[1]杨诚,贾民平.基于Volterra-PARAFAC模型的滚动轴承故障诊断方法[J].东南大学学报(自然科学版),2019,49(4):742-748.[doi:10.3969/j.issn.1001-0505.2019.04.018]
 Yang Cheng,Jia Minping.Fault diagnosis method for rolling bearing based on Volterra-PARAFAC model[J].Journal of Southeast University (Natural Science Edition),2019,49(4):742-748.[doi:10.3969/j.issn.1001-0505.2019.04.018]
点击复制

基于Volterra-PARAFAC模型的滚动轴承故障诊断方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
49
期数:
2019年第4期
页码:
742-748
栏目:
机械工程
出版日期:
2019-07-20

文章信息/Info

Title:
Fault diagnosis method for rolling bearing based on Volterra-PARAFAC model
作者:
杨诚贾民平
东南大学机械工程学院, 南京 211189
Author(s):
Yang Cheng Jia Minping
School of Mechanical Engineering, Southeast University, Nanjing 211189, China
关键词:
滚动轴承 Volterra-PARAFAC预测模型 最小均方自适应算法 故障诊断
Keywords:
rolling bearing Volterra-PARAFAC(parallel factor analysis)prediction model least mean square method fault diagnosis
分类号:
TH133.33
DOI:
10.3969/j.issn.1001-0505.2019.04.018
摘要:
为解决Volterra模型用于复杂机械系统非线性特征提取时存在估计参数过多的问题,提出了一种新的Volterra-PARAFAC预测模型.在非线性特征提取中,所提出的预测模型的估计参数数目大大低于传统的Volterra预测模型参数,有效地避免了维数灾难问题.在Volterra-PARAFAC预测模型辨识过程中,利用最小均方自适应(LMS)算法估计Volterra-PARAFAC预测模型的核参数向量,从而精确描述非线性系统.利用该方法对滚动轴承多种故障状态下的振动信号进行分析,得到的特征向量具有非常好的分类性能.试验结果表明,该方法能有效提取复杂机械系统的非线性特征,并能准确对不同状态下的滚动轴承故障信号进行分类.相比于传统的Volterra模型故障诊断方法,所提方法能够更准确地对滚动轴承故障进行诊断.
Abstract:
Estimating a huge number of parameters is the main drawback of Volterra prediction model applied in the nonlinear feature extraction of complex mechanical systems. To overcome this drawback, a new Volterra-PARAFAC(parallel factor analysis)prediction model is presented. In the nonlinear feature extraction, the number of estimated parameters of the proposed prediction model is much lower than that of the traditional Volterra prediction model, and the dimension curse can be avoided effectively. In the identification process of Volterra-PARAFAC prediction model, the parameter vector of Volterra-PARAFAC prediction model is estimated by the least mean square method so as to accurately describe nonlinear systems. The vibration signals of several rolling bearing faults are analyzed by the proposed method, and the obtained parameter vectors have excellent classification performance. Experimental results show that this method can effectively extract the nonlinear characteristics of complex mechanical systems, and the failure recognition of rolling bearing in different working states can be realized accurately. Compared with traditional fault diagnosis methods based on the Volterra model, the proposed method can improve the precision of rolling bearing fault diagnosis.

参考文献/References:

[1] Saray B N. An efficient algorithm for solving Volterra integro-differential equations based on Alpert’s multi-wavelets Galerkin method[J].Journal of Computational and Applied Mathematics, 2019, 348: 453-465. DOI:10.1016/j.cam.2018.09.016.
[2] Huang H L, Mao H Y, Mao H L, et al. Study of cumulative fatigue damage detection for used parts with nonlinear output frequency response functions based on NARMAX modelling[J].Journal of Sound and Vibration, 2017, 411: 75-87. DOI:10.1016/j.jsv.2017.08.023.
[3] 彭志科, 程长明. Volterra级数理论研究进展与展望[J]. 科学通报, 2015, 60(20): 1874-1888.
  Peng Z K, Cheng C M. Volterra series theory: A state-of-the-art review[J]. Chinese Science Bulletin, 2015, 60(20): 1874-1888.(in Chinese)
[4] Xia X, Zhou J Z, Xiao J, et al. A novel identification method of Volterra series in rotor-bearing system for fault diagnosis[J].Mechanical Systems and Signal Processing, 2016, 66/67: 557-567. DOI:10.1016/j.ymssp.2015.05.006.
[5] 王海涛, 王琨, 史丽晨. Volterra理论在滚动轴承内圈故障程度特征定量提取的研究[J]. 振动与冲击, 2018, 37(9): 173-179. DOI:10.13465/j.cnki.jvs.2018.09.027.
Wang H T, Wang K, Shi L C. Quantitative extraction of rolling bearings’ inner race fault level based on Volterra theory[J]. Journal of Vibration and Shock, 2018, 37(9): 173-179. DOI:10.13465/j.cnki.jvs.2018.09.027. (in Chinese)
[6] 张云强, 张培林, 王怀光, 等. 结合VMD和Volterra预测模型的轴承振动信号特征提取[J]. 振动与冲击, 2018, 37(3): 129-135, 152. DOI:10.13465/j.cnki.jvs.2018.03.021.
Zhang Y Q, Zhang P L, Wang H G, et al. Feature extraction method for rolling bearing vibration signals based on VMD and Volterra prediction model[J]. Journal of Vibration and Shock, 2018, 37(3): 129-135, 152. DOI:10.13465/j.cnki.jvs.2018.03.021. (in Chinese)
[7] 李志农, 蒋静, 冯辅周, 等. 基于量子粒子群优化Volterra时域核辨识的隐Markov模型识别方法[J]. 仪器仪表学报, 2011, 32(12): 2693-2698. DOI:10.19650/j.cnki.cjsi.2011.12.009.
Li Z N, Jiang J, Feng F Z, et al. Hidden Markov model recognition method based on Volterra kernel identified with particle swarm optimization[J]. Chinese Journal of Scientific Instrument, 2011, 32(12): 2693-2698. DOI:10.19650/j.cnki.cjsi.2011.12.009. (in Chinese)
[8] Khouaja A, Favier G. Identification of PARAFAC-Volterra cubic models using an alternating recursive least squares algorithm[C]//12th European Signal Processing Conference. Vienna, Austria, 2004: 1903-1906.
[9] Favier G, Kibangou A Y, Bouilloc T. Nonlinear system modeling and identification using Volterra-PARAFAC models[J].International Journal of Adaptive Control and Signal Processing, 2012, 26(1): 30-53. DOI:10.1002/acs.1272.
[10] 张玉梅, 胡小俊, 吴晓军, 等. 语音信号序列的Volterra预测模型[J]. 物理学报, 2015, 64(20): 200507. DOI:10.7498/aps.64.200507.
Zhang Y M, Hu X J, Wu X J, et al. Volterra prediction model for speech signal series[J]. Acta Physica Sinica, 2015, 64(20): 200507. DOI:10.7498/aps.64.200507. (in Chinese)
[11] Comon P, Golub G, Lim L H, et al. Symmetric tensors and symmetric tensor rank[J].SIAM Journal on Matrix Analysis and Applications, 2008, 30(3): 1254-1279. DOI:10.1137/060661569.
[12] 齐波, 张鹏, 荣智海, 等. 基于相空间重构的变压器油色谱数据最优长度选择方法[J]. 中国电机工程学报, 2018, 38(8): 2504-2512, 2560. DOI:10.13334/j.0258-8013.pcsee.170158.
Qi B, Zhang P, Rong Z H, et al. Optimal length selection method of DGA data based on phase space reconstruction[J]. Proceedings of the CSEE, 2018, 38(8): 2504-2512, 2560. DOI:10.13334/j.0258-8013.pcsee.170158. (in Chinese)
[13] Takens F. Detecting strange attractors in turbulence[M]//Lecture Notes in Mathematics. Berlin,Germany: Springer, 1981: 366-381. DOI:10.1007/bfb0091924.

相似文献/References:

[1]张菀,贾民平,朱林.一种自适应Morlet小波滤波方法及其在滚动轴承早期故障特征提取中的应用[J].东南大学学报(自然科学版),2016,46(3):457.[doi:10.3969/j.issn.1001-0505.2016.03.001]
 Zhang Wan,Jia Minping,Zhu Lin.An adaptive Morlet wavelet filter method and its application in detecting early fault feature of ball bearings[J].Journal of Southeast University (Natural Science Edition),2016,46(4):457.[doi:10.3969/j.issn.1001-0505.2016.03.001]

备注/Memo

备注/Memo:
收稿日期: 2019-01-04.
作者简介: 杨诚(1993—),男,博士生;贾民平(联系人),男,博士,教授,博士生导师,mpjia@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(51675098).
引用本文: 杨诚,贾民平.基于Volterra-PARAFAC模型的滚动轴承故障诊断方法[J].东南大学学报(自然科学版),2019,49(4):742-748. DOI:10.3969/j.issn.1001-0505.2019.04.018.
更新日期/Last Update: 2019-07-20