归一化小波熵与RVM的滚动轴承运行可靠度预测

摘要
图/表
参考文献(15)
相关文章 (15)

全文: PDF (1643 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对传统可靠度评估和预测方法难以实现对正在服役中的单台机械设备进行可靠度评估和预测的问题。设计了一种基于归一化小波包信息熵与相关向量机的滚动轴承运行可靠度预测方法；该方法主要包括确立运行可靠度指标以及构建相关向量机预测模型，通过试验测取滚动轴承运行过程中的振动信号，利用小波包分解，提取反映滚动轴承运行状态的特征频带能量，基于信息熵理论建立运行可靠度指标；构建相关向量机预测模型，准确预测正在服役中的滚动轴承运行可靠度指标及其变化趋势。试验结果表明，采用归一化小波包信息熵与相关向量机的可靠度预测模型，能有效克服传统基于概率统计数据的平均可靠度计算问题，并且相关向量机的可靠度预测精度更高。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈法法1
	刘莉莉1
	刘芙蓉1
	肖文荣1
	陈保家1
	杨勇2

关键词 ：相关向量机, 归一化信息熵, 运行可靠度, 滚动轴承

Abstract：Aimed at traditional methods are difficult to achieve reliability evaluation and prediction for a single serving machine, an operation reliability evaluation and prediction method based on normalized wavelet information entropy and Relevance Vector Machine was proposed in this paper.This method mainly includes the establishment of an operational reliability index and the construction of a Relevance Vector Machine prediction model.Firstly, the vibration signals of roller bearings in the operation process were acquired in a test experiment.The features which reflected roller bearings running status were extracted from the vibration signals using wavelet packet decomposition.Then, the operation reliability index was established based on information entropy theory.Finally, a Relevance Vector Machine prediction model was constructed to predict the operation reliability index and its changing trend for the actual roller bearing.The experiment results show that the operation reliability evaluation and prediction method by using the normalized wavelet information entropy and Relevance Vector Machine, can effectively overcome the traditional calculation problem with probability statistics, and obtain the better operation reliability result for a single serving machine.

Key words： relevance vector machine normalized information entropy operation reliability roller bearing

收稿日期: 2018-09-13 出版日期: 2020-04-15

引用本文:

陈法法1，刘莉莉1，刘芙蓉1，肖文荣1，陈保家1，杨勇2. 归一化小波熵与RVM的滚动轴承运行可靠度预测[J]. 振动与冲击, 2020, 39(8): 8-14.
CHEN Fafa1，LIU Lili1，LIU Furong1，XIAO Wenrong1，CHEN Baojia1，YANG Yong2. Roller bearing operation reliability prediction based on Relevance Vector Machine and normalized wavelet decomposition information entropy. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(8): 8-14.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2020/V39/I8/8

［1］肖婷, 汤宝平, 秦毅, 等.基于流形学习和最小二乘支持向量机的滚动轴承退化趋势预测［J］.振动与冲击, 2015, 34(9): 149-154. XIAO Ting, TANG Baoping, QIN Yi, et al.Degradation trend prediction of rolling bearing based on manifold learning and least squares support vector machine［J］.Journal of Vibration and Shock, 2015, 34(9): 149-154. ［2］何正嘉，曹宏瑞，訾艳阳，等.机械设备运行可靠性评估的发展与思考［J］.机械工程学报, 2014, 50(2): 171-186. HE Zhengjia, CAO Hongrui, ZI Yanyang, et al.Developments and thoughts on operational reliability assessment of mechanical equipment［J］.Journal of Mechanical Engineering, 2014, 50(2): 171-186. ［3］韩中合, 周沛, 苑一鸣.基于并行相关向量机的多步预测方法研究［J］.电网与清洁能源, 2017, 33(2): 112-116. HAN Zhonghe, ZHOU Pei, YUAN Yiming.Research on multi-step prediction based on parallel relevance vector machine［J］.Power System and Clean Energy, 2017, 33(2): 112-116. ［4］杨茂, 张强.基于最大相关最小冗余相关向量机的风电功率缺失数据补齐研究［J］.太阳能学报, 2017, 38(4): 938-944. YANG Mao, ZHANG Qiang.Polishing missing data for wind power based on MRMR of relevance vector machine［J］.Acta Energiae Solaris Sinica, 2017, 38(4): 938-944. ［5］YANG D, LI H, HU Y G, et al.Vibration condition monitoring system for wind turbine bearings based on noise suppression with multi-point data fusion［J］.Renewable Energy, 2016(92): 104-116. ［6］SUN H L, HE Z J, ZI Y Y, et al.Multiwavelet transform and its applications in mechanical fault diagnosis［J］.Mechanical Systems and Signal Processing, 2014(43): 1-24. ［7］YAN R Q, GAO R X, CHEN X F.Wavelets for fault diagnosis of rotary machines: a review with applications［J］.Signal Processing, 2014(96): 1-15. ［8］LI B, CHEN X F.Wavelet-based numerical analysis: a review and classification［J］.Finite Elements in Analysis and Design, 2014(81): 14-31. ［9］LI N P, LEI Y G, LIU Z Y, et al.A particle filtering-based approach for remaining useful life predication of rolling element bearings［C］//IEEE International Conference on Prognostics and Health Managemen.Washington: IEEE, 2014. ［10］何正嘉，蔡改改，申中杰，等.基于机械诊断信息的设备运行可靠性研究［J］.中国工程科学, 2013, 15(1): 9-14. HE Zhengjia, CAI Gaigai, SHEN Zhongjie, et al.Study of operation reliability based on diagnosis information for mechanical equipment［J］.Chinese Engineering Science, 2013, 15(1): 9-14. ［11］HE S M, XIAO L, WANG Y L, et al.A novel fault diagnosis method based on optimal relevance vector Machine［J］.Neurocomputing, 2017(7): 1-13. ［12］刘磊，杨鹏，刘作军.采用多核相关向量机的人体步态识别［J］.浙江大学学报(工学版)，2017, 51(3): 562-571. LIU Lei, YANG Peng, LIU Zuojun.Locomotion mode recognition using multiple kernel relevance vector machine［J］.Journal of Zhejiang University (Engineering Science), 2017, 51(3): 562-571. ［13］TRAN V T, YANG B S, GU F S, et al.Thermal image enhancement using bi-dimensional empirical mode decomposition in combination with relevance vector machine for rotating machinery fault diagnosis［J］.Mechanical Systems and Signal Processing, 2013(38): 601-614. ［14］LIU Y, ZHANG J H, MA L.A fault diagnosis approach for diesel engines based on self-adaptive WVD, improved FCBF and PECOC-RVM［J］.Neurocomputing, 2016(177): 600-611. ［15］HE F, XU J W, LI M, et al.Product quality modelling and prediction based on wavelet relevance vector machines［J］.Chemometrics and Intelligent Laboratory Systems, 2013 (121): 33-41.