基于数据挖掘的核电站故障诊断技术研究
|
摘要
故障诊断系统对保证核反应堆运行的安全性和经济性具有重要作用。目前，我国核电站主要采用传统的阈值报警方法，无法为操作人员提供故障发生的原因以及发展趋势等信息，因此核电站智能故障诊断技术的研究对提高核电站的安全性和经济性具有重大意义。知识获取已经成为建立智能故障诊断系统的瓶颈问题，而数据挖掘是解决知识获取问题的主要途径。在应用数据挖掘方法建立故障诊断模型时，诊断模型的可理解性、执行效率和泛化能力都是评价故障诊断模型性能的重要指标，而这也正是建立故障诊断系统的难点。
本文以核电站一回路和二回路主系统的典型故障为对象，针对目前核电站故障诊断中的上述困难和问题，对核电站故障诊断的技术和方法进行了以下几个方面的研究和探索。
首先，对核电站典型故障进行了分析，并根据特征参数的变化采集了故障样本。针对专家系统知识获取的瓶颈问题和神经网络等黑箱建模方法所建模型不易理解等问题，本文分别采用决策树C4.5和ID3算法建立了故障诊断模型，并将决策树算法获取的规则和理论分析得到的故障特征相比较，验证了决策树算法在知识获取方面的有效性。
其次，针对核电站采集和监测的参量众多，样本维数高，所造成的模型执行效率低、训练时间长等问题，本文采用邻域粗糙集对参数的重要程度进行评价，并采用贪心搜索策略构造了参数约简算法。克服了经典的Pawlak粗糙集只能处理离散数据，且参数离散化可能会丢失有效信息的问题。通过仿真分析证明进行参数约简可以大大提高诊断模型的执行效率。
然后，针对参数约简后可能会丢失部分有用信息，降低诊断模型的泛化性能的问题，本文采用集成学习算法，通过训练多个基模型，然后将这些基模型的结果进行融合并给出最终结果。集成学习算法可以在保证模型执行效率的情况下，提高模型的泛化能力。同时本文对核电站实际运行中可能出现的参数缺失问题进行了研究，证明了集成学习算法在有参数缺失的情况下依然可以得到较好的诊断结果，具有良好的容错能力。
同时，本文研究了核电站的时变特性。通过对参数的自相关系数曲线的分析，说明了核电站故障的发生是一个逐渐演化的过程，有必要把核电站的故障诊断当作序列监督学习的问题来对待。根据邻域粗糙集对参数重要程度的定义，计算了参数及其各阶延迟的依赖度函数，证明了随着参数各阶延迟的加入，参数对系统状态的分类能力逐渐提高，并根据依赖度函数的变化曲线选择滑动窗的尺寸。研究了参数的特征提取方法，根据参数的时变特性，选择合适的特征提取算法。通过仿真实验，验证了序列监督学习算法可以从数据中获取更多的信息，可以解决一些经典算法不能解决的问题。
Fault diagnosis system plays an important role for ensuring the safety and economy ofthe operation of nuclear reactor. At present threshold monitoring method is the main methodemployed in our country. This method can not provide the information of the root cause andthe deterioration trend. So studying the intelligent fault diagnosis technology of nuclearpower plant (NPP) has great significance to improve the safety and economy of nuclearpower plant. Knowledge acquisition has become the bottleneck problem of establishingintelligent fault diagnosis system. Data mining is the main way to solve problem ofknowledge acquisition. The comprehensibility, the efficiency and generalization ability ofdiagnostic model evaluation are all important indicators to evaluate the performance of thefault diagnosis model, when we establish the fault diagnosis model by data mining. Andthese aspects are the difficulties to establish fault diagnosis systom.
In this paper, with typical faults of primary loop and secondary loop system in NPP forobject, the research and exploration of fault diagnosis technology and methods according tothe above difficulties and problems are listed as follows:
Firstly，the typical faults of NPP are analyzed, and fault samples are collectedaccording to the analysis results. Knowledge acquisition is the bottleneck problem ofestablishing expert system. And the model established by black-box modeling method suchas artificial neural networks is not comprehensibile. According to these problems, in thispaper fault diagnosis model is established by decision tree ID3and C4.5respectively. Andthe classification rules which are obtained by decision tree algorithm are compared with therules which are obtained by theoretical analysis. The effectiveness of knowledge acquisitionof decision tree algorithm is verified.
Secondly, NPP is a very complex system, which need to collect and monitor vastparameters. So the dimension of fault samples is very high, leading to the executionefficiency of fault diagnosis model is low and the training time is long. According to theseproblems, in this paper the important degree of the parameters are evaluated byneighborhood rough set. And parameters reduction algorithm is constructed base on greedysearch strategy. The problem which Pawlak rough set can not process continuous data isovercomed. The simulation result shows that the execution efficiency of fault diagnosis model is greatly improved by parameters reduction.
Parameters reduction may be lose some useful information, leading to the thegeneralization ability of fault diagnosis model decreases. In this paper ensemble learningmethod was proposed according to the problem. Firstly, multiple base classifiers is trained.And the final results is obtained through fusing the base classifier. Ensemble learningmethod can increase the generalization ability of fault diagnosis model on condition ofensure the execution efficiency of fault diagnosis model. At the same time, this paperstudies the problem of invalid and absent parameters which may happen in the actualoperation of NPP. The Simulation results show that this method can get a good result on thecondition of invalid and absent parameters. So this medthod shows very good faulttolerance.
At the same time, the time-varying characteristic of NPP is studied in this paper. Theoccurrence of NPP failure is a gradual process of evolution through the analysis of theautocorrelation coefficient curve of parameters. So it is necessary to deal with faultdiagnosis of NPP as a sequential supervised learning problem. The dependency ofparameters and their order lags is computed according to the important degree of theparameters base on neighborhood rough set. The classification capability of parameters isimproved as adding the order lags of parameters. The size of sliding-window is chosenaccording to the dependency curve. The feature extracting algorithm is studied and chosenaccording to the time-variant characteristics of parameters. Simulation results verify that thesequential supervised learning algorithm can get more information from the parameters.Some problems which can’t be solved by classical algorithm can be diagnosed by sequentialsupervised learning method.
本文以核电站一回路和二回路主系统的典型故障为对象，针对目前核电站故障诊断中的上述困难和问题，对核电站故障诊断的技术和方法进行了以下几个方面的研究和探索。
首先，对核电站典型故障进行了分析，并根据特征参数的变化采集了故障样本。针对专家系统知识获取的瓶颈问题和神经网络等黑箱建模方法所建模型不易理解等问题，本文分别采用决策树C4.5和ID3算法建立了故障诊断模型，并将决策树算法获取的规则和理论分析得到的故障特征相比较，验证了决策树算法在知识获取方面的有效性。
其次，针对核电站采集和监测的参量众多，样本维数高，所造成的模型执行效率低、训练时间长等问题，本文采用邻域粗糙集对参数的重要程度进行评价，并采用贪心搜索策略构造了参数约简算法。克服了经典的Pawlak粗糙集只能处理离散数据，且参数离散化可能会丢失有效信息的问题。通过仿真分析证明进行参数约简可以大大提高诊断模型的执行效率。
然后，针对参数约简后可能会丢失部分有用信息，降低诊断模型的泛化性能的问题，本文采用集成学习算法，通过训练多个基模型，然后将这些基模型的结果进行融合并给出最终结果。集成学习算法可以在保证模型执行效率的情况下，提高模型的泛化能力。同时本文对核电站实际运行中可能出现的参数缺失问题进行了研究，证明了集成学习算法在有参数缺失的情况下依然可以得到较好的诊断结果，具有良好的容错能力。
同时，本文研究了核电站的时变特性。通过对参数的自相关系数曲线的分析，说明了核电站故障的发生是一个逐渐演化的过程，有必要把核电站的故障诊断当作序列监督学习的问题来对待。根据邻域粗糙集对参数重要程度的定义，计算了参数及其各阶延迟的依赖度函数，证明了随着参数各阶延迟的加入，参数对系统状态的分类能力逐渐提高，并根据依赖度函数的变化曲线选择滑动窗的尺寸。研究了参数的特征提取方法，根据参数的时变特性，选择合适的特征提取算法。通过仿真实验，验证了序列监督学习算法可以从数据中获取更多的信息，可以解决一些经典算法不能解决的问题。
Fault diagnosis system plays an important role for ensuring the safety and economy ofthe operation of nuclear reactor. At present threshold monitoring method is the main methodemployed in our country. This method can not provide the information of the root cause andthe deterioration trend. So studying the intelligent fault diagnosis technology of nuclearpower plant (NPP) has great significance to improve the safety and economy of nuclearpower plant. Knowledge acquisition has become the bottleneck problem of establishingintelligent fault diagnosis system. Data mining is the main way to solve problem ofknowledge acquisition. The comprehensibility, the efficiency and generalization ability ofdiagnostic model evaluation are all important indicators to evaluate the performance of thefault diagnosis model, when we establish the fault diagnosis model by data mining. Andthese aspects are the difficulties to establish fault diagnosis systom.
In this paper, with typical faults of primary loop and secondary loop system in NPP forobject, the research and exploration of fault diagnosis technology and methods according tothe above difficulties and problems are listed as follows:
Firstly，the typical faults of NPP are analyzed, and fault samples are collectedaccording to the analysis results. Knowledge acquisition is the bottleneck problem ofestablishing expert system. And the model established by black-box modeling method suchas artificial neural networks is not comprehensibile. According to these problems, in thispaper fault diagnosis model is established by decision tree ID3and C4.5respectively. Andthe classification rules which are obtained by decision tree algorithm are compared with therules which are obtained by theoretical analysis. The effectiveness of knowledge acquisitionof decision tree algorithm is verified.
Secondly, NPP is a very complex system, which need to collect and monitor vastparameters. So the dimension of fault samples is very high, leading to the executionefficiency of fault diagnosis model is low and the training time is long. According to theseproblems, in this paper the important degree of the parameters are evaluated byneighborhood rough set. And parameters reduction algorithm is constructed base on greedysearch strategy. The problem which Pawlak rough set can not process continuous data isovercomed. The simulation result shows that the execution efficiency of fault diagnosis model is greatly improved by parameters reduction.
Parameters reduction may be lose some useful information, leading to the thegeneralization ability of fault diagnosis model decreases. In this paper ensemble learningmethod was proposed according to the problem. Firstly, multiple base classifiers is trained.And the final results is obtained through fusing the base classifier. Ensemble learningmethod can increase the generalization ability of fault diagnosis model on condition ofensure the execution efficiency of fault diagnosis model. At the same time, this paperstudies the problem of invalid and absent parameters which may happen in the actualoperation of NPP. The Simulation results show that this method can get a good result on thecondition of invalid and absent parameters. So this medthod shows very good faulttolerance.
At the same time, the time-varying characteristic of NPP is studied in this paper. Theoccurrence of NPP failure is a gradual process of evolution through the analysis of theautocorrelation coefficient curve of parameters. So it is necessary to deal with faultdiagnosis of NPP as a sequential supervised learning problem. The dependency ofparameters and their order lags is computed according to the important degree of theparameters base on neighborhood rough set. The classification capability of parameters isimproved as adding the order lags of parameters. The size of sliding-window is chosenaccording to the dependency curve. The feature extracting algorithm is studied and chosenaccording to the time-variant characteristics of parameters. Simulation results verify that thesequential supervised learning algorithm can get more information from the parameters.Some problems which can’t be solved by classical algorithm can be diagnosed by sequentialsupervised learning method.
引文
[1]张力，黄曙东等．岭澳核电站人因可靠性分析．中国核科技报告，2000(00)
[2]陈进，机械设备故障诊断技术及其应用[M]．上海高教电子音像出版社，2003
[3]侯澍旻．时序数据挖掘及其在故障诊断中的应用研究[D].武汉科技大学博士论文，2006年10月：3-4页
[4]余红英．机械系统故障信号特征提取技术研究[D]．中北大学博士论文，2005：3-4页
[5] Jong Hyun Kim, Poong Hyun Seong. A methodology for the quantitative evaluationof NPP fault diagnostic systems dynamic aspects[J]. Annals of Nuclear Energy，2000，27:1459-1481P
[6]张晓华，奚树人．核电站故障诊断专家系统综述[J]．核动力工程，1999，20(3)：264-273页
[7] Reifman Jaques, Wei Thomas Y.C. PRODIAG: A process-independent transientdiagnostic system-I: Theoretical concepts[J]. Nuclear Science and Engineering,1999,131(3):329-347P
[8] Reifman, Jaques; Wei, Thomas Y.C. PRODIAG: A process-independent transientdiagnostic system-II: Validation tests[J]. Nuclear Science and Engineering,1999,131(3):348-369P
[9] Reifman Jaques, Glenn E. GRAHAM, Wei Thomas Y.C. F. Exible human machineinterface for process diagnositic[C]. Proceedings NPIC&HMIT’96,1996:1437-1444P
[10] Dieter Wach, Werner Bastl. On-line condition monitoring of large rotating machineryin NPPs[C]. Proceedings NPIC&HMIT’96.1996:1313-1320P
[11] Fantoni, Paolo F. Experiences and applications of PEANO for online monitoring inpower plants. Progress in Nuclear Energy, Computational Intelligence in NuclearApplications: Lessons Learned and Recent Developments,2005:206-225P
[12] Davide Roverso. Fault diagnosis with the Aladdin transient classifier[C]. Proceedingsof SPIE-The International Society for Optical Engineering,2003:162-172P
[13] P. F. Fantoni, M. I. Hoffmann, R. Shankar, E. L. Daviso. On-line monitoring ofinstrument channel performance in nuclear power plant using peano[C]. InternationalConference on Nuclear Engineering,2002:109-113P
[14] Roverso Davide. Plant diagnostics by transient classification: the ALADDINapproach[J]. International Journal of Intelligent Systems,2002(8):767-790P
[15] Kyung H. Cha, Hyun C. Lee, Won M.Park. A cooperative real-time simulation forgeneric PWR nuclear plant[C]. Proceedings NPIC&HMIT96,1996:197-202P
[16] Leger, R.P., Garland, Wm. J., Poehlman, W.F.S. Fault detection and diagnosis usingstatistical control charts and artificial neural networks[J], Artificial Intelligence inEngineering,1998:35-47P
[17] Mo, Kun, Lee, Seung Jun, Seong, Poong Hyun. A dynamic neural network aggregationmodel for transient diagnosis in nuclear power plants[J]. Progress in Nuclear Energy,2007:262-272P
[18] Serhat-Seker, Emine Ayaz, Erdin T.urkcan. Elman’s recurrent neural networkapplications to condition monitoring in nuclear power plant and rotating machinery[J].Engineering Applications of Artificial Intelligence,2003:647-656P
[19] Patton R J, Chen J. Review of parity space approaches to fault diagnosis for aerogpacesystem[J]. Journal of Guidance, Control and Dynamics,1994,17(2):278-285P
[20] S. Weiss, C. Kulikowski. Computer systems that learn: classification and predictionmethods from statistics, neural nets, machine learning, and expert systems[M]. MorganKaufmann Publishers Inc. San Francisco, CA, USA,1991:1-25P
[21] A. Freitas. A genetic programming framework for two data mining tasks:classificationand generalized rule induction[J]. Genetic programming,1997:96-101P
[22] X. Yin, J. Han. CPAR: Classification based on predictive association rules[C]. Pro-ceedings of the third SIAM international conference on data mining,2003:331-335P
[23] J. Grabmeier, A. Rudolph. techniques of cluster algorithms in data mining[J]. DataMining and Knowledge Discovery,2002,6(4):303-360P
[24] R. Ng, J. Han. Efficient and effective clustering methods for spatial data mining[C].Proceedings of the International Conference on Very Large Data Bases,1994:144-144P
[25] P. Bradley, U. Fayyad, C. Reina, et al. Scaling clustering algorithms to largedatabases[J]. Knowledge Discovery and Data Mining,1998:9-15P
[26]蔡伟杰，张晓辉．关联规则挖掘综述[J]．计算机工程，2001，27(005)：31-33页
[27] R. Agrawal, R. Srikant. Fast algorithms for mining association rules[C]. Proc.20th Int.Conf. Very Large Data Bases, VLDB.1994,1215:487-499P
[28]陈昊，王熙照，袁方，湛燕．Lazy和Eager分类算法的比较研究[J]．计算机工程与应用，2004,40(004)：72-73页
[29] Z. Liu, W. Wang, Y. Zhang. Research on eager classification and lazy classification[J].Minimicro Systems,2002,23(12):1489-1491P
[30] A. Veloso, W. Meira Jr. Eager. Lazy and hybrid algorithms for multi-criteria associativeclassification[C]. Anais do Workshop sobre Algoritmos de Mineracao de Dados(WAMD).2005:17-25P
[31] W. McCulloch, W. Pitts. A logical calculus of the ideas immanent in nervous activity[J].Bulletin of Mathematical Biology,1943,5(4):115-133P
[32] Shu-Hsien Liao, Chih-Hao Wen. Artificial neural networks classification and clusteringof methodologies and applications–literature analysis from1995to2005[J]. ExpertSystems with Applications,2007(32):1-11P
[33] Vapnik V. N. Statistical learning theory[M]. Wiley. New York.1998.
[34] Nello Cristianini, John Shawe-Taylor著，李国正,王猛,曾华军译．支持向量机导论[M]，电子工业出版社，2004
[35]翟永杰．基于支持向量机的故障智能诊断方法研究[D]．华北电力大学博士论文，2004
[36]孙卫祥等．基于PCA与决策树的转子故障诊断[J]．振动与冲击，2007，26(3)：72-74页
[37]韩泉东，胡小平，王艳梅．基于决策树方法的液体火箭发动机稳态段故障诊断[J]．火箭推进，2007，33(3)：26-30页
[38]韩泉东，胡小平，李京浩．结合动态时间弯曲与决策树方法的液体火箭发动机故障诊断[J]．国防科技大学学报，2007，29(4)：1-5页
[39]徐金良，张大发，张龙飞．基于粗糙决策模型的核电厂故障诊断方法[J]．核动力工程，2007,28(4)：81-84页
[40]胡笑旋．贝叶斯网建模技术及其在决策中的应用[D]．合肥工业大学博士论文，2006
[41] M. Wellman, J. Breese, R. Goldman. From knowledge bases to decision models[J]. TheKnowledge Engineering Review,2009,7(01):35-53P
[42] Z. Pawlak. Rough sets[J]. International Journal of Computer and Information Sciences.1982,11(5):341-356P
[43] L. A. Zadeh. Toward a theory of fuzzy information granulation and its centrality inhuman reasoning and fuzzy logic[J]. Fuzzy Set and System.1997,90(2):111-127P
[44]张铃，张钹．模糊商空间理论(模糊粒度计算方法)[J]．软件学报，2003,14(4)：770-776页
[45] A. Skowron, C. Rauszer. The discernibility matrics and functions in information system.R. Slowinski (Eds.). Intelligent Decision Support: Handbook of Applications andAdvances of the Rough Sets Theory. Kluwer Academic Publishers, Dordrecht,1992:331-362P
[46] J. W. Guan, D. A. Bell. Matrix computation for information system[J]. InformationSciences.2001,131:129-256P
[47] Z. Y. Xu, C. Q. Zhang, S. C. Zhang, W. Song, B. R. Yang. Efficient attribute reductionbased on discernibility matrix[J]. Lecture Notes in Artificial Intelligence.2006,4481:13-21P
[48] S. K. M. Wong, W. Ziarko. On optimal decision rules in decision tables[J]. Bulletin ofPolish Academy of Sciences.1985,33:693-696P
[49] W. Ziarko. The discovery, analysis and representation of data dependencies indatabases[C]. Knowledge Discovery in Databases. AAAI MIT Press, Cambrige, MA,1993:213-228P
[50] D. Q. Miao, L. S. Hou. A heuristic algorithm for reduction of knowledge based ondiscernibility matrix[C]. Proceedings of the International Conference on IntelligenceInformation Technology, Beijing, China,2002:276-279P
[51] X. H. Hu, N. Cercone. Learning in relational databases: a rough set approach[J].Computational Intelligence.1995,11(2):323-338P
[52] J. Jelonek, K. Krawiec, R. Slowinski. Rough set reduction of attributes and theirdomains for neural networks[J]. Computational Intelligence.1995,11(2):339-347P
[53] G. Michal, S. Jacek. RSL-The rough set library version2.0[C]. ICS Research Report,Warsaw University of Technology.1994:1-19P
[54]徐章艳，刘作鹏，杨炳儒，宋威．一个复杂度为max(O(|C||U|), O(|C|2|U/C|))的快速属性约简算法[J]．计算机学报，2006,29(3)：391-399页
[55] I. Duntsch, G. Gediga. Uncertainty measures of rough set prediction[J]. ArtificialIntelligence.1998,106(1):109-137P
[56] D. Q. Miao, J. Wang. An information-based algorithm for reduction of knowledge[C].Proceedings of the IEEE International Conference on Intelligent Processing Systems,Beijing, China,1997,10:1155-1158P
[57]王国胤，于洪，杨大春．基于条件信息熵的决策表约简[J]．计算机学报，2002,25(7)：759-766页
[58] G. Y. Wang. Rough reduction, in algebra view and information view[J]. InternationalJournal of Intelligent Systems.2003,18(6):679-688P
[59] G. Y. Wang, J. Zhao, J. J. An, Y. Wu. A comparative study of algebra viewpoint andinformation viewpoint in attribute reduction[J]. Fundamenta Informaticae.2005,68(3):289-301P
[60] X. Y. Wang, J. Yang, N. S. Peng, X. L. Teng. Finding minimal rough set reducts withparticle swarm optimization[J]. Lecture Notes in Computer Science.2005,3641:451-460P
[61] J. Wroblewski. Finding Minimal Reducts Using genetic algorithms[C]. Proceedings ofthe2ndJoint Annual Conference on Information Sciences, Wrightsville Beach, NC,USA,1995:186-189P
[62] F. Min, X. H. Du, H. Qiu, Q. H. Liu. Minimal attribute space bias for attributereduction[J]. Lecture Notes in Computer Science.2007,4481:379-386P
[63]叶东毅．Jelonek属性约简算法的一个改进[J]．电子学报，2000,28(12)：81-82页
[64] T. Beaubouef, F. Petry, G. Arora. Information-theoretic measures of uncertainty forrough sets and rough relational databases[J]. Information Sciences.1998:185-195P
[65] B Huang. X. He, X. Z. Zhou. Rough entropy based on generalized rough sets coveringreduction[J]. Journal of Software.2004,15(2):215-220P
[66] J. Liang, Z. Shi, D. Li, M. J. Wierman. Information entropy, rough entropy andknowledge granulation in incomplete information systems[J]. International Journal ofGeneral Systems.2006,35(6):641-654P
[67] W. H. Xu, H. Z. Yang, W. X. Zhang. Uncertainty measures of roughness of knowledgeand rough sets in ordered information systems[J]. Lecture Notes in Computer Science.2007,4682:759-769P
[68]刘少辉，盛秋戬，吴斌等．Rough集的高效学习算法[J]．计算机学报，2003,26(5)：1-6页
[69] D. Slezak. Approximate reducts in decision tables[C]. B. Bouchon-Meunier, M.Delgado, J. L. Verdegay, M. A. Vila, R. R. Yager (Eds.). Proceedings of the6thInternational Conference on Information Processing and Management of Uncertaintyin Knowledge-based System, Granada, Spain,1996:1159-1164P
[70] D. Slezak. Approximate entropy reducts[J]. Fundamenta Informaticae.2002,53(3-4):365-390P
[71] J. Bazan, A. Skowron, P. Synak. Dynamic reducts as a tool for extracting laws fromdecision tables[C]. Z. W. Ras, M. Zmankiva (Eds.). Proceedings of Symposium onMethodologies for Intelligent Systems. Springer-Verlag Berlin, Heidelberg,1994:346-355P
[72] J. Bazan. A comparision of dynamic and non-dynamic rough set methods for extractinglaws from decison tables[C]. L. Polkowski, A. Skowron (Eds.). Rough Sets inKnowledge Discovery. Phisica-Verlag, Heidelberg,1998:321-365P
[73] M. Kryszkiewicz. Comparative study of alternative type of knowledge reduction ininconsistent systems[J]. International Journal of Intelligent Systems.2001:105-120P
[74] J. Y. Liang, Z. B. Xu. The algorithm on knowledge reduction in incomplete informationsystems[J]. International Journal of Uncertainty, Fuzziness and Knowledge-BasedSystems.2002,10:95-103P
[75]张文修，米据生，吴伟志．不协调目标信息系统的知识约简[J]．计算机学报，2003,21(6)：12-18页
[76] D. G. Chen, C. Z. Wang, Q. H. Hu. A new approach to attribute reduction of consistentand inconsistent covering decision systems with covering rough sets[J]. InformationSciences.2007,177(17):3500-3518P
[77] R. Nowichi, R. Slowinski, J. Stefanowski. Evaluation of vibroacoustic diagnosticsymptoms by means of the rough sets theory[J]. Computers in Industry.1992,20:141-152P
[78]于刚，徐治皋．电站故障诊断系统中信号缺失处理的粗糙集方法[J]．华东电力，2004(06)：351-354页
[79]陈志辉，夏虹，黄伟．Rough集理论及其在核动力故障诊断中的应用[J]．核动力工程，2006(6)：82-86页
[80]苏宏升，李群湛．基于粗糙集理论和神经网络模型的变电站故障诊断方法[J]．电网技术，2005(16)：66-70页
[81]徐金良，陈五星，唐耀阳．基于粗糙集理论和支持向量机算法的核电厂故障诊断方法[J]．核动力工程，2009(4)：52-54页
[82] Hansen L K,Salamon R. Neural network ensembles[C]. IEEEE Transactions on PatternAnalysis and Machine Intelligence.1990,12(10):993-1001P
[83] Sollieh P, Krough A. Learning with ensembles: how over-fitting can be useful [J].Advances in Neural Information Processing Systems, MIT Press.1996:190-196P
[84]黄鑫．基于序列数据的太阳耀斑预报方法研究[D]．哈尔滨工业大学博士论文，2010
[85] Sejnowski, T.J. and C.R. Rosenberg. parallel networks that learn to pronounce englishtext[J]. Complex Systems.1987,1(1):45-168P
[86] Qian, N. and T.J. Sejnowski. Predicting the secondary structure of globular proteinsusing neural network models[C]. J. Mol. Biol.1988,202(4):65-88P
[87] Bakiri, G. and T.G. Dietterich, Achieving high-accuracy text-to-speech with machinelearning[J]. Data mining in speech synthesis.1999(10)
[88] Rabiner, L.R. A tutorial on hidden markov models and selected applications inspeechrecognition[C]. Proceedings of the IEEE.1989.77(2):257-286P
[89] Baker, J.K. Stochastic modeling for automatic speech understanding[J]. Readings inSpeech Recognition Table of Contents.1990:297-307P
[90] Elinek, F. Continuous speech recognition by statistical methods[C]. Proceedings of theIEEE.1976,64(4):532-556P
[91] Schenkel, M., et al. Recognition-based segmentation of on-line hand-printed words.Advances in Neural Information Processing Systems[C].5[NIPS Conference] table ofcontents.1992:723-730P
[92] Schenkel, M., I. Guyon, and D. Henderson, On-line cursive script recognition usingtime-delay neural networks and hidden Markov models[J]. Machine Vision andApplications.1995,8(4):215-223P
[93] Bengio, Y., et al. LeRec: ANN/HMM Hybrid for on-line handwriting recognition[J].Neural Computation.1995.7(6):1289-1303P
[94] Baldi, P., et al. Hidden Markov models of biological primary sequence information[C].Proceedings of the National Academy of Sciences of the United States of America.1994,91(3):1059-1063P
[95] Baldi, P. and Y. Chauvin. Hidden markov models of the g-protein-coupled receptorfamily[J]. J Comput Biol,1994.1(4):311-316P
[96] Karplus, K., et al. Predicting protein structure using hidden markov models[J]. Proteins.1997(1):134-139P
[97] Garcia, R. and P. Perron. An analysis of the real interest rate under regime shifts.Review of Economics and Statistics[J].1996,78(1):111-125P
[98]张文修，吴伟志，梁吉业等．粗糙集理论与方法[M]．科学出版社，2001：123-130页
[99] M. Dash, H. Liu. Consistency-based Search in Feature Selection[J]. ArtificialIntelligence.2003,151(1-2):155-176P
[100]胡清华．混合数据知识发现的粗糙计算模型和算法[D]．哈尔滨工业大学博士论文，2008
[101] T.M. Mitchell原著，曾华军，张银奎译．机器学习[M]．北京：机械工业出版社，2003：48-55页
[102] I. Guyon, A. Elisseeff. An introduction to variable and feature selection[J]. Journal ofmachine learning research.2003(3):1157-1182P
[103] L. Yu, H. Liu. Efficient feature selection via analysis of relevance and redundancy[J].Journal of Machine Learning Research.2004,5:1205-1224P
[104] T. K. Ho, M Basu. Complexity measures of supervised classification problems[C].IEEE Transactions on pattern analysis and machine intelligence.2002,24(3):289-300P
[105]胡清华，赵辉，于达仁．基于邻域粗糙集的符号与数值属性快速约简算法[J]．模式识别与人工智能，2008,21(6)：732-738页
[106] T. Dietterich. Ensemble methods in machine learning[J]. Lecture Notes in ComputerScience.2000:1-15P
[107] L. Breiman. Bagging predictors[J]. Machine learning.1996,24(2):123-140P
[108] Y. Freund, R. Schapire. Experiments with a new boosting algorithm[C]. InProceedings of the Thirteenth International Conference on Machine Learning.1996:148-156P
[109] T. Ho. The random subspace method for constructing decision forests[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(8):832–844P
[110] K. Tumer, N. Oza. Input decimated ensembles[J]. Pattern Analysis&Applications,2003,6(1):65-77P
[111] T. Dietterich, G. Bakiri. Solving Multiclass Learning problems via error-correctingoutput codes[J]. Journal of Artificial Intelligence Research.1995(2):263-286P
[112] T. Dietterich. An experimental comparison of three methods for constructingensembles of decision trees: bagging, boosting, and randomization[J]. Machinelearning.2000,40(2):139-157P
[113] J. Kitler, M. Hatef, R. Duin, J. Matas. On combining classifiers[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.1998,20(3):226-239P
[114] L. Kuncheva. Combining pattern classifiers: methods and algorithms[M]. WileyInterscience.2004:110-132P
[115]胡蜂，钱光岷．基于滑动时窗的小波变换实时算法[J]．信号处理，2007(6)：361-364页
[2]陈进，机械设备故障诊断技术及其应用[M]．上海高教电子音像出版社，2003
[3]侯澍旻．时序数据挖掘及其在故障诊断中的应用研究[D].武汉科技大学博士论文，2006年10月：3-4页
[4]余红英．机械系统故障信号特征提取技术研究[D]．中北大学博士论文，2005：3-4页
[5] Jong Hyun Kim, Poong Hyun Seong. A methodology for the quantitative evaluationof NPP fault diagnostic systems dynamic aspects[J]. Annals of Nuclear Energy，2000，27:1459-1481P
[6]张晓华，奚树人．核电站故障诊断专家系统综述[J]．核动力工程，1999，20(3)：264-273页
[7] Reifman Jaques, Wei Thomas Y.C. PRODIAG: A process-independent transientdiagnostic system-I: Theoretical concepts[J]. Nuclear Science and Engineering,1999,131(3):329-347P
[8] Reifman, Jaques; Wei, Thomas Y.C. PRODIAG: A process-independent transientdiagnostic system-II: Validation tests[J]. Nuclear Science and Engineering,1999,131(3):348-369P
[9] Reifman Jaques, Glenn E. GRAHAM, Wei Thomas Y.C. F. Exible human machineinterface for process diagnositic[C]. Proceedings NPIC&HMIT’96,1996:1437-1444P
[10] Dieter Wach, Werner Bastl. On-line condition monitoring of large rotating machineryin NPPs[C]. Proceedings NPIC&HMIT’96.1996:1313-1320P
[11] Fantoni, Paolo F. Experiences and applications of PEANO for online monitoring inpower plants. Progress in Nuclear Energy, Computational Intelligence in NuclearApplications: Lessons Learned and Recent Developments,2005:206-225P
[12] Davide Roverso. Fault diagnosis with the Aladdin transient classifier[C]. Proceedingsof SPIE-The International Society for Optical Engineering,2003:162-172P
[13] P. F. Fantoni, M. I. Hoffmann, R. Shankar, E. L. Daviso. On-line monitoring ofinstrument channel performance in nuclear power plant using peano[C]. InternationalConference on Nuclear Engineering,2002:109-113P
[14] Roverso Davide. Plant diagnostics by transient classification: the ALADDINapproach[J]. International Journal of Intelligent Systems,2002(8):767-790P
[15] Kyung H. Cha, Hyun C. Lee, Won M.Park. A cooperative real-time simulation forgeneric PWR nuclear plant[C]. Proceedings NPIC&HMIT96,1996:197-202P
[16] Leger, R.P., Garland, Wm. J., Poehlman, W.F.S. Fault detection and diagnosis usingstatistical control charts and artificial neural networks[J], Artificial Intelligence inEngineering,1998:35-47P
[17] Mo, Kun, Lee, Seung Jun, Seong, Poong Hyun. A dynamic neural network aggregationmodel for transient diagnosis in nuclear power plants[J]. Progress in Nuclear Energy,2007:262-272P
[18] Serhat-Seker, Emine Ayaz, Erdin T.urkcan. Elman’s recurrent neural networkapplications to condition monitoring in nuclear power plant and rotating machinery[J].Engineering Applications of Artificial Intelligence,2003:647-656P
[19] Patton R J, Chen J. Review of parity space approaches to fault diagnosis for aerogpacesystem[J]. Journal of Guidance, Control and Dynamics,1994,17(2):278-285P
[20] S. Weiss, C. Kulikowski. Computer systems that learn: classification and predictionmethods from statistics, neural nets, machine learning, and expert systems[M]. MorganKaufmann Publishers Inc. San Francisco, CA, USA,1991:1-25P
[21] A. Freitas. A genetic programming framework for two data mining tasks:classificationand generalized rule induction[J]. Genetic programming,1997:96-101P
[22] X. Yin, J. Han. CPAR: Classification based on predictive association rules[C]. Pro-ceedings of the third SIAM international conference on data mining,2003:331-335P
[23] J. Grabmeier, A. Rudolph. techniques of cluster algorithms in data mining[J]. DataMining and Knowledge Discovery,2002,6(4):303-360P
[24] R. Ng, J. Han. Efficient and effective clustering methods for spatial data mining[C].Proceedings of the International Conference on Very Large Data Bases,1994:144-144P
[25] P. Bradley, U. Fayyad, C. Reina, et al. Scaling clustering algorithms to largedatabases[J]. Knowledge Discovery and Data Mining,1998:9-15P
[26]蔡伟杰，张晓辉．关联规则挖掘综述[J]．计算机工程，2001，27(005)：31-33页
[27] R. Agrawal, R. Srikant. Fast algorithms for mining association rules[C]. Proc.20th Int.Conf. Very Large Data Bases, VLDB.1994,1215:487-499P
[28]陈昊，王熙照，袁方，湛燕．Lazy和Eager分类算法的比较研究[J]．计算机工程与应用，2004,40(004)：72-73页
[29] Z. Liu, W. Wang, Y. Zhang. Research on eager classification and lazy classification[J].Minimicro Systems,2002,23(12):1489-1491P
[30] A. Veloso, W. Meira Jr. Eager. Lazy and hybrid algorithms for multi-criteria associativeclassification[C]. Anais do Workshop sobre Algoritmos de Mineracao de Dados(WAMD).2005:17-25P
[31] W. McCulloch, W. Pitts. A logical calculus of the ideas immanent in nervous activity[J].Bulletin of Mathematical Biology,1943,5(4):115-133P
[32] Shu-Hsien Liao, Chih-Hao Wen. Artificial neural networks classification and clusteringof methodologies and applications–literature analysis from1995to2005[J]. ExpertSystems with Applications,2007(32):1-11P
[33] Vapnik V. N. Statistical learning theory[M]. Wiley. New York.1998.
[34] Nello Cristianini, John Shawe-Taylor著，李国正,王猛,曾华军译．支持向量机导论[M]，电子工业出版社，2004
[35]翟永杰．基于支持向量机的故障智能诊断方法研究[D]．华北电力大学博士论文，2004
[36]孙卫祥等．基于PCA与决策树的转子故障诊断[J]．振动与冲击，2007，26(3)：72-74页
[37]韩泉东，胡小平，王艳梅．基于决策树方法的液体火箭发动机稳态段故障诊断[J]．火箭推进，2007，33(3)：26-30页
[38]韩泉东，胡小平，李京浩．结合动态时间弯曲与决策树方法的液体火箭发动机故障诊断[J]．国防科技大学学报，2007，29(4)：1-5页
[39]徐金良，张大发，张龙飞．基于粗糙决策模型的核电厂故障诊断方法[J]．核动力工程，2007,28(4)：81-84页
[40]胡笑旋．贝叶斯网建模技术及其在决策中的应用[D]．合肥工业大学博士论文，2006
[41] M. Wellman, J. Breese, R. Goldman. From knowledge bases to decision models[J]. TheKnowledge Engineering Review,2009,7(01):35-53P
[42] Z. Pawlak. Rough sets[J]. International Journal of Computer and Information Sciences.1982,11(5):341-356P
[43] L. A. Zadeh. Toward a theory of fuzzy information granulation and its centrality inhuman reasoning and fuzzy logic[J]. Fuzzy Set and System.1997,90(2):111-127P
[44]张铃，张钹．模糊商空间理论(模糊粒度计算方法)[J]．软件学报，2003,14(4)：770-776页
[45] A. Skowron, C. Rauszer. The discernibility matrics and functions in information system.R. Slowinski (Eds.). Intelligent Decision Support: Handbook of Applications andAdvances of the Rough Sets Theory. Kluwer Academic Publishers, Dordrecht,1992:331-362P
[46] J. W. Guan, D. A. Bell. Matrix computation for information system[J]. InformationSciences.2001,131:129-256P
[47] Z. Y. Xu, C. Q. Zhang, S. C. Zhang, W. Song, B. R. Yang. Efficient attribute reductionbased on discernibility matrix[J]. Lecture Notes in Artificial Intelligence.2006,4481:13-21P
[48] S. K. M. Wong, W. Ziarko. On optimal decision rules in decision tables[J]. Bulletin ofPolish Academy of Sciences.1985,33:693-696P
[49] W. Ziarko. The discovery, analysis and representation of data dependencies indatabases[C]. Knowledge Discovery in Databases. AAAI MIT Press, Cambrige, MA,1993:213-228P
[50] D. Q. Miao, L. S. Hou. A heuristic algorithm for reduction of knowledge based ondiscernibility matrix[C]. Proceedings of the International Conference on IntelligenceInformation Technology, Beijing, China,2002:276-279P
[51] X. H. Hu, N. Cercone. Learning in relational databases: a rough set approach[J].Computational Intelligence.1995,11(2):323-338P
[52] J. Jelonek, K. Krawiec, R. Slowinski. Rough set reduction of attributes and theirdomains for neural networks[J]. Computational Intelligence.1995,11(2):339-347P
[53] G. Michal, S. Jacek. RSL-The rough set library version2.0[C]. ICS Research Report,Warsaw University of Technology.1994:1-19P
[54]徐章艳，刘作鹏，杨炳儒，宋威．一个复杂度为max(O(|C||U|), O(|C|2|U/C|))的快速属性约简算法[J]．计算机学报，2006,29(3)：391-399页
[55] I. Duntsch, G. Gediga. Uncertainty measures of rough set prediction[J]. ArtificialIntelligence.1998,106(1):109-137P
[56] D. Q. Miao, J. Wang. An information-based algorithm for reduction of knowledge[C].Proceedings of the IEEE International Conference on Intelligent Processing Systems,Beijing, China,1997,10:1155-1158P
[57]王国胤，于洪，杨大春．基于条件信息熵的决策表约简[J]．计算机学报，2002,25(7)：759-766页
[58] G. Y. Wang. Rough reduction, in algebra view and information view[J]. InternationalJournal of Intelligent Systems.2003,18(6):679-688P
[59] G. Y. Wang, J. Zhao, J. J. An, Y. Wu. A comparative study of algebra viewpoint andinformation viewpoint in attribute reduction[J]. Fundamenta Informaticae.2005,68(3):289-301P
[60] X. Y. Wang, J. Yang, N. S. Peng, X. L. Teng. Finding minimal rough set reducts withparticle swarm optimization[J]. Lecture Notes in Computer Science.2005,3641:451-460P
[61] J. Wroblewski. Finding Minimal Reducts Using genetic algorithms[C]. Proceedings ofthe2ndJoint Annual Conference on Information Sciences, Wrightsville Beach, NC,USA,1995:186-189P
[62] F. Min, X. H. Du, H. Qiu, Q. H. Liu. Minimal attribute space bias for attributereduction[J]. Lecture Notes in Computer Science.2007,4481:379-386P
[63]叶东毅．Jelonek属性约简算法的一个改进[J]．电子学报，2000,28(12)：81-82页
[64] T. Beaubouef, F. Petry, G. Arora. Information-theoretic measures of uncertainty forrough sets and rough relational databases[J]. Information Sciences.1998:185-195P
[65] B Huang. X. He, X. Z. Zhou. Rough entropy based on generalized rough sets coveringreduction[J]. Journal of Software.2004,15(2):215-220P
[66] J. Liang, Z. Shi, D. Li, M. J. Wierman. Information entropy, rough entropy andknowledge granulation in incomplete information systems[J]. International Journal ofGeneral Systems.2006,35(6):641-654P
[67] W. H. Xu, H. Z. Yang, W. X. Zhang. Uncertainty measures of roughness of knowledgeand rough sets in ordered information systems[J]. Lecture Notes in Computer Science.2007,4682:759-769P
[68]刘少辉，盛秋戬，吴斌等．Rough集的高效学习算法[J]．计算机学报，2003,26(5)：1-6页
[69] D. Slezak. Approximate reducts in decision tables[C]. B. Bouchon-Meunier, M.Delgado, J. L. Verdegay, M. A. Vila, R. R. Yager (Eds.). Proceedings of the6thInternational Conference on Information Processing and Management of Uncertaintyin Knowledge-based System, Granada, Spain,1996:1159-1164P
[70] D. Slezak. Approximate entropy reducts[J]. Fundamenta Informaticae.2002,53(3-4):365-390P
[71] J. Bazan, A. Skowron, P. Synak. Dynamic reducts as a tool for extracting laws fromdecision tables[C]. Z. W. Ras, M. Zmankiva (Eds.). Proceedings of Symposium onMethodologies for Intelligent Systems. Springer-Verlag Berlin, Heidelberg,1994:346-355P
[72] J. Bazan. A comparision of dynamic and non-dynamic rough set methods for extractinglaws from decison tables[C]. L. Polkowski, A. Skowron (Eds.). Rough Sets inKnowledge Discovery. Phisica-Verlag, Heidelberg,1998:321-365P
[73] M. Kryszkiewicz. Comparative study of alternative type of knowledge reduction ininconsistent systems[J]. International Journal of Intelligent Systems.2001:105-120P
[74] J. Y. Liang, Z. B. Xu. The algorithm on knowledge reduction in incomplete informationsystems[J]. International Journal of Uncertainty, Fuzziness and Knowledge-BasedSystems.2002,10:95-103P
[75]张文修，米据生，吴伟志．不协调目标信息系统的知识约简[J]．计算机学报，2003,21(6)：12-18页
[76] D. G. Chen, C. Z. Wang, Q. H. Hu. A new approach to attribute reduction of consistentand inconsistent covering decision systems with covering rough sets[J]. InformationSciences.2007,177(17):3500-3518P
[77] R. Nowichi, R. Slowinski, J. Stefanowski. Evaluation of vibroacoustic diagnosticsymptoms by means of the rough sets theory[J]. Computers in Industry.1992,20:141-152P
[78]于刚，徐治皋．电站故障诊断系统中信号缺失处理的粗糙集方法[J]．华东电力，2004(06)：351-354页
[79]陈志辉，夏虹，黄伟．Rough集理论及其在核动力故障诊断中的应用[J]．核动力工程，2006(6)：82-86页
[80]苏宏升，李群湛．基于粗糙集理论和神经网络模型的变电站故障诊断方法[J]．电网技术，2005(16)：66-70页
[81]徐金良，陈五星，唐耀阳．基于粗糙集理论和支持向量机算法的核电厂故障诊断方法[J]．核动力工程，2009(4)：52-54页
[82] Hansen L K,Salamon R. Neural network ensembles[C]. IEEEE Transactions on PatternAnalysis and Machine Intelligence.1990,12(10):993-1001P
[83] Sollieh P, Krough A. Learning with ensembles: how over-fitting can be useful [J].Advances in Neural Information Processing Systems, MIT Press.1996:190-196P
[84]黄鑫．基于序列数据的太阳耀斑预报方法研究[D]．哈尔滨工业大学博士论文，2010
[85] Sejnowski, T.J. and C.R. Rosenberg. parallel networks that learn to pronounce englishtext[J]. Complex Systems.1987,1(1):45-168P
[86] Qian, N. and T.J. Sejnowski. Predicting the secondary structure of globular proteinsusing neural network models[C]. J. Mol. Biol.1988,202(4):65-88P
[87] Bakiri, G. and T.G. Dietterich, Achieving high-accuracy text-to-speech with machinelearning[J]. Data mining in speech synthesis.1999(10)
[88] Rabiner, L.R. A tutorial on hidden markov models and selected applications inspeechrecognition[C]. Proceedings of the IEEE.1989.77(2):257-286P
[89] Baker, J.K. Stochastic modeling for automatic speech understanding[J]. Readings inSpeech Recognition Table of Contents.1990:297-307P
[90] Elinek, F. Continuous speech recognition by statistical methods[C]. Proceedings of theIEEE.1976,64(4):532-556P
[91] Schenkel, M., et al. Recognition-based segmentation of on-line hand-printed words.Advances in Neural Information Processing Systems[C].5[NIPS Conference] table ofcontents.1992:723-730P
[92] Schenkel, M., I. Guyon, and D. Henderson, On-line cursive script recognition usingtime-delay neural networks and hidden Markov models[J]. Machine Vision andApplications.1995,8(4):215-223P
[93] Bengio, Y., et al. LeRec: ANN/HMM Hybrid for on-line handwriting recognition[J].Neural Computation.1995.7(6):1289-1303P
[94] Baldi, P., et al. Hidden Markov models of biological primary sequence information[C].Proceedings of the National Academy of Sciences of the United States of America.1994,91(3):1059-1063P
[95] Baldi, P. and Y. Chauvin. Hidden markov models of the g-protein-coupled receptorfamily[J]. J Comput Biol,1994.1(4):311-316P
[96] Karplus, K., et al. Predicting protein structure using hidden markov models[J]. Proteins.1997(1):134-139P
[97] Garcia, R. and P. Perron. An analysis of the real interest rate under regime shifts.Review of Economics and Statistics[J].1996,78(1):111-125P
[98]张文修，吴伟志，梁吉业等．粗糙集理论与方法[M]．科学出版社，2001：123-130页
[99] M. Dash, H. Liu. Consistency-based Search in Feature Selection[J]. ArtificialIntelligence.2003,151(1-2):155-176P
[100]胡清华．混合数据知识发现的粗糙计算模型和算法[D]．哈尔滨工业大学博士论文，2008
[101] T.M. Mitchell原著，曾华军，张银奎译．机器学习[M]．北京：机械工业出版社，2003：48-55页
[102] I. Guyon, A. Elisseeff. An introduction to variable and feature selection[J]. Journal ofmachine learning research.2003(3):1157-1182P
[103] L. Yu, H. Liu. Efficient feature selection via analysis of relevance and redundancy[J].Journal of Machine Learning Research.2004,5:1205-1224P
[104] T. K. Ho, M Basu. Complexity measures of supervised classification problems[C].IEEE Transactions on pattern analysis and machine intelligence.2002,24(3):289-300P
[105]胡清华，赵辉，于达仁．基于邻域粗糙集的符号与数值属性快速约简算法[J]．模式识别与人工智能，2008,21(6)：732-738页
[106] T. Dietterich. Ensemble methods in machine learning[J]. Lecture Notes in ComputerScience.2000:1-15P
[107] L. Breiman. Bagging predictors[J]. Machine learning.1996,24(2):123-140P
[108] Y. Freund, R. Schapire. Experiments with a new boosting algorithm[C]. InProceedings of the Thirteenth International Conference on Machine Learning.1996:148-156P
[109] T. Ho. The random subspace method for constructing decision forests[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(8):832–844P
[110] K. Tumer, N. Oza. Input decimated ensembles[J]. Pattern Analysis&Applications,2003,6(1):65-77P
[111] T. Dietterich, G. Bakiri. Solving Multiclass Learning problems via error-correctingoutput codes[J]. Journal of Artificial Intelligence Research.1995(2):263-286P
[112] T. Dietterich. An experimental comparison of three methods for constructingensembles of decision trees: bagging, boosting, and randomization[J]. Machinelearning.2000,40(2):139-157P
[113] J. Kitler, M. Hatef, R. Duin, J. Matas. On combining classifiers[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.1998,20(3):226-239P
[114] L. Kuncheva. Combining pattern classifiers: methods and algorithms[M]. WileyInterscience.2004:110-132P
[115]胡蜂，钱光岷．基于滑动时窗的小波变换实时算法[J]．信号处理，2007(6)：361-364页
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |