应用AR模型的多参数与多测点信息融合的故障分类

孙国富; 徐玉秀

doi:10.13433/j.cnki.1003-8728.2017.0617

应用AR模型的多参数与多测点信息融合的故障分类

doi: 10.13433/j.cnki.1003-8728.2017.0617

孙国富^1,2,
徐玉秀^1,2, ,

1.
天津工业大学机械工程学院, 天津 300387;
2.
现代机电装备技术重点实验室, 天津 300387

基金项目:

国家重大科技成果转化项目（2060403）与天津市自然科学基金重点项目（10JCZDJC23400）资助

详细信息

作者简介:
孙国富(1988-),硕士,研究方向为机械振动与故障诊断,tjgydxjxxy@163.com

通讯作者:
徐玉秀(联系人),教授,硕士生导师,博士,xuyu@tjpu.edu.cn

计量
- 文章访问数: 191
- HTML全文浏览量: 42
- PDF下载量: 7
- 被引次数: 0
出版历程
- 收稿日期: 2015-06-29
- 刊出日期: 2017-06-05

Fault Classification based on Multi-parameter and Multi-point Information Fusion of AR Model

Sun Guofu^1,2,
Xu Yuxiu^{1,2
, ,}

1.
School of Mechanical Engineering, Tianjin Polytechnic University, Tianjin 300387, China;
2.
Key Laboratory of Advanced Mechatronics Equipment Technology, Tianjin 300387, China

摘要

摘要: 为了找到针对齿轮传动系统多类故障分类的有效方法，对行星齿轮传动系统进行故障实验，获取振动信号。采用EMD方法对该振动信号进行预处理，得到若干个IMF分量之和，对前4个有效的IMF分量分别建立AR模型，得到对应的自回归参数序列φ，进而对其分别计算关联维数、最大Lyapunov指数、样本熵这3个混沌特征参数，并将其作为辨识特征量。将不同测点对应的φ的不同混沌特征参数信息融合作为支持向量机的输入向量，建立6种不同故障状态的训练集，实现对故障类型进行分类。结果表明：对实验获取的振动信号进行EMD和AR模型处理后，能在很大程度上提高故障分类准确率。
- 行星齿轮传动系统 /
- 混沌特征参数 /
- 多测点 /
- 支持向量机 /
- EMD /
- AR模型
Abstract: In order to find an effective method of fault classification of gear transmission system, fault tests are conducted on the planetary gear transmission system to acquire vibration signals. Empirical mode decomposition (EMD) method is used to process the vibration signals. The sum of several intrinsic mode function (IMF) components are obtained and the auto regressive (AR) model of the former four IMF components is established. and the regression parameter sequence is obtained, then the correlation dimension, maximum Lyapunov exponent and sample entropy are calculated, and these three chaotic characteristic parameters are used as fault identification features. The information of different chaotic characteristic parameters of different measuring points are fused and fed as input vector of support vector machine (SVM) to establish six kinds of different state of the training sets, then the classification of fault type can be achieved. The results indicate that the use the experimental vibration signals proceeded by EMD and AR modeling, the fault classification accuracy can be improve.
- chaotic characteristic parameters /
- multiple measuring points /
- support vector machine /
- EMD /
- AR model /
- information fusion

HTML全文

参考文献(17)

[1]	陈文涛,谢志江,陈平.风力发电机组齿轮箱故障监测与诊断[J].机床与液压,2012,40(3):167-169 Chen W T, Xie Z J, Chen P. Fault diagnosis and detection for gearbox of wind turbine generator[J]. Machine Tool & Hydraulics, 2012,40(3):167-169 (in Chinese)
[2]	雷亚国,何正嘉,林京,等.行星齿轮箱故障诊断技术的研究进展[J].机械工程学报,2011,47(19):59-67 Lei Y G, He Z J, Lin J, et al. Research advances of fault diagnosis technique for planetary gearboxes[J]. Journal of Mechanical Engineering, 2011,47(19):59-67 (in Chinese)
[3]	张超,陈建军.随机共振消噪和EMD分解在轴承故障诊断中的应用[J].机械设计与研究,2013,29(1):35-38 Zhang C, Chen J J. Application of stochastic resonance for denoising and EMD to bearing fault diagnosis[J]. Machine Design and Research, 2013,29(1):35-38 (in Chinese)
[4]	宋飞,潘宏侠,黄晋英.基于HHT的齿轮箱复合故障诊断研究[J].煤炭技术,2010,29(12):24-26 Song F, Pan H X, Huang J Y. Research on gearbox composite fault diagnosis based on Hilbert-Huang transform[J]. Coal Technology, 2010,29(12):24-26 (in Chinese)
[5]	徐玉秀,赵晓清,杨文平,等.多参数与多测点信息融合的行星轮故障诊断[J].仪器仪表学报,2014,35(8):1789-1795 Xu Y X, Zhao X Q, Yang W P, et al. Planetary gear fault diagnosis based on information fusion of multi-parameters and multi-points[J]. Chinese Journal of Scientific Instrument, 2014,35(8):1789-1795 (in Chinese)
[6]	尉询楷,李应红,刘建勋,等.基于支持向量机的信息融合诊断方法[J].系统工程与电子技术,2005,27(9):1665-1668 Wei X K, Li Y H, Liu J X, et al. Novel information fusion fault diagnosis method based on support vector machines[J]. Systems Engineering and Electronics, 2005,27(9):1665-1668 (in Chinese)
[7]	王炳成,任朝晖,闻邦椿.故障诊断中的混沌参数分析[J].机床与液压,2010,38(23):144-147 Wang B C, Ren Z H, Wen B C. Chaotic parameters analysis in fault diagnoses[J]. Machine Tool & Hydraulics, 2010,38(23):144-147 (in Chinese)
[8]	吴震宇,袁惠群,李玲.基于混沌特征和支持向量机的内燃机故障诊断[J].机械强度,2010,32(5):723-728 Wu Z Y, Yuan H Q, Li L. Fault diagnosis of engine based on chaotic features and support vector machine[J]. Journal of Mechanical Strength, 2010,32(5):723-728 (in Chinese)
[9]	Huang N E, Shen Z, Long S R, et al. The Empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995
[10]	程军圣,于德介,杨宇,等.基于EMD的齿轮故障识别研究[J].电子与信息学报,2004,26(5):825-829 Cheng J S, Yu D J, Yang Y, et al. Research on gear fault diagnosis based on EMD[J]. Journal of Electronics & Information Technology, 2004,26(5):825-829 (in Chinese)
[11]	杨叔子,吴雅,轩建平.时间序列分析的工程应用[M].武汉:华中科技大学出版社,1991 Yang S Z, Wu X, Xuan J P. Time series analysis in engineering application[M]. Wuhan: Huazhong University of Science and Technology Press, 1991 (in Chinese)
[12]	张铮,杨文平.MATLAB程序设计与实例应用[J].北京:中国铁道出版社,2003 Zhang Z, Yang W P. Program design and application examples based on MATLAB[J]. Beijing: China Railway Publishing House, 2003 (in Chinese)
[13]	谢向荣,陈洪峰,朱石坚,等.关联维数在齿轮箱振动信号特征提取中的应用[J].海军工程大学学报,2005,17(6):102-107 Xie X R, Chen H F, Zhu S J, et al. Application of correlation dimension in extracting characteristics from vibration signals of gearbox[J]. Journal of Naval University of Engineering, 2005,17(6):102-107 (in Chinese)
[14]	罗志增,李亚飞,孟明,等.脑电信号的混沌分析和小波包变换特征提取算法[J].仪器仪表学报,2011,32(1):33-39 Luo Z Z, Li Y F, Meng M, et al. EEG feature extraction algorithm based on chaos analysis and wavelet packet transform[J]. Chinese Journal of Scientific Instrument, 2011,32(1):33-39 (in Chinese)
[15]	Richman J S, Moorman J R. Physiological time-series analysis using approximate entropy and sample entropy[J]. American Journal of Physiology, 2000,278(6):H2039-H2049
[16]	赵冲冲,廖明夫,于潇.基于支持向量机的旋转机械故障诊断[J].振动、测试与诊断,2006,26(1):53-57 Zhao C C, Liao M F, Yu X. Application of support vecter machine to fault diagnosis of rotation Machinery[J]. Journal of Vibration, Measurement & Diagnosis, 2006,26(1):53-57 (in Chinese)
[17]	齐岩磊,陈娟,杨祺,等.基于SVM的葛根素提取软测量系统的设计[J].电子测量与仪器学报,2012,26(8):726-731 Qi Y L, Chen J, Yang Q, et al. Design of a soft sensor system for Puerarin extraction based on SVM[J]. Journal of Electronic Measurement and Instrument, 2012,26(8):726-731 (in Chinese)