Principal Components of Superhigh-Dimensional Statistical Features and Support Vector Machine for Improving Identification Accuracies of Different Gear Crack Levels under Different Working Conditions

Gears are widely used in gearbox to transmit power from one shaft to another. Gear crack is one of the most frequent gear fault modes found in industry. Identification of different gear crack levels is beneficial in preventing any unexpected machine breakdown and reducing economic loss because gear...

Full description

Saved in:
Bibliographic Details
Main Authors: Dong Wang, Kwok-Leung Tsui, Peter W. Tse, Ming J. Zuo
Format: Article
Language:English
Published: Wiley 2015-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2015/420168
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849687044154982400
author Dong Wang
Kwok-Leung Tsui
Peter W. Tse
Ming J. Zuo
author_facet Dong Wang
Kwok-Leung Tsui
Peter W. Tse
Ming J. Zuo
author_sort Dong Wang
collection DOAJ
description Gears are widely used in gearbox to transmit power from one shaft to another. Gear crack is one of the most frequent gear fault modes found in industry. Identification of different gear crack levels is beneficial in preventing any unexpected machine breakdown and reducing economic loss because gear crack leads to gear tooth breakage. In this paper, an intelligent fault diagnosis method for identification of different gear crack levels under different working conditions is proposed. First, superhigh-dimensional statistical features are extracted from continuous wavelet transform at different scales. The number of the statistical features extracted by using the proposed method is 920 so that the extracted statistical features are superhigh dimensional. To reduce the dimensionality of the extracted statistical features and generate new significant low-dimensional statistical features, a simple and effective method called principal component analysis is used. To further improve identification accuracies of different gear crack levels under different working conditions, support vector machine is employed. Three experiments are investigated to show the superiority of the proposed method. Comparisons with other existing gear crack level identification methods are conducted. The results show that the proposed method has the highest identification accuracies among all existing methods.
format Article
id doaj-art-023d6965db9c4c0f80eeac1ae6433a8f
institution DOAJ
issn 1070-9622
1875-9203
language English
publishDate 2015-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-023d6965db9c4c0f80eeac1ae6433a8f2025-08-20T03:22:27ZengWileyShock and Vibration1070-96221875-92032015-01-01201510.1155/2015/420168420168Principal Components of Superhigh-Dimensional Statistical Features and Support Vector Machine for Improving Identification Accuracies of Different Gear Crack Levels under Different Working ConditionsDong Wang0Kwok-Leung Tsui1Peter W. Tse2Ming J. Zuo3Department of Systems Engineering and Engineering Management, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong KongDepartment of Systems Engineering and Engineering Management, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong KongDepartment of Systems Engineering and Engineering Management, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong KongSchool of Mechatronics Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu, Sichuan 611731, ChinaGears are widely used in gearbox to transmit power from one shaft to another. Gear crack is one of the most frequent gear fault modes found in industry. Identification of different gear crack levels is beneficial in preventing any unexpected machine breakdown and reducing economic loss because gear crack leads to gear tooth breakage. In this paper, an intelligent fault diagnosis method for identification of different gear crack levels under different working conditions is proposed. First, superhigh-dimensional statistical features are extracted from continuous wavelet transform at different scales. The number of the statistical features extracted by using the proposed method is 920 so that the extracted statistical features are superhigh dimensional. To reduce the dimensionality of the extracted statistical features and generate new significant low-dimensional statistical features, a simple and effective method called principal component analysis is used. To further improve identification accuracies of different gear crack levels under different working conditions, support vector machine is employed. Three experiments are investigated to show the superiority of the proposed method. Comparisons with other existing gear crack level identification methods are conducted. The results show that the proposed method has the highest identification accuracies among all existing methods.http://dx.doi.org/10.1155/2015/420168
spellingShingle Dong Wang
Kwok-Leung Tsui
Peter W. Tse
Ming J. Zuo
Principal Components of Superhigh-Dimensional Statistical Features and Support Vector Machine for Improving Identification Accuracies of Different Gear Crack Levels under Different Working Conditions
Shock and Vibration
title Principal Components of Superhigh-Dimensional Statistical Features and Support Vector Machine for Improving Identification Accuracies of Different Gear Crack Levels under Different Working Conditions
title_full Principal Components of Superhigh-Dimensional Statistical Features and Support Vector Machine for Improving Identification Accuracies of Different Gear Crack Levels under Different Working Conditions
title_fullStr Principal Components of Superhigh-Dimensional Statistical Features and Support Vector Machine for Improving Identification Accuracies of Different Gear Crack Levels under Different Working Conditions
title_full_unstemmed Principal Components of Superhigh-Dimensional Statistical Features and Support Vector Machine for Improving Identification Accuracies of Different Gear Crack Levels under Different Working Conditions
title_short Principal Components of Superhigh-Dimensional Statistical Features and Support Vector Machine for Improving Identification Accuracies of Different Gear Crack Levels under Different Working Conditions
title_sort principal components of superhigh dimensional statistical features and support vector machine for improving identification accuracies of different gear crack levels under different working conditions
url http://dx.doi.org/10.1155/2015/420168
work_keys_str_mv AT dongwang principalcomponentsofsuperhighdimensionalstatisticalfeaturesandsupportvectormachineforimprovingidentificationaccuraciesofdifferentgearcracklevelsunderdifferentworkingconditions
AT kwokleungtsui principalcomponentsofsuperhighdimensionalstatisticalfeaturesandsupportvectormachineforimprovingidentificationaccuraciesofdifferentgearcracklevelsunderdifferentworkingconditions
AT peterwtse principalcomponentsofsuperhighdimensionalstatisticalfeaturesandsupportvectormachineforimprovingidentificationaccuraciesofdifferentgearcracklevelsunderdifferentworkingconditions
AT mingjzuo principalcomponentsofsuperhighdimensionalstatisticalfeaturesandsupportvectormachineforimprovingidentificationaccuraciesofdifferentgearcracklevelsunderdifferentworkingconditions