基于ITD复杂度和PSO-SVM的滚动轴承故障诊断

PDF(1849 KB)

振动与冲击 ›› 2016, Vol. 35 ›› Issue (24) : 102-107.

论文

张小龙，张氢，秦仙蓉，孙远韬

作者信息 +

Rolling bearing fault diagnosis based on ITD Lempel-Ziv complexity and PSO-SVM

Zhang Xiao-long, Zhang Qing, Qin Xian-rong, Sun Yuan-tao

Author information +

文章历史 +

摘要

针对滚动轴承故障诊断问题，提出了一种基于固有时间尺度分解（ITD）、Lempel-Ziv复杂度特征和粒子群优化支持向量机（PSO-SVM）的故障诊断新方法。首先对滚动轴承的振动信号使用ITD方法进行分解，得到若干个频率由高到低的固有旋转（PR）分量，由于滚动轴承在不同的故障状态下的PR分量Lempel-Ziv复杂度的分布不同，提取各PR分量的Lempel-Ziv复杂度值作为每个样本的特征向量，使用支持向量机（SVM）对轴承振动信号样本进行故障类型的识别，并用粒子群优化（PSO）方法对支持向量机的参数优化以获得较高的识别准确率。对滚动轴承振动信号的实测结果的分析表明：该方法可以实现对滚动轴承快速、准确地诊断，且不受载荷变化的影响。

Abstract

A method for rolling bearing fault diagnosis based on intrinsic time scale decomposition (ITD), Lempel-Ziv complexity and support vector machine (SVM) based on particle swarm optimization (PSO) algorithm was proposed. The rolling bearing vibration signal was decomposed to several proper rotation (PR) components with ITD method. The distribution of Lempel-Ziv complexity of PR components under different fault conditions was distinguishing. The Lempel-Ziv complexity of PR components was calculated to construct the feature vector for each sample. The feature vector acted as the input of SVM to accomplish the classification of different fault types. And the PSO algorithm was employed to search for the best SVM parameters to achieve higher percentage of classification accuracy. The experimental research results indicate that the proposed method has the advantage of high computation efficiency and good prediction without the influence of variation in load.

导出引用

张小龙，张氢，秦仙蓉，孙远韬. 基于ITD复杂度和PSO-SVM的滚动轴承故障诊断[J]. 振动与冲击, 2016, 35(24): 102-107

Zhang Xiao-long, Zhang Qing, Qin Xian-rong, Sun Yuan-tao . Rolling bearing fault diagnosis based on ITD Lempel-Ziv complexity and PSO-SVM[J]. Journal of Vibration and Shock, 2016, 35(24): 102-107

参考文献

[1] Wu S D, Wu P H, Wu C W, Ding J J, et al. Bearing fault diagnosis based on multiscale permutation entropy and support vector machine [J]. Entropy, 2012; 14(8): 1343-1356.
[2] Feng Z P, L Ming L, Chu F L. Recent advances in time–frequency analysis methods for machinery fault diagnosis: A review with application examples [J]. Mechanical Systems and Signal Processing, 2013, 38(1): 165-205.
[3] 张立国，李盼，李梅梅，等.基于 ITD 模糊熵和 GG 聚类的滚动轴承故障诊断[J]. 仪器仪表学报, 2014, 35(11): 2624-2632.
ZHANG Li-guo, LI Pan, LI Mei-mei, et al. Fault diagnosis of rolling bearing based on ITD fuzzy entropy and GG clustering [J]. Chinese Journal of Scientific Instrument, 2014, 35(11): 2624-2632.
[4] Mark G F, Ivan O. Intrinsic time-scale decomposition: time–frequency–energy analysis and real-time filtering of non-stationary signals [J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2007, 463(2078), 321-342.
[5] Zhao S, Liang L, Xu G, Wang J, et al. Quantitative diagnosis of a spall-like fault of a rolling element bearing by empirical mode decomposition and the approximate entropy method [J], Mechanical Systems and Signal Processing, 2013, 40(1): 154-177.
[6] 苏文胜，王奉涛，朱泓，等. 基于小波包样本熵的滚动轴承故障特征提取[J]. 振动、测试与诊断, 2011, 31(2): 162-166.
SU Wen-sheng, WANG Feng-tao, ZHU Hong. Feature extraction of rolling element bearing fault using wavelet packet sample entropy [J]. Journal of Vibration, Measurement & Diagnosis, 2011, 31(2): 162-166.
[7] 窦东阳，赵英凯. 基于EMD和Lempel-Ziv指标的滚动轴承损伤程度识别研究[J]. 振动与冲击, 2010, 29(3): 5-8.
DOU Dong-yang, ZHAO Ying-kai. Fault severity assessment for rolling element bearings based on EMD and Lempel-Ziv index [J]. Journal of Vibration and Shock, 2010, 29(3): 5-8.
[8] Hong H B, Liang M. Fault severity assessment for rolling element bearings using the Lempel-Ziv complexity and continuous wavelet transform [J]. Journal of Sound and Vibration, 2009, 320(1-2): 452-468.
[9] Zhang X Y, Liang Y T, Zhong J, et al. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM [J]. Measurement, 2015, 69: 164–179.
[10] 李莎，潘宏侠，都衡.基于EEMD 信息熵和PSO- SVM 的自动机故障诊断[J].机械设计与研究, 2014, 30(6):26-29,33.
LI Sha, PAN Hong-xia, Du Heng. Automaton fault diagnosis based on EEMD information entropy and PSO-SVM [J]. Machine Design and Research, 2014, 30(6): 26-29, 33.
[11] 窦丹丹，姜洪开，何毅娜. 基于信息熵和SVM多分类的飞机液压系统故障诊断[J]. 西北工业大学学报, 2012, 30(4): 529-534.
DOU Dan-dan, JIANG Hong-kai, HE Yi-na. Effectively Diagnosing Faults for Aircraft Hydraulic System Based on Information Entropy and Multi-Classification SVM [J]. Journal of Northwestern Polytechnical University, 2012, 30(4): 529-534.
[12] 熊庆，张卫华. 基于MF-DFA与PSO优化LSSVM的滚动轴承故障诊断方法[J]. 振动与冲击, 2015, 34(11):188-193.
XIONG Qing, ZHANG Wei-hua. Rolling bearing fault diagnosis method using MF-DFA and LS-SVM based on PSO [J]. Journal of Vibration and Shock, 2015, 34(11): 188-193.
[13] 段礼祥，张来斌，岳晶晶. 基于ITD和模糊聚类的齿轮箱故障诊断方法[J].中国石油大学学报(自然科学版), 2013, 37(4): 133-139.
DUAN Li-xiang, ZHANG Lai-bin, YUE Jing-jing. Fault diagnosis method of gearbox based on intrinsic time-scale decomposition and fuzzy clustering [J].Journal of China University of Petroleum (Edition of Natural Science), 2013, 37(4): 133-139.
[14] 窦东阳，赵英凯. 集合经验模式分解在旋转机械故障诊断中的应用[J]. 农业工程学报. 2010(02): 190-196.
DOU Dong-yang, ZHAO Ying-kai. Application of ensemble empirical mode decomposition in failure analysis of rotating machinery [J]. Transactions of the CSAE, 2010, 26(2): 190-196.