基于负熵的旋转机械盲信号处理

中国机械工程 ›› 2011, Vol. 22 ›› Issue (10): 1193-1197.

基于负熵的旋转机械盲信号处理

毋文峰;陈小虎;苏勋家;姚春江;王旭平

第二炮兵工程学院,西安,710025

出版日期:2011-05-25 发布日期:2011-05-31
基金资助:
总装备部预研重点基金资助项目
Key Program of National Defense Pre-research Foundation of General Armament Department

Blind Signal Processing Based on Negentropy for Rotating Machines

Wu Wenfeng;Chen Xiaohu;Su Xunjia;Yao Chunjiang;Wang Xuping

The Second Artillery Engineering College,Xi’an,710025

Online:2011-05-25 Published:2011-05-31
Supported by:
Key Program of National Defense Pre-research Foundation of General Armament Department

摘要/Abstract

摘要：

针对机械设备盲信号处理实践中，机械源信号数目大于多通道观测数目的欠定盲信号处理问题,将非高斯性的度量指标——负熵和经验模式分解引入机械设备的故障特征提取，提出基于负熵的旋转机械盲信号处理方法，从而解决欠定的单通道机械盲信号处理问题。首先将机械设备的单通道观测信号经验模式分解，得到本征模函数,然后计算本征模函数的负熵值，并将负熵值依序组成负熵基特征向量，最后采用最小二乘支持向量机进行机械设备的模式判别和故障诊断。液压齿轮泵的盲信号处理试验表明，该方法的故障识别率达到了93%以上,表明该方法是可以应用于机械盲信号处理实践的。

关键词:

盲信号处理, 负熵, 经验模式分解, 最小二乘支持向量机



Abstract:

In blind signal processing of mechanical equipment,it is common that mechanical source number is more than that of multi-channel observation signals. This was called underdetermined blind signal processing. Then negentropy and empirical mode decomposition(EMD) was introduced into feature abstraction of mechanical equipment to deal with their single channel blind signal processing.This algorithm was composed of three steps. Step 1 was to decompose single channel mechanical observation signals with empirical mode decomposition and get intrinsic mode functions(IMFs).Step 2 was to compute negentropy values of IMFs and form a negentropy eigenvector according to IMFs sequence. Step 3 was to recognize different working patterns and diagnose different faults with LS-SVM. Its applications in blind signal processing of hydraulic gear pumps show that, its fault diagnosis rate is up to 93% on the whole. This indicates that this algorithm can be applied to mechanical blind signal processing.

Key words: blind signal processing, negentropy, empirical mode decomposition, least square support vector machine(LS-SVM)

中图分类号:

毋文峰, 陈小虎, 苏勋家, 姚春江, 王旭平.

基于负熵的旋转机械盲信号处理

[J]. 中国机械工程, 2011, 22(10): 1193-1197.

MOU Wen-Feng, CHEN Xiao-Hu, SU Xun-Jia, TAO Chun-Jiang, WANG Xu-Beng.

Blind Signal Processing Based on Negentropy for Rotating Machines

[J]. China Mechanical Engineering, 2011, 22(10): 1193-1197.

参考文献

[1]胥永刚[1],李强[1],王正英[1],王太勇[1].基于独立分量分析的机械故障信息提取[J].天津大学学报,2006,39(9):1066-1071.
[2]李力,屈梁生.应用独立分量分析提取机器的状态特征[J].西安交通大学学报,2003,37(1):45-48.
[3]陈长征[1],程锦生[1],韩丽娅[2],李明辉[3],王胤龙[1],周勃[1].基于盲源分离的齿轮箱状态检测与故障诊断[J].沈阳工业大学学报,2008,30(4):444-448.
[4]陈仲生[1],杨拥民[1],沈国际[1].独立分量分析在直升机齿轮箱故障早期诊断中的应用[J].机械科学与技术,2004,23(4):481-483.
[5]钟振茂,陈进,钟平.盲源分离技术用于机械故障诊断的研究初探[J].机械科学与技术,2002,21(2):282-284.
[6]Ypma A, Leshem A, Duin RPW. Blind Separation of Rotating Machine Sources..Bilinear Forms and Con- volutive Mixtures[J]. Neuro-- computing, 2002,49 (4) :349-368.
[7]Gelle G,Colas M, Delaunay G. Blind Source Separa- tion Applied to Rotating Machines Monitoring by Acoustical and Vibrations Analysis[J]. Mechanical System and Signal Processing, 2000, 14 (3):427- 442.
[8]Hyvarinen A, Oja E. Independent Component Anal- ysis : Algorithms and Applications [J]. Neural Net- works,2000,13(4/5) :411-430.
[9]Hyvarinen A, Karhunen J, Oja E. Independent Component Analysis[M]. New York: John Wiley & Sons. ,Inc. ,2001.
[10]李舜酩[1],雷衍斌[1].基于负熵的转子混叠振动信号盲识别[J].中国机械工程,2009,10(4):437-441.
[11]Huang N E,ghen Z,Long S R,et al. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Nonstationary Time Series Analysis [J]. Proceedings of the Royal of London Series A, 1998,454 : 903-995.
[12]于德介,程军圣,杨宇著.机械故障诊断的HIBERT-HUANG变换方法[M],2006:194.
[13]Cortes C,Vapnik V. Support Vector Networks[J].Machine Learning,1995,20(2):273-297.
[14]Suykens J A K, Vandewalle J. Least Squares Sup- port Vector Machine Classifiers [J]. Neural Pro- cessing Letters (S1370-4621), 1999,9 (3):293- 300.

[1]	张淑清, 黄文静, 胡永涛, 宿新爽, 陆超, 姜万录. 基于总体平均经验模式分解近似熵和混合PSO-BP算法的轴承故障诊断方法[J]. 中国机械工程, 2016, 27(22): 3048-3054.
[2]	张淑清, 胡永涛, 李盼, 包红燕, 姜万录, 钱磊. 基于MEMD互近似熵及FCM聚类的轴承故障诊断方法[J]. 中国机械工程, 2015, 26(19): 2613-2618.
[3]	孟宗;季艳. 基于DEMD和对称差分能量算子解调的滚动轴承故障诊断[J]. 中国机械工程, 2015, 26(12): 1658-1664.
[4]	李晓晖;傅攀. 基于EEMD的单通道盲源分离在轴承故障诊断中的应用[J]. 中国机械工程, 2014, 25(7): 924-930.
[5]	张根保;范秀君. 基于蚁群算法优化选取阈值的EMD消噪方法[J]. 中国机械工程, 2014, 25(4): 427-432.
[6]	赵军;崔颖;赖欣欢;孔明;林敏. 随机共振降噪下的齿轮微弱故障特征提取[J]. 中国机械工程, 2014, 25(4): 539-546.
[7]	王书涛;李亮;张淑清;孙国秀. 基于EEMD样本熵和GK模糊聚类的机械故障识别[J]. 中国机械工程, 2013, 24(22): 3036-3040,3044.
[8]	张俊红, 李林洁, 马文朋, 李周裕, 刘昱. EMD-ICA联合降噪在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2013, 24(11): 1468-1472.
[9]	田海雷, 李洪儒, 许葆华. 基于集总经验模式分解和支持向量机的液压泵故障预测研究[J]. 中国机械工程, 2013, 24(07): 926-931.
[10]	王翔, 王仲生. 基于改进Hilbert-Huang变换的转子碰摩故障诊断 [J]. 中国机械工程, 2011, 22(24): 2937-2940.
[11]	吴虎胜, 吕建新, 吴庐山, 王茂生. 基于EMD和SVM的柴油机气阀机构故障诊断 [J]. 中国机械工程, 2010, 21(22): 2710-2714.
[12]	陈建国;王奉涛;朱泓;张志新;李宏坤;. 改进ICA与HHT在转子故障诊断上的应用[J]. J4, 2009, 20(17): 0-2021.
[13]	李舜酩;雷衍斌. 基于负熵的转子混叠振动信号盲识别[J]. J4, 2009, 20(04): 0-503.
[14]	崔玲丽;高立新;殷海晨;胥永刚;. 基于第二代小波的复合故障诊断方法研究[J]. J4, 2009, 20(04): 0-388.
[15]	王雪;马俊杰;王晟. 机械设备状态的经验模式分解统计识别方法[J]. J4, 2008, 19(6): 0-644.