PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
January 1, 2013Journal of Mechanical Engineering70 citationsOpen Access

Remaining Life Predictions of Rolling Bearing Based on Relative Features and Multivariable Support Vector Machine

ZSZhongjie Shen

Key Points

Key points are not available for this paper at this time.

Abstract

摘要: 为解决有限状态数据下滚动轴承剩余寿命难以估算的问题,提出一种基于相对特征和多变量支持向量机(Multivariable support vector machine, MSVM)的剩余寿命预测的新方法。该方法利用不受轴承个体差异影响的相对方均根值(Relative root mean square, RRMS) 评估轴承性能衰退规律,运用相关分析选取敏感特征作为输入,构造兼顾多变量回归和小样本预测双重优势的MSVM模型预测轴承剩余寿命。与单变量支持向量机相比,MSVM克服了结构简单、信息匮乏等缺点,实现小样本数据潜在信息的最大挖掘。运用仿真数据和轴承全寿命试验数据对预测模型进行检验,结果表明MSVM可在小样本条件下利用尽可能多的有效信息获得准确的预测结果,具有较强的工程使用价值和通用性。

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Zhongjie Shen (2013) studied this question.

synapsesocial.com/papers/6a22ac73877bbd4bf81195a7https://doi.org/10.3901/jme.2013.02.183
Ask AI
Helpful
Bookmark
Share
View Full Paper