State evaluation of power-shift steering transmission based on hypersphere support vector machine

Yingfeng Zhang*, Biao Ma, Lili Cui, Hailing Zhang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

The hypersphere support vector machine is an efficient method to evaluate the state of mechanism. The state of Power-Shift Steering Transmission (PSST) is studied using hypersphere support vector machine. The theory of hypersphere support vector machine is researched and an evaluation model is developed. The generalization of the model is analyzed. The spectrometric oil analysis data are processed using Principal Component Analysis (PCA) method and the selection of parameters is made. The influence of abnormal for performance of hypersphere support vector machine is analyzed. On the basis of training samples, the state of test samples is evaluated. It has been proved that hypersphere support vector machine is suitable for evaluating the state of PSST. Moreover, the correct rate of model can be improved greatly if abnormal samples are taken into account.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Mechatronics and Automation, ICMA 2010
Pages1142-1146
Number of pages5
DOIs
Publication statusPublished - 2010
Event2010 IEEE International Conference on Mechatronics and Automation, ICMA 2010 - Xi'an, China
Duration: 4 Aug 20107 Aug 2010

Publication series

Name2010 IEEE International Conference on Mechatronics and Automation, ICMA 2010

Conference

Conference2010 IEEE International Conference on Mechatronics and Automation, ICMA 2010
Country/TerritoryChina
CityXi'an
Period4/08/107/08/10

Keywords

  • Hypersphere support vector machine
  • Power-Shift Steering Transmission(PSST)
  • State evaluation

Fingerprint

Dive into the research topics of 'State evaluation of power-shift steering transmission based on hypersphere support vector machine'. Together they form a unique fingerprint.

Cite this