基于MMSE和ABCSVM的液压泵故障模式识别

李洪儒1,王余奎1,2,马济,1,叶鹏1

振动与冲击 ›› 2016, Vol. 35 ›› Issue (9) : 152-158.

PDF(2472 KB)
PDF(2472 KB)
振动与冲击 ›› 2016, Vol. 35 ›› Issue (9) : 152-158.
论文

基于MMSE和ABCSVM的液压泵故障模式识别

  • 李洪儒1,王余奎1,2,马济,1,叶鹏1
作者信息 +

Fault pattern recognition of Hydraulic Pump based on MMSE and ABCSVM

  • LI Hongru1, MA Jiqiao1,2, WANG Yuku,1,YE Peng1
Author information +
文章历史 +

摘要

为了更好地实现液压泵的故障模式识别,对液压泵故障特征提取方法和模式识别方法进行研究。针对多尺度熵算法存在的
在尺度因子较大时时间序列较短而导致各尺度样本熵表征液压泵故障状态性能较差的问题,提出了改进的多尺度熵算法,通过对液压泵实测信号分析验证了所提出的改进多尺度熵的良好性能。针对液压泵故障状态与故障特征之间的非线性关系,采用支持向量机算法建立液压泵的故障模式识别模型,并提出采用人工蜂群优化算法对支持向量机模型参数进行优化。基于改进多尺度熵和蜂群优化参数的支持向量机实现液压泵故障模式识别,通过对比分析验证了所提出的液压泵故障模式识别方法的良好性能。

Abstract

In order to realize the purpose of fault pattern recognition of hydraulic pump, the methods of fault feature extraction and pattern recognition are researched. Aiming at the bad performance of large scale sample entropy to reflect the state of pump as the scale of Multi-scale Sample Entropy (MSE) is larger and then the length of time series is shorter, the modified multi-scale entropy (MMSE) is proposed in this paper. The results obtained by adopting MMSE to practical signals of pump testified the favorable performance of it. Considering the nonlinear relationship between pump fault pattern and fault features, the Support Vector Machine (SVM) is used to realize the fault pattern recognition of pump and the Artificial Bee Colony (ABC) algorithm is proposed to optimize the parameters of SVM model. The fault pattern recognition of pump is realized based on the MMSE and ABCSVM, the favorable performance of proposed method is demonstrated with comparison and analysis.
 

关键词

液压泵 / 模式识别 / 改进多尺度熵 / 人工蜂群算法 / SVM

引用本文

导出引用
李洪儒1,王余奎1,2,马济,1,叶鹏1. 基于MMSE和ABCSVM的液压泵故障模式识别[J]. 振动与冲击, 2016, 35(9): 152-158
LI Hongru1, MA Jiqiao1,2, WANG Yuku,1,YE Peng1. Fault pattern recognition of Hydraulic Pump based on MMSE and ABCSVM[J]. Journal of Vibration and Shock, 2016, 35(9): 152-158

参考文献

[1] Shaojiang Dong, Baoping Tang, Renxing Chen. Bearing running state recongnition based on non-extensive wavelet feature scale entropy and support vetor machine[J].Measurement,2013, 19(46):4186-4199.
[2] 王冰,李洪儒,许葆华.基于数学形态学分段分形维数的电机滚动轴承故障模式识别[J].振动与冲击, 2013,32(19):28-31.
WANG Bing,LI Hong-ru,XU Bao-hua.Fault pattern recognition for electromotor rolling bearing based on mathematical morphology sectionalized fractal dimension[J]. Journal of Vibration and Shock, 2013,32(19):28-31.
[3] 白蕾,梁平.基于小波包滤波的汽轮机转子振动故障的Kolmogorov熵诊断[J].振动与冲击,2008,27(5), 148-152.
BAI Lei, LIANG Ping. Kolmogorov entropy diagnosis for vibration faults of turbine rotor based on wavelet packet filtering[J]. Journal of Vibration and Shock, 2008,27(5):148-152.
[4] RichmanJ . S., Moorman J. R.. Physiological time-series analysis using approximate and sample entropy [J]. American Journal of Physiology Heart Circulatory Physiology, 2000,43(278):2039-2049.
[5] E. Cabal-Yepez, R. J. Romero-Troncoso, A. Garcia-Rerez, et al. Single-parameter fault identification through information entropy analysis at the startup transient current in induction motors[J]. Electric Power Systems Research, 2012,32(89):64-69.
[6] 李娜,方彦军.利用关联维数分析机械系统故障信号[J].振动与冲击,2007,26(4):136-139.
LI Na, FANG Yan jun. Fault signal analysis of mechanical system based on correlation dimension [J]. Journal of Vibration and Shock, 2007,26(4):136-139.
[7] Jennifer M., Yentes, Nathaniel Hunt, Kendra K.Schmid, et al. The appropriate use of approximate entropy and sample entropy with short data sets [J]. Annals of Biomedical Engineering, 2013,41(2):349-365.
[8] 赵志宏,杨绍普.一种基于样本熵的轴承故障诊断方法[J].振动与冲击,2012,31(6):136-140.
ZHAO Zhi hong,YANG Shao pu. Sample entropy-based roller bearing fault diagnosis method [J]. Journal of Vibration and Shock,2012,32 (6):136-140.
[9] 张毅,罗明伟,罗元.脑电信号的小波变换和样本熵特征提取[J].智能系统学报,2012,7(4):1-6.
ZHANG Yi, LUO Mingwei, LUO Yuan. EEG feature extraction method based on wavelet transform and sample entropy[J]. CAAI Transactions on Intelligent Systems, 2012,7(4):1-6.
[10] Costa M, Goldberger A L, Peng C K. Multiscale entropy analysis of biological signals[J]. Physical Review E, 2005,26(71):1-18.
[11] Shahina Begum, Shaibal Barua, Reno Filla, et al. Classification of physiological signals for wheel loader operators using Multi-scale Entropy analysis and case-based reasoning[J]. Expert Systems with Applications, 2014(41):295-305.
[12] Long Zhang, Guoliang Xiong, Hesheng Liu, et al. Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference [J]. Expert Systems with Applications, 2010(37):6077-6085.
[13] Keheng Zhu, Xigeng Song, Dongxin Xue. A roller bearing fault diagnosis method based on hierarchical entropy and support vector machine with particle swarm optimization algorithm[J]. Measurement, 2014(47):669-675.
[14] Ning Li, Rui Zhou, Qinghua Hu, et al. Mechanical fault diagnosis based on redundant second generation wavelet packet transform, neighborhood rough set and support vector machine[J]. Mechanical Systems and Signal Processing, 2012(28):608-621.
[15] 姜万录,吴胜强. 基于SVM和证据理论的多数据融合故障诊断方法[J]. 仪器仪表学报, 2010,31(8):1738-1743.
Jiang Wanlu, Wu Qiang. Multi-data fusion diagnosis method based on SVM and evidence theory[J]. Chinese Journal of Scientific Instrument, 2010,31(8):1738-1743.

PDF(2472 KB)

Accesses

Citation

Detail

段落导航
相关文章

/