English            | 设为主页 | 加入收藏 | 网站导航 | 读者留言 | 联系我们 | 返回首页 |
 
基于主元特征融合和SVM的轴承剩余寿命预测
Bearing residual life prediction based on principal component feature fusion and SVM
【索引】马海龙.基于主元特征融合和SVM的轴承剩余寿命预测[J].工矿自动化,2019,45(8):74-78.
【Reference】MA Hailong. Bearing residual life prediction based on principal component feature fusion and SVM[J].Industry and Mine Automation,2019,45(8):74-78.
【DOI】10.13272/j.issn.1671-251x.2019010085
【作者】马海龙
【Author】 MA Hailong
【作者机构】北京天地龙跃科技有限公司, 北京100013
【Unit】Beijing Tiandi Longyue Science and Technology Co.,Ltd., Beijing 100013, China
【摘要】为解决采用单一特征量预测轴承剩余寿命误差较大、有限数据样本条件下轴承剩余寿命难以估算的问题,提出了一种基于主元特征融合和支持向量机(SVM)的轴承剩余寿命预测方法。该方法采集振动加速度信号构建数据样本,提取有效值、峰值、小波熵等表征轴承退化趋势的特征指标;采用主元分析融合多个特征指标,消除特征间的冗余和相关性,构造出相对多特征的退化特征量;将退化特征量输入SVM模型中进行轴承剩余寿命预测。现场工程应用结果表明,基于主元特征融合和SVM的轴承剩余寿命预测方法可在小样本条件下筛选出包含信号绝大部分信息的主元,从而在保证预测精度的同时,减少了计算量。
【Abstract】In order to solve the problem that using single feature quantity for bearing residual life prediction had large error and it was difficult to estimate bearing residual life under the condition of limited data samples, a bearing residual life prediction method based on principal component feature fusion and support vector machine(SVM) was proposed. This method collects data samples of vibration acceleration signals and extracts the characteristic indexes such as RMS, peak value and wavelet entropy to characterize the degradation trend of bearings. The principal component analysis is used to fuse multiple feature indexs to eliminate the redundancy and correlation between features, and construct regressive feature quantities with relative multi-feature; the regressive feature quantities are input into SVM model for bearing residual life prediction. The field engineering application results show that the bearing residual life prediction method based on principal component feature fusion and SVM can screen out the principal components which contain most of the information under small sample condition, thus reducing the calculation amount while ensuring the prediction accuracy.
【关键词】 轴承剩余寿命预测; 主元特征融合; 支持向量机; 主元分析; 退化特征量
【Keywords】bearing residual life prediction; principal component feature fusion; support vector machine; principal component analysis; regressive feature
【文献出处】工矿自动化,2019年8期
【基金】中国煤炭科工集团有限公司科技创新创业资金专项资助项目(2018QN035);天地科技股份有限公司科技创新创业资金专项资助项目(2018-TD-QN045)
【分类号】TD67
HTML PDF下载
本网站仅提供本刊2009年之后的全文下载,其它年份的全文下载将自动转到中国知网。中国知网不支持迅雷等加速下载工具,请取消加速工具后下载。
【关 闭】