变压器在线监测与故障诊断系统研究
|
摘要
随着世界上装机容量的迅速增长,对供电可靠性的要求越来越高。对电力设备进行在线监测与故障诊断,是实现设备预知性维修的前提,是保证设备安全运行的关键,也是对传统的离线预防性试验的重大补充和拓展。
本文以变压器状态在线监测与故障诊断系统为研究对象,在深入研究最小二乘支持向量机(LS-SVM)和经验模态分解(EMD)理论的基础上,将其引入到变压器故障诊断系统中,着重对油中溶解气体分析(DGA)和局部放电监测中的信号抗干扰两个方面进行了研究。
DGA是变压器绝缘监督的一个重要手段,但放电和过热两类故障共存时的故障难分辨会导致诊断正判率较低。本文对多种故障类型作了详细分析后提出了两种故障识别方法:基于LS-SVM多分类的DGA方法,通过相关统计分析和数据预处理,选择变压油中典型气体作为LS-SVM的输入,然后利用典型故障气体的相对含量在高维空间的分布特性进行变压器故障类型诊断;基于邻域粒子群算法优化BP神经网络的DGA方法,选择油中典型气体作为神经网络的输入,然后利用训练好的邻域粒子群算法优化后的神经网络进行变压器故障类型诊断。试验结果表明,这两种方法具有很好的分类效果,较好地解决了变压器放电和过热共存时故障的难分辨问题,对故障诊断的正判率较高。
近年来局部放电监测一直是国内外研究的热点问题,而干扰抑制一直是其中的难点。本文针对窄带干扰,提出了两种方法:基于LS-SVM回归的频域分析法,将原始时域信号变换到频域,利用LS-SVM对信号干扰频率最大幅值点附近的数据进行拓延,最后逆变换以得到抑制干扰后的信号,该方法有效地拓展了干扰频带的宽度,较好地抑制了窄带干扰残余;基于EMD和自适应噪声对消的方法,首先在频域中降低干扰幅值,接着利用EMD的分频特性将宽频带的窄带干扰分解到不同频带,各频带内的窄带干扰频率相差有限,然后进行自适应噪声对消。针对白噪声干扰,提出了一种全新的方法:基于EMD和固有模态函数(IMF)重构的方法,首先对含噪的局部放电信号进行EMD,得到含特征频率的IMF,然后对所得的IMF分量进行自适应阈值处理后重构,从而抑制噪声干扰,相比于常规的小波去噪算法,该方法具有自适应性强,不受小波函数和最佳小波分解层数选取的限制等优点,而且实现了阈值和固有模态函数阈值处理层数的自动选取。
With the rapid growth of installed capacity in the world, the requirement for the reliability of power system becomes more and more urgent. Implement of state on-line monitoring and fault diagnosis of the power equipment is the precondition of predicting maintenance, is the key element of reliable run, and is the important supplement and updated development to the traditional off-line preventive maintenance.
In this thesis state on-line monitoring and fault diagnosis of transformer are the research objects. Firstly Least Squares Support Vector Machine (LS-SVM) and Empirical Mode Decomposition (EMD) are deeply studied. After that, they are applied into the fault diagnosis system for transformer, furthermore, study results of both Dissolved Gas Analysis (DGA) and on-line monitoring of Partial Discharge (PD) are given.
DGA is one of the mainly methods on insulation monitoring of transformer, but the accuracy is low because it is difficult to distinguish between failures when overheating and PD coexist. By analyzing all types of faults, two methods are raised. One is the DGA of transformer based on multi-classification LS-SVM. Based on correlation analysis and pretreatment, some key gases are selected as the inputs of LS-SVM, furthermore, fault diagnosis is accomplished according to the concentration distribution of typical fault gases in higher dimensional space. The other is the DGA of transformer by neural network based on particle swarm optimization (PSO) with neighborhood operator. Based on correlation analysis and pretreatment, the key gases are selected as the inputs of neural network, furthermore, fault diagnosis is accomplished by the neural network based on PSO with neighborhood operator. By discussing the experiment results, the methods of this paper have very good classification results, and figure out the problem that is difficult to distinguish between failures when overheating and PD coexist, meanwhile, the effectiveness and usefulness is proved.
In recent years, on-line monitoring of PD has been a focus at home and abroad, and suppression of interference is the difficulty of fault diagnosis. Two methods of suppressing narrow-band interference are proposed in this paper. One is the improved frequency domain analysis based on data extension using least squares support vector regression. Firstly, the actual PD signals with noise are transformed from time domain to frequency domain, then extending the data near the maximum of interference frequency, ultimately the final signals can be obtained by Inverse Fourier Transform (IFT). This method enlarges the range of interference frequency band and removes effectively the interference residue. The other is a new adaptive algorithm based on EMD. First, the mid-signals can be produced by reducing the amplitude of narrow-band interference in frequency region, which is decomposed with EMD, and intrinsic mode functions (IMF) which contain specific frequency can be obtained, then for every IMF adaptive noise canceller is used to suppress narrow-band interference. A new method of denoising based on EMD and reconstruction of IMF is investigated. The PD signals with noise are decomposed with EMD, and IMFs can be obtained, through thresholding and reconstructing every EMF, then the noise can be depressed. Compared with the conventional wavelet-based denoising algorithms, the new algorithm is simpler, more flexible, and not limited by the selection of wavelet function and optimal decomposition level of wavelet, meanwhile, automatic selection of threshold value and thresholding layers of intrinsic mode functions are realized.
本文以变压器状态在线监测与故障诊断系统为研究对象,在深入研究最小二乘支持向量机(LS-SVM)和经验模态分解(EMD)理论的基础上,将其引入到变压器故障诊断系统中,着重对油中溶解气体分析(DGA)和局部放电监测中的信号抗干扰两个方面进行了研究。
DGA是变压器绝缘监督的一个重要手段,但放电和过热两类故障共存时的故障难分辨会导致诊断正判率较低。本文对多种故障类型作了详细分析后提出了两种故障识别方法:基于LS-SVM多分类的DGA方法,通过相关统计分析和数据预处理,选择变压油中典型气体作为LS-SVM的输入,然后利用典型故障气体的相对含量在高维空间的分布特性进行变压器故障类型诊断;基于邻域粒子群算法优化BP神经网络的DGA方法,选择油中典型气体作为神经网络的输入,然后利用训练好的邻域粒子群算法优化后的神经网络进行变压器故障类型诊断。试验结果表明,这两种方法具有很好的分类效果,较好地解决了变压器放电和过热共存时故障的难分辨问题,对故障诊断的正判率较高。
近年来局部放电监测一直是国内外研究的热点问题,而干扰抑制一直是其中的难点。本文针对窄带干扰,提出了两种方法:基于LS-SVM回归的频域分析法,将原始时域信号变换到频域,利用LS-SVM对信号干扰频率最大幅值点附近的数据进行拓延,最后逆变换以得到抑制干扰后的信号,该方法有效地拓展了干扰频带的宽度,较好地抑制了窄带干扰残余;基于EMD和自适应噪声对消的方法,首先在频域中降低干扰幅值,接着利用EMD的分频特性将宽频带的窄带干扰分解到不同频带,各频带内的窄带干扰频率相差有限,然后进行自适应噪声对消。针对白噪声干扰,提出了一种全新的方法:基于EMD和固有模态函数(IMF)重构的方法,首先对含噪的局部放电信号进行EMD,得到含特征频率的IMF,然后对所得的IMF分量进行自适应阈值处理后重构,从而抑制噪声干扰,相比于常规的小波去噪算法,该方法具有自适应性强,不受小波函数和最佳小波分解层数选取的限制等优点,而且实现了阈值和固有模态函数阈值处理层数的自动选取。
With the rapid growth of installed capacity in the world, the requirement for the reliability of power system becomes more and more urgent. Implement of state on-line monitoring and fault diagnosis of the power equipment is the precondition of predicting maintenance, is the key element of reliable run, and is the important supplement and updated development to the traditional off-line preventive maintenance.
In this thesis state on-line monitoring and fault diagnosis of transformer are the research objects. Firstly Least Squares Support Vector Machine (LS-SVM) and Empirical Mode Decomposition (EMD) are deeply studied. After that, they are applied into the fault diagnosis system for transformer, furthermore, study results of both Dissolved Gas Analysis (DGA) and on-line monitoring of Partial Discharge (PD) are given.
DGA is one of the mainly methods on insulation monitoring of transformer, but the accuracy is low because it is difficult to distinguish between failures when overheating and PD coexist. By analyzing all types of faults, two methods are raised. One is the DGA of transformer based on multi-classification LS-SVM. Based on correlation analysis and pretreatment, some key gases are selected as the inputs of LS-SVM, furthermore, fault diagnosis is accomplished according to the concentration distribution of typical fault gases in higher dimensional space. The other is the DGA of transformer by neural network based on particle swarm optimization (PSO) with neighborhood operator. Based on correlation analysis and pretreatment, the key gases are selected as the inputs of neural network, furthermore, fault diagnosis is accomplished by the neural network based on PSO with neighborhood operator. By discussing the experiment results, the methods of this paper have very good classification results, and figure out the problem that is difficult to distinguish between failures when overheating and PD coexist, meanwhile, the effectiveness and usefulness is proved.
In recent years, on-line monitoring of PD has been a focus at home and abroad, and suppression of interference is the difficulty of fault diagnosis. Two methods of suppressing narrow-band interference are proposed in this paper. One is the improved frequency domain analysis based on data extension using least squares support vector regression. Firstly, the actual PD signals with noise are transformed from time domain to frequency domain, then extending the data near the maximum of interference frequency, ultimately the final signals can be obtained by Inverse Fourier Transform (IFT). This method enlarges the range of interference frequency band and removes effectively the interference residue. The other is a new adaptive algorithm based on EMD. First, the mid-signals can be produced by reducing the amplitude of narrow-band interference in frequency region, which is decomposed with EMD, and intrinsic mode functions (IMF) which contain specific frequency can be obtained, then for every IMF adaptive noise canceller is used to suppress narrow-band interference. A new method of denoising based on EMD and reconstruction of IMF is investigated. The PD signals with noise are decomposed with EMD, and IMFs can be obtained, through thresholding and reconstructing every EMF, then the noise can be depressed. Compared with the conventional wavelet-based denoising algorithms, the new algorithm is simpler, more flexible, and not limited by the selection of wavelet function and optimal decomposition level of wavelet, meanwhile, automatic selection of threshold value and thresholding layers of intrinsic mode functions are realized.
引文
[1]王昌长,李福祺,高胜友.电力设备的在线监测与故障诊断[M].北京:清华大学出版社,2006:1-10.
[2]周青山.俄罗斯110-500kV电力变压器运行故障和事故分析[J].电网技术,2003,27(4):76-78.
[3]黄建华,全零三.变电站高压电气设备状态检修的现状及其发展[J].电力系统自动化,2001,25(11):56-59.
[4]Jardine A K S.Optimizing condition based maintenance decisions[C].In the proceedings of Reliability and Maintainability Symposium,Japan,2002:90-97.
[5]苏鹏声,王欢.电力系统设备状态监测与故障诊断技术的分析[J].电力系统自动化,2003,27(1):61-65.
[6]张言苍,张毅刚,徐大可.变压器局部放电在线检测的现状及发展[J].继电器,2004,32(22):70.
[7]柳纲.电力设备故障诊断及状态检修的研究[D].南京:东南大学,2004:1-11.
[8]胡文平,尹项根,张哲,等.分布式变电站高压电气设备在线监测系统设计[J].高电压技术,2003,29(1):53-55.
[9]盛兆顺,尹琦岭.设备状态监测与故障诊断技术及其应用[M].北京:化学工业出版社,2003:1-30.
[10]程鹏,佟来生,吴广宁.大型变压器油中溶解气体在线监测技术进展[J].电力自动化设备,2004,24(11):90-93.
[11]董立新,肖登明,李喆,等.基于油中溶解气体分析数据挖掘的变压器绝缘故障诊断[J].电力系统自动化,2004,28(15):85-88.
[12]章政,杨荆林,肖登明,等.基于油中溶解气体分析的变压器绝缘故障诊断方法的研究和发展[J].电力设备,2004,5(1):20-23.
[13]刘娜,谈克雄,高文胜.基于油中溶解气体谱图的变压器故障识别方法[J].清华大学学报(自然科学版),2003,43(3):301-303.
[14]马翼敏.油中溶解气体的色谱分析在变压器故障诊断中的应用[J].变压器,2005,42(8):83-84.
[15]柳泽荣,丁在兴,翟岩,等.油色谱分析在变压器故障诊断中的应用[J].变压器,2005,42(9):43-46.
[16]郭俊,吴广宁,张血琴,等.局部放电检测技术的现状和发展[J].电工技术学报,2005,22(2):29-35.
[17]王颂,吴晓辉,袁鹏,等.局部放电超高频检测系统标定方法的研究现状及发展[J].高压电器,2007,43(1):59-61.
[18]徐晴,包玉树.变压器局部放电试验若干问题的探讨[J].高电压技术,2007,33(4):189-191.
[19]操敦奎.变压器油中气体分析诊断与故障检查[M].北京:中国电力出版社,2005:80-105.
[20]G L Marton.The Hydran-a System for the Detection and Monitoring of Failure Conditions in Power Transformers[J].IEEE Colloquium on Monitors and Condition Assessment Equipment,1996,3:1-5.
[21]T Mcgrail,A Wilson.On-line Gas Sensor[J]IEEE Colloquium on Conditon Monitoring of Large Machines and Power Transformers,2001,1:1-4.
[22]S Birlasekaran,G Ledwich.Use of FFT and ANN Techniques in Monitoring of Transformer Fault Gases[J].Proceedings of International Symposium on Electrical Insulating Materials,1998:75-78.
[23]B Spading.Managing the Life of Transformers.RCM for Substation[C].Transmission and Distribution Conference,1999:17-19.
[24]M D Judd,G P Cleary,etc.Power transformer Monitoring Using UHF Sensors[C],Conference Record of the 2002 IEEE International Symposium on Electrical Insulation.Boston,MA USA,2002(4):7-10.
[25]F.J.Zhou.Assembly on Tran Series of Transformer Incipient Fault Monitor[J].Beijing Ligong Modern Electric Equipment Co.Limited,2000:32-35.
[26]方琼,冯义,王凯,等.电力变压器用数字化局部放电在线监测系统[J].高电压技术,2002,28(7):25-27.
[27]陈江波,付锡年,聂德鑫,等.UFIV变压器故障监测与诊断的信息决策平台[J].高电压技术,2006,32(12):108-110.
[28]Scholkopf B,Burges C,Smola A J et al.Advances in kernel methods-support vector learning [M].Cambridge,MA:MIT press,1998:22-100.
[29]Burges C J C.A tutorial on support vector machines for pattern recognition[J].Data mining and knowledge discovery,1998,2(2):1-47.
[30]孙德山.支持向量机分类与回归方法研究[D].长沙:中南大学,2004:22-40.
[31]曾嵘.支持向量机在设备故障诊断中的应用研究[D].长沙:中南大学,2005:15-40.
[32]赵晶,张旭东,高隽.基于支持向量机的多类形状识别系统[J].合肥工业大学学报(自然科学版),2004,27(1):23-26.
[33]刘志刚,李德仁,秦前清,等.支持向量机在多类分类问题中的推广[J].计算机工程与应用,2004,7:10-13.
[34]孙即祥.现代模式多类识别[M].长沙:国防科技大学出版社,2002:1-50.
[35]文明,方凯,汪方斌,等.一种基于SVM的多类判别算法[J].工业仪表与自动化装置,2006,6:6-8.
[36]余艳芳,高大启.一种改进的最小二乘支持向量机及其应用[J].计算机工程与科学,2006,28(2):69-71.
[37]Francessco Masulli,Giorgio Valentini.Comparing decomposition methods for classification[C].Fourth international conference on knowledge-based intelligent engineering,Systems and technologies,2000:788-792.
[38]Dietterich T G,Bakiri G.Solving Multiclass learning problems via Error-Correcting Output Codes [J].Journal of Arti-ficial intelligence research,1995,(2):263-286.
[39]潘明清.基于支持向量机的机械故障模式分类研究[D].抗州:浙江大学,2005:15-30.
[40]贾嵘,蔡振华,康睿,等.基于最小二乘支持向量机的系统边际电价预测[J].高电压技术,2006,32(11):145-148.
[41]Suykens J A K,De Brabanter J,Lukas L,et al.Weighted least squares support vector machines:robustness and sparse approximation[J].Neurocomputing,2002,48(1-4):85-105.
[42]Suykeus J A K.,Vandewalle J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[43]Suykens J A K.,Vandewalle J,De Moor B.Optimal control by least squares support vector machines[J].Neural Networks,2001,(14):23-35.
[44]许亚洲.基于最小二乘支持向量机的数控机床热误差建模的研究[D].杭州:浙江大学,2006:9-41.
[45]Huang N E,Zheng S,Steven R L,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proc.R.Soc.London.A,1998,454:903-995.
[46]Kang Huang,Dave Tateh Chang,Thomas Hou.A bridge monitoring method based on vibration characteristics under a transient load[J].Proceeding of the international symposium of civil engineering in the 21st century,2000:563-565.
[47]Qiang G,Xiaojiang M,Haiyong Z.The partial wave method for the analysis of non-stationary signals and its use in machine fault diagnosis[J].Proceedings of the international symposium on test and measurement,2001,2:1465-1468.
[48]Gravier B M,Pelstring J A.An assessment of the application of the Hilbert spectrum to the fatigue analysis of marine risers[J].Proceedings of the international offshore and polar engineering conference,2001,2:268-275.
[49]Loh CH,Wu T C,Huang N E.Application of the empirical mode decomposition-Hilbert spectrum method to identify near-fault ground-motion characteristics and structural responses[J].BULLETIN OF THE SEISMOLOGICAL SOCIETY OF AMERICA,2001,91(5):1339-1357.
[50]Zhang Haiyong,Ma Xiaojiang,Gaiqiang.Wigner-Ville distribution based on intrinsic mode function[C].Pro.OflCR,Beijing,2001:1015-1017.
[51]Timashev SA,Shalin MG.Precise analysis of non-stationary vibration processes using the Hilbert transform[J].ACSIM 2000 Proceeding,2000,395-404.
[52]高云超.希尔伯特-黄变换方法的仿真研究[D].哈尔滨:哈尔滨工程大学,2005:14-32.
[53]Huang N E,M C Wu.A confidence limit for empirical mode decomposition and Hilbert spectral analysis[J].Proc.R.Soc.London,Ser.A,2003,459:2317-2345.
[54]Wu Z,Huang N E.A study of the characteristics of white noise using the empirical mode decomposition method[J].Proceedings of the Royal Society of London,Series A,2004,460:1597-1611.
[55]Gloersen P,Huang N E.Comparison of interannual intrinsic modes in hemispheric sea ice covers and other geophysical parameters[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(5):1062-1074.
[56]Huang N E,M L Wu.Application of Hilbert-Huang transform to non-stationary financial time series analysis[J].Applied Stochastic M- odels in Business and Industry,2003,19(6):245-268.
[57]王波,杨洪耕.电力系统电压短期扰动的三角模态检测方法[J].电工技术学报,2005,20(11):101-105.
[58]程军圣,于德介,杨宇.EMD方法在转子局部碰摩故障诊断中的应用[J].振动、测试与诊断,2006,26(1):24-27.
[59]李天云,赵妍,季小慧,等.HHT方法在电力系统故障信号分析中的应用[J].电工技术学报,2005,20(6):87-91.
[60]贾嵘,王小宇,张丽,等.基于EMD和AR模型的水轮机尾水管动态特征信息提取[J].电力系统及其自动化,2006,30(22):77-80.
[61]胡劲松,杨世锡.基于HHT的转子横向裂纹故障诊断[J].动力工程,2004,24(2):218-221.
[62]贾嵘,王小宇,蔡振华,等.经验模式分解的改进及其在发电机组振动信号处理中的应用[J].机械科学与技术,2007,26(5):626-630.
[63]贾嵘,王小宇,蔡振华,等.基于最小二乘支持向量机回归的Hilbert-Huang变换及其在发电机组故障诊断中的应用[J].中国电机工程学报,2006,26(22):128-133.
[64]牛发亮,黄进,杨家强,等.基于感应电机启动电磁转矩Hilbert-Huang变换的转子断条故障诊断[J].中国电机工程学报,2005,25(11):107-112.
[65]冯志鹏,褚福磊.基于Hilbert-Huang变换的水轮机非平稳压力脉动信号分析[J].中国电机工程学报,2005,25(10):111-115.
[66]成永红.电力设备绝缘检测与诊断[M].北京:中国电力出版社,2001,8:100-105.
[67]夏建涛,何明一.支持向量机与纠错编码相结合的多类分类算法[J].西北工业大学学报,2003,21(4):443-445.
[68]夏建涛.基于机器学习的高维多光谱数据分类[D].西安:西北工业大学,2002:35-55.
[69]SHI Yu-hui.EBERHART R.A modified particle swarm optimizer[C]//Proc IEEE Int conf on Evolutionary Computation Anchorage.IEEE,1998:69-73.
[70]EBERHART R.KENNEDY J.A new optimizer using particle swarm theory[C]//Proc 6th Int Symposium on Micro Machine Human Science,Nagoya.[s.n.].1995:39-43.
[71]曹铁泽.变压器油中溶解气体色谱在线监测系统关键技术研究[D].燕山:燕山大学,2004:20-50.
[72]罗建波.基于DGA的电力变压器故障诊断技术研究[D].杭州:浙江大学,2005:9-40.
[73]张允.基于神经网络的变压器油色谱在线监测与故障诊断系统[D].吉林:吉林大学,2004:15-53.
[74]徐志钮.基于油中溶解气体分析的变压器绝缘故障诊断研究[D].北京:华北电力大学,2004:11-44.
[75]黄伟.变压器油中溶解气体在线监测系统及其故障诊断方法研究[D].长沙:湖南大学,2005:17-48.
[76]徐安定.大型变压器状态监测与故障诊断技术[D].杭州:浙江大学,2005:20-55.
[77]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005:231.
[78]王少芳,蔡金锭,刘庆珍.基于改进GA-BP混合算法的电力变压器故障诊断[J].电网技术,2004,28(4):30-33.
[79]王少芳,蔡金锭.GA-BP算法在变压器色谱诊断中的应用[J].高电压技术,2003,29(7):3-6.
[80]剑光.变电设备状态检修应用研究[D].杭州:浙江大学,2004:12-40.
[81]莫娟,王雪,董明,等.基于粗糙集理论的电力变压器故障诊断方法[J].中国电机工程学报,2004,24(7):162-166.
[82]王楠,律方成,刘云鹏,等.基于粗糙集理论与模糊Petri网络的油浸电力变压器综合故障诊断[J].中国电机工程学报,2003,23(12):127-131.
[83]董明,孟源源,徐长响,等.基于支持向量机及油中溶解气体分析的大型电力变压器故障诊断模型研究[J].中国电机工程学报,2003,23(7):88-92.
[84]孙才新,李俭,郑海平,等.基于灰色面积关联度分析的电力变压器绝缘故障诊断方法[J].电网技术,2002,26(7):24-29.
[85]李俭,孙才新,陈伟根,等.基于灰色聚类分析的充油电力变压器绝缘故障诊断的研究[J].电工技术学报,2002,17(4):80-83.
[86]宋斌,于萍,罗运柏,等.基于灰关联熵的充油变压器故障诊断方法[J].电力系统自动化,2005,29(18):76-78.
[87]柳纲,郭基伟,唐国庆,等.基于灰色位势理论的变压器故障诊断算法[J].电力系统自动化学报,2004,16(2):54-57.
[88]吴立增,朱永利,苑津莎,等.基于贝叶斯网络分类器的变压器综合故障诊断方法[J].电工技术学报,2005,20(4):45-50.
[89]王永强,律方成,李和明,等.基于贝叶斯网络和油中溶解气体分析的变压器故障诊断方法[J].电工技术学报,2004,19(12):74-77.
[90]黄文涛,赵学增,王伟杰,等.基于物元模型的电力变压器故障的可拓诊断方法[J].电力系统自动化,2004,28(13):45-49.
[91]彭宁云,文习山,王一,等.基于线性分类器的充油变压器潜伏性故障诊断方法[J].中国电 机工程学报,2004,24(6):147-151.
[92]孙辉,李卫东,孙启忠,等.判决树方法用于变压器故障诊断的研究[J].中国电机工程学报,2001,21(2):50-55.
[93]王楠,律方成,刘云鹏,等.基于决策表约简的变压器故障诊断Petri网络模型及其应用研究[J].电工技术学报,2003,18(6):88-93.
[94]Angeline P J.Using Selection to Improve Particle Swarm Optimization[R].IEEE International Conference on Evolutionary Computation,Anchorage,Alaska,1998.
[95]Suganthan P N.Particle Swarm Optimizer with neighborhood Operator[R].Proceedings of Congress on Evolutionary Computation,1999.
[96]Parsopoulos K E,et al.Stretching Technique for Obtaining Global Minimizers through Particle Swarm Optimization[R].Proceedings of the Workshop on PSO,Indianapolis Purdue school of Engineering and Technology,2001.
[97]贾嵘,徐其惠,李辉,等.基于邻域粒子群优化神经网络的变压器故障诊断[J].高压电器,2008,44(1):8-10.
[98]Platt J,Cristianini N,Shawe-Taylor J.Large Margin DAG's for Multiclass Classification [J].Advances in Neural Information Processing Systems.2000:547-553.
[99]贾嵘,徐其惠,李辉,等.最小二乘支持向量机多分类在变压器故障诊断中的应用研究[J].高电压技术,2007,33(6):110-113.
[100]杨恩星.一种新型局部放电在线监测装置的研究[D].沈阳:沈阳工业大学,2003:20-40.
[101]Mangeret R et al.Optical Detection of Partial Discharges Using Fluorescent Fiber[J].IEEE Trans.on Elect.Insul,1991,26(4):783-789.
[102]王贤.变压器局部放电测量中抗干扰方法的试验研究[D].北京:华北电力大学(北京),2003:5-25.
[103]H.Bosi,M.Haitje.Application of rogowski coils for partial discharge decoupling and noise suppression[J].Prec.of 5th 2sh,1978mBraunschweig,No.42.02.
[104]R Malewski,et al.Insulation diagnostic system for HV power transformer in service[J].IREQ.CIGRE,1986,12-01.
[105]Luo Bin,Sun Caixin,et al.A new method of noise suppression for on-line monitoring Partial discharge in transformers[J].Proc.of 9th ISH,1995,G raz,No.5587.
[106]A.Krivda.Automated Recognition of Partial Discharges[J],IEEE Trans.on Dielectrics and Electrical Insulation,1995,2(1):796-821.
[107]孙才新,罗兵等.变压器局放在线监测中抗电磁干扰的定向耦合差动平衡法的研究[J].中国电机工程学报,1998,(5):340-344.
[108]V.Nagesh and B.LGururaj.Evaluation of Digital Filter for Rejepting Discrete Spectral Interference in On-site PD Measurements[J].IEEE Transactions on Electrical Insulation,1993,28(1):73-85.
[109]王志贤.最优状态估计与系统辨识[M].西安:西北工业大学出版社,2004:78.
[110]U.Kopf and K.Feser.Rejeption of Narrow-band Noise and Repititive Pulse in On-site PD Measurements[J].IEEE Transactions on Dielectrics and Electrical Insulation,1995,12(6):126-132.
[111]胡明友,谢恒堃.基于人工神经网络的绝缘局部放电信号提取方法的研究[J].高电压技术,1999,25(2):35-36.
[112]Tai-Chiu Hsung,Daniel Pakokong Lun,and Wan-Chi siu.Denoising by Ingularity Detection [J].IEEE Trans,On Signal Processing,1999,47(11):3139-3144.
[113]徐淑珍.小波分析在变压器局部放电在线监测中的应用研究[D].上海:上海交通大学,2001:33-49.
[114]乐波,曹戌平,李俭,等.局部放电在线监测中的自适应数字滤波器研究[J].西安交通大学学报,2003,37(6):617-621.
[115]黄成军,郁惟镛.基于小波分解的自适应滤波算法在抑制局部放电窄带周期干扰中的应用[J].中国电机工程学报,2003,23(1):107-111.
[116]毕为民,唐炬,姚陈果,等.基于熵阈值的小波包变换抑制局部放电窄带干扰的研究[J].中国电机工程学报,2003,23(5):128-131.
[117]徐剑,黄成军.局部放电窄带干扰抑制中改进快速傅里叶变换频域阈值算法的研究[J].电网技术,2004,28(13):80-83.
[118]于鹏娟,聂卫东.一种可用于局部放电在线检测的数字滤波器[J].变压器,1999,36(2):30-33.
[119]唐炬,孙才新,许中荣,等.局部放电信号中的白噪声和窄带干扰[J].高电压技术,2002,28(12):8-10.
[120]贾嵘,徐其惠,田录林,等.基于经验模态分解的水轮发电机组局部放电信号提取[J].水力发电学报,2007,26(4):146-150.
[121]唐炬,谢颜斌,朱伟.用于复小波变换的EWC阈值法抑制周期性窄带干扰[J].电力系统自动化,2005,29(7):43-47.
[122]Satish L,Nazneen B.Wavelet-based denoising of partial discharge signals buried in excessive noise and interference[J].IEEE Trans.on Dielectrics and Electrical Insulation,2003,10(2):354-367.
[123]贾嵘,徐其惠,田录林,等.基于经验模态分解和固有模态函数重构的局部放电干扰抑制方法[J].电工技术学报,2008,23(1):13-18.
[2]周青山.俄罗斯110-500kV电力变压器运行故障和事故分析[J].电网技术,2003,27(4):76-78.
[3]黄建华,全零三.变电站高压电气设备状态检修的现状及其发展[J].电力系统自动化,2001,25(11):56-59.
[4]Jardine A K S.Optimizing condition based maintenance decisions[C].In the proceedings of Reliability and Maintainability Symposium,Japan,2002:90-97.
[5]苏鹏声,王欢.电力系统设备状态监测与故障诊断技术的分析[J].电力系统自动化,2003,27(1):61-65.
[6]张言苍,张毅刚,徐大可.变压器局部放电在线检测的现状及发展[J].继电器,2004,32(22):70.
[7]柳纲.电力设备故障诊断及状态检修的研究[D].南京:东南大学,2004:1-11.
[8]胡文平,尹项根,张哲,等.分布式变电站高压电气设备在线监测系统设计[J].高电压技术,2003,29(1):53-55.
[9]盛兆顺,尹琦岭.设备状态监测与故障诊断技术及其应用[M].北京:化学工业出版社,2003:1-30.
[10]程鹏,佟来生,吴广宁.大型变压器油中溶解气体在线监测技术进展[J].电力自动化设备,2004,24(11):90-93.
[11]董立新,肖登明,李喆,等.基于油中溶解气体分析数据挖掘的变压器绝缘故障诊断[J].电力系统自动化,2004,28(15):85-88.
[12]章政,杨荆林,肖登明,等.基于油中溶解气体分析的变压器绝缘故障诊断方法的研究和发展[J].电力设备,2004,5(1):20-23.
[13]刘娜,谈克雄,高文胜.基于油中溶解气体谱图的变压器故障识别方法[J].清华大学学报(自然科学版),2003,43(3):301-303.
[14]马翼敏.油中溶解气体的色谱分析在变压器故障诊断中的应用[J].变压器,2005,42(8):83-84.
[15]柳泽荣,丁在兴,翟岩,等.油色谱分析在变压器故障诊断中的应用[J].变压器,2005,42(9):43-46.
[16]郭俊,吴广宁,张血琴,等.局部放电检测技术的现状和发展[J].电工技术学报,2005,22(2):29-35.
[17]王颂,吴晓辉,袁鹏,等.局部放电超高频检测系统标定方法的研究现状及发展[J].高压电器,2007,43(1):59-61.
[18]徐晴,包玉树.变压器局部放电试验若干问题的探讨[J].高电压技术,2007,33(4):189-191.
[19]操敦奎.变压器油中气体分析诊断与故障检查[M].北京:中国电力出版社,2005:80-105.
[20]G L Marton.The Hydran-a System for the Detection and Monitoring of Failure Conditions in Power Transformers[J].IEEE Colloquium on Monitors and Condition Assessment Equipment,1996,3:1-5.
[21]T Mcgrail,A Wilson.On-line Gas Sensor[J]IEEE Colloquium on Conditon Monitoring of Large Machines and Power Transformers,2001,1:1-4.
[22]S Birlasekaran,G Ledwich.Use of FFT and ANN Techniques in Monitoring of Transformer Fault Gases[J].Proceedings of International Symposium on Electrical Insulating Materials,1998:75-78.
[23]B Spading.Managing the Life of Transformers.RCM for Substation[C].Transmission and Distribution Conference,1999:17-19.
[24]M D Judd,G P Cleary,etc.Power transformer Monitoring Using UHF Sensors[C],Conference Record of the 2002 IEEE International Symposium on Electrical Insulation.Boston,MA USA,2002(4):7-10.
[25]F.J.Zhou.Assembly on Tran Series of Transformer Incipient Fault Monitor[J].Beijing Ligong Modern Electric Equipment Co.Limited,2000:32-35.
[26]方琼,冯义,王凯,等.电力变压器用数字化局部放电在线监测系统[J].高电压技术,2002,28(7):25-27.
[27]陈江波,付锡年,聂德鑫,等.UFIV变压器故障监测与诊断的信息决策平台[J].高电压技术,2006,32(12):108-110.
[28]Scholkopf B,Burges C,Smola A J et al.Advances in kernel methods-support vector learning [M].Cambridge,MA:MIT press,1998:22-100.
[29]Burges C J C.A tutorial on support vector machines for pattern recognition[J].Data mining and knowledge discovery,1998,2(2):1-47.
[30]孙德山.支持向量机分类与回归方法研究[D].长沙:中南大学,2004:22-40.
[31]曾嵘.支持向量机在设备故障诊断中的应用研究[D].长沙:中南大学,2005:15-40.
[32]赵晶,张旭东,高隽.基于支持向量机的多类形状识别系统[J].合肥工业大学学报(自然科学版),2004,27(1):23-26.
[33]刘志刚,李德仁,秦前清,等.支持向量机在多类分类问题中的推广[J].计算机工程与应用,2004,7:10-13.
[34]孙即祥.现代模式多类识别[M].长沙:国防科技大学出版社,2002:1-50.
[35]文明,方凯,汪方斌,等.一种基于SVM的多类判别算法[J].工业仪表与自动化装置,2006,6:6-8.
[36]余艳芳,高大启.一种改进的最小二乘支持向量机及其应用[J].计算机工程与科学,2006,28(2):69-71.
[37]Francessco Masulli,Giorgio Valentini.Comparing decomposition methods for classification[C].Fourth international conference on knowledge-based intelligent engineering,Systems and technologies,2000:788-792.
[38]Dietterich T G,Bakiri G.Solving Multiclass learning problems via Error-Correcting Output Codes [J].Journal of Arti-ficial intelligence research,1995,(2):263-286.
[39]潘明清.基于支持向量机的机械故障模式分类研究[D].抗州:浙江大学,2005:15-30.
[40]贾嵘,蔡振华,康睿,等.基于最小二乘支持向量机的系统边际电价预测[J].高电压技术,2006,32(11):145-148.
[41]Suykens J A K,De Brabanter J,Lukas L,et al.Weighted least squares support vector machines:robustness and sparse approximation[J].Neurocomputing,2002,48(1-4):85-105.
[42]Suykeus J A K.,Vandewalle J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[43]Suykens J A K.,Vandewalle J,De Moor B.Optimal control by least squares support vector machines[J].Neural Networks,2001,(14):23-35.
[44]许亚洲.基于最小二乘支持向量机的数控机床热误差建模的研究[D].杭州:浙江大学,2006:9-41.
[45]Huang N E,Zheng S,Steven R L,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proc.R.Soc.London.A,1998,454:903-995.
[46]Kang Huang,Dave Tateh Chang,Thomas Hou.A bridge monitoring method based on vibration characteristics under a transient load[J].Proceeding of the international symposium of civil engineering in the 21st century,2000:563-565.
[47]Qiang G,Xiaojiang M,Haiyong Z.The partial wave method for the analysis of non-stationary signals and its use in machine fault diagnosis[J].Proceedings of the international symposium on test and measurement,2001,2:1465-1468.
[48]Gravier B M,Pelstring J A.An assessment of the application of the Hilbert spectrum to the fatigue analysis of marine risers[J].Proceedings of the international offshore and polar engineering conference,2001,2:268-275.
[49]Loh CH,Wu T C,Huang N E.Application of the empirical mode decomposition-Hilbert spectrum method to identify near-fault ground-motion characteristics and structural responses[J].BULLETIN OF THE SEISMOLOGICAL SOCIETY OF AMERICA,2001,91(5):1339-1357.
[50]Zhang Haiyong,Ma Xiaojiang,Gaiqiang.Wigner-Ville distribution based on intrinsic mode function[C].Pro.OflCR,Beijing,2001:1015-1017.
[51]Timashev SA,Shalin MG.Precise analysis of non-stationary vibration processes using the Hilbert transform[J].ACSIM 2000 Proceeding,2000,395-404.
[52]高云超.希尔伯特-黄变换方法的仿真研究[D].哈尔滨:哈尔滨工程大学,2005:14-32.
[53]Huang N E,M C Wu.A confidence limit for empirical mode decomposition and Hilbert spectral analysis[J].Proc.R.Soc.London,Ser.A,2003,459:2317-2345.
[54]Wu Z,Huang N E.A study of the characteristics of white noise using the empirical mode decomposition method[J].Proceedings of the Royal Society of London,Series A,2004,460:1597-1611.
[55]Gloersen P,Huang N E.Comparison of interannual intrinsic modes in hemispheric sea ice covers and other geophysical parameters[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(5):1062-1074.
[56]Huang N E,M L Wu.Application of Hilbert-Huang transform to non-stationary financial time series analysis[J].Applied Stochastic M- odels in Business and Industry,2003,19(6):245-268.
[57]王波,杨洪耕.电力系统电压短期扰动的三角模态检测方法[J].电工技术学报,2005,20(11):101-105.
[58]程军圣,于德介,杨宇.EMD方法在转子局部碰摩故障诊断中的应用[J].振动、测试与诊断,2006,26(1):24-27.
[59]李天云,赵妍,季小慧,等.HHT方法在电力系统故障信号分析中的应用[J].电工技术学报,2005,20(6):87-91.
[60]贾嵘,王小宇,张丽,等.基于EMD和AR模型的水轮机尾水管动态特征信息提取[J].电力系统及其自动化,2006,30(22):77-80.
[61]胡劲松,杨世锡.基于HHT的转子横向裂纹故障诊断[J].动力工程,2004,24(2):218-221.
[62]贾嵘,王小宇,蔡振华,等.经验模式分解的改进及其在发电机组振动信号处理中的应用[J].机械科学与技术,2007,26(5):626-630.
[63]贾嵘,王小宇,蔡振华,等.基于最小二乘支持向量机回归的Hilbert-Huang变换及其在发电机组故障诊断中的应用[J].中国电机工程学报,2006,26(22):128-133.
[64]牛发亮,黄进,杨家强,等.基于感应电机启动电磁转矩Hilbert-Huang变换的转子断条故障诊断[J].中国电机工程学报,2005,25(11):107-112.
[65]冯志鹏,褚福磊.基于Hilbert-Huang变换的水轮机非平稳压力脉动信号分析[J].中国电机工程学报,2005,25(10):111-115.
[66]成永红.电力设备绝缘检测与诊断[M].北京:中国电力出版社,2001,8:100-105.
[67]夏建涛,何明一.支持向量机与纠错编码相结合的多类分类算法[J].西北工业大学学报,2003,21(4):443-445.
[68]夏建涛.基于机器学习的高维多光谱数据分类[D].西安:西北工业大学,2002:35-55.
[69]SHI Yu-hui.EBERHART R.A modified particle swarm optimizer[C]//Proc IEEE Int conf on Evolutionary Computation Anchorage.IEEE,1998:69-73.
[70]EBERHART R.KENNEDY J.A new optimizer using particle swarm theory[C]//Proc 6th Int Symposium on Micro Machine Human Science,Nagoya.[s.n.].1995:39-43.
[71]曹铁泽.变压器油中溶解气体色谱在线监测系统关键技术研究[D].燕山:燕山大学,2004:20-50.
[72]罗建波.基于DGA的电力变压器故障诊断技术研究[D].杭州:浙江大学,2005:9-40.
[73]张允.基于神经网络的变压器油色谱在线监测与故障诊断系统[D].吉林:吉林大学,2004:15-53.
[74]徐志钮.基于油中溶解气体分析的变压器绝缘故障诊断研究[D].北京:华北电力大学,2004:11-44.
[75]黄伟.变压器油中溶解气体在线监测系统及其故障诊断方法研究[D].长沙:湖南大学,2005:17-48.
[76]徐安定.大型变压器状态监测与故障诊断技术[D].杭州:浙江大学,2005:20-55.
[77]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005:231.
[78]王少芳,蔡金锭,刘庆珍.基于改进GA-BP混合算法的电力变压器故障诊断[J].电网技术,2004,28(4):30-33.
[79]王少芳,蔡金锭.GA-BP算法在变压器色谱诊断中的应用[J].高电压技术,2003,29(7):3-6.
[80]剑光.变电设备状态检修应用研究[D].杭州:浙江大学,2004:12-40.
[81]莫娟,王雪,董明,等.基于粗糙集理论的电力变压器故障诊断方法[J].中国电机工程学报,2004,24(7):162-166.
[82]王楠,律方成,刘云鹏,等.基于粗糙集理论与模糊Petri网络的油浸电力变压器综合故障诊断[J].中国电机工程学报,2003,23(12):127-131.
[83]董明,孟源源,徐长响,等.基于支持向量机及油中溶解气体分析的大型电力变压器故障诊断模型研究[J].中国电机工程学报,2003,23(7):88-92.
[84]孙才新,李俭,郑海平,等.基于灰色面积关联度分析的电力变压器绝缘故障诊断方法[J].电网技术,2002,26(7):24-29.
[85]李俭,孙才新,陈伟根,等.基于灰色聚类分析的充油电力变压器绝缘故障诊断的研究[J].电工技术学报,2002,17(4):80-83.
[86]宋斌,于萍,罗运柏,等.基于灰关联熵的充油变压器故障诊断方法[J].电力系统自动化,2005,29(18):76-78.
[87]柳纲,郭基伟,唐国庆,等.基于灰色位势理论的变压器故障诊断算法[J].电力系统自动化学报,2004,16(2):54-57.
[88]吴立增,朱永利,苑津莎,等.基于贝叶斯网络分类器的变压器综合故障诊断方法[J].电工技术学报,2005,20(4):45-50.
[89]王永强,律方成,李和明,等.基于贝叶斯网络和油中溶解气体分析的变压器故障诊断方法[J].电工技术学报,2004,19(12):74-77.
[90]黄文涛,赵学增,王伟杰,等.基于物元模型的电力变压器故障的可拓诊断方法[J].电力系统自动化,2004,28(13):45-49.
[91]彭宁云,文习山,王一,等.基于线性分类器的充油变压器潜伏性故障诊断方法[J].中国电 机工程学报,2004,24(6):147-151.
[92]孙辉,李卫东,孙启忠,等.判决树方法用于变压器故障诊断的研究[J].中国电机工程学报,2001,21(2):50-55.
[93]王楠,律方成,刘云鹏,等.基于决策表约简的变压器故障诊断Petri网络模型及其应用研究[J].电工技术学报,2003,18(6):88-93.
[94]Angeline P J.Using Selection to Improve Particle Swarm Optimization[R].IEEE International Conference on Evolutionary Computation,Anchorage,Alaska,1998.
[95]Suganthan P N.Particle Swarm Optimizer with neighborhood Operator[R].Proceedings of Congress on Evolutionary Computation,1999.
[96]Parsopoulos K E,et al.Stretching Technique for Obtaining Global Minimizers through Particle Swarm Optimization[R].Proceedings of the Workshop on PSO,Indianapolis Purdue school of Engineering and Technology,2001.
[97]贾嵘,徐其惠,李辉,等.基于邻域粒子群优化神经网络的变压器故障诊断[J].高压电器,2008,44(1):8-10.
[98]Platt J,Cristianini N,Shawe-Taylor J.Large Margin DAG's for Multiclass Classification [J].Advances in Neural Information Processing Systems.2000:547-553.
[99]贾嵘,徐其惠,李辉,等.最小二乘支持向量机多分类在变压器故障诊断中的应用研究[J].高电压技术,2007,33(6):110-113.
[100]杨恩星.一种新型局部放电在线监测装置的研究[D].沈阳:沈阳工业大学,2003:20-40.
[101]Mangeret R et al.Optical Detection of Partial Discharges Using Fluorescent Fiber[J].IEEE Trans.on Elect.Insul,1991,26(4):783-789.
[102]王贤.变压器局部放电测量中抗干扰方法的试验研究[D].北京:华北电力大学(北京),2003:5-25.
[103]H.Bosi,M.Haitje.Application of rogowski coils for partial discharge decoupling and noise suppression[J].Prec.of 5th 2sh,1978mBraunschweig,No.42.02.
[104]R Malewski,et al.Insulation diagnostic system for HV power transformer in service[J].IREQ.CIGRE,1986,12-01.
[105]Luo Bin,Sun Caixin,et al.A new method of noise suppression for on-line monitoring Partial discharge in transformers[J].Proc.of 9th ISH,1995,G raz,No.5587.
[106]A.Krivda.Automated Recognition of Partial Discharges[J],IEEE Trans.on Dielectrics and Electrical Insulation,1995,2(1):796-821.
[107]孙才新,罗兵等.变压器局放在线监测中抗电磁干扰的定向耦合差动平衡法的研究[J].中国电机工程学报,1998,(5):340-344.
[108]V.Nagesh and B.LGururaj.Evaluation of Digital Filter for Rejepting Discrete Spectral Interference in On-site PD Measurements[J].IEEE Transactions on Electrical Insulation,1993,28(1):73-85.
[109]王志贤.最优状态估计与系统辨识[M].西安:西北工业大学出版社,2004:78.
[110]U.Kopf and K.Feser.Rejeption of Narrow-band Noise and Repititive Pulse in On-site PD Measurements[J].IEEE Transactions on Dielectrics and Electrical Insulation,1995,12(6):126-132.
[111]胡明友,谢恒堃.基于人工神经网络的绝缘局部放电信号提取方法的研究[J].高电压技术,1999,25(2):35-36.
[112]Tai-Chiu Hsung,Daniel Pakokong Lun,and Wan-Chi siu.Denoising by Ingularity Detection [J].IEEE Trans,On Signal Processing,1999,47(11):3139-3144.
[113]徐淑珍.小波分析在变压器局部放电在线监测中的应用研究[D].上海:上海交通大学,2001:33-49.
[114]乐波,曹戌平,李俭,等.局部放电在线监测中的自适应数字滤波器研究[J].西安交通大学学报,2003,37(6):617-621.
[115]黄成军,郁惟镛.基于小波分解的自适应滤波算法在抑制局部放电窄带周期干扰中的应用[J].中国电机工程学报,2003,23(1):107-111.
[116]毕为民,唐炬,姚陈果,等.基于熵阈值的小波包变换抑制局部放电窄带干扰的研究[J].中国电机工程学报,2003,23(5):128-131.
[117]徐剑,黄成军.局部放电窄带干扰抑制中改进快速傅里叶变换频域阈值算法的研究[J].电网技术,2004,28(13):80-83.
[118]于鹏娟,聂卫东.一种可用于局部放电在线检测的数字滤波器[J].变压器,1999,36(2):30-33.
[119]唐炬,孙才新,许中荣,等.局部放电信号中的白噪声和窄带干扰[J].高电压技术,2002,28(12):8-10.
[120]贾嵘,徐其惠,田录林,等.基于经验模态分解的水轮发电机组局部放电信号提取[J].水力发电学报,2007,26(4):146-150.
[121]唐炬,谢颜斌,朱伟.用于复小波变换的EWC阈值法抑制周期性窄带干扰[J].电力系统自动化,2005,29(7):43-47.
[122]Satish L,Nazneen B.Wavelet-based denoising of partial discharge signals buried in excessive noise and interference[J].IEEE Trans.on Dielectrics and Electrical Insulation,2003,10(2):354-367.
[123]贾嵘,徐其惠,田录林,等.基于经验模态分解和固有模态函数重构的局部放电干扰抑制方法[J].电工技术学报,2008,23(1):13-18.