Fault pattern recognition of Power-Shift Steering Transmission based on support vector clustering

Ying Feng Zhang; Tao Huang; Yan Yu; Jian Guo Bu; Biao Ma

doi:10.1109/ICInfA.2012.6246909

Fault pattern recognition of Power-Shift Steering Transmission based on support vector clustering

Ying Feng Zhang^*, Tao Huang, Yan Yu, Jian Guo Bu, Biao Ma

^*Corresponding author for this work

School of Mechanical Engineering

Academy of Military Transportation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Fault pattern recognition is an important work in condition monitoring of Power-Shift Steering Transmission (PSST). Spectrometric oil analysis technology is a common and useful method to study the state of PSST. But, how to find the implicit information in data and classify the running state is a difficult work. In order to solve this problem, a support vector clustering(SVC) method is applied. The building process of this method is made. Four modes of PSST is made. And to get pattern information in data, three parameters of feature information are put forward. The influence of SVC model parameters for clustering regions is analyzed and optimal parameters are determined. On the basis of feature information extracting of spectrometric oil analysis data, fault pattern recognition is made with SVC model. The method has been proved that it has better accuracy in fault pattern recognition of PSST.

Original language	English
Title of host publication	2012 IEEE International Conference on Information and Automation, ICIA 2012
Pages	895-899
Number of pages	5
DOIs	https://doi.org/10.1109/ICInfA.2012.6246909
Publication status	Published - 2012
Event	2012 IEEE International Conference on Information and Automation, ICIA 2012 - Shenyang, China Duration: 6 Jun 2012 → 8 Jun 2012

Publication series

Name	2012 IEEE International Conference on Information and Automation, ICIA 2012

Conference

Conference	2012 IEEE International Conference on Information and Automation, ICIA 2012
Country/Territory	China
City	Shenyang
Period	6/06/12 → 8/06/12

Keywords

Fault pattern recognition
Power-Shift Steering Transmission (PSST)
Support Vector Clustering (SVC)

Access to Document

10.1109/ICInfA.2012.6246909

Cite this

Zhang, Y. F., Huang, T., Yu, Y., Bu, J. G., & Ma, B. (2012). Fault pattern recognition of Power-Shift Steering Transmission based on support vector clustering. In 2012 IEEE International Conference on Information and Automation, ICIA 2012 (pp. 895-899). Article 6246909 (2012 IEEE International Conference on Information and Automation, ICIA 2012). https://doi.org/10.1109/ICInfA.2012.6246909

@inproceedings{0385618a0d1b40738c168f33b2e1bf2a,

title = "Fault pattern recognition of Power-Shift Steering Transmission based on support vector clustering",

abstract = "Fault pattern recognition is an important work in condition monitoring of Power-Shift Steering Transmission (PSST). Spectrometric oil analysis technology is a common and useful method to study the state of PSST. But, how to find the implicit information in data and classify the running state is a difficult work. In order to solve this problem, a support vector clustering(SVC) method is applied. The building process of this method is made. Four modes of PSST is made. And to get pattern information in data, three parameters of feature information are put forward. The influence of SVC model parameters for clustering regions is analyzed and optimal parameters are determined. On the basis of feature information extracting of spectrometric oil analysis data, fault pattern recognition is made with SVC model. The method has been proved that it has better accuracy in fault pattern recognition of PSST.",

keywords = "Fault pattern recognition, Power-Shift Steering Transmission (PSST), Support Vector Clustering (SVC)",

author = "Zhang, {Ying Feng} and Tao Huang and Yan Yu and Bu, {Jian Guo} and Biao Ma",

year = "2012",

doi = "10.1109/ICInfA.2012.6246909",

language = "English",

isbn = "9781467322386",

series = "2012 IEEE International Conference on Information and Automation, ICIA 2012",

pages = "895--899",

booktitle = "2012 IEEE International Conference on Information and Automation, ICIA 2012",

note = "2012 IEEE International Conference on Information and Automation, ICIA 2012 ; Conference date: 06-06-2012 Through 08-06-2012",

}

Zhang, YF, Huang, T, Yu, Y, Bu, JG & Ma, B 2012, Fault pattern recognition of Power-Shift Steering Transmission based on support vector clustering. in 2012 IEEE International Conference on Information and Automation, ICIA 2012., 6246909, 2012 IEEE International Conference on Information and Automation, ICIA 2012, pp. 895-899, 2012 IEEE International Conference on Information and Automation, ICIA 2012, Shenyang, China, 6/06/12. https://doi.org/10.1109/ICInfA.2012.6246909

Fault pattern recognition of Power-Shift Steering Transmission based on support vector clustering. / Zhang, Ying Feng; Huang, Tao; Yu, Yan et al.
2012 IEEE International Conference on Information and Automation, ICIA 2012. 2012. p. 895-899 6246909 (2012 IEEE International Conference on Information and Automation, ICIA 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Fault pattern recognition of Power-Shift Steering Transmission based on support vector clustering

AU - Zhang, Ying Feng

AU - Huang, Tao

AU - Yu, Yan

AU - Bu, Jian Guo

AU - Ma, Biao

PY - 2012

Y1 - 2012

N2 - Fault pattern recognition is an important work in condition monitoring of Power-Shift Steering Transmission (PSST). Spectrometric oil analysis technology is a common and useful method to study the state of PSST. But, how to find the implicit information in data and classify the running state is a difficult work. In order to solve this problem, a support vector clustering(SVC) method is applied. The building process of this method is made. Four modes of PSST is made. And to get pattern information in data, three parameters of feature information are put forward. The influence of SVC model parameters for clustering regions is analyzed and optimal parameters are determined. On the basis of feature information extracting of spectrometric oil analysis data, fault pattern recognition is made with SVC model. The method has been proved that it has better accuracy in fault pattern recognition of PSST.

AB - Fault pattern recognition is an important work in condition monitoring of Power-Shift Steering Transmission (PSST). Spectrometric oil analysis technology is a common and useful method to study the state of PSST. But, how to find the implicit information in data and classify the running state is a difficult work. In order to solve this problem, a support vector clustering(SVC) method is applied. The building process of this method is made. Four modes of PSST is made. And to get pattern information in data, three parameters of feature information are put forward. The influence of SVC model parameters for clustering regions is analyzed and optimal parameters are determined. On the basis of feature information extracting of spectrometric oil analysis data, fault pattern recognition is made with SVC model. The method has been proved that it has better accuracy in fault pattern recognition of PSST.

KW - Fault pattern recognition

KW - Power-Shift Steering Transmission (PSST)

KW - Support Vector Clustering (SVC)

UR - http://www.scopus.com/inward/record.url?scp=84866595029&partnerID=8YFLogxK

U2 - 10.1109/ICInfA.2012.6246909

DO - 10.1109/ICInfA.2012.6246909

M3 - Conference contribution

AN - SCOPUS:84866595029

SN - 9781467322386

T3 - 2012 IEEE International Conference on Information and Automation, ICIA 2012

SP - 895

EP - 899

BT - 2012 IEEE International Conference on Information and Automation, ICIA 2012

T2 - 2012 IEEE International Conference on Information and Automation, ICIA 2012

Y2 - 6 June 2012 through 8 June 2012

ER -

Fault pattern recognition of Power-Shift Steering Transmission based on support vector clustering

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this