基于GA-NN的旋转机械故障逐次诊断研究
|
摘要
论文从研究传统的旋转机械故障的特征参数识别两类状态的能力出发,提出了特征参数灵敏度评价标准,并对其进行了实验验证;在传统的特征参数基础上,文中提出利用遗传算法对特征参数进行自组织生成新的高灵敏度的特征参数,并采用遗传算法对由所有特征参数组成的特征集合进行选择,去除了冗余的特征参数;最后建立了基于神经网络的逐次诊断模型,降低了诊断系统输入量的维数,并通过实验验证了整个诊断系统的有效性。该诊断系统结合了特征灵敏度的评价、特征提取、特征选择和逐次神经网络模型,有一定创新性,且易于实现,具有良好的工程应用价值。现将论文主要的研究成果归纳如下:
①提出了用于评价特征参数识别故障的灵敏度的概念。并假设特征参数概率密度函数是正态分布情况下,从理论上推导出了灵敏度的计算公式。最后通过实验验证了灵敏度与特征参数区分两种状态的识别率是成正比关系的,灵敏度高的特征参数就具有高的识别率。
②传统特征参数不能很好的区分两种状态,文中采用遗传算法重新提取新的高灵敏度的特征参数;该方法是对传统的特征参数进行再组织生成新的特征参数,文中用树形图来表示特征参数的公式,便于利用遗传算法进行交叉和变异;用特征参数灵敏度作为遗传算法的适应度函数。最后实验验证了新的特征参数的识别率高,证明了该方法的有效性。
③文中将传统特征参数和由遗传算法提取的新的特征参数共17个组成特征参数集合。提出了以类内和类间距离为适应度函数,基于遗传算法的特征选择策略,选择出最有效的几个特征参数来降维,同时达到提高识别两类状态识别率的目的。该方法能够充分利用遗传算法的隐并行性,有效地剔除原始特征集中冗余特征参数。并利用实验验证了将优化后的特征集合用于神经网络分类器训练,能够提高故障的识别精度。
④构建了逐次故障诊断神经网络模型,并从遗传算法特征选择后的特征参数集中选出灵敏度较大的三个特征参数作为逐次诊断神经网络的输入,降低了输入量的维数。
The ability of rotating machinery's symptom parameters (SPS) in distinguishing two states is studied in this paper, the evaluation standard of SPS is put forward. Based on traditional SPS, a way of using genetic algorithm (GA) to create new and high SPS by self-organization traditional SPS is proposed, the feature set composed of all s SPS is selected by GA , and redundant symptoms are removed by this way. The sequential diagnosis model based on neural network (NN) is build up, the dimension of input is decreased. The practical example of condition diagnosis is shown to verify the efficiency of the method proposed in this paper. The diagnosis system combined evaluation of SPS sensitivity, feature extraction, feature selection and sequential diagnosis model. This paper has innovation and engineering value. The main results and conclusions is presented as follows:
①The sensitivity of SPS is proposed to evaluate the ability of distinguishing two states. And the formula sensitivity is derived theoretically. We verifies that parameters sensitivity is proportional to the distinction rate (DR). SPS with high sensitivity have best DR.
②The sensitivity of traditional SPS is not high enough. We extract new and high sensitivity SPS with GA. SPS are self-organization and new SPS are created in this way. Arborescence is expressed to SPS formula and then intercrossed and variated by GA. Sensitivity of SPS is used as fitness.
③In this paper, the feature set is composed of traditional SPS and new SPS created by GA. We use inner and outer distance as fitness function and select most effective SPS by GA. It can decrease the feature set’s dimension and increase the precision of SPS distinguishing two states. Redundant SPS are removed.
④The sequential diagnosis model is build. Three SPS than have high sensitivity are selected and used as the inputs of sequential diagnosis neural network. Dimension of inputs is decreased.
①提出了用于评价特征参数识别故障的灵敏度的概念。并假设特征参数概率密度函数是正态分布情况下,从理论上推导出了灵敏度的计算公式。最后通过实验验证了灵敏度与特征参数区分两种状态的识别率是成正比关系的,灵敏度高的特征参数就具有高的识别率。
②传统特征参数不能很好的区分两种状态,文中采用遗传算法重新提取新的高灵敏度的特征参数;该方法是对传统的特征参数进行再组织生成新的特征参数,文中用树形图来表示特征参数的公式,便于利用遗传算法进行交叉和变异;用特征参数灵敏度作为遗传算法的适应度函数。最后实验验证了新的特征参数的识别率高,证明了该方法的有效性。
③文中将传统特征参数和由遗传算法提取的新的特征参数共17个组成特征参数集合。提出了以类内和类间距离为适应度函数,基于遗传算法的特征选择策略,选择出最有效的几个特征参数来降维,同时达到提高识别两类状态识别率的目的。该方法能够充分利用遗传算法的隐并行性,有效地剔除原始特征集中冗余特征参数。并利用实验验证了将优化后的特征集合用于神经网络分类器训练,能够提高故障的识别精度。
④构建了逐次故障诊断神经网络模型,并从遗传算法特征选择后的特征参数集中选出灵敏度较大的三个特征参数作为逐次诊断神经网络的输入,降低了输入量的维数。
The ability of rotating machinery's symptom parameters (SPS) in distinguishing two states is studied in this paper, the evaluation standard of SPS is put forward. Based on traditional SPS, a way of using genetic algorithm (GA) to create new and high SPS by self-organization traditional SPS is proposed, the feature set composed of all s SPS is selected by GA , and redundant symptoms are removed by this way. The sequential diagnosis model based on neural network (NN) is build up, the dimension of input is decreased. The practical example of condition diagnosis is shown to verify the efficiency of the method proposed in this paper. The diagnosis system combined evaluation of SPS sensitivity, feature extraction, feature selection and sequential diagnosis model. This paper has innovation and engineering value. The main results and conclusions is presented as follows:
①The sensitivity of SPS is proposed to evaluate the ability of distinguishing two states. And the formula sensitivity is derived theoretically. We verifies that parameters sensitivity is proportional to the distinction rate (DR). SPS with high sensitivity have best DR.
②The sensitivity of traditional SPS is not high enough. We extract new and high sensitivity SPS with GA. SPS are self-organization and new SPS are created in this way. Arborescence is expressed to SPS formula and then intercrossed and variated by GA. Sensitivity of SPS is used as fitness.
③In this paper, the feature set is composed of traditional SPS and new SPS created by GA. We use inner and outer distance as fitness function and select most effective SPS by GA. It can decrease the feature set’s dimension and increase the precision of SPS distinguishing two states. Redundant SPS are removed.
④The sequential diagnosis model is build. Three SPS than have high sensitivity are selected and used as the inputs of sequential diagnosis neural network. Dimension of inputs is decreased.
引文
[1]陈长征等编著.设备振动分析与故障诊断技术[M].北京:科学出版社, 2007.
[2]杨军等编著.装备智能故障诊断技术[M].北京:国防工业出版社, 2004.
[3]盛兆顺,尹琦岭主编.设备状态监测与故障诊断技术及应用[M].北京:化学工业出版社, 2003.
[4]易良集编著.简易振动诊断现场实用技术[M].北京:机械工业出版社,2003.
[5]陈大禧,朱铁光编著.大型回转机械诊断现场实用技术[M].北京:机械工业出版社, 2002.
[6]钟秉林,黄仁编著.机械故障诊断学(第三版)[M].北京:机械工业出版社,2006.
[7]卢文祥,杜润生编著.工程测试与信息处理[M].武汉:华中科技大学出版社,2002.
[8]滕召胜著.智能检测系统与数据融合[M].北京:机械工业出版社,2000.
[9]焦卫东.基于独立分量分析的旋转机械故障诊断方法研究[D].杭州:浙江大学博士学位论文,2003.
[10]叶大鹏.基于2D-HMM的旋转机械故障诊断方法及其应用研究[D].杭州:浙江大学博士学位论文,2004.
[11]杨宇.基于EMD和支持向量机的旋转机械故障诊断方法研究[D].长沙:湖南大学博士学位论文,2005.
[12]肯永刚.机电设备监测诊断时域新方法的应用研究[D].西安:西安交通大学,2003.
[13]孟庆丰,何正嘉,赵纪元.数字滤波在机械故障诊断方法中的应用技术[J].动态分析与测试技术,1994, (4): 5-10.
[14] Newland D E. Progress in the application of wavelet theory to vibration analysis[J]. 15th Proceedings of the 1995 AS ME Design Engineering Technical Conference, 1995.
[15]昌大伟.旋转机械故障诊断专家系统知识库与诊断推理的研究[D].浙江:浙江工业大学,2001.
[16]李跃华,杨小健,糜元根.小波变换用于采样信号的噪声滤除[J].南京化工大学学报,1999,21(2): 56-58.
[17]张民,丁常富,韩中合.小波分析在振动信号处理领域中的应用[J].电力情报, 2001 (3): 5-7.
[18]刘峰.基于神经网络的水轮发电机组振动故障诊断专家系统的研究[D].西安:西安理工大学,2003.
[19]甘晓哗.基于小波分解的信噪分离[J].振动与冲击, 2001,20 (4): 68-71.
[20]何勇,李增芳.智能化故障诊断技术的研究与应用[J].浙江大学学报(农业与生命科学版). 2003,29(2):119-124.
[21]何正嘉,李富才,杜远等.小波技术在机械监测诊断领域的应用现状与进展[J].西安交通大学学报, 2001, 35 (5): 540-545.
[22] Sohre J s. Trouble-shooting to stop vibration of centrifugal[J]. Petrol/Chem. Engineering,1968,11:22-33.
[23]白木万博(日).机械振动讲演论文集[C].郑州:郑州机械研究所,1984.
[24]韩清凯,俞建成,宫照民等.大型旋转机械振动现场测试与故障特征分析[J].振动、测试与诊断,2003,23(1):10-13.
[25]李录平,邹新元,陈荐等.汽轮发电机组碰磨故障的典型特征研究[J].振动、测试与诊断,2001,21(4):281-285
[26]徐敏强,王日新,张喜钟.基于梳状小波的旋转机械振动信号降噪方法的研究.振动工程学报, 2002,15 (1) : 90-92.
[27] Zhou Xiong, Wang Huaqing, Chen Peng, TANG Yike. Advances in Neural Networks-ISSN2008. 2008-Springer Volume 5264/2008:473-482.
[28] Zhou Xiong, Chen Peng, TANG Yike. Sequential Diagnosis for a Centrifugal Pump Based on Fuzzy Neural Network[J]. CHINESE JOURNAL OF MECHANICAL ENGINEERING. 2008.21(5).pp81-85.
[29]薛定宇,陈阳泉著.高等应用数学问题的MATLAB求解[M].北京:清华大学出版社, 2004.
[30]易丹辉.数据分析与E2Views应用[M].北京:中国统计出版社,2002.
[31]胡劲松,杨世锡,吴昭同等.基于经验模态分解的旋转机械振动信号滤波技术研究[J].振动、测试与诊断, 2003,23(2):96-98.
[32]胡劲松.面向旋转机械故障诊断的经验模态分解时频分析方法及实验研究[D].杭州:浙江大学机械系,2003.
[33]周强,顾必冲.一种机械故障信号滤波器的设计[J].水利电力机械,1998, (3): 15-16.
[34]王立忠,屈梁生.自相关的除噪作用及其在工程中的应用[J].中国设备工程,2001, (7) : 35-36.
[35] Unal A. Feature article, intelligent diagnostics of ball bearings[J]. The shock and vibration digest, 1994, (11): 9-12.
[36]屈梁生,何正嘉编著.机械故障诊断学[M].上海:上海科学技术出版社,1986.
[37]杨叔子,吴雅编著.时间序列分析的工程应用[M].武汉:华中理工大学出版社,1991.
[38]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(3): 104-107.
[39]张卫民,王信义,王克勇.时序模型参数及AR谱在压缩机故障检测中的应用[J].压缩机技术, 1997,(1): 25-28.
[40] Dote Y, OVaSKa S J, Gao Xiao-Zhi. Fault detection using RBFN- and AR-based general parameter methods. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 2001 (1):77-80.
[41] P. CHEN, X. LIANG and T. YAMAMOTO . Rough sets and partially-linearized neural network for structural fault diagnosis of rotating machinery[J]. ADVANCES IN NEURAL NETWORKS-ISNN 2004, PT 2 LECTURE NOTES IN COMPUTER SCIENCE 3174:574-580, SPRINGER, 2004.
[42]黄石红,陈勇.时序信号处理在旋转机械故障诊断中的应用研究[J].汽轮机技术,2001, 43(6) : 355-356.
[43]杨文献,徐光华,屈梁生.时域信号复杂度指标的建立及其在机械故障诊断技术中的应用. 1999, 10 (3):307-310.
[44] Cooley J W, Tukey J W. An algorithm for the machine calculation of complex Fourier series[J]. Mathematics of Computation, 1965,19(90):297-301.
[45]丁康,陈健林,苏向荣.平稳和非平稳振动信号的若干处理方法及发展[J].振动工程学报,2003, 16(1):1-10.
[46]丁康,谢明.离散频谱三点卷积幅值修正法的误差分析[J].振动工程学报,1996, 9 (1): 92-98.
[47] Burgess J C. On digital spectrum analysis of periodic signals[J]. J Acoust Soc Am. 1975,58 (3):556-567.
[48] Grandke T. Interpolation algorithms for discrete Fourier transforms of weighted signals[J]. IEEE Trans on Instru and Meas. 1983, IM-32(2):350-355.
[49]黄迪山. FFT相位误差分析及实用修正方法[J].振动工程学报,1994,7(2):185-189.
[50]刘明,张晓飞,丁康.频谱分析中相位和频率校正的一种新方法一相位差校正法[J].振动工程学报,1999,12(4): 454-459.
[51]丁康,张晓飞.频谱校正理论的发展[J].振动工程学报,2000,13(1):14-22.
[52]陈进.信号处理在机械设备故障诊断中的应用[J].振动与冲击, 1999,18(2):89-93.
[53]何正嘉,赵纪元,孟庆丰等.机械监测诊断中非平稳性信号处理的研究[J].西安交通大学学报,1996, 30(7):36-42.
[54]张春梅,王尚锦,张太锐等.时频分析在旋转机械状态监测及故障诊断中的应用[J].工程热物理学报,2002, 23(2): 187-189.
[55]郭永基.可靠性工程原理[M].北京:清华大学出版社,2002.
[56] Peng Chen, Toshio Toyota, Automated function generation of symptom parameters and application to fault diagnosis of machinery under variable operating conditions[J].Systems and Humans. 2001(11): 775~781.
[57] Spanjaard J M, Sherman P J, White L B, et al. Periodic autoregressive time-frequency analysis for monitoring of rotating machinery with variable period[J]. Time-frequency and time scale analysis, Proceedings of the IEEE SP International symposium, 1996:456-478.
[58] Peter W,Tsea, Wen-xian Yang,H.Y. Tam. Machine fault diagnosis through an effective exact wavelet analysis[J]. Journal of Sound and Vibration , 2004(277): 1005~1024.
[59] B.Samanta, K.R.Al-Balushi, S. A . Al-Araimi. Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection[J]. Engineering Applications of Artificial Intelligence, 2003 (7):57~65.
[60] X. Z. Gao, S. J. Ovaska. Genetic Algorithm Training of Elman Neural Network in Motor Fault Detection[J]. Neural Computing & Applications, 2002(1): p37~44.
[61]谢可夫,罗安.遗传算法在变压器故障诊断中的应用[J].电力自动化议备. 2005(4).
[62] Peter W, Tsea, Wen-xian Yang, H.Y. Tam.Machine fault diagnosis through an effective exact wavelet analysis[J]. Journal of Sound and Vibration 2004(277): 1005~1024.
[63]骆志高,陈鹏等.用于机械诊断的最佳特征参数自动生成法[J].农业机械学报, 2000(11):84~87.
[64]王娟,慈林林,姚康泽.特征选择方法综述.计算机工程与科学[J], 2005(12):68-70.
[65]苏映雪.特征选择算法研究[D].国防科学技术大学, 2006,11.
[66]毛勇,周晓波,夏铮,尹征,孙优贤.特征选择算法研究综述[J].模式识别与人工智能, 2007(2).
[67]严竣,朱利民.信号短时分析方法在机械故障诊断中的应用[J].南京邮电学院学报(自然科学版),1999, 19(4) 79-82.
[68] Ye H, Ding S X, Wang G. Integrated design of fault detection systems in time-frequency domain[J]. Automatic control IEEE Trans, 2002, 47(2): 384-390.
[69] Pon V S, Papandreou S L, Suppappola S B. Detecting faults in structures using time-frequency techniques[J]. ASSP IEEE International conference, 2002, 6: 3593-3596.
[70] Lee J Y, Won Y J, Jeong J M et al. Classification of power disturbances using feature extraction in time-frequency plane[J]. Electronics Letters, 2002, 38 (15):833-835.
[71]何正嘉.机械监测诊断中的小波应用技术(连载)[J].设备维修与管理,1998, (8):19-21, (9): 21-24.
[72]王吉军.一种改进的Morlet小波变换及其在工程中应用[J].振动工程学报,1997,10(2):208-212.
[73] Sung C K, Tai H M, Chen C W. Wavelets and imaging informatics: a review of the literature[J]. Mechanism and machine theory, 2000, 35(8):1169-1182.
[74] Zheng H, Ll Z, Chen X. Gear fault diagnosis based on continuous wavelet transform[J]. Mechanical Systems and Signal Processing,2002,16(2-3): 447-457.
[75] Yu Yang, Dejie Yu etc. A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM[J]. Measurement 40 (2007) :943-950.
[76] Kong F C, Ruheng. A combined method for triplex pump fault diagnosis based on wavelet transform, fuzzy logic and neuro-networks[J]. Mechanical Systems and Signal Processing, 2004, 18(1): 161-168.
[77]崔锦泰.小波分析导论[M].西安:西安交通大学出版社,1995.
[78] Li-chen L. On the convergence of wavelet-based iterative signal extrapolation algorithms[J]. Signal processing,1996,48:51-65.
[79] Changzheng Chen,Changtao Mo. A method for intelligent fault diagnosis of rotating machinery. Digital Signal Processing .14 (2004): 203–217.
[80] Sun Tao, Li Ming, Huang T S etc. Fault feature extraction of hydro-generator vibration signals based on wavelet shrinkage. In: Proceedings of the Third International Conference on Wavelet Analysis and Its Applications (WAA),Chongqing, China,2003.
[81] Newland, David E. Progress in the application of wavelet theory to vibration analysis. In: 15th Proceedings of the 1995 ASME Design Engineering Technical Conference, Boston, MA, USA 1995
[82]钟佑明,秦树人,汤宝平.一种振动信号新变换法的研究[J].振动工程学报,2002,15(2):233-238.
[83]胡劲松,杨世锡,吴昭同等.旋转机械振动信号基于EMD的HT和STF7分析比较[J].汽轮机技术,2002, 44(6):336-338.
[84]万书亭,李和明.汽轮发电机组轴心轨迹进动方向自动识别新方法[J].中国电机工程学报,2003, 23(3):146-149,160.
[85] Liangsheng Qu. The holo-spectrum: A new method for rotator surveillance and diagnosis. Mechanical system and signal processing. 1989, 13(1): 255-267.
[86]虞和济,韩大庆.设备故障诊断工程[J].北京:冶金工业出版社.2001.
[87]王峰.滚动轴承故障特征的提取和优化[D].西安:西安交通大学硕士论文,2002.
[88] Chow T. HOS non-parametric and parametric methodologies for machine fault detection, IEEE Trans. On Industrial electronics. 2000, 47(5): 1051-1059.
[89] Collis W B, White P R, Hammond J K. Higher-order spectra: the bispectrum and trispectrum. Mechanical systems and signal processing, 1998, 12(3): 375-394.
[90] Toyota T.Condition monitoring and diagnosis of rotating machinery by Gram-Charlier expansion of vibration signal. The fourth international conference on knowledge basedintelligent engineering systems and allied technologies, 2000, (2): 541-544.
[91]虞和济等编著.基于神经网络的智能诊断[M] .北京:冶金工业出版社,2000.
[92]史铁林,陈勇辉,李巍华等.提高大型复杂机电系统故障质量的几种新方法[J].机械工程学报,2003,39(9) : 1-10.
[93] Frank P M. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results. Automatica, 1990, 26(3): 459-474.
[94] Frank P M. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results. Automatica, 1990, 26(3): 459-474.
[95] Polycarpeu M M, Helnsicki A T Leaming methodology for failure detection and accommodation. 1995, (6): 16-24.
[96] Stuart J D. Turbo Mac an expert system to aid in the diagnosis of cause of vibration producing problem in large tubro-machinery. Proceeding ofASME computer in Engineer. Cant Boston USA 1985: 217-319.
[97]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社,1999.
[98] Wang H, Daley S. Actuator fault diagnosis:an adaptive observer-based technique. IEEE Transaction on automatic control, 1996,41(7):1073-1078.
[99]王小平,曹立明等.遗传算法理论应用与软件实现[M].西安:西安交通大学出版社.2002.
[100]郭晶,杨章玉. MATLAB 6.5辅助神经网络分析与设计[M].北京:电子工业出版社.2003.
[101] Stuart J D. Turbo Mac an expert system to aid in the diagnosis of cause of vibration producing problem in large tubro-machinery. Proceeding of ASME computer in Engineer. Cant Boston USA 1985: 217-319.
[102]史东锋,屈梁生等.遗传算法在故障特征选择中的应用研究[J].振动、测试与诊断.2000,20(3):171-176.
[103]吴今培.智能故障诊断技术的发展和展望[J].振动测试与诊断,1999,19(2): 79-86.
[104] Fink P K, Lusth J C. Expert system and diagnostic expertise in the mechanical and electrical domains. IEEE Trans on SMC, 1987, 17(3):340-349.
[105] White M F. Expert system based diagnosis of turbo machinery. In: Proc of IMEKO, 5th international symptom technical diagnosis, WG,1987.
[106]高贤维,刘三民等.基于遗传算法和神经网络的特征提取.计算机与现代化.2008,152(4):23-26.
[107]赵云,刘惟一.基于遗传算法的特征选择方法[J].计算机工程与应用,2004,15:52-54.
[108]王锋,屈梁生.用遗传编程方法提取和优化机械故障的声音特征[J ] .西安交通大学学报,2002 (12) :1307 - 1310.
[109] Liu Zhengjun.Wang Chang etc. Feature Extraction and Feature Selection Based on Waveletand Genetic Algorithm. Journal of Remote Sensing, 2005,9(2):176-185.
[110]王新峰,邱静.机械故障特征与分类器的联合优化[J].国防科技大学学报.2005,27(2):92-95.
[111]任江涛,黄焕宇等.基于相关性分析及遗传算法的高维数据特征选择[J].计算机应用.2006,26(6):1043-1045.
[112]谢涛,张育林.基于遗产算法与最大最小原理的故障模式特征选择.国防科技大学学报.1998,20(2):17-21
[113]杨世锡.基于神经网络的大型旋转机械故障诊断专家系统研究[D].杭州:浙江大学博士学位论文,1997.
[114]骆志高,田海泉等.遗传算法在故障中的应用研究综述[J].煤矿机械, 2006,27(1):169-172.
[115] Marcu T, Mirea L. Robust detection and isolation of process faults using neural networks. IEEE control system magazine, 1997:72-79.
[116] Venk V, Chan K. A neural network methodology for process fault diagnosis, AICHE J, 1989, 35:1993-2002.
[117] Weerasinghe M, Gomm J, Williams D. Neural network for fault diagnosis of a nuclear fuel processing plant at different operating points. Control Engrg. Practice, 1998,6:281-289.
[118] McCormick A C, Nandi A K. A comparison of artificial neural networks and other statistical methods for rotating machine condition classification. Modeling and Signal Processing for Fault Diagnosis (Digest No.: 1996/260), IEEE Colloquium on,1996, 2: 1-6.
[119] Meneganti M, Savidllo F, Tagliaferri R. Fuzzy neural networks for classification and detection of anomalies. IEEE Trans neural networks, 1998, 9(5):848-861.
[120] Tang T, Zhu Y, Li J et al. A fuzzy and neural network integrated intelligence approach for fault diagnosing and monitoring. In: Control'98. UKACC International Conference on (Conf Publ. No. 455), Swansea, UK, 1998.
[121] Taniguchi S, Akhmetov D, Dote Y Fault detection of rotating machine parts using novel fuzzy neural network. In: Systems, Man, and Cybernetics, 1999. IEEE SMC'99 Conference Proceedings, Tokyo,Japan, 1999.
[122] Xiaoqin Wen, Zhiyi Sun. Fault diagnosis approach based on fuzzy neural networks and its application.
[123] Control and Automation, 2002. ICCA_ Final Program and Book of Abstracts, 2002:217-218.
[124]何成兵,顾煌炯,杨昆.一种改进模糊神经网络及其在故障诊断中的应用[J].振动工程学报,2003, 16 (1):95-98.
[125] Sheng Zhang, Asakura T, Xiaoli Xu etal. Fault diagnosis system for rotary machines based onfuzzy neural networks. Advanced Intelligent Mechatronics, 2003. AIM 2003. Proceedings,2003:199-204.
[126] Khoo L P, Zhai L Y A rough set approach to the treatment of continuous-valued attributes in multi-concept classification for mechanical diagnosis. Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM, 2001,15 (3):211-221.
[127]许琦,顾海明,李永生.粗集理论及其在旋转机械故障诊断中的应用(二)旋转机械故障诊断知识库的形成[J].南京工业大学学报,2002,24(2):30-33.
[128] Jae Hong Suh, Soundar R. T. Kumara , Shreesh P. Mysore. Machinery Fault Diagnosis and Prognosis: Application of Advanced Signal Processing Techniques. Annals of the ClRP.1999,48(1):318-321.
[129] Xiaofeng Liu, Lin Ma , Joseph Mathew. Machinery Fault Diagnosis Based on Feature Level Fuzzy Integral Data Fusion Techniques. 2006 IEEE International Conference on Industrial Informatics. 2006:857-862.
[130] Yoshiki KAWABE, Kenji MAEGAWA etc. Diagnosis Method of Centrifugal Pumps by Rough Sets and Partially -linearized Neural Network. 1997 IEEE International Conference on Intelligent Processing Systems. Beijing. China. 1997:1490-1494.
[131] Jian-Da Wu , Chiu-Hong Liu. Investigation of engine fault diagnosis using discrete wavelet transform and neural network. Expert Systems with Applications. 2007:1-14;
[132] Mingsian Bai, Jiamin Huang, Minghong Hong, Fucheng Su. Fault diagnosis of rotating machinery using an intelligent order tracking system. Journal of Sound and Vibration.2005:699-718.
[133] Heck, L P, McClellan, J H. Mechanical system monitoring using hidden Markov models. Acoustics, Speech, and Signal Processing, 1991. ICASSP-91 ., 1991 International Conference on, 1991, 3: 1697 -1700.
[134] Owsley L. M D, Atlas L E, Bernard G D. Self-organizing feature maps and hidden M arkov models for machines-tool monitoring. IEEE Trans on signal processing, 1997, 45(11):2787-2798.
[135] Ertunc, H.M., Loparo, K.A-, Ozdemir, E., Ocak, H. Real time monitoring of tool wear using multiple modeling method. Electric Machines and Drives Conference, 2001. IEMDC 2001. IEEE International, 2001: 687 -691.
[136] Padhraic s. Hidden Markov models for fault detection in dynamic systems. Pattern Recognition. 1994, 27(l): 149-164.
[137] Kee-Choon K. Accident identification in nuclear power plants using hidden Markov models. Engineering applications of AI. 1999, (12): 491-501.
[138] Ocak, H., Loparo, K.A. new bearing fault detection end diagnosis scheme based on hidden Markov modeling of vibration signals. In: ICASSP IEEE Int ConfAcoust Speech Signal Process Proc, Salt Lake, U T,2001.
[139] Ge M, Du凡Xu Y Hidden Markov model based fault diagnosis for stamping processes. Mechanical system and signal processing, 2004 (18) :391-408.
[140]童进,吴昭同,严拱标.大型旋转机械升降速过程故障诊断研究[J].振动测试与诊断,1999,19(3): 193-195.
[141]童进,吴昭同,严拱标.大型旋转机械升降速过程故障诊断HMM方法研究[J].机械科学与技术(西安),1999, 18(6): 973-975.
[142]丁启全,冯长建,吴昭同等.旋转机械启动全过程DHMM故障诊断方法研究.振动工程学报,2003,16(1):41-45.
[143]冯长建,丁启全,吴昭同.线性AR-HMM在旋转机械故障诊断中的应用[J].汽轮机技术,2002, 44(5):301-303.
[144] Zhinong Li, Zhaotong Wu, Yongyong He etc. Hidden Markov model-based fault diagnosis method in speed-up and speed-down process for rotating machinery. Mechanical Systems and Signal Processing, 2004, (1):1-11.
[145] Jacob Goldberger etc. Segmental modeling using a continuous mixture of non-parametric models. IEEE Trans. On speech and audio processing. 1999, 7(2): 262-271.
[146]叶大鹅,丁启全,吴昭同.基于2D-HMM旋转机械升速过程的故障诊断方法研究[J].中国机械工程,2003 14(13):1149-1151.
[147]叶大鹏,丁启全,吴昭同.基于小波的2D-HMM旋转机械升速过程故障诊断[J].农业机械学报,2004 35 (1):117-120.
[148]边雄棋,张学工等编著.模式识别(第二版)[M].北京:清华大学出版社,2000.
[149]赵力编著.语音信号处理[M].北京:机械工业出版社,2003.
[150]张贤达著.现代信号处理[M].北京:清华大学出版社,1995.
[151]蒋志凯编著.数字滤波与卡尔曼滤波[M].北京:中国科学技术,1993.
[152] Beattie V L, Young S J. Noisy speech recognition using hidden Markov model state based filtering. Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1991:917-920.
[153] Matrouf D, Gauvain J L. Using AR HMM state-dependent filtering for speech enhancement. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. 1999,2: 785 -788.
[154]邓自立著.最优滤波理论及其应用-现代时间序列分析方法[M].哈尔滨:哈尔滨工业大学出版社.2000.
[155]韩西京,史铁林.故障诊断中几种征兆自动获取技术研究[J].华中理工大学学报,1997,25(8):53-55.
[156]陈书凯.转子系统振动故障分析与诊断[D].南京:南京航空航天大学,2005.
[157]李录平,韩守木,黄树红等.旋转机械故障特征的定性提取[J].华中理工大学学报,1998,6(l):101-103.
[158] P Orowski.Selected Problems of frequency anaysis for time varying, discrete-time system using singular value decomposition and discrete Fourier transform. Journal of Sound and Vibration,2004(4):903-921.
[2]杨军等编著.装备智能故障诊断技术[M].北京:国防工业出版社, 2004.
[3]盛兆顺,尹琦岭主编.设备状态监测与故障诊断技术及应用[M].北京:化学工业出版社, 2003.
[4]易良集编著.简易振动诊断现场实用技术[M].北京:机械工业出版社,2003.
[5]陈大禧,朱铁光编著.大型回转机械诊断现场实用技术[M].北京:机械工业出版社, 2002.
[6]钟秉林,黄仁编著.机械故障诊断学(第三版)[M].北京:机械工业出版社,2006.
[7]卢文祥,杜润生编著.工程测试与信息处理[M].武汉:华中科技大学出版社,2002.
[8]滕召胜著.智能检测系统与数据融合[M].北京:机械工业出版社,2000.
[9]焦卫东.基于独立分量分析的旋转机械故障诊断方法研究[D].杭州:浙江大学博士学位论文,2003.
[10]叶大鹏.基于2D-HMM的旋转机械故障诊断方法及其应用研究[D].杭州:浙江大学博士学位论文,2004.
[11]杨宇.基于EMD和支持向量机的旋转机械故障诊断方法研究[D].长沙:湖南大学博士学位论文,2005.
[12]肯永刚.机电设备监测诊断时域新方法的应用研究[D].西安:西安交通大学,2003.
[13]孟庆丰,何正嘉,赵纪元.数字滤波在机械故障诊断方法中的应用技术[J].动态分析与测试技术,1994, (4): 5-10.
[14] Newland D E. Progress in the application of wavelet theory to vibration analysis[J]. 15th Proceedings of the 1995 AS ME Design Engineering Technical Conference, 1995.
[15]昌大伟.旋转机械故障诊断专家系统知识库与诊断推理的研究[D].浙江:浙江工业大学,2001.
[16]李跃华,杨小健,糜元根.小波变换用于采样信号的噪声滤除[J].南京化工大学学报,1999,21(2): 56-58.
[17]张民,丁常富,韩中合.小波分析在振动信号处理领域中的应用[J].电力情报, 2001 (3): 5-7.
[18]刘峰.基于神经网络的水轮发电机组振动故障诊断专家系统的研究[D].西安:西安理工大学,2003.
[19]甘晓哗.基于小波分解的信噪分离[J].振动与冲击, 2001,20 (4): 68-71.
[20]何勇,李增芳.智能化故障诊断技术的研究与应用[J].浙江大学学报(农业与生命科学版). 2003,29(2):119-124.
[21]何正嘉,李富才,杜远等.小波技术在机械监测诊断领域的应用现状与进展[J].西安交通大学学报, 2001, 35 (5): 540-545.
[22] Sohre J s. Trouble-shooting to stop vibration of centrifugal[J]. Petrol/Chem. Engineering,1968,11:22-33.
[23]白木万博(日).机械振动讲演论文集[C].郑州:郑州机械研究所,1984.
[24]韩清凯,俞建成,宫照民等.大型旋转机械振动现场测试与故障特征分析[J].振动、测试与诊断,2003,23(1):10-13.
[25]李录平,邹新元,陈荐等.汽轮发电机组碰磨故障的典型特征研究[J].振动、测试与诊断,2001,21(4):281-285
[26]徐敏强,王日新,张喜钟.基于梳状小波的旋转机械振动信号降噪方法的研究.振动工程学报, 2002,15 (1) : 90-92.
[27] Zhou Xiong, Wang Huaqing, Chen Peng, TANG Yike. Advances in Neural Networks-ISSN2008. 2008-Springer Volume 5264/2008:473-482.
[28] Zhou Xiong, Chen Peng, TANG Yike. Sequential Diagnosis for a Centrifugal Pump Based on Fuzzy Neural Network[J]. CHINESE JOURNAL OF MECHANICAL ENGINEERING. 2008.21(5).pp81-85.
[29]薛定宇,陈阳泉著.高等应用数学问题的MATLAB求解[M].北京:清华大学出版社, 2004.
[30]易丹辉.数据分析与E2Views应用[M].北京:中国统计出版社,2002.
[31]胡劲松,杨世锡,吴昭同等.基于经验模态分解的旋转机械振动信号滤波技术研究[J].振动、测试与诊断, 2003,23(2):96-98.
[32]胡劲松.面向旋转机械故障诊断的经验模态分解时频分析方法及实验研究[D].杭州:浙江大学机械系,2003.
[33]周强,顾必冲.一种机械故障信号滤波器的设计[J].水利电力机械,1998, (3): 15-16.
[34]王立忠,屈梁生.自相关的除噪作用及其在工程中的应用[J].中国设备工程,2001, (7) : 35-36.
[35] Unal A. Feature article, intelligent diagnostics of ball bearings[J]. The shock and vibration digest, 1994, (11): 9-12.
[36]屈梁生,何正嘉编著.机械故障诊断学[M].上海:上海科学技术出版社,1986.
[37]杨叔子,吴雅编著.时间序列分析的工程应用[M].武汉:华中理工大学出版社,1991.
[38]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(3): 104-107.
[39]张卫民,王信义,王克勇.时序模型参数及AR谱在压缩机故障检测中的应用[J].压缩机技术, 1997,(1): 25-28.
[40] Dote Y, OVaSKa S J, Gao Xiao-Zhi. Fault detection using RBFN- and AR-based general parameter methods. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 2001 (1):77-80.
[41] P. CHEN, X. LIANG and T. YAMAMOTO . Rough sets and partially-linearized neural network for structural fault diagnosis of rotating machinery[J]. ADVANCES IN NEURAL NETWORKS-ISNN 2004, PT 2 LECTURE NOTES IN COMPUTER SCIENCE 3174:574-580, SPRINGER, 2004.
[42]黄石红,陈勇.时序信号处理在旋转机械故障诊断中的应用研究[J].汽轮机技术,2001, 43(6) : 355-356.
[43]杨文献,徐光华,屈梁生.时域信号复杂度指标的建立及其在机械故障诊断技术中的应用. 1999, 10 (3):307-310.
[44] Cooley J W, Tukey J W. An algorithm for the machine calculation of complex Fourier series[J]. Mathematics of Computation, 1965,19(90):297-301.
[45]丁康,陈健林,苏向荣.平稳和非平稳振动信号的若干处理方法及发展[J].振动工程学报,2003, 16(1):1-10.
[46]丁康,谢明.离散频谱三点卷积幅值修正法的误差分析[J].振动工程学报,1996, 9 (1): 92-98.
[47] Burgess J C. On digital spectrum analysis of periodic signals[J]. J Acoust Soc Am. 1975,58 (3):556-567.
[48] Grandke T. Interpolation algorithms for discrete Fourier transforms of weighted signals[J]. IEEE Trans on Instru and Meas. 1983, IM-32(2):350-355.
[49]黄迪山. FFT相位误差分析及实用修正方法[J].振动工程学报,1994,7(2):185-189.
[50]刘明,张晓飞,丁康.频谱分析中相位和频率校正的一种新方法一相位差校正法[J].振动工程学报,1999,12(4): 454-459.
[51]丁康,张晓飞.频谱校正理论的发展[J].振动工程学报,2000,13(1):14-22.
[52]陈进.信号处理在机械设备故障诊断中的应用[J].振动与冲击, 1999,18(2):89-93.
[53]何正嘉,赵纪元,孟庆丰等.机械监测诊断中非平稳性信号处理的研究[J].西安交通大学学报,1996, 30(7):36-42.
[54]张春梅,王尚锦,张太锐等.时频分析在旋转机械状态监测及故障诊断中的应用[J].工程热物理学报,2002, 23(2): 187-189.
[55]郭永基.可靠性工程原理[M].北京:清华大学出版社,2002.
[56] Peng Chen, Toshio Toyota, Automated function generation of symptom parameters and application to fault diagnosis of machinery under variable operating conditions[J].Systems and Humans. 2001(11): 775~781.
[57] Spanjaard J M, Sherman P J, White L B, et al. Periodic autoregressive time-frequency analysis for monitoring of rotating machinery with variable period[J]. Time-frequency and time scale analysis, Proceedings of the IEEE SP International symposium, 1996:456-478.
[58] Peter W,Tsea, Wen-xian Yang,H.Y. Tam. Machine fault diagnosis through an effective exact wavelet analysis[J]. Journal of Sound and Vibration , 2004(277): 1005~1024.
[59] B.Samanta, K.R.Al-Balushi, S. A . Al-Araimi. Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection[J]. Engineering Applications of Artificial Intelligence, 2003 (7):57~65.
[60] X. Z. Gao, S. J. Ovaska. Genetic Algorithm Training of Elman Neural Network in Motor Fault Detection[J]. Neural Computing & Applications, 2002(1): p37~44.
[61]谢可夫,罗安.遗传算法在变压器故障诊断中的应用[J].电力自动化议备. 2005(4).
[62] Peter W, Tsea, Wen-xian Yang, H.Y. Tam.Machine fault diagnosis through an effective exact wavelet analysis[J]. Journal of Sound and Vibration 2004(277): 1005~1024.
[63]骆志高,陈鹏等.用于机械诊断的最佳特征参数自动生成法[J].农业机械学报, 2000(11):84~87.
[64]王娟,慈林林,姚康泽.特征选择方法综述.计算机工程与科学[J], 2005(12):68-70.
[65]苏映雪.特征选择算法研究[D].国防科学技术大学, 2006,11.
[66]毛勇,周晓波,夏铮,尹征,孙优贤.特征选择算法研究综述[J].模式识别与人工智能, 2007(2).
[67]严竣,朱利民.信号短时分析方法在机械故障诊断中的应用[J].南京邮电学院学报(自然科学版),1999, 19(4) 79-82.
[68] Ye H, Ding S X, Wang G. Integrated design of fault detection systems in time-frequency domain[J]. Automatic control IEEE Trans, 2002, 47(2): 384-390.
[69] Pon V S, Papandreou S L, Suppappola S B. Detecting faults in structures using time-frequency techniques[J]. ASSP IEEE International conference, 2002, 6: 3593-3596.
[70] Lee J Y, Won Y J, Jeong J M et al. Classification of power disturbances using feature extraction in time-frequency plane[J]. Electronics Letters, 2002, 38 (15):833-835.
[71]何正嘉.机械监测诊断中的小波应用技术(连载)[J].设备维修与管理,1998, (8):19-21, (9): 21-24.
[72]王吉军.一种改进的Morlet小波变换及其在工程中应用[J].振动工程学报,1997,10(2):208-212.
[73] Sung C K, Tai H M, Chen C W. Wavelets and imaging informatics: a review of the literature[J]. Mechanism and machine theory, 2000, 35(8):1169-1182.
[74] Zheng H, Ll Z, Chen X. Gear fault diagnosis based on continuous wavelet transform[J]. Mechanical Systems and Signal Processing,2002,16(2-3): 447-457.
[75] Yu Yang, Dejie Yu etc. A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM[J]. Measurement 40 (2007) :943-950.
[76] Kong F C, Ruheng. A combined method for triplex pump fault diagnosis based on wavelet transform, fuzzy logic and neuro-networks[J]. Mechanical Systems and Signal Processing, 2004, 18(1): 161-168.
[77]崔锦泰.小波分析导论[M].西安:西安交通大学出版社,1995.
[78] Li-chen L. On the convergence of wavelet-based iterative signal extrapolation algorithms[J]. Signal processing,1996,48:51-65.
[79] Changzheng Chen,Changtao Mo. A method for intelligent fault diagnosis of rotating machinery. Digital Signal Processing .14 (2004): 203–217.
[80] Sun Tao, Li Ming, Huang T S etc. Fault feature extraction of hydro-generator vibration signals based on wavelet shrinkage. In: Proceedings of the Third International Conference on Wavelet Analysis and Its Applications (WAA),Chongqing, China,2003.
[81] Newland, David E. Progress in the application of wavelet theory to vibration analysis. In: 15th Proceedings of the 1995 ASME Design Engineering Technical Conference, Boston, MA, USA 1995
[82]钟佑明,秦树人,汤宝平.一种振动信号新变换法的研究[J].振动工程学报,2002,15(2):233-238.
[83]胡劲松,杨世锡,吴昭同等.旋转机械振动信号基于EMD的HT和STF7分析比较[J].汽轮机技术,2002, 44(6):336-338.
[84]万书亭,李和明.汽轮发电机组轴心轨迹进动方向自动识别新方法[J].中国电机工程学报,2003, 23(3):146-149,160.
[85] Liangsheng Qu. The holo-spectrum: A new method for rotator surveillance and diagnosis. Mechanical system and signal processing. 1989, 13(1): 255-267.
[86]虞和济,韩大庆.设备故障诊断工程[J].北京:冶金工业出版社.2001.
[87]王峰.滚动轴承故障特征的提取和优化[D].西安:西安交通大学硕士论文,2002.
[88] Chow T. HOS non-parametric and parametric methodologies for machine fault detection, IEEE Trans. On Industrial electronics. 2000, 47(5): 1051-1059.
[89] Collis W B, White P R, Hammond J K. Higher-order spectra: the bispectrum and trispectrum. Mechanical systems and signal processing, 1998, 12(3): 375-394.
[90] Toyota T.Condition monitoring and diagnosis of rotating machinery by Gram-Charlier expansion of vibration signal. The fourth international conference on knowledge basedintelligent engineering systems and allied technologies, 2000, (2): 541-544.
[91]虞和济等编著.基于神经网络的智能诊断[M] .北京:冶金工业出版社,2000.
[92]史铁林,陈勇辉,李巍华等.提高大型复杂机电系统故障质量的几种新方法[J].机械工程学报,2003,39(9) : 1-10.
[93] Frank P M. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results. Automatica, 1990, 26(3): 459-474.
[94] Frank P M. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results. Automatica, 1990, 26(3): 459-474.
[95] Polycarpeu M M, Helnsicki A T Leaming methodology for failure detection and accommodation. 1995, (6): 16-24.
[96] Stuart J D. Turbo Mac an expert system to aid in the diagnosis of cause of vibration producing problem in large tubro-machinery. Proceeding ofASME computer in Engineer. Cant Boston USA 1985: 217-319.
[97]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社,1999.
[98] Wang H, Daley S. Actuator fault diagnosis:an adaptive observer-based technique. IEEE Transaction on automatic control, 1996,41(7):1073-1078.
[99]王小平,曹立明等.遗传算法理论应用与软件实现[M].西安:西安交通大学出版社.2002.
[100]郭晶,杨章玉. MATLAB 6.5辅助神经网络分析与设计[M].北京:电子工业出版社.2003.
[101] Stuart J D. Turbo Mac an expert system to aid in the diagnosis of cause of vibration producing problem in large tubro-machinery. Proceeding of ASME computer in Engineer. Cant Boston USA 1985: 217-319.
[102]史东锋,屈梁生等.遗传算法在故障特征选择中的应用研究[J].振动、测试与诊断.2000,20(3):171-176.
[103]吴今培.智能故障诊断技术的发展和展望[J].振动测试与诊断,1999,19(2): 79-86.
[104] Fink P K, Lusth J C. Expert system and diagnostic expertise in the mechanical and electrical domains. IEEE Trans on SMC, 1987, 17(3):340-349.
[105] White M F. Expert system based diagnosis of turbo machinery. In: Proc of IMEKO, 5th international symptom technical diagnosis, WG,1987.
[106]高贤维,刘三民等.基于遗传算法和神经网络的特征提取.计算机与现代化.2008,152(4):23-26.
[107]赵云,刘惟一.基于遗传算法的特征选择方法[J].计算机工程与应用,2004,15:52-54.
[108]王锋,屈梁生.用遗传编程方法提取和优化机械故障的声音特征[J ] .西安交通大学学报,2002 (12) :1307 - 1310.
[109] Liu Zhengjun.Wang Chang etc. Feature Extraction and Feature Selection Based on Waveletand Genetic Algorithm. Journal of Remote Sensing, 2005,9(2):176-185.
[110]王新峰,邱静.机械故障特征与分类器的联合优化[J].国防科技大学学报.2005,27(2):92-95.
[111]任江涛,黄焕宇等.基于相关性分析及遗传算法的高维数据特征选择[J].计算机应用.2006,26(6):1043-1045.
[112]谢涛,张育林.基于遗产算法与最大最小原理的故障模式特征选择.国防科技大学学报.1998,20(2):17-21
[113]杨世锡.基于神经网络的大型旋转机械故障诊断专家系统研究[D].杭州:浙江大学博士学位论文,1997.
[114]骆志高,田海泉等.遗传算法在故障中的应用研究综述[J].煤矿机械, 2006,27(1):169-172.
[115] Marcu T, Mirea L. Robust detection and isolation of process faults using neural networks. IEEE control system magazine, 1997:72-79.
[116] Venk V, Chan K. A neural network methodology for process fault diagnosis, AICHE J, 1989, 35:1993-2002.
[117] Weerasinghe M, Gomm J, Williams D. Neural network for fault diagnosis of a nuclear fuel processing plant at different operating points. Control Engrg. Practice, 1998,6:281-289.
[118] McCormick A C, Nandi A K. A comparison of artificial neural networks and other statistical methods for rotating machine condition classification. Modeling and Signal Processing for Fault Diagnosis (Digest No.: 1996/260), IEEE Colloquium on,1996, 2: 1-6.
[119] Meneganti M, Savidllo F, Tagliaferri R. Fuzzy neural networks for classification and detection of anomalies. IEEE Trans neural networks, 1998, 9(5):848-861.
[120] Tang T, Zhu Y, Li J et al. A fuzzy and neural network integrated intelligence approach for fault diagnosing and monitoring. In: Control'98. UKACC International Conference on (Conf Publ. No. 455), Swansea, UK, 1998.
[121] Taniguchi S, Akhmetov D, Dote Y Fault detection of rotating machine parts using novel fuzzy neural network. In: Systems, Man, and Cybernetics, 1999. IEEE SMC'99 Conference Proceedings, Tokyo,Japan, 1999.
[122] Xiaoqin Wen, Zhiyi Sun. Fault diagnosis approach based on fuzzy neural networks and its application.
[123] Control and Automation, 2002. ICCA_ Final Program and Book of Abstracts, 2002:217-218.
[124]何成兵,顾煌炯,杨昆.一种改进模糊神经网络及其在故障诊断中的应用[J].振动工程学报,2003, 16 (1):95-98.
[125] Sheng Zhang, Asakura T, Xiaoli Xu etal. Fault diagnosis system for rotary machines based onfuzzy neural networks. Advanced Intelligent Mechatronics, 2003. AIM 2003. Proceedings,2003:199-204.
[126] Khoo L P, Zhai L Y A rough set approach to the treatment of continuous-valued attributes in multi-concept classification for mechanical diagnosis. Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM, 2001,15 (3):211-221.
[127]许琦,顾海明,李永生.粗集理论及其在旋转机械故障诊断中的应用(二)旋转机械故障诊断知识库的形成[J].南京工业大学学报,2002,24(2):30-33.
[128] Jae Hong Suh, Soundar R. T. Kumara , Shreesh P. Mysore. Machinery Fault Diagnosis and Prognosis: Application of Advanced Signal Processing Techniques. Annals of the ClRP.1999,48(1):318-321.
[129] Xiaofeng Liu, Lin Ma , Joseph Mathew. Machinery Fault Diagnosis Based on Feature Level Fuzzy Integral Data Fusion Techniques. 2006 IEEE International Conference on Industrial Informatics. 2006:857-862.
[130] Yoshiki KAWABE, Kenji MAEGAWA etc. Diagnosis Method of Centrifugal Pumps by Rough Sets and Partially -linearized Neural Network. 1997 IEEE International Conference on Intelligent Processing Systems. Beijing. China. 1997:1490-1494.
[131] Jian-Da Wu , Chiu-Hong Liu. Investigation of engine fault diagnosis using discrete wavelet transform and neural network. Expert Systems with Applications. 2007:1-14;
[132] Mingsian Bai, Jiamin Huang, Minghong Hong, Fucheng Su. Fault diagnosis of rotating machinery using an intelligent order tracking system. Journal of Sound and Vibration.2005:699-718.
[133] Heck, L P, McClellan, J H. Mechanical system monitoring using hidden Markov models. Acoustics, Speech, and Signal Processing, 1991. ICASSP-91 ., 1991 International Conference on, 1991, 3: 1697 -1700.
[134] Owsley L. M D, Atlas L E, Bernard G D. Self-organizing feature maps and hidden M arkov models for machines-tool monitoring. IEEE Trans on signal processing, 1997, 45(11):2787-2798.
[135] Ertunc, H.M., Loparo, K.A-, Ozdemir, E., Ocak, H. Real time monitoring of tool wear using multiple modeling method. Electric Machines and Drives Conference, 2001. IEMDC 2001. IEEE International, 2001: 687 -691.
[136] Padhraic s. Hidden Markov models for fault detection in dynamic systems. Pattern Recognition. 1994, 27(l): 149-164.
[137] Kee-Choon K. Accident identification in nuclear power plants using hidden Markov models. Engineering applications of AI. 1999, (12): 491-501.
[138] Ocak, H., Loparo, K.A. new bearing fault detection end diagnosis scheme based on hidden Markov modeling of vibration signals. In: ICASSP IEEE Int ConfAcoust Speech Signal Process Proc, Salt Lake, U T,2001.
[139] Ge M, Du凡Xu Y Hidden Markov model based fault diagnosis for stamping processes. Mechanical system and signal processing, 2004 (18) :391-408.
[140]童进,吴昭同,严拱标.大型旋转机械升降速过程故障诊断研究[J].振动测试与诊断,1999,19(3): 193-195.
[141]童进,吴昭同,严拱标.大型旋转机械升降速过程故障诊断HMM方法研究[J].机械科学与技术(西安),1999, 18(6): 973-975.
[142]丁启全,冯长建,吴昭同等.旋转机械启动全过程DHMM故障诊断方法研究.振动工程学报,2003,16(1):41-45.
[143]冯长建,丁启全,吴昭同.线性AR-HMM在旋转机械故障诊断中的应用[J].汽轮机技术,2002, 44(5):301-303.
[144] Zhinong Li, Zhaotong Wu, Yongyong He etc. Hidden Markov model-based fault diagnosis method in speed-up and speed-down process for rotating machinery. Mechanical Systems and Signal Processing, 2004, (1):1-11.
[145] Jacob Goldberger etc. Segmental modeling using a continuous mixture of non-parametric models. IEEE Trans. On speech and audio processing. 1999, 7(2): 262-271.
[146]叶大鹅,丁启全,吴昭同.基于2D-HMM旋转机械升速过程的故障诊断方法研究[J].中国机械工程,2003 14(13):1149-1151.
[147]叶大鹏,丁启全,吴昭同.基于小波的2D-HMM旋转机械升速过程故障诊断[J].农业机械学报,2004 35 (1):117-120.
[148]边雄棋,张学工等编著.模式识别(第二版)[M].北京:清华大学出版社,2000.
[149]赵力编著.语音信号处理[M].北京:机械工业出版社,2003.
[150]张贤达著.现代信号处理[M].北京:清华大学出版社,1995.
[151]蒋志凯编著.数字滤波与卡尔曼滤波[M].北京:中国科学技术,1993.
[152] Beattie V L, Young S J. Noisy speech recognition using hidden Markov model state based filtering. Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1991:917-920.
[153] Matrouf D, Gauvain J L. Using AR HMM state-dependent filtering for speech enhancement. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. 1999,2: 785 -788.
[154]邓自立著.最优滤波理论及其应用-现代时间序列分析方法[M].哈尔滨:哈尔滨工业大学出版社.2000.
[155]韩西京,史铁林.故障诊断中几种征兆自动获取技术研究[J].华中理工大学学报,1997,25(8):53-55.
[156]陈书凯.转子系统振动故障分析与诊断[D].南京:南京航空航天大学,2005.
[157]李录平,韩守木,黄树红等.旋转机械故障特征的定性提取[J].华中理工大学学报,1998,6(l):101-103.
[158] P Orowski.Selected Problems of frequency anaysis for time varying, discrete-time system using singular value decomposition and discrete Fourier transform. Journal of Sound and Vibration,2004(4):903-921.