Feature Extraction of Diesel Engine Wear Fault Based on Local Tangent Space Alignment

Hai Bing Xiao; Xiao Peng Xie; Shou Qin Zhou; Heng Xing Xie

doi:10.4028/www.scientific.net/AMM.482.179

Paper Titles

Effects of High-Speed Railway in Tunnel on Vibration Response of Upper Building
p.155

A Design Method of Position Schemes for Particle Dampers Applied to a Flywheel
p.163

The Vibration Characteristic Analysis of Feed System of CNC Machine Tool
p.169

Vibration Characteristics Analysis of Wide-Chord Hollow Fan Blade
p.174

Feature Extraction of Diesel Engine Wear Fault Based on Local Tangent Space Alignment
p.179

Field Test and Analysis for Environmental Vibration Induced by Road Traffic Load
p.183

Research of Frequency Band by Multiple-Mode Extended for Longitudinal Vibration Acoustic Transducer
p.188

Low Frequency Micro-Vibration Active Isolation Control System Design and Experimental Research
p.195

Study on Vibration Characteristics of the Vehicles Wing Structure in High Temperature Environment
p.200

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 482Feature Extraction of Diesel Engine Wear Fault...

Feature Extraction of Diesel Engine Wear Fault Based on Local Tangent Space Alignment

Abstract:

In view of diesel engine wear fault feature extraction, feature extraction of diesel engine wear fault based on Local Tangent Space Alignment (LTSA) was put forward. This paper analyzes LTSA algorithm which reveals the characteristics of manifold learning. Take diesel engine fault diagnosis test rig as example, vibration information was got through imitating different kinds of diesel engine wear fault. LTSA algorithm was applied for dimensionality reduction. LTSA algorithm’s classification performance was compared in accordance with recognition rate of multi-class SVM. The experimental results show that LTSA has high recognition rate and is a very effective feature extraction method for diesel engine wear fault.

You might also be interested in these eBooks

Structural Engineering, Vibration and Aerospace Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 482)

Pages:

179-182

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.482.179

Citation:

Cite this paper

Online since:

December 2013

Authors:

Hai Bing Xiao, Xiao Peng Xie, Shou Qin Zhou, Heng Xing Xie

Keywords:

Fault Diagnosis, Feature Extraction, Local Tangent Space Alignment, Vibration Analysis, Wear Fault

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] I. T. Jolliffe: Principle Component Analysis, 2nd ed., (Springer-Verlag press, New York 2002).

Google Scholar

[2] I. C. K. Williams: On a connection between kernel PCA and metric multidimensional scaling, machine learning Vol. 46, (2004): p.11.

Google Scholar

[3] S. Roweis, and L. K. Saul: Nonlinear dimensionality reduction by locally linear embedding, Science Vol. 290(2000), p.2323.

DOI: 10.1126/science.290.5500.2323

Google Scholar

[4] Jiang Quansheng, Jia Minping, and Hu Jianzhong: Manifold lapacian eigenmap method for fault diagnosis, Chinese Journal of Mechanical Engineering Vol. 21 (2008), p.90.

Google Scholar

[5] Xie Xiaopeng, Xiao Haibing, and Feng Wei: Study on the method of engine fault diagnosis based on energy loss, Lurbrication Engineering, Vol. 35(2011), p.1. (In Chinese).

Google Scholar

[6] ZHAN Yu-bin, YIN Jian-ping, and LIU Xin-wang: A Kernel PCA View of the Local Tangent Space Alignment Algorithm, Computer Engineering&Science, Vol. 6(2010), p.158. (In Chinese).

Google Scholar