矿用干式变压器局部放电模式识别方法
|
摘要
为提高矿用干式变压器局部放电模式识别准确率,提出了一种矿用干式变压器局部放电模式识别方法。首先,采用正交匹配追踪算法对原始局部放电信号进行去噪,最大程度保留原始局部放电信号的有用信息;然后,通过自回归模型提取去噪后局部放电信号的自回归系数特征;最后,将自回归系数特征输入随机森林集成分类器对局部放电模式进行识别。实验结果表明,该方法平均识别准确率达98%。
In order to improve recognition accuracy of partial discharge pattern of mine-used dry-type transformer,apartial discharge pattern recognition method for mine-used dry-type transformer was proposed.Firstly,orthogonal matching pursuit algorithm is used to denoise original partial discharge signal,which can retain useful information of the original partial discharge signal to the greatest extent.Then,autoregressive coefficient features of the partial discharge signal after denoising are extracted by autoregressive model.Finally,the autoregressive coefficient features are input into random forest integrated classifier to recognize partial discharge pattern.The experimental result shows that average recognition accuracy of the method is 98%.
In order to improve recognition accuracy of partial discharge pattern of mine-used dry-type transformer,apartial discharge pattern recognition method for mine-used dry-type transformer was proposed.Firstly,orthogonal matching pursuit algorithm is used to denoise original partial discharge signal,which can retain useful information of the original partial discharge signal to the greatest extent.Then,autoregressive coefficient features of the partial discharge signal after denoising are extracted by autoregressive model.Finally,the autoregressive coefficient features are input into random forest integrated classifier to recognize partial discharge pattern.The experimental result shows that average recognition accuracy of the method is 98%.
引文
[1]杨宁,阎春雨,毕建刚,等.超声波局部放电检测仪校验方法研究及应用[J].电测与仪表,2014,51(22):104-109.YANG Ning,YAN Chunyu,BI Jiangang,et al.Research on calibration technology of ultrasonic partial discharge detector and its application[J].Electrical Measurement&Instrumentation,2014,51(22):104-109.
[2]郭少朋,韩立,徐鲁宁,等.光纤传感器在局部放电检测中的研究进展综述[J].电工电能新技术,2016,35(3):47-53.GUO Shaopeng,HAN Li,XU Luning,et al.Review of research on fiber optic sensors for partial discharge detection[J].Advanced Technology of Electrical Engineering and Energy,2016,35(3):47-53.
[3]赵敏.FFT变换与小波变换在变压器局部放电信号去噪中的应用[J].变压器,2009,46(5):28-31.ZHAO Min. Application of FFT and wavelet transforms to noise elimination of transformer partial discharge signals[J].Transformer,2009,46(5):28-31.
[4]王洪涛,郑乃清,刘辉军.基于共振稀疏分解的局部放电信号窄带干扰抑制新方法[J].工矿自动化,2015,41(5):68-73.WANG Hongtao,ZHENG Naiqing,LIU Huijun.A new method of narrowband interference suppression of partial discharge signal based on resonance sparse decomposition[J].Industry and Mine Automation,2015,41(5):68-73.
[5]张建文,陈焕栩,周鹏.基于小波阈值的局部放电去噪新方法[J].电工电能新技术,2017,36(8):80-88.ZHANG Jianwen,CHEN Huanxu,ZHOU Peng.New de-noising method for partial discharge signals based on wavelet threshold[J].Advanced Technology of Electrical Engineering and Energy,2017,36(8):80-88.
[6]褚鑫,张建文,韩刚.统计特征参数及多分类SVM的局部放电类型识别[J].电测与仪表,2015,52(7):35-39.CHU Xin,ZHANG Jianwen,HAN Gang.Partial discharge pattern recognition based on statistical parameters and multi-classifications SVM[J].Electrical Measurement&Instrumentation,2015,52(7):35-39.
[7]弓艳朋,刘有为,吴立远.采用分形和支持向量机的气体绝缘组合电器局部放电类型识别[J].电网技术,2011,35(3):135-139.GONG Yanpeng, LIUYouwei, WULiyuan.Identification of partial discharge in gas insulated switchgears with fractal theory and support vector machine[J].Power System Technology,2011,35(3):135-139.
[8]周沙,景亮.基于矩特征与概率神经网络的局部放电模式识别[J].电力系统保护与控制,2016,44(3):98-102.ZHOU Sha,JING Liang.Pattern recognition of partial discharge based on moment features and probabilistic neural network[J].Power System Protection and Control,2016,44(3):98-102.
[9]杨宇.基于级联稀疏表示分类器的人脸识别算法[J].工矿自动化,2014,40(5):46-48.YANG Yu.Face recognition algorithm based on cascade sparse representation-based classifier[J].Industry and Mine Automation,2014,40(5):46-48.
[10]唐志国,唐铭泽,李金忠,等.电气设备局部放电模式识别研究综述[J].高电压技术,2017,43(7):2263-2277.TANG Zhiguo,TANG Mingze,LI Jinzhong,et al.Review on partial discharge pattern recognition of electrical equipment[J].High Voltage Engineering,2017,43(7):2263-2277.
[11]张建文,王恩俊,陈焕栩,等.基于自回归模型和超球面支持向量机的局部放电模式识别[J].电工电能新技术,2016,35(9):29-34.ZHANG Jianwen,WANG Enjun,CHEN Huanxu,et al.Partial discharge pattern recognition based on autoregression model and hypersphere support vector machine[J].Advanced Technology of Electrical Engineering and Energy,2016,35(9):29-34.
[12]李明,王晓茹.一种用于电力系统间谐波谱估计的自回归模型算法[J].中国电机工程学报,2010,30(1):72-76.LI Ming,WANG Xiaoru.An autoregressive model algorithm for the inter-harmonic spectral estimation in the power system[J].Proceedings of the CSEE,2010,30(1):72-76.
[13] CUTLER K,BREIMAN L.Random forests[J].Machine Learning,2004,45(1):157-176.
[14]曹正凤.随机森林算法优化研究[D].北京:首都经济贸易大学,2014.
[15]于凯.基于随机森林的局部放电识别分析[J].电子世界,2017(17):152.
[16]罗新.基于随机森林的文本分类模型研究[J].农业图书情报学刊,2016,28(11):50-54.LUO Xin.Research on text classification model based on random forests[J].Journal of Library and Information Sciencesin Agriculture,2016,28(11):50-54.
[17]罗新,牛海清,胡日亮,等.一种改进的用于快速傅里叶变换功率谱中的窄带干扰抑制的方法[J].中国电机工程学报,2013,33(12):167-175.LUO Xin,NIU Haiqing,HU Riliang,et al.A modifiedmethodofsuppressingnarrow-band interference using fast Fourier transform power spectrum[J].Proceedings of the CSEE,2013,33(12):167-175.
[18]周凯,谢敏,赵世林,等.基于改进FastICA的局部放电在线监测窄带干扰高保真性抑制方法[J].电工技术学报,2018,33(11):2604-2612.ZHOU Kai,XIE Min,ZHAO Shilin,et al.Periodic narrowband noise rejection with high fidelity of partial discharge on line monitoring based on improved FastICA algorithm[J].Transactions of China Electrotechnical Society,2018,33(11):2604-2612.
[19]唐炬,黄江岸,张晓星,等.局部放电在线监测中混频周期性窄带干扰的抑制[J].中国电机工程学报,2010,30(13):121-127.TANG Ju,HUANG Jiang'an,ZHANG Xiaoxing,et al.Suppression of the periodic narrow-band noise with mixed frequencies in partial discharge on-line monitoring[J].Proceedings of the CSEE,2010,30(13):121-127.
[2]郭少朋,韩立,徐鲁宁,等.光纤传感器在局部放电检测中的研究进展综述[J].电工电能新技术,2016,35(3):47-53.GUO Shaopeng,HAN Li,XU Luning,et al.Review of research on fiber optic sensors for partial discharge detection[J].Advanced Technology of Electrical Engineering and Energy,2016,35(3):47-53.
[3]赵敏.FFT变换与小波变换在变压器局部放电信号去噪中的应用[J].变压器,2009,46(5):28-31.ZHAO Min. Application of FFT and wavelet transforms to noise elimination of transformer partial discharge signals[J].Transformer,2009,46(5):28-31.
[4]王洪涛,郑乃清,刘辉军.基于共振稀疏分解的局部放电信号窄带干扰抑制新方法[J].工矿自动化,2015,41(5):68-73.WANG Hongtao,ZHENG Naiqing,LIU Huijun.A new method of narrowband interference suppression of partial discharge signal based on resonance sparse decomposition[J].Industry and Mine Automation,2015,41(5):68-73.
[5]张建文,陈焕栩,周鹏.基于小波阈值的局部放电去噪新方法[J].电工电能新技术,2017,36(8):80-88.ZHANG Jianwen,CHEN Huanxu,ZHOU Peng.New de-noising method for partial discharge signals based on wavelet threshold[J].Advanced Technology of Electrical Engineering and Energy,2017,36(8):80-88.
[6]褚鑫,张建文,韩刚.统计特征参数及多分类SVM的局部放电类型识别[J].电测与仪表,2015,52(7):35-39.CHU Xin,ZHANG Jianwen,HAN Gang.Partial discharge pattern recognition based on statistical parameters and multi-classifications SVM[J].Electrical Measurement&Instrumentation,2015,52(7):35-39.
[7]弓艳朋,刘有为,吴立远.采用分形和支持向量机的气体绝缘组合电器局部放电类型识别[J].电网技术,2011,35(3):135-139.GONG Yanpeng, LIUYouwei, WULiyuan.Identification of partial discharge in gas insulated switchgears with fractal theory and support vector machine[J].Power System Technology,2011,35(3):135-139.
[8]周沙,景亮.基于矩特征与概率神经网络的局部放电模式识别[J].电力系统保护与控制,2016,44(3):98-102.ZHOU Sha,JING Liang.Pattern recognition of partial discharge based on moment features and probabilistic neural network[J].Power System Protection and Control,2016,44(3):98-102.
[9]杨宇.基于级联稀疏表示分类器的人脸识别算法[J].工矿自动化,2014,40(5):46-48.YANG Yu.Face recognition algorithm based on cascade sparse representation-based classifier[J].Industry and Mine Automation,2014,40(5):46-48.
[10]唐志国,唐铭泽,李金忠,等.电气设备局部放电模式识别研究综述[J].高电压技术,2017,43(7):2263-2277.TANG Zhiguo,TANG Mingze,LI Jinzhong,et al.Review on partial discharge pattern recognition of electrical equipment[J].High Voltage Engineering,2017,43(7):2263-2277.
[11]张建文,王恩俊,陈焕栩,等.基于自回归模型和超球面支持向量机的局部放电模式识别[J].电工电能新技术,2016,35(9):29-34.ZHANG Jianwen,WANG Enjun,CHEN Huanxu,et al.Partial discharge pattern recognition based on autoregression model and hypersphere support vector machine[J].Advanced Technology of Electrical Engineering and Energy,2016,35(9):29-34.
[12]李明,王晓茹.一种用于电力系统间谐波谱估计的自回归模型算法[J].中国电机工程学报,2010,30(1):72-76.LI Ming,WANG Xiaoru.An autoregressive model algorithm for the inter-harmonic spectral estimation in the power system[J].Proceedings of the CSEE,2010,30(1):72-76.
[13] CUTLER K,BREIMAN L.Random forests[J].Machine Learning,2004,45(1):157-176.
[14]曹正凤.随机森林算法优化研究[D].北京:首都经济贸易大学,2014.
[15]于凯.基于随机森林的局部放电识别分析[J].电子世界,2017(17):152.
[16]罗新.基于随机森林的文本分类模型研究[J].农业图书情报学刊,2016,28(11):50-54.LUO Xin.Research on text classification model based on random forests[J].Journal of Library and Information Sciencesin Agriculture,2016,28(11):50-54.
[17]罗新,牛海清,胡日亮,等.一种改进的用于快速傅里叶变换功率谱中的窄带干扰抑制的方法[J].中国电机工程学报,2013,33(12):167-175.LUO Xin,NIU Haiqing,HU Riliang,et al.A modifiedmethodofsuppressingnarrow-band interference using fast Fourier transform power spectrum[J].Proceedings of the CSEE,2013,33(12):167-175.
[18]周凯,谢敏,赵世林,等.基于改进FastICA的局部放电在线监测窄带干扰高保真性抑制方法[J].电工技术学报,2018,33(11):2604-2612.ZHOU Kai,XIE Min,ZHAO Shilin,et al.Periodic narrowband noise rejection with high fidelity of partial discharge on line monitoring based on improved FastICA algorithm[J].Transactions of China Electrotechnical Society,2018,33(11):2604-2612.
[19]唐炬,黄江岸,张晓星,等.局部放电在线监测中混频周期性窄带干扰的抑制[J].中国电机工程学报,2010,30(13):121-127.TANG Ju,HUANG Jiang'an,ZHANG Xiaoxing,et al.Suppression of the periodic narrow-band noise with mixed frequencies in partial discharge on-line monitoring[J].Proceedings of the CSEE,2010,30(13):121-127.