The Research on Fault Diagnosis of Diesel Engine Based on EMD

Bao Lin Song

doi:10.4028/www.scientific.net/AMM.623.143

Paper Titles

Deformation Characteristic Analysis on Mechanical Expanding of Large Diameter Welding Pipe
p.125

Effects of Mould on Crimping of Large Diameter Welding Pipe
p.129

Effects of Technical Parameters on Mechanical Expanding of Large Diameter Welding Pipe
p.133

Sensitivity Analysis of Technical Parameters on Springback in Air Bending of JCO Forming
p.137

The Research on Fault Diagnosis of Diesel Engine Based on EMD
p.143

Research on the Bus Passenger Motion Vector Algorithm Based on Video Image
p.149

Mean Shift-Based Target Tracking for Moving Spherical Object in Video
p.156

Noise-Reducing and Effect-Enhancing System for Communication Equipment Mounted on Vehicle
p.161

An Improved Algorithm on Frequent Subgraph Query
p.169

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 623The Research on Fault Diagnosis of Diesel Engine...

The Research on Fault Diagnosis of Diesel Engine Based on EMD

Abstract:

In view of the superiority of support vector machine and the fault characteristic of diesel engine, a classify method for diesel engine fault based on support vector machine is presented in this paper. First the cylinder block vibration signal on different condition was measured by the simulation test of diesel engine fuel injection system fault, then the feature parameter was extracted by empirical mode decomposition and the most impactful parameter was selected to be the input of support vector machine. The result shows that this method has fine classified ability and precision.

You might also be interested in these eBooks

Engineering Research and Designing for Industry

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 623)

Pages:

143-148

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.623.143

Citation:

Cite this paper

Online since:

August 2014

Authors:

Bao Lin Song*

Keywords:

Diesel Engine, Empirical Mode Decomposition (EMD), Fault Diagnosis, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Huang N E, Shen Z, Long S R. The Ernpirical ModeDecomposition and the Hilbrt Spectrum For Nonlinearand Non-stationary Time Series Analysis [J]. Proc. RoyalSociety. London, 1998454 (12): 903-995.

Google Scholar

[2] Yu Dejie, Cheng Junsheng, Yang Yu. Hilbert-Huang transforms method of mechanical fault diagnosis [M]. Beijing: Science Press, 2006: 21-54.

Google Scholar

[3] Vladinir N. Vapnik. the nature of statistical learning theory [M]. Zhang Xuegong. Beijing: Tsinghua University press, (2000).

Google Scholar

[4] Liu Jianmin, Chen, Qiao Xinyong, et al. EMD, genetic algorithm and neural network to fault diagnosis of diesel engine based on [J]. Journal of The Academy of Armored Forces Engineering, 2010, 24 (5): 22-24.

Google Scholar

[5] Fang Ruiming. The theory of support vector machine and its application analysis [M]. Beijing: Chinese power press, 2004: 82-92.

Google Scholar

[6] Shi Feng, Wang Xiaochuan, Li Yang and. MATLAB neural network analysis of 30 cases [M]. Beijing: Beihang University press, 2010: 125-135.

Google Scholar

[7] Zhao Jie, Wang Jiufeng. Application of support vectormachine [J]. tractor in fault diagnosis of engine and vehicle, 2009, 36 (5): 127.

Google Scholar

[8] Sun Lin, Yang Shiyuan SVM the state diagnosis of rolling bearings [J]. Journal of HeFei University of Technology, a clustering structure based on the, 2009, 32 (1): 4-8.

Google Scholar