Multi-Resolution WNN Fault Diagnosis Model Based on Unscented Kalman Filtering for Rotating Machinery

Yan Ming Wei; Xu Sheng Gan; Jie Yang

doi:10.4028/www.scientific.net/AMM.687-691.1030

Paper Titles

Designing and Constructing a Non-Contact Measuring Device for 3D Objects
p.1011

Inference for Burr-XII Masked System Lifetime Data in Step-Stress Partially Accelerated Life Test with Type-I Progressive Hybrid Censoring
p.1015

Numerical Analysis of Transducer Installation Effect on Ultrasonic Gas Flow Meter
p.1019

The Research on Weak Fault Time Domain Feature Extraction of Diesel Engine Instantaneous Speed
p.1026

Multi-Resolution WNN Fault Diagnosis Model Based on Unscented Kalman Filtering for Rotating Machinery
p.1030

The Research on the Detection Methods of EMU Break Valves Features
p.1034

The Design and Realization of Airborne Electrical Equipments’ Online Test System in the Environments of Mechanics
p.1038

Application of Correlation Dimension in Extraction of Power Plant Blower Bearing Fault Feature
p.1044

The GUI-Based Simulation Optimization Platform for Fault Grey Prediction of Diesel Engine
p.1049

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 687-691Multi-Resolution WNN Fault Diagnosis Model Based...

Multi-Resolution WNN Fault Diagnosis Model Based on Unscented Kalman Filtering for Rotating Machinery

Abstract:

BP neural network has a good nonlinear mapping ability, and can describe the relationship between frequency characteristics and fault. However, the multi-resolution wavelet neural network has the simple learning rules, fast training speed with the avoidance of local minima. So a multi-resolution wavelet neural network based on UKF is proposed to solve the problem of fault diagnosis for rotating machinery. The simulation result shows that the proposed multi-resolution wavelet neural network based on UKF value has a good diagnosis capability, and is better than that of traditional BP neural network and wavelet neural network.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 687-691)

Pages:

1030-1033

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.687-691.1030

Citation:

Cite this paper

Online since:

November 2014

Authors:

Yan Ming Wei, Xu Sheng Gan, Jie Yang

Keywords:

Fault Diagnosis, Multi-Resolution, Rotating Machinery, UKF, WNN

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Z. C. Chang, T. M. Chang. A method for intelligent fault diagnosis of rotating machinery. Digital Signal Processing, 14, (2004), 203-217.

DOI: 10.1016/j.dsp.2003.12.003

Google Scholar

[2] M. J. Luan, F. Y. Xu, M. P. Jia. Research on the neural network in rotating Machinery fault diagnosis. Noise and Vibration Control, 2, (2008), 85-88.

Google Scholar

[3] Q. Huang, H. S. Yan, N. Li. Tian. Application of the improved genetic algorithm and BP network in rotating machinery fault diagnosis. Computer Science, 35(8), (2008), 104-105.

Google Scholar

[4] Q. H. Zhang, A. Benveniste. Wavelet networks. IEEE Trans. Neural Networks, 3, (1992), 889-898.

DOI: 10.1109/72.165591

Google Scholar

[5] M. Y. Fu, Z. H. Deng, J. W. Zhang. Kalman filter theory and application in navigation. Beijing: Science Press, (2003).

Google Scholar

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

DOI: 10.1109/jproc.2003.823141

Google Scholar

[7] Z. X. Ge, Y. M. Yang, X. S. Wen. Strong tracking UKF method and its application in fault identification. Chinese Journal of Scientific Instrument, 29(8), (2008), 1670-1674.

Google Scholar