奇异值分解在电缆局部放电信号模式识别中的应用
|
摘要
针对局部放电在线检测中的局部放电信号模式识别,在对局部放电信号进行去噪预处理的基础上,对去噪后的局部放电信号进行小波包分解,利用小波包系数构建小波包系数矩阵;然后,对小波包系数矩阵进行奇异值分解,定义奇异值能量百分比作为局部放电信号的特征向量,并利用M-ary算法将支持向量机二分类扩展到多分类,使用粒子群算法对支持向量机参数进行优化;最后,将特征向量作为输入,使用支持向量机对4种放电信号进行识别,并与BP神经网络的识别效果进行对比.结果表明:利用奇异值能量百分比构建的放电信号特征向量能够很好反映原始信号的特征;基于支持向量机能够有效对放电信号进行识别,平均识别率达到95%,随着分解尺度增大,4种放电信号的平均识别率增大,但增大的幅度减小;支持向量机和BP神经网络均能够很好识别4种放电信号,且支持向量机相比BP神经网络,具有更好的识别效果.
Aiming at pattern recognition of on-line partial discharge( PD) monitoring,the wavelet packet coefficient matrix is constructed on the basis of wavelet packet decomposition of de-noised PD signal after the wavelet packet decomposition of de-noised partial discharge signal is done. Then,by the singular value decomposition of the wavelet packet coefficient matrix,the singular value energy percentage is defined as the feature vector of the partial discharge signal. Two classifications of the supportive vector machine are extended to multi one by M-ary algorithm,and the particle swarm optimization algorithm is used to optimize the parameters of supportive vector machine. Finally,input is regarded as the feature vectors,supportive vector machines are used to recognize 4 kinds of discharge signals,and a comparison of recognition effect is made by means of BP neural network. The results show that the feature vector of the singular value energy percentage can reflect the characteristics of the original signal well. Based on supportive vector machines,the discharge signals can be effectively identified with a 95% average recognition rate. And with the increase of decomposition scale,the average recognition rate of 4 kinds of discharge signal increases,but the increment decreases. Supportive vector machine and BP neural network can well identify 4 kinds of discharge signals,and the former has a better recognition effect.
Aiming at pattern recognition of on-line partial discharge( PD) monitoring,the wavelet packet coefficient matrix is constructed on the basis of wavelet packet decomposition of de-noised PD signal after the wavelet packet decomposition of de-noised partial discharge signal is done. Then,by the singular value decomposition of the wavelet packet coefficient matrix,the singular value energy percentage is defined as the feature vector of the partial discharge signal. Two classifications of the supportive vector machine are extended to multi one by M-ary algorithm,and the particle swarm optimization algorithm is used to optimize the parameters of supportive vector machine. Finally,input is regarded as the feature vectors,supportive vector machines are used to recognize 4 kinds of discharge signals,and a comparison of recognition effect is made by means of BP neural network. The results show that the feature vector of the singular value energy percentage can reflect the characteristics of the original signal well. Based on supportive vector machines,the discharge signals can be effectively identified with a 95% average recognition rate. And with the increase of decomposition scale,the average recognition rate of 4 kinds of discharge signal increases,but the increment decreases. Supportive vector machine and BP neural network can well identify 4 kinds of discharge signals,and the former has a better recognition effect.
引文
[1]吴炬卓.中压电缆局部放电带电检测的白噪声抑制和放电类型识别方法研究[D].广州:华南理工大学,2015.
[2]唐炬,李伟,欧阳有鹏.采用小波变换奇异值分解方法的局部放电模式识别[J].高电压技术,2010,36(7):1686-1691.TANG Ju,LI Wei,OUYANG You-peng.Partial discharge pattern recognition using discrete wavelet transform and singular value decomposition[J].High Voltage Engineering,2010,36(7):1686-1691.
[3]唐炬,董玉林,樊雷,等.基于Hankel矩阵的复小波-奇异值分解法提取局部放电特征信息[J].中国电机工程学报,2015,35(7):1808-1817.TANG Ju,DONG Yu-lin,FAN Lei,et al.Feature information extraction of partial discharge signal with complex wavelet transform and singular value decomposition based on Hankel matrix[J].Proceedings of the CSEE,2015,35(7):1808-1817.
[4]阮羚,李成华,宿磊,等.基于奇异值分解的局部放电模式识别方法[J].电工技术学报,2015,30(18):223-228.RUAN Ling,LI Cheng-hua,SU Lei,et al.Pattern recognition for partial discharging using singular value decomposition[J].Transactions of China Electrotechnical Society,2015,30(18):223-228.
[5]鲁大勇,李鹏飞,荐波涛.绝缘局部放电特征量提取与模式识别研究[J].电气应用,2016,35(8):74-79.LU Da-yong,LI Peng-fei,JIAN Bo-tao.Research on feature extraction and pattern recognition of partial discharge in insulation[J].Electrotechnical Application,2016,35(8):74-79.
[6]张德丰.MATLAB小波分析[M].北京:机械工业出版社,2009.
[7]胡卫红,舒泓,栾宇光.基于奇异值分解的电能质量信号去噪[J].电力系统保护与控制,2010,38(2):30-33.HU Wei-hong,SHU Hong,LUAN Yu-guang.Power quality signals'de-noising method based on singular value decomposition(SVD)[J].Power System Protection and Control,2010,38(2):30-33.
[8]郑顾平,李强,李刚.基于遗传算法的奇异值分解信号去噪算法[J].计算机应用研究,2015,32(8):2281-2285.ZHENG Gu-ping,LI Qiang,LI Gang.Singular value decomposition signal de-noising algorithm based on genetic algorithm[J].Application Research of Computers,2015,32(8):2281-2285.
[9]李天云,陈昌雷,周博,等.奇异值分解和最小二乘支持向量机在电能质量扰动识别中的应用[J].中国电机工程学报,2008,28(34):124-128.LI Tian-yun,CHEN Chang-lei,ZHOU Bo,el al.Application of SVD and LS-SVM in power quality disturbancesclassification[J].Proceedings of the CSEE,2008,28(34):124-128.
[10]郭谋发,徐丽兰,缪希仁,等.采用时频矩阵奇异值分解的配电开关振动信号特征量提取方法[J].中国电机工程学报,2014,34(28):4990-4997.GOU Mou-fa,XU Li-lan,MIAO Xi-ren,el al.A vibration signal feature extraction method for distribution switches based on singular value decomposition of time-frequency matrix[J].Proceedings of the CSEE,2014,34(28):4990-4997.
[11]杨延西,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.YANG Yan-xi,LIU Ding.Short-term load forecasting based on wavelet transform and least square support vector machines[J].Power System Technology,2005,29(13):60-64.
[12]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.ZHANG Quan-ming,LIU Hui-jin.Application of LSSVM in classification of power quality[J].Proceedings of the CSEE,2008,28(1):106-110.
[13]SEBALD D J,BUCHLEW J A.Support vector machines and the multiple hypothesis test problem[J].IEEE Trans on Signal Proccessing,2001,49(11):2865-2872.
[14]吴炬卓,牛海清,许佳.小波包系数能量百分比在局部放电模式识别中的应用研究[J].电器与能效管理技术,2017(8):12-16.WU Ju-zhuo,NIU Hai-qing,XU Jia.Application of wavelet packet coefficients energy percentage in pattern recognition of partial discharge[J].Electrical&Energy Management Technology,2017(8):12-16.
[15]江天炎,李剑,杜林,等.粒子群优化小波自适应阈值法用于局部放电去噪[J].电工技术学报,2012,27(5):77-83.JIANG Tian-yan,LI Jian,DU Lin,el al.Application of LS-SVM in classification of power quality disturbances[J].Transactions of China Electrotechnical Society,2012,27(5):77-83.
[16]牛海清,叶开发,许佳,等.基于粒子群优化支持向量机的电缆温度计算[J].华南理工大学学报(自然科学版),2016,44(4):77-83.NIU Hai-qing,YE Kai-fa,XU Jia,el al.Calculation of cable temperature based on support vector machine optimized by particle swarm algorithm[J].Journal of South China University of Technology(Natural Science Edition),2016,44(4):77-83.
[2]唐炬,李伟,欧阳有鹏.采用小波变换奇异值分解方法的局部放电模式识别[J].高电压技术,2010,36(7):1686-1691.TANG Ju,LI Wei,OUYANG You-peng.Partial discharge pattern recognition using discrete wavelet transform and singular value decomposition[J].High Voltage Engineering,2010,36(7):1686-1691.
[3]唐炬,董玉林,樊雷,等.基于Hankel矩阵的复小波-奇异值分解法提取局部放电特征信息[J].中国电机工程学报,2015,35(7):1808-1817.TANG Ju,DONG Yu-lin,FAN Lei,et al.Feature information extraction of partial discharge signal with complex wavelet transform and singular value decomposition based on Hankel matrix[J].Proceedings of the CSEE,2015,35(7):1808-1817.
[4]阮羚,李成华,宿磊,等.基于奇异值分解的局部放电模式识别方法[J].电工技术学报,2015,30(18):223-228.RUAN Ling,LI Cheng-hua,SU Lei,et al.Pattern recognition for partial discharging using singular value decomposition[J].Transactions of China Electrotechnical Society,2015,30(18):223-228.
[5]鲁大勇,李鹏飞,荐波涛.绝缘局部放电特征量提取与模式识别研究[J].电气应用,2016,35(8):74-79.LU Da-yong,LI Peng-fei,JIAN Bo-tao.Research on feature extraction and pattern recognition of partial discharge in insulation[J].Electrotechnical Application,2016,35(8):74-79.
[6]张德丰.MATLAB小波分析[M].北京:机械工业出版社,2009.
[7]胡卫红,舒泓,栾宇光.基于奇异值分解的电能质量信号去噪[J].电力系统保护与控制,2010,38(2):30-33.HU Wei-hong,SHU Hong,LUAN Yu-guang.Power quality signals'de-noising method based on singular value decomposition(SVD)[J].Power System Protection and Control,2010,38(2):30-33.
[8]郑顾平,李强,李刚.基于遗传算法的奇异值分解信号去噪算法[J].计算机应用研究,2015,32(8):2281-2285.ZHENG Gu-ping,LI Qiang,LI Gang.Singular value decomposition signal de-noising algorithm based on genetic algorithm[J].Application Research of Computers,2015,32(8):2281-2285.
[9]李天云,陈昌雷,周博,等.奇异值分解和最小二乘支持向量机在电能质量扰动识别中的应用[J].中国电机工程学报,2008,28(34):124-128.LI Tian-yun,CHEN Chang-lei,ZHOU Bo,el al.Application of SVD and LS-SVM in power quality disturbancesclassification[J].Proceedings of the CSEE,2008,28(34):124-128.
[10]郭谋发,徐丽兰,缪希仁,等.采用时频矩阵奇异值分解的配电开关振动信号特征量提取方法[J].中国电机工程学报,2014,34(28):4990-4997.GOU Mou-fa,XU Li-lan,MIAO Xi-ren,el al.A vibration signal feature extraction method for distribution switches based on singular value decomposition of time-frequency matrix[J].Proceedings of the CSEE,2014,34(28):4990-4997.
[11]杨延西,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.YANG Yan-xi,LIU Ding.Short-term load forecasting based on wavelet transform and least square support vector machines[J].Power System Technology,2005,29(13):60-64.
[12]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.ZHANG Quan-ming,LIU Hui-jin.Application of LSSVM in classification of power quality[J].Proceedings of the CSEE,2008,28(1):106-110.
[13]SEBALD D J,BUCHLEW J A.Support vector machines and the multiple hypothesis test problem[J].IEEE Trans on Signal Proccessing,2001,49(11):2865-2872.
[14]吴炬卓,牛海清,许佳.小波包系数能量百分比在局部放电模式识别中的应用研究[J].电器与能效管理技术,2017(8):12-16.WU Ju-zhuo,NIU Hai-qing,XU Jia.Application of wavelet packet coefficients energy percentage in pattern recognition of partial discharge[J].Electrical&Energy Management Technology,2017(8):12-16.
[15]江天炎,李剑,杜林,等.粒子群优化小波自适应阈值法用于局部放电去噪[J].电工技术学报,2012,27(5):77-83.JIANG Tian-yan,LI Jian,DU Lin,el al.Application of LS-SVM in classification of power quality disturbances[J].Transactions of China Electrotechnical Society,2012,27(5):77-83.
[16]牛海清,叶开发,许佳,等.基于粒子群优化支持向量机的电缆温度计算[J].华南理工大学学报(自然科学版),2016,44(4):77-83.NIU Hai-qing,YE Kai-fa,XU Jia,el al.Calculation of cable temperature based on support vector machine optimized by particle swarm algorithm[J].Journal of South China University of Technology(Natural Science Edition),2016,44(4):77-83.