摘要
本文以国家自然科学基金资助项目:“定量评价旋转机械振动状态的融合信息熵方法研究”为课题背景,以火力发电厂中的大型汽轮发电机组为研究对象,对汽轮机轴系典型振动故障诊断中的信息融合与定量诊断进行了研究,分别从时域、频域及时频域探讨了故障信号的信息融合方法,并将部分研究成果应用到实际的汽轮机故障诊断系统中。
首先,根据论文研究的需要,设计了汽轮机转子轴系故障模拟试验方案,并对各种故障进行了多组升速试验,获取了大量的故障试验数据,为论文的研究工作奠定了分析基础。对故障信号进行了傅立叶分析,以三维幅值谱和升速过程波德图为工具,对故障信号的频域信息进行了融合研究,同时验证了故障数据的正确性。
第二,研究了连续小波变换灰度图对信号的识别能力,提出利用小波灰度矩作为定量指标对信号的时频信息进行融合,对转子试验台故障模拟试验信号的研究表明,灰度矩可对汽轮机轴系故障进行有效识别,具有较好应用前景。在灰度矩研究基础上,进一步提出了分区灰度矩的思想,并提出利用一阶矩向量三维图对信号进行识别。研究表明,一阶矩向量三维图不仅融合了信号的时频特征,还融合了信号的空间特征,因而可用来对故障的产生过程进行全面分析,是进行轴系典型故障诊断的又一有效工具。
第三,基于信息熵方法,对故障信号的奇异谱熵、功率谱熵、小波能量谱熵、小波空间状态特征谱熵进行了融合研究,采用最小距离分类器和概率神经网络对四种信息熵特征进行了融合研究,并对融合结果进行了对照分析。研究表明,传统最小距离分类器对汽轮机轴系故障的识别能力较差,而改进的最小距离分类器通过对类中心的细化,有效提高了故障识别能力,在实时应用中具有一定的应用前景;概率神经网络综合了Bayes分类器和神经网络的优势,对汽轮机轴系典型故障具有很好的分类能力,故障识别正确率远远超过最小距离分类器,是实现汽轮机轴系故障识别的一种可行的诊断方法。
第四,研究了振动信号的分形维数对故障的表征能力。振动信号的分形维数较好地融合了波形的时域信息,可以定量地评估该时间序列在基线附近波动的不规则性,因而可实现对故障的识别。在对关联分形维计算研究的基础上,提出利用信号的二进小波高频重构信号计算关联维数。对转子试验台故障模拟试验信号的原始采样信号和高频重构信号分别计算了关联维数并进行了对照分析,结果表明,经过高频重构后的关联维数能够更好地进行故障识别,是对汽轮机典型故障进行定量诊断的有效时域特征,值得进行深入的理论和应用研究。
最后,研究了小波灰度图及小波灰度矩在实际诊断系统中的应用。研究了小波算法的程序实现,将小波灰度图及小波灰度矩作为独立的小波诊断模块,应用在某省的“汽轮机组振动远程监测及故障诊断专家系统”中。作为故障诊断的辅助模块,小波诊断模块在该远程诊断系统中发挥了应有的作用。
In this paper, the problem of information fusion and quantitative diagnosis of large-scale turbine generators were explored. The fusions of faulty signals were carried from time domain, frequency domain, and time-frequency domain respectively, and some research were applied on actual diagnosis system.
At first, the fault simulation rotor test rig of turbine rotor shaft system was designed, and several typical faulty signals during speed rising were collected from this rotor test rig. This established the analysis foundation in this paper. To check the correctness of collected faulty signals, the Fourier ways, 3-D amplitude spectrum and Bode diagram was used to analyze these signals.
At the second, the continuous wavelet transform scalogram was explored, and two features, wavelet gray moment and first-order wavelet gray moment vector, are proposed for fault classification of steam turbine rotor. The analysis indicates that first-order wavelet gray moment can reveal the time-frequency features of viberation signals well, and could be used to diagnose faults quantitatively. The effectiveness of the first-order wavelet gray moment vector is also demontrated by experimental data. Result show that the first-order wavelet gray moment vector is suitable to reflect the local information of scalogram, and would be a effective method of vibration signal analysis for fault diagnostics of rotating machinery.
At the third, based on the method of information entropy, fusion research on four information entropy: singular spectrum entropy, power spectrum entropy, wavelet energy spectrum entropy and wavelet space state spectrum entropy were carried. Two methods were explored to fuse the four information entropy above, one is the Minimum Distance Classifier (MDC), another is Probability Neural Networks(PNN). Research shows that general MDC has poor classification ability on faults, and the improved MDC has better classification ability than general MDC, which has a good future in real-time application; With the advantages of Bayes classifier and neural networks, Probability Neural Networks have good classification ability of typical vibration faults of turbine, the accuracy of classification is far more than that of improved MDC, so it can be deduced that PNN is a practical fusion diagnosis method for typical fault identification of turbine rotor.
The fourth, the fault classification ability by fractal dimension of vibration signal was researched. The fractal dimension of variation signal fuses the time domain information of signals well, which can evaluate irregularities of the time series’fluctuating on the baseline quantitatively, so it can be used as an index for fault identification. On the basis of computation research of correlative fractal dimension, two kinds of correlative dimension were calculated. One kind of correlative dimension was calculated from the time-serials of faulty signal directly, another kind of correlative dimension was calculated from the high frequency reconstruction signal of original time-serials. the analysis shows that correlative dimension can be used as a quantitative index for fault diagnosis, and the correlative dimension calculated from the high frequency reconstruction signal has better identification ability than that from time-serials, and is worthy of theoretical and applicable research.
At last, application of the wavelet transform scalogram and the first-order wavelet gray moment were researched and used in an actual diagnosis system. The program realization of wavelet algorithm was studied. The wavelet transform scalogram and the first-order wavelet gray moment were designed as an independent wavelet diagnosis module, and was applied on a provincial long-distance networked steam turbine group monitoring and fault diagnose system. As auxiliary module of fault diagnosis, the wavelet diagnosis module has played on its role in the long-distance diagnosis system.
引文
[1] 刘石, 屈梁生. 回转机械故障诊断中的三维全息谱技术. 西安交通大学学报, 2004, 38(9): 900-903
[2] 杜永祚, 秦志英. 旋转机械动态信号全息谱分析. 振动、测试与诊断, 2002, 22(2): 81-89
[3] Juluri, Naresh, Swarnamani. Improved accuracy of fault diagnosis of rotating machinery using wavelet de-noising and feature selection. American Society of Mechanical Engineers, International Gas Turbine Institute, 2003, (1): 563-571
[4] Changzheng Chen, Changtao Mo. A method for intelligent fault diagnosis of rotating machinery. Digital Signal Processing, 2004, 14(3): 203-17
[5] 秦岭, 杨君. 小波包分析在旋转机械故障诊断中的应用. 电子工程师 2006,32(1): 48-50
[6] 侯敬宏, 黄树红, 申弢等. 基于小波分析的旋转机械振动信号定量特征研究. 机械工程学报, 2004, 40(1): 131-135
[7] 乔海涛, 冯永新. 大型汽轮发电机组故障诊断技术现状与发展. 广东电力, 2003, 16(2), 9-13
[8] 张正松. 旋转机械振动监测及故障诊断. 北京: 机械工业出版社, 1991
[9] 陈炜峰, 陆静霞. 故障诊断技术及其发展趋势. 农机化研究, 2005, (2): 10-14
[10] 杨春燕, 朱茹敏, 李长诗. 多级混合数据融合在回转机械诊断中的应用. 郑州轻工业学院学报(自然科学版), 2005, 20(3): 84-88
[11] 王耀南, 李树涛.多传感器信息融合及应用综述. 控制与决策, 2001, 16(5): 518-522
[12] 邓乐. 多传感器信息融合技术与液压系统状态监测、故障诊断. 机床与液压, 2004, (2): 159-151
[13] Parham Aarabi, Safwat Zaky. Robust sound localization using multi-source audiovisual information fusion. Information Fusion, 2001, (2): 209-233
[14] Shu Li Sun. Multi-sensor information fusion white noise filter weighted by scalarsbased on Kalman predictor. Automation, 2004, 40: 1447-1453
[15] Hung Chin-Pao, Wang Mang-Hui, Cheng Chin-Hsing. Fault Diagnosis of Steam Turbine-generator Using CMAC Neural Network Approach. Proceedings of the International Joint Conference on Neural Networks, 2003, (4): 2988-2993
[16] Gail A. Carpenter, Siegfried Martens, Ogi J. Ogas. Self-organizing information fusion and hierarchical knowledge discovery: a new framework using ARTMAP neural networks. Neural Networks, 2005, 18: 287-295
[17] 孙卫祥, 陈进, 伍星等. 基于信息融合的支撑座早期松动故障诊断. 上海交通大学学报, 2006, (2): 239-242
[18] 李东辉, 周巍巍. 基于多分辨率小波网络_BP 神经网络_D_S 证据理论信息融合模型的直流系统故障诊断. 电网技术, 2004, 28(24): 16-20
[19] S.Fabre, A.Appriou, X. Briottet. Presentation and description of two classification methods using data fusion based on sensor management. Information Fusion, 2001, (2): 49-71
[20] Kunze, U. Condition telemonitoring and diagnosis of power plants using web technology. Progress in Nuclear Energy, 2003, 43(1-4): 129-136
[21] Chan, Christine W. An expert decision support system for monitoring and diagnosis of petroleum production and separation processes. Expert Systems With Applications, 2005, 29(1): 131-143
[22] 杨涛, 黄树红, 高伟等. 网络化汽轮机组远程监测及故障诊断系统的研究. 动力工程, 2004, 24(6): 840-844
[23] S.C. Patwardhan, S.L. Shah. From data to fault diagnosis and control. Part 1: Development of state observer, Journal of Process Control, 2005, 15: 819-835
[24] Qin Jianying and Wang Shengwei. A fault detection and diagnosis strategy of VAV air-conditioning systems for improved energy and control performances. Energy & Buildings, 2005, 37(10): 1035-1048
[25] S.C. Patwardhan, Manuja et al. From data to diagnosis and control using generalized orthonormal basis filters. Part II: Model predictive and fault tolerant control. Journal of Process Control, 2006, 16(2): 157-175
[26] 陈非, 黄树红, 张燕平等. 火电机组信息融合故障诊断方法及其发展. 振动、测试与诊断, 2005, 25(1): 17-22
[27] Y.M. Chena, H.C. Huangb. Fuzzy logic approach to multisensor data association. Mathematics and Computers in Simulation, 2000, 52: 399-412
[28] Shu-Li Sun, Zi-Li Deng. Multi-sensor optimal information fusion Kalman filter. Automatica, 2004, 40: 1017-1023
[29] Yang M., Manabe K., Hayashi K. et al. Data fusion of distributed AE sensors for the detection of friction sources during press forming. Journal of Materials Processing Technology, 2003, 139(1-3): 368-372
[30] Zhang S., Mathew J., Ma L. et al. Best basis-based intelligent machine fault diagnosis. Mechanical Systems and Signal Processing, 2005, 19(2): 357-370
[31] Z Zhang, R.S. Blum, A categorization of multiscale decomposition based image fusion schemes with a performance study for a digital camera application. Proceedings of IEEE, 1999, 87 (8): 1315-1326
[32] T. Ranchin, L. Wald. Fusion of high spatial and spectral resolution images: the ARSIS concept and its implementation. Photogrammetric Engineering Remote Sensing, 2000, 66 (1): 49-61
[33] H Li, B.S. Manjunath, S.K. Mitra. Multisensor image fusion using the wavelet transform. Graphical Models Image Process, 1995, 57(3): 235-245
[34] Gonzalo Pajares, Jesus Manuel de la Cruz. A wavelet-based image fusion tutorial. Pattern Recognition, 2004, 37: 1855- 1872
[35] 李冬辉, 周巍巍. 基于多分辨率小波网络–BP 神经网络–D-S 证据理论信息融合模型的直流系统故障诊断方法. 电网技术, 2004, 28(24): 16-20
[36] D.M. Tsai, B. Hsiao, Automatic surface inspection using wavelet reconstruction. Pattern Recognition, 2001, 34: 1285-1305
[37] S.G. Nikolov, D.R. Bull, C.N. Canagarajah et al. Fusion of 2-D images using their multiscale edges. Proceedings of the International Conference on Pattern Recognition, 2000: 1051-1054
[38] 高强, 何正嘉. 谐波小波及其时频剖面图在旋转机械诊断中的应用. 西安交通大学学报, 2000, 34(9): 62-66
[39] Roseanna M. Neupauer, Kaye L. Powel. A fully-anisotropic Morlet wavelet toidentify dominant orientations in a porous medium. Computers & Geosciences, 2005, 31: 465-471
[40] 王锋, 屈梁生. 小波一循环谱密度法在旋转机械敌障诊断中的应用. 中国设备工程, 2002, (6): 38-39
[41] 王锋, 屈梁生. 小波一循环谱密度法在旋转机械敌障诊断中的应用(续). 中国设备工程, 2002, (7): 45-46
[42] Sweldens W, Schr6der P.Building your own wavelets at home [B/OL].URL: http: //cm.bell-labs.corn/who/wire/papers/papers. html#athome, 1996
[43] Wire Sweldens . The lifting scheme: A construction of Second generation wavelets.SlAM J.Math.Anal, 1996, 29(2): 5ll-546
[44] 段晨东, 李凌均, 何正嘉. 第二代小波变换在旋转机械故障诊断中的应用. 机械科学与技术, 2004, 23(2): 224-226
[45] 岳岚, 王颢, 刘同明. 基于知识的神经网络及其在 CRM 中的应用. 计算机与现代化, 2005, (5): 15-17
[46] 卢学军, 邱忠宇, 陈仲仪等. 基于知识与模糊神经网络的故障诊断专家系统. 机械强度, 2000, 22(1): 4-7
[47] L.Yiyao, Y.V. Venkatesh, C.C. Ko. A knowledge-based neural network for fusing edge maps of multi-sensor images. Information Fusion, 2001, (2): 121-133
[48] B. Samanta, K.R. Al-Balushi, Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mechanical Systems and Signal Processing, 2003, 17 (2): 317-328
[49] Alok Madan. Vibration control of building structures using self-organizing and self-learning neural networks. Journal of Sound and Vibration, 2005, 287: 759-784
[50] 丁凯峰, 樊思齐.基于 RBF 网络的航空发动机模型辨识.航空动力学报, 2000, 15(2): 96-9
[51] Ye Zhifeng, Sun Jianguo. Simulation investigation of acre engine fault diagnoses using neural networks. Transaction of Nanjing University of Aeronautics and Astronautics, 2001, 18(2): 157-163
[52] 王建波, 于达仁.基于 RBF 网络的火箭发动机动态过程建模. 推进技术, 1999,(4): 9-12
[53] Eustace R, Merrington G. Fault diagnosis of fleet engines using neural networks. ISABE 95-7085: 926-936
[54] 叶志锋, 孙健国.基于概率神经网络的发动机故障诊断. 航空学报, 2002, 23(2): 155-157
[55] 孔莲芳. 集成神经网络信息融合技术在旋转机械故障诊断中的应用. 机械与电子, 2004, (1): 12-15
[56] 王由华, 刘振娟, 李宏光. 混合型集成神经网络故障诊断方法研究. 北京化工大学学报, 2003, 30(1): 66-69
[57] Prasad K.D.V. Yarlagadda. Development of an integrated neural network system for prediction of process parameters in metal injection moulding. Journal of Materials Processing Technology, 2002, (130-131): 315-320
[58] Gail A. Carpenter, Siegfried Martens, Ogi J. Ogas. Self-organizing information fusion and hierarchical knowledge discovery: a new framework using ARTMAP neural networks. Neural Networks, 2005, 18: 287-295
[59] J. Kim, H. Jung, I. Lee. Optimal structural control using neural networks. Journal of Engineering Mechanics, ASCE, 2000, (2): 201-205
[60] 尉询楷,李应红,刘建勋. 基于支持向量机的信息融合诊断方法. 系统工程与电子技术, 2005, 27(9): 1665-1668
[61] Tsai, Chih-Fong. Training support vector machines based on stacked generalization for image classification. Neurocomputing, 2005, 64: 497-503
[62] S. P?yh?nen, A. Arkkiob, P. Joverb et al. Coupling pairwise support vector machines for fault classification. Control Engineering Practice, 2005, 13: 759-769
[63] Assaf J., Sabo E., Eldar S. Fractal dynamics in the differential diagnosis of thyroideal follicular neoplasms. Pathology - Research and Practice, 2004, 200(6): 447-458
[64] Purkait P.a, Chakravorti S.a. Can fractal techniques be used for impulse fault pattern discrimination in distribution transformers? Electric Power Systems Research, 2004, 68(3): 258-267
[65] Patrice Simard and Emmanuel Le Tavernier. Fractal Approach for Signal Processingand Application to the Diagnosis of Cavitation. Mechanical Systems and Signal Processing , 2000, 14(3): 459-469
[66] 徐玉秀 , 钟建军 , 刘薇等. 基于广义分形的旋转机械故障诊断识别与分类. 辽宁工程技术大学学报, 2005, 24(4): 591-594
[67] 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. 中国机械工程, 2005, 16(12): 1088-1091
[68] Patrice Simard and Emmanuel Le Tavernier. Fractal Approach for Signal Processing and Application to the Diagnosis of Cavitation. Mechanical Systems and Signal Processing , 2000, 14(3): 459-469
[69] Yang, Bo-Suk and Kim, Kwang Jin. Application of Dempster–Shafer theory in fault diagnosis of induction motors using vibration and current signals. Mechanical Systems and Signal Processing, 2006, 20(2): 403-420
[70] F.Cremer, K.Schutte, J.G.M.Schavemaker et al. A comparison of decision-level sensor-fusion methods for anti-personnel landmine detection. Information Fusion, 2001, (2): 187-208
[71] Rottensteiner, Franz, Trinder et al. Using the Dempster–Shafer method for the fusion of LIDAR data and multi-spectral images for building detection. Information Fusion, 2005, (6): 283-300
[72] Chinmay R. Parikh, Michael J.pont, N.Barrie Jones. Application of Dempster-Shafer theory in condition monitoring applications: a case study. Pattern Rocongnition Letter, 2001, 22: 777-785
[73] 邱英. D-S 证据推理在机械故障诊断中的应用. 华东交通大学学报, 2004, 21(2): 107-120
[74] 董明, 严璋, 杨莉等. 基于证据推理的电力变压器故障诊断策略. 中国电机工程学报, 2006, 26(1): 106-114(英文)
[75] 王奉涛, 马孝江, 朱泓等. 基于证据理论的集成神经网络故障诊断方法. 系统工程与电子技术, 2004, 26(2): 240-244
[76] J.B. Gao, C.J. Harris. Some remarks on Kalman filters for the multisensor fusion. Information Fusion, 2003, (2): 191-201
[77] Shu-Li Sun. Distributed optimal component fusion weighted by scalars for fixed-lag Kalman smoother. Automatica, 2005, 41: 2153-2159
[78] 孙书利, 史雪岩, 崔平远. 多传感器最优信息融合 Kalman 多步预报器及其应用. 宇航学报, 2004, 25(2): 241-246
[79] Francois Caron, Emmanuel Duflos, Denis Pomorski. GPS/IMU data fusion using multisensor Kalman filtering: introduction of contextual aspects. Information Fusion, 2006, (7): 221-230
[80] Amditis Angelosa, Polychronopoulos Arisa, Floudas Nikolaosa et al. Fusion of infrared vision and radar for estimating the lateral dynamics of obstacles. Information Fusion, 2005, (2): 129-141
[81] Fionn Murtagh, Adrian E. Raftery, Jean-Luc Starck. Bayesian inference for multiband image segmentation via model-based cluster trees. Image and Vision Computing, 2005, 23: 587-596
[82] 王华伟, 周经伦, 何祖玉. 基于贝叶斯网络的复杂系统故障诊断. 计算机集成制造系统-CIMS, 10(2): 230-234
[83] 魏民祥, 董龙雷, 王晓云等. 基于不确定性推理原理的机组振动信息融合技术.中国电机工程学报, 2000, 20(9): 64-66
[84] D. Moshoua, C. Bravoa, R. Obertib. Plant disease detection based on data fusion of hyper-spectral and multi-spectral fluorescence imaging using Kohonen maps. Real-Time Imaging, 2005, 11: 75-83
[85] 韩捷, 董辛, 郝伟等. 旋转机械同源数据全信息倒频谱分析与应用. 机械强度, 2005, 27(4):452-455
[86] J.Z. Sasiadek. Sensor Fusion. Annual Reviews in Control, 2002,26: 203-228
[87] 盛兆顺, 尹琦岭. 设备状态监测与故障诊断技术及应用. 北京: 化学工业出版社, 2002
[88] 韩捷, 张瑞林. 旋转机械故障机理及诊断技术. 北京: 机械工业出版社, 1997
[89] Cao Siyuan, Chen Xiangpeng. The Second-generation Wavelet Transform and its Application in Denoising of Seismic Data. Applied Geophysics, 2005, 2(2): 70-75
[90] 叶敬福, 詹永照. 基于 Gabor 小波变换的人脸表情特征提取. 计算机工程, 2005,31(15): 172-174
[91] Hasan F. Ates, Michael T. Orchard. An adaptive edge model in the wavelet domain for wavelet image coding. Signal Processing: Image Communication, 2005, 20: 169-185
[92] David C. Dunn, Jonathan F. Morrison. Analysis of the energy budget in turbulent channel ?ow using orthogonal wavelets. Computers & Fluids, 2005, 34: 199-224
[93] S. Sekhar. Crack Detection Through Wavelet Transform for a Run-up Rotor. Journal of Sound and Vibration, 2003, 259(2): 461-472
[94] 殷光伟, 郑丕谔. 小波包变换在股市预测中的应用研究. 北京理工大学学报(社会科学版), 2005, 7(3): 73-76
[95] 罗发根, 郎锐, 金燕波. 基于小波分解红外雷场目标提取方法的研究. 电波科学学报, 2005, 20(4): 510-512
[96] 邓懿波, 谭志洪, 谢志刚. 自适应小波分析应用于回转机械设备的故障诊断. 南昌大学学报(工科版), 2005, 27(3): 67-70
[97] A.vudainayagam. Wavelet based multigrid methods for linear and nonlinear elliptic partial differential equations. Applied Mathematics and Computation, 2004, 148: 307-320
[98] Morten Bjerk?s. Wavelet transforms and ice actions on structures. Cold Regions Science and Technology, 2006, 44: 159-169
[99] 李晓欧, 冯焕清. 基于小波变换和盲源分离算法提取事件相关电位. 北京生物医学工程, 2005, 24(4): 246-249
[100] Ze Wanga, Chi-Sing Leung, Yi-Sheng Zhu, et al. Data compression with spherical wavelets and wavelets for the image-based relighting. Computer Vision and Image Understanding, 2004, 96: 327-344
[101] E.M. Barj, M. Afifi, A.A. Idrissi. Speckle correlation fringes denoising using stationary wavelet transform, Application in the wavelet phase evaluation technique. Optics & Laser Technology, 2006, 38: 506-511
[102] Liu Rui-Lin, Wu Yue-Qi, Liu Jian-Hua et al. The Segmentation of FMI Image Based on 2-D Dyadic Wavelet Transform. Applied Geophysics, 2005, 2(2): 89-94
[103] 彭玉华. 小波变换与工程应用. 北京: 科学出版社, 2003
[104] 杨福生. 小波变换的工程分析与应用. 科学出版社 ,2000
[105] Zhang YanPing, Huang ShuHong, Hou JingHong et al. Continuous wavelet grey moment approach for vibration analysis of rotating machinery. Mechanical Systems and Signal Processing, 2006, 20(5), 1202-1220
[106] 申弢.大型旋转机械智能监测诊断中信息融合理论与技术的研究. [博士学位论文]. 武汉: 华中科技大学能源学院, 1999
[107] 申弢,黄树红,韩守木等. 旋转机械振动信号的信息熵特征. 机械工程学报, 2001, 37(6): 94-98
[108] 庞剑锋, 卜东波, 白硕.基于向量空间模型的文本自动分类系统的研究与实现.计算机应用研究, 2001, 18(9): 23-26
[109] TOTH D, AACH T.Improved minimum distance classification with Gaussian outlier detection for industrial inspection.Italy, lth International Conference on Image Analysis and Processing Palermo, 2001: 584-588
[110] 任靖, 李春平. 最小距离分类器的改进算法—加权最小距离分类器. 计算机应用, 2005, 25(5): 992-994
[111] Daoqiang Zhang, Songcan Chen, Zhi-Hua Zhou. Learning the kernel parameters in kernel minimum distance classifier. Pattern Recognition, 2006, 39: 133-135
[112] Xuezhi Yang, Grantham Pang, Nelson Yung. Discriminative training approaches to fabric defect classification based on wavelet transform. Pattern Recognition, 2004,37: 889-899
[113] Han GuoMing, Yun ShaoHui, Cao XinHua et al. Acquisition and pattern recognition of spectrum information of welding metal transfer. Materials and Design, 2003, 24: 699-703
[114] 朱建华, 刘政凯, 俞能海. 一种多光谱遥感图象的自适应最小距离分类方法. 中国图象图形学报, 2005(A,1): 21-24
[115] 刘伟强, 胡静, 夏德深. 基于核空间的多光谱遥感图像分类方法. 国土资源遥感, 2002, (3): 44-46
[116] 王洪元, 曾生根, 王平安等. 基于自适应最小距离分割算法和神经网络的腹水脱落癌细胞识别. 计算机应用与软件, 2003, (10): 44-47
[117] 杨善林, 李永森, 胡笑旋等. K-means算法中的k值优化问题研究. 系统工程理论与实践, 2006, (2): 97-101
[118] Clausi D A. K-means iterative fisher(KIF) unsupervised clustering algorithm applied to image texture segmentation. Pattern Recognition, 2002, 35: 1959-1972
[119] Speeht D F. Probabilistic Neural Networks. Neural Networks, 1990, 3(1): 109-118
[120] 王明怡,王德林,黄金钟. 基于概率神经网络的基因选择和组织分类方法. 科技通报, 2005, 21(1): 10-13
[121] 郭晓敏, 伍小明, 詹希美. 基于概率神经网络的寄生虫卵显微图像识别.计算机工程与应用, 2005, 15: 198-200
[122] 孙晓刚, 张建华, 侯国莲, 金慰刚. 基于概率神经网络的凝汽器故障诊断研究. 现代电力, 2005, 22(3): 58-61
[123] 陈小强,李刚,刘长武. 概率神经网络及其在岩土类别判定中的应用. 铜业工程, 2005, (2): 11-14
[124] 李三平, 岳振军. 基于概率神经网络的手写数字识别系统的 Matlab 实现. 军事通信技术, 2005,26(1): 54-57
[125] Plamondon R, Srihari S N. On-line and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(1): 63-84
[126] 訾艳阳.小波分形技术及其在非平稳故障诊断中的应用. 西安交通大学学报, 2000, 34(9): 82-87
[127] 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. 哈尔滨工业大学学报, 1996, 28(2): 27-31
[128] Grassberge, P, Procaecia I. Characterization of strange attractors. Physics Review Letters A, 1983, 50(5): 346-349
[129] 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. 哈尔滨工业大学学报, 1999, 31(1): 55-56, 92
[130] 滕丽娜, 陈兆能, 佟德纯等. 关联维数在旋转机械支承系统状态监测中的应用.上海交通大学学报, 2002, 36(9): 1377-1380
[131] 王洪, 左行中, 柳亦兵等. 关联维数在齿轮故障诊断中应用的试验研究. 现代电力, 2002, 19(4): 21-26
[132] 姜万录, 陈东宁, 姚成玉等. 关联维数分析方法及其在液压泵故障诊断中的应用. 传感技术学报, 2004, (1): 62-65
[133] 吕志民, 徐金栋, 张武军等. 分形维数在滚动轴承故障诊断中的应用.北京科技大学学报, 1998, 20(5): 475-478
[134] H. Kantz, T. Schreiber. Nonlinear Time Series Analysis. Cambridge: Cambridge Univ. Press, 1997
[135] Logan D. Using the Correlation Dimensional for Vibration Fault Diagnosis of Rolling Element Bearings - Basic Concepts. Mechanical Systems and Signal Processing, 1996, 10(3): 241-250
[136] 石博强, 申焱华. 机械故障诊断的分形方法. 北京: 冶金工业出版社, 2001
[137] 秦卫阳, 孟光. 采用小波方法计算关联维数. 机械科学与技术, 2000, 19(6): 925-926
[138] Hai-Feng Liu, Wei-Feng Li, Zheng-Hua Dai. The dimension of chaotic dynamical system in wavelet space and its application. Physics Letters A, 2003, 316: 44-54
[139] 杨涛, 黄树红, 高伟. 网络化汽轮机组远程监测及故障诊断系统的研究. 动力工程, 2004, 24(6): 840-844
[140] 游佳, 何健鹰. Delphi 与 Matlab 接口以及脱离 Matlab 运行. 计算机与数字工程, 2004, 32(6): 21-23
[141] 董超, 刘洪锦, 李俊芳. Windows 应用程序与 Matlab 接口技术的研究. 天津理工大学学报, 2005, 2l(4): 61-63
[142] 刘颖, 唐世钢, 于贵江. VC 与 Matlab 接口在图像处理中的实现. 哈尔滨理工大学学报, 2003, 8(6): 51-53
[143] 姚天任, 江天辉. 数字信号处理. 武汉: 华中科技大学出版社, 1999