利用AP-SSVM算法识别GIS的局放缺陷类型
|
摘要
针对传统方法对GIS的缺陷类型识别准确率低的问题,利用AP-SSVM算法识别GIS的缺陷类型,首先将不同缺陷的GIS局放信号进行小波包分解,对各小波包系数进行时频分析,提取信号时域和频域的信息熵,经过AP聚类后,确定最优小波包系数,并将对应的信息熵带入各分类器进行识别。试验结果表明,提出的AP-SSVM算法在识别精确度方面优于SVM和APSVM,能够达到85%以上,为现场GIS故障诊断提供了新的思路,有利于GIS的安全运行。
Aiming at low accuracy rate of identification of GIS defect types through conventional methods,this paper uses AP-SSVM algorithm to identify GIS defect types. First,GIS partial discharge signals of different defectsgo through wavelet packet decomposition. Then,time-frequency analysis is made of various wavelet packet coefficients to extract time-domain and frequency-domain information entropy of the signals. After AP clustering,we can determine the optimal wavelet packet coefficient and bring corresponding information entropies into classifiersfor identification. Experimental results indicate that the proposed AP-SSVM algorithm is superior to SVM and AP-SVM in the respect of identification accuracy and its accuracy can exceed 85%,thus providing a new idea for on-site GIS fault diagnosis in favor of safe GIS operation.
Aiming at low accuracy rate of identification of GIS defect types through conventional methods,this paper uses AP-SSVM algorithm to identify GIS defect types. First,GIS partial discharge signals of different defectsgo through wavelet packet decomposition. Then,time-frequency analysis is made of various wavelet packet coefficients to extract time-domain and frequency-domain information entropy of the signals. After AP clustering,we can determine the optimal wavelet packet coefficient and bring corresponding information entropies into classifiersfor identification. Experimental results indicate that the proposed AP-SSVM algorithm is superior to SVM and AP-SVM in the respect of identification accuracy and its accuracy can exceed 85%,thus providing a new idea for on-site GIS fault diagnosis in favor of safe GIS operation.
引文
[1]丁登伟,唐诚,高文胜,等.GIS中典型局部放电的频谱特征及传播特性[J].高电压技术,2014,40(10):3243-3251.
[2]唐炬,曾福平,范庆涛,等.基于荧光光纤检测GIS局部放电的多重分形谱识别[J].高电压技术,2014,40(2):465-473.
[3]张晓星,舒娜,徐晓刚,等.基于三维谱图混沌特征的GIS局部放电识别[J].电工技术学报,2015,30(1):249-254.
[4]律方成,金虎,王子建,等.主分量稀疏化在GIS局部放电特征提取中的应用[J].电工技术学报,2015,30(8):282-288.
[5]李庆辉,李艾华,苏延召,等.结合FCM聚类与SVM的火焰检测算法[J].红外与激光工程,2014,43(5):1660-1666.
[6]费成巍,白广忱,李晓颖.基于过程功率谱熵SVM的转子振动故障诊断方法[J].推进技术,2012,33(2):293-298.
[7]朱艳伟,但扬清,陈东海,等.小波包变换和支持向量机在孤岛与扰动识别中的应用[J].高电压技术,2014,40(8):2343-2347.
[8]李一兵,葛娟,林云.基于熵特征和支持向量机的调制识别方法[J].系统工程与电子技术,2012,34(8):1691-1695.
[9]陈伟根,谢波,龙震泽,等.基于小波包能量熵的油纸绝缘气隙放电阶段识别[J].中国电机工程学报,2016,36(2):563-569.
[10]周琼,贠志皓,丰颖,等.风电接入下基于AP聚类的无功功率—电压控制分区方法[J].电力系统自动化,2016,40(13):19-27.
[11]陈伟根,谢波,龙震泽,等.基于小波包能量熵的油纸绝缘气隙放电阶段识别[J].中国电机工程学报,2016,36(2):563-569.
[12]徐德刚,徐戏阳,陈晓,等.基于Minkowski距离的一致聚类改进算法及应用研究[J].湖南大学学报(自然科学版),2016,43(4):133-140.
[13]贾嵘,张欣伟,徐其惠,等.基于LS-SVM回归的频域分析法及其在局放窄带干扰抑制中应用[J].电力自动化设备,2009(9):50-53.
[2]唐炬,曾福平,范庆涛,等.基于荧光光纤检测GIS局部放电的多重分形谱识别[J].高电压技术,2014,40(2):465-473.
[3]张晓星,舒娜,徐晓刚,等.基于三维谱图混沌特征的GIS局部放电识别[J].电工技术学报,2015,30(1):249-254.
[4]律方成,金虎,王子建,等.主分量稀疏化在GIS局部放电特征提取中的应用[J].电工技术学报,2015,30(8):282-288.
[5]李庆辉,李艾华,苏延召,等.结合FCM聚类与SVM的火焰检测算法[J].红外与激光工程,2014,43(5):1660-1666.
[6]费成巍,白广忱,李晓颖.基于过程功率谱熵SVM的转子振动故障诊断方法[J].推进技术,2012,33(2):293-298.
[7]朱艳伟,但扬清,陈东海,等.小波包变换和支持向量机在孤岛与扰动识别中的应用[J].高电压技术,2014,40(8):2343-2347.
[8]李一兵,葛娟,林云.基于熵特征和支持向量机的调制识别方法[J].系统工程与电子技术,2012,34(8):1691-1695.
[9]陈伟根,谢波,龙震泽,等.基于小波包能量熵的油纸绝缘气隙放电阶段识别[J].中国电机工程学报,2016,36(2):563-569.
[10]周琼,贠志皓,丰颖,等.风电接入下基于AP聚类的无功功率—电压控制分区方法[J].电力系统自动化,2016,40(13):19-27.
[11]陈伟根,谢波,龙震泽,等.基于小波包能量熵的油纸绝缘气隙放电阶段识别[J].中国电机工程学报,2016,36(2):563-569.
[12]徐德刚,徐戏阳,陈晓,等.基于Minkowski距离的一致聚类改进算法及应用研究[J].湖南大学学报(自然科学版),2016,43(4):133-140.
[13]贾嵘,张欣伟,徐其惠,等.基于LS-SVM回归的频域分析法及其在局放窄带干扰抑制中应用[J].电力自动化设备,2009(9):50-53.