切削加工过程中颤振的监测与识别方法研究
摘要
切削加工是使用切削工具,把坯料或工件上多余的材料层切去,使工件获得规定的几何形状、尺寸和表面质量的加工方法。在切削加工过程中所产生的颤振是影响工件质量的主要原因之一,颤振具有非线性、时变性和不确定性等特点,难以进行精确的测量和识别,多年来吸引了国际上众多学者持续对其进行研究,取得了一些重要的研究成果,但仍然存在一些问题有待于解决。本文综合了隐马尔可夫、支持向量机及核主元分析等理论和方法,对机床启动过程、刀具磨损状态等诱发颤振的因素进行诊断分析,并且对切削加工中的颤振监测和识别方法进行研究。论文完成的主要工作如下：
(1)通过对切削加工时机床启动过程的故障特征分析,基于隐马尔可夫理论,建立了混合密度连续隐马尔可夫模型,对机床启动过程的故障进行识别。采用连续混合密度隐马尔可夫模型识别车床启动过程的运行状态,解决了隐马尔可夫模型的溢出问题,根据高斯密度函数特点,提取启动过程的工件松动、不平衡、不对中和正常启动等特征信息,依据信息特征进行故障诊断识别。该模型克服了传统的诊断方法容易丢失特征信息的弊端,方法简单、识别率高,适合应用于旋转机械的启动过程故障诊断。与隐马尔可夫模型进行比较分析,实验结果表明,该模型具有较好的识别效果。
(2)通过刀具磨损量对颤振影响程度的分析,基于离散隐马尔可夫理论,建立了刀具磨损诊断模型。采用对切削加工中的动态切削力信号和刀柄振动信号进行快速傅立叶变换并提取特征量,将提取的特征谱矢量作归一化处理,然后利用自组织特征映射
对归一化矢量进行预分类离散编码,编码量值作为观测序列引入到离散隐马尔可夫模型
中进行机器学习,识别出刀具磨损程度,识别结果作为控制切削进给量大小的依据。该
模型克服了传统识别方法的计算量大、算法复杂的缺点,识别速度高,具有良好的实时
性,并通过与隐马尔可夫模型和分形理论比较分析,实验结果表明,该模型具有较好的
识别效果,为正确识别切削颤振奠定基础。(3)针对切削力信号和工件振动信号的非线性、不确定性和时变性的特点,提取切削过程的大样本数据,建立了基于核主元分析与支持向量机结合的故障诊断模型(KPCA-SVM)。该模型通过KPCA方法提取非线性颤振数据中的线性主元信息,根据主元信息贡献率的大小,确定能够代表颤振特性的线性主元,然后,通过SVM的分类能力,对线性主元进行一对多方式分类,分类结果作为判定是否具有颤振趋势的依据,为控制任务提供数据基础。该方法弥补了传统识别方法难于充分描述颤振发展过程的缺陷,实验结果表明：对于能够描述切削过程的大样本数据,KPCA-SVM是一种新的有效的颤振趋势识别方法。与主元分析与支持向量机模型(PCA-SVM)的识别效果比较,具有一定的优越性。
(4)针对切削加工过程中的颤振发生时的小样本数据,建立了基于支持向量机与隐马尔可夫模型(SVM-HMM)结合的诊断模型,辨识颤振发生的程度。该模型首先求取小样本数据在支持向量机下的最优比率,然后把最优比率转化成Sigmoid概率,作为观测序列输入到HMM模型,通过隐马尔可夫模型的良好的类内分类能力,对切削过程中能够表现颤振的振动信号和切削力信号做出有效训练和识别。实验结果表明,对于小样本数据,该方法对切削颤振具有较强的识别能力,识别效果优于支持向量机方法、隐马尔可夫方法,该方法克服了非颤振信息颤振化错误判断的弊端,是一种颤振诊断的新方法。
Cutting is a machining way, by which superabundant material layer is cut by cutting tools from blank or work piece, in order to get specific figure, size and surface quality. Chatter in cutting process is one of the main causes which can affect the quality of work piece. It is difficult to accurately measure and identify chatter because of its nonlinear, time variation and uncertainty. For many years, lots of scholars from various countries always tried to study chatter and have achieved some important results. But there are still some problems that need to be solved. In this paper, the theories and methods of Markov, Support Vector Machine and Kernel Principal Component Analysis was synthesized, and was applied in diagnostic analysis of startup process and tool wear which are inducing factors for chatter, and the study about methods of monitor and identification of chatter in cutting process was performed. The main works in the research are as follows:
(1) Through analysis of fault feature of startup process in cutting, based on Markov's theory,Continue Hidden Markov Model with mixture probability Densities(CDHMM) was established in the research in order to identify fault condition during startup process. When it was used in identifying running state of startup process the overflow of Markov's model was settled. Characteristic information including workpiece loosing, unbalance, asymmetry and normally starting was extracted based on Gaussian density function,, then the CDHMM did identify and diagnose fault according to these information.The new model was better than the traditional diagnostic method for it overcame the traditional model's defect of losing information in feature information abstraction.The new method was simple, good in recognition rate, and suitable for diagnosis of startup fault about rotating machinery. The experimental results showed that the new model had better recognition effect than Hidden Markov model.
(2) After analysis the effect of tool wear to chatter, a tool wear diagnosis model was established based on discrete hidden Markov model(DHMM). Dynamic cutting force signal and tool holder vibration signal was dealt by fast fourier transformation, and characteristic parameter was extracted and was normalized, then the parameter was presorted and coded by self-organizing feature maps. The coding value was introduced into the discrete hidden Markov models as observation sequence for machine learning, which could recognize condition of tool wear and feeding quantity was controlled according to the recognition results. The model overcame defect of the traditional identification means including large calculation and complex algorithm. The new model had higher recognition speed and better real-time character.The experimental results showed that the new method had better recognition results than the Hidden Markov Model which could establish basement for recognizing chatter correctly.
(3) According to the nonlinearity, uncertainty and variability of signal of vibration and cutting force, a diagnostic model of fault was built in the research based on Kernel Principal Component Analysis and Support Vector Machine (KPCA-SVM) through extracting a large sample of cutting. This model extracted linear principal component information from nonlinear chatter value through KPCA, the linear principal component which could reflect character of chatter could be identified according to the contribution rate of principal component information. Linear principal component was classified by one-to-many mode and classification results could be used for judging chatter trend which provided data foundation for controlling duty. This method could fully describe development of chatter which is difficult for the traditional method. Experimental results showed that KPCA-SVM was a new effective method for recognizing chatter trend and better than PCA-SVM (Principal Component Analysis and Support Vector Machine) for large samples which could describe cutting process.
(4) A diagnostic model was established based on Support Vector Machine and Hidden Markov Model(SVM-HMM) to recognize degree of chatter for small samples when chatter occurring in cutting process. This model got optimum rate of small sample in SVM, and the output results from SVM was transformed into Sigmoid probability, which then was transported into HMM model, where vibration signals and cutting force signals was effectively studied and recognized through HMM's ideal class classification ability. In the research, the results showed that this method had better ability in recognition of cutting chatter and could get better recognition effect than SVM and HMM for small samples. This method overcame the disadvantage of recognizing non-chatter information as chatter and it was a new method for diagnosis of chatter.
(1)通过对切削加工时机床启动过程的故障特征分析,基于隐马尔可夫理论,建立了混合密度连续隐马尔可夫模型,对机床启动过程的故障进行识别。采用连续混合密度隐马尔可夫模型识别车床启动过程的运行状态,解决了隐马尔可夫模型的溢出问题,根据高斯密度函数特点,提取启动过程的工件松动、不平衡、不对中和正常启动等特征信息,依据信息特征进行故障诊断识别。该模型克服了传统的诊断方法容易丢失特征信息的弊端,方法简单、识别率高,适合应用于旋转机械的启动过程故障诊断。与隐马尔可夫模型进行比较分析,实验结果表明,该模型具有较好的识别效果。
(2)通过刀具磨损量对颤振影响程度的分析,基于离散隐马尔可夫理论,建立了刀具磨损诊断模型。采用对切削加工中的动态切削力信号和刀柄振动信号进行快速傅立叶变换并提取特征量,将提取的特征谱矢量作归一化处理,然后利用自组织特征映射
对归一化矢量进行预分类离散编码,编码量值作为观测序列引入到离散隐马尔可夫模型
中进行机器学习,识别出刀具磨损程度,识别结果作为控制切削进给量大小的依据。该
模型克服了传统识别方法的计算量大、算法复杂的缺点,识别速度高,具有良好的实时
性,并通过与隐马尔可夫模型和分形理论比较分析,实验结果表明,该模型具有较好的
识别效果,为正确识别切削颤振奠定基础。(3)针对切削力信号和工件振动信号的非线性、不确定性和时变性的特点,提取切削过程的大样本数据,建立了基于核主元分析与支持向量机结合的故障诊断模型(KPCA-SVM)。该模型通过KPCA方法提取非线性颤振数据中的线性主元信息,根据主元信息贡献率的大小,确定能够代表颤振特性的线性主元,然后,通过SVM的分类能力,对线性主元进行一对多方式分类,分类结果作为判定是否具有颤振趋势的依据,为控制任务提供数据基础。该方法弥补了传统识别方法难于充分描述颤振发展过程的缺陷,实验结果表明：对于能够描述切削过程的大样本数据,KPCA-SVM是一种新的有效的颤振趋势识别方法。与主元分析与支持向量机模型(PCA-SVM)的识别效果比较,具有一定的优越性。
(4)针对切削加工过程中的颤振发生时的小样本数据,建立了基于支持向量机与隐马尔可夫模型(SVM-HMM)结合的诊断模型,辨识颤振发生的程度。该模型首先求取小样本数据在支持向量机下的最优比率,然后把最优比率转化成Sigmoid概率,作为观测序列输入到HMM模型,通过隐马尔可夫模型的良好的类内分类能力,对切削过程中能够表现颤振的振动信号和切削力信号做出有效训练和识别。实验结果表明,对于小样本数据,该方法对切削颤振具有较强的识别能力,识别效果优于支持向量机方法、隐马尔可夫方法,该方法克服了非颤振信息颤振化错误判断的弊端,是一种颤振诊断的新方法。
Cutting is a machining way, by which superabundant material layer is cut by cutting tools from blank or work piece, in order to get specific figure, size and surface quality. Chatter in cutting process is one of the main causes which can affect the quality of work piece. It is difficult to accurately measure and identify chatter because of its nonlinear, time variation and uncertainty. For many years, lots of scholars from various countries always tried to study chatter and have achieved some important results. But there are still some problems that need to be solved. In this paper, the theories and methods of Markov, Support Vector Machine and Kernel Principal Component Analysis was synthesized, and was applied in diagnostic analysis of startup process and tool wear which are inducing factors for chatter, and the study about methods of monitor and identification of chatter in cutting process was performed. The main works in the research are as follows:
(1) Through analysis of fault feature of startup process in cutting, based on Markov's theory,Continue Hidden Markov Model with mixture probability Densities(CDHMM) was established in the research in order to identify fault condition during startup process. When it was used in identifying running state of startup process the overflow of Markov's model was settled. Characteristic information including workpiece loosing, unbalance, asymmetry and normally starting was extracted based on Gaussian density function,, then the CDHMM did identify and diagnose fault according to these information.The new model was better than the traditional diagnostic method for it overcame the traditional model's defect of losing information in feature information abstraction.The new method was simple, good in recognition rate, and suitable for diagnosis of startup fault about rotating machinery. The experimental results showed that the new model had better recognition effect than Hidden Markov model.
(2) After analysis the effect of tool wear to chatter, a tool wear diagnosis model was established based on discrete hidden Markov model(DHMM). Dynamic cutting force signal and tool holder vibration signal was dealt by fast fourier transformation, and characteristic parameter was extracted and was normalized, then the parameter was presorted and coded by self-organizing feature maps. The coding value was introduced into the discrete hidden Markov models as observation sequence for machine learning, which could recognize condition of tool wear and feeding quantity was controlled according to the recognition results. The model overcame defect of the traditional identification means including large calculation and complex algorithm. The new model had higher recognition speed and better real-time character.The experimental results showed that the new method had better recognition results than the Hidden Markov Model which could establish basement for recognizing chatter correctly.
(3) According to the nonlinearity, uncertainty and variability of signal of vibration and cutting force, a diagnostic model of fault was built in the research based on Kernel Principal Component Analysis and Support Vector Machine (KPCA-SVM) through extracting a large sample of cutting. This model extracted linear principal component information from nonlinear chatter value through KPCA, the linear principal component which could reflect character of chatter could be identified according to the contribution rate of principal component information. Linear principal component was classified by one-to-many mode and classification results could be used for judging chatter trend which provided data foundation for controlling duty. This method could fully describe development of chatter which is difficult for the traditional method. Experimental results showed that KPCA-SVM was a new effective method for recognizing chatter trend and better than PCA-SVM (Principal Component Analysis and Support Vector Machine) for large samples which could describe cutting process.
(4) A diagnostic model was established based on Support Vector Machine and Hidden Markov Model(SVM-HMM) to recognize degree of chatter for small samples when chatter occurring in cutting process. This model got optimum rate of small sample in SVM, and the output results from SVM was transformed into Sigmoid probability, which then was transported into HMM model, where vibration signals and cutting force signals was effectively studied and recognized through HMM's ideal class classification ability. In the research, the results showed that this method had better ability in recognition of cutting chatter and could get better recognition effect than SVM and HMM for small samples. This method overcame the disadvantage of recognizing non-chatter information as chatter and it was a new method for diagnosis of chatter.
引文
[1]于骏一,吴博达.机械加工振动的诊断识别与控制[M].北京：清华大学出版社,1994.
[2]张正松,傅尚新,冯冠平,徐玉铮等编著.旋转机械振动监测及故障诊断[M].北京：机械工业出版社,1991.
[3]吴今培,肖建华著.智能故障诊断与专家系统[M].北京：科学出版社,1997.
[4]冯长建.HMM动态模式识别理论、方法以及在旋转机械故障诊断中的应用[D].杭州：浙江大学,2002.
[5]Sohre J S. Trouble-shooting to stop vibration of centrifugal[J]. Petro/Chem engineering, 1968,11:22-33.
[6]白木万博阳[日].机械振动讲演论文集[C].郑州机械研究所.1984.
[7]夏松波,张礼勇.旋转机械故障诊断技术的现状与展望[J].振动与冲击,1997,16(2)：1-5.
[8]魏文辉,宋强,滕乐天,王伟,刘文华,袁志昌.基于反故障控制的链式STATCOM动态控制策略的研究[J].中国电机工程学报,2005,25(4)：19-24.
[9]晏巨,何晓军,唐岚.电磁悬浮隔振系统控制方法[J].光电工程,1999,26(4)：18-22.
[10]刘春生.复杂非线性系统的智能故障诊断与容错控制[D].南京：南京航空航天大学,2006.
[11]胡寿松,唐建秋.故障大系统的鲁棒容错控制方法[J].南京航空航天大学学报,1993,25(1)：1-6.
[12]王军政,汪首坤,郑万煦.某高炮随动系统故障诊断装置的研制[J].北京理工大学学报,2002,22(3)：328-330.
[13]张瑞芳,叶汉民,覃嘉恒.基于DSP的齿轮减速器故障诊断装置[J].煤矿机械,2008,28(8)：190-192.
[14]于传强,郭晓松,张安,余相桃.大型机电设备故障诊断装置的实现[J].计算机测量与控制,2003,11(7)：531-532,552.
[15]王秀贞.汽车故障诊断与检测技术[M].北京：人民邮电出版社,2003.
[16]黄守道.无刷双馈电机的控制方法研究[D].长沙：湖南大学,2005.
[17]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[J].中国机械工程,1999,10(3)：307-310.
[18]Cooley J W, Tukey J W. An algorithm for the machine calculation of complex Fourier series[J]. Mathematies of Computation.1965,19(90):297-301.
[19]Littlewood J E, et al. Theorems on Fourier series and power series [J]. J. L.M. S.,1931,6: 230-238.
[20]Grandke T. Interpolation algorithms for discrete Fourier transforms of weighted signals[C]. IEEE Trans on Instru and Meas.1983, IM-32(2):350-55.
[21]Pgoupilaud P. Cycle-octive and Related Transform in Seismic Singal Analysis Geoerploration[J]. Singal Analysis,1985,23(984):85-102.
[22]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—相位差校正法[J].振动工程学报,1999,12(4)：454-459.
[23]胡红英.局域波分解方法、特征剖析及应用研究[D].大连：大连理工大学,2006.
[24]J.B. Theoeharis. A high-order neuron-fuzzy system internal dynamies:APPlication to the adaptive cancellation[J]. Fuzzy Sets and Systems.2006,157(1):471-500.
[25]Ocak, H., Loparo, K. A. New bearing fault detection and diagnosis scheme based on hidden Markov modeling of vibration signals[C]. Acoustics, Speech, and Signal Processing,2001. Proceedings.2001 IEEE International Conference on,2001(5):3141-3144.
[26]Frank P.M. Fault diagnosis in dynamic systems using analytical and knowledge based redundancy-A Survey and Some New Results[J]. Automatica,1990,26(3):459-474.
[27]Mastorocostas, P. A, Theoehairs, J. B. A recurrent fuzzy-neural model for dynamic system identification[J]. IEEE Transactions on Systems,Man and Cybernetics, partB (Cybernetics).2002,32(2):179-190.
[28]A. Ciehoeki,W. KasPrzka. Nonlinear learning algorithms for blind separation of natural images[J]. Neural Network World,1996,4:515-523.
[29]D. Yu,. F. Sat. A new blind image watermarking technique based on independent component analysis[J]. Lecture Notes in Computer Science, Springer-Verlag,2003,51-63.
[30]J. Karhumen, A. HyVarinen, R. Vigario, J.Hurri, andE.oja. APPlications of neural blind separation to signal and image Proeessing[C]. IEEE Int. Conf. on Aeoustics, speech and Signal Proeessing(ICASSP,97),1997:131-134.
[31]Talyor F W.. "On the Art of Cutting Metals" [M]. ASME,1907.
[32]#12
[33]#12
[34]Arnold R. N.. The Mechanism of Tool Vibration in the Cutting of Steel [J]. Proc. of Inst. Mech. Eng, Vol.154, London,1946.
[35]Hahn R.S..Metal-Cutting Chatter and Its Elimination[J].Trans. ASME, Vol.75,1953.
[36]Hahn R. S..On the Theory of Regenerative Chatter in Precision-Grinding Operations [J]. Trans. ASME, Vol.76,1954.
[37]Tlusty J. Spacek L.. Self-Excited Vibrations in Machine Tools[M]. Prague,1954.
[38]索科洛夫斯基著,浙江大学机械制造教研室译.机械制造工艺的科学基础[M].北京：机械工业出版社,1955.
[39]星铁太郎.楼械加工びびり现象——解析と封策[R].工业调查会登行.1977.
[40]费仁元,王民.切削颤振在线监控的研究现状及进展[J].中国机械工程,2001,12(9)：1075-1079.
[41]王先上.车床振动的自动控制[J].机械工程学报,1986,22(2)：38-47.
[42]ShiraishiM. Yamanaka K, Fujita H. Optimal Control of Chatter in Turning[J]. Int. J. Mach. Tools Manufact,1991,31(1):31-43.
[43]Eugene I, Rivin, Kang Hongling. Enhancement of Dynamic Stability of Cantilever Tooling Structure[J]. Int J.Mach. Tools Manufact,1992,32(4):539-561.
[44]费仁元,阿不都热依木,王民,关剑,朱志坚,伯提古丽.制造系统监控中模糊神经元网络的结构和应用[J].北京工业大学学报,2000,26(4)：1-4.
[45]孔繁森,赵新刚,刘春颖.切削过程混沌颤振的控制方法仿真研究[J].振动与冲击,2008,27(11)：22-26,195.
[46]Eman, K.,Wu, S.M. Feasibility Study of On-line Identification of Chatter in Turning Operations[J].J Eng Ind Trans ASME,1980,102(4):315-321.
[47]Tansel I N. Recognition of Chatter with Neural Networks. Int[J]. J. Mach. Tools Manufact, 1991,31 (4):539-552.
[48]Miyoshi Y. Estimation and application of mean square frequency[J].Bull. JSPE,1992(3): 221-225.
[49]于骏一等.切削颤振的预报控制[J].振动工程学报,1990,3(1)：72-78.
[50]赵芝眉,谢锡俊,吴波.切削颤振预兆的研究[J].南京工学院学报,1988,18(2)：47-54.
[51]高国利,王仁德,王启义.车削颤振的稳定区搜索控制[J].东北大学学报(自然科学版),1996.17(4)：412-415.
[52]贺长生,李慧,庞海文,梁旭.切削颤振预报方法探讨[J].长春大学学报,2003,13(6)：4-6.
[53]张永亮,于骏一,侯东霞,张守勤吴华.基于电流变效应的车削颤振预报控制技术的研究[J].机械工程学报,2005,41(4)：206-211.
[54]石莉,贾春德,孙玉龙.应用小波研究动态铣削力及预报铣削颤振[J].哈尔滨工业大学学报,2006,38(10)：1778-1780.
[55]康晶,冯长健,杨国田.离散隐马尔可夫模型在颤振预报中的应用研究[J].机械科学与技术,2008,27(3)：360-364.
[56]Jong Min Lee, Seung-Jong Kim et al. Diagnosis of mechanical fault signal using continuous hidden Markov model[J]. Journal of Sound and Vibration,2004,276:1065-1080.
[57]Dornf eld, D. A., et al., Neural Network Sensor Fusion for Tool Condition Moniroring[J]. Annals of the CIRP,1990,39(1):101-105.
[58]Lezanski P, Rafalowicz J. An Intelligent Monitoring System for Cylindrical Grinding[J]. Annals of the CIRP,1993,42(1):393-396.
[59]Dimla E. Tool Wear Monitoring in Metal Cutting Operation Using Neural Networks and Multivariate Process Parameters[J]. NC 1998:807-810.
[60]陈花玲,戴德沛.机床切削颤振的非线性理论研究[J].振动工程学报,1992,5(4)：335-342.
[61]蔡志强,吴雅,周笠,杨叔子.故障诊断与切削颤振的小波分析[J].华中理工大学学报,1993,21(1)：88-94.
[62]周晓勤,于骏一,王文才.人工神经网络在切削颤振类别诊断中的应用[J].农业机械学报,1998,29(2)：156-160.
[63]胡耀斌,江涌涛,张春良,吕海波.基于支持向量回归的切削颤振状态趋势预测的研究[J].组合机床与自动化加工技术,2006,3(13),42-46.
[64]黄强,张根保,张新玉,曹东风.对再生型切削颤振模型的试验分析[J].振动工程学报,2008,12(6)：547-552.
[65]Kondo, Eiji, et al. Effects of tool flank wear on occurrences of regenerative chatter[J]. C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C,1995,61 (584):1279-1285.
[66]E. Marui,M. Hashimoto et al. Regenerative chatter vibration occurring in turning with different sidecutting edge angles[J]. Journal of Engineering for Industry, Transactions of the ASME,1995,117(4):551-558.
[67]付连宇,于骏一,鲍明.切削颤振的相位特性研究[J].振动工程学报,2000,13(4)：510-515.
[68]刘安民,彭程,刘吉兆,郭雪娥.高速铣削时颤振的诊断和稳定加工区域的预报[J].机械工程学报,2007,43(1)：164-169.
[69]孔繁森,于骏一,潘志刚.切削过程再生颤振的模糊稳定性分析[J].振动工程学报,1998,11(1)：106-109.
[70]E. Solis, C. R. Peres, J. E. Jimeneza, R. Alique, J. C. Monje. A new analytical-experimental method for the identification of stability lobes in high-speed milling[J]. International Journal of Machine Tools & Manufacture,2004,44(1):1591-1597.
[71]谢锦辉.隐Markov模型(HMM)及其在语音处理中的应用[M].武汉：华中理工大学出版社,1995.
[72]Qing Wang, Zheru Chi, Feng, D. D., Rongchun Zhao. Hidden Markov random field based approachfor off-line handwritten Chinese character recognition[C]. Pattern Recognition,2000. Proceedings.15th International Conference on,2000,2:347-350.
[73]童进,吴昭同等.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.
[74]Heck, L. P., McClellan, J. H. Mechanical system monitoring using hidden Markov models[C]. International Conference on coustics, Speech, and Signal Processing,1991,3:1697-1700.
[75]Changjun Zhou,Xiaopeng Wei,Qiang Zhang. Face recognition based on HMM-SVM[J]. ICIC Express Letters,2007,1(2):137-143.
[76]Siohan.0.,Chesta. C., Chin-Hui Lee. Joint maximum a posteriori adaptation of transformation and HMM parameters. Speech and Audio Processing[J]. IEEE Transactions on Image Processing,2001,9(4):417-428.
[77]V. Vapnik. Estimaiton of Dependencies Based on Empirical Data [M]. Berlin:Springer Verlag,1982.
[78]V. Vapnik. The Nature of statislical Learning Theory[M]. Berlin:Springer Verlag,1995.
[79]V. Vapnik.Statistical Learning Theory[M]. Berlin:Wiley,1998.
[80]范玉妹,赵丽丽.关于支持向量分类机算法的研究[J].石家庄铁道学院学报(自然科学版),2007,20(3)：31-36.
[81]Reyna R. A., Hernandez N., Esteve D. et al. Segmenting images with support vector machines[C]. In Proceedings of 2000 International Conference on Image Processing, Vancover, BC, Canada,2000,1(1):820-823.
[82]Isermann,R. Model based fault detection and diagnosis methods[C]. American Control Conference,1995:1605-1609.
[83]Valentini A., Zhang Hongjiang. Automatic image orientation detection[J]. IEEE Trans on Image Processing,2002,11(7):746-755.
[84]Guo Guo-Dong, Jain A. K.,Ma Wei-Ying et al. Learning similarity measeure for natural image retrieval with relevance feedback[J]. IEEE Trans on Neural Networks,2002, 13(4):811-820.
[85]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(1)：45-48,53.
[86]Li Xuemei,Ding Lixing, Li Jincheng,Xu Gang. Combining KPCA and LSSVM for HVAC fan machinery fault recognition[C]. IEEE International Conference on Robotics and Biomimetics,2009:1241-1246.
[87]Seongkyu Y, John F, MacGregor. Fault diagnosis with multivariate statistical models part I:using steady state fault signatures[J]. Journal of process control, 2001,11:387-400.
[88]王华忠,俞金寿.基于核函数主元分析的软测量建模方法及应用[J].华东理工大学学报,2004,30(5)：567-570.
[89]Turk M. Pentland A. Eigenfaces for Recognition[J]. Journal of Cognitive Neuroscience, 1991,3(1):71-86.
[90]Yang Ming Hsuan, Ahuja N, Kriegman D. Face Recognition Using Kernel Eigenfaces[C].In Proceedings, International Conference on Image Processing,2000,1:37-40.
[91]Zhong Bingxiang, You Mingying. Research on Traffic Prediction Model Based on KPCA[J]. Advances in Intelligent and Soft Computing,2009,62(2):869-878.
[92]王作英,肖熙.基于段长分布的HMM语音识别模型[J].电子学报,2004,32(1)：46-49.
[93]Heck, L. P. Signal processing research in automatic tool wear monitoring[C]. IEEE International Conference on Acoustics, Speech,and Signal Processing,1993,1:55-58.
[94]L. R. Rabiner. A tutorial on Hidden Markov Models and selected application in speech recognition[J]. Proc. IEEE,1989,77(2):257-286.
[95]茅晓泉,胡光锐等.一种DHMM的混合训练方法[J].电子学报,2002,30(1)：148-150.
[96]高雨清,陈永彬.隐Markov模型参数估计的一种新方法[J].自动化学报,1991,17(1)：56-62.
[97]何强,何英.Matlab扩展编程[M].北京：清华大学出版社,2002
[98]何强,张有为.多观察序列连续隐含马尔柯夫模型的无溢出参数重估[J].电子学报,2000,28(10)：98-101.
[99]许丽红,余小清,万旺根.基于HMM算法的语音识别系统设计及其混合编程实现[J].计算机工程,2002,28(5)：139-140,163.
[100]Yuan ZM, Pan H. Hybrid SVM-HMM based recognition algorithm for pen-based tutoring system[J]. Proceedings of the Society of Photo-optical Instrumentation Engineers (SPIE),2007,2(1):67-90.
[101]Rahim M G,Biing-Hwang Juang, Wu Chou et al. Signal conditioning techniques for robust speech recognition[J]. IEEE Signal Processing Letters,1996,3(4):107-109.
[102]Chin-HuiLee, Chih-Heng, Bing-Hwang Juang.A Study on Speaker Adaptation of Contimuous Density HMM Parameters[C]. ICASSP-1990:145-148.
[103]熊四昌.基于计算机视觉的刀具磨损状态监测技术的研究[D].杭州：浙江大学,2003.
[104]高宏力.切削加工过程中刀具磨损的智能监测技术研究[D].成都：西南交通大学,2005.
[105]Tanaka, M., Sakawa, M., Shiromaru, I., Matsumoto, T. Application of Kohonen's self-organizing network to the diagnosis system for rotating machinery [M]. Systems, Man and Cybernetics,1995.
[106]Nadas A, et al. On a Model-Robust Training Method for Speech Recognition[J]. IEEE Trains. ASSP,1988,36(9):1432-1436.
[107]Rabiner L R, Juang B H.An Introduction to Hidden Markov Models[J]. IEEE ASSP Magazine.1986,3(1):4-6.
[108]战普明等.语音识别隐马尔可夫模型的改进[J].电子学报,1994,22(1)：9-15.
[109]V. Vapnik and A. Chervonenkis.On the uniform convergence of relative frequencies of events to their probabilities[J]. Theory of Probability and its Applications, 1971,16 (2):264-280.
[110]Suykens J A K, Brabanter J Se, Lukas L, et al. Weighted least squares support vector machines:robustness and sparse approximation[J]. Neurocomputing,2002,48:85-105.
[111]Shawe-Taylor, J., Bartlett, P. L.,Williamson, R. C.,Struetural risk minimization over data dependent hierarchies[J]. IEEE Transa Ctions on Information Theory,1998, 44 (5):1926-1940.
[112]邓乃扬,田英杰.数据挖掘中的新方法—支持向量机[M].北京：科学出版社,2004.
[113]Huang Yimin, Du Shuxin. Weighted support vector machine for classification with uneven training class sizes[C]. Proceedings of the Fourth International Conference on Machine Learning and Cybernetics. New York:[S. n.],2005:18-21.
[114]Zhang Xue-gong. Using class-center vectors to build support vector machines [J]. Neural Networks for Signal Processing IX-Proc of the 1999 IEEE Workshop, Wisconsin, 1999,33-37.
[115]Keerthi S S. Shavade S K. A fast interative nearest point algorithm for support vector machine classifier design[J].IEEE Trans on Neural Networks,2000,11(1):124-136.
[116]Suykens J, Vandewalle J. Least square support vector machine classifiers[J]. Neural Processing Letters,1999,9(3):293-300.
[117]Lu Shuxia, Wang Xizhao. A comparison among four SVM classification methods: LSVM,NLSVM,SSVM and NSVM[C].Proceedings of the Third International Conference on Machine Learning and Cybernetics. New York:[S. n.],2004:4277-4282.
[118]ReynaR. A., HemandezN., EsteveD. et al. Segmeniing images with support vector machines[C]. Proeeedings 2000 Intemational Conference on Image processing,2000, 1(1),820-823.
[119]Tian Q., Hong P. and Huang T. S. Update relevant image weights for conient-based image retrieval using support vector machines[C]. Proceedings of 2000 IEEE International Conference on MultI media and ExPo,2000,1199-1202.
[120]Sehwenker F., Kestler H. A. and Simon S..3D object recognition for autonomous mobile robots utilizing support vector classifiers [J]. Proeeedings 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation,2001, 2 (2):344-349.
[121]K. Lee, H. Byun. A new face authentication system for memory-constrained devices [J]. IEEE Transactions on Consumer Electronics,2003,49(4):1214-1222.
[122]K. H. Lee, Y. W. Chung, H. Byun. SVM-based face verification with feature set of small size[J]. Electronics Letters,2002,38(15):787-789.
[123]C. Bahlmann, B. Haasdonk, H. Burkhardt. On-line handwriting recognition with support vector machines-A kernel approach[C]. In Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition,2002:49-54.
[124]D. Gorgevik, D. Cakmakov. Combining SVM classifiers for handwritten digit recognition [J]. In Proceedings of 16th International Conference on Pattern Recognition,2002, 3:102-105.
[125]W. M. Campbell.A SVM/HMM system for speaker recognition[C]. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing,2003,2:209-212.
[126]A. V. Anghelescu, I. B. Muchnik. Combinatorial PCA and SVM methods for feature selection in learning classifications (Applications to text categorization) [C]. International Conference on Integration of Knowledge Intensive Multi-Agent Systems,2003,491-496.
[127]A. Kuh. Adaptive kernel methods for CDMA systems [C]. Proceedings of International Joint Conference on Neural Networks,2001,4:2404-2409.
[128]S. Chen, L. Hanzo. Block-adaptive kernel-based CDMA multiuser detection[C]. IEEE International Conference on Communications,2002,2:682-686.
[129]S. Osowski, L. T.Hoai, T.Markiewicz. Support vector machine-based expert system for reliable heartbeat recognition[J]. IEEE Transactions on Biomedical Engineering,2004, 51(4):582-589.
[130]W. H. Land, L.Wong, D. W. Mckee, et al. Breast cancer computer aided diagnosis (CAD)using a recently developed SVM/GRNN Oracle hybrid[C]. IEEE International Conference on Systems, Man and Cybernetics,2003,5:4705-4711.
[131]C. Batur, L. Zhou, C. C. Chan. Support vector machines for fault detection[C]. Proceedings of the 41st IEEE Conference on Decision and Control,2002,2:1355-1366.
[132]Scholkopf B, Burges C, V apnik V. Extracting support data for a given task[C].Proc of 1st Int Conf on Knowledge D iscovery & Data Mining,1995,262-267.
[133]高学,金连文,尹俊勋等.一种基于支持向量机的手写汉字识别方法[J].电子学报,2002,30(5)：651-654.
[134]张宝昌,陈熙霖等.基于支持向量的Kernel判别分析[J].计算机学报,2006,29(12)：2143-2150.
[135]李国正,王猛,曾华军.支持向量机导论[M].北京：电子工业出版社,2004.
[136]Scholkopf B, Burges S, Knirsch C, et al. Input spaces as feature space in kernel-based methods[J].IEEE Transactions on Neural Networks,1999,10(5):1299-1319.
[137]Scholkopf B, Smola A, Muller K R. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation,1998,12(2):1244-1249.
[138]Scholkopf B, Smola A, Muller K R.Kernel principal component analysis/Advances in Kernel Methods-Support Vector Learning[J]. Cambridge MA:M IT Press,1999:327-352.
[139]T S Jaakkola, D Haussler. Probabilistic kernel regression models[C]. In:Proceeding of the Confece on A.I. and Statistics,1999:123-128.
[140]F. Camastra. Kernel methods for Computer Vision:Theory and Applications[D]. Thesis Prosition, Genova University, Italy,2001.
[141]C.Campbell, K. P. Bennell. A Linear programming approach to novely detection[J]. In Advance in Neural Information Processing Systems, V.11 MIT press,2001.
[142]ValleS, LiW, Qin S J. Selection of the number of Principal components:The variance of the reconstruction error criterion with a comparison to other methods [J]. Industrial & Engineering Chemistry Research,1999,38(11):4389-4401.
[143]Qin S J, Dunia R. Determining the number of Principal components for best reconstruction[J]. Joumal of proeess Control,2000,10(2-3):245-250.
[144]Anthony M. Probabilistic Analysis of Leaming in Artificial Neural Networks:The PCA Model and Its Variants[J]. Neural ComPuting Surveys,1997,1:1-47.
[145]何新,史迎春,黄兵,周献中.基于SVM/HMM混合模型的音频分类方法[C].中国控制与决策学术年会论文集,2005：1503-1508.
[146]忻栋,杨莹春,吴朝晖.基于SVM-HMM混合模型的说话人确认[J].计算机辅助设计与图形学学报,2002,14(11)：1080-1082.
[147]Liu Jiang-hua, Chen Jia-pin,Chen Jun-shi. Hybrid SVM/HMM Method for Face Recognition[J]. Journal DongHua University,2004,21(1):34-38.
[148]刘冠军,徐哲,邱静,吕克洪.基于TSMD-SVM-HMM的机内测试智能降虚警方法[J].国防科技大学学报,2007,29(4)：100-104.
[149]卢秉恒.机械制造技术基础[M].北京：机械工业出版社,2001.
[150]康晶,孟广耀,邵强,吴树财.组合机床自动线中数控滑的PLC控制[J].组合机床与自动化加工技术,2002,8：74-75.
[151]王树逵,齐济源.数控加工技术[M].北京：清华大学出版社,2009.
[2]张正松,傅尚新,冯冠平,徐玉铮等编著.旋转机械振动监测及故障诊断[M].北京：机械工业出版社,1991.
[3]吴今培,肖建华著.智能故障诊断与专家系统[M].北京：科学出版社,1997.
[4]冯长建.HMM动态模式识别理论、方法以及在旋转机械故障诊断中的应用[D].杭州：浙江大学,2002.
[5]Sohre J S. Trouble-shooting to stop vibration of centrifugal[J]. Petro/Chem engineering, 1968,11:22-33.
[6]白木万博阳[日].机械振动讲演论文集[C].郑州机械研究所.1984.
[7]夏松波,张礼勇.旋转机械故障诊断技术的现状与展望[J].振动与冲击,1997,16(2)：1-5.
[8]魏文辉,宋强,滕乐天,王伟,刘文华,袁志昌.基于反故障控制的链式STATCOM动态控制策略的研究[J].中国电机工程学报,2005,25(4)：19-24.
[9]晏巨,何晓军,唐岚.电磁悬浮隔振系统控制方法[J].光电工程,1999,26(4)：18-22.
[10]刘春生.复杂非线性系统的智能故障诊断与容错控制[D].南京：南京航空航天大学,2006.
[11]胡寿松,唐建秋.故障大系统的鲁棒容错控制方法[J].南京航空航天大学学报,1993,25(1)：1-6.
[12]王军政,汪首坤,郑万煦.某高炮随动系统故障诊断装置的研制[J].北京理工大学学报,2002,22(3)：328-330.
[13]张瑞芳,叶汉民,覃嘉恒.基于DSP的齿轮减速器故障诊断装置[J].煤矿机械,2008,28(8)：190-192.
[14]于传强,郭晓松,张安,余相桃.大型机电设备故障诊断装置的实现[J].计算机测量与控制,2003,11(7)：531-532,552.
[15]王秀贞.汽车故障诊断与检测技术[M].北京：人民邮电出版社,2003.
[16]黄守道.无刷双馈电机的控制方法研究[D].长沙：湖南大学,2005.
[17]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[J].中国机械工程,1999,10(3)：307-310.
[18]Cooley J W, Tukey J W. An algorithm for the machine calculation of complex Fourier series[J]. Mathematies of Computation.1965,19(90):297-301.
[19]Littlewood J E, et al. Theorems on Fourier series and power series [J]. J. L.M. S.,1931,6: 230-238.
[20]Grandke T. Interpolation algorithms for discrete Fourier transforms of weighted signals[C]. IEEE Trans on Instru and Meas.1983, IM-32(2):350-55.
[21]Pgoupilaud P. Cycle-octive and Related Transform in Seismic Singal Analysis Geoerploration[J]. Singal Analysis,1985,23(984):85-102.
[22]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—相位差校正法[J].振动工程学报,1999,12(4)：454-459.
[23]胡红英.局域波分解方法、特征剖析及应用研究[D].大连：大连理工大学,2006.
[24]J.B. Theoeharis. A high-order neuron-fuzzy system internal dynamies:APPlication to the adaptive cancellation[J]. Fuzzy Sets and Systems.2006,157(1):471-500.
[25]Ocak, H., Loparo, K. A. New bearing fault detection and diagnosis scheme based on hidden Markov modeling of vibration signals[C]. Acoustics, Speech, and Signal Processing,2001. Proceedings.2001 IEEE International Conference on,2001(5):3141-3144.
[26]Frank P.M. Fault diagnosis in dynamic systems using analytical and knowledge based redundancy-A Survey and Some New Results[J]. Automatica,1990,26(3):459-474.
[27]Mastorocostas, P. A, Theoehairs, J. B. A recurrent fuzzy-neural model for dynamic system identification[J]. IEEE Transactions on Systems,Man and Cybernetics, partB (Cybernetics).2002,32(2):179-190.
[28]A. Ciehoeki,W. KasPrzka. Nonlinear learning algorithms for blind separation of natural images[J]. Neural Network World,1996,4:515-523.
[29]D. Yu,. F. Sat. A new blind image watermarking technique based on independent component analysis[J]. Lecture Notes in Computer Science, Springer-Verlag,2003,51-63.
[30]J. Karhumen, A. HyVarinen, R. Vigario, J.Hurri, andE.oja. APPlications of neural blind separation to signal and image Proeessing[C]. IEEE Int. Conf. on Aeoustics, speech and Signal Proeessing(ICASSP,97),1997:131-134.
[31]Talyor F W.. "On the Art of Cutting Metals" [M]. ASME,1907.
[32]#12
[33]#12
[34]Arnold R. N.. The Mechanism of Tool Vibration in the Cutting of Steel [J]. Proc. of Inst. Mech. Eng, Vol.154, London,1946.
[35]Hahn R.S..Metal-Cutting Chatter and Its Elimination[J].Trans. ASME, Vol.75,1953.
[36]Hahn R. S..On the Theory of Regenerative Chatter in Precision-Grinding Operations [J]. Trans. ASME, Vol.76,1954.
[37]Tlusty J. Spacek L.. Self-Excited Vibrations in Machine Tools[M]. Prague,1954.
[38]索科洛夫斯基著,浙江大学机械制造教研室译.机械制造工艺的科学基础[M].北京：机械工业出版社,1955.
[39]星铁太郎.楼械加工びびり现象——解析と封策[R].工业调查会登行.1977.
[40]费仁元,王民.切削颤振在线监控的研究现状及进展[J].中国机械工程,2001,12(9)：1075-1079.
[41]王先上.车床振动的自动控制[J].机械工程学报,1986,22(2)：38-47.
[42]ShiraishiM. Yamanaka K, Fujita H. Optimal Control of Chatter in Turning[J]. Int. J. Mach. Tools Manufact,1991,31(1):31-43.
[43]Eugene I, Rivin, Kang Hongling. Enhancement of Dynamic Stability of Cantilever Tooling Structure[J]. Int J.Mach. Tools Manufact,1992,32(4):539-561.
[44]费仁元,阿不都热依木,王民,关剑,朱志坚,伯提古丽.制造系统监控中模糊神经元网络的结构和应用[J].北京工业大学学报,2000,26(4)：1-4.
[45]孔繁森,赵新刚,刘春颖.切削过程混沌颤振的控制方法仿真研究[J].振动与冲击,2008,27(11)：22-26,195.
[46]Eman, K.,Wu, S.M. Feasibility Study of On-line Identification of Chatter in Turning Operations[J].J Eng Ind Trans ASME,1980,102(4):315-321.
[47]Tansel I N. Recognition of Chatter with Neural Networks. Int[J]. J. Mach. Tools Manufact, 1991,31 (4):539-552.
[48]Miyoshi Y. Estimation and application of mean square frequency[J].Bull. JSPE,1992(3): 221-225.
[49]于骏一等.切削颤振的预报控制[J].振动工程学报,1990,3(1)：72-78.
[50]赵芝眉,谢锡俊,吴波.切削颤振预兆的研究[J].南京工学院学报,1988,18(2)：47-54.
[51]高国利,王仁德,王启义.车削颤振的稳定区搜索控制[J].东北大学学报(自然科学版),1996.17(4)：412-415.
[52]贺长生,李慧,庞海文,梁旭.切削颤振预报方法探讨[J].长春大学学报,2003,13(6)：4-6.
[53]张永亮,于骏一,侯东霞,张守勤吴华.基于电流变效应的车削颤振预报控制技术的研究[J].机械工程学报,2005,41(4)：206-211.
[54]石莉,贾春德,孙玉龙.应用小波研究动态铣削力及预报铣削颤振[J].哈尔滨工业大学学报,2006,38(10)：1778-1780.
[55]康晶,冯长健,杨国田.离散隐马尔可夫模型在颤振预报中的应用研究[J].机械科学与技术,2008,27(3)：360-364.
[56]Jong Min Lee, Seung-Jong Kim et al. Diagnosis of mechanical fault signal using continuous hidden Markov model[J]. Journal of Sound and Vibration,2004,276:1065-1080.
[57]Dornf eld, D. A., et al., Neural Network Sensor Fusion for Tool Condition Moniroring[J]. Annals of the CIRP,1990,39(1):101-105.
[58]Lezanski P, Rafalowicz J. An Intelligent Monitoring System for Cylindrical Grinding[J]. Annals of the CIRP,1993,42(1):393-396.
[59]Dimla E. Tool Wear Monitoring in Metal Cutting Operation Using Neural Networks and Multivariate Process Parameters[J]. NC 1998:807-810.
[60]陈花玲,戴德沛.机床切削颤振的非线性理论研究[J].振动工程学报,1992,5(4)：335-342.
[61]蔡志强,吴雅,周笠,杨叔子.故障诊断与切削颤振的小波分析[J].华中理工大学学报,1993,21(1)：88-94.
[62]周晓勤,于骏一,王文才.人工神经网络在切削颤振类别诊断中的应用[J].农业机械学报,1998,29(2)：156-160.
[63]胡耀斌,江涌涛,张春良,吕海波.基于支持向量回归的切削颤振状态趋势预测的研究[J].组合机床与自动化加工技术,2006,3(13),42-46.
[64]黄强,张根保,张新玉,曹东风.对再生型切削颤振模型的试验分析[J].振动工程学报,2008,12(6)：547-552.
[65]Kondo, Eiji, et al. Effects of tool flank wear on occurrences of regenerative chatter[J]. C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C,1995,61 (584):1279-1285.
[66]E. Marui,M. Hashimoto et al. Regenerative chatter vibration occurring in turning with different sidecutting edge angles[J]. Journal of Engineering for Industry, Transactions of the ASME,1995,117(4):551-558.
[67]付连宇,于骏一,鲍明.切削颤振的相位特性研究[J].振动工程学报,2000,13(4)：510-515.
[68]刘安民,彭程,刘吉兆,郭雪娥.高速铣削时颤振的诊断和稳定加工区域的预报[J].机械工程学报,2007,43(1)：164-169.
[69]孔繁森,于骏一,潘志刚.切削过程再生颤振的模糊稳定性分析[J].振动工程学报,1998,11(1)：106-109.
[70]E. Solis, C. R. Peres, J. E. Jimeneza, R. Alique, J. C. Monje. A new analytical-experimental method for the identification of stability lobes in high-speed milling[J]. International Journal of Machine Tools & Manufacture,2004,44(1):1591-1597.
[71]谢锦辉.隐Markov模型(HMM)及其在语音处理中的应用[M].武汉：华中理工大学出版社,1995.
[72]Qing Wang, Zheru Chi, Feng, D. D., Rongchun Zhao. Hidden Markov random field based approachfor off-line handwritten Chinese character recognition[C]. Pattern Recognition,2000. Proceedings.15th International Conference on,2000,2:347-350.
[73]童进,吴昭同等.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.
[74]Heck, L. P., McClellan, J. H. Mechanical system monitoring using hidden Markov models[C]. International Conference on coustics, Speech, and Signal Processing,1991,3:1697-1700.
[75]Changjun Zhou,Xiaopeng Wei,Qiang Zhang. Face recognition based on HMM-SVM[J]. ICIC Express Letters,2007,1(2):137-143.
[76]Siohan.0.,Chesta. C., Chin-Hui Lee. Joint maximum a posteriori adaptation of transformation and HMM parameters. Speech and Audio Processing[J]. IEEE Transactions on Image Processing,2001,9(4):417-428.
[77]V. Vapnik. Estimaiton of Dependencies Based on Empirical Data [M]. Berlin:Springer Verlag,1982.
[78]V. Vapnik. The Nature of statislical Learning Theory[M]. Berlin:Springer Verlag,1995.
[79]V. Vapnik.Statistical Learning Theory[M]. Berlin:Wiley,1998.
[80]范玉妹,赵丽丽.关于支持向量分类机算法的研究[J].石家庄铁道学院学报(自然科学版),2007,20(3)：31-36.
[81]Reyna R. A., Hernandez N., Esteve D. et al. Segmenting images with support vector machines[C]. In Proceedings of 2000 International Conference on Image Processing, Vancover, BC, Canada,2000,1(1):820-823.
[82]Isermann,R. Model based fault detection and diagnosis methods[C]. American Control Conference,1995:1605-1609.
[83]Valentini A., Zhang Hongjiang. Automatic image orientation detection[J]. IEEE Trans on Image Processing,2002,11(7):746-755.
[84]Guo Guo-Dong, Jain A. K.,Ma Wei-Ying et al. Learning similarity measeure for natural image retrieval with relevance feedback[J]. IEEE Trans on Neural Networks,2002, 13(4):811-820.
[85]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(1)：45-48,53.
[86]Li Xuemei,Ding Lixing, Li Jincheng,Xu Gang. Combining KPCA and LSSVM for HVAC fan machinery fault recognition[C]. IEEE International Conference on Robotics and Biomimetics,2009:1241-1246.
[87]Seongkyu Y, John F, MacGregor. Fault diagnosis with multivariate statistical models part I:using steady state fault signatures[J]. Journal of process control, 2001,11:387-400.
[88]王华忠,俞金寿.基于核函数主元分析的软测量建模方法及应用[J].华东理工大学学报,2004,30(5)：567-570.
[89]Turk M. Pentland A. Eigenfaces for Recognition[J]. Journal of Cognitive Neuroscience, 1991,3(1):71-86.
[90]Yang Ming Hsuan, Ahuja N, Kriegman D. Face Recognition Using Kernel Eigenfaces[C].In Proceedings, International Conference on Image Processing,2000,1:37-40.
[91]Zhong Bingxiang, You Mingying. Research on Traffic Prediction Model Based on KPCA[J]. Advances in Intelligent and Soft Computing,2009,62(2):869-878.
[92]王作英,肖熙.基于段长分布的HMM语音识别模型[J].电子学报,2004,32(1)：46-49.
[93]Heck, L. P. Signal processing research in automatic tool wear monitoring[C]. IEEE International Conference on Acoustics, Speech,and Signal Processing,1993,1:55-58.
[94]L. R. Rabiner. A tutorial on Hidden Markov Models and selected application in speech recognition[J]. Proc. IEEE,1989,77(2):257-286.
[95]茅晓泉,胡光锐等.一种DHMM的混合训练方法[J].电子学报,2002,30(1)：148-150.
[96]高雨清,陈永彬.隐Markov模型参数估计的一种新方法[J].自动化学报,1991,17(1)：56-62.
[97]何强,何英.Matlab扩展编程[M].北京：清华大学出版社,2002
[98]何强,张有为.多观察序列连续隐含马尔柯夫模型的无溢出参数重估[J].电子学报,2000,28(10)：98-101.
[99]许丽红,余小清,万旺根.基于HMM算法的语音识别系统设计及其混合编程实现[J].计算机工程,2002,28(5)：139-140,163.
[100]Yuan ZM, Pan H. Hybrid SVM-HMM based recognition algorithm for pen-based tutoring system[J]. Proceedings of the Society of Photo-optical Instrumentation Engineers (SPIE),2007,2(1):67-90.
[101]Rahim M G,Biing-Hwang Juang, Wu Chou et al. Signal conditioning techniques for robust speech recognition[J]. IEEE Signal Processing Letters,1996,3(4):107-109.
[102]Chin-HuiLee, Chih-Heng, Bing-Hwang Juang.A Study on Speaker Adaptation of Contimuous Density HMM Parameters[C]. ICASSP-1990:145-148.
[103]熊四昌.基于计算机视觉的刀具磨损状态监测技术的研究[D].杭州：浙江大学,2003.
[104]高宏力.切削加工过程中刀具磨损的智能监测技术研究[D].成都：西南交通大学,2005.
[105]Tanaka, M., Sakawa, M., Shiromaru, I., Matsumoto, T. Application of Kohonen's self-organizing network to the diagnosis system for rotating machinery [M]. Systems, Man and Cybernetics,1995.
[106]Nadas A, et al. On a Model-Robust Training Method for Speech Recognition[J]. IEEE Trains. ASSP,1988,36(9):1432-1436.
[107]Rabiner L R, Juang B H.An Introduction to Hidden Markov Models[J]. IEEE ASSP Magazine.1986,3(1):4-6.
[108]战普明等.语音识别隐马尔可夫模型的改进[J].电子学报,1994,22(1)：9-15.
[109]V. Vapnik and A. Chervonenkis.On the uniform convergence of relative frequencies of events to their probabilities[J]. Theory of Probability and its Applications, 1971,16 (2):264-280.
[110]Suykens J A K, Brabanter J Se, Lukas L, et al. Weighted least squares support vector machines:robustness and sparse approximation[J]. Neurocomputing,2002,48:85-105.
[111]Shawe-Taylor, J., Bartlett, P. L.,Williamson, R. C.,Struetural risk minimization over data dependent hierarchies[J]. IEEE Transa Ctions on Information Theory,1998, 44 (5):1926-1940.
[112]邓乃扬,田英杰.数据挖掘中的新方法—支持向量机[M].北京：科学出版社,2004.
[113]Huang Yimin, Du Shuxin. Weighted support vector machine for classification with uneven training class sizes[C]. Proceedings of the Fourth International Conference on Machine Learning and Cybernetics. New York:[S. n.],2005:18-21.
[114]Zhang Xue-gong. Using class-center vectors to build support vector machines [J]. Neural Networks for Signal Processing IX-Proc of the 1999 IEEE Workshop, Wisconsin, 1999,33-37.
[115]Keerthi S S. Shavade S K. A fast interative nearest point algorithm for support vector machine classifier design[J].IEEE Trans on Neural Networks,2000,11(1):124-136.
[116]Suykens J, Vandewalle J. Least square support vector machine classifiers[J]. Neural Processing Letters,1999,9(3):293-300.
[117]Lu Shuxia, Wang Xizhao. A comparison among four SVM classification methods: LSVM,NLSVM,SSVM and NSVM[C].Proceedings of the Third International Conference on Machine Learning and Cybernetics. New York:[S. n.],2004:4277-4282.
[118]ReynaR. A., HemandezN., EsteveD. et al. Segmeniing images with support vector machines[C]. Proeeedings 2000 Intemational Conference on Image processing,2000, 1(1),820-823.
[119]Tian Q., Hong P. and Huang T. S. Update relevant image weights for conient-based image retrieval using support vector machines[C]. Proceedings of 2000 IEEE International Conference on MultI media and ExPo,2000,1199-1202.
[120]Sehwenker F., Kestler H. A. and Simon S..3D object recognition for autonomous mobile robots utilizing support vector classifiers [J]. Proeeedings 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation,2001, 2 (2):344-349.
[121]K. Lee, H. Byun. A new face authentication system for memory-constrained devices [J]. IEEE Transactions on Consumer Electronics,2003,49(4):1214-1222.
[122]K. H. Lee, Y. W. Chung, H. Byun. SVM-based face verification with feature set of small size[J]. Electronics Letters,2002,38(15):787-789.
[123]C. Bahlmann, B. Haasdonk, H. Burkhardt. On-line handwriting recognition with support vector machines-A kernel approach[C]. In Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition,2002:49-54.
[124]D. Gorgevik, D. Cakmakov. Combining SVM classifiers for handwritten digit recognition [J]. In Proceedings of 16th International Conference on Pattern Recognition,2002, 3:102-105.
[125]W. M. Campbell.A SVM/HMM system for speaker recognition[C]. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing,2003,2:209-212.
[126]A. V. Anghelescu, I. B. Muchnik. Combinatorial PCA and SVM methods for feature selection in learning classifications (Applications to text categorization) [C]. International Conference on Integration of Knowledge Intensive Multi-Agent Systems,2003,491-496.
[127]A. Kuh. Adaptive kernel methods for CDMA systems [C]. Proceedings of International Joint Conference on Neural Networks,2001,4:2404-2409.
[128]S. Chen, L. Hanzo. Block-adaptive kernel-based CDMA multiuser detection[C]. IEEE International Conference on Communications,2002,2:682-686.
[129]S. Osowski, L. T.Hoai, T.Markiewicz. Support vector machine-based expert system for reliable heartbeat recognition[J]. IEEE Transactions on Biomedical Engineering,2004, 51(4):582-589.
[130]W. H. Land, L.Wong, D. W. Mckee, et al. Breast cancer computer aided diagnosis (CAD)using a recently developed SVM/GRNN Oracle hybrid[C]. IEEE International Conference on Systems, Man and Cybernetics,2003,5:4705-4711.
[131]C. Batur, L. Zhou, C. C. Chan. Support vector machines for fault detection[C]. Proceedings of the 41st IEEE Conference on Decision and Control,2002,2:1355-1366.
[132]Scholkopf B, Burges C, V apnik V. Extracting support data for a given task[C].Proc of 1st Int Conf on Knowledge D iscovery & Data Mining,1995,262-267.
[133]高学,金连文,尹俊勋等.一种基于支持向量机的手写汉字识别方法[J].电子学报,2002,30(5)：651-654.
[134]张宝昌,陈熙霖等.基于支持向量的Kernel判别分析[J].计算机学报,2006,29(12)：2143-2150.
[135]李国正,王猛,曾华军.支持向量机导论[M].北京：电子工业出版社,2004.
[136]Scholkopf B, Burges S, Knirsch C, et al. Input spaces as feature space in kernel-based methods[J].IEEE Transactions on Neural Networks,1999,10(5):1299-1319.
[137]Scholkopf B, Smola A, Muller K R. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation,1998,12(2):1244-1249.
[138]Scholkopf B, Smola A, Muller K R.Kernel principal component analysis/Advances in Kernel Methods-Support Vector Learning[J]. Cambridge MA:M IT Press,1999:327-352.
[139]T S Jaakkola, D Haussler. Probabilistic kernel regression models[C]. In:Proceeding of the Confece on A.I. and Statistics,1999:123-128.
[140]F. Camastra. Kernel methods for Computer Vision:Theory and Applications[D]. Thesis Prosition, Genova University, Italy,2001.
[141]C.Campbell, K. P. Bennell. A Linear programming approach to novely detection[J]. In Advance in Neural Information Processing Systems, V.11 MIT press,2001.
[142]ValleS, LiW, Qin S J. Selection of the number of Principal components:The variance of the reconstruction error criterion with a comparison to other methods [J]. Industrial & Engineering Chemistry Research,1999,38(11):4389-4401.
[143]Qin S J, Dunia R. Determining the number of Principal components for best reconstruction[J]. Joumal of proeess Control,2000,10(2-3):245-250.
[144]Anthony M. Probabilistic Analysis of Leaming in Artificial Neural Networks:The PCA Model and Its Variants[J]. Neural ComPuting Surveys,1997,1:1-47.
[145]何新,史迎春,黄兵,周献中.基于SVM/HMM混合模型的音频分类方法[C].中国控制与决策学术年会论文集,2005：1503-1508.
[146]忻栋,杨莹春,吴朝晖.基于SVM-HMM混合模型的说话人确认[J].计算机辅助设计与图形学学报,2002,14(11)：1080-1082.
[147]Liu Jiang-hua, Chen Jia-pin,Chen Jun-shi. Hybrid SVM/HMM Method for Face Recognition[J]. Journal DongHua University,2004,21(1):34-38.
[148]刘冠军,徐哲,邱静,吕克洪.基于TSMD-SVM-HMM的机内测试智能降虚警方法[J].国防科技大学学报,2007,29(4)：100-104.
[149]卢秉恒.机械制造技术基础[M].北京：机械工业出版社,2001.
[150]康晶,孟广耀,邵强,吴树财.组合机床自动线中数控滑的PLC控制[J].组合机床与自动化加工技术,2002,8：74-75.
[151]王树逵,齐济源.数控加工技术[M].北京：清华大学出版社,2009.