基于改进支持向量机和特征信息融合的水电机组故障诊断
|
摘要
当前,我国经济高速发展,电力需求十分旺盛,系统供电的可靠性要求越来越高。近三十年来,我国大力开发水电能源,水电装机容量在电力系统中所占的比重逐步提高。同时,随着制造技术的发展,水电机组单机容量越来越大,在系统中的调频、调峰和事故备用功能亦越来越重要。水电机组运行的安全性和可靠性已经成为水电能源学科学术界和工程界研究的热点之一。
水电机组是强耦合、非线性的复杂系统,其故障特征分布也具有耦合性和非线性,如果采用单一的、线性的方法,很难对其运行状态做出准确的评价。信息融合能够综合水电机组异源异构信息,全面了解机组状态。带有核函数的支持向量机能够实现输入空间向特征空间的非线性映射,适宜解决非线性问题。这些方法的采用对实施水电机组故障诊断,进而实现水电机组状态检修具有重要的现实意义。
现有的故障诊断方法通常在平稳工况下进行,由于开机工况及其过程复杂,信号不容易处理,因此,较少考虑机组启停过程的过渡特性进行故障诊断。实际上,在开机过程中能够获取更多机组故障特征信息,有利于提高故障诊断准确性。同时,结合工程中水电机组振动试验(转速试验、励磁试验和负荷试验)的要求,本文提出了基于多特征信息融合的开机自诊断故障诊断方法。水电机组开机过程包括加速、加励磁和加负荷三个阶段,利用机组开机过程,获取机组频率、时间和空间特征信息,进而对其进行信息融合,这将提高机组故障诊断的准确度。
轴心轨迹是水电机组状态信息在数据层时域信息空间的融合结果,其图形特征从另一个角度反映了机组的运行状态。曲线不变矩满足轴心轨迹不封闭的特点,能够表征轴心轨迹的图形特征。但是,离散的曲线不变矩不具有缩放不变性,因此本文在讨论轴心轨迹曲线不变矩不变性的基础上,提出了改进曲线不变矩。实验结果表明,改进后的曲线不变矩具有平移、旋转和缩放不变性。
为了有效实现信息输入空间向信息特征空间的非线性映射,本文针对支持向量机中的RBF核函数,研究了其几何特性,采用以黎曼几何为基础的数据依赖性改进方法,以此剔除支持向量机的冗余支持向量,从而显著提高了支持向量机故障诊断的速度和准确度。此外,本文将改进支持向量机应用于水电机组故障诊断。通过理论分析和实验验证,阐明了支持向量机具有较强的泛化推广能力和小样本学习能力,适应于水电机组故障诊断先验知识不足的现实情况。故障实例分析表明,改进支持向量机能够提高机组故障诊断的速度和准确度。
针对多元数据融合过程中的“组合爆炸”问题,并在分析证据联合计算复杂度的基础上,提出采用交换律和结合律进行D-S证据信息融合的分解,以降低计算的复杂度。利用相关故障数据进行诊断测试,证实了D-S证据理论交换律和结合律的成立。此外,将信息融合技术应用于水电机组故障诊断,得到了更准确的诊断结论。与单一特征诊断相比,通过水电机组故障信息的频率阶次特征、时间特征和空间特征的融合,故障诊断结论的不确定性更低,而可信度更高。
最后,本文设计了一套水电机组稳定性状态监测及故障诊断原型系统。在系统总体设计的框架下,完成了各功能模块的硬件设计和软件设计,建立了故障诊断专家子系统和SVM辅助决策子系统,以满足水电机组稳定性状态监测和故障诊断的实际需要。
With high-speeded growth of Chinese economy, demand for electricity increased and requirement for reliable electriciy became stronger. In the past twenty years, water resource and hydropower was exploited widely and capacity of hydro-electricity played a more and more important role in capacity of power system. Development of manufacture technology promoted hugemazation of Hydropower Generating Unit (HGU). Security and reliability of HGU became one of the most attentional objects in research and application of hydropower science.
HGU is a complex nonlinear system with strong coupling between partions. It is difficult to comment condition of HGU with single and linear method. By information fusion, all kinds of HGU’s information with different distruction and from different resource are integrated. And Support Vector Machine (SVM) with kernel results HGU’s nonlinear problem with mapping input data into feature space. It is valuable for HGU’s fault diagnosis and condition-based mentanence to apply these methods.
Fault diagnosis methods are generally in the condition of stabilization. Vibration signal in starting process is so complex that it is not used to fault diagnosis in starting process. In fact, more fault information could be got in starting process. The idea of fault ditection and analysis in starting process is expounded and the method of fault dignosis by multi-feature information fusion is proposed in this thesis. HGU starting process includes rising-speed phase, rising-excitation phase and rising-load phase, which meets condition of HGU vibration experiments (altering-speed experiment, altering-excitation experiment and altering-load experiment). Frenquency feature, temporal feature and spatial feature of vibration could be gained in HGU starting process. It could raise veracity of fault diagnosis with multi-feature information fusion.
Shaft orbit is the result of HGU running information fusion in time domain of data level. It is an open line. Linear moment invarint is a kind of graphics feature of shaft orbit and could reflect condition of running HGU. However, discrete linear moment invariant is change in zoom. Improved linear moment invariant is presented in this thesis. Experiment result shows improved linear moments are invariant in movement, rotation and zoom.
In order to map sample from input space to feature sapce effectively, geometry of RBF kernel used in SVM is analyzed and data dependent method based on Riemannian geometry is used in this thesis. Results of analysis and experiments show delecting redandent support vectors is one reason for raising fault diagnosis speed and veracity of SVM. In addition, results of analysis and experiments demonstrate SVM has strong generalization capability and learning capability from little sample set, which meets condition of HGU fault diagnosis with a little prior knownledge. A fault diagnosis example exhibit improved SVM could raise speed and veracity of HGU fault diagnosis.
For the problem of combination explosion in inforemation fusion, exchange theorem and conjunction theorem in combination process amonge evidences are researched in this thesis. Results of analysis on calculate complex of combine among evidences show information fusion by D-S theory could be reduced with exchange theorem and conjunction theorem. Results of experiments demonstrate these theorems. In addition, information fusion is applied in HGU fault diagnosis. By fusing frequency featrure information, temporal feature information and spatial feature information, HGU is diagnosed with lower uncertainty and higher reliability.
At last, a HGU condition monitoring and fault diagnosis system is designed. Hardware and software design of each module is finished based on general design of the system. At the same time, Fault Diagnosis Expert Subsystem and SVM Assistant Decision Subsystem are built. The system could satisfy many requirements of HGU condition monitoring and fault diagnosis.
水电机组是强耦合、非线性的复杂系统,其故障特征分布也具有耦合性和非线性,如果采用单一的、线性的方法,很难对其运行状态做出准确的评价。信息融合能够综合水电机组异源异构信息,全面了解机组状态。带有核函数的支持向量机能够实现输入空间向特征空间的非线性映射,适宜解决非线性问题。这些方法的采用对实施水电机组故障诊断,进而实现水电机组状态检修具有重要的现实意义。
现有的故障诊断方法通常在平稳工况下进行,由于开机工况及其过程复杂,信号不容易处理,因此,较少考虑机组启停过程的过渡特性进行故障诊断。实际上,在开机过程中能够获取更多机组故障特征信息,有利于提高故障诊断准确性。同时,结合工程中水电机组振动试验(转速试验、励磁试验和负荷试验)的要求,本文提出了基于多特征信息融合的开机自诊断故障诊断方法。水电机组开机过程包括加速、加励磁和加负荷三个阶段,利用机组开机过程,获取机组频率、时间和空间特征信息,进而对其进行信息融合,这将提高机组故障诊断的准确度。
轴心轨迹是水电机组状态信息在数据层时域信息空间的融合结果,其图形特征从另一个角度反映了机组的运行状态。曲线不变矩满足轴心轨迹不封闭的特点,能够表征轴心轨迹的图形特征。但是,离散的曲线不变矩不具有缩放不变性,因此本文在讨论轴心轨迹曲线不变矩不变性的基础上,提出了改进曲线不变矩。实验结果表明,改进后的曲线不变矩具有平移、旋转和缩放不变性。
为了有效实现信息输入空间向信息特征空间的非线性映射,本文针对支持向量机中的RBF核函数,研究了其几何特性,采用以黎曼几何为基础的数据依赖性改进方法,以此剔除支持向量机的冗余支持向量,从而显著提高了支持向量机故障诊断的速度和准确度。此外,本文将改进支持向量机应用于水电机组故障诊断。通过理论分析和实验验证,阐明了支持向量机具有较强的泛化推广能力和小样本学习能力,适应于水电机组故障诊断先验知识不足的现实情况。故障实例分析表明,改进支持向量机能够提高机组故障诊断的速度和准确度。
针对多元数据融合过程中的“组合爆炸”问题,并在分析证据联合计算复杂度的基础上,提出采用交换律和结合律进行D-S证据信息融合的分解,以降低计算的复杂度。利用相关故障数据进行诊断测试,证实了D-S证据理论交换律和结合律的成立。此外,将信息融合技术应用于水电机组故障诊断,得到了更准确的诊断结论。与单一特征诊断相比,通过水电机组故障信息的频率阶次特征、时间特征和空间特征的融合,故障诊断结论的不确定性更低,而可信度更高。
最后,本文设计了一套水电机组稳定性状态监测及故障诊断原型系统。在系统总体设计的框架下,完成了各功能模块的硬件设计和软件设计,建立了故障诊断专家子系统和SVM辅助决策子系统,以满足水电机组稳定性状态监测和故障诊断的实际需要。
With high-speeded growth of Chinese economy, demand for electricity increased and requirement for reliable electriciy became stronger. In the past twenty years, water resource and hydropower was exploited widely and capacity of hydro-electricity played a more and more important role in capacity of power system. Development of manufacture technology promoted hugemazation of Hydropower Generating Unit (HGU). Security and reliability of HGU became one of the most attentional objects in research and application of hydropower science.
HGU is a complex nonlinear system with strong coupling between partions. It is difficult to comment condition of HGU with single and linear method. By information fusion, all kinds of HGU’s information with different distruction and from different resource are integrated. And Support Vector Machine (SVM) with kernel results HGU’s nonlinear problem with mapping input data into feature space. It is valuable for HGU’s fault diagnosis and condition-based mentanence to apply these methods.
Fault diagnosis methods are generally in the condition of stabilization. Vibration signal in starting process is so complex that it is not used to fault diagnosis in starting process. In fact, more fault information could be got in starting process. The idea of fault ditection and analysis in starting process is expounded and the method of fault dignosis by multi-feature information fusion is proposed in this thesis. HGU starting process includes rising-speed phase, rising-excitation phase and rising-load phase, which meets condition of HGU vibration experiments (altering-speed experiment, altering-excitation experiment and altering-load experiment). Frenquency feature, temporal feature and spatial feature of vibration could be gained in HGU starting process. It could raise veracity of fault diagnosis with multi-feature information fusion.
Shaft orbit is the result of HGU running information fusion in time domain of data level. It is an open line. Linear moment invarint is a kind of graphics feature of shaft orbit and could reflect condition of running HGU. However, discrete linear moment invariant is change in zoom. Improved linear moment invariant is presented in this thesis. Experiment result shows improved linear moments are invariant in movement, rotation and zoom.
In order to map sample from input space to feature sapce effectively, geometry of RBF kernel used in SVM is analyzed and data dependent method based on Riemannian geometry is used in this thesis. Results of analysis and experiments show delecting redandent support vectors is one reason for raising fault diagnosis speed and veracity of SVM. In addition, results of analysis and experiments demonstrate SVM has strong generalization capability and learning capability from little sample set, which meets condition of HGU fault diagnosis with a little prior knownledge. A fault diagnosis example exhibit improved SVM could raise speed and veracity of HGU fault diagnosis.
For the problem of combination explosion in inforemation fusion, exchange theorem and conjunction theorem in combination process amonge evidences are researched in this thesis. Results of analysis on calculate complex of combine among evidences show information fusion by D-S theory could be reduced with exchange theorem and conjunction theorem. Results of experiments demonstrate these theorems. In addition, information fusion is applied in HGU fault diagnosis. By fusing frequency featrure information, temporal feature information and spatial feature information, HGU is diagnosed with lower uncertainty and higher reliability.
At last, a HGU condition monitoring and fault diagnosis system is designed. Hardware and software design of each module is finished based on general design of the system. At the same time, Fault Diagnosis Expert Subsystem and SVM Assistant Decision Subsystem are built. The system could satisfy many requirements of HGU condition monitoring and fault diagnosis.
引文
[1] A.巴特尔.全球水电开发概况.水利水电快报,2003,24(23):13～17
[2]周双超.中国水能资源富甲天下解读——全国水力资源复查工作综述.中国三峡建设,2005,(6):68～73
[3]黄宝南.三峡电站及我国今后水电建设方略综述.能源研究与应用,2003,(3):7～8
[4]中国电力行业五年发展成就辉煌(2002年～2007年).中国电力报,2007年10月16日
[5] Vladimir N. Vapnik. An Overview of Statistical Learning Theory. IEEE trans. Neural Networks, 1999, vol. 10(5): 988～999
[6] Klaus-Robert Müller, Sebastian Mika, Gunnar R?tsch. An Introduction to Kernel-Based Learning Algorithms. IEEE trans. Neural Networks, 2001, vol. 12(2): 181～201
[7]翟永杰,韩璞,王东风,等.基于损失函数的SVM算法及其在轻微故障诊断中的应用.中国电机工程学报,2003,23(9):198～203
[8]马骞,杨以涵,刘文颖,等.多输入特征融合的组合支持向量机电力系统暂态稳定评估.中国电机工程学报,2005,25(6):17～23
[9]鹿卫国,戴亚平,高峰.一种基于概率分布估计的水电机组故障预警方法.中国电机工程学报,2005,25(4):94～98
[10]国家电力公司.水电厂开展设备状态检修工作的指导意见,2002
[11]涂长庚.水力发电设备预知维修.华中电力, 2000, 13(3):37～39.
[12]梁武科,赵道利.水电机组监测与诊断技术的现状及发展.水利水电技术,2003,34(4):41～43
[13]瞿曌，赖旭，盛旺.水电机组状态检修的研究.人民长江,2007,38(6):54～56
[14]瞿曌，赖旭，盛旺.水电机组状态检修现状分析.中国电力,2007,40(10):20～23
[15]杨晓萍,解建宝,张靠社,等.水轮发电机组的事故停机分析与故障诊断专家系统的研究.西安理工大学学报,1998,14(2):91～95.
[16]陈铁华,陈启卷.模糊聚类分析在水电机组振动故障诊断中的应用.中国电机工程学报,2002,22(2):43～47.
[17]梁业国,王乘.人工神经网络在水电机组故障诊断中的应用研究.四川水力发电,2003,22(1):57～59.
[18]陈卫钢,周建中,常黎.基于专家系统的水电机组振动故障诊断研究.华中科技大学学报(自然科学版),2002,30(6):102～104.
[19] Kumamaru K. et. all. Roust fault detection using index of Kullback discrimination information Proc. of IFAC World Congress, 2001, vol. 20(5): 205～210
[20]邱浩,王道波,张焕春.控制系统的故障诊断方法综述.航天控制,2004,22(2):53～57
[21]洪冶,蔡维由,乐振春.模糊故障树诊断及应用.武汉大学学报(工学版),2001,34(1):95～96.
[22]余涛,王晶,沈善德,等.分布式水电机组故障诊断集成专家系统的研究.动力工程,2002,22(4):1902～1907.
[23]陈喜阳,张克危,彭玉成.基于多种诊断方法的水电机组故障诊断系统的研究.水力发电,2003, 29(5):23～26.
[24]李苹,窦海波,王正.水轮发电机组主轴系统的建模及其非线性瞬态响应.清华大学学报(自然科学版),1998,38(6):123～128
[25]付波,周建中,彭兵,等.固定式刚性联轴器不对中弯扭耦合振动特性.华中科技大学学报(自然科学版),2007,36(4):96～99
[26]倪传坤,周建中.基于SVD的水电机组轴心轨迹自动识别.水电自动化与大坝监测,2003,27(6):22～24.
[27]唐保鑫.广西原恶滩水电厂探索“状态检修”成效.水电厂自动化,2006(4):161～164
[28]杨金栋,周志清.我国水电厂自动化工作的实践与展望.水电厂自动化,2006增刊:1～5
[29]屈梁生,史冬锋.全息谱十年:回顾与展望.振动、测试与诊断,1998,18(4):235～242
[30]徐鸣,温仲元,李志敏,等.机械变速过程中的工频跟踪测振技术.振动、测试与诊断,2000,20(2):106～110
[31]胡劲松,吴昭同,严拱标.提高旋转机械振动信号整周期采样精度的一种方法.浙江大学学报(工学版),2002,36(3):273～275
[32]田昊,栾军英,田广,等.阶次跟踪分析在齿面磨损故障诊断中的应用.军械工程学院学报,2005,17(5):57～60
[33]华斌.贝叶斯网络在水电机组状态检修中的应用研究:[博士学位论文].武汉:华中科技大学图书馆,2004
[34]何正嘉.我国小波技术的应用现状与进展.振动工程学报,2000,13(增刊):16～22
[35]刘志刚,曾怡达,钱清泉.多小波在电力系统信号消噪中的应用.中国电机工程学报,2004,24(1):30～33
[36]韩敏,刘玉花,席剑辉.基于小波变换阈值决策的混沌信号去噪研究.信息与控制,2005,34(5):543～547
[37]韩西京,史铁林,李录平等.故障诊断中几种征兆自动获取技术研究.华中理工大学学报,1997,25(8):53～55.
[38]王海,郑莉媛.水轮发电机组轴心轨迹自动识别方法研究.水力发电学报,2002(3):73～80.
[39]李友平,陈启卷.基于灰色理论与不变性矩的水电机组轴心轨迹自动识别.电力系统自动化,2001(10):19～22
[40]倪传坤,周建中,付波.基于改进不变矩的发电机组轴心轨迹识别.电力科学与工程,2004(2):16～18.
[41]付波,周建中,陈文清,等.一种基于傅立叶描述子的轴心轨迹自动识别方法.电力系统自动化,2004,28(12):40～44.
[42]付波,周建中,彭兵,等.基于仿射不变矩的轴心轨迹自动识别方法研究.华中科技大学学报(自然科学版),2007,35(3):119～122
[43]唐贵基,王誉蓉,郭新富,等.基于熵带法的旋转机械故障诊断与故障分类.煤矿机械,2006,27(9):189～191
[44]苑宇,马孝江.基于多分量奇异熵的往复式压缩机故障分类.大连理工大学学报,2007,47(2):196～200
[45]耿俊豹,黄树红,陈非,等.基于信息熵贴近度的旋转机械故障诊断.华中科技大学学报(自然科学版),2006,34(11):93～95
[46]桂中华,韩凤琴.小波包-最大熵谱估计及其在水轮机故障诊断中的应用.电力系统自动化,2004,28(2):62～66.
[47]胡红英,马孝江.局域波近似熵及其在机械故障诊断中的应用.振动与冲击,2006,25(6):38～42
[48]孙卫祥,陈进,吴立伟,等.基于PCA与决策树的转子故障诊断.振动与冲击,2007,26(3):72～74
[49]胡金海,谢寿生,侯胜利.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
[50]郭小荟,马小平.基于粗糙集的故障诊断特征提取.计算机工程与应用,2007,23(1):221～224
[51]梁武科,赵道利,马薇,等.基于粗糙集-神经网络的水电机组故障诊断.仪器仪表学报,2007,28(10):1806～1810
[52] Vapnik V N,The Nature of Statistical Learning Theory(First Edition). N Y: Springer-Verlag, 1995. 203～232
[53] Vapnik V N.统计学习理论的本质(第1版).张学工译.北京:清华大学出版社,2000. 35～71
[54]许建华,张学工,李衍达,等.支持向量机的新发展.控制与决策,2004,19(5):481～485
[55]张学工,关于统计学习理论和支持向量机.自动化学报,2000,26(1):32～34
[56] Joachims T. Making Large Scale SVM Learning Practical. in: Sellflkopf B. et all. Advances in Kernel Methods Support Vector Learning. Cambridge: MIT Press, 1999. 201～210
[57] Platt J. Fast training of support vector machines using sequential minimal optimization. in: Advances in Kernel Method——Support Vector Learning. Cambridge: MIT Press, 1999. 185～208.
[58] Keerthi S S. Improvements to Ptatt's SMO Algorithm for SVM Classier Design. in: TR CD-99-14. Singapore: Department of Mechanic and Proceeding Engin, National University of Singapore,1999. 1121～1132
[59] Chih W H. A Simple Decomposition Method for Support Vector Machines. in: Technical report. Taiwan: National Taiwan University, 1999. 539～545
[60] Suykens J A K, Vandew alle J. Least squares support vector machines. Neural Processing Letters, 1999, 9(3): 293～300.
[61] Scolkopf B. Estimating the support of a high-dimensional distribution. in: TR 99-87. NewYork: Microsoft Research, 1999. 25～36
[62] Mangasarian O L. Generalized support vector machines. in: Advances in Large Margin Classifiers. Cambridge: MIT Press, 2000. 135～146.
[63] Bernhard Scholkopf, Sebastian Mika, Chris J. C. Burges, et. all. Input Space Versus Feature Spacein Kernel-Based Methods. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, vol. 10(5): 1000～1017
[64] James Tin-Yau KWok. Moderating the Outputs of Support Vector Machine Classifiers. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999,vol. 10(5):1018～1031
[65] James Tin-Yau KWok. The Evidence Framework Applied to Support Vector Machines. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, vol. 11(5): 1162～1173
[66]卢增祥,李衍达.交互支持向量机学习算法及其应用.清华大学学报(自然科学版),1999,39(7):93～97
[67]刘江华,程君实,陈佳品.支持向量机训练算法综述.信息与控制,2002,31(1):45～50
[68] Cortes C, Vapnik V. Support vector networks. Machine Learning, 1995, 20: 273～297
[69] Oren M, Papageorgiou C, Sinha Petal. Pedestrian detection using wavelet templates. In: Proc. of CV PR’97, Puerto: Rico, 1997. 78～83
[70] HearstM A , Schoblkopf B, Dumais S, et al. Trends and controversies support vector machines. IEEE Intelligent Systems, 1998, 13 (4): 18～28
[71] Osuna E, Freund R, Girosi F. Training support vector machines: an application to face detection. in: Proc. Of CV PR’97, Puerto: Rico, 1997. 102～107
[72] Harris Drucker, Donghui Wu, and Vladimir N. Vapnik. Support Vector Machines forSpam Categorization. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, vol. 10(5):1048～1054
[73] Olivier Chapelle, Patrick Haffner, and Vladimir N. Vapnik. Support Vector Machines for Histogram-Based Image Classification. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, vol. 10(5): 1055～1064
[74]肖健华.人脸识别中的核方法.五邑大学学报(自然科学版),2005,19(2):8～13
[75]黄鹍,陈森发,亓霞,周振国.基于粗集理论和支持向量机的多源信息融合方法及应用.模式识别和人工智能,2005,18(3):354～358
[76]任建峰,郭雷,李刚.多类支持向量机的自然图像分类.西北工业大学学报,2005,23(3):295～299
[77]潘明清,周晓军,杨辰龙等.基于信息谱熵的支持向量机机械状态识别.传感技术学报,2005,18(2):277～280
[78]杨俊燕,张优云,赵荣珍.支持向量机在机械设备振动信号趋势预测中的应用.西安交通大学学报,2005,39(9):950～953
[79]赵冲冲,廖明夫,于潇.基于支持向量机的旋转机械故障诊断.振动、测试与诊断,2006,26(1):53～58
[80]姜万录,程晓盛,陈东宁.基于支持向量机和多Agent融合的智能故障诊断系统研究.五邑大学学报(自然科学版),2005,19(3):13～19
[81]王灵,俞金寿.基于离散粒子群和支持向量机的故障诊断方法.华东理工大学学报(自然科学版),2005,31(5):697～700
[82]张龙,熊国良,柳和生等.基于时变自回归模型与支持向量机的旋转机械故障诊断方法.中国电机工程学报,2007,27(9):99～103
[83]唐浩,屈梁生.基于支持向量机的发动机故障诊断.西安交通大学学报,2007,41(9):1124～1126
[84]徐启华,师军.应用SVM的发动机故障诊断若干问题研究.航空学报,2005,26(6):686～690
[85]翟永杰,王东风,韩璞.基于多类支持向量机的汽轮发电机组故障诊断.动力工程,2003,23(5):2694～2698
[86]张曦,阎威武,刘振亚等.基于核主元分析和邻近支持向量机的汽轮机凝汽器的过程监控和故障诊断.中国电机工程学报,2007,27(14):56～61
[87]耿兰芹,王芳,赵文清. SVM回归与朴素贝叶斯分类相结合的变压器故障诊断.华北电力大学学报,2006,23(6):28～32
[88]张国云,章兢.基于模糊支持向量机的多级二叉树分类器的水轮机调速系统故障诊断.中国电机工程学报,2005,25(8):100～104
[89]谭逢友,卢宏伟,刘成俊等.信息融合技术在机械故障诊断中的应用.重庆大学学报(自然科学版),2006,29(1):14～17
[90]王文杰,叶世伟.人工智能原理与应用(第1版).北京:人民邮电出版社,2004. 178～186
[91]周芳,韩立岩.多传感器信息融合技术综述.遥测遥控,2006,27(3):1～7
[92]臧大进,严宏凤,王跃才.多传感器信息融合技术综述.工矿自动化,2005,(6):31～33
[93] Parikh C R, Pont M J, Jones N B. Application of dempster-shafer theory in condition monitoring applications: a case study. Pattern Recognition Letter, 2001, 22: 777～785.
[94]付华,王传英,冯爱伟,等.信息融合在煤层自然发火预测系统中的应用研究.矿业安全与环保,2006,13(3):36～37
[95] Jia Yuqin, Wang Peixia, Li Yue. Study of Manufacturing System Based on Neural Network Multi-sensor Data Fusion and Its Application. Robotics Intelligent Systems and Signal Processing, 2003, vol.2(8): 1022～1026.
[96] Alan N Steinberg. Data Fusion System Engineering. IEEE AESS Systems Magazine, 2001, 6: 7～14.
[97] Valetl, Mauris G, Bolon Ph. A Statistical Overview of Recent Literature in Information Fusion. IEEE AESS Systems Magazine, 2001, 3: 7～14.
[98] Tanaka K, Klir G J. A design condition for incorporating human judgement into monitoring systems. Reliability Engineering and System Safety, 1999, 65: 251～258
[99]行小帅,焦李成.粒度神经网络在数字语言中的数据融合.计算机科学,2002,29(11):40～43
[100]伍学奎,陈进.基于多指标融合的故障诊断理论与方法.振动工程学报,1999,12(1):55～63
[101] He Yongyong, Chu Fulei, Zhong Binglin. A study on group decision-making based fault multi-symptom-domain consensus diagnosis.Reliability Engineering and System Safety, 2001, 74: 43～52.
[102]胡仕刚.一种机械故障检测的信息融合.机床与液压, 2003, (6): 325～327.
[103]朱大奇,于盛林.基于D-S证据理论的数据融合算法及其在电路故障诊断中的应用.电子学报,2002,30(2):221～223
[104]尚勇,闫春江,严璋,等.基于信息融合的大型油浸电力变压器故障诊断.中国电机工程学报,2002,22(7):115～118.
[105]蔡兴国,马平.基于信息融合技术的并发故障诊断的研究.中国电机工程学报,2003,23(5):112～115
[106]郑德忠,何乐,周浔.基于Fuzzy理论的供热管网故障诊断系统的研究.传感技术学报,2003,(3):367～370
[107]米东,徐章遂,王平.模糊信息融合及其在发动机失火故障诊断中的应用.河北工业大学学报,2005,34(1):65～69
[108]彭敏放,何怡刚,王耀南.基于信息融合技术的模拟电路故障诊断.微电子学,2005,35(2):149～152
[109]张晓东,张振中,胡明.基于信息融合的船舶机电设备故障诊断.船舶工程,2007,29(3):44～46
[110]彭涛,桂卫华,吴敏,等.轴承故障融合诊断方法.基础自动化,2001,8(4):54～57
[111]王毅.风机故障诊断的集成神经网络信息融合法.风机技术,2005(2):35～37
[112]孙卫祥,陈进,伍星,等.基于信息融合的支撑座早期松动故障诊断.上海交通大学学报,2006,40(2):239～243
[113]姜万录,李冲祥.神经网络和证据理论融合的故障诊断方法研究.中国机械工程,2004,15(9):760～764
[114]谢春丽,夏虹,刘永阔.多传感器数据融合技术在故障诊断中的应用.传感器技术,2004,23(4):67～69.
[115]高美静,王魁荣,谈爱玲.混沌神经网络多传感器信息融合系统设计.系统仿真学报,2005,17(9):2218～2221
[116]王天宇,董彩凤.一种多组并联模糊神经网络用于信息融合诊断.哈尔滨工业大学学报,2004,36(3):324～328
[117]刘燕燕.基于模糊神经网络的信息融合在电网故障诊断中的应用.继电器,2005,33(9):9～12
[118]张敬芬,赵德有.基于模糊神经网络和数据融合的结构裂纹故障诊断.船舶力学,2004,8(2):55～62
[119]周建中,陈遗志.基于数据融合和数据共享的水电机组故障诊断.华中科技大学学报(自然科学版),2002,30(7):54～56.
[120]华斌,周建中.水电机组故障诊断中的数据融合算法.水电自动化与大坝监测,2004,28(1):12～15
[121]苏羽,赵海,苏威积,等.一种基于模糊神经网络的融合故障诊断方法.计算机工程,2004,30(17):5～7
[122]赵道利,马薇,梁武科,等.水电机组振动故障的信息融合诊断与仿真研究.中国电机工程学报,2005,25(20):137～142
[123]杨晓萍,南海鹏,张江滨.信息融合技术在水轮发电机组故障诊断中的应用.水力发电学报,2004,23(6):111～115
[124]王海.水轮发电机组状态监测、诊断及综合试验分析系统研究: [博士学位论文].武汉:华中科技大学图书馆,2001.
[125]常近时,寿梅华,于希哲.水轮机运行(第1版).北京:水利电力出版社,1983. 87～192
[126]董毓新.水轮发电机组振动(第1版).大连:大连理工大学出版社,1989. 142～173
[127]程宝清,韩凤琴,桂中华.基于小波的灰色预测理论在水电机组故障预测中的应用.电网技术,2005,29(13):40～44
[128]冯辅周,褚福磊.轴承典型安装状态对水轮发电机转子横向振动的影响.见:全国第6届转子动力学学术讨论会ROTDYA 2001论文集,北京:中国机械工程学会,2001. 194～199
[129]刘云.水轮发电机故障处理与检修(第1版).北京:水利水电出版社,2002. 56～89
[130]赵道利.水电机组振动故障的信息融合诊断与仿真研究:[硕士学位论文].西安:西安理工大学图书馆,2004.
[131]林铭贤.混流式水轮机组振动初探.水利科技,2001(1):52～53
[132]马震岳,董毓新.水轮发电机组动力学(第1版).大连:大连理工大学出版社,2003. 231～257
[133]常近时.水力机械装置过渡过程(第3版).北京:高等教育出版社,2005. 113～117
[134]刘忠,周建中,张勇传,等.基于水电机组复合特征提取的RBFNN故障诊断.电力系统自动化,2007,31(11):87～91
[135]张吉先,钟秋海,戴亚平.“小波门限消噪法应用中分解层数及阈值的确定”.中国电机工程学报,2004,24(2):118～122
[136] Box G E P,Jenkins G M ,Reinsel G C.Time series analysis: forecasting and control(Third Edition). Englewood Clifs: NJ Prentice Hall, 1994. 203～216
[137]朱浩,陈喜阳,李友平等.水电机组在线监测中同步整周期采样实现策略.电力系统自动化,2007,31(4):80～84
[138]杨国田,白焰.回转机械多通道同步整周期采样的实现方案.自动化仪表, 2003 , 24 (10): 24～28
[139]周伟达,张莉,焦李成.一种改进的推广能力衡量准则.计算机学报,2003,26(5):598～604
[140] M. Seeger. Bayesian model selection for Support Vector machines, Gaussian processes and other kernel classifiers. Advances in Neural Information Systems , 2000, 12: 603～609
[141] J. Smola, B. Scholkopf , K. R Muller, et. all. The connection between regularization operators and support vector kernels. Neural Networks, 1998,11: 637～649.
[142] B. Scholkopf, P. Simard, A. Smola ,V. N. Vapnik. Prior knowledge in support vector kernels. Advances in Neural Information Processing Systems 1998, 10: 37～49.
[143] S. Amari, S. Wu. Improving support vector machine classifiers by modifying kernel function. Journal of Neural Networks, 1999, 12: 783～789
[144] Si Wu, S. Amari. Conformal Transformation of Kernel Functions: A Data-Dependent Way to Improve Support Vector Machine Classifiers. NeuralProcessing Letters, 2002, 15: 59～67
[145] VapNik V.N.Statistical learning theory (Second Edition). J.Wiley, New York, 1998. 175～203
[146] Kressel U. Pairwise classification and support vector machines. In: B.Scholkopf, ed. Advances in Kernel Methods—Support Vector Learning. Cambrifge: MIT Press, 1999. 255～268
[147]邓乃扬,田英杰.数据挖掘中的新方法:支持向量机(第1版).北京:科学出版社,2004. 307～339
[148] C. J. C. Burges. Geometry and Invariance in Kernel Based Method. In: B. Scholkopf, C. J. C. Burges and A. J. Smola (eds). Advances in Kernel Methods. Cambrifge, Massachusetts: MIT Press, 1999. 89～116
[149]高隽.人工神经网络原理及仿真实例(第1版).北京:机械工业出版社,2003. 76～93
[150] Wu Fangfang, Zhao Yinliang. Least Squares Support Vector Machine Based on Scaling Kernel Function. Chinese Journal of PR&AI, 2006, vol. 19(5): 598～603
[151]沈东,褚福涛,陈思.水轮发电机组振动故障诊断与识别.水动力学研究与进展,2000,15(1):129～133.
[152]王征.信息融合算法发展综述.船舶论证参考,2002(1):53～57
[153]张仰森.人工智能原理与应用(第1版).北京:高等教育出版社,2004. 170～182
[154]戴冠中,潘泉.证据推理的进展及其存在的问题.控制理论与应用,1999,16(4):465～469
[155]何友,王国宏,陆大琻,等.多传感器信息融合及应用(第2版).北京:电子工业出版社,2000. 96～131
[156]陈小玄,罗大庸,单勇腾.基于神经网络信息融合的机车牵引电机故障诊断.计算机测量与控制,2007,15(5):563～566
[157]侯俊.证据理论的几个关键问题研究:[硕士学位论文].西安:西北工业大学图书馆,2003.
[2]周双超.中国水能资源富甲天下解读——全国水力资源复查工作综述.中国三峡建设,2005,(6):68～73
[3]黄宝南.三峡电站及我国今后水电建设方略综述.能源研究与应用,2003,(3):7～8
[4]中国电力行业五年发展成就辉煌(2002年～2007年).中国电力报,2007年10月16日
[5] Vladimir N. Vapnik. An Overview of Statistical Learning Theory. IEEE trans. Neural Networks, 1999, vol. 10(5): 988～999
[6] Klaus-Robert Müller, Sebastian Mika, Gunnar R?tsch. An Introduction to Kernel-Based Learning Algorithms. IEEE trans. Neural Networks, 2001, vol. 12(2): 181～201
[7]翟永杰,韩璞,王东风,等.基于损失函数的SVM算法及其在轻微故障诊断中的应用.中国电机工程学报,2003,23(9):198～203
[8]马骞,杨以涵,刘文颖,等.多输入特征融合的组合支持向量机电力系统暂态稳定评估.中国电机工程学报,2005,25(6):17～23
[9]鹿卫国,戴亚平,高峰.一种基于概率分布估计的水电机组故障预警方法.中国电机工程学报,2005,25(4):94～98
[10]国家电力公司.水电厂开展设备状态检修工作的指导意见,2002
[11]涂长庚.水力发电设备预知维修.华中电力, 2000, 13(3):37～39.
[12]梁武科,赵道利.水电机组监测与诊断技术的现状及发展.水利水电技术,2003,34(4):41～43
[13]瞿曌，赖旭，盛旺.水电机组状态检修的研究.人民长江,2007,38(6):54～56
[14]瞿曌，赖旭，盛旺.水电机组状态检修现状分析.中国电力,2007,40(10):20～23
[15]杨晓萍,解建宝,张靠社,等.水轮发电机组的事故停机分析与故障诊断专家系统的研究.西安理工大学学报,1998,14(2):91～95.
[16]陈铁华,陈启卷.模糊聚类分析在水电机组振动故障诊断中的应用.中国电机工程学报,2002,22(2):43～47.
[17]梁业国,王乘.人工神经网络在水电机组故障诊断中的应用研究.四川水力发电,2003,22(1):57～59.
[18]陈卫钢,周建中,常黎.基于专家系统的水电机组振动故障诊断研究.华中科技大学学报(自然科学版),2002,30(6):102～104.
[19] Kumamaru K. et. all. Roust fault detection using index of Kullback discrimination information Proc. of IFAC World Congress, 2001, vol. 20(5): 205～210
[20]邱浩,王道波,张焕春.控制系统的故障诊断方法综述.航天控制,2004,22(2):53～57
[21]洪冶,蔡维由,乐振春.模糊故障树诊断及应用.武汉大学学报(工学版),2001,34(1):95～96.
[22]余涛,王晶,沈善德,等.分布式水电机组故障诊断集成专家系统的研究.动力工程,2002,22(4):1902～1907.
[23]陈喜阳,张克危,彭玉成.基于多种诊断方法的水电机组故障诊断系统的研究.水力发电,2003, 29(5):23～26.
[24]李苹,窦海波,王正.水轮发电机组主轴系统的建模及其非线性瞬态响应.清华大学学报(自然科学版),1998,38(6):123～128
[25]付波,周建中,彭兵,等.固定式刚性联轴器不对中弯扭耦合振动特性.华中科技大学学报(自然科学版),2007,36(4):96～99
[26]倪传坤,周建中.基于SVD的水电机组轴心轨迹自动识别.水电自动化与大坝监测,2003,27(6):22～24.
[27]唐保鑫.广西原恶滩水电厂探索“状态检修”成效.水电厂自动化,2006(4):161～164
[28]杨金栋,周志清.我国水电厂自动化工作的实践与展望.水电厂自动化,2006增刊:1～5
[29]屈梁生,史冬锋.全息谱十年:回顾与展望.振动、测试与诊断,1998,18(4):235～242
[30]徐鸣,温仲元,李志敏,等.机械变速过程中的工频跟踪测振技术.振动、测试与诊断,2000,20(2):106～110
[31]胡劲松,吴昭同,严拱标.提高旋转机械振动信号整周期采样精度的一种方法.浙江大学学报(工学版),2002,36(3):273～275
[32]田昊,栾军英,田广,等.阶次跟踪分析在齿面磨损故障诊断中的应用.军械工程学院学报,2005,17(5):57～60
[33]华斌.贝叶斯网络在水电机组状态检修中的应用研究:[博士学位论文].武汉:华中科技大学图书馆,2004
[34]何正嘉.我国小波技术的应用现状与进展.振动工程学报,2000,13(增刊):16～22
[35]刘志刚,曾怡达,钱清泉.多小波在电力系统信号消噪中的应用.中国电机工程学报,2004,24(1):30～33
[36]韩敏,刘玉花,席剑辉.基于小波变换阈值决策的混沌信号去噪研究.信息与控制,2005,34(5):543～547
[37]韩西京,史铁林,李录平等.故障诊断中几种征兆自动获取技术研究.华中理工大学学报,1997,25(8):53～55.
[38]王海,郑莉媛.水轮发电机组轴心轨迹自动识别方法研究.水力发电学报,2002(3):73～80.
[39]李友平,陈启卷.基于灰色理论与不变性矩的水电机组轴心轨迹自动识别.电力系统自动化,2001(10):19～22
[40]倪传坤,周建中,付波.基于改进不变矩的发电机组轴心轨迹识别.电力科学与工程,2004(2):16～18.
[41]付波,周建中,陈文清,等.一种基于傅立叶描述子的轴心轨迹自动识别方法.电力系统自动化,2004,28(12):40～44.
[42]付波,周建中,彭兵,等.基于仿射不变矩的轴心轨迹自动识别方法研究.华中科技大学学报(自然科学版),2007,35(3):119～122
[43]唐贵基,王誉蓉,郭新富,等.基于熵带法的旋转机械故障诊断与故障分类.煤矿机械,2006,27(9):189～191
[44]苑宇,马孝江.基于多分量奇异熵的往复式压缩机故障分类.大连理工大学学报,2007,47(2):196～200
[45]耿俊豹,黄树红,陈非,等.基于信息熵贴近度的旋转机械故障诊断.华中科技大学学报(自然科学版),2006,34(11):93～95
[46]桂中华,韩凤琴.小波包-最大熵谱估计及其在水轮机故障诊断中的应用.电力系统自动化,2004,28(2):62～66.
[47]胡红英,马孝江.局域波近似熵及其在机械故障诊断中的应用.振动与冲击,2006,25(6):38～42
[48]孙卫祥,陈进,吴立伟,等.基于PCA与决策树的转子故障诊断.振动与冲击,2007,26(3):72～74
[49]胡金海,谢寿生,侯胜利.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
[50]郭小荟,马小平.基于粗糙集的故障诊断特征提取.计算机工程与应用,2007,23(1):221～224
[51]梁武科,赵道利,马薇,等.基于粗糙集-神经网络的水电机组故障诊断.仪器仪表学报,2007,28(10):1806～1810
[52] Vapnik V N,The Nature of Statistical Learning Theory(First Edition). N Y: Springer-Verlag, 1995. 203～232
[53] Vapnik V N.统计学习理论的本质(第1版).张学工译.北京:清华大学出版社,2000. 35～71
[54]许建华,张学工,李衍达,等.支持向量机的新发展.控制与决策,2004,19(5):481～485
[55]张学工,关于统计学习理论和支持向量机.自动化学报,2000,26(1):32～34
[56] Joachims T. Making Large Scale SVM Learning Practical. in: Sellflkopf B. et all. Advances in Kernel Methods Support Vector Learning. Cambridge: MIT Press, 1999. 201～210
[57] Platt J. Fast training of support vector machines using sequential minimal optimization. in: Advances in Kernel Method——Support Vector Learning. Cambridge: MIT Press, 1999. 185～208.
[58] Keerthi S S. Improvements to Ptatt's SMO Algorithm for SVM Classier Design. in: TR CD-99-14. Singapore: Department of Mechanic and Proceeding Engin, National University of Singapore,1999. 1121～1132
[59] Chih W H. A Simple Decomposition Method for Support Vector Machines. in: Technical report. Taiwan: National Taiwan University, 1999. 539～545
[60] Suykens J A K, Vandew alle J. Least squares support vector machines. Neural Processing Letters, 1999, 9(3): 293～300.
[61] Scolkopf B. Estimating the support of a high-dimensional distribution. in: TR 99-87. NewYork: Microsoft Research, 1999. 25～36
[62] Mangasarian O L. Generalized support vector machines. in: Advances in Large Margin Classifiers. Cambridge: MIT Press, 2000. 135～146.
[63] Bernhard Scholkopf, Sebastian Mika, Chris J. C. Burges, et. all. Input Space Versus Feature Spacein Kernel-Based Methods. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, vol. 10(5): 1000～1017
[64] James Tin-Yau KWok. Moderating the Outputs of Support Vector Machine Classifiers. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999,vol. 10(5):1018～1031
[65] James Tin-Yau KWok. The Evidence Framework Applied to Support Vector Machines. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, vol. 11(5): 1162～1173
[66]卢增祥,李衍达.交互支持向量机学习算法及其应用.清华大学学报(自然科学版),1999,39(7):93～97
[67]刘江华,程君实,陈佳品.支持向量机训练算法综述.信息与控制,2002,31(1):45～50
[68] Cortes C, Vapnik V. Support vector networks. Machine Learning, 1995, 20: 273～297
[69] Oren M, Papageorgiou C, Sinha Petal. Pedestrian detection using wavelet templates. In: Proc. of CV PR’97, Puerto: Rico, 1997. 78～83
[70] HearstM A , Schoblkopf B, Dumais S, et al. Trends and controversies support vector machines. IEEE Intelligent Systems, 1998, 13 (4): 18～28
[71] Osuna E, Freund R, Girosi F. Training support vector machines: an application to face detection. in: Proc. Of CV PR’97, Puerto: Rico, 1997. 102～107
[72] Harris Drucker, Donghui Wu, and Vladimir N. Vapnik. Support Vector Machines forSpam Categorization. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, vol. 10(5):1048～1054
[73] Olivier Chapelle, Patrick Haffner, and Vladimir N. Vapnik. Support Vector Machines for Histogram-Based Image Classification. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, vol. 10(5): 1055～1064
[74]肖健华.人脸识别中的核方法.五邑大学学报(自然科学版),2005,19(2):8～13
[75]黄鹍,陈森发,亓霞,周振国.基于粗集理论和支持向量机的多源信息融合方法及应用.模式识别和人工智能,2005,18(3):354～358
[76]任建峰,郭雷,李刚.多类支持向量机的自然图像分类.西北工业大学学报,2005,23(3):295～299
[77]潘明清,周晓军,杨辰龙等.基于信息谱熵的支持向量机机械状态识别.传感技术学报,2005,18(2):277～280
[78]杨俊燕,张优云,赵荣珍.支持向量机在机械设备振动信号趋势预测中的应用.西安交通大学学报,2005,39(9):950～953
[79]赵冲冲,廖明夫,于潇.基于支持向量机的旋转机械故障诊断.振动、测试与诊断,2006,26(1):53～58
[80]姜万录,程晓盛,陈东宁.基于支持向量机和多Agent融合的智能故障诊断系统研究.五邑大学学报(自然科学版),2005,19(3):13～19
[81]王灵,俞金寿.基于离散粒子群和支持向量机的故障诊断方法.华东理工大学学报(自然科学版),2005,31(5):697～700
[82]张龙,熊国良,柳和生等.基于时变自回归模型与支持向量机的旋转机械故障诊断方法.中国电机工程学报,2007,27(9):99～103
[83]唐浩,屈梁生.基于支持向量机的发动机故障诊断.西安交通大学学报,2007,41(9):1124～1126
[84]徐启华,师军.应用SVM的发动机故障诊断若干问题研究.航空学报,2005,26(6):686～690
[85]翟永杰,王东风,韩璞.基于多类支持向量机的汽轮发电机组故障诊断.动力工程,2003,23(5):2694～2698
[86]张曦,阎威武,刘振亚等.基于核主元分析和邻近支持向量机的汽轮机凝汽器的过程监控和故障诊断.中国电机工程学报,2007,27(14):56～61
[87]耿兰芹,王芳,赵文清. SVM回归与朴素贝叶斯分类相结合的变压器故障诊断.华北电力大学学报,2006,23(6):28～32
[88]张国云,章兢.基于模糊支持向量机的多级二叉树分类器的水轮机调速系统故障诊断.中国电机工程学报,2005,25(8):100～104
[89]谭逢友,卢宏伟,刘成俊等.信息融合技术在机械故障诊断中的应用.重庆大学学报(自然科学版),2006,29(1):14～17
[90]王文杰,叶世伟.人工智能原理与应用(第1版).北京:人民邮电出版社,2004. 178～186
[91]周芳,韩立岩.多传感器信息融合技术综述.遥测遥控,2006,27(3):1～7
[92]臧大进,严宏凤,王跃才.多传感器信息融合技术综述.工矿自动化,2005,(6):31～33
[93] Parikh C R, Pont M J, Jones N B. Application of dempster-shafer theory in condition monitoring applications: a case study. Pattern Recognition Letter, 2001, 22: 777～785.
[94]付华,王传英,冯爱伟,等.信息融合在煤层自然发火预测系统中的应用研究.矿业安全与环保,2006,13(3):36～37
[95] Jia Yuqin, Wang Peixia, Li Yue. Study of Manufacturing System Based on Neural Network Multi-sensor Data Fusion and Its Application. Robotics Intelligent Systems and Signal Processing, 2003, vol.2(8): 1022～1026.
[96] Alan N Steinberg. Data Fusion System Engineering. IEEE AESS Systems Magazine, 2001, 6: 7～14.
[97] Valetl, Mauris G, Bolon Ph. A Statistical Overview of Recent Literature in Information Fusion. IEEE AESS Systems Magazine, 2001, 3: 7～14.
[98] Tanaka K, Klir G J. A design condition for incorporating human judgement into monitoring systems. Reliability Engineering and System Safety, 1999, 65: 251～258
[99]行小帅,焦李成.粒度神经网络在数字语言中的数据融合.计算机科学,2002,29(11):40～43
[100]伍学奎,陈进.基于多指标融合的故障诊断理论与方法.振动工程学报,1999,12(1):55～63
[101] He Yongyong, Chu Fulei, Zhong Binglin. A study on group decision-making based fault multi-symptom-domain consensus diagnosis.Reliability Engineering and System Safety, 2001, 74: 43～52.
[102]胡仕刚.一种机械故障检测的信息融合.机床与液压, 2003, (6): 325～327.
[103]朱大奇,于盛林.基于D-S证据理论的数据融合算法及其在电路故障诊断中的应用.电子学报,2002,30(2):221～223
[104]尚勇,闫春江,严璋,等.基于信息融合的大型油浸电力变压器故障诊断.中国电机工程学报,2002,22(7):115～118.
[105]蔡兴国,马平.基于信息融合技术的并发故障诊断的研究.中国电机工程学报,2003,23(5):112～115
[106]郑德忠,何乐,周浔.基于Fuzzy理论的供热管网故障诊断系统的研究.传感技术学报,2003,(3):367～370
[107]米东,徐章遂,王平.模糊信息融合及其在发动机失火故障诊断中的应用.河北工业大学学报,2005,34(1):65～69
[108]彭敏放,何怡刚,王耀南.基于信息融合技术的模拟电路故障诊断.微电子学,2005,35(2):149～152
[109]张晓东,张振中,胡明.基于信息融合的船舶机电设备故障诊断.船舶工程,2007,29(3):44～46
[110]彭涛,桂卫华,吴敏,等.轴承故障融合诊断方法.基础自动化,2001,8(4):54～57
[111]王毅.风机故障诊断的集成神经网络信息融合法.风机技术,2005(2):35～37
[112]孙卫祥,陈进,伍星,等.基于信息融合的支撑座早期松动故障诊断.上海交通大学学报,2006,40(2):239～243
[113]姜万录,李冲祥.神经网络和证据理论融合的故障诊断方法研究.中国机械工程,2004,15(9):760～764
[114]谢春丽,夏虹,刘永阔.多传感器数据融合技术在故障诊断中的应用.传感器技术,2004,23(4):67～69.
[115]高美静,王魁荣,谈爱玲.混沌神经网络多传感器信息融合系统设计.系统仿真学报,2005,17(9):2218～2221
[116]王天宇,董彩凤.一种多组并联模糊神经网络用于信息融合诊断.哈尔滨工业大学学报,2004,36(3):324～328
[117]刘燕燕.基于模糊神经网络的信息融合在电网故障诊断中的应用.继电器,2005,33(9):9～12
[118]张敬芬,赵德有.基于模糊神经网络和数据融合的结构裂纹故障诊断.船舶力学,2004,8(2):55～62
[119]周建中,陈遗志.基于数据融合和数据共享的水电机组故障诊断.华中科技大学学报(自然科学版),2002,30(7):54～56.
[120]华斌,周建中.水电机组故障诊断中的数据融合算法.水电自动化与大坝监测,2004,28(1):12～15
[121]苏羽,赵海,苏威积,等.一种基于模糊神经网络的融合故障诊断方法.计算机工程,2004,30(17):5～7
[122]赵道利,马薇,梁武科,等.水电机组振动故障的信息融合诊断与仿真研究.中国电机工程学报,2005,25(20):137～142
[123]杨晓萍,南海鹏,张江滨.信息融合技术在水轮发电机组故障诊断中的应用.水力发电学报,2004,23(6):111～115
[124]王海.水轮发电机组状态监测、诊断及综合试验分析系统研究: [博士学位论文].武汉:华中科技大学图书馆,2001.
[125]常近时,寿梅华,于希哲.水轮机运行(第1版).北京:水利电力出版社,1983. 87～192
[126]董毓新.水轮发电机组振动(第1版).大连:大连理工大学出版社,1989. 142～173
[127]程宝清,韩凤琴,桂中华.基于小波的灰色预测理论在水电机组故障预测中的应用.电网技术,2005,29(13):40～44
[128]冯辅周,褚福磊.轴承典型安装状态对水轮发电机转子横向振动的影响.见:全国第6届转子动力学学术讨论会ROTDYA 2001论文集,北京:中国机械工程学会,2001. 194～199
[129]刘云.水轮发电机故障处理与检修(第1版).北京:水利水电出版社,2002. 56～89
[130]赵道利.水电机组振动故障的信息融合诊断与仿真研究:[硕士学位论文].西安:西安理工大学图书馆,2004.
[131]林铭贤.混流式水轮机组振动初探.水利科技,2001(1):52～53
[132]马震岳,董毓新.水轮发电机组动力学(第1版).大连:大连理工大学出版社,2003. 231～257
[133]常近时.水力机械装置过渡过程(第3版).北京:高等教育出版社,2005. 113～117
[134]刘忠,周建中,张勇传,等.基于水电机组复合特征提取的RBFNN故障诊断.电力系统自动化,2007,31(11):87～91
[135]张吉先,钟秋海,戴亚平.“小波门限消噪法应用中分解层数及阈值的确定”.中国电机工程学报,2004,24(2):118～122
[136] Box G E P,Jenkins G M ,Reinsel G C.Time series analysis: forecasting and control(Third Edition). Englewood Clifs: NJ Prentice Hall, 1994. 203～216
[137]朱浩,陈喜阳,李友平等.水电机组在线监测中同步整周期采样实现策略.电力系统自动化,2007,31(4):80～84
[138]杨国田,白焰.回转机械多通道同步整周期采样的实现方案.自动化仪表, 2003 , 24 (10): 24～28
[139]周伟达,张莉,焦李成.一种改进的推广能力衡量准则.计算机学报,2003,26(5):598～604
[140] M. Seeger. Bayesian model selection for Support Vector machines, Gaussian processes and other kernel classifiers. Advances in Neural Information Systems , 2000, 12: 603～609
[141] J. Smola, B. Scholkopf , K. R Muller, et. all. The connection between regularization operators and support vector kernels. Neural Networks, 1998,11: 637～649.
[142] B. Scholkopf, P. Simard, A. Smola ,V. N. Vapnik. Prior knowledge in support vector kernels. Advances in Neural Information Processing Systems 1998, 10: 37～49.
[143] S. Amari, S. Wu. Improving support vector machine classifiers by modifying kernel function. Journal of Neural Networks, 1999, 12: 783～789
[144] Si Wu, S. Amari. Conformal Transformation of Kernel Functions: A Data-Dependent Way to Improve Support Vector Machine Classifiers. NeuralProcessing Letters, 2002, 15: 59～67
[145] VapNik V.N.Statistical learning theory (Second Edition). J.Wiley, New York, 1998. 175～203
[146] Kressel U. Pairwise classification and support vector machines. In: B.Scholkopf, ed. Advances in Kernel Methods—Support Vector Learning. Cambrifge: MIT Press, 1999. 255～268
[147]邓乃扬,田英杰.数据挖掘中的新方法:支持向量机(第1版).北京:科学出版社,2004. 307～339
[148] C. J. C. Burges. Geometry and Invariance in Kernel Based Method. In: B. Scholkopf, C. J. C. Burges and A. J. Smola (eds). Advances in Kernel Methods. Cambrifge, Massachusetts: MIT Press, 1999. 89～116
[149]高隽.人工神经网络原理及仿真实例(第1版).北京:机械工业出版社,2003. 76～93
[150] Wu Fangfang, Zhao Yinliang. Least Squares Support Vector Machine Based on Scaling Kernel Function. Chinese Journal of PR&AI, 2006, vol. 19(5): 598～603
[151]沈东,褚福涛,陈思.水轮发电机组振动故障诊断与识别.水动力学研究与进展,2000,15(1):129～133.
[152]王征.信息融合算法发展综述.船舶论证参考,2002(1):53～57
[153]张仰森.人工智能原理与应用(第1版).北京:高等教育出版社,2004. 170～182
[154]戴冠中,潘泉.证据推理的进展及其存在的问题.控制理论与应用,1999,16(4):465～469
[155]何友,王国宏,陆大琻,等.多传感器信息融合及应用(第2版).北京:电子工业出版社,2000. 96～131
[156]陈小玄,罗大庸,单勇腾.基于神经网络信息融合的机车牵引电机故障诊断.计算机测量与控制,2007,15(5):563～566
[157]侯俊.证据理论的几个关键问题研究:[硕士学位论文].西安:西北工业大学图书馆,2003.