基于核学习理论的船舶柴油机故障诊断研究
|
摘要
船舶柴油机是船舶动力装置的关键设备，如果发生故障，将会影响船舶营运，并可能造成巨大的经济损失，甚至造成关键设备损坏，危及人身安全。对船舶柴油机进行状态监测和故障诊断，能够有助于及时有效地发现并排除船舶柴油机的故障。这对于提高船舶柴油机工作时的安全性和可靠性，降低设备维修费用，减少经济损失，避免重大事故发生具有十分重大的意义。
船舶柴油机是典型的综合性复杂系统，其组成结构和工作原理导致了故障症状的复杂性。船舶柴油机的故障原因与故障征兆数值之间表现为极其错综复杂非线性关系，并且各特征参数之间往往呈现出强耦合性和非线性，因此必须采用非线性方法对其进行状态监测和故障诊断。
本文在总结和汲取前人研究成果的基础上，结合核学习理论在处理非线性问题方面所独有的优势，着重对基于核学习理论的柴油机故障诊断技术进行深入、系统的研究，其主要研究内容及成果包括以下几个方面。
1.利用核主元分析非线性状态监测的优势，针对船舶柴油机的燃料系统提出了一种基于核主元分析的状态监测方法。首先对正常采样数据进行核主元分析，计算监测统计量及其控制限，从而建立状态监测模型。然后利用建立的状态监测模型对船舶柴油机的燃料系统进行状态监测。对某型船舶柴油机燃料系统的状态监测结果验证了本文提出的方法的有效性。
2.结合核主元分析的特征提取优势和支持向量机具有较高的辨识率的特点，提出了一种新的船舶柴油机喷油系统的故障诊断方法。首先利用核主元分析对训练样本集进行特征提取，提取出最能反映船舶柴油机喷油系统故障状态的非线性主元。然后将提取的非线性主元用于支持向量机的训练，建立船舶柴油机喷油系统的故障诊断模型。最后利用所建立的故障诊断模型对船舶柴油机喷油系统的未知故障样本进行诊断。对某型船舶柴油机喷油系统的故障诊断结果表明：该方法能够准确识别船舶柴油机喷油系统的几种常见故障。
3.针对船舶柴油机的涡轮增压系统具有模糊性和非线性的特点，提出了一种基于模糊核聚类算法的船舶柴油机涡轮增压系统故障诊断的方法。首先对历史故障数据集进行模糊核聚类，得到聚类中心，建立船舶柴油机涡轮增压系统的故障诊断模型。然后，利用建立的故障诊断模型对船舶柴油机涡轮增压系统的未知故障样本进行诊断。对某型船舶柴油机涡轮增压系统的故障诊断结果表明：该方法对于船舶柴油机涡轮增压系统的几种常见故障具有较高的区分度。因为引入了模糊逻辑的概念，所以该方法的诊断结果也更加真实、客观。
4.针对智能化柴油机与传统柴油机的故障机理之间的差异，结合核fisher判别分析判别精度高和运算时间短等优点，提出了一种基于多类核fisher判别分析的故障诊断方法，并采用留一交叉检验法确定其中的参数。对某型船用智能化柴油机进行故障诊断的结果表明：该方法具有计算量小、耗时少、故障诊断准确率高等优点。因此，该方法非常适合于对船用智能化柴油机进行实时的故障诊断。
本文主要研究了核学习理论，提出和改进了各类基于核的分类方法，对船舶柴油机的各子系统建立了一系列的状态监测和故障诊断模型。这些方法分别具有各自的优点，能够满足不同子系统的故障诊断要求。
Marine diesel engine is the key equipment of ship power plant. If it does not work well,the operation of marine will be affected. And also, the economic loss and damage of otherkey equipments, even the personal safety will be affected. The condition monitoring and faultdiagnosis for marine diesel engine are helpful to find and eliminate the faults of marine dieselengine promptly and effectively. It has important significance towards improving the securityand reliability of marine diesel engine, lowing equipment maintenance expenses, reducingeconomic loss and avoiding major accidents.
Marine diesel engine is a typical complex system. Its structure and operational principleresult the complexity of fault symptom. The relationship between fault reasons of marinediesel engine and characteristic parameters is extremely complicated and nonlinear. Therelationship among characteristic parameters is also strong coupling and nonlinear. Therefore,a nonlinear method should be adopted for the condition monitoring and fault diagnosis ofmarine diesel engine.
On the basis of summing up and drawing the previous research results, combined withthe unique advantages in solving nonlinear problems of kernel-based learning theory, thisdissertation researches the condition monitoring and fault diagnosis technology for the marinediesel engine in detail. The research contents and contributions of this dissertation are statedas follows:
1. Using the advantage of kernel component analysis for nonlinear monitoring, a newcondition monitoring for the fuel system in marine diesel engine is proposed. Firstly, by thekernel principal component analysis of the normal sampling data set of fuel system andcalculating the monitoring statistics and their control limits, a condition monitoring model isbuilt. Secondly, the condition monitoring model is used to detect the fault of fuel system inmarine diesel engine. The results of condition monitoring in the fuel system of certain typemarine diesel engine verify the effectiveness of this method.
2. Combining with the advantages of kernel principal component analysis for extractingnonlinear feature and the higher recognition rate of support vector machine, a new fault diagnosis method for the fuel injection system in marine diesel engine is proposed. Firstly, bythe kernel principal component analysis of training sample data set, the nonlinear principalcomponents are extracted. The nonlinear principal components can reflect the fault state offuel injection system in marine diesel engine. Secondly, the support vector machines aretrained by using the extracted nonlinear principal components, and a fault diagnosis model isbuilt. Finally, the unknown fault samples of fuel injection system in marine diesel engine arediagnosed by the fault diagnosis model. The results of fault diagnosis for fuel injectionsystem in a certain type marine diesel engine show that the several common faults in fuelinjection system can be identified accurately by using the method.
3. According to the fuzzy and nonlinear features of turbocharged system in marine dieselengine, a fault diagnosis method based on kernel-based fuzzy clustering is proposed. Firstly,kernel-based fuzzy clustering is applied to classify the faults of historical data set in order toget the clustering centers. And a fault diagnosis model for turbocharged system in marinediesel engine is built. Secondly, the unknown fault samples of turbocharged system in marinediesel engine are diagnosed by the fault diagnosis model. The results of fault diagnosis forturbocharged system in a certain type marine diesel engine show that the several commonfaults in turbocharged system can be identified accurately. By introducing the concept offuzzy logic, the diagnosis results of this method are more close to practice and objective.
4. According to the differences between intelligent diesel engine and traditional dieselengine, a fault diagnosis method for intelligent diesel engine based on multiclass kernel fisherdiscriminant analysis is proposed. Kernel fisher discriminant analysis has many advantagessuch as high precision of discriminant, short computing time, etc. The parameters aredetermined by using leave-one-out cross-validation method. The results of fault diagnosis fora certain type marine diesel engine show that the method has the advantages such as lowcomputational complexity, short time consuming, high diagnosis accuracy, etc. Therefore,this method is very suitable for the real-time fault diagnosis of intelligent marine dieselengine.
This dissertation mainly researches the kernel-based learning theory, proposes andimproves the kernel-based classification method, and builds a series of condition monitoringand fault diagnosis models for the subsystems in marine diesel engine. These methods allhave their own advantages and can satisfy the requirements of fault diagnosis for the different subsystems.
船舶柴油机是典型的综合性复杂系统，其组成结构和工作原理导致了故障症状的复杂性。船舶柴油机的故障原因与故障征兆数值之间表现为极其错综复杂非线性关系，并且各特征参数之间往往呈现出强耦合性和非线性，因此必须采用非线性方法对其进行状态监测和故障诊断。
本文在总结和汲取前人研究成果的基础上，结合核学习理论在处理非线性问题方面所独有的优势，着重对基于核学习理论的柴油机故障诊断技术进行深入、系统的研究，其主要研究内容及成果包括以下几个方面。
1.利用核主元分析非线性状态监测的优势，针对船舶柴油机的燃料系统提出了一种基于核主元分析的状态监测方法。首先对正常采样数据进行核主元分析，计算监测统计量及其控制限，从而建立状态监测模型。然后利用建立的状态监测模型对船舶柴油机的燃料系统进行状态监测。对某型船舶柴油机燃料系统的状态监测结果验证了本文提出的方法的有效性。
2.结合核主元分析的特征提取优势和支持向量机具有较高的辨识率的特点，提出了一种新的船舶柴油机喷油系统的故障诊断方法。首先利用核主元分析对训练样本集进行特征提取，提取出最能反映船舶柴油机喷油系统故障状态的非线性主元。然后将提取的非线性主元用于支持向量机的训练，建立船舶柴油机喷油系统的故障诊断模型。最后利用所建立的故障诊断模型对船舶柴油机喷油系统的未知故障样本进行诊断。对某型船舶柴油机喷油系统的故障诊断结果表明：该方法能够准确识别船舶柴油机喷油系统的几种常见故障。
3.针对船舶柴油机的涡轮增压系统具有模糊性和非线性的特点，提出了一种基于模糊核聚类算法的船舶柴油机涡轮增压系统故障诊断的方法。首先对历史故障数据集进行模糊核聚类，得到聚类中心，建立船舶柴油机涡轮增压系统的故障诊断模型。然后，利用建立的故障诊断模型对船舶柴油机涡轮增压系统的未知故障样本进行诊断。对某型船舶柴油机涡轮增压系统的故障诊断结果表明：该方法对于船舶柴油机涡轮增压系统的几种常见故障具有较高的区分度。因为引入了模糊逻辑的概念，所以该方法的诊断结果也更加真实、客观。
4.针对智能化柴油机与传统柴油机的故障机理之间的差异，结合核fisher判别分析判别精度高和运算时间短等优点，提出了一种基于多类核fisher判别分析的故障诊断方法，并采用留一交叉检验法确定其中的参数。对某型船用智能化柴油机进行故障诊断的结果表明：该方法具有计算量小、耗时少、故障诊断准确率高等优点。因此，该方法非常适合于对船用智能化柴油机进行实时的故障诊断。
本文主要研究了核学习理论，提出和改进了各类基于核的分类方法，对船舶柴油机的各子系统建立了一系列的状态监测和故障诊断模型。这些方法分别具有各自的优点，能够满足不同子系统的故障诊断要求。
Marine diesel engine is the key equipment of ship power plant. If it does not work well,the operation of marine will be affected. And also, the economic loss and damage of otherkey equipments, even the personal safety will be affected. The condition monitoring and faultdiagnosis for marine diesel engine are helpful to find and eliminate the faults of marine dieselengine promptly and effectively. It has important significance towards improving the securityand reliability of marine diesel engine, lowing equipment maintenance expenses, reducingeconomic loss and avoiding major accidents.
Marine diesel engine is a typical complex system. Its structure and operational principleresult the complexity of fault symptom. The relationship between fault reasons of marinediesel engine and characteristic parameters is extremely complicated and nonlinear. Therelationship among characteristic parameters is also strong coupling and nonlinear. Therefore,a nonlinear method should be adopted for the condition monitoring and fault diagnosis ofmarine diesel engine.
On the basis of summing up and drawing the previous research results, combined withthe unique advantages in solving nonlinear problems of kernel-based learning theory, thisdissertation researches the condition monitoring and fault diagnosis technology for the marinediesel engine in detail. The research contents and contributions of this dissertation are statedas follows:
1. Using the advantage of kernel component analysis for nonlinear monitoring, a newcondition monitoring for the fuel system in marine diesel engine is proposed. Firstly, by thekernel principal component analysis of the normal sampling data set of fuel system andcalculating the monitoring statistics and their control limits, a condition monitoring model isbuilt. Secondly, the condition monitoring model is used to detect the fault of fuel system inmarine diesel engine. The results of condition monitoring in the fuel system of certain typemarine diesel engine verify the effectiveness of this method.
2. Combining with the advantages of kernel principal component analysis for extractingnonlinear feature and the higher recognition rate of support vector machine, a new fault diagnosis method for the fuel injection system in marine diesel engine is proposed. Firstly, bythe kernel principal component analysis of training sample data set, the nonlinear principalcomponents are extracted. The nonlinear principal components can reflect the fault state offuel injection system in marine diesel engine. Secondly, the support vector machines aretrained by using the extracted nonlinear principal components, and a fault diagnosis model isbuilt. Finally, the unknown fault samples of fuel injection system in marine diesel engine arediagnosed by the fault diagnosis model. The results of fault diagnosis for fuel injectionsystem in a certain type marine diesel engine show that the several common faults in fuelinjection system can be identified accurately by using the method.
3. According to the fuzzy and nonlinear features of turbocharged system in marine dieselengine, a fault diagnosis method based on kernel-based fuzzy clustering is proposed. Firstly,kernel-based fuzzy clustering is applied to classify the faults of historical data set in order toget the clustering centers. And a fault diagnosis model for turbocharged system in marinediesel engine is built. Secondly, the unknown fault samples of turbocharged system in marinediesel engine are diagnosed by the fault diagnosis model. The results of fault diagnosis forturbocharged system in a certain type marine diesel engine show that the several commonfaults in turbocharged system can be identified accurately. By introducing the concept offuzzy logic, the diagnosis results of this method are more close to practice and objective.
4. According to the differences between intelligent diesel engine and traditional dieselengine, a fault diagnosis method for intelligent diesel engine based on multiclass kernel fisherdiscriminant analysis is proposed. Kernel fisher discriminant analysis has many advantagessuch as high precision of discriminant, short computing time, etc. The parameters aredetermined by using leave-one-out cross-validation method. The results of fault diagnosis fora certain type marine diesel engine show that the method has the advantages such as lowcomputational complexity, short time consuming, high diagnosis accuracy, etc. Therefore,this method is very suitable for the real-time fault diagnosis of intelligent marine dieselengine.
This dissertation mainly researches the kernel-based learning theory, proposes andimproves the kernel-based classification method, and builds a series of condition monitoringand fault diagnosis models for the subsystems in marine diesel engine. These methods allhave their own advantages and can satisfy the requirements of fault diagnosis for the different subsystems.
引文
[1]付宗仁.船舶柴油机常见故障及使用管理注意事项.装备制造技术，2011，（15）：83-85页.
[2]张旭.人工免疫算法及其在船舶柴油机智能故障诊断中的应用研究.大连海事大学博士学位论文，2007：1-10页.
[3]李宏坤.基于信息融合技术船舶柴油机故障诊断方法的研究与应用.大连理工大学博士学位论文，2003：2-5页.
[4]黄加亮，蔡振雄，张均东.船舶柴油机智能故障诊断仿真方法的研究.航海技术，2001，（3）：37-39页.
[5]王珍，马孝江，李作州等.基于局域波法的车用柴油机预知维修研究.车用发动机，2002，（1）：44-46页.
[6]王洪锋.船用智能化柴油机热力参数监测与诊断技术研究.武汉理工大学硕士学位论文，2008：2-5页.
[7] Edge K A, Boston O P, Burrows C R, et al. Approach to automated fault diagnosis ofhydraulic circuits using neural networks. American Society of Mechanical Engineers,1995,2(1):37-43P.
[8]罗存刚.基于神经网络的船舶柴油机远程故障诊断研究.大连海事大学硕士学位论文，2009：40-45页.
[9] Hountalas Dimitrios T. Prediction of marine diesel engine performance under faultconditions. Applied Thermal Engineering,2000,20(18):1753-1783P.
[10] Lunt Stuart, Recent developments in online oil condition monitoring sensors andalignment with astm methods and practices, Journal of ASTM International, v8, n7,July2011,8(7):86-106P.
[11]张维竞，张鹏，罗蛟龙.船舶动力装置故障诊断专家系统的开发.船舶工程，2000，（5）：38-40页.
[12] Eberle M K. DIAGNOSTIC SYSTEM FOR DIESEL ENGINES. Sulzer TechnicalReview,1976,58(4):163-167P.
[13]黄加亮，黄少竹，李玩幽.船用柴油机智能诊断技术的现状和发展动态.天津航海，2000，（1）：13-19页.
[14] Koga Mikio. Super advanced ship operation support system. Proceedings of theInternational Offshore and Polar Engineering Conference, Osaka, Japan,1994. UnitedStates: Int Soc of Offshore and Polar Engineerns,1994:636-643P.
[15] Guettinger Heinz, Koenig, Ferdinand, Meili Regula. Artificial intelligence formachines. Sulzer Technical Review,1992,74(4):18-22P.
[16] HIRPA L GELGELE, KESHENG WANG. An expert system for engine fault diagnosis:development and application. Journal of Intelligent Manufacturing,1998,9(6):539-545P.
[17] Ilkka Priha. FAKS—an on-line expert system based on hyperobjects. Expert Systemswith Applications,1991,3(2):207–217P.
[18] Grimmelius H T, Meiler P P, Maas H L M M, et al. Three state-of-the-art methods forcondition monitoring. IEEE Transactions on Industrial Electronics,1999,46(2):407-416P.
[19] Armstrong Robert A. Fault Assessment of a Diesel Engine Using VibrationMeasurements and Advanced Signal Processing. Master’s thesis of NAVALPOSTGRADUATE SCHOOL MONTEREY CA,1997:22-34P.
[20] Angeli, Chr. Integrating symbolic and numerical features for fault prediction anddiagnosis by an expert system. Expert Systems,1999,16(4):233-239P.
[21] Sun Ruixiang, Tsung Fugee, Qu Liangsheng. Combining bootstrap and geneticprogramming for feature discovery in diesel engine diagnosis. International Journal ofIndustrial Engineering: Theory Applications and Practice,2004,11(3):273-281P.
[22]郭江华，侯馨光，陈国钧等.船舶柴油机故障诊断技术研究.中国航海，2005，65（4）：75-78页.
[23]刘俊磊.柴油机智能故障诊断系统的综合研究与工程实现.东北大学硕士学位论文，2007：1-20页.
[24]刘世元，杜润生，杨叔子.小波包改进算法及其在柴油机振动诊断中的应用.内燃机学报，2000，18（1）：11-16页.
[25]伍学奎，陈进.基于小波包变换的内燃机气阀漏气诊断方法.振动工程学报，2000，13（2）：210-215页.
[26]李志敏，王义，宋希庚等.内燃机主轴承磨损故障的振动监测方法研究.内燃机学报，2000，18（2）：203-206页.
[27]吴恒，高强，温宇钦等. MAN B&W MC系列船用柴油机故障诊断专家系统.航海技术，1999，（1）：45-48页.
[28]朱建元.基于BP神经网络的船用柴油机振动状态监测.机电设备，2008，（3）：33-36页.
[29]牛洪瑜.基于神经网络的船舶柴油发电机组的故障诊断.兰州理工大学硕士学位论文，2007：4-8页.
[30]李海量，汤天浩.基于人工神经网络的船用主柴油机故障诊断.中国航海，1997，（2）：67-72页.
[31]黄加亮，蔡振雄. RBF网络在柴油机故障诊断领域中的应用与实现.集美大学学报，2002，7（4）：338-342页.
[32] Sch lkoph Bernhard, Sung Kah-Kay, Burges Chris J C, et al. Comparing supportvector machines with Gaussian kernels to radial basis function classifiers. IEEETransactions on Signal Processing,1997,45(11):2758-2765P.
[33] Tipping Michael E. Sparse Bayesian Learning and the Relevance Vector Machine.Journal of Machine Learning Research,2001,1(3):211-244P.
[34] N Aronszajn. Theory of reproducing kernels. Transactions of the AmericanMathematical Society,1950,68(3):337-404P.
[35] N Aronszajn, K T Smith. Invariant Subspaces of Completely Continuous Operators.Annals of Mathematics,1954,60(2):345-350P.
[36] A Aizerman, E M Braverman, L I Rozoner. Theoretical foundations of the potentialfunction method in pattern recognition learning. Automation and Remote Control,1964,25:821-837P.
[37] Boser B E, Guyon I M, Vapnik. A training algorithm for optimal margin classifiers.Proceedings of the5th Annual ACM Workshop on Computational Learning Theory,Pittsburgh, USA,1992. New York: ACM Press,1992:144-152P.
[38] Sch lkoph B, Smola A, Müller K R. Nonlinear component analysis as a kerneleigenvalue problem. Neural Computation,1998,10(5):1299-1399P.
[39] Mika S, Ratsch G, Weston J, et al. Fisher discriminant analysis with kernels. Fisherdiscriminant analysis with kernels. Proceedings of the1999IEEE Signal ProcessingSociety Workshop, Madison, USA,1999. Piscataway: IEEE,1999:41-48P.
[40] Baudat G,Anouar F. Generalized discriminant analysis using a kernel approach. NeuralComput,2000,12:2385-2404P.
[41] Peiling Lai, Colin Fyfe. Kernel and Nonlinear Canonical Correlation Analysis.International Journal of Neural Systems,2000,10(5):365-377P.
[42] Francis R Bach, Michael I Jordan. Kernel independent component analysis. Journal ofMachine Learning Research,2002,3(1):1-48P.
[43] Xie Xudong, Lam Kin-Man. Gabor-based kernel PCA with doubly nonlinear mappingfor face recognition with a single face image. IEEE Transactions on Image Processing,2006,15(9):2481-2492P.
[44] Fonseca Everthon Silva, Guido Rodrigo Capobianco, Scalassara Paulo Rogério, et al.Wavelet time-frequency analysis and least squares support vector machines for theidentification of voice disorders. Computers in Biology and Medicine,2007,37(4):571-578P.
[45] Xiuyan Peng, Yanyou Chai, Liufeng Xu, et al. Research on Fault Diagnosis of MarineDiesel Engine Based on Grey Relational Analysis and Kernel Fuzzy C-meansClustering. The Fifth International Conference on Intelligent Computation Technologyand Automation, Zhangjiajie, China,2012. United States: IEEE Computer Society,2012:283-286P.
[46]罗公亮.核函数方法（上）.冶金自动化，2002，（3）：1-4页.
[47]罗公亮.核函数方法（下）.冶金自动化，2002，（4）：1-4页.
[48] Zhang Yankun, Gu Xuefeng, Liu Chongqing. Face Recognition Using KernelDiscriminant Analysis. High Technology Letters,2002,8(4):43-46P.
[49]肖健华，吴今培.基于核的特征提取技术及应用研究.计算机工程，2002，28（10）：36-38页.
[50]邵惠鹤.支持向量机理论及其应用.自动化博览，2003，（S1）：90-95页.
[51]熊志化，黄国宏，邵惠鹤.基于高斯过程和支持向量机的软测量建模比较及应用研究.信息与控制，2004，33（6）：754-757页.
[52]阎威武，常俊林，邵惠鹤.一种贝叶斯证据框架下支持向量机建模方法的研究.控制与决策，2004，19（5）：523-528页.
[53]黄国宏，邵惠鹤.核主元分析及其在人脸识别中的应用.计算机工程，2004，30（13）：13-14页.
[54]陈才扣，杨静宇，杨健.一种融合PCA和KFDA的人脸识别方法.控制与决策，2004，19（10）：1147-1154页.
[55]刘海峰，姚泽清，刘守生等.文本分类中基于核的非线性判别.应用科学学报，2008，26（6）：627-631页.
[56]江南，王士同，贺杨成.核参数优化选取的混合C均值核模糊聚类算法.计算机工程与设计，2011，32（9）：3148-3151页.
[57]林材宽，乔建忠，王国仁等.基于核方法的非线性时间序列预测建模.计算机工程，2007，33（17）：23-25页.
[58]刘磊.优化算法在船舶柴油机智能故障诊断中的应用研究.哈尔滨工程大学硕士学位论文，2008：19-25页.
[59]王珍.基于局域波分析的柴油机故障诊断方法的研究及应用.大连理工大学博士学位论文，2002：3-10页.
[60]徐向荣.船舶柴油机故障诊断技术的研究及展望.南通航运职业技术学院学报，2007，6（3）：53-56页.
[61] Yanyou Chai, Xiuyan Peng, Xinjiang Man. Research on Fault Diagnosis of MarineDiesel Engine Based on KFDA. Advanced Materials Research,2012,442(1):262-266P.
[62]李斌.船舶柴油机.大连海事大学出版社，2008：33-37页.
[63]常勇，胡以怀.柴油机振动监测及故障诊断系统.噪声与振动控制，2008，（1）：93-96页.
[64] Li Yujun, Tse Peter W, Yang Xin, et al. EMD-based fault diagnosis for abnormalclearance between contacting components in a diesel engine. Mechanical Systems andSignal Processing,2010,24(1):193-210P.
[65] Amstutz Alois, Del Re Luigi R. EGO sensor based robust output control of EGR indiesel engines. IEEE Transactions on Control Systems Technology,1995,3(1):39-48P.
[66]王南兰.基于数据挖掘的柴油机磨损故障诊断Petri网络模型.机械与电子，2008，（1）：34-37页.
[67]陈平.浅析柴油机拉缸的成因及预防措施.南通航运职业技术学院学报，2009，8（2）：59-62页.
[68]周朝霞，张传爱.柴油机涡轮增压器的正确使用与维护.工程机械与维修，2003，（1）：116页.
[69] Farinha Torres, Fonseca Inácio, Sim es António, et al. New ways for terology throughpredictive maintenance in an environmental perspective. WSEAS Transactions onCircuits and Systems,2008,7(7):630-647P.
[70]陈亚，汪丛笑，周旭等.防爆柴油机车状态监测平台可靠性研究.工矿自动化，2011，（4）：51-53页.
[71]郭建平，马茂，刘增宝.一般柴油机故障原因的分析与排查.铁道机车车辆，2011，31（S1）：418-421页.
[72] Kouremenos D A, Hountalas D T. Diagnosis and condition monitoring ofmedium-speed marine diesel engines. Tribo Test,1997,4(1):63-91P.
[73]占惠文.基于模糊神经网络的船舶柴油机故障诊断系统研究.武汉理工大学硕士学位论文，2009：2-30页.
[74]黄少竹.现代船舶柴油机故障分析.大连海事大学出版社，2005：109-111页.
[75] Li Yujun, Tse Peter W, Yang Xin et al. EMD-based fault diagnosis for abnormalclearance between contacting components in a diesel engine. Mechanical Systems andSignal Processing,2010,24(1):193-210P.
[76] Li Hongkun, Zhou Peilin; Xiaojiang Ma. Marine diesel engine fault diagnosis by usingan improved Hubert spectrum. Journal of Ship Research,2006,50(4):378-387P.
[77] Martin K F. Review by discussion of condition monitoring and fault diagnosis inmachine tools. International Journal of Machine Tools and Manufacture,1994,34(4):527-551P.
[78] Lamaris V T, Hountalas D T. A general purpose diagnostic technique for marine dieselengines-Application on the main propulsion and auxiliary diesel units of a marinevessel. Energy Conversion and Management,2010,51(4):740-753P.
[79] Martin Brett, Meckl Peter. Input selection for modeling and diagnostics withapplication to diesel engines. Journal of Dynamic Systems, Measurement and Control,2007,129(1):114-120P.
[80] Thomson Bill. Machinery monitoring adds to ship intelligence. Motor Ship,1994,75(882):40-43P.
[81] Grimmelius Hugo T. Three state-of-the-art methods for condition monitoring. IEEETransactions on Industrial Electronics,1999,46(2):407-416P.
[82] Tan Yanghong, He Yigang, Cui Chun, et al. A novel method for analog fault diagnosisbased on neural networks and genetic algorithms. IEEE Transactions onInstrumentation and Measurement,2008,57(11):2631-2639P.
[83] Qinghua Wang, Youyun Zhang, Lei Cai, et al. Fault diagnosis for diesel valve trainsbased on non-negative matrix factorization and neural network ensemble. MechanicalSystems and Signal Processing,2009,23(5):1683-1695P.
[84] Morgan Ian, Liu Honghai. Predicting future states with n-dimensional markov chainsfor fault diagnosis. IEEE Transactions on Industrial Electronics,2009,56(5):1774-1781P.
[85] Nyberg Mattias, Stutte Thomas. Model based diagnosis of the air path of an automotivediesel engine. Control Engineering Practice,2004,12(5):513-525P.
[86] Wu X, Chen J, Wang W, et al. Multi-index fusion-based fault diagnosis theories andmethods. Mechanical Systems and Signal Processing,2001,15(5):995-1006P.
[87] Wang Zhihua. Fault diagnosis of diesel engine piston-ring using time-frequencyanalysis method. Journal of Wuhan University of Technology (Transportation Scienceand Engineering),2004,28(6):953-956P.
[88] Desbazeille M, Randall R B, Guillet F, et al. Model-based diagnosis of large dieselengines based on angular speed variations of the crankshaft. Mechanical Systems andSignal Processing,2010,24(5):1529-1541P.
[89] Zhou P, Li H, Clelland D. Pattern recognition on diesel engine working conditions bywavelet Kullback-Leibler distance method. Journal of Mechanical Engineering Science,2005,219(9):879-887P.
[90]廖明，石博强，张文明等.分形在柴油机燃油系故障诊断中的应用.北京科技大学学报，1998，20（5）：417-420页.
[91]吕琛，宋希庚.基于Kohonen网络的柴油机噪声故障分析系统.振动、测试与诊断，1999，19（3）：208-213页.
[92] Macián Vicente, Tormos Bernardo, Sala Antonio, et al. Fuzzy logic-based expertsystem for diesel engine oil analysis diagnosis. Insight: Non-Destructive Testing andCondition Monitoring,2006,48(8):462-469.
[93] Zhang Bin, Yan Jun, Liu Hongliang. Research on oil ferrography analysis faultdiagnosis of diesel engine based on BP neural network. Proceedings-20082ndInternational Symposium on Intelligent Information Technology Application, Shanghai,China,2008. United States: Inst. of Elec. and Elec. Eng. Computer Society,2008:519-524P.
[94]孙云岭，郭文勇，张永祥.基于瞬时转速的柴油机故障诊断仪的研制.内燃机，2010，（2）：16-17页.
[95] Antory David. Application of a data-driven monitoring technique to diagnose air leaksin an automotive diesel engine: A case study. Mechanical Systems and SignalProcessing,2007,21(2):795-808P.
[96] Charles P, Sinha Jyoti K, Gu F, et al. Detecting the crankshaft torsional vibration ofdiesel engines for combustion related diagnosis. Journal of Sound and Vibration,2009,321(3-5):1171-1185P.
[97] Tseng Chyuan-Yow, Lin Chiu-Feng. Characterisation of solenoid valve failure forelectronic diesel fuel injection system of commercial trucks. International Journal ofHeavy Vehicle Systems,2006,13(3):180-193P.
[98]张世康.钻井柴油机发生故障的原因与预防.石油机械，1992，20（9）：31-36页.
[99] Lee Jong-Min, Yoo ChangKyoo, Choi SangWook, et al, Nonlinear process monitoringusing kernel principal component analysis. Chemical Engineering Science,2004,59(1):223-234P.
[100]张曦，陈锐民，陈世和等.基于核主元分析和模式匹配的非线性性能监控和故障诊断.华北电力大学学报，2010，37（6）：69-73页.
[101] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619P.
[102]邓乃扬，田英杰.数据挖掘中的新方法—支持向量机.科学出版社，2004：92-97页.
[103]王华忠，俞金寿.核函数方法及其在过程控制中的应用.石油化工自动化，2005，25（1）：25-30页.
[104]张曦.基于统计理论的工业过程综合性能监控、诊断及质量预测方法研究.上海交通大学博士学位论文，2008：17-30页.
[105]胡金海，谢寿生，侯胜利等.核函数主元分析及其在故障特征提取中的应用.振动、测试与诊断，2007，27（1）：48-52页.
[106]关山.基于声发射信号多特征分析与融合的刀具磨损分类与预测技术，吉林大学博士学位论文，2011：79-88页.
[107] Yanyou Chai, Xiuyan Peng, Liufeng Xu, et al. Research on Fault Diagnosis of MarineDiesel Engine Based on Integrated Similarity. Communications in Computer andInformation Science,2011,227(4):678-685P.
[108]李玉峰.基于神经网络的柴油机燃油系统故障诊断的研究和实现.山东大学硕士学位论文，2007：29-35页.
[109] Corinna Cortes, Vladimir Vapnik. Support-Vector Networks. Machine Learning,1995,20(3):273-297P.
[110]马铁军，欧阳徕.基于混合核函数和PLS的胎面尺寸预测模型.橡胶工业，2010，57（8）：466-470页.
[111]彭秀艳，柴艳有，满新江.基于PCA-KFCM的船舶柴油机故障诊断.控制工程，2012，19（1）：152-156页.
[112]谭琨.基于支持向量机的高光谱遥感影像分类研究.中国矿业大学博士学位论文，2010：10-20页.
[113]邓乃扬，田英杰.支持向量机—理论、算法与拓展.科学出版社，2009：92-111页.
[114]明阳，陈进.基于谱相关密度切片分析和SVM的滚动轴承故障诊断.振动与冲击，2010，29（1）：197-199页.
[115]郎宇宁，蔺娟如.基于支持向量机的多分类方法研究.中国西部科技，2010，9（17）：28-29页.
[116] Hsu Chih-Wei, Lin Chih-Jen. A comparison of methods for multiclass support vectormachines. IEEE Transactions on Neural Networks,2002,13(2):415-425P.
[117] Sebald Daniel J, Bucklew James A. Support vector machine techniques for nonlinearequalization. IEEE Transactions on Signal Processing,2000,48(11):3217-3226P.
[118]王艳，陈欢欢，沈毅.有向无环图的多类支持向量机分类算法.电机与控制学报，2011，15（4）：85-89页.
[119]郎宇宁.基于支持向量机的多分类方法研究及应用.西南交通大学硕士学位论文，2010：16-25页.
[120] Van Gestel Tony, Suykens Johan A K., Baesens Bart, et al. Benchmarking LeastSquares Support Vector Machine Classifiers. Machine Learning,2004,54(1):5-32P.
[121]彭红星，陈祥光，徐巍. PCA特征抽取与SVM多类分类在传感器故障诊断中的应用.数据采集与处理，2010，25（1）：111-116页.
[122]杨艺芳. SVM和FCM相结合的故障诊断方法的研究.西安科技大学硕士学位论文，2008：38-44页.
[123] Zhong Ping, Fukushima Masao. Regularized nonsmooth Newton method formulti-class support vector machines. Optimization Methods and Software,2007,22(1):225-236P.
[124]黄移军.基于局部线性嵌入的高维数据降维研究.中南大学硕士学位论文，2009：25-26页.
[125]朱志宇，张冰，刘维亭.模糊支持向量机在船舶柴油机故障诊断中的应用.中国造船，2006，47（3）：64-69页.
[126]陈景锋，周程生，王诗武.柴油机喷油器启阀压力降低对工况的影响及其对策.集美航海学院学报，1998，16（2）：5-7页.
[127]林金田，陈景锋.喷油正时对船舶柴油机排气中有害成分的影响.铁道机车车辆，2003，23（S1）：108-110页.
[128]石侠红.船用柴油机性能数据库开发与故障仿真计算.武汉理工大学硕士学位论文，2010：77-86页.
[129] Enrique H. Ruspini. On the semantics of fuzzy logic. International Journal ofApproximate Reasoning,1991,5(1):45-88P.
[130]杨浩杰.高考志愿填报的数据分析研究.河南大学硕士学位论文，2011：27-29页.
[131]吕泽华.模糊集理论的新拓展及其应用研究.华中科技大学博士学位论文，2007：81-102页.
[132]任建斌.基于自适应遗传算法的椭圆聚类方法研究.中北大学硕士学位论文，2009：3-6页.
[133]郭素娜.电器产品概念设计中的模糊信息处理方法.河北工业大学硕士学位论文，2006：8-15页.
[134] J C Dunn. A Fuzzy Relative of the ISODATA Process and Its Use in DetectingCompact Well-Separated Clusters. Journal of Cybernetics,1973,3(3):32-57P.
[135] Bezdek James C. A Convergence Theorem for the Fuzzy ISODATA ClusteringAlgorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence,1980,2(1):1-8P.
[136]江伟.城市道路应急疏散能力综合评价的研究.北京交通大学硕士学位论文，2009：38-49页.
[137]冯宏亮.数据挖掘中若干关键算法的研究.西安科技大学硕士学位论文，2010：23-30页.
[138] J MacQueen. Some methods for classification and analysis of multivariate observations.Proceedings of the fourth Berkeley symposium on mathematical statistics andprobability, Berkeley, USA,1960. USA: University of California Press,1961:281-297P.
[139] Krishnapuram R, Keller J M. The possibilistic C-means algorithm: insights andrecommendations. IEEE Transactions on Fuzzy Systems,1996,4(3):385-393P.
[140] James C Bezdek, Sankar K Pal. Fuzzy Models for Pattern Recognition. IEEE Press,1992:25-36P.
[141]曲福恒，马驷良，胡雅婷.一种基于核的模糊聚类算法.吉林大学学报（理学版），2008，46（6）：1137-1141页.
[142]孟丽敏，宋余庆，朱峰.基于空间邻域加权的模糊C-均值聚类及其应用研究.计算机应用研究，2010，27（10）：3968-3973页.
[143]严晓明，郑之.基于混合仿生算法的SVM参数优化.广西师范大学学报（自然科学版），2011，29（2）：114-118页.
[144]白庆虹.船用柴油机性能数据库开发与神经网络诊断方法研究.武汉理工大学硕士学位论文，2010：56-66页.
[145] Mika S, Ratsch G, Weston J, et al. Fisher discriminant analysis with kernels.Proceedings of the1999IEEE Signal Processing Society Workshop, Madison, WI,USA,1999. United States: IEEE, Piscataway,1999:41-48P.
[146]贺峥嵘，王刚，王番.基于核的Fisher分类在PolSAR图像的应用.信息工程大学学报，2011，12（4）：473-477页.
[147]石玉清.一种加权融合两类核判别信息算法.西北民族大学学报（自然科学版），2011，32（1）：5-9页.
[148]高爱华，曹剑，秦文罡. Fisher准则挑选特征的快速行人检测算法.西安工业大学学报，2011，31（2）：109-114页.
[149]李国齐，赵广社，孙照莹. Fisher准则K-L变换和SVM在分类中的应用.计算机工程与应用，2006，（19）：147-150页.
[150]谢永林. LDA算法及其在人脸识别中的应用.计算机工程与应用，2010，46（19）：189-192页.
[151]赵旭，阎威武，邵惠鹤.基于核Fisher判别分析方法的非线性统计过程监控与故障诊断.化工学报，2007，58（4）：951-956页.
[152] Xu J, Zhang X, Li Y. Kernel MSE algorithm: A unified framework for KFD, LS-SVMand KRR. International Joint Conference on Neural Networks, Washington, Unitedstates,2001. USA: Institute of Electrical and Electronics Engineers Inc,2001:1486-1491P.
[153] Cawley Gavin C, Talbot Nicola L C. Efficient leave-one-out cross-validation of kernelfisher discriminant classifiers. Pattern Recognition,2003,36(11):2585-2592P.
[154]周欣，吴瑛.基于四阶累积量与核Fisher判别分析的MPSK信号分类方法.系统工程与电子技术，2009，31（12）：2844-2847页
[155] Ryan Rifkin, Aldebaro Klautau. In Defense of One-Vs-All Classification. Journal ofMachine Learning Research,2004,(5):101-141P.
[156] Liefeng Bo, LingWang, Licheng Jiao. Feature Scaling for Kernel Fisher DiscriminantAnalysis Using Leave-One-Out Cross Validation. Neural Computation,2006,18(4):961-978P.
[2]张旭.人工免疫算法及其在船舶柴油机智能故障诊断中的应用研究.大连海事大学博士学位论文，2007：1-10页.
[3]李宏坤.基于信息融合技术船舶柴油机故障诊断方法的研究与应用.大连理工大学博士学位论文，2003：2-5页.
[4]黄加亮，蔡振雄，张均东.船舶柴油机智能故障诊断仿真方法的研究.航海技术，2001，（3）：37-39页.
[5]王珍，马孝江，李作州等.基于局域波法的车用柴油机预知维修研究.车用发动机，2002，（1）：44-46页.
[6]王洪锋.船用智能化柴油机热力参数监测与诊断技术研究.武汉理工大学硕士学位论文，2008：2-5页.
[7] Edge K A, Boston O P, Burrows C R, et al. Approach to automated fault diagnosis ofhydraulic circuits using neural networks. American Society of Mechanical Engineers,1995,2(1):37-43P.
[8]罗存刚.基于神经网络的船舶柴油机远程故障诊断研究.大连海事大学硕士学位论文，2009：40-45页.
[9] Hountalas Dimitrios T. Prediction of marine diesel engine performance under faultconditions. Applied Thermal Engineering,2000,20(18):1753-1783P.
[10] Lunt Stuart, Recent developments in online oil condition monitoring sensors andalignment with astm methods and practices, Journal of ASTM International, v8, n7,July2011,8(7):86-106P.
[11]张维竞，张鹏，罗蛟龙.船舶动力装置故障诊断专家系统的开发.船舶工程，2000，（5）：38-40页.
[12] Eberle M K. DIAGNOSTIC SYSTEM FOR DIESEL ENGINES. Sulzer TechnicalReview,1976,58(4):163-167P.
[13]黄加亮，黄少竹，李玩幽.船用柴油机智能诊断技术的现状和发展动态.天津航海，2000，（1）：13-19页.
[14] Koga Mikio. Super advanced ship operation support system. Proceedings of theInternational Offshore and Polar Engineering Conference, Osaka, Japan,1994. UnitedStates: Int Soc of Offshore and Polar Engineerns,1994:636-643P.
[15] Guettinger Heinz, Koenig, Ferdinand, Meili Regula. Artificial intelligence formachines. Sulzer Technical Review,1992,74(4):18-22P.
[16] HIRPA L GELGELE, KESHENG WANG. An expert system for engine fault diagnosis:development and application. Journal of Intelligent Manufacturing,1998,9(6):539-545P.
[17] Ilkka Priha. FAKS—an on-line expert system based on hyperobjects. Expert Systemswith Applications,1991,3(2):207–217P.
[18] Grimmelius H T, Meiler P P, Maas H L M M, et al. Three state-of-the-art methods forcondition monitoring. IEEE Transactions on Industrial Electronics,1999,46(2):407-416P.
[19] Armstrong Robert A. Fault Assessment of a Diesel Engine Using VibrationMeasurements and Advanced Signal Processing. Master’s thesis of NAVALPOSTGRADUATE SCHOOL MONTEREY CA,1997:22-34P.
[20] Angeli, Chr. Integrating symbolic and numerical features for fault prediction anddiagnosis by an expert system. Expert Systems,1999,16(4):233-239P.
[21] Sun Ruixiang, Tsung Fugee, Qu Liangsheng. Combining bootstrap and geneticprogramming for feature discovery in diesel engine diagnosis. International Journal ofIndustrial Engineering: Theory Applications and Practice,2004,11(3):273-281P.
[22]郭江华，侯馨光，陈国钧等.船舶柴油机故障诊断技术研究.中国航海，2005，65（4）：75-78页.
[23]刘俊磊.柴油机智能故障诊断系统的综合研究与工程实现.东北大学硕士学位论文，2007：1-20页.
[24]刘世元，杜润生，杨叔子.小波包改进算法及其在柴油机振动诊断中的应用.内燃机学报，2000，18（1）：11-16页.
[25]伍学奎，陈进.基于小波包变换的内燃机气阀漏气诊断方法.振动工程学报，2000，13（2）：210-215页.
[26]李志敏，王义，宋希庚等.内燃机主轴承磨损故障的振动监测方法研究.内燃机学报，2000，18（2）：203-206页.
[27]吴恒，高强，温宇钦等. MAN B&W MC系列船用柴油机故障诊断专家系统.航海技术，1999，（1）：45-48页.
[28]朱建元.基于BP神经网络的船用柴油机振动状态监测.机电设备，2008，（3）：33-36页.
[29]牛洪瑜.基于神经网络的船舶柴油发电机组的故障诊断.兰州理工大学硕士学位论文，2007：4-8页.
[30]李海量，汤天浩.基于人工神经网络的船用主柴油机故障诊断.中国航海，1997，（2）：67-72页.
[31]黄加亮，蔡振雄. RBF网络在柴油机故障诊断领域中的应用与实现.集美大学学报，2002，7（4）：338-342页.
[32] Sch lkoph Bernhard, Sung Kah-Kay, Burges Chris J C, et al. Comparing supportvector machines with Gaussian kernels to radial basis function classifiers. IEEETransactions on Signal Processing,1997,45(11):2758-2765P.
[33] Tipping Michael E. Sparse Bayesian Learning and the Relevance Vector Machine.Journal of Machine Learning Research,2001,1(3):211-244P.
[34] N Aronszajn. Theory of reproducing kernels. Transactions of the AmericanMathematical Society,1950,68(3):337-404P.
[35] N Aronszajn, K T Smith. Invariant Subspaces of Completely Continuous Operators.Annals of Mathematics,1954,60(2):345-350P.
[36] A Aizerman, E M Braverman, L I Rozoner. Theoretical foundations of the potentialfunction method in pattern recognition learning. Automation and Remote Control,1964,25:821-837P.
[37] Boser B E, Guyon I M, Vapnik. A training algorithm for optimal margin classifiers.Proceedings of the5th Annual ACM Workshop on Computational Learning Theory,Pittsburgh, USA,1992. New York: ACM Press,1992:144-152P.
[38] Sch lkoph B, Smola A, Müller K R. Nonlinear component analysis as a kerneleigenvalue problem. Neural Computation,1998,10(5):1299-1399P.
[39] Mika S, Ratsch G, Weston J, et al. Fisher discriminant analysis with kernels. Fisherdiscriminant analysis with kernels. Proceedings of the1999IEEE Signal ProcessingSociety Workshop, Madison, USA,1999. Piscataway: IEEE,1999:41-48P.
[40] Baudat G,Anouar F. Generalized discriminant analysis using a kernel approach. NeuralComput,2000,12:2385-2404P.
[41] Peiling Lai, Colin Fyfe. Kernel and Nonlinear Canonical Correlation Analysis.International Journal of Neural Systems,2000,10(5):365-377P.
[42] Francis R Bach, Michael I Jordan. Kernel independent component analysis. Journal ofMachine Learning Research,2002,3(1):1-48P.
[43] Xie Xudong, Lam Kin-Man. Gabor-based kernel PCA with doubly nonlinear mappingfor face recognition with a single face image. IEEE Transactions on Image Processing,2006,15(9):2481-2492P.
[44] Fonseca Everthon Silva, Guido Rodrigo Capobianco, Scalassara Paulo Rogério, et al.Wavelet time-frequency analysis and least squares support vector machines for theidentification of voice disorders. Computers in Biology and Medicine,2007,37(4):571-578P.
[45] Xiuyan Peng, Yanyou Chai, Liufeng Xu, et al. Research on Fault Diagnosis of MarineDiesel Engine Based on Grey Relational Analysis and Kernel Fuzzy C-meansClustering. The Fifth International Conference on Intelligent Computation Technologyand Automation, Zhangjiajie, China,2012. United States: IEEE Computer Society,2012:283-286P.
[46]罗公亮.核函数方法（上）.冶金自动化，2002，（3）：1-4页.
[47]罗公亮.核函数方法（下）.冶金自动化，2002，（4）：1-4页.
[48] Zhang Yankun, Gu Xuefeng, Liu Chongqing. Face Recognition Using KernelDiscriminant Analysis. High Technology Letters,2002,8(4):43-46P.
[49]肖健华，吴今培.基于核的特征提取技术及应用研究.计算机工程，2002，28（10）：36-38页.
[50]邵惠鹤.支持向量机理论及其应用.自动化博览，2003，（S1）：90-95页.
[51]熊志化，黄国宏，邵惠鹤.基于高斯过程和支持向量机的软测量建模比较及应用研究.信息与控制，2004，33（6）：754-757页.
[52]阎威武，常俊林，邵惠鹤.一种贝叶斯证据框架下支持向量机建模方法的研究.控制与决策，2004，19（5）：523-528页.
[53]黄国宏，邵惠鹤.核主元分析及其在人脸识别中的应用.计算机工程，2004，30（13）：13-14页.
[54]陈才扣，杨静宇，杨健.一种融合PCA和KFDA的人脸识别方法.控制与决策，2004，19（10）：1147-1154页.
[55]刘海峰，姚泽清，刘守生等.文本分类中基于核的非线性判别.应用科学学报，2008，26（6）：627-631页.
[56]江南，王士同，贺杨成.核参数优化选取的混合C均值核模糊聚类算法.计算机工程与设计，2011，32（9）：3148-3151页.
[57]林材宽，乔建忠，王国仁等.基于核方法的非线性时间序列预测建模.计算机工程，2007，33（17）：23-25页.
[58]刘磊.优化算法在船舶柴油机智能故障诊断中的应用研究.哈尔滨工程大学硕士学位论文，2008：19-25页.
[59]王珍.基于局域波分析的柴油机故障诊断方法的研究及应用.大连理工大学博士学位论文，2002：3-10页.
[60]徐向荣.船舶柴油机故障诊断技术的研究及展望.南通航运职业技术学院学报，2007，6（3）：53-56页.
[61] Yanyou Chai, Xiuyan Peng, Xinjiang Man. Research on Fault Diagnosis of MarineDiesel Engine Based on KFDA. Advanced Materials Research,2012,442(1):262-266P.
[62]李斌.船舶柴油机.大连海事大学出版社，2008：33-37页.
[63]常勇，胡以怀.柴油机振动监测及故障诊断系统.噪声与振动控制，2008，（1）：93-96页.
[64] Li Yujun, Tse Peter W, Yang Xin, et al. EMD-based fault diagnosis for abnormalclearance between contacting components in a diesel engine. Mechanical Systems andSignal Processing,2010,24(1):193-210P.
[65] Amstutz Alois, Del Re Luigi R. EGO sensor based robust output control of EGR indiesel engines. IEEE Transactions on Control Systems Technology,1995,3(1):39-48P.
[66]王南兰.基于数据挖掘的柴油机磨损故障诊断Petri网络模型.机械与电子，2008，（1）：34-37页.
[67]陈平.浅析柴油机拉缸的成因及预防措施.南通航运职业技术学院学报，2009，8（2）：59-62页.
[68]周朝霞，张传爱.柴油机涡轮增压器的正确使用与维护.工程机械与维修，2003，（1）：116页.
[69] Farinha Torres, Fonseca Inácio, Sim es António, et al. New ways for terology throughpredictive maintenance in an environmental perspective. WSEAS Transactions onCircuits and Systems,2008,7(7):630-647P.
[70]陈亚，汪丛笑，周旭等.防爆柴油机车状态监测平台可靠性研究.工矿自动化，2011，（4）：51-53页.
[71]郭建平，马茂，刘增宝.一般柴油机故障原因的分析与排查.铁道机车车辆，2011，31（S1）：418-421页.
[72] Kouremenos D A, Hountalas D T. Diagnosis and condition monitoring ofmedium-speed marine diesel engines. Tribo Test,1997,4(1):63-91P.
[73]占惠文.基于模糊神经网络的船舶柴油机故障诊断系统研究.武汉理工大学硕士学位论文，2009：2-30页.
[74]黄少竹.现代船舶柴油机故障分析.大连海事大学出版社，2005：109-111页.
[75] Li Yujun, Tse Peter W, Yang Xin et al. EMD-based fault diagnosis for abnormalclearance between contacting components in a diesel engine. Mechanical Systems andSignal Processing,2010,24(1):193-210P.
[76] Li Hongkun, Zhou Peilin; Xiaojiang Ma. Marine diesel engine fault diagnosis by usingan improved Hubert spectrum. Journal of Ship Research,2006,50(4):378-387P.
[77] Martin K F. Review by discussion of condition monitoring and fault diagnosis inmachine tools. International Journal of Machine Tools and Manufacture,1994,34(4):527-551P.
[78] Lamaris V T, Hountalas D T. A general purpose diagnostic technique for marine dieselengines-Application on the main propulsion and auxiliary diesel units of a marinevessel. Energy Conversion and Management,2010,51(4):740-753P.
[79] Martin Brett, Meckl Peter. Input selection for modeling and diagnostics withapplication to diesel engines. Journal of Dynamic Systems, Measurement and Control,2007,129(1):114-120P.
[80] Thomson Bill. Machinery monitoring adds to ship intelligence. Motor Ship,1994,75(882):40-43P.
[81] Grimmelius Hugo T. Three state-of-the-art methods for condition monitoring. IEEETransactions on Industrial Electronics,1999,46(2):407-416P.
[82] Tan Yanghong, He Yigang, Cui Chun, et al. A novel method for analog fault diagnosisbased on neural networks and genetic algorithms. IEEE Transactions onInstrumentation and Measurement,2008,57(11):2631-2639P.
[83] Qinghua Wang, Youyun Zhang, Lei Cai, et al. Fault diagnosis for diesel valve trainsbased on non-negative matrix factorization and neural network ensemble. MechanicalSystems and Signal Processing,2009,23(5):1683-1695P.
[84] Morgan Ian, Liu Honghai. Predicting future states with n-dimensional markov chainsfor fault diagnosis. IEEE Transactions on Industrial Electronics,2009,56(5):1774-1781P.
[85] Nyberg Mattias, Stutte Thomas. Model based diagnosis of the air path of an automotivediesel engine. Control Engineering Practice,2004,12(5):513-525P.
[86] Wu X, Chen J, Wang W, et al. Multi-index fusion-based fault diagnosis theories andmethods. Mechanical Systems and Signal Processing,2001,15(5):995-1006P.
[87] Wang Zhihua. Fault diagnosis of diesel engine piston-ring using time-frequencyanalysis method. Journal of Wuhan University of Technology (Transportation Scienceand Engineering),2004,28(6):953-956P.
[88] Desbazeille M, Randall R B, Guillet F, et al. Model-based diagnosis of large dieselengines based on angular speed variations of the crankshaft. Mechanical Systems andSignal Processing,2010,24(5):1529-1541P.
[89] Zhou P, Li H, Clelland D. Pattern recognition on diesel engine working conditions bywavelet Kullback-Leibler distance method. Journal of Mechanical Engineering Science,2005,219(9):879-887P.
[90]廖明，石博强，张文明等.分形在柴油机燃油系故障诊断中的应用.北京科技大学学报，1998，20（5）：417-420页.
[91]吕琛，宋希庚.基于Kohonen网络的柴油机噪声故障分析系统.振动、测试与诊断，1999，19（3）：208-213页.
[92] Macián Vicente, Tormos Bernardo, Sala Antonio, et al. Fuzzy logic-based expertsystem for diesel engine oil analysis diagnosis. Insight: Non-Destructive Testing andCondition Monitoring,2006,48(8):462-469.
[93] Zhang Bin, Yan Jun, Liu Hongliang. Research on oil ferrography analysis faultdiagnosis of diesel engine based on BP neural network. Proceedings-20082ndInternational Symposium on Intelligent Information Technology Application, Shanghai,China,2008. United States: Inst. of Elec. and Elec. Eng. Computer Society,2008:519-524P.
[94]孙云岭，郭文勇，张永祥.基于瞬时转速的柴油机故障诊断仪的研制.内燃机，2010，（2）：16-17页.
[95] Antory David. Application of a data-driven monitoring technique to diagnose air leaksin an automotive diesel engine: A case study. Mechanical Systems and SignalProcessing,2007,21(2):795-808P.
[96] Charles P, Sinha Jyoti K, Gu F, et al. Detecting the crankshaft torsional vibration ofdiesel engines for combustion related diagnosis. Journal of Sound and Vibration,2009,321(3-5):1171-1185P.
[97] Tseng Chyuan-Yow, Lin Chiu-Feng. Characterisation of solenoid valve failure forelectronic diesel fuel injection system of commercial trucks. International Journal ofHeavy Vehicle Systems,2006,13(3):180-193P.
[98]张世康.钻井柴油机发生故障的原因与预防.石油机械，1992，20（9）：31-36页.
[99] Lee Jong-Min, Yoo ChangKyoo, Choi SangWook, et al, Nonlinear process monitoringusing kernel principal component analysis. Chemical Engineering Science,2004,59(1):223-234P.
[100]张曦，陈锐民，陈世和等.基于核主元分析和模式匹配的非线性性能监控和故障诊断.华北电力大学学报，2010，37（6）：69-73页.
[101] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619P.
[102]邓乃扬，田英杰.数据挖掘中的新方法—支持向量机.科学出版社，2004：92-97页.
[103]王华忠，俞金寿.核函数方法及其在过程控制中的应用.石油化工自动化，2005，25（1）：25-30页.
[104]张曦.基于统计理论的工业过程综合性能监控、诊断及质量预测方法研究.上海交通大学博士学位论文，2008：17-30页.
[105]胡金海，谢寿生，侯胜利等.核函数主元分析及其在故障特征提取中的应用.振动、测试与诊断，2007，27（1）：48-52页.
[106]关山.基于声发射信号多特征分析与融合的刀具磨损分类与预测技术，吉林大学博士学位论文，2011：79-88页.
[107] Yanyou Chai, Xiuyan Peng, Liufeng Xu, et al. Research on Fault Diagnosis of MarineDiesel Engine Based on Integrated Similarity. Communications in Computer andInformation Science,2011,227(4):678-685P.
[108]李玉峰.基于神经网络的柴油机燃油系统故障诊断的研究和实现.山东大学硕士学位论文，2007：29-35页.
[109] Corinna Cortes, Vladimir Vapnik. Support-Vector Networks. Machine Learning,1995,20(3):273-297P.
[110]马铁军，欧阳徕.基于混合核函数和PLS的胎面尺寸预测模型.橡胶工业，2010，57（8）：466-470页.
[111]彭秀艳，柴艳有，满新江.基于PCA-KFCM的船舶柴油机故障诊断.控制工程，2012，19（1）：152-156页.
[112]谭琨.基于支持向量机的高光谱遥感影像分类研究.中国矿业大学博士学位论文，2010：10-20页.
[113]邓乃扬，田英杰.支持向量机—理论、算法与拓展.科学出版社，2009：92-111页.
[114]明阳，陈进.基于谱相关密度切片分析和SVM的滚动轴承故障诊断.振动与冲击，2010，29（1）：197-199页.
[115]郎宇宁，蔺娟如.基于支持向量机的多分类方法研究.中国西部科技，2010，9（17）：28-29页.
[116] Hsu Chih-Wei, Lin Chih-Jen. A comparison of methods for multiclass support vectormachines. IEEE Transactions on Neural Networks,2002,13(2):415-425P.
[117] Sebald Daniel J, Bucklew James A. Support vector machine techniques for nonlinearequalization. IEEE Transactions on Signal Processing,2000,48(11):3217-3226P.
[118]王艳，陈欢欢，沈毅.有向无环图的多类支持向量机分类算法.电机与控制学报，2011，15（4）：85-89页.
[119]郎宇宁.基于支持向量机的多分类方法研究及应用.西南交通大学硕士学位论文，2010：16-25页.
[120] Van Gestel Tony, Suykens Johan A K., Baesens Bart, et al. Benchmarking LeastSquares Support Vector Machine Classifiers. Machine Learning,2004,54(1):5-32P.
[121]彭红星，陈祥光，徐巍. PCA特征抽取与SVM多类分类在传感器故障诊断中的应用.数据采集与处理，2010，25（1）：111-116页.
[122]杨艺芳. SVM和FCM相结合的故障诊断方法的研究.西安科技大学硕士学位论文，2008：38-44页.
[123] Zhong Ping, Fukushima Masao. Regularized nonsmooth Newton method formulti-class support vector machines. Optimization Methods and Software,2007,22(1):225-236P.
[124]黄移军.基于局部线性嵌入的高维数据降维研究.中南大学硕士学位论文，2009：25-26页.
[125]朱志宇，张冰，刘维亭.模糊支持向量机在船舶柴油机故障诊断中的应用.中国造船，2006，47（3）：64-69页.
[126]陈景锋，周程生，王诗武.柴油机喷油器启阀压力降低对工况的影响及其对策.集美航海学院学报，1998，16（2）：5-7页.
[127]林金田，陈景锋.喷油正时对船舶柴油机排气中有害成分的影响.铁道机车车辆，2003，23（S1）：108-110页.
[128]石侠红.船用柴油机性能数据库开发与故障仿真计算.武汉理工大学硕士学位论文，2010：77-86页.
[129] Enrique H. Ruspini. On the semantics of fuzzy logic. International Journal ofApproximate Reasoning,1991,5(1):45-88P.
[130]杨浩杰.高考志愿填报的数据分析研究.河南大学硕士学位论文，2011：27-29页.
[131]吕泽华.模糊集理论的新拓展及其应用研究.华中科技大学博士学位论文，2007：81-102页.
[132]任建斌.基于自适应遗传算法的椭圆聚类方法研究.中北大学硕士学位论文，2009：3-6页.
[133]郭素娜.电器产品概念设计中的模糊信息处理方法.河北工业大学硕士学位论文，2006：8-15页.
[134] J C Dunn. A Fuzzy Relative of the ISODATA Process and Its Use in DetectingCompact Well-Separated Clusters. Journal of Cybernetics,1973,3(3):32-57P.
[135] Bezdek James C. A Convergence Theorem for the Fuzzy ISODATA ClusteringAlgorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence,1980,2(1):1-8P.
[136]江伟.城市道路应急疏散能力综合评价的研究.北京交通大学硕士学位论文，2009：38-49页.
[137]冯宏亮.数据挖掘中若干关键算法的研究.西安科技大学硕士学位论文，2010：23-30页.
[138] J MacQueen. Some methods for classification and analysis of multivariate observations.Proceedings of the fourth Berkeley symposium on mathematical statistics andprobability, Berkeley, USA,1960. USA: University of California Press,1961:281-297P.
[139] Krishnapuram R, Keller J M. The possibilistic C-means algorithm: insights andrecommendations. IEEE Transactions on Fuzzy Systems,1996,4(3):385-393P.
[140] James C Bezdek, Sankar K Pal. Fuzzy Models for Pattern Recognition. IEEE Press,1992:25-36P.
[141]曲福恒，马驷良，胡雅婷.一种基于核的模糊聚类算法.吉林大学学报（理学版），2008，46（6）：1137-1141页.
[142]孟丽敏，宋余庆，朱峰.基于空间邻域加权的模糊C-均值聚类及其应用研究.计算机应用研究，2010，27（10）：3968-3973页.
[143]严晓明，郑之.基于混合仿生算法的SVM参数优化.广西师范大学学报（自然科学版），2011，29（2）：114-118页.
[144]白庆虹.船用柴油机性能数据库开发与神经网络诊断方法研究.武汉理工大学硕士学位论文，2010：56-66页.
[145] Mika S, Ratsch G, Weston J, et al. Fisher discriminant analysis with kernels.Proceedings of the1999IEEE Signal Processing Society Workshop, Madison, WI,USA,1999. United States: IEEE, Piscataway,1999:41-48P.
[146]贺峥嵘，王刚，王番.基于核的Fisher分类在PolSAR图像的应用.信息工程大学学报，2011，12（4）：473-477页.
[147]石玉清.一种加权融合两类核判别信息算法.西北民族大学学报（自然科学版），2011，32（1）：5-9页.
[148]高爱华，曹剑，秦文罡. Fisher准则挑选特征的快速行人检测算法.西安工业大学学报，2011，31（2）：109-114页.
[149]李国齐，赵广社，孙照莹. Fisher准则K-L变换和SVM在分类中的应用.计算机工程与应用，2006，（19）：147-150页.
[150]谢永林. LDA算法及其在人脸识别中的应用.计算机工程与应用，2010，46（19）：189-192页.
[151]赵旭，阎威武，邵惠鹤.基于核Fisher判别分析方法的非线性统计过程监控与故障诊断.化工学报，2007，58（4）：951-956页.
[152] Xu J, Zhang X, Li Y. Kernel MSE algorithm: A unified framework for KFD, LS-SVMand KRR. International Joint Conference on Neural Networks, Washington, Unitedstates,2001. USA: Institute of Electrical and Electronics Engineers Inc,2001:1486-1491P.
[153] Cawley Gavin C, Talbot Nicola L C. Efficient leave-one-out cross-validation of kernelfisher discriminant classifiers. Pattern Recognition,2003,36(11):2585-2592P.
[154]周欣，吴瑛.基于四阶累积量与核Fisher判别分析的MPSK信号分类方法.系统工程与电子技术，2009，31（12）：2844-2847页
[155] Ryan Rifkin, Aldebaro Klautau. In Defense of One-Vs-All Classification. Journal ofMachine Learning Research,2004,(5):101-141P.
[156] Liefeng Bo, LingWang, Licheng Jiao. Feature Scaling for Kernel Fisher DiscriminantAnalysis Using Leave-One-Out Cross Validation. Neural Computation,2006,18(4):961-978P.