基于核方法的旋转机械故障诊断技术与模式分析方法研究
|
摘要
旋转机械是国民经济支撑行业中广泛使用的关键性核心设备,开展旋转机械故障诊断技术研究,对于确保此类设备安全、可靠、高效、长周期、满负荷、优质运行,避免巨大的经济损失和灾难性事故的发生,具有极大的经济、社会意义。旋转机械故障诊断过程实质是模式分析过程,以支持向量机为代表的核方法带来了模式分析领域的第三次革命,该类方法通过核函数将原始空间数据隐式映射到特征空间,在特征空间寻找线性关系,实现非线性问题的高效求解。旋转机械发生的故障常常呈现出非线性行为,核方法特别适用于旋转机械故障诊断与模式分析问题的处理。
典型的核方法除支持向量机(SVM),还有核主成分分析(KPCA)、核独立成分分析(KICA)、核聚类(KC)、核Fish判别(KFD)等。论文围绕核方法及其在旋转机械故障诊断中的应用而展开,主要研究内容包括：
1.面向核方法应用的旋转机械振动信号采集与预处理
以机械故障综合模拟实验台为平台,设计了旋转机械典型故障振动测试实验,并采集了数据。提取时域统计特征、小波包分解和经验模态分解所得不同频段的能量、熵和能量熵特征、时序特征、关联维特征,构成11个旋转机械故障特征库,为核方法应用研究提供数据基础。
针对EMD过程中易产生冗余IMF的不足,提出改进HHT方法。小波包去噪后,以EMD所得每个IMF与分解前信号的相关系数作为判断依据,剔除冗余IMF,滚动轴承故障诊断实例表明该方法可有效提取微弱信号故障特征频率。
2.面向旋转机械故障诊断的KPCA核参数优选与消噪方法研究
揭示了核函数及核参数对KPCA性能影响规律,发现无论选用高斯核还是多项式核,累计贡献率大于0.85的核主成分个数均随核参数的增大而递减,最终呈收敛状态；选用高斯核的KPCA,其核主成分具有更好的聚类性能,对没有任何先验知识的特征向量执行KPCA时,建议取高斯核参数σ≥25。
提出了基于KPCA的信号消噪方法,克服滤波、小波消噪等常用消噪方法需要先验知识,给实际应用带来困难的不足。通过相空间重构将一维观测信号扩展为多维向量,再执行KPCA,提取核主成分,实现信号消噪,整个过程无需任何先验知识。仿真与滚动轴承振动信号消噪实例验证了方法的有效。
3.基于KICA的旋转机械故障信号消噪与特征提取
提出了基于KICA的信号消噪方法,通过引入适配噪声分量,将一维观测信号扩展为多维向量,再执行KICA,实现信噪分离,达到消噪目的。KICA消噪过程不受信噪比影响,具有其它消噪方法无法比拟的优势。转子不平衡振动信号的消噪实例验证了方法的有效性。
定义了旋转机械KIC特征量,实测信号分析表明KIC对滚动轴承与齿轮故障均具有有较好的识别性,可作为敏感特征量用于故障诊断。
4.基于(核)聚类的旋转机械故障诊断
提出了EMD-模糊聚类法、基于高阶累积量的AR参数估计-模糊聚类法,滚动轴承故障诊断与性能退化评估实例验证了方法的有效性。
提出了基于双谱分布区域的匹配聚类方法,有效克服了传统基于谱图频率峰值的故障诊断方法容易受混频干扰的不足,滚动轴承与齿轮的故障诊断实例验证了方法的有效性。
提出了两种核聚类方法,重点研究了初始核聚类中心、及进一步核聚类中心的确定方法,实例验证了方法的有效性。
5.基于SVM与多振动信息融合的旋转机械故障诊断
提出了基于SVM的多振动信息融合旋转机械故障诊断方法,多个传感器的单一特征量的SVM融合可实现较高精度的滚动轴承与齿轮的故障诊断。
研究了基于基座的旋转机械故障诊断,SVM对基座多传感器微弱信号执行信息融合,有效实现转子裂纹与滚动轴承的故障诊断。基座传感器安装方式具有通用性,可克服现场传感器安装不便等问题,具有极大的应用推广前景。
Rotating machinery are the key equipments in supporting industry of national economy. It has great economic and social significance to study on the rotating machinery fault diagnosis, for it can ensure a safe, reliable, efficient, long period, full load and quality environment for equipment operation, avoid enormous economic loss and disastrous accident. The process of rotating machinery fault diagnos is a pattern analysis process, and the kernel method represented by Support Vector Machine brought the third revolution of pattern analysis. This method implicit maps original spatial data to feature space through kernel function, seeks for linear relationship in feature space to achieve the efficient solving of nonlinear problem. The rotating machinery faults are usual nonlinear behaviour, and the kernel method is applicable to rotating machinery fault diagnosis and modal analysis especially.
Besides SVM, there are some typica kernel methods such as KPCA, KICA, KC, KFD and so on. This paper expanded around the kernel method and its application on rotating machinery fault diagnosis, the main research contents include:
1. Acquisition and preprocessing of rotating machinery vibration signal aimed kernel method application
It experimented on vibration test of typical rotating machinery faults and collected datas based on Machinery Fault Simulator. Through extracting time domain features, energy, entropy, energy entropy, sequential characteristic and correlation dimension of different frequency bands by wavelet decomposition and empirical mode decomposition, it constituted eleven feature libraries, and provide a data base for applied research of kernel function. According to the deficiency that EMD is easy to produce redundancy IMF, it proposed a improved HHT method. After wavelet packet de-noising, it took correlation coefficients which between each IMF and original signal as the judgment basis, then rejected the redundancy IMF. The fault diagnosis example of rolling bearing shows that this method can extract weak signal fault feature effectively.
2. Optimization of KPCA kernel parameter and research of de-noising method aimed rotating machinery fault diagnos
It revealed the regular patterns of kernel function and kernel parameter on KPCA performance, discovered both gaussian kernel and polynomial kernel, when accumulative ratio above 0.85, the number of kernel principal component decreases with the increase of kernel parameter, and finally takes on convergence status. The KPCA which selected gaussian kernel has a better clustering performance on kernel principal component. It suggests choosing gaussian kernel parameterσ≥25 when conducting KPCA on feature vectors has no prior knowledge.
It proposed a signal de-noising method based on KPCA, which overcomed the deficiency of common de-noising methods such as filter and wavelet de-noising need prior knowledge in practical application. It expanded one-dimensional observed signal as the multi-dimension vector through the phase space reconstruction, then extracted kernel principal component by KPCA to achieve signal de-noising, and the whole process needn't any prior knowledge. It verified the effectiveness of this method by simulation and vibration signal de-noising example of rolling bearing.
3. Fault signal de-noising and feature extraction of rotating machinery based on KICA
It proposed a signal de-noising method based on KICA, this method expanded one-dimensional observed signal as the multi-dimension vector through introducing the adaptation noise component, then executed KICA to implement noise separation, achieved the goal of de-noising. The de-noising process of KICA won't be influenced by signal-to-noise ratio, and the other de-noising methods can't be compared with it. It verified the effectiveness of this method by signal de-noising of unbalanced rotor.
It defined the KIC characteristic quantity of rotating machinery, measured signal analysis showed that KIC can identify the fault of bearing and gear well, and it could be the sensitive characteristic quantity in fault diagnosis.
4. Rotating machinery fault diagnosis based on (kernel) clustering
It proposed a EMD-fuzzy clustering method and a AR-parameter estimation fuzzy clustering method, and verified the effectiveness of these methods by examples of frolling bearing fault diagnosis and evaluate the degree of performance degradation.
It proposed a clustering match method based on the bi-spectrum distribution area, this method can effectively overcomed the deficiency that traditional fault diagnosis methods based on the peak of frequency spectrum are easy interfered by mixing, and verified this method's effectiveness by rolling bearing and gear fault diagnosis examples.
It proposed two kinds of kernel clustering algorithms, and key researched the determination method of initial kernel clustering center and further kernel clustering center, verified the effectiveness of this method by examples.
5. Rotating machinery fault diagnosis based on SVM and multi-vibration information fusion
It proposed a multi-vibration information fusion rotating machinery fault diagnosis method based on SVM, it can achieve high precision rolling bearing and gear fault diagnosis through SVM fusion of single characteristic quantity from multi sensors.
It studied on the rotating machinery fault diagnosis based on base, SVM fused weak signals from base multi-sensors, which effectively achieved the fault diagnosis of rotor crack and rolling bearing. Installing sensor on the base has generality which can overcome some on site questions such as inconvenience of sensor installation, and has a great application prospect.
典型的核方法除支持向量机(SVM),还有核主成分分析(KPCA)、核独立成分分析(KICA)、核聚类(KC)、核Fish判别(KFD)等。论文围绕核方法及其在旋转机械故障诊断中的应用而展开,主要研究内容包括：
1.面向核方法应用的旋转机械振动信号采集与预处理
以机械故障综合模拟实验台为平台,设计了旋转机械典型故障振动测试实验,并采集了数据。提取时域统计特征、小波包分解和经验模态分解所得不同频段的能量、熵和能量熵特征、时序特征、关联维特征,构成11个旋转机械故障特征库,为核方法应用研究提供数据基础。
针对EMD过程中易产生冗余IMF的不足,提出改进HHT方法。小波包去噪后,以EMD所得每个IMF与分解前信号的相关系数作为判断依据,剔除冗余IMF,滚动轴承故障诊断实例表明该方法可有效提取微弱信号故障特征频率。
2.面向旋转机械故障诊断的KPCA核参数优选与消噪方法研究
揭示了核函数及核参数对KPCA性能影响规律,发现无论选用高斯核还是多项式核,累计贡献率大于0.85的核主成分个数均随核参数的增大而递减,最终呈收敛状态；选用高斯核的KPCA,其核主成分具有更好的聚类性能,对没有任何先验知识的特征向量执行KPCA时,建议取高斯核参数σ≥25。
提出了基于KPCA的信号消噪方法,克服滤波、小波消噪等常用消噪方法需要先验知识,给实际应用带来困难的不足。通过相空间重构将一维观测信号扩展为多维向量,再执行KPCA,提取核主成分,实现信号消噪,整个过程无需任何先验知识。仿真与滚动轴承振动信号消噪实例验证了方法的有效。
3.基于KICA的旋转机械故障信号消噪与特征提取
提出了基于KICA的信号消噪方法,通过引入适配噪声分量,将一维观测信号扩展为多维向量,再执行KICA,实现信噪分离,达到消噪目的。KICA消噪过程不受信噪比影响,具有其它消噪方法无法比拟的优势。转子不平衡振动信号的消噪实例验证了方法的有效性。
定义了旋转机械KIC特征量,实测信号分析表明KIC对滚动轴承与齿轮故障均具有有较好的识别性,可作为敏感特征量用于故障诊断。
4.基于(核)聚类的旋转机械故障诊断
提出了EMD-模糊聚类法、基于高阶累积量的AR参数估计-模糊聚类法,滚动轴承故障诊断与性能退化评估实例验证了方法的有效性。
提出了基于双谱分布区域的匹配聚类方法,有效克服了传统基于谱图频率峰值的故障诊断方法容易受混频干扰的不足,滚动轴承与齿轮的故障诊断实例验证了方法的有效性。
提出了两种核聚类方法,重点研究了初始核聚类中心、及进一步核聚类中心的确定方法,实例验证了方法的有效性。
5.基于SVM与多振动信息融合的旋转机械故障诊断
提出了基于SVM的多振动信息融合旋转机械故障诊断方法,多个传感器的单一特征量的SVM融合可实现较高精度的滚动轴承与齿轮的故障诊断。
研究了基于基座的旋转机械故障诊断,SVM对基座多传感器微弱信号执行信息融合,有效实现转子裂纹与滚动轴承的故障诊断。基座传感器安装方式具有通用性,可克服现场传感器安装不便等问题,具有极大的应用推广前景。
Rotating machinery are the key equipments in supporting industry of national economy. It has great economic and social significance to study on the rotating machinery fault diagnosis, for it can ensure a safe, reliable, efficient, long period, full load and quality environment for equipment operation, avoid enormous economic loss and disastrous accident. The process of rotating machinery fault diagnos is a pattern analysis process, and the kernel method represented by Support Vector Machine brought the third revolution of pattern analysis. This method implicit maps original spatial data to feature space through kernel function, seeks for linear relationship in feature space to achieve the efficient solving of nonlinear problem. The rotating machinery faults are usual nonlinear behaviour, and the kernel method is applicable to rotating machinery fault diagnosis and modal analysis especially.
Besides SVM, there are some typica kernel methods such as KPCA, KICA, KC, KFD and so on. This paper expanded around the kernel method and its application on rotating machinery fault diagnosis, the main research contents include:
1. Acquisition and preprocessing of rotating machinery vibration signal aimed kernel method application
It experimented on vibration test of typical rotating machinery faults and collected datas based on Machinery Fault Simulator. Through extracting time domain features, energy, entropy, energy entropy, sequential characteristic and correlation dimension of different frequency bands by wavelet decomposition and empirical mode decomposition, it constituted eleven feature libraries, and provide a data base for applied research of kernel function. According to the deficiency that EMD is easy to produce redundancy IMF, it proposed a improved HHT method. After wavelet packet de-noising, it took correlation coefficients which between each IMF and original signal as the judgment basis, then rejected the redundancy IMF. The fault diagnosis example of rolling bearing shows that this method can extract weak signal fault feature effectively.
2. Optimization of KPCA kernel parameter and research of de-noising method aimed rotating machinery fault diagnos
It revealed the regular patterns of kernel function and kernel parameter on KPCA performance, discovered both gaussian kernel and polynomial kernel, when accumulative ratio above 0.85, the number of kernel principal component decreases with the increase of kernel parameter, and finally takes on convergence status. The KPCA which selected gaussian kernel has a better clustering performance on kernel principal component. It suggests choosing gaussian kernel parameterσ≥25 when conducting KPCA on feature vectors has no prior knowledge.
It proposed a signal de-noising method based on KPCA, which overcomed the deficiency of common de-noising methods such as filter and wavelet de-noising need prior knowledge in practical application. It expanded one-dimensional observed signal as the multi-dimension vector through the phase space reconstruction, then extracted kernel principal component by KPCA to achieve signal de-noising, and the whole process needn't any prior knowledge. It verified the effectiveness of this method by simulation and vibration signal de-noising example of rolling bearing.
3. Fault signal de-noising and feature extraction of rotating machinery based on KICA
It proposed a signal de-noising method based on KICA, this method expanded one-dimensional observed signal as the multi-dimension vector through introducing the adaptation noise component, then executed KICA to implement noise separation, achieved the goal of de-noising. The de-noising process of KICA won't be influenced by signal-to-noise ratio, and the other de-noising methods can't be compared with it. It verified the effectiveness of this method by signal de-noising of unbalanced rotor.
It defined the KIC characteristic quantity of rotating machinery, measured signal analysis showed that KIC can identify the fault of bearing and gear well, and it could be the sensitive characteristic quantity in fault diagnosis.
4. Rotating machinery fault diagnosis based on (kernel) clustering
It proposed a EMD-fuzzy clustering method and a AR-parameter estimation fuzzy clustering method, and verified the effectiveness of these methods by examples of frolling bearing fault diagnosis and evaluate the degree of performance degradation.
It proposed a clustering match method based on the bi-spectrum distribution area, this method can effectively overcomed the deficiency that traditional fault diagnosis methods based on the peak of frequency spectrum are easy interfered by mixing, and verified this method's effectiveness by rolling bearing and gear fault diagnosis examples.
It proposed two kinds of kernel clustering algorithms, and key researched the determination method of initial kernel clustering center and further kernel clustering center, verified the effectiveness of this method by examples.
5. Rotating machinery fault diagnosis based on SVM and multi-vibration information fusion
It proposed a multi-vibration information fusion rotating machinery fault diagnosis method based on SVM, it can achieve high precision rolling bearing and gear fault diagnosis through SVM fusion of single characteristic quantity from multi sensors.
It studied on the rotating machinery fault diagnosis based on base, SVM fused weak signals from base multi-sensors, which effectively achieved the fault diagnosis of rotor crack and rolling bearing. Installing sensor on the base has generality which can overcome some on site questions such as inconvenience of sensor installation, and has a great application prospect.
引文
[1].韩捷,张瑞林.旋转机械故障机理及诊断技术[M].北京：机械工业出版社,1997.
[2].赵玉成,陈荣华,马占国.旋转机械动力辨识与故障诊断技术[M].徐州：中国矿业大学出版社,2008.
[3].李力.机械信号处理及其应用[M].武汉：华中科技大学出版社,2007.
[4]. Lei Y G, He Z J, Zi Y Y, et al. New clustering algorithm-based fault diagnosis using compensation distance evaluation technique[J]. Mechanical Systems and Signal Process,2008,22(2):419-435.
[5]. Yang J Y, Zhang Y Y, Zhu Yongsheng, et al. Intelligent fault diagnosis of rolling element bearing based on svms and statistical characteristics[C]. Proceedings of the 2007 International Manufacturing Science and Engineering Conference, Ocotber 15-17,2007, Atlanta,Georgia,US A.
[6].向玲,朱永利,唐贵基.HHT方法在转子振动故障诊断中的应用[J].中国电机工程学报,2007(35)：84-89.
[7].马孝江,王凤利,蔡悦等.局域波时频分布在转子系统早期故障诊断中的应用研究[J].中国电机工程学报,2004(03)：161-164,168.
[8].张辉,王淑娟,张青森等,基于小波包变换的滚动轴承故障诊断方法的研究[J].振动与冲击,2004,23(04)：127-130.
[9].冯志鹏,刘力,张文明等.基于小波时频框架分解方法的滚动轴承故障诊断[J].振动与冲击,2008，27(02)：110-114
[10].万书亭,吕路勇,何玉灵.基于提升模式非抽样小波变换的滚动轴承故障诊断方法研究[J].振动与冲击,2009,28(01)：170-173.
[11].段晨东,郭研.基于提升小波包变换的滚动轴承包络分析诊断方法[J].农业机械学报,2008,39(05)：192-196.
[12]. Sheen Y T. On the study of applying Morlet wavelet to the Hilbert transform for the envelope detection of bearing vibrations [J]. Mechanical Systems and Signal Processing,2009,23(5):1518-1527.
[13].丁夏完,刘葆,刘金朝等.基于自适应STFT的货车滚动轴承故障诊断[J].中国铁道科学,2005,26(06)：24-27.
[14].孙晖,赵菁,朱善安.基于切片双谱分析的滚动轴承故障识别研究[J].浙江大学学报(工学版),2005,39(06)：826-829.
[15].李军伟,赵箐,朱善安.小波变换域双谱分析及其在滚动轴承故障诊断中的应用[J].振动与冲击,2006,39(05)：826-829.
[16].曹冲锋,杨世锡,杨将新等.基于双谱特征量的滚动轴承损伤部位识别[J].农业机械学报,2007,38(09)：179-182
[17]. Yu D J, Cheng J S, Yang Y. Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings[J]. Mechanical Systems and Signal Processing,2005,19(2):259-270.
[18].杨宇,于德介,程军圣.基于Hilbert边际谱的滚动轴承故障诊断方法[J].振动与冲击,2005,24(01)：
[19].康海英,栾军英,郑海起等.基于阶次跟踪和经验模态分解的滚动轴承包络解调分析[J].机械工程学报,2007,43(08)：119-122
[20]. Rai V K, Mohanty A R. Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert-Huang transform[J]. Mechanical Systems and Signal Processing,2007,21(6):2607-2615
[21].熊良才,史铁林,杨叔子.基于双谱分析的齿轮故障诊断研究[J].华中科技大学学报,2001,29(11)：4-5.
[22].张桂才,史铁林,杨叔子.基于高阶统计量的机械故障特征提取方法研究[J].华中理工大学学报,1999,27(3)：6-8.
[23].李友荣,曾法力,吕勇等.小波包分析在齿轮故障诊断中的应用[J].振动与冲击,2005,24(05)：101-103.
[24].成琼,于德介.基于复小波变换相位功率谱的齿轮故障诊断[J].湖南大学学报(自然科学版),2001,28(3)：23-26
[25].于德介,程军圣.EMD方法在齿轮故障诊断中的应用[J].湖南大学学报(自然科学版),2002,29(6)：48-51.
[26].陈忠,郑时雄.基于经验模式分解(EMD)的齿轮箱齿轮故障诊断技术研究[J].振动工程学报,2003,16(02)：229-232.
[27].郑海波,陈心昭,李志远.基追踪降噪及在齿轮故障诊断中的应用[J].振动、测试与诊断,2003,23(02)：128-130.
[28].来五星,轩建平,史铁林等Wigner-Ville时频分布研究及其在齿轮故障诊断中的应用[J].振动工程学报,2003,16(02)：247-250.
[29].康海英,栾军英,郑海起等.基于阶次跟踪和经验模式分解的齿轮故障诊断[J].上海交通大学学报,2007,41(09)：1529-1532
[30].康海英,栾军英,郑海起等,基于阶次跟踪与伪魏格纳分布的齿轮故障诊断[J].振动、测试与诊断,2007,27(03)：196-198.
[31].程军圣,杨宇,于德介.局部均值分解方法及其在齿轮故障诊断中的应用[J].振动工程学报,2009,22(01)：76-83.
[32].鞠萍华,秦树人,秦毅等.多分辨EMD方法与频域平均在齿轮早期故障诊断中的研究[J].振动与冲击,2009,28(05)：97-101
[33].方泽南,傅尚新,张勇.时间序列在故障诊断中的应用[J].清华大学学报,1998,38(9)：123-126.
[34].程军圣,于德介,杨宇.一种基于Hilbert-Huang变换和AR模型的滚动轴承故障诊断方法[J].系统工程理论与实践,2004,(10)：92-109.
[35].于德介,程军圣,杨宇.基于EMD和AR模型的滚动轴承故障诊断方法[J].振动工程学报,2004,17(3)：332-335.
[36].李志农,何永勇,吴昭同ARMA模型盲辨识仿真研究及其在机械故障诊断中的应用[J].振动与冲击,2006,25(1)：122-125.
[37].蒋东翔,黄文虎,徐世昌.分形几何及其在旋转机械故障诊断中的应用[J].哈尔滨工业大学学报,1996,28(02)：27-31.
[38].刘占生,刘成敏,刘树春等.小波分析和分形几何在转子动静碰摩故障诊断中的应用[J].哈尔滨工业大学学报,1999,31(1)：55-56,92.
[39].訾艳阳,何正嘉,张周锁.小波分形技术及其在非平稳故障诊断中的应用[J],西安交通大学学报,2000,34(9)：82-87.
[40].侯祥林,李永强,虞和济.非线性机械设备系统的分形神经网络诊断方法[J].振动工程学报,2001,14(2)：220-223.
[41].彭志科,何永勇,卢青等.小波多重分形及其在振动信号分析中应用的研究[J].机械工程学报,2002,38(8)：59-63.
[42].徐玉秀,侯荣涛,杨文平.广义分形维数在旋转机械故障诊断中的应用研究[J].中国机械工程,2003,14(21)：1812-1814.
[43].胥永刚,何正嘉.分形维数和近似熵用于度量信号复杂性的比较研究[J].振动与冲击,2003,22(3)：25-27,5
[44].王凤利,马孝江.局域波分形动力学在旋转机械故障诊断中的应用[J].农业机械学报,2004,35(2)：134-134,141.
[45].程军圣,于德介,杨宇.基于EMD和分形维数的转子系统故障诊断[J].中国机械工程,2005,16(12)：1088-1091.
[46].肖涵,李友荣,吕勇.四分位偏差分形维及其在齿轮故障识别中的应用[J].振动与冲击,2006,25(6)：108-110.
[47].李永强,刘杰.分形维数在大型旋转机械故障诊断中的应用[J].应用力学学报,2007,24(2)：302-305.
[48].李兵,张培林,任国全等.基于数学形态学的分形维数计算及在轴承故障诊断中的应用[J].振动与冲击,2010,29(5)：191-193.
[49]. Jackson J E, A user's guide to principal components[M]. New York:John Wiley,1991.
[50].潘明清,周晓军,吴瑞明.基于主元分析的支持向量数据描述机械故障诊断[J].传感技术学报,2006,19(1)：128-131.
[51].彭红星,陈祥光,徐巍.PCA特征抽取与SVM多类分类在传感器故障诊断中的应用[J].数据采集与处理,2010,25(1)：111-116.
[52].徐洪涛,王跃钢.基于相空间重构和主分量分析的遥测信号噪声消除[J].计算机应用,2010,30(3)：793-795.
[53]. Jutten C, Heranlt J. Independent component analysis versus PCA[C]. In: Proceeding of European Signal Processing Conf.1988,287-314.
[54]. Bell A J, Sejnowski T J. An information-maximization approach to blind separation and blind deconvolution[J]. Neural computation,1995, (7):1129-1159.
[55]. Widodo A, Yang B S, Han T. Combination of independent component analysis and support vector machines for intelligent faults diagnosis of induction motors[J]. Expert Syst. Appl.,2007,32(2):299-312.
[56].郭明,王树青.基于独立分量分析的系统性能监控方法研究[J].浙江大学学报(工学版),2004,538(6)：665-669.
[57].杨世锡,焦卫东,吴昭同.独立分量分析基网络应用于旋转机械故障特征提取与分类[J].机械工程学报,2004,40(3)：45-48.
[58].焦卫东,杨世锡,吴昭同.基于独立分量分析的噪声消除技术研究[J].浙江大学学报(工学版),2004,38(7)：872-876.
[59].夏文静,傅行军.基于ICA在强背景噪声振动信号中的去噪研究[J].汽轮机技术,2006,48(02)：121-124.
[60].黄晋英,毕世华,潘宏侠等.独立分量分析在齿轮箱故障诊断中的应用[J].振动、测试与诊断,2008,28(2)：126-130.
[61].吴慧英,帅仁俊.汽轮发电机组转子振动故障的模糊聚类分析[J].上海交通大学学报,1999,33(08)：1051-1054.
[62].陈铁华,陈启卷.模糊聚类分析在水电机组振动故障诊断中的应用[J].中国电机工程学报,2002,22(03)：43-46.
[63].李如强,陈进,伍星.基于奇异值分解、模糊聚类和粗糙集理论的旋转机械故障诊断[J].振动与冲击,2005,24(04)：46-49.
[64].刘晓波,黄其柏.基于动态核聚类分析的水轮机组故障模式识别[J].华中科技大学学报(自然科学版),2005,33(09)：47-52.
[65].尹安东,赵韩,羊拯民.基于小波变换一模糊聚类的变速箱齿轮故障诊断[J].中国机械工程,2006,17(20)：2121-2125.
[66].崔宝珍,王泽兵,潘宏侠.小波分析-模糊聚类法用于滚动轴承故障诊断[J].振动、测试与诊断,2008,28(02)：151-154.
[67].周川,伍星,刘畅等.基于EMD和模糊C均值聚类的滚动轴承故障诊断[J].昆明理工大学学报(理工版),2009,34(06)：34-39.
[68].田景文,高美娟.人工神经网络算法研究及应用[M].北京理工大学出版社,2006.
[69]. Venkatasubramanian V, Chan K. A neural network methodology for process fault diagnosis[J]. Journal of American Institute of Chemical Engineers,1989,35(12):1993-2002.
[70]. Hoskins J C, Kaliyur K M, David M Himmelblau. Fault diagnosis in complete chemical plants using artificial neural networks[J]. Journal of American Institute of Chemical Engineers,1991,37(1):137-141.
[71]. Kajiro, Watanabe. Incipient fault diagnosis of chemical processes via artificial neural networks[J]. Journal of American Institute of Chemical Engineers,1989,3(11):1803-1812
[72]. Kajiro, Watanabe. Diagnosis of multiple simultaneous fault via hierarchical artificial neural networks[J]. Journal of American Institute of Chemical Engineers,1994,40(5):839-848.
[73].张炜,张优云,战仁军等.旋转机械故障诊断中的神经网络改进算法研究[J].振动工程学报,1996,9(1)：31-37.
[74].许飞云,贾民平,钟秉林.旋转机械振动故障诊断的一种模糊神经网络方法研究[J].振动工程学报,1996,9(3)：213-219.
[75].陈长征,张省,虞和济.基于神经网络的旋转机械故障诊断研究[J].机械强度,2000,22(02)：104-112
[76].栗青,陈长征.集成神经网络在旋转机械故障诊断中的应用[J].沈阳工业大学学报,2001,23(4)：339-341.
[77].盛昭瀚,李春雨.小波神经网络及其在旋转机械轴心轨迹识别中的应用[J].系统工程理论与实践,1998(10)：98-103.
[78].万书亭,李和明,李永刚.自适应神经网络在发电机组故障诊断中的应用[J].华北电力大学学报,2002,29(2)：339-341.
[79].冯志鹏,宋希庚,薛冬新.基于广义粗糙集与神经网络集成的旋转机械故障诊断研究[J].机械科学与技术,2003,22(05)：815-820
[80].张利平,王铁生,索丽生.改进的BP网络在汽轮发电机组故障诊断中的应用[J].河海大学学报(自然科学版),2003,31(2)：233-236.
[81].朱大奇,陈尔奎.旋转机械故障诊断的量子神经网络算法[J].中国电机工程学报,2006,26(01)：132-136.
[82].周鹏,秦树人.基于切片谱RBF神经网络的旋转机械故障诊断[J].中国机械工程,2008,19(12)：1488-1491.
[83].毕云龙,回转设备转子故障诊断专家系统的初步研究[J].机械强度,1989,11(03)：7-11.
[84].赵美德,黄文虎,夏松波等.大型旋转机械故障诊断专家系统ETHYLENE的理论研究[J].振动工程学报,1992,5(02)：105-112.
[85].韩秋实,许宝杰,王红军等.旋转机械故障诊断监测专家系统中的时间序列模式识别技术研究[J].机械工程学报,2002,38(03)：104-107.
[86].刘贵立,王立鹏与张国英,基于Alopex神经网络的旋转机械故障诊断专家系统[J].振动、测试与诊断,2004,24(01)：61-64.
[87].黄开启,黄跃飞,刘晓波.多征兆模糊诊断知识表示及专家系统的研究[J].中国机械工程,2004,15(12).
[88].郑小霞,钱锋.模糊神经网络推理的实时故障诊断专家系统[J].计算机工程与应用,2006,03：226-229.
[89].窦东阳,赵英凯.基于优先级诊断树的旋转机械故障诊断专家系统[J].中国电机工程学报,2008,28(32)：81-88.
[90]. Scholkopf B. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation,1998,10(5):1229-1319.
[91].Mika S, Ratsch G, Weston J, et al. Fisher discriminant analysis with kernels[J]. Neural Networks for Signal Processing Ⅸ, IEEE,1999:41-48.
[92].白鹏,张喜斌,张斌等.支持向量机理论及工程应用实例[M].西安：西安电子科技大学出版社,2008.
[93]. Nello C, John S T. An Introduction to Support Vector Machine and Othe Kernel-based Learning Methods[M], Cambridge University Press,2000.
[94]. Poyhonen S, Negrea M, Arkkio A, etc. Support vector classi-fication for fault diagnostics of an electrical machine [C].Proc. of International Conference on Signal Proceeding(IC-SP'02), Beijing China, August26—30,2002.
[95].张周锁,李凌均,何正嘉.基于支持向量机的机械故障诊断方法研究[J].西安交通大学学报,2002,36(12)：1303-1306.
[96].李凌均,张周锁,何正嘉.支持向量机在机械故障诊断中的应用研究[J].计算机工程与应用,2002,19-21.
[97].何学文,赵海鸣,支持向量机及其在机械故障诊断中的应用[J].中南大学学报(自然科学版),2005,36(01)：97-101.
[98].翟永杰,毛继珮,于丽敏等.分级聚类支持向量机在汽轮机故障诊断中的应用[J].华北电力大学学报,2003,30(06)：25-29
[99].于德介,杨宇,程军圣.一种基于SVM和EMD的齿轮故障诊断方法[J].机械工程学报,2005,41(1)：140-144.
[100].程军圣,于德介,杨宇.基于SVM和EMD包络谱的滚动轴承故障诊断方法[J].系统工程理论与实践,2005,(09)：131-136.
[101].柳新民,刘冠军,邱静等.一种改进的无监督学习SVM及其在故障识别中的应用[J].机械工程学报,2006,42(04)：107-111.
[102].柳新民,刘冠军,邱静.基于HMM-SVM的故障诊断模型及应用[J].仪器仪表学报,2006,27(01)：45-48,53.
[103].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(02)：238-241.
[104]. Yuan S F, Chu F L. Support vector machines-based fault diagnosis for turbo-pump rotor[J]. Mechanical Systems and Signal Processing,2006,20:939-952.
[105].袁胜发,褚福磊.基于引力球结构支持向量机多类算法的涡轮泵故障诊断[J].宇航学报,2006,27(04)：635-639.
[106].彭文季,郭鹏程,罗兴绮.基于最小二乘支持向量机和信息融合技术的水电机组振动故障诊断研究[J].水力发电学报,2007,26(06)：137-142.
[107]. Zhang L, Nandi A K. Fault classification using genetic programming[J].Mechanical Systems and Signal Processing,2007,21:1273-1284.
[108]. Widodo A, Yang B S. Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motors[J], Expert Systems with Applications,2007,33:241-250.
[109]. Widodo A, Yang B S. Wavelet support vector machine for induction machine fault diagnosis based on transient current signal[J],2008,35:307-316.
[110]. Saravanan N, Kumar S V N S, Ramachandran K L. Expert Systems with Applications,2008,35(3):1351-1366.
[111]. Xian G M, Zeng B Q. An intelligent fault diagnosis method based on wavelet packer analysis and hybrid support vector machines[J].Expert Systems with Application,2009,36(10):12131-12136.
[112].邱绵浩,王自营,安钢等,基于核主元分析与纠错输出编码SVM的齿轮故障诊断[J].振动与冲击,2009,28(05)：1-5
[113].何学文.基于支持向量机的故障智能诊断理论与方法研究：[博士学位论文].长沙：中南大学,2004.
[114].翟永杰.基于支持向量机的故障智能诊断方法研究：[博士学位论文].河北：华北电力大学,2004.
[115].张超.基于支持向量机的汽轮机轴系振动故障智能诊断研究：[博士学位论文].河北：华北电力大学,2009.
[116].杨宇,基于EMD和支持向量机的旋转机械故障诊断方法研究：[博士学位论文].长沙：湖南大学,2005.
[117].邹敏.基于支持向量机的水电机组故障诊断研：[博士学位论文].华中科技大学,2007
[118].彭兵,基于改进支持向量机和特征信息融合的水电机组故障诊断：[博士学位论文].华中科技大学,2008.
[119].张莉,周伟达,焦李成.核聚类算法[J].计算机学报,2002,25(6)：587-590.
[120].孔锐,张国宣,施泽生.基于核的K-均值聚类[J].计算机工程,2004,30(11)：12-13,80.
[121].伍忠东,高新波,谢维信.基于核方法的模糊聚类算法[J].西安电子科技大学学报,2004,31(4)：533-537.
[122]. Daniel G, Witold P. Kernel-based fuzzy clustering and fuzzy clustering: A comparative experimental study[J]. Fuzzy Sets and Systems,2010, 161(4):Pages 522-543.
[123].潘庆丰,陈水利,陈国龙.基于核函数的模糊C均值聚类算法[J].集美大学学报,2006,11(4)：369-374.
[124].赵犁丰,李新,王栋.多核模糊聚类算法的研究[J].中国海洋大学学报,2009,39(5)：1047-1050
[125].李颖,李传龙,马龙等.动态加权模糊核聚类算法[J].计算机工程与设计,2009,30(24)：5584-5587.
[126].李巍华,廖广兰,史铁林.核函数主元分析及其在齿轮故障诊断中的应用[J].机械工程学报,2003,39(8)：65-70.
[127].邓晓刚,田学民.一种基于KPCA的非线性故障诊断方法[J].山东大学学报(工学版),2005,35(3)：103～106.
[128]. Cho J H, Lee J M, Choi S W. Fault identification for process monitoring using kernel principal component analysis[J]. Chemical Engineering Science,2005,60(1):279-288.
[129].郭磊,陈进,朱义等.基于小波函数的核主元特征约简方法研究[J].振动工程学报,2009,22(3)：287-291.
[130]. Ding M T, Zheng T, Xu H X. Adaptive kernel principal component analysis[J]. Signal Processing,2010,90(5):1542-1553.
[131].王新峰,邱静,刘冠军.核主元分析中核函数参数优选方法研究[J].振动、测试与诊断,2007,27(1)：62-64.
[132].魏秀业,潘宏侠,王福杰.基于粒子群优化的核主元分析特征的提取技术[J].振动、测试与诊断,2009,29(2)：162-166.
[133]. Francis R B, Michael I J.Kernel independent component analysis[J]. Journal of Machine Learning Research,2002, (3):1-48.
[134].田昊,唐力伟,田广.基于核独立分量分析的齿轮箱故障诊断[J].振动与冲击,2009,28(5)：163-164,191.
[135]. 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 & Engineering Sciences,1998,454:903-995.
[136]. Yan R Q, Gao R X. Hilbert-Huang transform-based vibration signal analysis for machine health monitoring [J]. IEEE Transactions on Instrumentation and Measurement,2006,55(6):2320-2329.
[137].于德介,程军圣,杨宇.Hilbert-Huang变换在滚动轴承故障诊断中的应用[J].中国机械工程,2003,14(24)：2140～2142.
[138].李常有,徐敏强,郭嵩.基于改进的Hilbert-Huang变换的滚动轴承故障诊断[J].振动与冲击,2007,26(4)：39～41,50.
[139]. Chen H X, Chua P S K, Lim G H. Fault degradation assessment of water hydraulic motor by impulse vibration signal with Wavelet Packet Analysis and Kolmogorov-Smirnov Test[J]. Mechanical Systems and Signal Processing,2008,22(7):1670-1684.
[140]. Hu Q, He Z J, Zhang Z S, et al. Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble[J]. Mechanical Systems and Signal Processing,2007,21(2):688-705.
[141]. Nedjah O, Hussein A M, Krishnan S, Sotudeh R. Comparative study of adaptive techniques for denoising CN Tower lightning current derivative signals[J]. Digital Signal Processing,2010,20(2):607-618.
[142]. Huang J J, Ning L V, Li S Q, et al. Feature Selection for Classificatory Analysis Based on Information-theoretic Criteria[J]. Acta Automatica Sinica,2008,34(3):383-392
[143].陆振波,蔡志明,姜可宇.基于改进的C-C方法的相空间重构参数选择[J].系统仿真学报,2007,19(11)：2527-2538
[144].吕金虎,陆君安,陈士华.混沌时间序列分析及其应用[M].湖北：武汉大学出版社,2002.
[145]. Luis B A. Linear and nonlinear ICA based on mutual information—the MISEP method[J]. Signal Processing,2004,84(2):231-245.
[146]. Peter G, Anke M, Simon F, et al. ICA, kernel methods and nonnegativity: New paradigms for dynamical component analysis of fMRI data[J]. Engineering Applications of Artificial Intelligence,2009, 22(4-5):497-504.
[147]. Hyvarinen A. Survey on independent component analysis[J]. Neural Computing Surveys,1999,(2):94-128.
[148]. Cheng J S, Yu D J, Yang Y. A fault diagnosis approach for roller bearings based on EMD method and AR model[J]. Mechanical Systems and Signal Processing,20(2006):350-362.
[149]. Daniel G, Witold P. Kernel-based fuzzy clustering and fuzzy clustering: A comparative experimental study[J]. Fuzzy Sets and Systems, 2010,61(4):522-543
[150]. Mac Q J. Some methods for classification and analysis of multivariate observations[J]. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability,1965:1-12.
[151].齐敏,李大健,郝重阳等.模式识别导论[M].北京：清华大学出版社,2009.
[152]. Mark G. Mercer kernel-based clustering in feature space[J]. IEEE Transactions on Neural Networks,2002,13(3):780-784.
[153]. Boser B, Guyon I, Vapnik V N. A training algorithm for optimal margin classifiers[C]. Fifth Annual Workshop on Computational Learning Theory, Pittsburgh ACM:144～152.
[154]. Hsu C, Chang C C, Lin C J. A practical guide to support vector classification[EB/OL]. [2009-05-19]. http://www.csie.ntu.edu.tw/～cjlin,
[155]. Hsu C, Lin C J. A comparison of methods for multi-class support vector machines[J]. IEEE Transactions on Neural Networks, 2002,13(2):415-425.
[2].赵玉成,陈荣华,马占国.旋转机械动力辨识与故障诊断技术[M].徐州：中国矿业大学出版社,2008.
[3].李力.机械信号处理及其应用[M].武汉：华中科技大学出版社,2007.
[4]. Lei Y G, He Z J, Zi Y Y, et al. New clustering algorithm-based fault diagnosis using compensation distance evaluation technique[J]. Mechanical Systems and Signal Process,2008,22(2):419-435.
[5]. Yang J Y, Zhang Y Y, Zhu Yongsheng, et al. Intelligent fault diagnosis of rolling element bearing based on svms and statistical characteristics[C]. Proceedings of the 2007 International Manufacturing Science and Engineering Conference, Ocotber 15-17,2007, Atlanta,Georgia,US A.
[6].向玲,朱永利,唐贵基.HHT方法在转子振动故障诊断中的应用[J].中国电机工程学报,2007(35)：84-89.
[7].马孝江,王凤利,蔡悦等.局域波时频分布在转子系统早期故障诊断中的应用研究[J].中国电机工程学报,2004(03)：161-164,168.
[8].张辉,王淑娟,张青森等,基于小波包变换的滚动轴承故障诊断方法的研究[J].振动与冲击,2004,23(04)：127-130.
[9].冯志鹏,刘力,张文明等.基于小波时频框架分解方法的滚动轴承故障诊断[J].振动与冲击,2008，27(02)：110-114
[10].万书亭,吕路勇,何玉灵.基于提升模式非抽样小波变换的滚动轴承故障诊断方法研究[J].振动与冲击,2009,28(01)：170-173.
[11].段晨东,郭研.基于提升小波包变换的滚动轴承包络分析诊断方法[J].农业机械学报,2008,39(05)：192-196.
[12]. Sheen Y T. On the study of applying Morlet wavelet to the Hilbert transform for the envelope detection of bearing vibrations [J]. Mechanical Systems and Signal Processing,2009,23(5):1518-1527.
[13].丁夏完,刘葆,刘金朝等.基于自适应STFT的货车滚动轴承故障诊断[J].中国铁道科学,2005,26(06)：24-27.
[14].孙晖,赵菁,朱善安.基于切片双谱分析的滚动轴承故障识别研究[J].浙江大学学报(工学版),2005,39(06)：826-829.
[15].李军伟,赵箐,朱善安.小波变换域双谱分析及其在滚动轴承故障诊断中的应用[J].振动与冲击,2006,39(05)：826-829.
[16].曹冲锋,杨世锡,杨将新等.基于双谱特征量的滚动轴承损伤部位识别[J].农业机械学报,2007,38(09)：179-182
[17]. Yu D J, Cheng J S, Yang Y. Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings[J]. Mechanical Systems and Signal Processing,2005,19(2):259-270.
[18].杨宇,于德介,程军圣.基于Hilbert边际谱的滚动轴承故障诊断方法[J].振动与冲击,2005,24(01)：
[19].康海英,栾军英,郑海起等.基于阶次跟踪和经验模态分解的滚动轴承包络解调分析[J].机械工程学报,2007,43(08)：119-122
[20]. Rai V K, Mohanty A R. Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert-Huang transform[J]. Mechanical Systems and Signal Processing,2007,21(6):2607-2615
[21].熊良才,史铁林,杨叔子.基于双谱分析的齿轮故障诊断研究[J].华中科技大学学报,2001,29(11)：4-5.
[22].张桂才,史铁林,杨叔子.基于高阶统计量的机械故障特征提取方法研究[J].华中理工大学学报,1999,27(3)：6-8.
[23].李友荣,曾法力,吕勇等.小波包分析在齿轮故障诊断中的应用[J].振动与冲击,2005,24(05)：101-103.
[24].成琼,于德介.基于复小波变换相位功率谱的齿轮故障诊断[J].湖南大学学报(自然科学版),2001,28(3)：23-26
[25].于德介,程军圣.EMD方法在齿轮故障诊断中的应用[J].湖南大学学报(自然科学版),2002,29(6)：48-51.
[26].陈忠,郑时雄.基于经验模式分解(EMD)的齿轮箱齿轮故障诊断技术研究[J].振动工程学报,2003,16(02)：229-232.
[27].郑海波,陈心昭,李志远.基追踪降噪及在齿轮故障诊断中的应用[J].振动、测试与诊断,2003,23(02)：128-130.
[28].来五星,轩建平,史铁林等Wigner-Ville时频分布研究及其在齿轮故障诊断中的应用[J].振动工程学报,2003,16(02)：247-250.
[29].康海英,栾军英,郑海起等.基于阶次跟踪和经验模式分解的齿轮故障诊断[J].上海交通大学学报,2007,41(09)：1529-1532
[30].康海英,栾军英,郑海起等,基于阶次跟踪与伪魏格纳分布的齿轮故障诊断[J].振动、测试与诊断,2007,27(03)：196-198.
[31].程军圣,杨宇,于德介.局部均值分解方法及其在齿轮故障诊断中的应用[J].振动工程学报,2009,22(01)：76-83.
[32].鞠萍华,秦树人,秦毅等.多分辨EMD方法与频域平均在齿轮早期故障诊断中的研究[J].振动与冲击,2009,28(05)：97-101
[33].方泽南,傅尚新,张勇.时间序列在故障诊断中的应用[J].清华大学学报,1998,38(9)：123-126.
[34].程军圣,于德介,杨宇.一种基于Hilbert-Huang变换和AR模型的滚动轴承故障诊断方法[J].系统工程理论与实践,2004,(10)：92-109.
[35].于德介,程军圣,杨宇.基于EMD和AR模型的滚动轴承故障诊断方法[J].振动工程学报,2004,17(3)：332-335.
[36].李志农,何永勇,吴昭同ARMA模型盲辨识仿真研究及其在机械故障诊断中的应用[J].振动与冲击,2006,25(1)：122-125.
[37].蒋东翔,黄文虎,徐世昌.分形几何及其在旋转机械故障诊断中的应用[J].哈尔滨工业大学学报,1996,28(02)：27-31.
[38].刘占生,刘成敏,刘树春等.小波分析和分形几何在转子动静碰摩故障诊断中的应用[J].哈尔滨工业大学学报,1999,31(1)：55-56,92.
[39].訾艳阳,何正嘉,张周锁.小波分形技术及其在非平稳故障诊断中的应用[J],西安交通大学学报,2000,34(9)：82-87.
[40].侯祥林,李永强,虞和济.非线性机械设备系统的分形神经网络诊断方法[J].振动工程学报,2001,14(2)：220-223.
[41].彭志科,何永勇,卢青等.小波多重分形及其在振动信号分析中应用的研究[J].机械工程学报,2002,38(8)：59-63.
[42].徐玉秀,侯荣涛,杨文平.广义分形维数在旋转机械故障诊断中的应用研究[J].中国机械工程,2003,14(21)：1812-1814.
[43].胥永刚,何正嘉.分形维数和近似熵用于度量信号复杂性的比较研究[J].振动与冲击,2003,22(3)：25-27,5
[44].王凤利,马孝江.局域波分形动力学在旋转机械故障诊断中的应用[J].农业机械学报,2004,35(2)：134-134,141.
[45].程军圣,于德介,杨宇.基于EMD和分形维数的转子系统故障诊断[J].中国机械工程,2005,16(12)：1088-1091.
[46].肖涵,李友荣,吕勇.四分位偏差分形维及其在齿轮故障识别中的应用[J].振动与冲击,2006,25(6)：108-110.
[47].李永强,刘杰.分形维数在大型旋转机械故障诊断中的应用[J].应用力学学报,2007,24(2)：302-305.
[48].李兵,张培林,任国全等.基于数学形态学的分形维数计算及在轴承故障诊断中的应用[J].振动与冲击,2010,29(5)：191-193.
[49]. Jackson J E, A user's guide to principal components[M]. New York:John Wiley,1991.
[50].潘明清,周晓军,吴瑞明.基于主元分析的支持向量数据描述机械故障诊断[J].传感技术学报,2006,19(1)：128-131.
[51].彭红星,陈祥光,徐巍.PCA特征抽取与SVM多类分类在传感器故障诊断中的应用[J].数据采集与处理,2010,25(1)：111-116.
[52].徐洪涛,王跃钢.基于相空间重构和主分量分析的遥测信号噪声消除[J].计算机应用,2010,30(3)：793-795.
[53]. Jutten C, Heranlt J. Independent component analysis versus PCA[C]. In: Proceeding of European Signal Processing Conf.1988,287-314.
[54]. Bell A J, Sejnowski T J. An information-maximization approach to blind separation and blind deconvolution[J]. Neural computation,1995, (7):1129-1159.
[55]. Widodo A, Yang B S, Han T. Combination of independent component analysis and support vector machines for intelligent faults diagnosis of induction motors[J]. Expert Syst. Appl.,2007,32(2):299-312.
[56].郭明,王树青.基于独立分量分析的系统性能监控方法研究[J].浙江大学学报(工学版),2004,538(6)：665-669.
[57].杨世锡,焦卫东,吴昭同.独立分量分析基网络应用于旋转机械故障特征提取与分类[J].机械工程学报,2004,40(3)：45-48.
[58].焦卫东,杨世锡,吴昭同.基于独立分量分析的噪声消除技术研究[J].浙江大学学报(工学版),2004,38(7)：872-876.
[59].夏文静,傅行军.基于ICA在强背景噪声振动信号中的去噪研究[J].汽轮机技术,2006,48(02)：121-124.
[60].黄晋英,毕世华,潘宏侠等.独立分量分析在齿轮箱故障诊断中的应用[J].振动、测试与诊断,2008,28(2)：126-130.
[61].吴慧英,帅仁俊.汽轮发电机组转子振动故障的模糊聚类分析[J].上海交通大学学报,1999,33(08)：1051-1054.
[62].陈铁华,陈启卷.模糊聚类分析在水电机组振动故障诊断中的应用[J].中国电机工程学报,2002,22(03)：43-46.
[63].李如强,陈进,伍星.基于奇异值分解、模糊聚类和粗糙集理论的旋转机械故障诊断[J].振动与冲击,2005,24(04)：46-49.
[64].刘晓波,黄其柏.基于动态核聚类分析的水轮机组故障模式识别[J].华中科技大学学报(自然科学版),2005,33(09)：47-52.
[65].尹安东,赵韩,羊拯民.基于小波变换一模糊聚类的变速箱齿轮故障诊断[J].中国机械工程,2006,17(20)：2121-2125.
[66].崔宝珍,王泽兵,潘宏侠.小波分析-模糊聚类法用于滚动轴承故障诊断[J].振动、测试与诊断,2008,28(02)：151-154.
[67].周川,伍星,刘畅等.基于EMD和模糊C均值聚类的滚动轴承故障诊断[J].昆明理工大学学报(理工版),2009,34(06)：34-39.
[68].田景文,高美娟.人工神经网络算法研究及应用[M].北京理工大学出版社,2006.
[69]. Venkatasubramanian V, Chan K. A neural network methodology for process fault diagnosis[J]. Journal of American Institute of Chemical Engineers,1989,35(12):1993-2002.
[70]. Hoskins J C, Kaliyur K M, David M Himmelblau. Fault diagnosis in complete chemical plants using artificial neural networks[J]. Journal of American Institute of Chemical Engineers,1991,37(1):137-141.
[71]. Kajiro, Watanabe. Incipient fault diagnosis of chemical processes via artificial neural networks[J]. Journal of American Institute of Chemical Engineers,1989,3(11):1803-1812
[72]. Kajiro, Watanabe. Diagnosis of multiple simultaneous fault via hierarchical artificial neural networks[J]. Journal of American Institute of Chemical Engineers,1994,40(5):839-848.
[73].张炜,张优云,战仁军等.旋转机械故障诊断中的神经网络改进算法研究[J].振动工程学报,1996,9(1)：31-37.
[74].许飞云,贾民平,钟秉林.旋转机械振动故障诊断的一种模糊神经网络方法研究[J].振动工程学报,1996,9(3)：213-219.
[75].陈长征,张省,虞和济.基于神经网络的旋转机械故障诊断研究[J].机械强度,2000,22(02)：104-112
[76].栗青,陈长征.集成神经网络在旋转机械故障诊断中的应用[J].沈阳工业大学学报,2001,23(4)：339-341.
[77].盛昭瀚,李春雨.小波神经网络及其在旋转机械轴心轨迹识别中的应用[J].系统工程理论与实践,1998(10)：98-103.
[78].万书亭,李和明,李永刚.自适应神经网络在发电机组故障诊断中的应用[J].华北电力大学学报,2002,29(2)：339-341.
[79].冯志鹏,宋希庚,薛冬新.基于广义粗糙集与神经网络集成的旋转机械故障诊断研究[J].机械科学与技术,2003,22(05)：815-820
[80].张利平,王铁生,索丽生.改进的BP网络在汽轮发电机组故障诊断中的应用[J].河海大学学报(自然科学版),2003,31(2)：233-236.
[81].朱大奇,陈尔奎.旋转机械故障诊断的量子神经网络算法[J].中国电机工程学报,2006,26(01)：132-136.
[82].周鹏,秦树人.基于切片谱RBF神经网络的旋转机械故障诊断[J].中国机械工程,2008,19(12)：1488-1491.
[83].毕云龙,回转设备转子故障诊断专家系统的初步研究[J].机械强度,1989,11(03)：7-11.
[84].赵美德,黄文虎,夏松波等.大型旋转机械故障诊断专家系统ETHYLENE的理论研究[J].振动工程学报,1992,5(02)：105-112.
[85].韩秋实,许宝杰,王红军等.旋转机械故障诊断监测专家系统中的时间序列模式识别技术研究[J].机械工程学报,2002,38(03)：104-107.
[86].刘贵立,王立鹏与张国英,基于Alopex神经网络的旋转机械故障诊断专家系统[J].振动、测试与诊断,2004,24(01)：61-64.
[87].黄开启,黄跃飞,刘晓波.多征兆模糊诊断知识表示及专家系统的研究[J].中国机械工程,2004,15(12).
[88].郑小霞,钱锋.模糊神经网络推理的实时故障诊断专家系统[J].计算机工程与应用,2006,03：226-229.
[89].窦东阳,赵英凯.基于优先级诊断树的旋转机械故障诊断专家系统[J].中国电机工程学报,2008,28(32)：81-88.
[90]. Scholkopf B. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation,1998,10(5):1229-1319.
[91].Mika S, Ratsch G, Weston J, et al. Fisher discriminant analysis with kernels[J]. Neural Networks for Signal Processing Ⅸ, IEEE,1999:41-48.
[92].白鹏,张喜斌,张斌等.支持向量机理论及工程应用实例[M].西安：西安电子科技大学出版社,2008.
[93]. Nello C, John S T. An Introduction to Support Vector Machine and Othe Kernel-based Learning Methods[M], Cambridge University Press,2000.
[94]. Poyhonen S, Negrea M, Arkkio A, etc. Support vector classi-fication for fault diagnostics of an electrical machine [C].Proc. of International Conference on Signal Proceeding(IC-SP'02), Beijing China, August26—30,2002.
[95].张周锁,李凌均,何正嘉.基于支持向量机的机械故障诊断方法研究[J].西安交通大学学报,2002,36(12)：1303-1306.
[96].李凌均,张周锁,何正嘉.支持向量机在机械故障诊断中的应用研究[J].计算机工程与应用,2002,19-21.
[97].何学文,赵海鸣,支持向量机及其在机械故障诊断中的应用[J].中南大学学报(自然科学版),2005,36(01)：97-101.
[98].翟永杰,毛继珮,于丽敏等.分级聚类支持向量机在汽轮机故障诊断中的应用[J].华北电力大学学报,2003,30(06)：25-29
[99].于德介,杨宇,程军圣.一种基于SVM和EMD的齿轮故障诊断方法[J].机械工程学报,2005,41(1)：140-144.
[100].程军圣,于德介,杨宇.基于SVM和EMD包络谱的滚动轴承故障诊断方法[J].系统工程理论与实践,2005,(09)：131-136.
[101].柳新民,刘冠军,邱静等.一种改进的无监督学习SVM及其在故障识别中的应用[J].机械工程学报,2006,42(04)：107-111.
[102].柳新民,刘冠军,邱静.基于HMM-SVM的故障诊断模型及应用[J].仪器仪表学报,2006,27(01)：45-48,53.
[103].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(02)：238-241.
[104]. Yuan S F, Chu F L. Support vector machines-based fault diagnosis for turbo-pump rotor[J]. Mechanical Systems and Signal Processing,2006,20:939-952.
[105].袁胜发,褚福磊.基于引力球结构支持向量机多类算法的涡轮泵故障诊断[J].宇航学报,2006,27(04)：635-639.
[106].彭文季,郭鹏程,罗兴绮.基于最小二乘支持向量机和信息融合技术的水电机组振动故障诊断研究[J].水力发电学报,2007,26(06)：137-142.
[107]. Zhang L, Nandi A K. Fault classification using genetic programming[J].Mechanical Systems and Signal Processing,2007,21:1273-1284.
[108]. Widodo A, Yang B S. Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motors[J], Expert Systems with Applications,2007,33:241-250.
[109]. Widodo A, Yang B S. Wavelet support vector machine for induction machine fault diagnosis based on transient current signal[J],2008,35:307-316.
[110]. Saravanan N, Kumar S V N S, Ramachandran K L. Expert Systems with Applications,2008,35(3):1351-1366.
[111]. Xian G M, Zeng B Q. An intelligent fault diagnosis method based on wavelet packer analysis and hybrid support vector machines[J].Expert Systems with Application,2009,36(10):12131-12136.
[112].邱绵浩,王自营,安钢等,基于核主元分析与纠错输出编码SVM的齿轮故障诊断[J].振动与冲击,2009,28(05)：1-5
[113].何学文.基于支持向量机的故障智能诊断理论与方法研究：[博士学位论文].长沙：中南大学,2004.
[114].翟永杰.基于支持向量机的故障智能诊断方法研究：[博士学位论文].河北：华北电力大学,2004.
[115].张超.基于支持向量机的汽轮机轴系振动故障智能诊断研究：[博士学位论文].河北：华北电力大学,2009.
[116].杨宇,基于EMD和支持向量机的旋转机械故障诊断方法研究：[博士学位论文].长沙：湖南大学,2005.
[117].邹敏.基于支持向量机的水电机组故障诊断研：[博士学位论文].华中科技大学,2007
[118].彭兵,基于改进支持向量机和特征信息融合的水电机组故障诊断：[博士学位论文].华中科技大学,2008.
[119].张莉,周伟达,焦李成.核聚类算法[J].计算机学报,2002,25(6)：587-590.
[120].孔锐,张国宣,施泽生.基于核的K-均值聚类[J].计算机工程,2004,30(11)：12-13,80.
[121].伍忠东,高新波,谢维信.基于核方法的模糊聚类算法[J].西安电子科技大学学报,2004,31(4)：533-537.
[122]. Daniel G, Witold P. Kernel-based fuzzy clustering and fuzzy clustering: A comparative experimental study[J]. Fuzzy Sets and Systems,2010, 161(4):Pages 522-543.
[123].潘庆丰,陈水利,陈国龙.基于核函数的模糊C均值聚类算法[J].集美大学学报,2006,11(4)：369-374.
[124].赵犁丰,李新,王栋.多核模糊聚类算法的研究[J].中国海洋大学学报,2009,39(5)：1047-1050
[125].李颖,李传龙,马龙等.动态加权模糊核聚类算法[J].计算机工程与设计,2009,30(24)：5584-5587.
[126].李巍华,廖广兰,史铁林.核函数主元分析及其在齿轮故障诊断中的应用[J].机械工程学报,2003,39(8)：65-70.
[127].邓晓刚,田学民.一种基于KPCA的非线性故障诊断方法[J].山东大学学报(工学版),2005,35(3)：103～106.
[128]. Cho J H, Lee J M, Choi S W. Fault identification for process monitoring using kernel principal component analysis[J]. Chemical Engineering Science,2005,60(1):279-288.
[129].郭磊,陈进,朱义等.基于小波函数的核主元特征约简方法研究[J].振动工程学报,2009,22(3)：287-291.
[130]. Ding M T, Zheng T, Xu H X. Adaptive kernel principal component analysis[J]. Signal Processing,2010,90(5):1542-1553.
[131].王新峰,邱静,刘冠军.核主元分析中核函数参数优选方法研究[J].振动、测试与诊断,2007,27(1)：62-64.
[132].魏秀业,潘宏侠,王福杰.基于粒子群优化的核主元分析特征的提取技术[J].振动、测试与诊断,2009,29(2)：162-166.
[133]. Francis R B, Michael I J.Kernel independent component analysis[J]. Journal of Machine Learning Research,2002, (3):1-48.
[134].田昊,唐力伟,田广.基于核独立分量分析的齿轮箱故障诊断[J].振动与冲击,2009,28(5)：163-164,191.
[135]. 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 & Engineering Sciences,1998,454:903-995.
[136]. Yan R Q, Gao R X. Hilbert-Huang transform-based vibration signal analysis for machine health monitoring [J]. IEEE Transactions on Instrumentation and Measurement,2006,55(6):2320-2329.
[137].于德介,程军圣,杨宇.Hilbert-Huang变换在滚动轴承故障诊断中的应用[J].中国机械工程,2003,14(24)：2140～2142.
[138].李常有,徐敏强,郭嵩.基于改进的Hilbert-Huang变换的滚动轴承故障诊断[J].振动与冲击,2007,26(4)：39～41,50.
[139]. Chen H X, Chua P S K, Lim G H. Fault degradation assessment of water hydraulic motor by impulse vibration signal with Wavelet Packet Analysis and Kolmogorov-Smirnov Test[J]. Mechanical Systems and Signal Processing,2008,22(7):1670-1684.
[140]. Hu Q, He Z J, Zhang Z S, et al. Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble[J]. Mechanical Systems and Signal Processing,2007,21(2):688-705.
[141]. Nedjah O, Hussein A M, Krishnan S, Sotudeh R. Comparative study of adaptive techniques for denoising CN Tower lightning current derivative signals[J]. Digital Signal Processing,2010,20(2):607-618.
[142]. Huang J J, Ning L V, Li S Q, et al. Feature Selection for Classificatory Analysis Based on Information-theoretic Criteria[J]. Acta Automatica Sinica,2008,34(3):383-392
[143].陆振波,蔡志明,姜可宇.基于改进的C-C方法的相空间重构参数选择[J].系统仿真学报,2007,19(11)：2527-2538
[144].吕金虎,陆君安,陈士华.混沌时间序列分析及其应用[M].湖北：武汉大学出版社,2002.
[145]. Luis B A. Linear and nonlinear ICA based on mutual information—the MISEP method[J]. Signal Processing,2004,84(2):231-245.
[146]. Peter G, Anke M, Simon F, et al. ICA, kernel methods and nonnegativity: New paradigms for dynamical component analysis of fMRI data[J]. Engineering Applications of Artificial Intelligence,2009, 22(4-5):497-504.
[147]. Hyvarinen A. Survey on independent component analysis[J]. Neural Computing Surveys,1999,(2):94-128.
[148]. Cheng J S, Yu D J, Yang Y. A fault diagnosis approach for roller bearings based on EMD method and AR model[J]. Mechanical Systems and Signal Processing,20(2006):350-362.
[149]. Daniel G, Witold P. Kernel-based fuzzy clustering and fuzzy clustering: A comparative experimental study[J]. Fuzzy Sets and Systems, 2010,61(4):522-543
[150]. Mac Q J. Some methods for classification and analysis of multivariate observations[J]. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability,1965:1-12.
[151].齐敏,李大健,郝重阳等.模式识别导论[M].北京：清华大学出版社,2009.
[152]. Mark G. Mercer kernel-based clustering in feature space[J]. IEEE Transactions on Neural Networks,2002,13(3):780-784.
[153]. Boser B, Guyon I, Vapnik V N. A training algorithm for optimal margin classifiers[C]. Fifth Annual Workshop on Computational Learning Theory, Pittsburgh ACM:144～152.
[154]. Hsu C, Chang C C, Lin C J. A practical guide to support vector classification[EB/OL]. [2009-05-19]. http://www.csie.ntu.edu.tw/～cjlin,
[155]. Hsu C, Lin C J. A comparison of methods for multi-class support vector machines[J]. IEEE Transactions on Neural Networks, 2002,13(2):415-425.