基于LPP与VPMCD的液压泵故障模式识别

摘要/Abstract

摘要：

针对液压泵振动信号复杂且难以提取有效特征量的问题，提出一种基于局部保留投影(LPP)算法的故障特征提取方法。采用集总经验模态分解(EEMD)法对液压泵振动信号进行分解，从得到的内禀模态分量(IMF)中选取敏感分量,对敏感分量进行分析并从中提取液压泵故障高维特征向量，利用局部保留投影法对高维特征向量进行融合降维，提取隐藏在高维特征空间中的故障本质信息，即敏感特征向量。基于变量预测模型的模式识别(VPMCD)算法实现模式识别的良好性能，提出采用VPMCD算法实现液压泵故障模式识别。基于提取的敏感特征集，建立各状态敏感特征的变量预测模型，进而实现液压泵的故障识别，实测液压泵振动信号分析结果验证了所提出液压泵故障模式识别方法的有效性。通过对比分析验证了所提出方法的良好性能。

关键词: 液压泵, 故障模式识别, 局部保留投影法, 基于变量预测模型的模式识别

Abstract:

Aiming at the problems that vibration signals were complex and the effective features were difficult to extract,a novel fault feature extraction method for pump was proposed based on LPP algorithm.The vibration signals of pump were decomposed into a number of intrinsic mode function(IMF) with ensemble empirical mode decomposition(EEMD),and then sensitive IMFs which contained more state informations were selected,and the high dimensional fault feature sets were extracted from the sensitive IMFs.Then the sensitive feature sets were gained by carrying out fusion and dimensional reduction to the high dimensional feature sets with LPP processing.On account of the favorable performance of VPMCD,the VPMCD was proposed to realize the fault pattern identification of pump.A variable predictive model(VPM) of each sensitive feature was established and the fault pattern of pump was diagnosed based on the VPMs.The analysis results of practical pump signals testify the rationality and availability of proposed method.In addition,comparative analysis results demonstrate the more favorable performance of proposed method.

Key words: hydraulic pump;fault mode identification, locality , preserving projection(LPP);variable predictive model based class discriminate(VPMCD）

中图分类号:

TH322
TP306

王余奎, 李洪儒, 许葆华. 基于LPP与VPMCD的液压泵故障模式识别[J]. 中国机械工程, 2015, 26(24): 3327-3335.

Wang Yukui, Li Hongru, Xu Baohua. Fault Pattern Identification of Hydraulic Pump Based on VPMCD and LPP Algorithm[J]. China Mechanical Engineering, 2015, 26(24): 3327-3335.

参考文献

[1]Zhao Zhen,Jia Mingxing,Wang Fuli,et al.Intermittent Chaos and Sliding Window Symbol Sequence Statistics-based Early Fault Diagnosis for Hydraulic Pump on Hydraulic Tube Tester[J].Mechanical Systems and Signal Processing,2009,23（5）:1573-1585.
[2]王余奎,李洪儒,叶鹏. 基于多尺度排列熵的液压泵故障识别[J].中国机械工程,2015,26(4):518-523.
Wang Yukui,Li Hongru,Ye Peng.Research on the Fault Identification of Hydraulic Pump Based on Multi-scale Permutation Entropy[J].China Mechanical Engineering,2015,26(4):518-523.
[3]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,1998,454(1):903-955.
[4]Wu Z H,Huang N E.Ensemble Empirical Mode Decomposition:a Noise Assisted Data Analysis Method[J].Advances in Adaptive Data Analysis, 2009,1:1-4.
[5]陈仁祥,汤宝平,杨黎霞,等. 自适应参数优化EEMD机械故障特征提取方法[J].振动测试与诊断,2014,34(6): 1065-1071.
Chen Renxiang,Tang Baoping,Yang Lixia,et al.An EEMD-feature Extraction Method of Mechanical Fault Based on Adaptive Parameter Optimum[J].Journal of Vibration,Measurement & Diagnosis,2014,34(6):1065-1071.
[6]李月仙,韩振南,黄宏臣,等.基于拉普拉斯特征映射的旋转机械故障识别[J].振动与冲击,2014,33(18):21-25.
Li Yuexian,Han Zhennan,Huang Hongchen,et al.Fault Diagnosis of Rotating Machineries Based on Laplacian Eigenmaps[J].Journal of Vibration and Shock, 2014,33(18):21-25.
[7]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.
[8]吴坚,赵阳,何睿.基于支持向量机回归算法的电子机械制动传感器系统故障诊断[J].吉林大学学报, 2013,43(5):1178-1183.
Wu Jian,Zhao Yang,He Rui.Fault Detection and Diagnosis of EMB Sensor System Based on SVR[J]. Journal of Jilin University, 2013, 43(5): 1178-1183.
[9]杨宇,王欢欢,曾鸣,等. 基于变量预测模型的模式识别方法在滚动轴承故障诊断中的应用[J].湖南大学学报(自然科学版),2013,40(3): 36-40.
Yang Yu,Wang Huanhuan,Zeng Ming,et al.Application of Pattern Recognition Approach Based on VPMCD in Roller Bearing Fault Diagnosis[J]. Journal of Hunan University(Natural Sciences),2013,40(3):36-40.
[10]Raghuraj R,Lakshminarayanan S. Variable Predictive Models—A New Multivariate Classification Approach for Pattern Recognition Application[J].Pattern Recognition,2009,42(1):7-16.
[11]Raghuraj R,Lakshminarayanan S. Variable Predictive Model Based Classification Algorithm for Effective Separation of Protein Structural Classes[J].Computational Biology and Chemistry,2008,32(4):302-306.
[12]Raghuraj R,Lakshminarayanan S.VPMCD: Variable Interaction Modeling Approach for Class Discrimination in Biological System [J].FEBS Letter,2007,581(5):826-830.
[13]程军圣,马兴伟,杨宇.基于排列熵和VPMCD的滚动轴承故障诊断方法[J].振动与冲击,2014,33(11):120-123.
Cheng Junsheng,Ma Xingwei,Yang Yu. Rolling Bearing Fault Diagnosis Method Based on Permutation Entropy and VPMCD[J].Journal of Vibration and Shock,2014,33(11):120-123.
[14]苏文胜,王奉涛,张志新，等.EMD降噪和谱峭度法在滚动轴承早期故障诊断中的应用[J].振动与冲击,2010,29(3):18-21.
Su Wensheng,Wang Fengtao,Zhang Zhixin,et al.Application of EMD de-noising and Spectral Kurtosis in Early Fault Diagnosis of Rolling Element Bearings[J]. Journal of Vibration and Shock,2010,29(3):18-21.
[15]张志刚,石晓辉,施全,等. 基于改进EMD和谱峭度法滚动轴承故障特征提取[J]. 振动、测试与诊断，2013，33(3)：478-482.
Zhang Zhigang,Shi Xiaohui,Shi Quan,et al.Fault Feature Extraction of Rolling Element Bearing Based on Improved EMD and Spectral Kurtosis[J].Journal of Vibration,Measurement & Diagnosis,2013,33(3):478-482.
[16]Wang Yukui,Li Hongru,Ye Peng.Fault Feature Extraction of Hydraulic Pump Based on CNC De-noising and HHT[J].Journal of Failure Analysis and Prevention,2015,15(1):139-151.
[17]Pan W T.A New Fruit Fly Optimization Algorithm:Taking the Financial Distress Model as an Example[J].Knowledge-based Systems, 2012, 26(1): 69-74.
[18]宁剑平,王冰,李洪儒,等.递减步长果蝇优化算法及应用[J].深圳大学学报(理工版),2014,31(4):367-373.
Ning Jianping,Wang Bing,Li Hongru,et al.Research on an Application of Diminishing Step Fruit Fly Optimization Algorithm[J].Journal of Shenzhen University Science an Engineering,2014,31(4):367-373.