Paper Titles
Comparison of Computational Crack Path Predictions with Experimental Findings for a Quarter-Circular Surface Crack in a Shaft under Torsion
p.161
Wire Cable Failures in Climbing Anchor Chocks
p.165
Experiment Studies on Fracture Energy of Cement Paste and Mortar
p.169
Deformation and Damage Evolution of the Microstructure around Ti-Particles in IF Steel during Tensile Deformation
p.173
Gearbox Failure Detection Using Growing Hierarchical Self-Organizing Map
p.177
Interfacial Fracture Toughness of APS Thermal Barrier Coating under High Temperature
p.181
Fatigue Analysis of Forged Aerospace Components Based on Micro Structural Parameters
p.185
Research on Fracture Damage Coupled with Crack Arrest by Anchorage Model of Discontinuous Jointed Rock Mass under the State of Complex Stress
p.189
Patternanalysis of the Severity of Multiple Crack Arrays
p.193

Gearbox Failure Detection Using Growing Hierarchical Self-Organizing Map

Article Preview

Abstract:

Machine fault diagnosis is essentially an issue of pattern recognition, which heavily depends on suitable unsupervised learning method. The Self-Organizing Map (SOM), a popular unsupervised neural network, has been used for failure detection but with two limitations: needing predefined static architecture and lacking ability for the representation of hierarchical relations in the data. This paper presents a novel study on failure detection of gearbox using the Growing Hierarchical Self-Organizing Map (GHSOM), an artificial neural network model with hierarchical architecture composed of independent growing SOMs. The GHSOM can adapt its architecture during unsupervised training process and provide a global orientation in the individual layers of the hierarchy; hence the original data structure can be described correctly for machine faults diagnosis. Gearbox vibration signals measured under different operating conditions are analyzed using the proposed technique. The results prove that the hierarchical relations in the gearbox failure data can be intuitively represented, and inherent structure can be unfolded. Then gearbox operating conditions including normal, tooth cracked and tooth broken are classified and recognized clearly. The study confirms that GHSOM is very useful and effective for pattern recognition in mechanical fault diagnosis, and provides a good potential for application in practice.

You might also be interested in these eBooks
Advances in Fracture and Damage Mechanics VI View Preview

Info:

Periodical:

Key Engineering Materials (Volumes 348-349)

Pages:

177-180

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.348-349.177

Citation:

Cite this paper

Online since:

September 2007

Authors:

Guang Lan Liao, Tie Lin Shi, Zi Rong Tang

Keywords:

Failure Detection, Hierarchical Structure, Self-Organizing Maps

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2007 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

References

[1] A. Versicherungs-AG: Handbook of Loss Prevention (Springer- Verlag, Berlin 1978).

Google Scholar

[2] T. Kohonen. Self-organized formation of topologically correct feature maps. Biological Cybernetics. Vol. 43 (1982), p.59.

DOI: 10.1007/bf00337288

Google Scholar

[3] A. Rauber, D. Merkl, M. Dittenbach. The Growing Hierarchical Self-Organizing Map: Exploratory Analysis of High-Dimensional Data. IEEE Transactions on Neural Networks. Vol. 13 (2002), p.1331.

DOI: 10.1109/tnn.2002.804221

Google Scholar

[4] X.D. Zhang, J. Zhu, D.M. Qiu. The application of self-organizing maps neural networks model in turbine fault diagnosis. Turbine Technology. Vol. 36 (1994), p.243(in Chinese).

Google Scholar

[5] G.C. Zhang, W.Y. Zhao, Y.D. Shen and F.R. Tu: The feature of gear fatigue crack and its diagnostic method. J. of Chinese Mech. Transm., Vol. 18 (1994), p.21(in Chinese).

Google Scholar