基于混沌理论的滚动轴承振动信号融合模型预测

孟凡念; 杜文辽; 李浩

doi:10.13224/j.cnki.jasp.2020.08.011

基于混沌理论的滚动轴承振动信号融合模型预测

doi: 10.13224/j.cnki.jasp.2020.08.011

基金项目: 国家自然科学基金（U1804141）；河南省高校科技创新人才支持计划项目（17HASTIT028）；河南省机械装备智能制造重点实验室开放基金(IM201910)；河南省科技攻关项目(202102210086)

计量
- 文章访问数: 581
- HTML浏览量: 172
- PDF量: 434
- 被引次数: 0
出版历程
- 收稿日期: 2020-01-16
- 刊出日期: 2020-08-28

Fusion model prediction of rolling bearing vibration signal based on chaos theory,

Henan Key Laboratory of Intelligent Manufacturing of Mechanical Equipment,College of Mechanical and Electrical Engineering，,Zhengzhou University of Light Industry,Zhengzhou 450002,China

摘要

摘要: 提出融合算法模型,在混沌理论的基础上对滚动轴承振动信号进行预测。基于相图法、最大Lyapunov指数法和关联维数法对滚动轴承振动信号进行混沌判别,证明其混沌性。以预测值和真值间差值范数最小为目标导向优化出Kriging模型、最小二乘支持向量机(LSSVM)模型和极端学习机(ELM)模型的权重,加权法构建融合算法模型。相空间重构法构建滚动轴承振动信号预测的训练样本,并对融合模型、Kriging模型、LSSVM模型和ELM模型进行训练,训练好的模型用于振动轴承振动信号混沌预测。以案例1和案例2共两个实验的滚动轴承振动信号为对象进行验证,两案例的最大Lyapunov指数大于0,从而判断这两个案例的轴承振动信号呈现混沌特性。另外,从方均误差、方均根误差和平均绝对误差指标来评价,融合算法模型的指标值均小于单一模型算法,融合算法模型的预测精度优于单一模型算法。
- 滚动轴承 /
- 融合模型 /
- 混沌预测 /
- Kriging模型 /
- LSSVM模型 /
- ELM模型
Abstract: The fusion algorithm model was used to predict the vibration signal of rolling bearing on the basis of chaos theory. Based on the phase diagram method, the maximum Lyapunov exponent method and the correlation dimension method, the chaos characteristic of rolling bearing vibration signal was proved. The weights of Kriging model, least squares support vector machine（LSSVM）model and extreme learning machine（ELM）model were optimized to minimize the norm of the difference between the predicted value and the true value, and the fusion algorithm model was constructed by weighting method. The phase space reconstruction method was used to construct the training samples of the rolling bearing vibration signal prediction, and the fusion model, Kriging model, LSSVM model and ELM model were trained. The trained model was used to predict the vibration signal of rolling bearing. For case 1 and case 2, the rolling bearing vibration signals of two experiments were used to verify the results. The maximum Lyapunov exponent for two cases was greater than 0, from which chaotic characteristic on bearing vibration signal can be determined. Besides, the index value for fusion model was less than the single model from the evaluation index of mean squared error, root mean squared error and mean absolute error, so the prediction accuracy of the fusion algorithm model was better than that of the single algorithm model.
- rolling bearing /
- fusion model /
- chaotic prediction /
- Kriging model /
- ,LSSVM model /
- ELM model

HTML

参考文献(17)

[1]	夏新涛,徐永智.滚动轴承性能变异的近代统计学分析［M］.北京:科学出版社,2016.
[2]	PACKARD N H,CRUTCHFIELD J P,FARMER J D,et al.Geometry from a time series［J］.Physical Review Letters,1980,45(9):712-716.
[3]	MASSIMO C,BARBARA C.The role of the embedding dimension and time delay in time series forecasting［J］.IFAC Proceedings,2009,42(7):316-320.
[4]	邱华旭,黄张裕,朱华.改进的饱和关联维数法在时间序列研究中的应用［J］.勘察科学技术,2014(1):53-54. QIU Huaxu,HUANG Zhangyu,ZHU Hua.Application of improved G-P method in time series study［J］.Reconnaissance Science and Technology,2014(1):53-54.(in Chinese)
[5]	NUR H A,MOHD S M N.Predicting time series data at floodplain area using chaos approach［J］.Sains Malaysiana,2015,44(3):463-471.
[6]	SMALL M,TSE C K.Optimal embedding parameters:a modeling paradigm［J］.Physica D:Nonlinear Phenomena,2004,194(3/4):283-296.
[7]	MAUS A,SPROTT J C.Neural network method for determining embedding dimension of a time series［J］.Communications in Nonlinear Science and Numerical Simulation,2011,16(8):3294-3302.
[8]	SU Xin,WANG Yi,DUAN Shengsen,et al.Detecting chaos from agricultural product price time series［J］.Entropy,2014,16(12):6415-6433.
[9]	SUN Yun,WANG Ying,MENG Xiangfei,et al.Methodology of estimating the embedding dimension in chaos time series based on the prediction performance of K-CV-GRNN［C］∥Proceedings of International Conference on Information System and Computer Aided Educaton.New York:IEEE,2018:202-205.
[10]	CAO L Y.Practical method for determining the minimum embedding dimension of a scalar time series［J］.Physica D:Nonlinear Phenomena,1997,110(1):43-50.
[11]	FRASER A M,SWINNEY H L.Independent coordinates for strange attractors from mutual information［J］.Physical Review:A,1986,33(2):1134-1140.
[12]	KIM H S,EYKHOLT R,SALAS J D.Nonlinear dynamics,delay times,and embedding windows［J］.Physica D:Nonlinear Phenomena,1999,127(1):48-60.
[13]	YE Liang,XIA Xintao,CHANG Zhen.Dynamic prediction of the performance reliability of high-speed railway bearings［J］.Journal of the Brazilian Society of Mechanical Sciences and Engineering,2019,41(11):1-12.
[14]	张淑清,贺朋,左一格,等.混沌奇异谱特性研究及在滚动轴承故障诊断中的应用［J］.中国机械工程,2018,29(12):1398-1404. ZHANG Shuqing,HE Peng,ZUO Yige,et al.Study on characteristics of chaotic singular spectrum and applications in rolling bearing fault diagnosis［J］.China Mechanical Engineering,2018,29(12):1398-1404.(in Chinese)
[15]	李兆飞,任小洪,黄臣程.滚动轴承振动的非线性超混沌特性研究［J］.轴承,2016(7):54-60. LI Zhaofei,REN Xiaohong,HUANG Chencheng.Study on nonlinear hyper chaotic characteristics for vibration of rolling bearings［J］.Bearing,2016(7):54-60.(in Chinese)
[16]	徐永智,夏新涛,南翔.基于混沌理论滚动轴承振动稳健化试验数据的动态分析［J］.航空动力学报,2015,30(8):1959-1965. XU Yongzhi,XIA Xintao,NAN Xiang.Dynamic analysis of the robust test data on rolling bearing vibration based on chaos theory［J］.Journal of Aerospace Power,2015,30(8):1959-1965.(in Chinese).
[17]	潘海洋,杨宇,郑近德,等.基于径向基函数的变量预测模型模式识别方法［J］.航空动力学报,2017,32(2):500-506. PAN Haiyang,YANG Yu,ZHENG Jinde,et al.Variable predictive model based RBF class discriminate method［J］.Journal of Aerospace Power,2017,32(2):500-506.(in Chinese)