The Application on Gear Fault Detection by Using Fast Time-Frequency Order Spectrum

Yuan Kang; Chun Chieh Wang

doi:10.4028/www.scientific.net/AMM.284-287.538

Paper Titles

Optimization of Aerodynamic Performance of Wind Turbine Blades
p.518

Rapid Discrimination of Bacteria and Bacteriophages by Raman Spectroscopy
p.523

Seawater Flow Characteristics and Drag Force Variation with Inflow Angle in Tidal Current Turbine System
p.528

Taguchi Optimization of Machining Quality in Step Drilling of Composites Based on Membership Function
p.533

The Application on Gear Fault Detection by Using Fast Time-Frequency Order Spectrum
p.538

The Fluorescence Image of Portable System Enhanced by Asynchronous Trigger UV-LED Excitation
p.543

The Membrane Thickness Prediction of Solder Paste Process by Phase-Shifting Projection
p.550

The Numerical Simulation of Two-Degrees-of-Freedom Vortex-Induced Vibrations of Circular Cylinder with High Mass-Ratio
p.557

The Study of Dynamic Simulation on Five Axis CNC Machine
p.562

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 284-287The Application on Gear Fault Detection by Using...

The Application on Gear Fault Detection by Using Fast Time-Frequency Order Spectrum

Abstract:

The increased instantaneous speed in signal patterns which generated by the mechanical equipment are largely non-stationary. The signal features are averaged in correspondence with the length of analysis time, thus making it impossible to highlight the signal characteristics and caused the difficulties in identifying or diagnosing faults. In this paper, the wavelet order spectrum method using a combination of wavelet transform (WT) and speed frequency ordering. The feature order does not change with variations in speed, thus can effectively identify non-stationary faults in mechanical equipment. In addition, Principal Components Analysis (PCA) is used to extract the main features of the wavelet order spectrum and reduce the volume of data. This is combined with self-organizing maps (SOM) to devise an artificial intelligence method for fault diagnosis in non-stationary states. Lastly, the wavelet order spectrum method is verified by using a gear-rotor test platform that proofs the feasibility for the theory.

You might also be interested in these eBooks

Innovation for Applied Science and Technology

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 284-287)

Pages:

538-542

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.284-287.538

Citation:

Cite this paper

Online since:

January 2013

Authors:

Yuan Kang, Chun Chieh Wang

Keywords:

Non-Stationary Signal, Self-Organizing Maps, Wavelet Order Spectrum

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] C. F. Xu, and G. K. Li, Practical wavelet method, Huazhong University of Science & Technology Press, pp.46-48. (2004).

Google Scholar

[2] N. Saravanan, Features by fast single-shot multiclass PSVM using Morlet wavelet for fault diagnosis of spur bevel gear box, Expert Systems with Applications, Vol. 36.

DOI: 10.1016/j.eswa.2009.01.053

Google Scholar

[3] J. Lin, and L. Qu, Feature extraction based on Morlet wavelet and its application for mechanical fault diagnosis, Journal of Sound and Vibration, Vol. 234, pp.135-148. (2000).

DOI: 10.1006/jsvi.2000.2864

Google Scholar

[4] P. Chang, Applied SOM And Neural Networks To Fault Diagnosis In Gas Turbine Generator Assemblies, Chongqing University of Science, Vol. 28, No. 2, pp.36-38. (2005).

Google Scholar

[5] S. Liu, Fault Diagnosis of Hydraulic Pump Based on Rough Set and PCA Algorithm, Fifth International Conference on Fuzzy Systems, pp.256-260. (2008).

DOI: 10.1109/fskd.2008.538

Google Scholar