数据挖掘方法在电力电缆状态评估中的应用研究
|
摘要
供电线路中的电缆所占的比重很大,工业、企业部门所使用的电缆在运行一段时间后,由于各种原因会发生老化,留下事故隐患,如不及时采取措施可能造成重大的经济损失。电缆的绝缘状态通常可以分为良好、不好、差和故障四种,以电缆的日常检修数据、试验数据和在线监测数据为基础,对电缆的状态进行评估具有重要的工程价值和实用意义。数据挖掘是从大量数据中挖掘出隐含的、先前未知的、对决策有潜在价值的知识和规则。为了保证系统的完整性,易于集成,本文在开发高精度的电缆状态监测装置基础上,利用有线、无线通讯以及网络技术收集数据,利用数据挖掘手段对电缆的状态进行评估。主要工作及结论如下:
①对电力电缆绝缘系统的老化机理,及其状态检测方法做了概述。介绍了数据挖掘技术的分类及其在电力行业中的应用。
②介绍了附加低频信号的在线检测原理和实现方式。由于泄露电流和介质损失正切tanδ具有代表性,故本文采用低频信号迭加方法,利用傅立叶变换技术对低频泄露电流和介质损失正切角进行计算,并将测量数据通过SCADA系统传输到数据分析工作站中进行分析。
③运用数据挖掘理论对孤立点和中心点进行挖掘。对于数据的不一致性和空缺数据问题,本文采用基于回归技术的空缺值填充方法来提高数据挖掘的质量。
④阐述了在线时序数据挖掘的神经网络分析方法。首先运用简单的线性和正弦模型对时序数据的变化趋势进行预测,此后采用三层的前向神经网络模型,在隐层神经元数量的判断上采用将离散变量进行连续化的松弛优化算法,并按照BP算法将神经元的数据与权重系数一起进行训练,取得了较好的效果。
⑤论述了基于决策树技术的电缆绝缘状态评估方法。将决策树技术应用于电缆绝缘状态的判断中,得到电缆在线和离线实验数据之间的关联性不是很大,可以单独形成决策子树;对子树的合成必须有相关联的属性,这种相关联的属性可以转化为一个可以结合两棵子树的公共属性;对于电缆的在线监测数据,由于受运行环境的影响,并没有确切的判断电缆绝缘状态的标准,在形成分类规则时必须选取那些能够根据经验或离线试验确定状态的数据集合。
通过实际电缆的各种数据,采用SPSS软件进行实际应用,最终的仿真结果说明数据挖掘方法的应用能够精确地评估出电力电缆状态。
The cables take up a large proportion in power supply line. The cables used in industry and the business sector in operation for some time will appear aging and hidden trouble for accident. It may cause significant economic losses if not taking timely measures. The cable insulation condition is usually can be divided into good, not good, bad and the failure. Assessing the cable status on the basis of the daily maintenance data, test data and on-line monitoring data has a momentous engineering value and practical significance.
Data mining finds out the connotative, unknown, and potentially valuable knowledge and rules. In order to ensure the integrity of systems, easy integration, on the basis of developing high-precision cable status monitoring device, using wired and wireless communications and Internet technologies to collect data and using data mining tools to assess the state of the cable. The main work and conclusions are as follows:
①The aging mechanism of power cable insulation system and its method for state detection were summarized. The sorts of data mining technology and its applications in power industry were introduced.
②The on-line detection theory and its realizing way of additional low frequency signal was introduced. Because of the leakage current and medium loss tangent value Xanδwere representative, This paper adopted the low frequency signal superposition method, and used the foutier transform technique to calculate the low frequency leakage current and the medium loss tangent value, and the measurement datas were transmited to the data analyzing workstation by the SCADA system.
③The data mining theory was used to finds out the isolated point and the center point. To the problem of data inconsistency and missing data, this paper adopted the regression technique of vacancy value filling method to improve the quality of data mining.
④The neural network analysis method of on line time sequence was described. Firstly, the liner and sine model were used to forecast the trend of the time sequence data, then adopted the three-layer feed-forward neural network model, the relaxed optimization algorithm was adopted to make the discrete variable continuous based on the judgement of the number of hidden neurons, lastly according to the BP atithmetic the nerve cell data and the weight coefficient were trained together.
⑤The cable insulation state evaluation method based on the decision tree technology was discussed, the decision tree technology was used to judge the cable insulation, and abtained that the relevance between the cable on line and the off line experimental data was not very big, so the decision subtrees could be formed alone. To the subtree compose there must has the correlation attribute, which can translate to a public attribute. The cable on line monitoring datas were affected by the running environment so they had no right standard to judge the cable insulation state. The stae data sets which can be confirmed according to the experience or off line experiments must be selected when forming the classification rule.
Through kinds of data of the actual cables, using SPSS software for actual application, the ultimate simulation results indicate that the application of data mining methods can accurately assess the state of the power cable.
①对电力电缆绝缘系统的老化机理,及其状态检测方法做了概述。介绍了数据挖掘技术的分类及其在电力行业中的应用。
②介绍了附加低频信号的在线检测原理和实现方式。由于泄露电流和介质损失正切tanδ具有代表性,故本文采用低频信号迭加方法,利用傅立叶变换技术对低频泄露电流和介质损失正切角进行计算,并将测量数据通过SCADA系统传输到数据分析工作站中进行分析。
③运用数据挖掘理论对孤立点和中心点进行挖掘。对于数据的不一致性和空缺数据问题,本文采用基于回归技术的空缺值填充方法来提高数据挖掘的质量。
④阐述了在线时序数据挖掘的神经网络分析方法。首先运用简单的线性和正弦模型对时序数据的变化趋势进行预测,此后采用三层的前向神经网络模型,在隐层神经元数量的判断上采用将离散变量进行连续化的松弛优化算法,并按照BP算法将神经元的数据与权重系数一起进行训练,取得了较好的效果。
⑤论述了基于决策树技术的电缆绝缘状态评估方法。将决策树技术应用于电缆绝缘状态的判断中,得到电缆在线和离线实验数据之间的关联性不是很大,可以单独形成决策子树;对子树的合成必须有相关联的属性,这种相关联的属性可以转化为一个可以结合两棵子树的公共属性;对于电缆的在线监测数据,由于受运行环境的影响,并没有确切的判断电缆绝缘状态的标准,在形成分类规则时必须选取那些能够根据经验或离线试验确定状态的数据集合。
通过实际电缆的各种数据,采用SPSS软件进行实际应用,最终的仿真结果说明数据挖掘方法的应用能够精确地评估出电力电缆状态。
The cables take up a large proportion in power supply line. The cables used in industry and the business sector in operation for some time will appear aging and hidden trouble for accident. It may cause significant economic losses if not taking timely measures. The cable insulation condition is usually can be divided into good, not good, bad and the failure. Assessing the cable status on the basis of the daily maintenance data, test data and on-line monitoring data has a momentous engineering value and practical significance.
Data mining finds out the connotative, unknown, and potentially valuable knowledge and rules. In order to ensure the integrity of systems, easy integration, on the basis of developing high-precision cable status monitoring device, using wired and wireless communications and Internet technologies to collect data and using data mining tools to assess the state of the cable. The main work and conclusions are as follows:
①The aging mechanism of power cable insulation system and its method for state detection were summarized. The sorts of data mining technology and its applications in power industry were introduced.
②The on-line detection theory and its realizing way of additional low frequency signal was introduced. Because of the leakage current and medium loss tangent value Xanδwere representative, This paper adopted the low frequency signal superposition method, and used the foutier transform technique to calculate the low frequency leakage current and the medium loss tangent value, and the measurement datas were transmited to the data analyzing workstation by the SCADA system.
③The data mining theory was used to finds out the isolated point and the center point. To the problem of data inconsistency and missing data, this paper adopted the regression technique of vacancy value filling method to improve the quality of data mining.
④The neural network analysis method of on line time sequence was described. Firstly, the liner and sine model were used to forecast the trend of the time sequence data, then adopted the three-layer feed-forward neural network model, the relaxed optimization algorithm was adopted to make the discrete variable continuous based on the judgement of the number of hidden neurons, lastly according to the BP atithmetic the nerve cell data and the weight coefficient were trained together.
⑤The cable insulation state evaluation method based on the decision tree technology was discussed, the decision tree technology was used to judge the cable insulation, and abtained that the relevance between the cable on line and the off line experimental data was not very big, so the decision subtrees could be formed alone. To the subtree compose there must has the correlation attribute, which can translate to a public attribute. The cable on line monitoring datas were affected by the running environment so they had no right standard to judge the cable insulation state. The stae data sets which can be confirmed according to the experience or off line experiments must be selected when forming the classification rule.
Through kinds of data of the actual cables, using SPSS software for actual application, the ultimate simulation results indicate that the application of data mining methods can accurately assess the state of the power cable.
引文
[1]J.H.Head,P.S.Gale,D.J.Skipper,and A.W.Stannentt.Ageing of Oil-Filled Cable Insulation.CIGRE paper 1982.
[2]W.G.Lawson,M.A.Simmons,and P.S.Gale.Thermal Ageing of Cellulose Paper Insulation[J].IEEE Transactions on Electrical Insulation.1977,12(1):61-66.
[3]A.M.Emsley,and G.C.Stevens.Kinetics and Mechanisms of The Low-Temperature Degradation of Cellulose[J].Cellulose,1994,12(1):26-54.
[4]J.Densley.Ageing Mechanisms and Diagnostics for Power Cables-An Overview[J].IEEE Electrical Insulation Magazine.2001,17(1):14-22.
[5]E.Pultrum,W.Boone,and T.Aabo.VLF Diagnostic Testing of Distribution Cable System.Minutes of 101 st meeting of ICC,Scottsdale,AZ,April,1997.
[6]D.L.Dorris,M.O.Pace,T.V.Blalock,and I.Alexeff.Current Pulses During Water Treeing(a)Detection System,(b) Procedures and results[J].IEEE Transactions Dielectrics and Electrical Insulation.1996,10(3):512-522 and 523-528.
[7]A.Bulinski,E.So,S.Bamji,Y.Chen,J.Densley,and J.M.Braun.Diagnostic Measurements of High Voltage Insulation Using Current Comparator Technology.[J].1994 Proceedings of IEEE ISEI.1994,10(7):115-118.
[8]G.S.Eager,Jr.,C.Katz,B.Fryszczyn,J.Densley,and B.S.Bernstein.High Voltage VLF Testing of Power Cables[J].IEEE Transactions on Power Delivery.1997,12(2):565-570.
[9]M.Bmehlmann,F.Kraehenbuehi,and Veluzat.Experience with On-site Diagnosis and Laboratory Tests on MV Cables with Extruded Insulation[J].Minutes of 92nd meeting of IEEE Insulated Conductors Committee,1992.
[10]M.S.mashikian,R.Bansal,and R.B.Northrop.Location and Characterization of Partial Discharge Sites in Shielded Power Cables[J].IEEE Transactions on power Delivery.1990,5(2):833-839.
[11]H.Hu.Evaluation of Discharge s Resistance of Solid Dielectric Power Cable Insulation[J].IEEE Electrical Insulation Magazine,1995,11(1):18-22.
[12]J.He,J.M.Braun,J.Densley,N.Fujimoto,and H.G.Sedding.Partial Discharge Characteristics of Electrical Trees in Polymeric Cable Insulation[J].Annual Report of 1994 CEIDP.1994,11(7):91-96.
[13]江秀臣,蔡军,董小兵,曾奕.110kV及以上电压等级交联电缆在线监测技术[J],电力自动化设备,2005,25(8):54-57.
[14]孙茁,南春雷,魏万水.110 kV交联聚乙烯电缆的在线监测[J].高电压技术,2004,136(30):75-79.
[15]罗俊华,邱毓昌,马翠姣.基于局部放电频谱分析的XLPE电力电缆在线监测技术[J].电工电能新技术,2002,21(1):3-8.
[16]WeiZhang,etal.A study on DC component method of on-line diagnosis for XLPE cables[A].Proceedings of the 4th International Conference on Properties and Applications of Dielectric Materials[C].Australia,1994,375-378.
[17]Nakayama T.Online cable monitor developed in Japan[J].IEEE Transactions on Power Delivery.1991,6(4):1359-1365.
[18]柴旭峥,关根志,黄海鲲等。交联聚乙烯电力电缆的绝缘在线监测技术[J],电线电缆,2000,6(5):30-33.
[19]罗俊华,马翠姣,邱毓吕.交联聚乙烯电缆绝缘的在线监测[J].高压电器,1999,35(6):44-46.
[20]周龙,电力电缆绝缘监测中的低频交流电压叠加法研究[J].电线电缆,2004,6:30-32.
[21]王洪新,贺景亮。交流叠加冲击电压下XLPE中电树起始特性[J].高电压技术,1999,25(2):3-5.
[22]赵中原,吕征宇,段乃欣,等。交联聚乙烯电缆局部放电在线监测系统研制[J].电力系统自动化,2004,28(5):59-62.
[23]Henningsen C G,etal.Experience with an on-line monitoring system for 400kV XLPE cables[A].Proceedings of 1996 IEEE Transmission and Distribution Conference[C].1996,515-520.
[24]Vanegas O,etal.Diagnosis of oil-insulated power apparatus by using neural network simulation[J].IEEE Transaction on Dielectrics and Electrical Insulation,1997,4(3):290-299.
[25]Hamerling B R,etal.Fundamental aspects of on-line PD measurements on distribution power cables[A].Proceedings of the 2001 IEEE 7th International Conference on Solid Dielectrics[C].Netherlands:2001.408-411.
[26]Knowledge discovery in database,KDD in China 网站,2000.
[27]Bhavani Thuraisingham.A primer for understanding and applying data mining,IT Professional,2000,2(1):28-31.
[28]Gulski,E.;Seitz,P.N.Use of data mining for decision support of CBM of power cables[J].Przeglad Elektrotechniczny,2003,23(79).464-73.
[29]Agrawal R,Imielinski T,Swami A.Mining association rules between sets of items in large databases[J].In:Proc of ACMSIGMOD Conf on Management of Data(SIGMOD'93).Washington,1993,20(15):207-216.
[30]Houtsma M,Swami A.Set-oriented mining of association rules.IBM Almaden Reserch Center,Research Report RJ9567,1993.
[31]AgrawalR,SrikantR.Fast algorithms for mining association rules.In:Proc 20th VLDB Conference Santiago,Chile,1994.487-499
[32]Bayardo R,Agrawal R.Mining the most interesting rules.In:ProcKDD-99,San Diego,1999.122-131
[33]肖利,王能斌,徐宏炳等.挖掘转移规则:一种新的数据挖掘技术[J].计算机研究与发展,1998,35(10):902-906.
[34]李雄飞,苑森鑫,董立岩,全勃.多段支持度数据挖掘算法研究[J].计算机学报,2001,24(6):661-665.
[35]Fu L.Rule generation from neural networks[J].IEEE Transactions on Systems,Man,Cybemetics,1994,24(8):1114-1124
[36]倪志伟,蔡庆生,史东辉.神经网络专家系统及其数据挖掘技术的探讨[J].系统工程学报2001,16(1):61-65.
[37]Quinlan J R.Induction of decision trees.MachineLearning,1986,1:811-106.
[38]Michalski R S,Larson J B.Selection of the most representative training examples and incremental generation of VL1 hypotheses.Rept.No.78-867,Urbana-Champaign:Department of Computer Science,University of Illinois,1978.
[39]Cestnik B,Kononenko I,Bratko I.ASSISTANT 86:a knowledge elicitation tool for sophisticated users.In:Proceedings of EWSL-87,Bled,Yugoslavia,1987.31-45.
[40]Pagallo G,Haussler D.Boolean feature discovery in empirical learning.Machine Learning,1990,5:71-99.
[41]Brodley C E,UtgoffP E.Multivariate decision trees.Machine Learning,1995,19:45-77.
[42]刘小虎,李生.决策树的优化算法[J].软件学报,1998,9(10):797-800.
[43]朱绍文,胡宏银,王泉德等.决策树采集技术及发展趋势[J].计算机工程,2000,26(10):55-61.
[44]Deffuant G.Neural units recruitment algorithm for generation of decision trees.In:Proc International Joint Conference on Neural Networks,San Diego,CA,1990,1(2):637-642
[45]Sethi I K.Entropy nets:From decision trees to neural networks.Proceedings of the IEEE,1990,78(10):1605-1613
[46]Sanger T D.A tree-structured adaptive network for function approximation in high-dimensional spaces.IEEE Trans Neural Networks,1991,2(2):285-293
[47]Li T,Fang L,Jennings A.Structurally adaptive self-organizing neural trees.In:Proc International Joint Conference on Neural Networks,Baltimore,MD,1992,25(3):329-334
[48]Kubat M.Decision trees can initialize radial-basis function networks.IEEE Tmns Neural Networks,1998,9(5):813-821
[49]Sankar A,Mammone R J.Optimal pruning of neural tree networks for improved generalization.In:Proc International Joint Conference on Neural Networks,Seattle,WA,1991,19(2):219-224.
[50]Guo H,Gelfand S B.Classification trees with neural network feature extraction.IEEE Trans Neural Networks,1992,3(6):923-933
[51]Behnk S,Karayiannis N B.CNeT:Competitive neural trees for pattern classification.In:Proc IEEE International Conference on Neural Networks,Washington,DC,1996,16(3):1439-1444.
[52]Sethi I K,Yoo J H.Structure-driven induction of decision tree classifiers through neural learning.Pattern Recognition,1997,30(11):1893-1904
[53]Craven M W,Shavlik J W.Extracting tree-structured representations of trained neural networks.In:Touretzky D,Mozer M,Hasselmo Meds.Advances in Neural Information Processing Systems8,Cambridge,MA:MIT Press,1996,16(5):24-30.
[54]Schmitz G P J,Aldrich C,Gouws F S.ANN-DT:An algorithm for extraction of decision trees from artificial neural networks.IEEE Trans Neural Networks,1999,10(6):1392-1401
[55]Krishnan R,Sivakumar G,Bhattacharya P.Extracting decision trees from trained neural networks.Pattern Recognition,1999,32(12):1999-2009
[56]Pawlak Z.Rough set theory and its applications to data analysis[J].Cybernetics and Systems,1998,29(1):661-688
[57]Skowron A,Rauszer C.The discernibility matrices and functions in information systems[C].In:Slowinski Red.Intelligent Decision Support Handbook of Applications and Advances of the Rough Sets Theory,Kluwer Academic Publishers,1992,331-362
[58]Wong S KM,Ziarko W.On optimal decision rules in decision tables[J].Bulletin of Polish Academy of Sciences,1985,33:693-696
[59]苗夺谦,胡桂荣.知识约简的一种启发式算法[J].计算机研究与发展,1999,36(6):681-684
[60]王珏,王任,苗夺谦,等.基于Rough Set理论的“数据浓缩”[J].计算机学报,1998,21(5):393-400
[61]Marzena Kryszkiewicz.Rough set approach to incomplete information systems[J].Information Sciences,1998,15(112):39-49
[62]Kryszkiewicz M.Rules in incomplete information systems[C],in:Proceedings of the Third Joint Conference on Information Sciences,North Carolina,USA,225 March 1997
[63]Holte R C.Very simple classification rules perform well on most commonly used datasets[J],Machine Learning,1993,15(11):63-90
[64]Kerber R.Chimerge:Discretization of numeric attributes[C].Proc of the Tenth National Conference on Artificial Intelligence,1992,MIT the Tenth National Conference on Artificial Intelligence,1992,13(15):123-128
[65]Chiu D K Y,Cheung B,Wong A KC.Information systhesis based on hierarchical entropy discretizatio n[J],Journal of Experimental and Theoretical Artificial Intelligence,1990,20(2):117-129.
[66]于金龙,李晓红,孙立新1连续属性的整体离散化[J],哈尔滨工业大学学报,2000,32(3):48-53
[67]Mohua Banerjee,Sushmita,Sankar K.Rough fuzzy MLP:Knowledge encoding and classification [J],IEEE Transactions on Neural Networks,1998,9(6):1203-1206
[68]李永敏,朱善君,陈湘晖,等.根据粗糙集理论进行BP网络设计的研究[J].系统工程理论与实践,1999,19(4):62-69
[69]王秩彤,许学标,施伯乐.Rough集理论在数据挖掘中的应用及其推广[J].计算机工程,1997,25(23):122-126.
[70]万星火,檀亦丽.数据挖掘的聚类方法,统计与决策,2005年,18期.
[71]Klements U,Schnatting.Deep Knowledge Discovery from Natural Language Texts[A].In:Proc.of the 3rd Conf.on Knowledge Discovery and Data Mining[C].US:Kluwer Academic Publishers,1997,23(15):175-178.
[72]吴小明,邱家驹,张国江等.软计算方法和数据挖掘理论在电力系统负荷预测中的应用,电力系统自动化学报,2003,15(1):1-4.
[73]S Madan,K E Bollinger.Artificial Intelligence Assisted Voltage Stability Enhancement[A].Canadian Conference on Electrical and Computer Engineering,1996,19(1):392-395.
[74]J A Steele,J R McDonald,C D(a|¨) Arcy.Knowledge Discovery in Databases:Application in the Electrical Power Engineering Domain[A],IEE Colloquium on It Strategies for Information Overload,1997,28(340):1-4.
[75]杨宜东,孙志挥(Yang Yidong,Sun Zhihui).基于时间序列的电力系统故障诊断规则挖掘(Mining Rules Based on Time Sequences for Fault Diagnosis in Electric Power System),计算机工程与应用(Computer Engineering and Application),2003,17(15):223-224.
[76]何俊佳.朱文俊.狄美华,数据挖掘技术在油中气体分析和故障诊断中的应用研究[J].高压电器,2003,25(03):31-38.
[77]廖志伟,孙雅明.数据挖掘技术及其在电力系统中的应用[J].电力系统自动化,2001,25(11):62-66.
[78]Gulski,E.Seitz,P.N,Use of data mining for decision support of CBM of power cables,Przeglad Elektrotechniczny vol.79,no.7-8 p.464-73
[79]Quak,B.Gulski,E.Smit,J.J.Wester,F.J.Groot,E.R.S.Database support for condition assessment of distribution power cables,Conference Record of the 2002 IEEE International Symposium on Electrical Insulation(Cat.No.02CH37316) pp.468-71.
[2]W.G.Lawson,M.A.Simmons,and P.S.Gale.Thermal Ageing of Cellulose Paper Insulation[J].IEEE Transactions on Electrical Insulation.1977,12(1):61-66.
[3]A.M.Emsley,and G.C.Stevens.Kinetics and Mechanisms of The Low-Temperature Degradation of Cellulose[J].Cellulose,1994,12(1):26-54.
[4]J.Densley.Ageing Mechanisms and Diagnostics for Power Cables-An Overview[J].IEEE Electrical Insulation Magazine.2001,17(1):14-22.
[5]E.Pultrum,W.Boone,and T.Aabo.VLF Diagnostic Testing of Distribution Cable System.Minutes of 101 st meeting of ICC,Scottsdale,AZ,April,1997.
[6]D.L.Dorris,M.O.Pace,T.V.Blalock,and I.Alexeff.Current Pulses During Water Treeing(a)Detection System,(b) Procedures and results[J].IEEE Transactions Dielectrics and Electrical Insulation.1996,10(3):512-522 and 523-528.
[7]A.Bulinski,E.So,S.Bamji,Y.Chen,J.Densley,and J.M.Braun.Diagnostic Measurements of High Voltage Insulation Using Current Comparator Technology.[J].1994 Proceedings of IEEE ISEI.1994,10(7):115-118.
[8]G.S.Eager,Jr.,C.Katz,B.Fryszczyn,J.Densley,and B.S.Bernstein.High Voltage VLF Testing of Power Cables[J].IEEE Transactions on Power Delivery.1997,12(2):565-570.
[9]M.Bmehlmann,F.Kraehenbuehi,and Veluzat.Experience with On-site Diagnosis and Laboratory Tests on MV Cables with Extruded Insulation[J].Minutes of 92nd meeting of IEEE Insulated Conductors Committee,1992.
[10]M.S.mashikian,R.Bansal,and R.B.Northrop.Location and Characterization of Partial Discharge Sites in Shielded Power Cables[J].IEEE Transactions on power Delivery.1990,5(2):833-839.
[11]H.Hu.Evaluation of Discharge s Resistance of Solid Dielectric Power Cable Insulation[J].IEEE Electrical Insulation Magazine,1995,11(1):18-22.
[12]J.He,J.M.Braun,J.Densley,N.Fujimoto,and H.G.Sedding.Partial Discharge Characteristics of Electrical Trees in Polymeric Cable Insulation[J].Annual Report of 1994 CEIDP.1994,11(7):91-96.
[13]江秀臣,蔡军,董小兵,曾奕.110kV及以上电压等级交联电缆在线监测技术[J],电力自动化设备,2005,25(8):54-57.
[14]孙茁,南春雷,魏万水.110 kV交联聚乙烯电缆的在线监测[J].高电压技术,2004,136(30):75-79.
[15]罗俊华,邱毓昌,马翠姣.基于局部放电频谱分析的XLPE电力电缆在线监测技术[J].电工电能新技术,2002,21(1):3-8.
[16]WeiZhang,etal.A study on DC component method of on-line diagnosis for XLPE cables[A].Proceedings of the 4th International Conference on Properties and Applications of Dielectric Materials[C].Australia,1994,375-378.
[17]Nakayama T.Online cable monitor developed in Japan[J].IEEE Transactions on Power Delivery.1991,6(4):1359-1365.
[18]柴旭峥,关根志,黄海鲲等。交联聚乙烯电力电缆的绝缘在线监测技术[J],电线电缆,2000,6(5):30-33.
[19]罗俊华,马翠姣,邱毓吕.交联聚乙烯电缆绝缘的在线监测[J].高压电器,1999,35(6):44-46.
[20]周龙,电力电缆绝缘监测中的低频交流电压叠加法研究[J].电线电缆,2004,6:30-32.
[21]王洪新,贺景亮。交流叠加冲击电压下XLPE中电树起始特性[J].高电压技术,1999,25(2):3-5.
[22]赵中原,吕征宇,段乃欣,等。交联聚乙烯电缆局部放电在线监测系统研制[J].电力系统自动化,2004,28(5):59-62.
[23]Henningsen C G,etal.Experience with an on-line monitoring system for 400kV XLPE cables[A].Proceedings of 1996 IEEE Transmission and Distribution Conference[C].1996,515-520.
[24]Vanegas O,etal.Diagnosis of oil-insulated power apparatus by using neural network simulation[J].IEEE Transaction on Dielectrics and Electrical Insulation,1997,4(3):290-299.
[25]Hamerling B R,etal.Fundamental aspects of on-line PD measurements on distribution power cables[A].Proceedings of the 2001 IEEE 7th International Conference on Solid Dielectrics[C].Netherlands:2001.408-411.
[26]Knowledge discovery in database,KDD in China 网站,2000.
[27]Bhavani Thuraisingham.A primer for understanding and applying data mining,IT Professional,2000,2(1):28-31.
[28]Gulski,E.;Seitz,P.N.Use of data mining for decision support of CBM of power cables[J].Przeglad Elektrotechniczny,2003,23(79).464-73.
[29]Agrawal R,Imielinski T,Swami A.Mining association rules between sets of items in large databases[J].In:Proc of ACMSIGMOD Conf on Management of Data(SIGMOD'93).Washington,1993,20(15):207-216.
[30]Houtsma M,Swami A.Set-oriented mining of association rules.IBM Almaden Reserch Center,Research Report RJ9567,1993.
[31]AgrawalR,SrikantR.Fast algorithms for mining association rules.In:Proc 20th VLDB Conference Santiago,Chile,1994.487-499
[32]Bayardo R,Agrawal R.Mining the most interesting rules.In:ProcKDD-99,San Diego,1999.122-131
[33]肖利,王能斌,徐宏炳等.挖掘转移规则:一种新的数据挖掘技术[J].计算机研究与发展,1998,35(10):902-906.
[34]李雄飞,苑森鑫,董立岩,全勃.多段支持度数据挖掘算法研究[J].计算机学报,2001,24(6):661-665.
[35]Fu L.Rule generation from neural networks[J].IEEE Transactions on Systems,Man,Cybemetics,1994,24(8):1114-1124
[36]倪志伟,蔡庆生,史东辉.神经网络专家系统及其数据挖掘技术的探讨[J].系统工程学报2001,16(1):61-65.
[37]Quinlan J R.Induction of decision trees.MachineLearning,1986,1:811-106.
[38]Michalski R S,Larson J B.Selection of the most representative training examples and incremental generation of VL1 hypotheses.Rept.No.78-867,Urbana-Champaign:Department of Computer Science,University of Illinois,1978.
[39]Cestnik B,Kononenko I,Bratko I.ASSISTANT 86:a knowledge elicitation tool for sophisticated users.In:Proceedings of EWSL-87,Bled,Yugoslavia,1987.31-45.
[40]Pagallo G,Haussler D.Boolean feature discovery in empirical learning.Machine Learning,1990,5:71-99.
[41]Brodley C E,UtgoffP E.Multivariate decision trees.Machine Learning,1995,19:45-77.
[42]刘小虎,李生.决策树的优化算法[J].软件学报,1998,9(10):797-800.
[43]朱绍文,胡宏银,王泉德等.决策树采集技术及发展趋势[J].计算机工程,2000,26(10):55-61.
[44]Deffuant G.Neural units recruitment algorithm for generation of decision trees.In:Proc International Joint Conference on Neural Networks,San Diego,CA,1990,1(2):637-642
[45]Sethi I K.Entropy nets:From decision trees to neural networks.Proceedings of the IEEE,1990,78(10):1605-1613
[46]Sanger T D.A tree-structured adaptive network for function approximation in high-dimensional spaces.IEEE Trans Neural Networks,1991,2(2):285-293
[47]Li T,Fang L,Jennings A.Structurally adaptive self-organizing neural trees.In:Proc International Joint Conference on Neural Networks,Baltimore,MD,1992,25(3):329-334
[48]Kubat M.Decision trees can initialize radial-basis function networks.IEEE Tmns Neural Networks,1998,9(5):813-821
[49]Sankar A,Mammone R J.Optimal pruning of neural tree networks for improved generalization.In:Proc International Joint Conference on Neural Networks,Seattle,WA,1991,19(2):219-224.
[50]Guo H,Gelfand S B.Classification trees with neural network feature extraction.IEEE Trans Neural Networks,1992,3(6):923-933
[51]Behnk S,Karayiannis N B.CNeT:Competitive neural trees for pattern classification.In:Proc IEEE International Conference on Neural Networks,Washington,DC,1996,16(3):1439-1444.
[52]Sethi I K,Yoo J H.Structure-driven induction of decision tree classifiers through neural learning.Pattern Recognition,1997,30(11):1893-1904
[53]Craven M W,Shavlik J W.Extracting tree-structured representations of trained neural networks.In:Touretzky D,Mozer M,Hasselmo Meds.Advances in Neural Information Processing Systems8,Cambridge,MA:MIT Press,1996,16(5):24-30.
[54]Schmitz G P J,Aldrich C,Gouws F S.ANN-DT:An algorithm for extraction of decision trees from artificial neural networks.IEEE Trans Neural Networks,1999,10(6):1392-1401
[55]Krishnan R,Sivakumar G,Bhattacharya P.Extracting decision trees from trained neural networks.Pattern Recognition,1999,32(12):1999-2009
[56]Pawlak Z.Rough set theory and its applications to data analysis[J].Cybernetics and Systems,1998,29(1):661-688
[57]Skowron A,Rauszer C.The discernibility matrices and functions in information systems[C].In:Slowinski Red.Intelligent Decision Support Handbook of Applications and Advances of the Rough Sets Theory,Kluwer Academic Publishers,1992,331-362
[58]Wong S KM,Ziarko W.On optimal decision rules in decision tables[J].Bulletin of Polish Academy of Sciences,1985,33:693-696
[59]苗夺谦,胡桂荣.知识约简的一种启发式算法[J].计算机研究与发展,1999,36(6):681-684
[60]王珏,王任,苗夺谦,等.基于Rough Set理论的“数据浓缩”[J].计算机学报,1998,21(5):393-400
[61]Marzena Kryszkiewicz.Rough set approach to incomplete information systems[J].Information Sciences,1998,15(112):39-49
[62]Kryszkiewicz M.Rules in incomplete information systems[C],in:Proceedings of the Third Joint Conference on Information Sciences,North Carolina,USA,225 March 1997
[63]Holte R C.Very simple classification rules perform well on most commonly used datasets[J],Machine Learning,1993,15(11):63-90
[64]Kerber R.Chimerge:Discretization of numeric attributes[C].Proc of the Tenth National Conference on Artificial Intelligence,1992,MIT the Tenth National Conference on Artificial Intelligence,1992,13(15):123-128
[65]Chiu D K Y,Cheung B,Wong A KC.Information systhesis based on hierarchical entropy discretizatio n[J],Journal of Experimental and Theoretical Artificial Intelligence,1990,20(2):117-129.
[66]于金龙,李晓红,孙立新1连续属性的整体离散化[J],哈尔滨工业大学学报,2000,32(3):48-53
[67]Mohua Banerjee,Sushmita,Sankar K.Rough fuzzy MLP:Knowledge encoding and classification [J],IEEE Transactions on Neural Networks,1998,9(6):1203-1206
[68]李永敏,朱善君,陈湘晖,等.根据粗糙集理论进行BP网络设计的研究[J].系统工程理论与实践,1999,19(4):62-69
[69]王秩彤,许学标,施伯乐.Rough集理论在数据挖掘中的应用及其推广[J].计算机工程,1997,25(23):122-126.
[70]万星火,檀亦丽.数据挖掘的聚类方法,统计与决策,2005年,18期.
[71]Klements U,Schnatting.Deep Knowledge Discovery from Natural Language Texts[A].In:Proc.of the 3rd Conf.on Knowledge Discovery and Data Mining[C].US:Kluwer Academic Publishers,1997,23(15):175-178.
[72]吴小明,邱家驹,张国江等.软计算方法和数据挖掘理论在电力系统负荷预测中的应用,电力系统自动化学报,2003,15(1):1-4.
[73]S Madan,K E Bollinger.Artificial Intelligence Assisted Voltage Stability Enhancement[A].Canadian Conference on Electrical and Computer Engineering,1996,19(1):392-395.
[74]J A Steele,J R McDonald,C D(a|¨) Arcy.Knowledge Discovery in Databases:Application in the Electrical Power Engineering Domain[A],IEE Colloquium on It Strategies for Information Overload,1997,28(340):1-4.
[75]杨宜东,孙志挥(Yang Yidong,Sun Zhihui).基于时间序列的电力系统故障诊断规则挖掘(Mining Rules Based on Time Sequences for Fault Diagnosis in Electric Power System),计算机工程与应用(Computer Engineering and Application),2003,17(15):223-224.
[76]何俊佳.朱文俊.狄美华,数据挖掘技术在油中气体分析和故障诊断中的应用研究[J].高压电器,2003,25(03):31-38.
[77]廖志伟,孙雅明.数据挖掘技术及其在电力系统中的应用[J].电力系统自动化,2001,25(11):62-66.
[78]Gulski,E.Seitz,P.N,Use of data mining for decision support of CBM of power cables,Przeglad Elektrotechniczny vol.79,no.7-8 p.464-73
[79]Quak,B.Gulski,E.Smit,J.J.Wester,F.J.Groot,E.R.S.Database support for condition assessment of distribution power cables,Conference Record of the 2002 IEEE International Symposium on Electrical Insulation(Cat.No.02CH37316) pp.468-71.