基于HOS的滚动轴承故障诊断方法应用研究
摘要
滚动轴承是各种旋转机械中应用最为广泛的一种通用机械部件,也是确保机械设备功能和性能的关键部件。由于滚动轴承的结构特点及工作条件恶劣,极易造成损坏,对滚动轴承进行故障诊断与状态监测意义重大。故障轴承振动信号呈现出较强的非高斯、非线性、非平稳特性,使用传统的基于线性平稳假设的信号处理方法处理效果不理想。
高阶统计量(Higher-Order Statistic, HOS)是最近十几年发展较快的一种现代信号处理方法,由于其出色的噪声消除性能及相位保留能力,是处理非线性、非高斯、非平稳、非最小相位、非因果信号的有效手段,被广泛应用于雷达、声纳、生物医学、地球物理、盲信号处理、盲系统辨识、机械故障诊断等众多领域。
本文对双谱、三谱、双相干谱、双谱切片、Hilbert双谱、高阶时频谱的定义、性质、估计方法及物理意义进行了研究；讨论了信号幅值和相位重构的意义及常用方法,使用基于双谱的最小二乘法对轴承振动信号进行相位和幅值重构分析；讨论了滚动轴承故障机理及振动模型,对滚动轴承振动信号在高频共振处带通滤波,对滤波后的信号进行双谱分析并与传统的双谱分析结果进行了对比,结果表明该方法在消除噪声、突出故障特征方面具有优势；高阶时频分布兼有时频分布及高阶统计量的优点,针对滚动轴承振动信号的高阶时频及其切片分析表明该方法的有效性。本文还研究了常用的机械故障分类方法和特征提取方法,使用双谱峰值频率对信息、振动信号AR (Autoregressive, AR)模型参数等构造用于轴承模式识别的特征向量；研究了常用的优化算法及故障分类算法,分别使用遗传算法和微粒群优化算法对支持向量机的主要参数进行优化,使用优化的支持向量机对测试数据进行分类,取得较高的分类准确率。最后,基于MATLAB的GUIDE对本文中所使用和改进的算法开发了MATLAB工具包。
Rolling bearings are one of the most common elements in rotating machinery; rolling bearings are also critical parts to insure function and performance of rotating machinery. Because of the structural characteristics and adverse working conditions, rolling bearings are vulnerable to damage. Thus, fault diagnosis and condition monitoring of rolling bearings is important. The vibration signals caused by faulty bearings are typical non-Gaussian, non-linear, and non-stationary; the conventional methods based on linear time-invariant are not effectiveness.
Higher-Order statistic is a kind of new signal-processing method which with rapid development in recent decades. Because of its capability of eliminating Gaussian noise and retaining the signal phase information, HOS is a useful tool for non-linear, non-Gaussian, non-stationary, non-minimum phase, non-causal signals, and it is now applied in many fields, such as radar, sonar, physical geography, biomedicine, blind system identification, blind signal separation, fault diagnosis.
In this dissertation, the definition, characteristics, algorithm and physical meaning of mainly used HOS is summarized. Signal amplitude and phase reconstruction from its bispectrum is proposed, different reconstruction methods are discussed. Mechanism of rolling bearing vibration and models of different defect bearings are given. Vibration signals of bearings are pre-processed and the high frequency resonance signals are used for bispectrum analysis, experiment results have shown the effectiveness of these methods. Higher-Order time frequency distributions have both the advantages of HOS and time frequency distribution; Higher-Order time frequency distributions analyses of bearing vibration signals are shown feasible. Defect classification and feature extraction methods are also researched in this dissertation, peak information of bispectrum, AR model parameters are used for feature vectors of support vector machine. PSO and genetic algorithm are use for optimizing key parameters of SVM, the optimized SVM is used for bearing condition classification, and the results have shown that the diagnosis precision has been improved. Finally, a toolbox is developed for the proposed HOS analysis algorithms based on the MATLAB GUIDE.
高阶统计量(Higher-Order Statistic, HOS)是最近十几年发展较快的一种现代信号处理方法,由于其出色的噪声消除性能及相位保留能力,是处理非线性、非高斯、非平稳、非最小相位、非因果信号的有效手段,被广泛应用于雷达、声纳、生物医学、地球物理、盲信号处理、盲系统辨识、机械故障诊断等众多领域。
本文对双谱、三谱、双相干谱、双谱切片、Hilbert双谱、高阶时频谱的定义、性质、估计方法及物理意义进行了研究；讨论了信号幅值和相位重构的意义及常用方法,使用基于双谱的最小二乘法对轴承振动信号进行相位和幅值重构分析；讨论了滚动轴承故障机理及振动模型,对滚动轴承振动信号在高频共振处带通滤波,对滤波后的信号进行双谱分析并与传统的双谱分析结果进行了对比,结果表明该方法在消除噪声、突出故障特征方面具有优势；高阶时频分布兼有时频分布及高阶统计量的优点,针对滚动轴承振动信号的高阶时频及其切片分析表明该方法的有效性。本文还研究了常用的机械故障分类方法和特征提取方法,使用双谱峰值频率对信息、振动信号AR (Autoregressive, AR)模型参数等构造用于轴承模式识别的特征向量；研究了常用的优化算法及故障分类算法,分别使用遗传算法和微粒群优化算法对支持向量机的主要参数进行优化,使用优化的支持向量机对测试数据进行分类,取得较高的分类准确率。最后,基于MATLAB的GUIDE对本文中所使用和改进的算法开发了MATLAB工具包。
Rolling bearings are one of the most common elements in rotating machinery; rolling bearings are also critical parts to insure function and performance of rotating machinery. Because of the structural characteristics and adverse working conditions, rolling bearings are vulnerable to damage. Thus, fault diagnosis and condition monitoring of rolling bearings is important. The vibration signals caused by faulty bearings are typical non-Gaussian, non-linear, and non-stationary; the conventional methods based on linear time-invariant are not effectiveness.
Higher-Order statistic is a kind of new signal-processing method which with rapid development in recent decades. Because of its capability of eliminating Gaussian noise and retaining the signal phase information, HOS is a useful tool for non-linear, non-Gaussian, non-stationary, non-minimum phase, non-causal signals, and it is now applied in many fields, such as radar, sonar, physical geography, biomedicine, blind system identification, blind signal separation, fault diagnosis.
In this dissertation, the definition, characteristics, algorithm and physical meaning of mainly used HOS is summarized. Signal amplitude and phase reconstruction from its bispectrum is proposed, different reconstruction methods are discussed. Mechanism of rolling bearing vibration and models of different defect bearings are given. Vibration signals of bearings are pre-processed and the high frequency resonance signals are used for bispectrum analysis, experiment results have shown the effectiveness of these methods. Higher-Order time frequency distributions have both the advantages of HOS and time frequency distribution; Higher-Order time frequency distributions analyses of bearing vibration signals are shown feasible. Defect classification and feature extraction methods are also researched in this dissertation, peak information of bispectrum, AR model parameters are used for feature vectors of support vector machine. PSO and genetic algorithm are use for optimizing key parameters of SVM, the optimized SVM is used for bearing condition classification, and the results have shown that the diagnosis precision has been improved. Finally, a toolbox is developed for the proposed HOS analysis algorithms based on the MATLAB GUIDE.
引文
[1]邱天爽,张旭秀,李小兵等.统计信号处理——非高斯信号处理及应用.北京：电子工业出版社,2004
[2]Olivier Michael, Patrick Flandrin. Application of methods based on higher-order statistics for chaotic time series analysis. Signal Processing,1996, 53:133-148
[3]W.B. Collis, P. R. White, J. K. Hammond. Higher-Order Spectra:The Bispectrum and Trispectrum. Mechanical System and Signal Processing,1998, 12(3):375-394
[4]B. Eugene Parker Jr, H. A. Ware, D. P. Wipf, et al. Fault Diagnostics Using Statistical Statistical Change Detection in the Bispectual Domain. Mechanical System and Signal Processing,2000,14(4):561-570
[5]Dusan Kocur, Radoslav Stanko. Order Bispectrum:A New Tool for Reciprocated Machine Condition Monitoring. Mechanical System and Signal Processing,2000,14(6):871-890
[6]Yang Xiang, S.k. Tso. Detection and classification of flaws in concrete structure using bispectra and neural networks. NDT&E International,2002,35:19-27
[7]D.-M. Yang, A. F. Stronach, P. MacConnell, et al. Higher-Order Spectral Techniques for the Diagnosis of Motor Bearing Condition Using Artificial Neural Networks. Mechanical System and Signal Processing,2002,16(2-3): 391-411
[8]Melvin J. Hinich, Murray Wolinsky. Normalizing bispectra. Journal of Statistical Planning and Interence,2005,130:405-411
[9]Fidel Ernesto Hernandez Montero, Oscar Caveda Medina. The application of bispectrum on diagnosis of rolling element bearing:A theoretical approach. Mechanical System and Signal Processing,2008,22:588-596
[10]Juggrapong Treetrong, Jyoti K. Sinha, Fengshu Gu, et al. Bispectrum of stator phase current for fault detection of induction motor. ISA Transactions,2009,48: 378-382
[11]Jyoti K. Sinha. Higher Order Coherences for fatigue crack detection. Engineering Structures,2009,31:534-538
[12]杨江天.高阶谱和灰色系统理论在机械故障诊断中的应用研究[博士学位论文].天津,天津大学,1999
[13]周越.非高斯信号的多尺度分析与特征提取研究[博士学位论文].西安,西北工业大学,2000
[14]张桂才.基于高阶统计分析的机械故障特征提取技术研究[博士学位论文].武汉,华中科技大学,2002
[15]张子瑜,陈进,史习智.双谱分析在齿轮故障诊断中的应用.振动工程学报,1998,11(S)：90-93
[16]熊良才,史铁林,杨叔子.基于双谱分析的齿轮故障诊断研究.华中科技大学学报,2001,29(11)：4-5
[17]郑海波,陈心昭,李志远.基于双谱的齿轮故障特征提取与识别.振动工程学报,2002,15(3)：354-358
[18]邵忍平,黄欣娜,刘宏昱等.基于高阶累积量的齿轮系统故障检测与诊断.机械工程学报,2008,44(6)：161-168
[19]杨江天,陈家骥,曾子平.基于高阶谱的旋转机械故障征兆提取.振动工程学报,2001,11(1)：13-17
[20]李志农,丁启全,吴昭同等.旋转机械升降速过程的双谱-]FHMM识别方法.振动工程学报,2003,16(2)：171-174
[21]韩捷,李军伟,李志农.阶比双谱及其在旋转机械故障诊断中的应用.机械强度,2006,28(6)：791-795
[22]李军伟,韩捷,李志农等.小波变换域双谱分析及其在滚动轴承故障诊断中的应用.振动与冲击,2006,25(5)：92-95
[23]刘占生,窦唯,王晓伟.基于主元-双谱支持向量机的旋转机械故障诊断方法.振动与冲击,2007,26(12)：23-27
[24]梅宏斌.滚动轴承振动监测与诊断理论方法系统.北京：机械工业出版社,1996
[25]孟涛.齿轮与滚动轴承故障的振动分析与诊断[博士学位论文].西安,西北工业大学,2003
[26]朱忠奎.非平稳特征表示和提取与故障诊断研究[博士学位论文].合肥,中 国科学技术大学,2004
[27]毕果.基于循环平稳的滚动轴承及齿轮微弱故障特征提取应用研究[博士学位论文].上海,上海交通大学,2007
[28]胡桥,何正嘉,张周锁等.基于提升小波包变换和集成支持矢量机的早期故障诊断.机械工程学报,2006,42(8)：16-22
[29]唐贵基,蔡伟.应用小波包和包络分析的滚动轴承故障诊断.振动、测试与诊断,2009,29(2)：201-204
[30]杨洁明,田英.基于EMD和球结构SVM的滚动轴承故障诊断.振动、测试与诊断,2009,29(2)：155-158
[31]胡邦喜.基于解调技术的双特征分析法在轴承故障诊断中的研究.机械强度,2006,28(6)：948-952
[32]王志刚,李友荣,吕勇.基于谐波小波变换的共振解调法.振动与冲击,2006,25(4)：159-161
[33]刘金朝,丁夏完,王成国.自适应共振解调法及其在滚动轴承故障诊断中的应用.振动与冲击,2006,26(1)：38-41
[34]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.机械工程学报,2007,43(8)：119-122
[35]胡晓依,何庆复,王华胜等.基于STFT的振动信号解调方法及其在轴承故障检测中的应用.振动与冲击,2008,27(2):82-86
[36]何沿江,齐明侠,罗红梅.基于ICA和SVM的滚动轴承声发射故障诊断技术.振动与冲击,2008,27(3)：150-153
[37]于湘涛,褚福磊,郝如江.基于柔性形态滤波和支持矢量机的滚动轴承故障诊断方法.机械工程学报,2009,45(7)：75-80
[38]王凯,张永祥,李军.基于支持向量机的齿轮故障诊断方法研究.振动与冲击,2006,25(6)：97-99
[39]曹建军,张培林,任国全等.基于蚁群优化的振动信号特征选择.振动与冲击,2008,27(5)：24-31
[40]张贤达.现代信号处理(第二版).北京：清华大学出版社,2002
[41]Gopal Sundaramoorthy, M. R. Raghuveer, Soheil A. Dianat. Bispectral Reconstruction of Signals in Noise:Amplitude Reconstruction Issues. IEEE Transactions on Acoustics, Speech, and Signal Processing,1990,38(7): 1297-1306
[42]Christopher A. Haniff. Least-squares Fourier phase estimation from the modulo 2π bispectrum phase. Optical Society of America,1991,8(1):134-1306
[43]A.Glindemann, R.GLane, J.C.Dainty. Least-Squares Reconstruction of the Object Phase from the Bispectrum. DIGITAL SIGNAL PROCESSING,1991, 8(1):59-65
[44]R.S. Holambe, A.K. Ray, T.K. Basu. Signal phase recovery using bispectrum. Signal Processing,1996,55(1):321-337
[45]Xuejun Liao, Zheng Bao. Signal Reconstruction from accumulation of bispectral radial slices. Optical Engineering,2000,39(8):2065-2074
[46]H. Bartelt, A. W. Lohmann, B. Wirnitzer. Phase and amplitude recovery from bispectra. APPLIED OPTICS,1984,23(18):3121-3129
[47]Toshidumi Matsuoka, Tad J. Ulrych. Phase Estimation Using the Bispectrum. PROCEEDINGS OF THE IEEE,1984,72(10):1403-1411
[48]陈仲生.直升机旋转部件故障特征提取的高阶统计量方法研究[博士学位论文].长沙,国防科学技术大学,2004
[49]贾继德.往复机械非平稳信号的特征提取及诊断研究[博士学位论文].长沙,国防科学技术大学,2004
[50]J. Pineyro, A. Klempnow, V. Lescano. Effectiveness of new spectral tools in the anomaly detection of rolling element bearings. Journal of Alloys and Compounds,2000,310(10):276-279
[51]赵慧敏,夏超英,肖云魁等.柴油发动机曲轴轴承振动信号的双谱分析.振动测试与诊断,2009,29(1)：14-17
[52]姜鸣,陈进,汪慰军.几种Cohen类时频分布的比较及应用.机械工程学报,2003,39(8)：129-134
[53]马瑞恒,王新晴.基于一种新的时频分布的机械故障诊断.振动与冲击,2003,22(3)：68-74
[54]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.振动工程学报,2003,16(2)：247-250
[55]L. Gelman, I. Petrumin, J. Komoda. The new chrip-Wigner higher order spectra for transient signals with any known nonlinear frequency variation. Mechanical Systems and Signal Processing,2010,24(10):567-571
[56]阎威武.支持向量机理论方法和应用研究[博士学位论文].上海,上海交通 大学,2003
[57]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
[58]潘明清.基于支持向量机的机械故障模式分类研究[博士学位论文]杭州,浙江大学,2004
[59]袁胜发,褚福磊.支持向量机及其在机械故障诊断中的应用.振动与冲击,2007,26(11)：29-35
[60]JIANG Zhi-qiang, FU Han-guang, LI Ling-jun. Support Vector Machine for mechanical faults classification. Journal of Zhejiang University SCIENCE, 2005,6A(5):433-439
[61]于德介绍,杨宇,程军圣.一种基于SVM和EMD的齿轮故障诊断方法.机械工程学报,2005,41(1)：140-144
[62]肖成勇,石博强,王文莉等.基于小波包和进化支持向量机的齿轮早期诊断研究.振动与冲击,2007,26(7)：10-26
[63]王凯,张永祥,李军.基于支持向量机的齿轮故障诊断方法研究.振动与冲击,2006,25(6)：97-99
[64]冼广铭,曾碧卿,唐华等.小波包结合支持向量机的故障诊断方法.计算机工程,2009,35(4)：212-214
[65]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.振动与冲击,2009,28(5)：1-5
[66]王凯,张永祥,李军.遗传算法和支持向量机在机械故障诊断中的应用研究.机械强度,2008,30(3)：349-353
[67]吴震宇,袁惠群.蚁群支持向量机在内燃机故障诊断中的应用研究.振动与冲击,2008,28(3)：83-86
[68]袁胜发,褚福磊.SVM多类分类算法及其在故障诊断中的应用.振动工程学报,2004,17(S)：419-421
[69]Achmad Widodo, Bo-Suk Yang. Support Vector Machine in machine condition monitoring and fault diagnosis. Mechanical Systems and Signal Processing, 2007,21(5):2560-2574
[70]闫志刚,杜培军.多类支持向量机推广性能分析.数据采集与处理,2009,24(4)：469-475
[71]李宁.粒子群优化算法的理论分析与应用研究[博士学位论文].武汉,华中 科技大学,2006
[72]Seyed-Hamid Zahiri, Seyed-Alireza Seyedin. Swarm intelligence based classifiers. Journal of The Franklin Institute,2007,344:362-376
[73]Qian-jin Guo, Hai-bin Yu, Ai-dong Xu. A hybrid PSO-GD based intelligent method for machine diagnosis. Digital Signal Processing,2006,16:402-418
[74]Lin-Lai Li, Dong-Hua Zhou, Ling Wang. Fault Diagnosis of Nonlinear Systems Based on Hybrid PSOSA Optimization Algorithm. International Journal of Automation and Computing,2007,04(2):183-188
[75]Taher Niknam, Babak Amiri. An efficient hybrid approach based on PSO, ACO and k-means for cluster analysis. Applied Soft Computing,2010,10:183-197
[76]Sheng-Fa Yuan, Fu-Lei Chu. Fault diagnostics based on particle swarm optimization and support vector machines. Mechanical Systems and Signal Processing,2007,21:1787-1798
[77]Cheng-Lung Huang, Jian-Fan Dun. A distributed PSO-SVM hybrid system with feature selection and parameter optimization. Applied Soft Computing, 2008,8:1381-1391
[78]Shih-Wei Lin, Kuo-Ching Ying, Shih-Chieh Chen, Zne-Jung Lee. Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Systems with Applications,2008,35: 1817-1824
[79]陈垚光,毛涛涛,王正林等.精通MATLAB GUI设计.北京：电子工业出版社,2008
[2]Olivier Michael, Patrick Flandrin. Application of methods based on higher-order statistics for chaotic time series analysis. Signal Processing,1996, 53:133-148
[3]W.B. Collis, P. R. White, J. K. Hammond. Higher-Order Spectra:The Bispectrum and Trispectrum. Mechanical System and Signal Processing,1998, 12(3):375-394
[4]B. Eugene Parker Jr, H. A. Ware, D. P. Wipf, et al. Fault Diagnostics Using Statistical Statistical Change Detection in the Bispectual Domain. Mechanical System and Signal Processing,2000,14(4):561-570
[5]Dusan Kocur, Radoslav Stanko. Order Bispectrum:A New Tool for Reciprocated Machine Condition Monitoring. Mechanical System and Signal Processing,2000,14(6):871-890
[6]Yang Xiang, S.k. Tso. Detection and classification of flaws in concrete structure using bispectra and neural networks. NDT&E International,2002,35:19-27
[7]D.-M. Yang, A. F. Stronach, P. MacConnell, et al. Higher-Order Spectral Techniques for the Diagnosis of Motor Bearing Condition Using Artificial Neural Networks. Mechanical System and Signal Processing,2002,16(2-3): 391-411
[8]Melvin J. Hinich, Murray Wolinsky. Normalizing bispectra. Journal of Statistical Planning and Interence,2005,130:405-411
[9]Fidel Ernesto Hernandez Montero, Oscar Caveda Medina. The application of bispectrum on diagnosis of rolling element bearing:A theoretical approach. Mechanical System and Signal Processing,2008,22:588-596
[10]Juggrapong Treetrong, Jyoti K. Sinha, Fengshu Gu, et al. Bispectrum of stator phase current for fault detection of induction motor. ISA Transactions,2009,48: 378-382
[11]Jyoti K. Sinha. Higher Order Coherences for fatigue crack detection. Engineering Structures,2009,31:534-538
[12]杨江天.高阶谱和灰色系统理论在机械故障诊断中的应用研究[博士学位论文].天津,天津大学,1999
[13]周越.非高斯信号的多尺度分析与特征提取研究[博士学位论文].西安,西北工业大学,2000
[14]张桂才.基于高阶统计分析的机械故障特征提取技术研究[博士学位论文].武汉,华中科技大学,2002
[15]张子瑜,陈进,史习智.双谱分析在齿轮故障诊断中的应用.振动工程学报,1998,11(S)：90-93
[16]熊良才,史铁林,杨叔子.基于双谱分析的齿轮故障诊断研究.华中科技大学学报,2001,29(11)：4-5
[17]郑海波,陈心昭,李志远.基于双谱的齿轮故障特征提取与识别.振动工程学报,2002,15(3)：354-358
[18]邵忍平,黄欣娜,刘宏昱等.基于高阶累积量的齿轮系统故障检测与诊断.机械工程学报,2008,44(6)：161-168
[19]杨江天,陈家骥,曾子平.基于高阶谱的旋转机械故障征兆提取.振动工程学报,2001,11(1)：13-17
[20]李志农,丁启全,吴昭同等.旋转机械升降速过程的双谱-]FHMM识别方法.振动工程学报,2003,16(2)：171-174
[21]韩捷,李军伟,李志农.阶比双谱及其在旋转机械故障诊断中的应用.机械强度,2006,28(6)：791-795
[22]李军伟,韩捷,李志农等.小波变换域双谱分析及其在滚动轴承故障诊断中的应用.振动与冲击,2006,25(5)：92-95
[23]刘占生,窦唯,王晓伟.基于主元-双谱支持向量机的旋转机械故障诊断方法.振动与冲击,2007,26(12)：23-27
[24]梅宏斌.滚动轴承振动监测与诊断理论方法系统.北京：机械工业出版社,1996
[25]孟涛.齿轮与滚动轴承故障的振动分析与诊断[博士学位论文].西安,西北工业大学,2003
[26]朱忠奎.非平稳特征表示和提取与故障诊断研究[博士学位论文].合肥,中 国科学技术大学,2004
[27]毕果.基于循环平稳的滚动轴承及齿轮微弱故障特征提取应用研究[博士学位论文].上海,上海交通大学,2007
[28]胡桥,何正嘉,张周锁等.基于提升小波包变换和集成支持矢量机的早期故障诊断.机械工程学报,2006,42(8)：16-22
[29]唐贵基,蔡伟.应用小波包和包络分析的滚动轴承故障诊断.振动、测试与诊断,2009,29(2)：201-204
[30]杨洁明,田英.基于EMD和球结构SVM的滚动轴承故障诊断.振动、测试与诊断,2009,29(2)：155-158
[31]胡邦喜.基于解调技术的双特征分析法在轴承故障诊断中的研究.机械强度,2006,28(6)：948-952
[32]王志刚,李友荣,吕勇.基于谐波小波变换的共振解调法.振动与冲击,2006,25(4)：159-161
[33]刘金朝,丁夏完,王成国.自适应共振解调法及其在滚动轴承故障诊断中的应用.振动与冲击,2006,26(1)：38-41
[34]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.机械工程学报,2007,43(8)：119-122
[35]胡晓依,何庆复,王华胜等.基于STFT的振动信号解调方法及其在轴承故障检测中的应用.振动与冲击,2008,27(2):82-86
[36]何沿江,齐明侠,罗红梅.基于ICA和SVM的滚动轴承声发射故障诊断技术.振动与冲击,2008,27(3)：150-153
[37]于湘涛,褚福磊,郝如江.基于柔性形态滤波和支持矢量机的滚动轴承故障诊断方法.机械工程学报,2009,45(7)：75-80
[38]王凯,张永祥,李军.基于支持向量机的齿轮故障诊断方法研究.振动与冲击,2006,25(6)：97-99
[39]曹建军,张培林,任国全等.基于蚁群优化的振动信号特征选择.振动与冲击,2008,27(5)：24-31
[40]张贤达.现代信号处理(第二版).北京：清华大学出版社,2002
[41]Gopal Sundaramoorthy, M. R. Raghuveer, Soheil A. Dianat. Bispectral Reconstruction of Signals in Noise:Amplitude Reconstruction Issues. IEEE Transactions on Acoustics, Speech, and Signal Processing,1990,38(7): 1297-1306
[42]Christopher A. Haniff. Least-squares Fourier phase estimation from the modulo 2π bispectrum phase. Optical Society of America,1991,8(1):134-1306
[43]A.Glindemann, R.GLane, J.C.Dainty. Least-Squares Reconstruction of the Object Phase from the Bispectrum. DIGITAL SIGNAL PROCESSING,1991, 8(1):59-65
[44]R.S. Holambe, A.K. Ray, T.K. Basu. Signal phase recovery using bispectrum. Signal Processing,1996,55(1):321-337
[45]Xuejun Liao, Zheng Bao. Signal Reconstruction from accumulation of bispectral radial slices. Optical Engineering,2000,39(8):2065-2074
[46]H. Bartelt, A. W. Lohmann, B. Wirnitzer. Phase and amplitude recovery from bispectra. APPLIED OPTICS,1984,23(18):3121-3129
[47]Toshidumi Matsuoka, Tad J. Ulrych. Phase Estimation Using the Bispectrum. PROCEEDINGS OF THE IEEE,1984,72(10):1403-1411
[48]陈仲生.直升机旋转部件故障特征提取的高阶统计量方法研究[博士学位论文].长沙,国防科学技术大学,2004
[49]贾继德.往复机械非平稳信号的特征提取及诊断研究[博士学位论文].长沙,国防科学技术大学,2004
[50]J. Pineyro, A. Klempnow, V. Lescano. Effectiveness of new spectral tools in the anomaly detection of rolling element bearings. Journal of Alloys and Compounds,2000,310(10):276-279
[51]赵慧敏,夏超英,肖云魁等.柴油发动机曲轴轴承振动信号的双谱分析.振动测试与诊断,2009,29(1)：14-17
[52]姜鸣,陈进,汪慰军.几种Cohen类时频分布的比较及应用.机械工程学报,2003,39(8)：129-134
[53]马瑞恒,王新晴.基于一种新的时频分布的机械故障诊断.振动与冲击,2003,22(3)：68-74
[54]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.振动工程学报,2003,16(2)：247-250
[55]L. Gelman, I. Petrumin, J. Komoda. The new chrip-Wigner higher order spectra for transient signals with any known nonlinear frequency variation. Mechanical Systems and Signal Processing,2010,24(10):567-571
[56]阎威武.支持向量机理论方法和应用研究[博士学位论文].上海,上海交通 大学,2003
[57]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
[58]潘明清.基于支持向量机的机械故障模式分类研究[博士学位论文]杭州,浙江大学,2004
[59]袁胜发,褚福磊.支持向量机及其在机械故障诊断中的应用.振动与冲击,2007,26(11)：29-35
[60]JIANG Zhi-qiang, FU Han-guang, LI Ling-jun. Support Vector Machine for mechanical faults classification. Journal of Zhejiang University SCIENCE, 2005,6A(5):433-439
[61]于德介绍,杨宇,程军圣.一种基于SVM和EMD的齿轮故障诊断方法.机械工程学报,2005,41(1)：140-144
[62]肖成勇,石博强,王文莉等.基于小波包和进化支持向量机的齿轮早期诊断研究.振动与冲击,2007,26(7)：10-26
[63]王凯,张永祥,李军.基于支持向量机的齿轮故障诊断方法研究.振动与冲击,2006,25(6)：97-99
[64]冼广铭,曾碧卿,唐华等.小波包结合支持向量机的故障诊断方法.计算机工程,2009,35(4)：212-214
[65]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.振动与冲击,2009,28(5)：1-5
[66]王凯,张永祥,李军.遗传算法和支持向量机在机械故障诊断中的应用研究.机械强度,2008,30(3)：349-353
[67]吴震宇,袁惠群.蚁群支持向量机在内燃机故障诊断中的应用研究.振动与冲击,2008,28(3)：83-86
[68]袁胜发,褚福磊.SVM多类分类算法及其在故障诊断中的应用.振动工程学报,2004,17(S)：419-421
[69]Achmad Widodo, Bo-Suk Yang. Support Vector Machine in machine condition monitoring and fault diagnosis. Mechanical Systems and Signal Processing, 2007,21(5):2560-2574
[70]闫志刚,杜培军.多类支持向量机推广性能分析.数据采集与处理,2009,24(4)：469-475
[71]李宁.粒子群优化算法的理论分析与应用研究[博士学位论文].武汉,华中 科技大学,2006
[72]Seyed-Hamid Zahiri, Seyed-Alireza Seyedin. Swarm intelligence based classifiers. Journal of The Franklin Institute,2007,344:362-376
[73]Qian-jin Guo, Hai-bin Yu, Ai-dong Xu. A hybrid PSO-GD based intelligent method for machine diagnosis. Digital Signal Processing,2006,16:402-418
[74]Lin-Lai Li, Dong-Hua Zhou, Ling Wang. Fault Diagnosis of Nonlinear Systems Based on Hybrid PSOSA Optimization Algorithm. International Journal of Automation and Computing,2007,04(2):183-188
[75]Taher Niknam, Babak Amiri. An efficient hybrid approach based on PSO, ACO and k-means for cluster analysis. Applied Soft Computing,2010,10:183-197
[76]Sheng-Fa Yuan, Fu-Lei Chu. Fault diagnostics based on particle swarm optimization and support vector machines. Mechanical Systems and Signal Processing,2007,21:1787-1798
[77]Cheng-Lung Huang, Jian-Fan Dun. A distributed PSO-SVM hybrid system with feature selection and parameter optimization. Applied Soft Computing, 2008,8:1381-1391
[78]Shih-Wei Lin, Kuo-Ching Ying, Shih-Chieh Chen, Zne-Jung Lee. Particle swarm optimization for parameter determination and feature selection of support vector machines. Expert Systems with Applications,2008,35: 1817-1824
[79]陈垚光,毛涛涛,王正林等.精通MATLAB GUI设计.北京：电子工业出版社,2008