基于小波包和拉普拉斯特征值映射的柱塞泵健康评估方法

PDF(1494 KB)

振动与冲击 ›› 2017, Vol. 36 ›› Issue (22) : 45-50.

论文

王浩任1，黄亦翔1，赵帅1，刘成良 1，王双园1，张大庆 2

作者信息 +

Health Assessment for Piston Pump based on WPD and LE

WANG HaorenHUANGYixiangZHAO Shuai LIUChengliangWANGShuangyuan WANG Ye

Author information +

文章历史 +

摘要

柱塞泵是液压系统的关键部件之一，监测其健康状态对液压系统的可靠运行具有重要意义。因此本文提出一种基于小波包和流形学习的方法，用于分析柱塞泵出口振动信号，从而对其进行健康评估。该方法首先利用小波包对原始信号进行分解，从中提取用于描述柱塞泵健康状态的有效特征群。其次，把提取的高维特征群作为输入，利用并比较多种流形学习方法进行特征降维，选取状态识别准确率最高的拉普拉斯特征映射方法，建立起的特征向量到健康状态之间的对应关系，实现液压泵健康状态监测的分类要求。实验结果表明，采用小波包和拉普拉斯特征映射相结合的方法可以有效提高柱塞泵状态评估的准确性。

Abstract

Piston pump is one of the key components in the hydraulic system, monitoring its health condition is of significant importance for reliable performance of the hydraulic system. Therefore, a health state evaluation method has been proposedbased on wavelet packet decomposition(WPD) and manifold learning by the analysis of the vibration signals at the piston outlet. Wavelet packet method has been used to decomposeoriginal signalsand effectively extract health state features group from them. The high dimensional feature groupis set as an input andmultiple manifold learning methods are conducted and compared for dimensional reduction. Thelaplacianeigenmaps(LE) method of the highest accuracy is selectedto establish a relationship between feature vectors and health states, whichachieve the aimof health state classification.It is shown thatthe combination of wavelet packet decomposition and manifold learning methods improves the accuracy ofpistonpump health state evaluation.

导出引用

王浩任1，黄亦翔1，赵帅1，刘成良 1，王双园1，张大庆 2. 基于小波包和拉普拉斯特征值映射的柱塞泵健康评估方法[J]. 振动与冲击, 2017, 36(22): 45-50

WANG HaorenHUANGYixiangZHAO Shuai LIUChengliangWANGShuangyuan WANG Ye. Health Assessment for Piston Pump based on WPD and LE[J]. Journal of Vibration and Shock, 2017, 36(22): 45-50

参考文献

[1] 何正嘉，訾艳阳，孟庆丰．机械设备非平稳信号的故障诊断原理及应用[M]．北京高等教育出版社，2001．
[2] Daubechies, I. and B.J. Bates, Ten lectures on wavelets[J]. The Journal of the Acoustical Society of America, 1993. 93(3): 1671-1671.
[3] 高英杰，孔祥东. 基于小波包分析的液压泵状态监测方法[J]. 机械工程学报, 2009. 45(8): 80-88.
GAO Yingjie, KONG Xiangdong. Wavelet Packets Analysis Based Method for Hydraulic Pump Condition Monitoring [J]. Journal of Mechanical Engineering, 2009. 45(8): 80-88.
[4] Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290: 2323-2326.
[5] Tenenbaum J B, Silva V D, Langford J C. A global geometric framework for nonlinear dimensionality reduction[J]. Science, 2000, 290: 2319-2323.
[6] 蒋全胜，贾民平，胡建中，等. 基于拉普拉斯特征映射的故障模式识别方法[J].系统仿真学报，2008，20(20)： 5710-5713. JIANG Quansheng，JIA Minping，HU Jianzhong，et al. Method of fault pattern recognition based on Laplacian eigenmaps[J]. Journal of System Simulation，2008，20(20)：5710-5713.
[7] HE X，NIYOGI P. Locality preserving projections[M] Advances in Neural Information Processing Systems 16，Vancouver，British Columbia，Canada：MIT Press，2003：153-160.
[8] JIANG Quansheng，JIA Minping，HU Jianzhong，et al. Machinery fault diagnosis using supervised manifold learning[J]. Mechanical Systems and Signal Processing，2009，23: 2301-2311.
[9] YU Jianbo. Local and non-local preserving projection for bearing defect classification and performance assessment[J]. IEEE Trans. Ind. Electron，2012，59(5): 2363-2376.
[10] 王红军, 徐小力，万鹏. 基于轴心轨迹流形拓扑空间的转子系统故障诊断[J]. 机械工程学报, 2014. 50(5): 95-101.
WANG Hongjun, XU Xiaoli, WAN Peng, Rotor System Fault Diagnosis Based on Orbit Manifold Topological[J] Journal of Mechanical Engineering, 2014. 50(5): 95-101.
[11] 黄宏臣，韩振南，张倩倩，李月仙，张志伟. 基于拉普拉斯特征映射的滚动轴承故障识别[J]. 振动与冲击, 2015, 34(5): 128-134.
HUANG Hongchen,HAN Zhennan,ZHANGQianqian, LI Yuexian, ZHANG Zhiwei. A Method for Fault Diagnosis of Rolling Bearings Based on Laplacian Eigenmap[J]. Journal of Vibration and Shock, 2015, 34(5): 128-134.
[12] 高东，吴重光，张贝克，马昕.基于PCA和SDG的传感器故障诊断方法研究及应用[J].系统仿真学报, 2011. 23(3): 567-573.
GAO Dong, WU Chongguang, ZHANG Beike, MA Xin. Method Combining PCA and SDG for Fault Diagnosisof Sensors and Its Application[J]. Journal of System Simulation, 2011. 23(3): 567-573.
[13] XU Yong, et al., A method for speeding up feature extraction based on KPCA[J]. Neurocomputing, 2007. 70(4): 1056-1061.
[14] 杨先勇，周晓军，张文斌，杨富春. 基于局域波法和 KPCA-LSSVM的滚动轴承故障诊断[J]浙江大学学报: 工学版, 2010(8): 1519-1524.
YANG Xianyong, ZHOU Xiaojun, ZHANG Wenbin, YANG Fuchun. Rolling bearing fault diagnosis based on local wave methodand KPCA-LSSVM[J]. Journal of Zhejiang University (Engineering Science), 2010(8): 1519-1524.
[15] 徐金梧，吕勇，王海峰. 局部投影算法及其在非线性时间序列分析中的应用[J]. 机械工程学报，2003，39(9)：146-150.
XU Jinwu, LU Yong, WANGHaifeng.Local projective method andit’s application onnonlinear time series[J]. Journal of Mechanical Engineering,2003,39(9): 146-150.
[16] Balasubramanian, M. and E.L. Schwartz, The isomap algorithm and topological stability[J]. Science, 2002. 295(5552): 7-7.
[17] 孟德宇，徐晨，徐宗本. 基于Isomap的流形结构重建方法.[J] 计算机学报, 2010. 33(3): 545-555.
MENGDeyu, XU Chen, XUZongben. A new manifold reconstruction method based on Isomap[J]. Chinese Journal of Computers.2010. 33(3): 545-555.
[18] 刘爱萍王洪元程起才冯燕，基于KISOMAP-LDA-KNN算法TE过程故障诊断研究[J]. 计算机与数字工程, 2010. 38(11): 34-37.
LIU Aiping, WANG Hongyuan, CHENGQicai, FENG Yan. An algorithm of KISOMAP-LDA-KNN for the research of the fault diagnosis of TE Process[J]. Computer and Digital Engineering.2010. 38(11): 34-37.
[19] Kantz, H. and T. Schreiber, Nonlinear time series analysis[M]. Vol. 7. 2004: Cambridge university press
[20] 丁晓喜，何清波. 基于WPD和LPP的设备故障诊断方法研究[J].振动与冲击, 2014. 33(3): 89-93.
DING Xiaoxi, HE Qingbo. Machine fault diagnosis based on WPD and LPP[J]. Journal of vibration and shock. 2014. 33(3): 89-93.