109/72.80341

Google Scholar

[4] E. A. Wan, R. van der Merwe. The unscented Kalman filter for nonlinear estimation. Proceedings of IEEE Symposium 2000, Lake Louise Alberta, Canada, Oct. (2000).

DOI: 10.1109/asspcc.2000.882463

Google Scholar

[5] S. J. Julier, J. K. Uhlmann, H. F. Durrant-whyte. A new approach for the nonlinear transformation of means and covariances in filters and estimators. IEEE Transactions on Automatic Control, 45(3), (2000), 477-482.

DOI: 10.1109/9.847726

Google Scholar

[6] S. J. Julier, J. K. Uhlmann. Unscented filtering and nonlinear estimation. Proceedings of the IEEE, 92(3), (2004), 401-422.

DOI: 10.1109/jproc.2003.823141

Google Scholar

[7] S. J. Julier. The spherical simplex unscented transformation. Proceedings of the American Control Conference, Denver, (2003).

Google Scholar

[8] X. H. Zhang, Y. Lei. Application of BP neural network in mechanical fault diagnosis. Noise and Vibration Control, 28(5), (2008), 95-97.

Google Scholar