往复压缩机气阀故障振动信号具有较强的非线性和非平稳性。为了从往复压缩机气阀振动信号中提取故障特征用于故障诊断,本文提出了一种基于变分模态分解(VMD)与多尺度样本熵(MSE)的故障特征提取方法,并与采用麻雀寻优算法(SSA)优化的支持向量机(SVM)相结合,用于往复压缩机气阀故障诊断。通过对往复压缩机气阀信号进行VMD分解,选取合适的内禀模态分量(IMF)进行信号重构,基于MSE熵值分析构成特征向量集,最后将其输入SSA-SVM训练并识别故障类型。实验结果表明,基于VMD-MSE与SSA-SVM的故障诊断模型能有效并准确的识别出往复压缩机气阀故障。
关键词:往复压缩机;变分模态分解;多尺度样本熵;支持向量机;模式识别
Abstract
The fault vibration signal of reciprocating compressor gas valve contains strong nonlinearity and non-stationarity. In order to extract fault features from the vibration signal of the reciprocating compressor valve for fault diagnosis, a fault feature extraction method based on Variational Mode Decomposition(VMD) and Multiscale Sample Entropy(MSE) was proposed, and the model of Support Vector Machine(SVM) optimized by Sparrow Search Algorithm(SSA) was studied for reciprocating compressor valve fault mode recognition. Through the VMD decomposition, the appropriate Intrinsic Mode Function (IMF) component of the vibration signal from the reciprocating compressor valve was selected for signal reconstruction, from which the MSE entropy value was obtained to form a feature vector set. Finally it was input into SSA-SVM for training and mode identification. Experimental study showed that the fault diagnosis model based on VMD-MSE and SSA-VMD can effectively and accurately identified the fault of the reciprocating compressor valve.
Keywords: reciprocating compressor; Variational Modal Decomposition; Multiscale Sample Entropy; Support Vector Machine; mode recognition
关键词
往复压缩机 /
变分模态分解 /
多尺度样本熵 /
支持向量机 /
模式识别
{{custom_keyword}} /
Key words
reciprocating compressor /
Variational Modal Decomposition /
Multiscale Sample Entropy /
Support Vector Machine /
mode recognition
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 赵海洋,徐敏强,王金东. 有理Hermite插值局部均值分解方法及其往复压缩机故障诊断应用[J]. 机械工程学报,2015,51(01):83-89.
Zhao Haiyang, Xu Minqiang, Wang Jindong. Rational Hermite interpolation local mean decomposition method and its application in fault diagnosis of reciprocating compressors[J].Chinese Journal of Mechanical Engineering, 2015, 51(01): 83-89.
[2] 唐友福,刘树林,刘颖慧. 基于非线性复杂测度的往复压缩机故障诊断[J]. 机械工程学报,2012,48(03):102-107.
Tang Youfu, Liu Shulin, Liu Yinghui. Fault diagnosis of reciprocating compressor based on nonlinear complexity measure[J]. Chinese Journal of Mechanical Engineering, 2012, 48(03): 102-107.
[3] Dragomiretskiy K, Zosso D. Variational Mode Decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[4] Huang N E,Shen Z,Long S R. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings of the Royal Society of London Series A, 1998, 454(1971): 903-995.
[5] 何勇,王红,谷穗. 一种基于遗传算法的VMD参数优化轴承故障诊断新方法[J]. 振动与冲击,2021,40(06):184-189.
He Yong, Wang Hong, Gu Sui. A new method of bearing fault diagnosis based on genetic algorithm for VMD parameter optimization[J]. Journal of Vibration and Shock, 2021, 40(06): 184-189.
[6] 王新刚,王超,韩凯忠. 基于优化VMD和MCKD的滚动轴承早期故障诊断方法[J]. 东北大学学报(自然科学版) ,2021,42(03):373-380+388.
Wang Xingang, Wang Chao, Han Kaizhong. Early fault diagnosis method of rolling bearing based on optimized VMD and MCKD[J]. Journal of Northeastern University (Natural Science Edition), 2021, 42(03): 373-380+388.
[7] Costa M,Goldberger A L. Multiscale entropy analysis of biological signals.[J]. Physical review. E, Statistical, nonlinear, and soft matter physics, 2005, 71(2 Pt 1).
[8] 苟先太,李昌喜,金炜东. VMD多尺度熵用于高速列车横向减振器故障诊断[J]. 振动.测试与诊断,2019,39(02):292-297+442.
Gou Xiantai, Li Changxi, Jin Weidong. VMD multi-scale entropy used for fault diagnosis of transverse shock absorbers of high-speed trains[J]. Vibration. Test and Diagnosis, 2019, 39(02): 292-297+442.
[9] Tong S,Koller D. Support vector machine active learning with applications to text classification[J]. Journal of Machine Learning Research, 2002, 2(1) :999-1006.
[10] 丁世飞,齐丙娟,谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报,2011,40(01):2-10.
Ding Shifei, Qi Bingjuan, Tan Hongyan. Summary of Support Vector Machine Theory and Algorithm Research[J]. Journal of University of Electronic Science and Technology of China, 2011, 40(01): 2-10.
[11] Xue J,Shen B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.
[12] 魏文军,刘新发. 基于EEMD多尺度样本熵的S700K转辙机故障诊断[J]. 中南大学学报(自然科学版),2019,50(11):2763-2772.
Wei Wenjun, Liu Xinfa. Fault diagnosis of S700K point machine based on EEMD multi-scale sample entropy[J]. Journal of Central South University (Natural Science Edition), 2019, 50(11): 2763-2772.
[13] Zhou J G,Chen D F. Carbon Price Forecasting Based on Improved CEEMDAN and Extreme Learning Machine Optimized by Sparrow Search Algorithm[J]. Sustainability, 2021, 13(9): 4896.
[14] GB/T 7777-2003.容积式压缩机机械振动测量与评价[s]. 北京:中国标准出版社,2004
GB/T 7777-2003. Measurement and evaluation of mechanical vibration of positive displacement compressor[s]. Beijing: China Standard Press, 2004
[15] 郑小霞,周国旺,任浩翰. 基于变分模态分解和排列熵的滚动轴承故障诊断[J]. 振动与冲击,2017,36(22):22-28.
Zheng Xiaoxia, Zhou Guowang, Ren Haohan. Fault diagnosis of rolling bearing based on variational mode decomposition and permutation entropy[J]. Journal of Vibration and Shock, 2017, 36(22): 22-28.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}