多方法融合的电力系统过电压分层模式识别研究
|
摘要
电力系统过电压直接影响到电力系统的安全运行,是发展超高压和特高压电网所必须研究的重要课题。电力系统中的过电压发生类型多种多样,发生机理不尽相同,波形、幅值、持续时间也不相同。过电压信号携带着丰富的电力系统运行状态信息,利用目前监测到的过电压信号进行特征提取以及识别算法研究,实现过电压类型的自动识别和诊断,对保证电网安全运行具有十分重要的意义。
基于目前学界对于过电压类型的划分,本文在充分考虑不同类型过电压之间的从属层次关系后,提出了过电压分层识别的思路。与传统的单层整体识别方式所不同,分层识别算法采用基于不同数学方法的独立分类器,实现对过电压的逐层依次细分。由于各个分类器是相互独立的,可以根据该分类器所需要识别的过电压类型,采取多种数学方式,优化提取特征量及识别算法,从而能有效提高系统的针对性及计算效率。同时,由于采用了模块化思想来设计分类系统,整个分层识别系统易于进行修改,系统扩展性好。
本文通过对电力系统中雷电过电压,工频电压升高,谐振过电压及操作过电压的发生机理,发展过程,波形特点的分析,阐述了上述几种过电压在本质特征方面的区别。文中介绍了小波理论,并结合不同过电压信号在时频空间能量分布差异,提出了基于小波时频理论的过电压特征提取方式。本文还介绍了S变换理路和矩阵奇异值分解理论,并从理论上分析了S变换和奇异值分解理论在降低信号随机扰动方面的独特优势,将S变换和奇异值分解理论结合,提出了基于S变换奇异值分解理论的过电压特征提取方式。根据感应,反击,绕击等三种雷电过电压的波形特点,提出了采用输电线路电流行波的时域参数来辨识三种雷电过电压的方法。该方法避开了雷电流行波折反射干扰,具有计算量小,识别方式简单等优点。在提出了多种过电压特征量提取方法后,本文针对性的考虑了分层识别系统各层分类器的不同识别任务,综合考虑各种过电压特征提取方式的优点与实用性,为过电压分层识别系统的各个分类器选择了合理的特征量。
最后,本文介绍了支持向量机和粒子群优化算法的基本原理以及特性。针对目前实测过电压数据较少,训练样本不多的情况,提出了采用基于样本风险最小化思想的支持向量机作为识别算法,对过电压进行辨识。系统研究了采用分层结构后,对过电压识别率造成的影响,提出需要对每一个分类器优化其识别算法以保证最终的识别率。针对目前支持向量机参数选取缺乏理论依据的问题,提出了利用粒子群算法来优化选取每层分类器的支持向量机参数。由于粒子群算法对自身初始参数设定不敏感,收敛性好,因此十分适合于优化支持向量机参数。测试计算表明,本文提出的粒子群优化支持向量机算法能有效提高支持向量机的识别率,避免分层识别结构对识别率造成的影响,在同样的样本训练数情况下,识别结果优于单层识别结构系统。
Overvoltge is one of the key factors for safety operations of power system. There are varieties of overvoltage types which are caused by different reasons happened in power system ever year. Since the overvoltage signal contains plenty of power system information. Utilizing the data from overvoltage on-line monitoring system to identify the types of the overvoltage automatically is quite beneficial for the self-diagnose and safety design or operation of power system.
Based on the currently consensus about overvoltage types classification, a new overvoltage multi-level recognition structure is proposed by this paper by considering the multi-level subordination relationship of different overvoltage types. Unlike the traditional single level recognition structure, the multi-level overvoltage recognition algorithm uses different independent classifier to subdivision the overvoltage type gradually. Since each classifier is independent from each other, different mathematic methods can be used to abstract characteristics parameters and construct classifier algorithm. As a result, each classifier can classify overvoltage pertinently with high efficient and the whole multi-level recognition algorithm is easy to be modified.
The happening reason, developing process and waveform characteristics of lightning overvoltage, power frequency overvoltage, operation overvoltage and resonance overvoltage are introduced in this paper. Wavelet theory is adopted to abstract the characteristics of overvoltage energy distribution in time-frequency space. Also, due to the unique advantage of S transform theory and singular value theory in reducing the signal random disturbance, the two theories above are combined together to abstract overvoltage characteristics in this paper. For lightning overvoltage, shield failure overvoltage and back flashover recognition, this paper suggests use front part of transmission line current wave as research object because the front part of current wave can avoid the disturbance of wave reflection. The time domain characteristic parameters of transmission current wave are raised to identify the three kind of lightning overvoltage above. By comprehensively considering the mathematic method above and the task of each classifier, this paper chooses different characteristic parameters abstraction mathematic methods for each classifier pertinently.
At last, the basic principles of support vector machine and particle swarm optimism algorithm are introduced. Support vector machine, which is suitable for classify data in finite sample set condition, is adopted as classify algorithm cause there is no too much field overvoltage data. The effect of multi-level recognition structure to classify rate is discussed in the paper and it is found that in order to maintain high classify rate, suitable initial value for the parameters of support vector machine is necessary. The particle swarm optimism algorithm is introduced to improve the support vector machine. The particle swarm optimism takes the classify rate as fitness function and the improved support vector machine is used to classify the overvoltage type. The testing calculation demonstrates that since the particle swarm optimism algorithm is quite insensitive to itself initial parameters value and has good performance in convergence, it is quite suitable to improve the support vector machine. The compare of three kinds of classify algorithm shows that the particle swarm optimism algorithm optimized support vector machine can greatly remedy the disadvantage of multi-level structure and has better performance than common support vector machine and BP artificial networks under same condition.
基于目前学界对于过电压类型的划分,本文在充分考虑不同类型过电压之间的从属层次关系后,提出了过电压分层识别的思路。与传统的单层整体识别方式所不同,分层识别算法采用基于不同数学方法的独立分类器,实现对过电压的逐层依次细分。由于各个分类器是相互独立的,可以根据该分类器所需要识别的过电压类型,采取多种数学方式,优化提取特征量及识别算法,从而能有效提高系统的针对性及计算效率。同时,由于采用了模块化思想来设计分类系统,整个分层识别系统易于进行修改,系统扩展性好。
本文通过对电力系统中雷电过电压,工频电压升高,谐振过电压及操作过电压的发生机理,发展过程,波形特点的分析,阐述了上述几种过电压在本质特征方面的区别。文中介绍了小波理论,并结合不同过电压信号在时频空间能量分布差异,提出了基于小波时频理论的过电压特征提取方式。本文还介绍了S变换理路和矩阵奇异值分解理论,并从理论上分析了S变换和奇异值分解理论在降低信号随机扰动方面的独特优势,将S变换和奇异值分解理论结合,提出了基于S变换奇异值分解理论的过电压特征提取方式。根据感应,反击,绕击等三种雷电过电压的波形特点,提出了采用输电线路电流行波的时域参数来辨识三种雷电过电压的方法。该方法避开了雷电流行波折反射干扰,具有计算量小,识别方式简单等优点。在提出了多种过电压特征量提取方法后,本文针对性的考虑了分层识别系统各层分类器的不同识别任务,综合考虑各种过电压特征提取方式的优点与实用性,为过电压分层识别系统的各个分类器选择了合理的特征量。
最后,本文介绍了支持向量机和粒子群优化算法的基本原理以及特性。针对目前实测过电压数据较少,训练样本不多的情况,提出了采用基于样本风险最小化思想的支持向量机作为识别算法,对过电压进行辨识。系统研究了采用分层结构后,对过电压识别率造成的影响,提出需要对每一个分类器优化其识别算法以保证最终的识别率。针对目前支持向量机参数选取缺乏理论依据的问题,提出了利用粒子群算法来优化选取每层分类器的支持向量机参数。由于粒子群算法对自身初始参数设定不敏感,收敛性好,因此十分适合于优化支持向量机参数。测试计算表明,本文提出的粒子群优化支持向量机算法能有效提高支持向量机的识别率,避免分层识别结构对识别率造成的影响,在同样的样本训练数情况下,识别结果优于单层识别结构系统。
Overvoltge is one of the key factors for safety operations of power system. There are varieties of overvoltage types which are caused by different reasons happened in power system ever year. Since the overvoltage signal contains plenty of power system information. Utilizing the data from overvoltage on-line monitoring system to identify the types of the overvoltage automatically is quite beneficial for the self-diagnose and safety design or operation of power system.
Based on the currently consensus about overvoltage types classification, a new overvoltage multi-level recognition structure is proposed by this paper by considering the multi-level subordination relationship of different overvoltage types. Unlike the traditional single level recognition structure, the multi-level overvoltage recognition algorithm uses different independent classifier to subdivision the overvoltage type gradually. Since each classifier is independent from each other, different mathematic methods can be used to abstract characteristics parameters and construct classifier algorithm. As a result, each classifier can classify overvoltage pertinently with high efficient and the whole multi-level recognition algorithm is easy to be modified.
The happening reason, developing process and waveform characteristics of lightning overvoltage, power frequency overvoltage, operation overvoltage and resonance overvoltage are introduced in this paper. Wavelet theory is adopted to abstract the characteristics of overvoltage energy distribution in time-frequency space. Also, due to the unique advantage of S transform theory and singular value theory in reducing the signal random disturbance, the two theories above are combined together to abstract overvoltage characteristics in this paper. For lightning overvoltage, shield failure overvoltage and back flashover recognition, this paper suggests use front part of transmission line current wave as research object because the front part of current wave can avoid the disturbance of wave reflection. The time domain characteristic parameters of transmission current wave are raised to identify the three kind of lightning overvoltage above. By comprehensively considering the mathematic method above and the task of each classifier, this paper chooses different characteristic parameters abstraction mathematic methods for each classifier pertinently.
At last, the basic principles of support vector machine and particle swarm optimism algorithm are introduced. Support vector machine, which is suitable for classify data in finite sample set condition, is adopted as classify algorithm cause there is no too much field overvoltage data. The effect of multi-level recognition structure to classify rate is discussed in the paper and it is found that in order to maintain high classify rate, suitable initial value for the parameters of support vector machine is necessary. The particle swarm optimism algorithm is introduced to improve the support vector machine. The particle swarm optimism takes the classify rate as fitness function and the improved support vector machine is used to classify the overvoltage type. The testing calculation demonstrates that since the particle swarm optimism algorithm is quite insensitive to itself initial parameters value and has good performance in convergence, it is quite suitable to improve the support vector machine. The compare of three kinds of classify algorithm shows that the particle swarm optimism algorithm optimized support vector machine can greatly remedy the disadvantage of multi-level structure and has better performance than common support vector machine and BP artificial networks under same condition.
引文
[1]张纬钹,何金良,高玉明.过电压防护及绝缘配合[M].北京:清华大学出版社, 2002.
[2]解广润.电力系统过电压[M].北京:水利电力出版社, 1985.
[3] Soares A,Schroeder MAO,Visacro S,Transient voltages in transmission lines caused by direct lightning strikes,IEEE TRANSACTIONS ON POWER DELIVERY Part 2 APR 2005.20 (2): 1447-1452
[4]陈慈萱.过电压保护原理与运行技术[M].北京:中国电力出版社,2001.
[5]兰海涛.高压电网过电压在线监测系统设计与实现研究[D].重庆大学,2006
[6]刘伟明.基于容性设备泄漏电流的嵌入式电网过电压在线监测系统研究[D].重庆大学,2008
[7]刘强,张元芳,黄海鲲等。MV-I型过电压在线监测装置的研制[J]。高电压技术,2008,8(28):8
[8] Caixin Sun,et al. Identifying the Internal and External Overvoltage of Distribution Networks Based on Fisher Discriminate Method[C].2006 International Conference on Power System Technology.
[9] Du Lin, Dai Bin et al.Identifying the Overvoltage in Distribution Networks Based on Support Vector Machine [C].2008 international Conference on High Voltage Engineering and Application, Chongqing, China, November 9-13.
[10] Hauer J F,et al. Initial results in Prony analysis of power system response signals[J].IEEE Trans on Power System. 1990,5(1)
[11] Trydnowski D J,et al. An application of Prony methods in PSS design for multimachine system[J].IEEE Trans on Power System.1991,6(1)
[12] Smith J R, et al. Transfer function identification in power system applications[J].IEEE Trans on Power System.1993,8(3)
[13] Hauner J F, et al. Application of Prony analysis to the determination of modal content and equivalent models for measured power system response[J].IEEE Trans on Power System,1991,6(3)
[14]曹维,翁斌伟等.电力系统暂态变量的Prony分析.电工技术学报[J].2000, 15(6).
[15] I. Daubechies. The wavelet transform, time frequency localization and signal analysis [J].IEEE Trans on Signal Processing.1990, 36(5):961-1005.
[16] I.Daubechise.Ten lectures on wavelets [M].SIMA, Philadelphia, 1992.
[17] S. Mallet. A Wavelet Tour of Signal Processing, Second Edition. Academic Press,1998
[18]杨福生.小波变换的工程分析与应用[M].北京:科学出版社,2002
[19]唐晓初.小波分析及其应用[M].重庆:重庆大学出版社
[20] Surga Sntoso,Edward J.Powers,Grady W Mack.Electric power quality disturbance detection using wavelet transform analysis[C].2006 The IEEE SP International Symposium on Time-frequency and Time-Scale analysis,Philadelphia,PA,U.S.A,166-169.
[21] Brito N S D,Souza B A,Pires F A C.Daubechies wavelets in quality of electrical power[C].The 1998 ICHQP,Athens,Greece 511-515.
[22] Wilkinson W A.Cox M D.Discrete wavelet analysis of Power system transients[J].IEEE Transactions on power systems,1996,11(4):2038-2044.
[23] Olivier Poisson,Pascal Rioual,Michel Meunier.Detection and measurement of power quality disturbances using wavelet transform[J].IEEE Trans.On power delivery,2000 15(3):1039-1044.
[24] Angrisani L,Daponte P,Apuzzo M D.A measurement method based on the wavelet transform for power quality analysis[J].IEEE Transaction on Power delivery,1998,13(4):990-998.
[25]胡铭,陈珩.基于小波变换模极大值得电能质量扰动检测与定位[J].电网技术2001,25(3):12-16.
[26] Surya Santoso,Powers E J,Grady W Mack.Power quality assessment via wavelet transform analysis[J].IEEE Transactions on power Delivery,1996,11(2):924-930.
[27] Dave Robertson,Octavia I.Camps,Jeffrey Mayer et al.Wavelets and electromagnetic power system transients[J].IEEE Transactions on Power Delivery,1996,11(2):1050-1058.
[28] Perunicic B,Malini M,Wang Z et al.Power quality disturbance detection and classification using wavelets and artificial neural networks[C].Proceedings of the 8th ICHQP,1998:77-82.
[29]王建赜,纪延超,冉启文等.小波变换在电能质量分析中的应用[J].继电器,1999,27(5):13-19.
[30]陈祥训.正交紧支复小波的生成及其在电力系统的应用[J].中国电机工程学报,2000,20(7):83-88
[31]何建军,任震,黄雯莹等.电力系统奇异信号的复值小波分析[J].中国电机工程学报,1999,19(11): 41,51.
[32]何正友,刘志刚,钱清泉.小波熵理论及其在电力系统中应用的可行性探讨[J].电网技术,2004,28(21):17-21.
[33]何正友,蔡玉梅,钱清泉.小波熵理论及其在电力系统故障检测中的应用研究[J].电机工程学报,2005,25(5):28-43
[34] R.G.Stockwell, L.Mansinha, and R.P.Lowe. Localization of the Complex Spectrum: The STransform[J].IEEE Trans On Signal Processing,1996,44(4):998-1001
[35]辛欣,张效民.基于S-变换的水中目标特征提取[J].电声基础,2007,31(1):10-12
[36]张曦,杜兴民,王星.基于S变换的跳频信号特征参数盲估计[J].现代雷达,2008,30(2):94-99
[37]吴宝杰,杨桦,张伟光.探地雷达数据的S变换时频分析[J].上海地质,2008,14(3):13-19
[38]樊剑,吕超,张辉.基S变换的地震波时频分析及人工调整[J].振动工程学报,2008,21(4):381-387
[39]甄莉,彭真明.基于广义S变换的图像局部时频分析[J].航空学报,2008,29(4):1013-1019
[40] P.L.Dash,B.K.Panigrahi,et al.Power Quality Anlysis Using S-Transform[J].IEEE Trans on Power Delivery.2003,18(2):405-411
[41] I.W.C.Lee ,P.L.Dash. S-Transform-Based Intelligent System for Classification of Power Quality Disturbance Signals[J].IEEE Trans on Power Delivery.2003,50(4):800-805
[42] M.V.Chilukuri,P.L.Dash.Multiresolution S-Transform-Based Fuzzy Recognition System for Power Quality Events[J].IEEE Trans on Power Delivery.2004,19(1):323-329
[43] P.L.Dash, B.K.Panigrahi,et al.Power Quality Disturbance Data Compression, Detection, and Classification Using Integrated Spline Wavelet and S-Transform[J].IEEE Trans on Power Delivery.2003,18(2):595-600
[44]全惠敏,戴瑜兴.基于S变换模矩阵的电能质量扰动信号检测与定位[J].电工技术学报,2007,22(8):119-125
[45]杨洪耕,刘守亮等.基于S变换的电压凹陷分类专家系统[J].中国电机工程学报.2007,27(1):98-104
[46]占勇,程忠浩.基于S变换的电能质量扰动支持向量机分类识别[J].中国电机工程学报,2005,25(4):51-56
[47]杨洪耕,刘守亮等.基于S变换模时频矩阵相似度的短时电能质量扰动分类[J].电网技术,2006,20(5):67-71
[48]吕干云,程忠浩等.基于S变换和多级SVM的电能质量扰动检测识别[J].电工技术学报,2006,21(1):121-126
[49]杨洪耕,刘守亮等.利用S变换时频等值线图与幅值包罗向量实现电压凹陷分类[J].电工技术学报,2006,21(8):74-79
[50]朱福喜,杜友福等.人工智能引论[M] .武汉大学出版社,2006
[51]黄席樾,张著洪等.现代智能算法理论及应用[M].科学出版社,2005
[52] C.M. Bishop, Networks for Pattern Recognition [M]. Oxford, Unites Kingdom: Oxford University Press, 1995.
[53] B.D. Ripley, Pattern Recognition and Neural Networks [M]. Cambridge, Great Britain:Cambridge University Press, 1996.
[54] J. Chen, Classification of transients in power systems [D]. Department of Electrical and Computer University of Manitoba Winnipeg, Manitoba, Canada. December 2001
[55]杨耿煌,温渤婴.基于量子行为粒子群优化–人工神经网络的电能质量扰动识别[J].中国电机工程学报,2008,28(10):123-129
[56]王立德,李欣然等.基于人工神经网络的综合负荷模型[J].电网技术,2008,32(16):59-62
[57]罗建.基于人工神经网络模型的母线保护研究和实现[D].重庆大学博士学位论文.2004
[58]毛颖科,关志成等.基于BP人工神经网络的绝缘子泄漏电流预测[J].中国电机工程学报,2007,27(27):7-12
[59] A.K.Ghosh,D.Lubkeman.The classification of power system disturbance waveforms using a neural network approach[J].IEEE Trans on Power Delivery,1995,10(12): 109-115
[60] N. Kandil, V. sood,et al. Fault identification in an ac-dc transmission system using neural network[J]. IEEE trans on power System,1992,7(6) :812-819
[61] S.Santoso,J.Lamoree et al. A scalable PQ event identification system[J].IEEE Trans on Power Delivery,2000,15(11):738-743
[62]刘云峰等.电液伺服系统的自适应模糊滑模控制研究[J].中国电机工程学报.2006,26(12):140-144
[63]焦邵华,刘万顺,杨奇逊等.用模糊集合理论识别电力系统振荡中的短路的研究[J].中国电机工程学报.1998,11(18):67-72
[64]孙和义,浦昭邦,赵学增.基于模糊神经网络高压电气设备绝缘状况评价方法研究[J].电力系统自动化设备.2007,1(27):14-19
[65]徐文,王大忠,周泽存.基于模糊理论的变压器故障诊断专家系统.电力系统自动化,1995,19(6):32-37
[66] An expert system for transmission substation event analysis.IEEE Trans on Power Delivery, vol. 8, pp. 1942-1949, October 1993
[67] Vapnik V. The nature of statistical learning theory[M].New York: Springer-Verlag, 1999
[68]张学工.关于统计学习理论与支持向量机[J].自动化学报.2000,1(26):12-18
[69] Burges C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2): 121-127
[70] C. Cortes, V. Vapnik. Support vector networks [J]. Machine Learning, 1995, 20(3): 273-297
[71]肖先勇,葛嘉等.基于支持向量机的中长期电力负荷组合预测[J].电力系统自动化学报,2008,20(1):84-88
[72]申涛等.基于支持向量机和DGA的变压器状态评估方法[J].电力科学与工程,2008,24(3):47-50
[73]张全明,刘会金.最小二乘支持向量机在电能质量扰动分类中的应用[J].中国电机工程学报.2008,28(1)
[74]张全明,刘会金.最小二乘支持向量机在电能质量扰动分类中的应用[J].中国电机工程学报.2008,28(1)
[75]杜林,刘伟明,王有元等.基于CPLD的电网过电压变频数据采集卡设计[J].高电压技术,2008,34(8):1589-1593
[76]梁义明,葛栋.同塔多回线路防雷计算中的杆塔模型[J]高电压技术,2006.32(1):76-78.
[77]杨庆,赵杰,司马文霞,等.云广特高压直流输电线路反击耐雷性能. [J]高电压技术,2008.34(7):1330-1335
[78]伏进,司马文霞,李建标,等.基于分形理论的超特高压线路绕击耐雷性能评估.[J].高电压技术,2009,35(6):1274-1278
[79]李海峰,王钢,赵建仓.输电线路感应雷暂态特征分析及其识别方法[J].中国电机工程学报,2004. 24(3):114-119
[80] Voislav Jankov. Estimation of the maximal voltage induced on an overhead line due to the near by lightning [J].IEEE Trans. On Power Delivery, 1997,12(1): 315-324.
[81] Yamada T, Mochizuki A, Sawada J, et al. Experiment evaluation of a UHV tower model for lightning surge analysis[J]. IEEE Trans. on Power Delivery, 1995,10(1):393-402
[82] IEEE Working Group 3.4.11 of Surge Protection Devices Committee. Modeling of metal oxide surge arresters [J]. IEEE Trans. on Power Delivery, 1992, 7(1): 302-309
[83]施围,郭洁.电力系统过电压计算[M]. 2版.北京:高等教育出版社
[84]张贤达.矩阵分析与应用.北京:清华大学出版社,2004
[85]张峰,梁军,张利等.奇异值分解理论和小波变换结合的行波信号奇异点检测[J].电力系统自动化,2008,32(20):57-60
[86]梁霖,徐光华,刘弹,栗茂林.小波-奇异值分解在异步电机转子故障特征提取中的应用[J].中国电机工程学报,2005.25(19):111-115
[87]魏小鹏,于万波,金一粟.奇异值方法用于汽车车型识别[J].中国图像图形学报,2003,8A(1):47-50.
[88]洪子全,杨静宇.基于奇异值特征和统计模型的人像识别算法[J].计算机研究与发展,1994,31(3):60-65.
[89]魏小鹏,于万波,金一粟.奇异值方法用于汽车车型识别[J].中国图像图形学报,2003,8A(1):47-50.
[90]闫荣华,彭进业,李岩等.基于小波域奇异值分解的人脸识别方法[J].计算机工程,2007,33(4):212-217.
[91]甘俊英,张有为.一种基于奇异值特征的神经网络人脸识别新途径[J].电子学报,2004,32(1):170-173
[92] Tian Y, Tang T, Wang Y H, et al. Do Singular Value Contain Adequate Information for Face Recognition[J]. Pattern Recognition, 2003,36 (6):649-655.
[93]束洪春,张广斌,孙士运,等.±800kV直流输电线路雷电绕击与反击的识别方法[J].中国电机工程学报,2009. 29(7):13-19.
[94]齐冲.高压输电线路雷电绕击和反击的识别[D].广西大学,2007
[95]李海峰,王钢,赵建仓.输电线路感应雷暂态特征分析及其识别方法[J].中国电机工程学报,
[96]段建东,任晋峰,张保会,等.超高速保护中雷电干扰识别的暂态研究[J].中国电机工程学报,2006.26(23):7-13.
[97]王钢,李海峰,赵建仓,等.基于小波多尺度的输电线路直击雷暂态识别[J].中国电机工程学报,2004.24(4):139-144.
[98]司大军,束洪春,陈学允,等.输电线路雷击电磁暂态特征分析及其识别方法研究[J].中国电机工程学报,2005. 25(7):64-69.
[99]束洪春,王永治,程春河,孙士云等.±800kV直流输电线路雷击电磁暂态分析与故障识别[J].中国电机工程学报,2008.28(19):93-100.
[100]郭宁明,覃剑.雷击输电线路故障情况下的短路点定位方法[J].电力系统自动化,2009,33(10):74-77
[101]段建东,张保会,郝治国等.超高压线路暂态保护中雷电干扰与短路故障识别[J].电力系统自动化, 2004. 28(18):30-35
[102]郭宁明,覃剑,陈祥训.雷击对行波故障测距的影响及识别[J].电力系统自动化,2008, 32(5):76-79
[103]杜林,戴斌,司马文霞等.基于支持向量机的配电网过电压模式识别[J].高电压技术,2009,25(3):521-526
[104]张庆宝,程浩忠,刘青山等.基于粗糙集属性约简算法和支持向量机的短期负荷预测[J].电网技术, 2006, 30(8): 56-59.
[105]姜惠兰,刘晓津,关颖等.基于硬C均值聚类分析算法和支持向量机的电力系统短期符合预测[J].电网技术, 2006, 30(8): 81-85.
[106]颜秉勇,刘喜梅,田作华等.协同滤波器和支持向量机在HVDC系统故障诊断中的应用[J].中国电机工程学报, 2008, 28(1): 23-29.
[107]占勇,程浩忠,丁屹峰等.基于S变换的电能质量扰动支持向量机分类识别[J].中国电机工程学报, 2005, 25(4): 51-56.
[108]张全明,刘会金.最小二乘支持向量机在电能质量扰动分类中的应用[J].中国电机工程学报, 2008, 28(1): 106-110.
[109] Chang C C,Lin C J.(2001)LIVBSVM: A library for support vector machine [EB/OL] http://www.csie.ntu.edu.tw/~cjlin/ libsvm.
[110]杨光正,吴岷,张晓莉等.模式识别[M].合肥:中国科学技术大学出版社,2001
[2]解广润.电力系统过电压[M].北京:水利电力出版社, 1985.
[3] Soares A,Schroeder MAO,Visacro S,Transient voltages in transmission lines caused by direct lightning strikes,IEEE TRANSACTIONS ON POWER DELIVERY Part 2 APR 2005.20 (2): 1447-1452
[4]陈慈萱.过电压保护原理与运行技术[M].北京:中国电力出版社,2001.
[5]兰海涛.高压电网过电压在线监测系统设计与实现研究[D].重庆大学,2006
[6]刘伟明.基于容性设备泄漏电流的嵌入式电网过电压在线监测系统研究[D].重庆大学,2008
[7]刘强,张元芳,黄海鲲等。MV-I型过电压在线监测装置的研制[J]。高电压技术,2008,8(28):8
[8] Caixin Sun,et al. Identifying the Internal and External Overvoltage of Distribution Networks Based on Fisher Discriminate Method[C].2006 International Conference on Power System Technology.
[9] Du Lin, Dai Bin et al.Identifying the Overvoltage in Distribution Networks Based on Support Vector Machine [C].2008 international Conference on High Voltage Engineering and Application, Chongqing, China, November 9-13.
[10] Hauer J F,et al. Initial results in Prony analysis of power system response signals[J].IEEE Trans on Power System. 1990,5(1)
[11] Trydnowski D J,et al. An application of Prony methods in PSS design for multimachine system[J].IEEE Trans on Power System.1991,6(1)
[12] Smith J R, et al. Transfer function identification in power system applications[J].IEEE Trans on Power System.1993,8(3)
[13] Hauner J F, et al. Application of Prony analysis to the determination of modal content and equivalent models for measured power system response[J].IEEE Trans on Power System,1991,6(3)
[14]曹维,翁斌伟等.电力系统暂态变量的Prony分析.电工技术学报[J].2000, 15(6).
[15] I. Daubechies. The wavelet transform, time frequency localization and signal analysis [J].IEEE Trans on Signal Processing.1990, 36(5):961-1005.
[16] I.Daubechise.Ten lectures on wavelets [M].SIMA, Philadelphia, 1992.
[17] S. Mallet. A Wavelet Tour of Signal Processing, Second Edition. Academic Press,1998
[18]杨福生.小波变换的工程分析与应用[M].北京:科学出版社,2002
[19]唐晓初.小波分析及其应用[M].重庆:重庆大学出版社
[20] Surga Sntoso,Edward J.Powers,Grady W Mack.Electric power quality disturbance detection using wavelet transform analysis[C].2006 The IEEE SP International Symposium on Time-frequency and Time-Scale analysis,Philadelphia,PA,U.S.A,166-169.
[21] Brito N S D,Souza B A,Pires F A C.Daubechies wavelets in quality of electrical power[C].The 1998 ICHQP,Athens,Greece 511-515.
[22] Wilkinson W A.Cox M D.Discrete wavelet analysis of Power system transients[J].IEEE Transactions on power systems,1996,11(4):2038-2044.
[23] Olivier Poisson,Pascal Rioual,Michel Meunier.Detection and measurement of power quality disturbances using wavelet transform[J].IEEE Trans.On power delivery,2000 15(3):1039-1044.
[24] Angrisani L,Daponte P,Apuzzo M D.A measurement method based on the wavelet transform for power quality analysis[J].IEEE Transaction on Power delivery,1998,13(4):990-998.
[25]胡铭,陈珩.基于小波变换模极大值得电能质量扰动检测与定位[J].电网技术2001,25(3):12-16.
[26] Surya Santoso,Powers E J,Grady W Mack.Power quality assessment via wavelet transform analysis[J].IEEE Transactions on power Delivery,1996,11(2):924-930.
[27] Dave Robertson,Octavia I.Camps,Jeffrey Mayer et al.Wavelets and electromagnetic power system transients[J].IEEE Transactions on Power Delivery,1996,11(2):1050-1058.
[28] Perunicic B,Malini M,Wang Z et al.Power quality disturbance detection and classification using wavelets and artificial neural networks[C].Proceedings of the 8th ICHQP,1998:77-82.
[29]王建赜,纪延超,冉启文等.小波变换在电能质量分析中的应用[J].继电器,1999,27(5):13-19.
[30]陈祥训.正交紧支复小波的生成及其在电力系统的应用[J].中国电机工程学报,2000,20(7):83-88
[31]何建军,任震,黄雯莹等.电力系统奇异信号的复值小波分析[J].中国电机工程学报,1999,19(11): 41,51.
[32]何正友,刘志刚,钱清泉.小波熵理论及其在电力系统中应用的可行性探讨[J].电网技术,2004,28(21):17-21.
[33]何正友,蔡玉梅,钱清泉.小波熵理论及其在电力系统故障检测中的应用研究[J].电机工程学报,2005,25(5):28-43
[34] R.G.Stockwell, L.Mansinha, and R.P.Lowe. Localization of the Complex Spectrum: The STransform[J].IEEE Trans On Signal Processing,1996,44(4):998-1001
[35]辛欣,张效民.基于S-变换的水中目标特征提取[J].电声基础,2007,31(1):10-12
[36]张曦,杜兴民,王星.基于S变换的跳频信号特征参数盲估计[J].现代雷达,2008,30(2):94-99
[37]吴宝杰,杨桦,张伟光.探地雷达数据的S变换时频分析[J].上海地质,2008,14(3):13-19
[38]樊剑,吕超,张辉.基S变换的地震波时频分析及人工调整[J].振动工程学报,2008,21(4):381-387
[39]甄莉,彭真明.基于广义S变换的图像局部时频分析[J].航空学报,2008,29(4):1013-1019
[40] P.L.Dash,B.K.Panigrahi,et al.Power Quality Anlysis Using S-Transform[J].IEEE Trans on Power Delivery.2003,18(2):405-411
[41] I.W.C.Lee ,P.L.Dash. S-Transform-Based Intelligent System for Classification of Power Quality Disturbance Signals[J].IEEE Trans on Power Delivery.2003,50(4):800-805
[42] M.V.Chilukuri,P.L.Dash.Multiresolution S-Transform-Based Fuzzy Recognition System for Power Quality Events[J].IEEE Trans on Power Delivery.2004,19(1):323-329
[43] P.L.Dash, B.K.Panigrahi,et al.Power Quality Disturbance Data Compression, Detection, and Classification Using Integrated Spline Wavelet and S-Transform[J].IEEE Trans on Power Delivery.2003,18(2):595-600
[44]全惠敏,戴瑜兴.基于S变换模矩阵的电能质量扰动信号检测与定位[J].电工技术学报,2007,22(8):119-125
[45]杨洪耕,刘守亮等.基于S变换的电压凹陷分类专家系统[J].中国电机工程学报.2007,27(1):98-104
[46]占勇,程忠浩.基于S变换的电能质量扰动支持向量机分类识别[J].中国电机工程学报,2005,25(4):51-56
[47]杨洪耕,刘守亮等.基于S变换模时频矩阵相似度的短时电能质量扰动分类[J].电网技术,2006,20(5):67-71
[48]吕干云,程忠浩等.基于S变换和多级SVM的电能质量扰动检测识别[J].电工技术学报,2006,21(1):121-126
[49]杨洪耕,刘守亮等.利用S变换时频等值线图与幅值包罗向量实现电压凹陷分类[J].电工技术学报,2006,21(8):74-79
[50]朱福喜,杜友福等.人工智能引论[M] .武汉大学出版社,2006
[51]黄席樾,张著洪等.现代智能算法理论及应用[M].科学出版社,2005
[52] C.M. Bishop, Networks for Pattern Recognition [M]. Oxford, Unites Kingdom: Oxford University Press, 1995.
[53] B.D. Ripley, Pattern Recognition and Neural Networks [M]. Cambridge, Great Britain:Cambridge University Press, 1996.
[54] J. Chen, Classification of transients in power systems [D]. Department of Electrical and Computer University of Manitoba Winnipeg, Manitoba, Canada. December 2001
[55]杨耿煌,温渤婴.基于量子行为粒子群优化–人工神经网络的电能质量扰动识别[J].中国电机工程学报,2008,28(10):123-129
[56]王立德,李欣然等.基于人工神经网络的综合负荷模型[J].电网技术,2008,32(16):59-62
[57]罗建.基于人工神经网络模型的母线保护研究和实现[D].重庆大学博士学位论文.2004
[58]毛颖科,关志成等.基于BP人工神经网络的绝缘子泄漏电流预测[J].中国电机工程学报,2007,27(27):7-12
[59] A.K.Ghosh,D.Lubkeman.The classification of power system disturbance waveforms using a neural network approach[J].IEEE Trans on Power Delivery,1995,10(12): 109-115
[60] N. Kandil, V. sood,et al. Fault identification in an ac-dc transmission system using neural network[J]. IEEE trans on power System,1992,7(6) :812-819
[61] S.Santoso,J.Lamoree et al. A scalable PQ event identification system[J].IEEE Trans on Power Delivery,2000,15(11):738-743
[62]刘云峰等.电液伺服系统的自适应模糊滑模控制研究[J].中国电机工程学报.2006,26(12):140-144
[63]焦邵华,刘万顺,杨奇逊等.用模糊集合理论识别电力系统振荡中的短路的研究[J].中国电机工程学报.1998,11(18):67-72
[64]孙和义,浦昭邦,赵学增.基于模糊神经网络高压电气设备绝缘状况评价方法研究[J].电力系统自动化设备.2007,1(27):14-19
[65]徐文,王大忠,周泽存.基于模糊理论的变压器故障诊断专家系统.电力系统自动化,1995,19(6):32-37
[66] An expert system for transmission substation event analysis.IEEE Trans on Power Delivery, vol. 8, pp. 1942-1949, October 1993
[67] Vapnik V. The nature of statistical learning theory[M].New York: Springer-Verlag, 1999
[68]张学工.关于统计学习理论与支持向量机[J].自动化学报.2000,1(26):12-18
[69] Burges C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2): 121-127
[70] C. Cortes, V. Vapnik. Support vector networks [J]. Machine Learning, 1995, 20(3): 273-297
[71]肖先勇,葛嘉等.基于支持向量机的中长期电力负荷组合预测[J].电力系统自动化学报,2008,20(1):84-88
[72]申涛等.基于支持向量机和DGA的变压器状态评估方法[J].电力科学与工程,2008,24(3):47-50
[73]张全明,刘会金.最小二乘支持向量机在电能质量扰动分类中的应用[J].中国电机工程学报.2008,28(1)
[74]张全明,刘会金.最小二乘支持向量机在电能质量扰动分类中的应用[J].中国电机工程学报.2008,28(1)
[75]杜林,刘伟明,王有元等.基于CPLD的电网过电压变频数据采集卡设计[J].高电压技术,2008,34(8):1589-1593
[76]梁义明,葛栋.同塔多回线路防雷计算中的杆塔模型[J]高电压技术,2006.32(1):76-78.
[77]杨庆,赵杰,司马文霞,等.云广特高压直流输电线路反击耐雷性能. [J]高电压技术,2008.34(7):1330-1335
[78]伏进,司马文霞,李建标,等.基于分形理论的超特高压线路绕击耐雷性能评估.[J].高电压技术,2009,35(6):1274-1278
[79]李海峰,王钢,赵建仓.输电线路感应雷暂态特征分析及其识别方法[J].中国电机工程学报,2004. 24(3):114-119
[80] Voislav Jankov. Estimation of the maximal voltage induced on an overhead line due to the near by lightning [J].IEEE Trans. On Power Delivery, 1997,12(1): 315-324.
[81] Yamada T, Mochizuki A, Sawada J, et al. Experiment evaluation of a UHV tower model for lightning surge analysis[J]. IEEE Trans. on Power Delivery, 1995,10(1):393-402
[82] IEEE Working Group 3.4.11 of Surge Protection Devices Committee. Modeling of metal oxide surge arresters [J]. IEEE Trans. on Power Delivery, 1992, 7(1): 302-309
[83]施围,郭洁.电力系统过电压计算[M]. 2版.北京:高等教育出版社
[84]张贤达.矩阵分析与应用.北京:清华大学出版社,2004
[85]张峰,梁军,张利等.奇异值分解理论和小波变换结合的行波信号奇异点检测[J].电力系统自动化,2008,32(20):57-60
[86]梁霖,徐光华,刘弹,栗茂林.小波-奇异值分解在异步电机转子故障特征提取中的应用[J].中国电机工程学报,2005.25(19):111-115
[87]魏小鹏,于万波,金一粟.奇异值方法用于汽车车型识别[J].中国图像图形学报,2003,8A(1):47-50.
[88]洪子全,杨静宇.基于奇异值特征和统计模型的人像识别算法[J].计算机研究与发展,1994,31(3):60-65.
[89]魏小鹏,于万波,金一粟.奇异值方法用于汽车车型识别[J].中国图像图形学报,2003,8A(1):47-50.
[90]闫荣华,彭进业,李岩等.基于小波域奇异值分解的人脸识别方法[J].计算机工程,2007,33(4):212-217.
[91]甘俊英,张有为.一种基于奇异值特征的神经网络人脸识别新途径[J].电子学报,2004,32(1):170-173
[92] Tian Y, Tang T, Wang Y H, et al. Do Singular Value Contain Adequate Information for Face Recognition[J]. Pattern Recognition, 2003,36 (6):649-655.
[93]束洪春,张广斌,孙士运,等.±800kV直流输电线路雷电绕击与反击的识别方法[J].中国电机工程学报,2009. 29(7):13-19.
[94]齐冲.高压输电线路雷电绕击和反击的识别[D].广西大学,2007
[95]李海峰,王钢,赵建仓.输电线路感应雷暂态特征分析及其识别方法[J].中国电机工程学报,
[96]段建东,任晋峰,张保会,等.超高速保护中雷电干扰识别的暂态研究[J].中国电机工程学报,2006.26(23):7-13.
[97]王钢,李海峰,赵建仓,等.基于小波多尺度的输电线路直击雷暂态识别[J].中国电机工程学报,2004.24(4):139-144.
[98]司大军,束洪春,陈学允,等.输电线路雷击电磁暂态特征分析及其识别方法研究[J].中国电机工程学报,2005. 25(7):64-69.
[99]束洪春,王永治,程春河,孙士云等.±800kV直流输电线路雷击电磁暂态分析与故障识别[J].中国电机工程学报,2008.28(19):93-100.
[100]郭宁明,覃剑.雷击输电线路故障情况下的短路点定位方法[J].电力系统自动化,2009,33(10):74-77
[101]段建东,张保会,郝治国等.超高压线路暂态保护中雷电干扰与短路故障识别[J].电力系统自动化, 2004. 28(18):30-35
[102]郭宁明,覃剑,陈祥训.雷击对行波故障测距的影响及识别[J].电力系统自动化,2008, 32(5):76-79
[103]杜林,戴斌,司马文霞等.基于支持向量机的配电网过电压模式识别[J].高电压技术,2009,25(3):521-526
[104]张庆宝,程浩忠,刘青山等.基于粗糙集属性约简算法和支持向量机的短期负荷预测[J].电网技术, 2006, 30(8): 56-59.
[105]姜惠兰,刘晓津,关颖等.基于硬C均值聚类分析算法和支持向量机的电力系统短期符合预测[J].电网技术, 2006, 30(8): 81-85.
[106]颜秉勇,刘喜梅,田作华等.协同滤波器和支持向量机在HVDC系统故障诊断中的应用[J].中国电机工程学报, 2008, 28(1): 23-29.
[107]占勇,程浩忠,丁屹峰等.基于S变换的电能质量扰动支持向量机分类识别[J].中国电机工程学报, 2005, 25(4): 51-56.
[108]张全明,刘会金.最小二乘支持向量机在电能质量扰动分类中的应用[J].中国电机工程学报, 2008, 28(1): 106-110.
[109] Chang C C,Lin C J.(2001)LIVBSVM: A library for support vector machine [EB/OL] http://www.csie.ntu.edu.tw/~cjlin/ libsvm.
[110]杨光正,吴岷,张晓莉等.模式识别[M].合肥:中国科学技术大学出版社,2001