The Performance Analysis and Prognosis Techniques of Gearbox

Abstract:

Under the situation of increasingly stringent requirements for production speed and quality, gearboxes in many manufacturing equipment production lines lose final processing quality after long-term severe service.Machine fault prognosis is for experts or on-site maintenance personnel to use measurement equipment to capture signals and conduct diagnosis and maintenance based on personal experience. As technologies are advancing rapidly and equipment is evolving with increasing level of scale, automation and complexity, traditional diagnostic methods are no longer applicable. The article aims at vibration signal of gearbox to establish analysis and prognosis techniques. Principal components analysis is utilized to effectively capture the characteristic signal. Logistic regression and autoregressive moving average models are utilized to establish the correlation between characteristic signal and gearbox health status and performance trend model for on-site maintenance personnel to instantly understand gearbox health status and potential problems.In addition, Self-organizing map is utilized to establish fault identification model for maintenance personnel to significantly reduce troubleshooting time. In the article, gear-rotor experiment platform is used to assess the feasibility of gearbox performance analysis and prognosis techniques. It is expected to provide gearbox makers and users with understanding of gearbox health status and total solutions.

• Periodical: Applied Mechanics and Materials (Volume 319)
• Pages: 393-398
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.319.393
• Online since: May 2013
• Authors: Chun Chieh Wang, Yuan Kang, Tse Yi Tu
• Keywords: Autoregressive Moving Average, Logistic Regression, Principal Component Analysis (PCA), Self-Organizing Maps

References

[1] Man, Z., Wang, W., Khoo, S., Yin, J., "Optimal sinusoidal modeling of gear mesh vibration signals for gear diagnosis and prognosis," Mechanical Systems and Signal Processing, Vol.33, (2012) pp.256-274

DOI: 10.1016/j.ymssp.2012.07.004

[2] Chen, Y., He, T., Xiao, D., Cui, H.,"Gear pitting corrosion fault diagnosis based on local mean decomposition," Advanced Materials Research, Vol.562-564 (2012), pp.812-815

DOI: 10.4028/www.scientific.net/amr.562-564.812

[3] Chen, H. L., Huang, C. C., Yu, X. G., Xu, X., Sun, X., Wang, G., Wang, S. J., "An efficient diagnosis system for detection of Parkinson's disease using fuzzy k-nearest neighbor approach," Expert Systems with Applications, Vol.40, No.1 (2013),pp.263-271

DOI: 10.1016/j.eswa.2012.07.014

[4] Endo, H. and Randall, R. B., "Enhancement of Autoregressive Model Based Gear Tooth Fault Detection Technique by the Use of Minimum Entropy Deconvolution Filter," Mechanical Systems and Signal Processing, Vol.21, No.2 (2007), pp.906-919

DOI: 10.1016/j.ymssp.2006.02.005

[5] Wang, W. and Wong, A. K., "Autoregressive Model-Based Gear Fault Diagnosis," Journal of Vibration and Acoustics, Transactions of the ASME, Vol.124, No.2 (2002),pp.172-179

DOI: 10.1115/1.1456905

[6] McDonald, G. L., Zhao, Q., Zuo, Ming J.," Maximum correlated Kurtosis deconvolution and application on gear tooth chip fault detection," Mechanical Systems and Signal Processing, Vol.33,(2012), pp.237-255

DOI: 10.1016/j.ymssp.2012.06.010

[7] T. Kohonen, "The self-organizing map," Proc. IEEE, Vol.78, No.9 (1990), pp.1481-1480

[8] J. Vesanto, "SOM-Based Data Visualization Method," Intelligence Data Anal, Vol.3,No.2, (1999), pp.111-126

[9] Cao, Y. P., "Fault diagnosis of a gas turbine gas fuel system using a self-organizing network," Advanced Science Letters, Vol.8 (2012), pp.386-392

DOI: 10.1166/asl.2012.2402