基于频谱相关性分析的齿轮早期磨损诊断

doi:10.12068/j.issn.1005-3026.2023.01.003

东北大学学报（自然科学版） ›› 2023, Vol. 44 ›› Issue (1): 18-25.DOI: 10.12068/j.issn.1005-3026.2023.01.003

基于频谱相关性分析的齿轮早期磨损诊断

王宏民^1,2，禅亮^1,2

(1.哈尔滨理工大学自动化学院，黑龙江哈尔滨150080； 2.黑龙江省复杂智能系统与集成重点实验室，黑龙江哈尔滨150080)

发布日期:2023-01-30
通讯作者: 王宏民
作者简介:王宏民(1962-)，男，黑龙江哈尔滨人，哈尔滨理工大学教授.
基金资助:
黑龙江省自然科学基金资助项目(F201310).

Early Wear Diagnosis of Gears Based on Spectrum Correlation Analysis

WANG Hong-min^1,2， CHAN Liang^1,2

1. School of Automation， Harbin University of Science and Technology， Harbin 150080， China; 2. Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration， Harbin 150080， China.

Published:2023-01-30
Contact: WANG Hong-min
About author:-
Supported by:
-

摘要/Abstract

摘要： 基于振动分析的齿轮故障检测已被证明在故障识别中是有效的，但对表征早期磨损的振动信号的提取和识别仍没有得到很好的解决.本文提出一种基于频谱相关性分析的变分模态分解(VMD)和核支持向量机(SVM)相结合的齿轮早期磨损诊断方法，对能够揭示早期磨损状态的微弱齿轮振动信号采用近似完全重构的准则来初始化模式数，并采用信号功率谱密度最大值对应的频率初始化VMD方法的中心频率，用以有效提取齿轮磨损信息，进而结合核支持向量机进行齿轮的早期磨损诊断.实验结果表明，所提方法可有效克服背景噪声大无法预设模式数的问题，对噪声具有更好的鲁棒性，诊断准确率达到94.4%，可为齿轮早期磨损检测提供解决方法.

关键词: 齿轮振动信号的提取；早期磨损诊断；频谱相关性分析；变分模态分解；支持向量机

Abstract: Gear fault detection based on vibration analysis has been proven to be effective in fault identification. However， the extraction and identification of vibration signals characterizing early wear have not been solved well. This paper proposes a method for early wear diagnosis of gears， combining variational mode decomposition (VMD) based on spectrum correlation analysis with kernel support vector machine (SVM). For weak gear vibration signals that can characterize early wear， the modal numbers are initialized by an approximate complete reconstruction criterion. Meanwhile， the frequency corresponding to the maximum value of the signal power spectral density is used to initialize the center frequency of the VMD method. It is used to effectively extract gear wear information from gear vibration signals and then be combined with kernel support vector machines for early wear diagnosis of gears. The experimental results show that the proposed method can effectively overcome the problem that the modal numbers cannot be preset with large background noise， be with better robustness to noisy situations， and achieve a diagnostic accuracy of 94.4%， which provides a solution for early wear detection of gears.

Key words: extraction of gear vibration signals； early wear diagnosis； spectrum correlation analysis； variational mode decomposition (VMD); support vector machines (SVM)

中图分类号:

TP273
TH132

王宏民，禅亮. 基于频谱相关性分析的齿轮早期磨损诊断[J]. 东北大学学报（自然科学版）, 2023, 44(1): 18-25.

WANG Hong-min， CHAN Liang. Early Wear Diagnosis of Gears Based on Spectrum Correlation Analysis[J]. Journal of Northeastern University(Natural Science), 2023, 44(1): 18-25.

参考文献

[1]Liu L H， Chen L Q， Wang Z L， et al.Early fault detection of planetary gearbox based on acoustic emission and improved variational mode decomposition［J］.IEEE Sensors Journal，2020，21(2):1735-1745.
[2]Liang P F，Deng C，Wu J.Intelligent fault diagnosis of rotating machinery via wavelet transform，generative adversarial nets and convolutional neural network［J］.Measurement，2020，159: 107768.
[3]Yan R Q，Gao R X，Chen X F.Wavelets for fault diagnosis rotary machines: a review with applications［J］.Signal Processing，2013，96: 1-15.
[4]Huang N E.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis［J］.Proceedings of the Royal Society of London，1998，454:903-995.
[5]Wu Z H，Huang N E.Ensemble empirical mode decomposition: a noise-assisted data analysis method［J］.Advances in Adaptive Data Analysis，2009，1(1): 1-41.
[6]Torres M E，Colominas M A，Schlotthauer G，et al.A complete ensemble empirical mode decomposition with adaptive noise［C］//IEEE International Conference on Acoustics，Speech and Signal Processing(ICASSP).Prague: IEEE，2011: 4144-4147.
[7]Lu Y F，Xie R，Liang S.CEEMD-assisted kernel support vector machines for bearing diagnosis［J］.The International Journal of Advanced Manufacturing Technology，2020，106(7):3063-3070.
[8]Dutta S，Singh M，Kumar A.Classification of non-motor cognitive task on EEG based brain-computer interface using phase space features in multivariate empirical mode decomposition domain［J］.Biomedical Signal Processing and Control，2017，39: 378-389.
[9]Dragomiretskiy K，Zosso D.Variational mode decomposition［J］.IEEE Transactions on Signal Processing，2014，62(3):531-544.
[10]Li H D，Xu Y，An D，et al.Application of a flat variational modal decomposition algorithm in fault diagnosis of rolling bearings［J］.Journal of Low Frequency Noise Vibration and Active Control，2020，39(2):335-351.
[11]Yang T G，Yu X G，Li G C，et al.An early fault diagnosis method based on the optimization of a variational modal decomposition and convolutional neural network for aeronautical hydraulic pipe clamps［J］.Measurement Science and Technology，2020，31(5):055007.
[12]Gai J B，Shen J X，Hu Y F，et al.An integrated method based on hybrid grey wolf optimizer improved variational mode decomposition and deep neural network for fault diagnosis of rolling bearing［J］.Measurement，2020，162: 107901.
[13]朱永利，贾亚飞，王永旺，等.基于改进变分模态分解和Hilbert变换的变压器局部放电信号特征提取及分类［J］.电工技术学报，2017，32(9):221-235.(Zhu Yong-li，Jia Ya-fei，Wang Yong-wang，et al.Feature extraction and classification on partial discharge signal of power transformers based on improved variational mode decomposition and Hilbert transform［J］.Transactions of China Electrotechnical Society，2017，32(9):221-235.)
[14]Ma L，Liu X G.A novel APSO-aided weighted LSSVM method for nonlinear hammerstein system identification［J］.Journal of the Franklin Institute，2017，354(4):1892-1906.
[15]Han T T，Zhao Q C.Financial crisis predictions based on biorthogonal wavelet hybrid kernel support vector machine［C］//2015 11th International Conference on National Computation.Zhangjiajie: IEEE，2015:719-724.
[16]Gao T Y，Yang J L，Jiang S D，et al.A novel incipient fault diagnosis method for analog circuits based on GMKL-SVM and wavelet fusion features［J］.IEEE Transactions on Instrumentation and Measurement，2020，70: 3502315.
[17]Yao L，Fang Z P，Xiao Y Q，et al.An intelligent fault diagnosis for lithium battery systems based on grid search support vector machine［J］.Energy，2021，214: 118866.
[18]Wu J，Guo P F，Cheng Y F，et al.Ensemble generalized multiclass support-vector-machine-based health evaluation of complex degradation systems［J］.IEEE/ASME Transactions on Mechatronics，2020，25(5):2230-2240.

基于频谱相关性分析的齿轮早期磨损诊断

Early Wear Diagnosis of Gears Based on Spectrum Correlation Analysis

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	叶宁，宋锦春，高曦莹，于忠亮. 基于输出反馈的电液作动器自适应指令滤波控制[J]. 东北大学学报:自然科学版, 2020, 41(9): 1310-1315.
[2]	史家顺，董金龙，刘聪，于天彪. 随五轴加工轨迹变抛光力的控制策略与方法[J]. 东北大学学报:自然科学版, 2020, 41(1): 89-94.
[3]	刘云山，贾磊，闻邦椿. 反向回转双机驱动振动系统的倍频控制同步[J]. 东北大学学报:自然科学版, 2019, 40(12): 1726-1731.
[4]	关守平，邹立夫，张菁菁. 区间多目标粒子群优化算法及其应用[J]. 东北大学学报:自然科学版, 2019, 40(11): 1521-1526.
[5]	王占山，王继东，刘秀翀，孙鉴. 二阶系统的复特征根对其鲁棒H_∞控制性能的影响[J]. 东北大学学报:自然科学版, 2019, 40(9): 1217-1222.
[6]	杨英华，石翔，李鸿儒. 基于数据特征的加热炉钢温预报模型[J]. 东北大学学报:自然科学版, 2019, 40(3): 305-309.
[7]	杨冬梅，姚齐. 一类切换广义时滞系统的鲁棒指数镇定[J]. 东北大学学报:自然科学版, 2018, 39(7): 922-926.
[8]	李海燕，井元伟. 基于ＳＯＲＡ的多学科协同优化可靠性优化方法[J]. 东北大学学报:自然科学版, 2018, 39(1): 1-5.
[9]	白晶，毛志忠，浦铁成. 多变量Hammerstein-Wiener模型的参数辨识[J]. 东北大学学报:自然科学版, 2018, 39(1): 6-10.
[10]	孟范伟，徐博，吕晓永，刘胤圻. 神经网络预测控制在SCR烟气脱硝系统中应用[J]. 东北大学学报:自然科学版, 2017, 38(6): 778-782.
[11]	李明杰，周平. 机械制浆过程磨机负荷内模PI控制[J]. 东北大学学报:自然科学版, 2017, 38(6): 783-788.
[12]	赵海，雷凯茹，司帅宗，许子文. Platoon模式下车载自组织网络性能分析与研究[J]. 东北大学学报:自然科学版, 2017, 38(5): 634-638.
[13]	连莲，高宪文，齐文海. 一般不确定转移速率下Markov切换系统的弹性控制器[J]. 东北大学学报:自然科学版, 2017, 38(4): 457-461.
[14]	齐文海，李新，高宪文. 执行器饱和的分段齐次Markov跳变系统的镇定[J]. 东北大学学报:自然科学版, 2017, 38(4): 462-466.
[15]	张廷丰，毛志忠，袁平，张弼. 基于多变量阶跃响应的风洞系统辨识[J]. 东北大学学报:自然科学版, 2016, 37(11): 1521-1525.