國立虎尾科技大學 |

Early Fault Detection for Gear Shaft and Planetary Gear Based on Wavelet and Hidden Markov Modeling.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Early Fault Detection for Gear Shaft and Planetary Gear Based on Wavelet and Hidden Markov Modeling./
Author:	Yu, Jing.
Description:	148 p.
Notes:	Source: Dissertation Abstracts International, Volume: 73-06, Section: B, page: .
Contained By:	Dissertation Abstracts International73-06B.
Subject:	Engineering, Mechanical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NR78067
ISBN:	9780494780671

Early Fault Detection for Gear Shaft and Planetary Gear Based on Wavelet and Hidden Markov Modeling.
Yu, Jing.

Early Fault Detection for Gear Shaft and Planetary Gear Based on Wavelet and Hidden Markov Modeling. - 148 p.

Source: Dissertation Abstracts International, Volume: 73-06, Section: B, page: .

Thesis (Ph.D.)--University of Toronto (Canada), 2011.

Fault detection and diagnosis of gear transmission systems have attracted considerable attention in recent years, due to the need to decrease the downtime on production machinery and to reduce the extent of the secondary damage caused by failures. However, little research has been done to develop gear shaft and planetary gear crack detection methods based on vibration signal analysis. In this thesis, an approach to gear shaft and planetary gear fault detection based on the application of the wavelet transform to both the time synchronously averaged (TSA) signal and residual signal is presented. Wavelet approaches themselves are sometimes inefficient for picking up the fault signal characteristic under the presence of strong noise. In this thesis, the autocovariance of maximal energy wavelet coefficients is first proposed to evaluate the gear shaft and planetary gear fault advancement quantitatively. For a comparison, the advantages and disadvantages of some approaches such as using variance, kurtosis, the application of the Kolmogorov-Smirnov test (K-S test), root mean square (RMS) , and crest factor as fault indicators with continuous wavelet transform (CWT) and discrete wavelet transform (DWT) for residual signal, are discussed. It is demonstrated using real vibration data that the early faults in gear shafts and planetary gear can be detected and identified successfully using wavelet transforms combined with the approaches mentioned above.

ISBN: 9780494780671Subjects--Topical Terms:

845387
Engineering, Mechanical.

Early Fault Detection for Gear Shaft and Planetary Gear Based on Wavelet and Hidden Markov Modeling.
LDR:03111nam 2200277 4500 001 712983
005 20121003100328.5
008 121101s2011 ||||||||||||||||| ||eng d
020 $a 9780494780671
035 $a (UMI)AAINR78067
035 $a AAINR78067
040 $a UMI $c UMI
100 1 $a Yu, Jing. $3 845542
245 1 0 $a Early Fault Detection for Gear Shaft and Planetary Gear Based on Wavelet and Hidden Markov Modeling.
300 $a 148 p.
500 $a Source: Dissertation Abstracts International, Volume: 73-06, Section: B, page: .
500 $a Adviser: Viliam Makis.
502 $a Thesis (Ph.D.)--University of Toronto (Canada), 2011.
520 $a Fault detection and diagnosis of gear transmission systems have attracted considerable attention in recent years, due to the need to decrease the downtime on production machinery and to reduce the extent of the secondary damage caused by failures. However, little research has been done to develop gear shaft and planetary gear crack detection methods based on vibration signal analysis. In this thesis, an approach to gear shaft and planetary gear fault detection based on the application of the wavelet transform to both the time synchronously averaged (TSA) signal and residual signal is presented. Wavelet approaches themselves are sometimes inefficient for picking up the fault signal characteristic under the presence of strong noise. In this thesis, the autocovariance of maximal energy wavelet coefficients is first proposed to evaluate the gear shaft and planetary gear fault advancement quantitatively. For a comparison, the advantages and disadvantages of some approaches such as using variance, kurtosis, the application of the Kolmogorov-Smirnov test (K-S test), root mean square (RMS) , and crest factor as fault indicators with continuous wavelet transform (CWT) and discrete wavelet transform (DWT) for residual signal, are discussed. It is demonstrated using real vibration data that the early faults in gear shafts and planetary gear can be detected and identified successfully using wavelet transforms combined with the approaches mentioned above.
520 $a In the second part of the thesis, the planetary gear deterioration process from the new condition to failure is modeled as a continuous time homogeneous Markov process with three states: good, warning, and breakdown. The observation process is represented by two characteristics: variance and RMS based on the analysis of autocovariance of DWT applied to the TSA signal obtained from planetary gear vibration data. The hidden Markov model parameters are estimated by maximizing the pseudo likelihood function using the EM iterative algorithm. Then, a multivariate Bayesian control chart is applied for fault detection. It can be seen from the numerical results that the Bayesian chart performs better than the traditional Chi-square chart.
590 $a School code: 0779.
650 4 $a Engineering, Mechanical. $3 845387
690 $a 0548
710 2 $a University of Toronto (Canada). $b Mechanical and Industrial Engineering. $3 845502
773 0 $t Dissertation Abstracts International $g 73-06B.
790 1 0 $a Makis, Viliam, $e advisor
790 $a 0779
791 $a Ph.D.
792 $a 2011
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NR78067