|本期目录/Table of Contents|

[1]田淑华,王华,洪荣晶.基于多特征集融合与多变量支持向量回归的回转支承剩余寿命评估[J].南京工业大学学报(自然科学版),2016,38(03):50-57.[doi:10.3969/j.issn.1671-7627.2016.03.009]
 TIAN Shuhua,WANG Hua,HONG Rongjing.Residual life assessment of slewing bearing based on multivariate eigenvalues fusion and support vector regression[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),2016,38(03):50-57.[doi:10.3969/j.issn.1671-7627.2016.03.009]
点击复制

基于多特征集融合与多变量支持向量回归的回转支承剩余寿命评估()
分享到:

《南京工业大学学报(自然科学版)》[ISSN:1671-7627/CN:32-1670/N]

卷:
38
期数:
2016年03期
页码:
50-57
栏目:
出版日期:
2016-05-28

文章信息/Info

Title:
Residual life assessment of slewing bearing based on multivariate eigenvalues fusion and support vector regression
文章编号:
1671-7627(2016)03-0050-08
作者:
田淑华1王华12洪荣晶1
1.南京工业大学 机械与动力工程学院,江苏 南京 211800; 2.洛阳LYC轴承有限公司,河南 洛阳 471003
Author(s):
TIAN Shuhua1WANG Hua12HONG Rongjing1
1.College of Mechanical and Power Engineering,Nanjing Tech University,Nanjing 211800,China; 2.Luoyang LYC Bearing Co. Ltd., Luoyang 471003,China
关键词:
回转支承 特征值 主成分分析 多变量支持向量回归 寿命评估
Keywords:
slewing bearing eigenvalue PCA MSVR residual life assessment
分类号:
TP206.3;TP18
DOI:
10.3969/j.issn.1671-7627.2016.03.009
文献标志码:
A
摘要:
针对回转支承剩余寿命难以评估的问题,提出一种基于温度、扭矩、振动信号时域内多个特征值融合和多变量支持向量回归(MSVR)的剩余寿命评估新方法。该方法通过主成分分析(PCA)求得温度、扭矩、振动信号性能衰退指标量化回转支承性能衰退规律,以此作为输入量构建多变量支持向量回归回转支承剩余寿命评估模型。MSVR克服了结构简单、信息匮乏等缺点,实现变量之间冗余信息的消除和样本数据潜在信息的最大挖掘,采用回转支承全寿命实验数据对评估模型进行检验,结果表明 MSVR可获得准确的评估结果。
Abstract:
A residual life assessment for slewing bearing based on characteristic indexes in time domain including temperature,torque and vibration information fusion and multivariable support vector regression was proposed. The principle analysis(PCA)was used to obtain recession indicators(temperature, torque and vibration signal)and quantize the degradation pattern of slewing bearing performance. With the three recession indicators being used as input data, a residual life assessment model for slewing bearing based on multivariable support vector regression was established. Overcoming the shortcomings of simple structure and information scarce, the proposed method was able to obtain the potential information in sample data and to eliminate redundant information contained between characteristic values,and was applied in lab slewing bearing data, results showed that multivariable support vector regression(MSVR)could obtain accurate assessment results.

参考文献/References:

[1] 高学海,黄筱调,王华.双排四点接触球转盘轴承滚道接触压力分布[J].南京工业大学学报(自然科学版),2011(1):80.
[2] MOODIE C A S.An investigation into the condition monitoring of large slow speed slew bearings[D].Wollongong:University of Wollongon,2009.
[3] SIKORSKA J Z,HODKIEWICZ M,MA L.Prognostic modelling options for remaining useful life estimation by industry[J].Mechanical systems and signal processing,2011,25(5):1803.
[4] CAESARENDRA W,KOSASIH P B,TIEU A K,et al.Condition monitoring of naturally damaged slow speed slewing bearing based on ensemble empirical mode decomposition[J].Journal of mechanical science and technology,2013,27(8),2253.
[5] CONG F Y,CHEN J,DONG G M,et al.Short-time matrix series based singular value decomposition for rolling bearing fault diagnosis[J].Mechanical systems and signal processing,2013,34(1/2):218.
[6] 张小丽,陈雪峰,李兵,等.机械重大装备寿命评估综述[J].机械工程学报,2011,47(11):100.
[7] 刘美芳,余建波,尹纪庭.基于贝叶斯推论和自组织映射的轴承性能退化评估方法[J].计算机集成制统,2012,18(10):2237.
[8] 申中杰,陈雪峰,何正嘉,等.基于相对特征和多变量支持向量机的滚动轴承剩余寿命评估[J].机械工程报,2013,49(2):183.
[9] 奚立峰,黄润青,李兴林,等.基于神经网络的球轴承剩余寿命预测[J].机械工程学报,2007,43(10):137.
[10] GEBRAEEL N,LAWLEY M,LIU R,et al.Residual life predictions from vibration-based degradation signals:a neural network approach[J].IEEE transactions on industrial electronics,2004,51(3):694.
[11] CONG F Y,CHEN J,PAN Y N.Kolmogorov-Smirnov test for rolling bearing performance degradation assessment and prognosis[J].Journal of vibration and control,2011,17(9):1337.
[12] 王华伟,吴海桥.基于信息融合的航空发动机剩余寿命评估[J].航空动力报,2012,27(12):2749.
[13] BENKEDJOUH T,MEDJAHER K,ZERHOUNI N,et al.Remaining useful life estimation based on nonlinear feature reduction and support vector regression[J].Engineering applications of artificial intelligence,2013,26(7):1751.
[14] VAPNIK V N.Statistical learning theory [M].New York:Wiley-Interscience,1998.
[15] ABDI H,WILLIAMS L J.Principal component analysis[J].Wiley interdisciplinary reviews:computational statistics,2010,2(4):433.

相似文献/References:

[1]谢冬华,洪荣晶,王华.回转支承自适应负载的运动控制方法[J].南京工业大学学报(自然科学版),2013,35(04):110.[doi:10.3969/j.issn.1671-7627.2013.04.023]
 XIE Donghua,HONG Rongjing,WANG Hua.Slewing bearing motion control based on adaptive load method[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),2013,35(03):110.[doi:10.3969/j.issn.1671-7627.2013.04.023]
[2]黄文龙,曾昭景.双轴向疲劳试件的稳定性分析[J].南京工业大学学报(自然科学版),1987,9(03):90.
 Huang Wenlong Zeng Zhaojing.STABILITY ANALYSIS OF THE BIAXIAL FATIGUE SPECIMEN[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),1987,9(03):90.
[3]杨杰,陈捷,徐新庭,等.基于小波-能量模式的回转支承故障诊断方法研究与应用[J].南京工业大学学报(自然科学版),2015,37(04):134.[doi:10.3969/j.issn.1671-7627.2015.04.024]
 YANG Jie,CHEN Jie,XU Xintin,et al.Slewing bearing analysis on fault diagnosis based on wavelet and energy fault mode and its application[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),2015,37(03):134.[doi:10.3969/j.issn.1671-7627.2015.04.024]
[4]陆超,陈捷,洪荣晶,等.基于粒子群优化支持向量机的回转支承寿命状态识别[J].南京工业大学学报(自然科学版),2016,38(01):56.[doi:10.3969/j.issn.1671-7627.2016.01.010]
 LU Chao,CHEN Jie,HONG Rongjing,et al.Slewing bearing life state recognition based on support vector machine optimized by particle swarm[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),2016,38(03):56.[doi:10.3969/j.issn.1671-7627.2016.01.010]
[5]李媛媛,黄筱调,陈捷,等.基于遗传程序设计的回转支承寿命状态识别[J].南京工业大学学报(自然科学版),2017,39(06):111.[doi:10.3969/j.issn.1671-7627.2017.06.017]
 LI Yuanyuan,HUANG Xiaodiao,CHEN Jie,et al.Life state recognition of slewing bearing based on genetic programming[J].Journal of NANJING TECH UNIVERSITY(NATURAL SCIENCE EDITION),2017,39(03):111.[doi:10.3969/j.issn.1671-7627.2017.06.017]

备注/Memo

备注/Memo:
收稿日期:2014-06-30
基金项目:国家自然科学基金(51105191,51375222); 江苏省自然科学基金(BK2011797)
作者简介:田淑华(1986—),女,山东菏泽人,硕士,主要研究方向为智能算法的剩余寿命评估; 王华(联系人),副教授,E-mail:wanghua@njtech.edu.cn.
引用本文:田淑华,王华,洪荣晶.基于多特征集融合与多变量支持向量回归的回转支承剩余寿命评估[J].南京工业大学学报(自然科学版),2016,38(3):50-57..
更新日期/Last Update: 2016-05-20