The Fault Diagnosis Method of Diesel Based on Wavelet Pocket and BP Neural Network

Hong Hui Sun; Jun Xu; Qing Hua Zhang; Hong Xia Wang

doi:10.4028/www.scientific.net/AMM.635-637.910

Paper Titles

Development of Key Reliability Tester
p.890

Multi-Channel Simultaneous Data Acquisition System with Variable Sampling Rate
p.896

Somatosensory Application Study Based on Kinect Skeletal Tracking
p.901

Vibration Signal of Generator Features and its Fault Diagnosis Application
p.906

The Fault Diagnosis Method of Diesel Based on Wavelet Pocket and BP Neural Network
p.910

Study on Inversion Surface Parameters of Remote-Sensing Information Serving Vegetation-Surface
p.914

Transmission Method Based on Small Relay Core for Achieve Dynamic Measurement of the Flatness
p.918

Multiple Leakage Detection and Localization Method Based on Bayesian Theory and Genetic Algorithm
p.924

Novel Low-Frequency Rectangular-Loop Piezoelectric Energy Harvester
p.928

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 635-637The Fault Diagnosis Method of Diesel Based on...

The Fault Diagnosis Method of Diesel Based on Wavelet Pocket and BP Neural Network

Abstract:

Because of the well time-frequency spectrum disposal capability of wavelet packet, the wavelet packet algorithm is used to analyze the time - frequency characteristics of diesel vibration signals. The signal energy distributing characteristics based on wavelet packet transform. are extracted and taken as diagnostic characteristic vector, then improved BP neural network algorithm that connects additional momentum with self-adaptive learning rate was used to classify and recognize faults of diesel valves. The experimental results show the fault diagnosis method of diesel based on wavelet pocket and BP neural network is effective and feasible.

You might also be interested in these eBooks

Advanced Design and Manufacturing Technology IV

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 635-637)

Pages:

910-913

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.635-637.910

Citation:

Cite this paper

Online since:

September 2014

Authors:

Hong Hui Sun, Jun Xu, Qing Hua Zhang, Hong Xia Wang

Keywords:

BP Neural Network (BPNN), Fault Diagnosis, Vibration Signal, Wavelet Packe

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Antoni,J.,J. Daniere, et al, in: Effective Vibration Analysis of IC Engines using Stability. Part. 1 New result on the reconstruction of the cylinder pressure, Journal of Sound and Vibration Vol. 57 (2002), p: 839-856.

DOI: 10.1006/jsvi.2002.5063

Google Scholar

[2] Meyer Y, in: Wavelets Algorithms and Applications, edited by Philadelphia: Society for Industrial and Applied Mathematics (1993).

Google Scholar

[3] Liu Shi-yuan, in: An improved algorithm for wavelet packet and its application to vibration diagnosis in diesel engines, Transactions of CSICE. Vol. 18 (2000), p: 11-15. (In Chinese).

Google Scholar

[4] Sun Hong-hui, in: The recognition method of objects based on moment invariant and BP Neural Network, Microelectronics & computer. Vol. 28 (2011), p: 63-65. (In Chinese).

Google Scholar

[5] Kung . S Y, Hwang J N. in: An Algebraic Projection Analysis for Optional Hidden Units Size and Learning Rates in Back-Propagation Learning. IEEE, Vol. 49 (2007), p: 363-370.

DOI: 10.1109/icnn.1988.23868

Google Scholar