基于S变换的电能质量扰动分析
|
摘要
随着国民经济和科学技术的迅猛发展,电力系统中的非线性、冲击性、非对称性负荷显著增加,电能质量问题带来的经济损失越来越严重,如何有效的治理电能质量问题已经成为广大科技工作者研究的重点。改善和提高电能质量的首要前提是对电能质量扰动类型进行检测、分析与识别,只有快速准确地检测出电能质量问题,并进行有效的分析,识别扰动的类型,才能对其进行有效的控制和治理。
本文系统地分析了电能质量问题的分类、产生原因及主要分析方法,并构建了电能质量扰动较完善的信号模型。利用目前电力系统中广泛应用的时频分析方法小波变换,对暂态电能质量扰动进行了时间定位,并分析了小波变换在处理电能质量扰动检测上的优点和性能。利用S变换对常见电能质量扰动的特征信息进行了检测,并分析了S变换在处理电能质量扰动检测上的优点。比较了小波变换和S变换在处理电能质量扰动问题时的区别,分析结果表明S变换比小波变换更适合应用于电能质量扰动检测与识别领域。
为了实现电能质量扰动信号自动分类和识别,本文提出了一种基于S变换和最小二乘支持向量机的电能质量扰动分类识别的新方法：S变换主要用于提取电能质量扰动的特征向量；最小二乘支持向量机主要用于根据提取的特征向量对电能质量扰动进行分类识别。仿真结果表明,该方法识别准确率高,抗噪能力强,且训练样本少,训练时间短,适用于电能质量扰动辨识系统。
最后,本文设计了基于DSP5416的电能质量分析实验平台的硬件电路,为进一步分析处理电能质量问题提供了基础。硬件电路主要由5个部分组成：数据采集模块、数据处理模块、串行通信模块、电源模块及复位模块。其中数据采集模块由信号调理电路和模数转换电路构成,数据处理模块主要由DSP数字信号处理器及外围存储器件组成。
With the rapid development of national economy and scientific technology, a great deal of nonlinear, impact and unsymmetrical load increased significantly in the power system, power quality problems caused more and more serious economic losses, how to effectively reduce the impact of power quality problems has become a research focus of the technology workers. The first step to improve the power quality is the detection, analysis and identification of power quality disturbances. Only to detect power quality problems rapidly and accurately, conduct effectively analysis, and identify the type of disturbances, power quality problems can be controled and governed effectively.
This paper systematically analysed the classification, causes and analysis method of power quality problems and established the signal models of power quality disturbances, identified the time of the transient power quality disturbances by using the wavelet transform and analyzed the characteristics of the walvelet transform in processing power quality disturbances, and detected the feature of common power quality disturbances by using the S-transform and analyzed the characteristics of the S-transform in detecting power quality disturbances. The comparison of the wavelet transform and S-transform in dealing with power quality disturbances showed the S-transform was more suitable for the area of power quality disturbances detection and identification.
In order to achieve automatic classfication and identification of power quality disturbances, a new method based on S-transform and least square support vector machine was proposed. S-transform was used for extracting the feature vector of power quality disturbances and the least square support vector was used for classification and identification of power quality disturbances. Simulation results showed that the proposed method had an good performance on correct ratio and training speed, and strong resistances to nosies, so it is suitable to classification system for power quality disturbances.
Finally, the hardware circuit of the power quality analysis experimental platform based on DSP 5416 was designed. The hardware circuit provided a basis for future analysis and processing of power quality problems. The hardware circuit was made up of the following five parts:data acquisition circuit, data processing circuit, serial communication circuit, power circuit and reset circuit. The data acquisition circuit consisted of signal conditioning circuit and analog-digital conversion circuit. The data processing circuit was mainly composed of the DSP5416 and external storage decives.
本文系统地分析了电能质量问题的分类、产生原因及主要分析方法,并构建了电能质量扰动较完善的信号模型。利用目前电力系统中广泛应用的时频分析方法小波变换,对暂态电能质量扰动进行了时间定位,并分析了小波变换在处理电能质量扰动检测上的优点和性能。利用S变换对常见电能质量扰动的特征信息进行了检测,并分析了S变换在处理电能质量扰动检测上的优点。比较了小波变换和S变换在处理电能质量扰动问题时的区别,分析结果表明S变换比小波变换更适合应用于电能质量扰动检测与识别领域。
为了实现电能质量扰动信号自动分类和识别,本文提出了一种基于S变换和最小二乘支持向量机的电能质量扰动分类识别的新方法：S变换主要用于提取电能质量扰动的特征向量；最小二乘支持向量机主要用于根据提取的特征向量对电能质量扰动进行分类识别。仿真结果表明,该方法识别准确率高,抗噪能力强,且训练样本少,训练时间短,适用于电能质量扰动辨识系统。
最后,本文设计了基于DSP5416的电能质量分析实验平台的硬件电路,为进一步分析处理电能质量问题提供了基础。硬件电路主要由5个部分组成：数据采集模块、数据处理模块、串行通信模块、电源模块及复位模块。其中数据采集模块由信号调理电路和模数转换电路构成,数据处理模块主要由DSP数字信号处理器及外围存储器件组成。
With the rapid development of national economy and scientific technology, a great deal of nonlinear, impact and unsymmetrical load increased significantly in the power system, power quality problems caused more and more serious economic losses, how to effectively reduce the impact of power quality problems has become a research focus of the technology workers. The first step to improve the power quality is the detection, analysis and identification of power quality disturbances. Only to detect power quality problems rapidly and accurately, conduct effectively analysis, and identify the type of disturbances, power quality problems can be controled and governed effectively.
This paper systematically analysed the classification, causes and analysis method of power quality problems and established the signal models of power quality disturbances, identified the time of the transient power quality disturbances by using the wavelet transform and analyzed the characteristics of the walvelet transform in processing power quality disturbances, and detected the feature of common power quality disturbances by using the S-transform and analyzed the characteristics of the S-transform in detecting power quality disturbances. The comparison of the wavelet transform and S-transform in dealing with power quality disturbances showed the S-transform was more suitable for the area of power quality disturbances detection and identification.
In order to achieve automatic classfication and identification of power quality disturbances, a new method based on S-transform and least square support vector machine was proposed. S-transform was used for extracting the feature vector of power quality disturbances and the least square support vector was used for classification and identification of power quality disturbances. Simulation results showed that the proposed method had an good performance on correct ratio and training speed, and strong resistances to nosies, so it is suitable to classification system for power quality disturbances.
Finally, the hardware circuit of the power quality analysis experimental platform based on DSP 5416 was designed. The hardware circuit provided a basis for future analysis and processing of power quality problems. The hardware circuit was made up of the following five parts:data acquisition circuit, data processing circuit, serial communication circuit, power circuit and reset circuit. The data acquisition circuit consisted of signal conditioning circuit and analog-digital conversion circuit. The data processing circuit was mainly composed of the DSP5416 and external storage decives.
引文
[1]肖湘宁,徐永海.电能质量问题剖析[J].电网技术,2001,25(3)：66-69
[2]林海雪.现代电能质量的基本问题[J].电网技术,2001,25(10)：5-12
[3]U.S.-Canada Power System Outage Task Force. Interim report:Cause of the August 14th Blackout in the United States and Canada[C]. November 2003
[4]肖湘宁.电能质量分析与控制[M].北京：中国电力出版社,2002
[5]刘小彩,肖湘宁.电能质量评估与分析方法研究[D].北京：华北电力大学,1997
[6]Dugan R C, Megranghan M F, Benty H W. Electrical Power Systems Quality[M]. NewYork:MC Graw-Hill,1996
[7]IEC 61000-4-30. Electromagnetic Compatibility Part 4-30:Testing and Measurement Techniques-Power Quality Measurement Methods[S].2006
[8]IEEE Std 1159-2009. IEEE Recommended Practice for Monitoring Electric Power Quality[S].2009
[9]Bollen M H. Understanding Power Quality Problems, Volage Sags and Interruptions[M]. NewYork:IEEE PRESS,2000
[10]胡铭,陈珩.电能质量及分析方法综述[J].电网技术,2000,24(2)：36-38
[11]GB/T156-2007.标准电压[S].北京：中国标准出版社,2007
[12]GB/T12325-2008.电能质量 供电压偏差[S].北京：中国标准出版社,2008
[13]GB/T15945-2008.电能质量 电力系统频率偏差[S].北京：中国标准出版社,2008
[14]GB/T15543-2008.电能质量 三相电压不平衡[S].北京：中国标准出版社,2008
[15]GB/T12326-2008.电能质量 电压波动和闪变[S].北京：中国标准出版社,2008
[16]GB/T14549-1993.电能质量 公用电网谐波[S].北京：中国标准出版社,1993
[17]GB/T24337-2009.电能质量 公用电网间谐波[S].北京：中国标准出版社,2009
[18]GB/T19862-2005.电能质量 监测设备通用要求[S].北京：中国标准出版社,2005
[19]IEEE Std 1159.1. IEEE Guide For Recorder and Data Acquisition Requirements for Characterization of Power Quality Events[S].2003
[20]IEEE Std 1159.2. IEEE Power Quality Event Characterization[S].2003
[21]IEEE Std 1159.3. IEEE Recommended Practice for the Transfer of Power Quality Data[S].2003
[22]Santoso S, Powers E J, Grady W M. Power Quality Disturbance Identification Using Wavelet Transforms and Artificial Neural Networks[C]. Proceedings of the 7th IEEE ICHQP, Las Vegas, USA,1996:615-618
[23]Santoso S, Powers E J, Grady W M, et al. Power Quality Disturbance Waveform Recognition Using Wavelet-based Neural Classifier I Theoretical Foundation[J]. IEEE Transacions on Power Delivery,2000,15(1):222-228
[24]Santoso S, Powers E J, Grady W M, et al. Power Quality Disturbance Waveform Recognition Using Wavelet-based Neural Classifier II Application [J]. IEEE Transacions on Power Delivery,2000,15(1):229-235
[25]张智远,李庚银,冯任卿.基于小波和进化网络的电能质量动态扰动自动识别[J].华北电力学报,2002,29(3)：1-4
[26]Gating, Zwe-Lee. Wavelet-based Neural Network for Power Disturbance Recognition and Classification[J]. IEEE Trans. on Power Delivery,2004,19(4):1560-1568
[27]Abdel-Galil T K, El-Saadany E F, Yourself A M, et al. Disturbance Classification Using Hidden Markov Models and Vector Quantization[J]. IEEE Transacions on Power Delivery,2005,20(3): 2129-2135
[28]何为,杨洪耕.基于第二代小波变换和离散隐马尔可夫模型的电能质量扰动分类[J].电工技术学报,2007,22(5)：146-152
[29]Sami Ekici. Classification of Power System Disturbances Using Support Vector Machines[J]. Expert System with Applications:An Internationl Journal,2009,36(6)
[30]Gu Y H, Bollen H J. Time-frequency and Time-scale Doman Analysis of Voltage Disturbances[J]. IEEE Transactions on Power Delivery,2000,15(4):1279-1284
[31]赵成勇,何明峰.基于特定频带的短时傅立叶分析[J].电力系统自动化,2004,28(14)：41-44
[32]D.Devaraj Jayasree. Classificaiton of Power Quality Disturbance Signals Using FFT STFT Wavelet Transforms and Netural Networks-A Comparative Analysis[J]. Proceedings of the International Conference on Computational Intelligence and Multimedia Applications,2007.
[33]郭辉,傅成华,何春芳.基于短时傅里叶变换的电压间谐波分析[J].电力系统通信,2008,29(186)：66-68
[34]Stockwell R G, Mansinha L, Lower R P. Localization of the Complex Spectrum the S Transform[J].1996,44(4):998-1001
[35]Dash P K. S Transform Based Intelligent System for Classification of Power Quality Disturbance Signals [J]. IEEE Trans on Industrial Electronics,2003,50(4):800-805
[36]占勇,程浩忠,丁屺峰.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
[37]赵凤展,杨仁刚.基于S变换和时域分析的电能质量扰动识别[J].电网技术,2006,30(15)：90-94
[38]Huimin Quan, Yuxing Dai. Power Quality Disturbance Classification Using S-transform and Decision Tree[J]. Proceedings of the 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application,2008.
[39]唐求,王耀南.基于S变换与PNN的电能质量多扰动检测[J].仪器仪表学报,2009,30(8)：1668-1673
[40]Huang N E, Shen Z, Long S R, et al. The Empirical Mode Decomposition and the Hibert Spectrum for Nonlinear and Non-stationary Time Series Analysis[J]. Proceedings of the Royal Society of London Series A,1998,45(4):903-905
[41]李云天,赵妍,李楠.基于HHT变换的电能质量检测新方法[J].中国电机工程学报,2005,25(17)：52-56
[42]苏玉香,刘志刚,李东敏,李科亮.一种改善HHT端点效应的新方法及其在电能质量中的应用[J].电力自动化设备,2008,28(11)：40-45
[43]彭玉华.小波变换与工程应用[M].北京：科学出版社,2003
[44]孙延奎.小波分析及其应用[M].北京：机械工业出版社,2004
[45]Stockwell R G, Mansinha L, Lowe R P. Localization of the Complex Spectrum:the S Transform[J]. IEEE Trans. on Signal Process,1996,44(4):998-1001
[46]Stockwell R G S-Transform Analysis of Gravity Wave Activity from a Small Scale Network of Airglow Imagers[J].1999.
[47]何正友,钱清泉.电力系统暂态信号分析中小波基的选择原则[J].电力系统自动化,2003,27(10)：45-48
[48]杨淑英,王丽宏,杜荣华,苏涛.电力系统暂态保护中小波基的选择与应用[J].电力系统及自动化学报,2008,20(5)：106-111
[49]Heydt G T, Fjeld P S, Liu C C, et al. Applications of the window FFT to electric power quality assessment[J]. IEEE Trans. on Power Delivery,1999,14(3):1411-1416
[50]Sun P, Zhang J F, Zhang D J, et al. Morphological identification of transformer magnetising inrush current[J]. IEEE Electronics Letters,2002,38(9):437-438
[51]袁帅,佟为明.基于Hilbert变换和dq变换的电压暂降检测新方法[J].高压电技术,2009,35(5)：1220-1224
[52]Bhende C N, Mishra S, Panigrahi B K. Detection and classification of power quality disturbances using S-transform and modular neural network[J]. Electric Power System Research,2007, 78(2008):122-128
[53]Chilukuri M V, Dash P K. Multi-resolution S-transform based fuzzy recognition system for power quality events[J]. IEEE Trans. on Power Delivery,2004,19(1):323-330
[54]Emmanoul S, Math H J, Irene Y H. Expert system for classification and analysis of power system events[J]. IEEE Trans. on Power Delivery,2002,17(2):423-428
[55]周建萍,郑应平,王志萍.最小二乘支持向量机分类问题的算法实现[J].上海电力学院学报,2008,24(4)：381-384
[56]杨廷西,刘丁.基于小波变换和最小二乘支持向量机的短期电力负荷预测[J].电网技术,2005,29(13)：60-64
[57]孙亮,禹晶.模式识别原理[M].北京：北京工业大学出版社,2009
[58]Vapnik V N. The Nature of Statistical Learning Theory[M]. New York:Spring-Verlag,1995
[59]杨志民,刘广利.不确定性支持向量机原理及应用[M].北京：科学出版社,2007
[60]Suykens A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letter,1999,9(3):293-300
[61]Suykens A K, Vandewalle J,el al. LS-SVMLab1.5 toolbox[CP/OL]. [2003-02-26]
[62]姜斌,黎湘.模式分类方法研究[J].系统工程与电子技术,2007,29(1)：99-102
[63]杨光正,吴珉,张晓莉.模式识别[M].安徽：中国科学技术大学出版社,2001
[64]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
[2]林海雪.现代电能质量的基本问题[J].电网技术,2001,25(10)：5-12
[3]U.S.-Canada Power System Outage Task Force. Interim report:Cause of the August 14th Blackout in the United States and Canada[C]. November 2003
[4]肖湘宁.电能质量分析与控制[M].北京：中国电力出版社,2002
[5]刘小彩,肖湘宁.电能质量评估与分析方法研究[D].北京：华北电力大学,1997
[6]Dugan R C, Megranghan M F, Benty H W. Electrical Power Systems Quality[M]. NewYork:MC Graw-Hill,1996
[7]IEC 61000-4-30. Electromagnetic Compatibility Part 4-30:Testing and Measurement Techniques-Power Quality Measurement Methods[S].2006
[8]IEEE Std 1159-2009. IEEE Recommended Practice for Monitoring Electric Power Quality[S].2009
[9]Bollen M H. Understanding Power Quality Problems, Volage Sags and Interruptions[M]. NewYork:IEEE PRESS,2000
[10]胡铭,陈珩.电能质量及分析方法综述[J].电网技术,2000,24(2)：36-38
[11]GB/T156-2007.标准电压[S].北京：中国标准出版社,2007
[12]GB/T12325-2008.电能质量 供电压偏差[S].北京：中国标准出版社,2008
[13]GB/T15945-2008.电能质量 电力系统频率偏差[S].北京：中国标准出版社,2008
[14]GB/T15543-2008.电能质量 三相电压不平衡[S].北京：中国标准出版社,2008
[15]GB/T12326-2008.电能质量 电压波动和闪变[S].北京：中国标准出版社,2008
[16]GB/T14549-1993.电能质量 公用电网谐波[S].北京：中国标准出版社,1993
[17]GB/T24337-2009.电能质量 公用电网间谐波[S].北京：中国标准出版社,2009
[18]GB/T19862-2005.电能质量 监测设备通用要求[S].北京：中国标准出版社,2005
[19]IEEE Std 1159.1. IEEE Guide For Recorder and Data Acquisition Requirements for Characterization of Power Quality Events[S].2003
[20]IEEE Std 1159.2. IEEE Power Quality Event Characterization[S].2003
[21]IEEE Std 1159.3. IEEE Recommended Practice for the Transfer of Power Quality Data[S].2003
[22]Santoso S, Powers E J, Grady W M. Power Quality Disturbance Identification Using Wavelet Transforms and Artificial Neural Networks[C]. Proceedings of the 7th IEEE ICHQP, Las Vegas, USA,1996:615-618
[23]Santoso S, Powers E J, Grady W M, et al. Power Quality Disturbance Waveform Recognition Using Wavelet-based Neural Classifier I Theoretical Foundation[J]. IEEE Transacions on Power Delivery,2000,15(1):222-228
[24]Santoso S, Powers E J, Grady W M, et al. Power Quality Disturbance Waveform Recognition Using Wavelet-based Neural Classifier II Application [J]. IEEE Transacions on Power Delivery,2000,15(1):229-235
[25]张智远,李庚银,冯任卿.基于小波和进化网络的电能质量动态扰动自动识别[J].华北电力学报,2002,29(3)：1-4
[26]Gating, Zwe-Lee. Wavelet-based Neural Network for Power Disturbance Recognition and Classification[J]. IEEE Trans. on Power Delivery,2004,19(4):1560-1568
[27]Abdel-Galil T K, El-Saadany E F, Yourself A M, et al. Disturbance Classification Using Hidden Markov Models and Vector Quantization[J]. IEEE Transacions on Power Delivery,2005,20(3): 2129-2135
[28]何为,杨洪耕.基于第二代小波变换和离散隐马尔可夫模型的电能质量扰动分类[J].电工技术学报,2007,22(5)：146-152
[29]Sami Ekici. Classification of Power System Disturbances Using Support Vector Machines[J]. Expert System with Applications:An Internationl Journal,2009,36(6)
[30]Gu Y H, Bollen H J. Time-frequency and Time-scale Doman Analysis of Voltage Disturbances[J]. IEEE Transactions on Power Delivery,2000,15(4):1279-1284
[31]赵成勇,何明峰.基于特定频带的短时傅立叶分析[J].电力系统自动化,2004,28(14)：41-44
[32]D.Devaraj Jayasree. Classificaiton of Power Quality Disturbance Signals Using FFT STFT Wavelet Transforms and Netural Networks-A Comparative Analysis[J]. Proceedings of the International Conference on Computational Intelligence and Multimedia Applications,2007.
[33]郭辉,傅成华,何春芳.基于短时傅里叶变换的电压间谐波分析[J].电力系统通信,2008,29(186)：66-68
[34]Stockwell R G, Mansinha L, Lower R P. Localization of the Complex Spectrum the S Transform[J].1996,44(4):998-1001
[35]Dash P K. S Transform Based Intelligent System for Classification of Power Quality Disturbance Signals [J]. IEEE Trans on Industrial Electronics,2003,50(4):800-805
[36]占勇,程浩忠,丁屺峰.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
[37]赵凤展,杨仁刚.基于S变换和时域分析的电能质量扰动识别[J].电网技术,2006,30(15)：90-94
[38]Huimin Quan, Yuxing Dai. Power Quality Disturbance Classification Using S-transform and Decision Tree[J]. Proceedings of the 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application,2008.
[39]唐求,王耀南.基于S变换与PNN的电能质量多扰动检测[J].仪器仪表学报,2009,30(8)：1668-1673
[40]Huang N E, Shen Z, Long S R, et al. The Empirical Mode Decomposition and the Hibert Spectrum for Nonlinear and Non-stationary Time Series Analysis[J]. Proceedings of the Royal Society of London Series A,1998,45(4):903-905
[41]李云天,赵妍,李楠.基于HHT变换的电能质量检测新方法[J].中国电机工程学报,2005,25(17)：52-56
[42]苏玉香,刘志刚,李东敏,李科亮.一种改善HHT端点效应的新方法及其在电能质量中的应用[J].电力自动化设备,2008,28(11)：40-45
[43]彭玉华.小波变换与工程应用[M].北京：科学出版社,2003
[44]孙延奎.小波分析及其应用[M].北京：机械工业出版社,2004
[45]Stockwell R G, Mansinha L, Lowe R P. Localization of the Complex Spectrum:the S Transform[J]. IEEE Trans. on Signal Process,1996,44(4):998-1001
[46]Stockwell R G S-Transform Analysis of Gravity Wave Activity from a Small Scale Network of Airglow Imagers[J].1999.
[47]何正友,钱清泉.电力系统暂态信号分析中小波基的选择原则[J].电力系统自动化,2003,27(10)：45-48
[48]杨淑英,王丽宏,杜荣华,苏涛.电力系统暂态保护中小波基的选择与应用[J].电力系统及自动化学报,2008,20(5)：106-111
[49]Heydt G T, Fjeld P S, Liu C C, et al. Applications of the window FFT to electric power quality assessment[J]. IEEE Trans. on Power Delivery,1999,14(3):1411-1416
[50]Sun P, Zhang J F, Zhang D J, et al. Morphological identification of transformer magnetising inrush current[J]. IEEE Electronics Letters,2002,38(9):437-438
[51]袁帅,佟为明.基于Hilbert变换和dq变换的电压暂降检测新方法[J].高压电技术,2009,35(5)：1220-1224
[52]Bhende C N, Mishra S, Panigrahi B K. Detection and classification of power quality disturbances using S-transform and modular neural network[J]. Electric Power System Research,2007, 78(2008):122-128
[53]Chilukuri M V, Dash P K. Multi-resolution S-transform based fuzzy recognition system for power quality events[J]. IEEE Trans. on Power Delivery,2004,19(1):323-330
[54]Emmanoul S, Math H J, Irene Y H. Expert system for classification and analysis of power system events[J]. IEEE Trans. on Power Delivery,2002,17(2):423-428
[55]周建萍,郑应平,王志萍.最小二乘支持向量机分类问题的算法实现[J].上海电力学院学报,2008,24(4)：381-384
[56]杨廷西,刘丁.基于小波变换和最小二乘支持向量机的短期电力负荷预测[J].电网技术,2005,29(13)：60-64
[57]孙亮,禹晶.模式识别原理[M].北京：北京工业大学出版社,2009
[58]Vapnik V N. The Nature of Statistical Learning Theory[M]. New York:Spring-Verlag,1995
[59]杨志民,刘广利.不确定性支持向量机原理及应用[M].北京：科学出版社,2007
[60]Suykens A K, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letter,1999,9(3):293-300
[61]Suykens A K, Vandewalle J,el al. LS-SVMLab1.5 toolbox[CP/OL]. [2003-02-26]
[62]姜斌,黎湘.模式分类方法研究[J].系统工程与电子技术,2007,29(1)：99-102
[63]杨光正,吴珉,张晓莉.模式识别[M].安徽：中国科学技术大学出版社,2001
[64]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