基于等距特征映射和支持矢量机的转子故障诊断方法
|
摘要
针对振动信号的非线性特征,提出一种基于等距特征映射(Isometric feature mapping,ISOMAP)和支持矢量机(Support vector machine,SVM)的转子故障诊断方法。利用ISOMAP把数据从高维空间投影到低维空间而不改变数据内在属性的特点,对高维的故障振动信号降维并提取出低维的数据作为特征矢量,采用一种新核函数支持矢量机作为分类器进行故障诊断。将该方法应用于转子故障诊断,结果表明,ISOMAP-SVM方法不仅具有较高的故障诊断率,而且取得振动信号在低维空间的可视化表示。与其他核函数相比新核函数支持矢量机具有较好的诊断效果。
Aiming at the non-linear characteristics of vibration signals,a method of fault diagnosis of turbine rotor based on isometric feature mapping(ISOMAP) and support vector machine(SVM) is proposed.For the advantages of ISOMAP that it can maintain the inner feature while projecting the high dimension data onto low dimension data space.The vectors form low dimension data space are extracted,which produced by ISOMAP from high dimension space of vibration signal,and consider them as feature vectors,adopting a new kernel function SVM classifier to diagnosis fault types.The proposed ISOMAP-SVM approach is applied to the rotor fault diagnosis.The results show that this method has higher fault diagnosis accuracy,it can make a visual outcome of fault diagnosis.Compared with other kernel functions,the new kernel function SVM has better diagnosis effect.
Aiming at the non-linear characteristics of vibration signals,a method of fault diagnosis of turbine rotor based on isometric feature mapping(ISOMAP) and support vector machine(SVM) is proposed.For the advantages of ISOMAP that it can maintain the inner feature while projecting the high dimension data onto low dimension data space.The vectors form low dimension data space are extracted,which produced by ISOMAP from high dimension space of vibration signal,and consider them as feature vectors,adopting a new kernel function SVM classifier to diagnosis fault types.The proposed ISOMAP-SVM approach is applied to the rotor fault diagnosis.The results show that this method has higher fault diagnosis accuracy,it can make a visual outcome of fault diagnosis.Compared with other kernel functions,the new kernel function SVM has better diagnosis effect.
引文
[1]于德介,陈淼峰,程军圣,等.一种基于经验模式分解与支持向量机的转子故障诊断方法[J].中国电机工程学报,2006,26(16):162-167.YU Dejie,CHEN Miaofeng,CHENG Junsheng,et al.A fault diagnosis approach for rotor systems based on empirical mode decomposition method and support vector machines[J].Proceeding of the CSEE,2006,26(16):162-167.
[2]高金吉.旋转机械振动故障原因及识别特征研究[J].振动、测试与诊断,1995,15(3):1-8.GAO Jinji.Approach to mechanical vibration faults and distinctive symptoms in rotating machinery[J].Journal of Vibration,Measurement&Diagnosis,1995,15(3):1-8.
[3]颜廷虎,钟秉林,黄仁,等.神经网络技术及其在旋转机械故障诊断中的应用[J].振动工程学报,1993,6(3):205-212.YAN Tinghu,ZHONG Binglin,HUANG Ren,et al.Artificial neural network technique and its applications to rotating machinery fault diagnosis[J].Journal of Vibration Engineering,1993,6(3):205-212.
[4]刘占生,窦唯.基于旋转机械振动参数图形融合灰度共生矩阵的故障诊断方法[J].中国电机工程学报,2008,28(2):88-95.LIU Zhansheng,DOU Wei.A fault diagnosis method based on combination gray co-occurrence matrix of vibration parameter image for rotating machinery[J].Proceedings of the CSEE,2008,28(2):88-95.
[5]梁平,白蕾,龙新峰,等.基于小波包分析及神经网络的汽轮机转子振动故障诊断[J].控制理论与应用,2007,24(6):981-985.LIANG Ping,BAI Lei,LONG Xinfeng,et al.Turbine rotor vibration fault diagnosis based on wavelet packet analysis and neural network[J].Control Theory&Application,2007,24(6):981-985.
[6]TENENBAUM J B,SILVAVD,LANGFORD J C.A global geometric framework for nonlinear dimensionality reduction[J].Science,2000,290(5500):2319-2323.
[7]黎敏,徐金梧,阳建宏,等.一种基于流形拓扑结构的轴承故障分类方法[J].控制工程,2009,16(3):358-362.LI Min,XU Jinwu,YANG Jianhong,et al.Classification method of bearing faults based on topological structure of manifold[J].Control Engineering of China,2009,16(3):358-362.
[8]ROWEIS S T,SAUL L K.Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,290(5500):2323-2326.
[9]刘杏芳,郑晓东,徐光成,等.基于流形学习的地震属性特征提取方法及应用[C]//2010年国际石油地球物理技术交流会,2010年7月23-24,中国,兰州.2010:144-146.LIU Xingfang,ZHENG Xiaodong,XU Guangcheng,et al.Seismic attribute feature extraction and application based on manifold learning[C]//Conference on Exploration Geophysics in the West of China-CEG,July 23-24,2010,Lanzhou,China.2010:144-146.
[10]侯晓宇.基于流形学习的特征提取方法研究[D].大连:大连理工大学,2009.HOU Xiaoyu.Study on feature extraction based on manifold learning[D].Dalian:Dalian University of Technology,2009.
[11]VAPNIK V N.统计学习理论本质[M].张学工,译.北京:清华大学出版社,2000.VAPNIK V N.The nature of statistical learning theory[M].Translated by ZHANG Xuegong.Beijing:Tsinghua University Press,2000.
[12]李凌均,韩捷,李朋勇,等.基于矢双谱的智能故障诊断方法[J].机械工程学报,2011,47(11):64-68.LI Lingjun,HAN Jie,LI Pengyong,et al.Intelligent fault diagnosis method based on vector-bispectrum[J].Journal of Mechanical Engineering,2011,47(11):64-68.
[13]王太勇,何慧龙,王国锋,等.基于经验模式分解和最小二乘支持矢量机的滚动轴承故障诊断[J].机械工程学报,2007,43(4):88-92.WANG Taiyong,HE Huilong,WANG Guofeng,et al.Rolling-bearings fault diagnosis based on empirical mode decomposition and least square support vector machine[J].Chinese Journal of Mechanical Engineering,2007,43(4):88-92.
[14]李巍华,史铁林,杨叔子.基于核函数估计的转子故障诊断方法[J].机械工程学报,2006,42(9):76-81.LI Weihua,SHI Tielin,YANG Shuzi.Rotor fault diagnosis method based on kernel function approximation[J].Chinese Journal of Mechanical Engineering,2006,42(9):76-81.
[15]彭文季,罗兴锜.基于小波包分析和支持向量机的水电机组振动故障诊断研究[J].中国电机工程学报,2006,26(24):164-168.PENG Wenji,LUO Xingqi.Research on vibrant fault diagnosis of hydro-turbine generating unit based on wavelet packet analysis and support vector machine[J].Proceedings of the CSEE,2006,26(24):164-168.
[16]VONG Chiman,WONG Pakkin,TAM Lapmou,et al.Ignition pattern analysis for automotive engine trouble diagnosis using wavelet packet transform and support vector machines[J].Chinese Journal of Mechanical Engineering,2011,24(5):870-878.
[17]LIU Guanjun,LIU Xinmin,QIU Jing,et al.Fault support vector machine[J].Chinese Journal of Mechanical Engineering,2007,20(5):92-95.
[18]吴峰崎,孟光.基于支持向量机的转子振动信号故障分类研究[J].振动工程学报,2006,19(2):238-241.WU Fengqi,MENG Guang.Fault classification of rotor vibration signal based on support vector machine[J].Journal of Vibration Engineering,2006,19(2):238-241.
[19]SAMUEL K,MARTIN D L.Face detection in gray scale images using locally embeddings[J].Computer Vision and Image Understanding,2007,105(1):1-20.
[20]SMOLA A J,SCHOLKOPF B,MULLER K R.The connection between regularization operators and support vector kernels[J].Neural Networks,1998,11:637-649.
[21]USTUN B,MELSSEN W J,BUYDENS L M C.Facilitating the application of support vector regression by using a universal Pearson VII function based kernel[J].Chemomatrics and Intelligent Laboratory Systems,2006,81:29-40.
[22]郑启富,陈德钊,刘化章.基于PersonⅦ核函数的支持向量机及其在化学模式分类中的应用[J].分析化学,2007,35(8):1142-1146.ZHENG Qifu,CHEN Dezhao,LIU Huazhang.Support vector machine based on PersonⅦkernel function and its application in chemical pattern classification[J].Chinese Journal of Analysis Chemistry,2007,35(8):1142-1146.
[2]高金吉.旋转机械振动故障原因及识别特征研究[J].振动、测试与诊断,1995,15(3):1-8.GAO Jinji.Approach to mechanical vibration faults and distinctive symptoms in rotating machinery[J].Journal of Vibration,Measurement&Diagnosis,1995,15(3):1-8.
[3]颜廷虎,钟秉林,黄仁,等.神经网络技术及其在旋转机械故障诊断中的应用[J].振动工程学报,1993,6(3):205-212.YAN Tinghu,ZHONG Binglin,HUANG Ren,et al.Artificial neural network technique and its applications to rotating machinery fault diagnosis[J].Journal of Vibration Engineering,1993,6(3):205-212.
[4]刘占生,窦唯.基于旋转机械振动参数图形融合灰度共生矩阵的故障诊断方法[J].中国电机工程学报,2008,28(2):88-95.LIU Zhansheng,DOU Wei.A fault diagnosis method based on combination gray co-occurrence matrix of vibration parameter image for rotating machinery[J].Proceedings of the CSEE,2008,28(2):88-95.
[5]梁平,白蕾,龙新峰,等.基于小波包分析及神经网络的汽轮机转子振动故障诊断[J].控制理论与应用,2007,24(6):981-985.LIANG Ping,BAI Lei,LONG Xinfeng,et al.Turbine rotor vibration fault diagnosis based on wavelet packet analysis and neural network[J].Control Theory&Application,2007,24(6):981-985.
[6]TENENBAUM J B,SILVAVD,LANGFORD J C.A global geometric framework for nonlinear dimensionality reduction[J].Science,2000,290(5500):2319-2323.
[7]黎敏,徐金梧,阳建宏,等.一种基于流形拓扑结构的轴承故障分类方法[J].控制工程,2009,16(3):358-362.LI Min,XU Jinwu,YANG Jianhong,et al.Classification method of bearing faults based on topological structure of manifold[J].Control Engineering of China,2009,16(3):358-362.
[8]ROWEIS S T,SAUL L K.Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,290(5500):2323-2326.
[9]刘杏芳,郑晓东,徐光成,等.基于流形学习的地震属性特征提取方法及应用[C]//2010年国际石油地球物理技术交流会,2010年7月23-24,中国,兰州.2010:144-146.LIU Xingfang,ZHENG Xiaodong,XU Guangcheng,et al.Seismic attribute feature extraction and application based on manifold learning[C]//Conference on Exploration Geophysics in the West of China-CEG,July 23-24,2010,Lanzhou,China.2010:144-146.
[10]侯晓宇.基于流形学习的特征提取方法研究[D].大连:大连理工大学,2009.HOU Xiaoyu.Study on feature extraction based on manifold learning[D].Dalian:Dalian University of Technology,2009.
[11]VAPNIK V N.统计学习理论本质[M].张学工,译.北京:清华大学出版社,2000.VAPNIK V N.The nature of statistical learning theory[M].Translated by ZHANG Xuegong.Beijing:Tsinghua University Press,2000.
[12]李凌均,韩捷,李朋勇,等.基于矢双谱的智能故障诊断方法[J].机械工程学报,2011,47(11):64-68.LI Lingjun,HAN Jie,LI Pengyong,et al.Intelligent fault diagnosis method based on vector-bispectrum[J].Journal of Mechanical Engineering,2011,47(11):64-68.
[13]王太勇,何慧龙,王国锋,等.基于经验模式分解和最小二乘支持矢量机的滚动轴承故障诊断[J].机械工程学报,2007,43(4):88-92.WANG Taiyong,HE Huilong,WANG Guofeng,et al.Rolling-bearings fault diagnosis based on empirical mode decomposition and least square support vector machine[J].Chinese Journal of Mechanical Engineering,2007,43(4):88-92.
[14]李巍华,史铁林,杨叔子.基于核函数估计的转子故障诊断方法[J].机械工程学报,2006,42(9):76-81.LI Weihua,SHI Tielin,YANG Shuzi.Rotor fault diagnosis method based on kernel function approximation[J].Chinese Journal of Mechanical Engineering,2006,42(9):76-81.
[15]彭文季,罗兴锜.基于小波包分析和支持向量机的水电机组振动故障诊断研究[J].中国电机工程学报,2006,26(24):164-168.PENG Wenji,LUO Xingqi.Research on vibrant fault diagnosis of hydro-turbine generating unit based on wavelet packet analysis and support vector machine[J].Proceedings of the CSEE,2006,26(24):164-168.
[16]VONG Chiman,WONG Pakkin,TAM Lapmou,et al.Ignition pattern analysis for automotive engine trouble diagnosis using wavelet packet transform and support vector machines[J].Chinese Journal of Mechanical Engineering,2011,24(5):870-878.
[17]LIU Guanjun,LIU Xinmin,QIU Jing,et al.Fault support vector machine[J].Chinese Journal of Mechanical Engineering,2007,20(5):92-95.
[18]吴峰崎,孟光.基于支持向量机的转子振动信号故障分类研究[J].振动工程学报,2006,19(2):238-241.WU Fengqi,MENG Guang.Fault classification of rotor vibration signal based on support vector machine[J].Journal of Vibration Engineering,2006,19(2):238-241.
[19]SAMUEL K,MARTIN D L.Face detection in gray scale images using locally embeddings[J].Computer Vision and Image Understanding,2007,105(1):1-20.
[20]SMOLA A J,SCHOLKOPF B,MULLER K R.The connection between regularization operators and support vector kernels[J].Neural Networks,1998,11:637-649.
[21]USTUN B,MELSSEN W J,BUYDENS L M C.Facilitating the application of support vector regression by using a universal Pearson VII function based kernel[J].Chemomatrics and Intelligent Laboratory Systems,2006,81:29-40.
[22]郑启富,陈德钊,刘化章.基于PersonⅦ核函数的支持向量机及其在化学模式分类中的应用[J].分析化学,2007,35(8):1142-1146.ZHENG Qifu,CHEN Dezhao,LIU Huazhang.Support vector machine based on PersonⅦkernel function and its application in chemical pattern classification[J].Chinese Journal of Analysis Chemistry,2007,35(8):1142-1146.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心