基于Hilbert边际谱和SAE-DNN的局部放电模式识别方法
|
摘要
提出了一种基于Hilbert边际谱和稀疏自编码器(SAE)—深度神经网络(DNN)的局部放电(PD)信号的模式识别方法。首先,以变分模态分解(VMD)对PD信号进行分解,对所得各分量进行Hilbert变换构建相应的Hilbert边际谱。其次,以PD信号的Hilbert边际谱为输入数据,利用SAE自动学习复杂数据的内在特征来提取简明的数据特征表达获得参数。再次,利用SAE的训练结果初始化DNN,再以大量训练样本进行分类器的训练。同时,为了加快SAE和DNN学习过程的收敛速度,以自适应步长的学习速率对网络进行调优,更新权值参数。最后,用训练好的DNN完成测试样本的PD类型的识别。此外,以基于BP神经网络和支持向量机的识别结果与文中结果进行比较。实验结果证明,所采用的识别方法具有更高的正确识别率。
A method based on Hilbert marginal spectrum and sparse autoencoder(SAE)-deep neural networks(DNN)is proposed to recognize partial discharge(PD)types.Firstly,PD signals are dealt with variational mode decomposition(VMD),and these obtained modes are used to construct corresponding Hilbert marginal spectrum by Hilbert transformation.Secondly,a Hilbert marginal spectrum of PD signal is taken as an input vector,and SAE can learn the inherent features and extract the succinct expressions from original data automatically.Thirdly,the results obtained by SAE are used to initialize DNN which is trained by a large number of samples.In the meanwhile,in order to speed up the convergence in the processes of learning for SAE and DNN,the network is optimized with the adaptive-step learning rate and updated with the weight parameters.Finally,DNN is trained well to identify the PD types of samples.Besides,compared with the results based on BP neural networks and support vector machines,the results based on SAE-DNN can achieve a higher accuracy.
A method based on Hilbert marginal spectrum and sparse autoencoder(SAE)-deep neural networks(DNN)is proposed to recognize partial discharge(PD)types.Firstly,PD signals are dealt with variational mode decomposition(VMD),and these obtained modes are used to construct corresponding Hilbert marginal spectrum by Hilbert transformation.Secondly,a Hilbert marginal spectrum of PD signal is taken as an input vector,and SAE can learn the inherent features and extract the succinct expressions from original data automatically.Thirdly,the results obtained by SAE are used to initialize DNN which is trained by a large number of samples.In the meanwhile,in order to speed up the convergence in the processes of learning for SAE and DNN,the network is optimized with the adaptive-step learning rate and updated with the weight parameters.Finally,DNN is trained well to identify the PD types of samples.Besides,compared with the results based on BP neural networks and support vector machines,the results based on SAE-DNN can achieve a higher accuracy.
引文
[1]黄大荣,陈长沙,孙国玺,等.电力变压器故障的客观熵权识别及诊断方法[J].电力系统自动化,2017,41(12):206-211.DOI:10.7500/AEPS20161028003.HUANG Darong,CHEN Changsha,SUN Guoxi,et al.Recognition diagnosis method of objective entropy weight for power transformer fault[J].Automation of Electric Power Systems,2017,41(12):206-211.DOI:10.7500/AEPS20161028003.
[2]朱永利,贾亚飞,王刘旺,等.基于改进变分模态分解和Hilbert变换的变压器局部放电信号特征提取及分类[J].电工技术学报,2017,32(9):221-235.ZHU Yongli,JIA Yafei,WANG Liuwang,et al.Feature extraction and classification on partial discharge signals of power transformers based on improved variational mode decomposition and Hilbert transform[J].Transactions of China Electrotechnical Society,2017,32(9):221-235.
[3]谈克雄,李福祺.局部放电识别用的几种人工神经网络[J].高电压技术,1996,22(4):3-7.TAN Kexiong,LI Fuqi.Some types of artificial neural networks used for recognition of partial discharge[J].High Voltage Engineering,1996,22(4):3-7.
[4]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,LIU Youwei,WU Liyuan.Identification of partial discharge in gas insulated switchgears with fractal theory and support vector machine[J].Power System Technology,2011,35(3):135-139.
[5]陈新美,潘笑颜,路光辉,等.基于朴素贝叶斯的局部放电诊断模型[J].计算机应用与软件,2016,33(9):51-55.CHEN Xinmei,PAN Xiaoyan,LU Guanghui,et al.A partial discharge diagnosis model based on naive Bayes[J].Computer Applications and Software,2016,33(9):51-55.
[6]杨志超,范立新,杨成顺,等.基于GK模糊聚类和LS-SVC的GIS局部放电类型识别[J].电力系统保护与控制,2014,42(20):38-45.YANG Zhichao,FAN Lixin,YANG Chengshun,et al.Identification of partial discharge in gas insulated switchgears based on GK fuzzy clustering&LS-SVC[J].Power System Protection and Control,2014,42(20):38-45.
[7]薛禹胜,赖业宁.大能源思维与大数据思维的融合:(一)大数据与电力大数据[J].电力系统自动化,2016,40(1):1-8.DOI:10.7500/AEPS20151208005.XUE Yusheng,LAI Yening.Integration of macro energy thinking and big data thinking:Part one big data and power big data[J].Automation of Electric Power Systems,2016,40(1):1-8.DOI:10.7500/AEPS20151208005.
[8]HINTON G,SALAKHUTDINOV R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[9]TAN J,LU W,AN J,et al.Fault diagnosis method study in roller bearing based on wavelet transform and stacked autoencoder[C]//Chinese Control and Decision Conference,May23-25,2015,Qingdao,China:6p.
[10]ZHU H,RUI T,WANG X,et al.Fault diagnosis of hydraulic pump based on stacked autoencoders[C]//IEEE International Conference on Electronic Measurement&Instruments,July16-18,2015,Qingdao,China:5p.
[11]黄新波,杨璐雅,张烨,等.基于图像增强的瓷质绝缘子灰密程度检测方法[J].电力系统自动化,2018,42(14):151-157.DOI:10.7500/AEPS20170614017.HUANG Xinbo,YANG Luya,ZHANG Ye,et al.Image enhancement based detection method of non-soluble de-posit density levels of porcelain insulator[J].Automation of Electric Power Systems,2018,42(14):151-157.DOI:10.7500/AEPS20170614017.
[12]缪希仁,吴晓梅,石敦义,等.采用HHT振动分析的低压断路器合闸同期辨识[J].电工技术学报,2014,29(11):154-161.MIAO Xiren,WU Xiaomei,SHI Dunyi,et al.Switching synchronism identification of low voltage circuit breaker utilizing HHT analysis to vibration signal[J].Transactions of China Electrotechnical Society,2014,29(11):154-161.
[13]DRAGOMIRETSKIY K,ZOSSO D.Variational mode decomposition[J].IEEE Transactions on Signal Processing,2014,62(3):531-544.
[14]叶吉祥,胡海翔.Hilbert边际能量谱在语音情感识别中的应用[J].计算机工程与应用,2014,50(7):203-207.YE Jixiang,HU Haixiang.Application of Hilbert marginal energy spectrum in speech emotion recognition[J].Computer Engineering and Applications,2014,50(7):203-207.
[15]钟佑明,秦树人,汤宝平.希尔伯特黄变换中边际谱的研究[J].系统工程与电子技术,2004,26(9):1323-1326.ZHONG Youming,QIN Shuren,TANG Baoping.Study on the marginal spectrum in Hilbert-Huang transform[J].Systems Engineering and Electronics,2004,26(9):1323-1326.
[16]蔡剑华,胡惟文,王先春.基于边际谱的功率谱估计方法[J].核电子学与探测技术,2011,31(9):1062-1066.CAI Jianhua,HU Weiwen,WANG Xianchun.Spectrum estimation method based on marginal spectrum[J].Nuclear Electronics&Detection Technology,2011,31(9):1062-1066.
[17]SHIN H,ORTON M,COLLINS D,et al.Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4Dpatient data[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2013,35(8):1930-1943.
[18]赵洪山,刘辉海,刘宏杨,等.基于堆叠自编码网络的风电机组发电机状态监测与故障诊断[J].电力系统自动化,2018,42(11):102-108.DOI:10.7500/AEPS20170730001.ZHAO Hongshan,LIU Huihai,LIU Hongyang,et al.Condition monitoring and fault diagnosis of wind turbine generator based on stacked autoencoders network[J].Automation of Electric Power Systems,2018,42(11):102-108.DOI:10.7500/AEPS20170730001.
[19]孙文珺,邵思羽,严如强.基于稀疏自动编码深度神经网络的感应电动机故障诊断[J].机械工程学报,2016,52(9):65-71.SUN Wenjun,SHAO Siyu,YAN Ruqiang.Induction motor fault diagnosis based on deep neural network of sparse autoencoder[J].Journal of Mechanical Engineering,2016,52(9):65-71.
[20]刘福才,贾亚飞,任丽娜.基于混沌粒子群优化算法的异结构混沌反同步自抗扰控制[J].物理学报,2013,62(12):98-105.LIU Fucai,JIA Yafei,REN Lina.Anti-synchronizing different chaotic systems using active disturbance rejection controller based on the chaos particle swarm optimization algorithm[J].Acta Physica Sinica,2013,62(12):98-105.
[21]时培明,梁凯,赵娜,等.基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断[J].中国机械工程,2017,28(9):1056-1061.SHI Peiming,LIANG Kai,ZHAO Na,et al.Intelligent fault diagnosis for gears based on deep learning feature extraction and partial swarm optimization SVM state identification[J].China Mechanical Engineering,2017,28(9):1056-1061.
[22]贾亚飞,朱永利,王刘旺,等.基于VMD和多尺度熵的变压器内绝缘局部放电信号特征提取及分类[J].电工技术学报,2016,31(19):208-217.JIA Yafei,ZHU Yongli,WANG Liuwang,et al.Feature extraction and classification on partial discharge signals of power transformers based on VMD and multiscale entropy[J].Transactions of China Electrotechnical Society,2016,31(19):208-217.
[2]朱永利,贾亚飞,王刘旺,等.基于改进变分模态分解和Hilbert变换的变压器局部放电信号特征提取及分类[J].电工技术学报,2017,32(9):221-235.ZHU Yongli,JIA Yafei,WANG Liuwang,et al.Feature extraction and classification on partial discharge signals of power transformers based on improved variational mode decomposition and Hilbert transform[J].Transactions of China Electrotechnical Society,2017,32(9):221-235.
[3]谈克雄,李福祺.局部放电识别用的几种人工神经网络[J].高电压技术,1996,22(4):3-7.TAN Kexiong,LI Fuqi.Some types of artificial neural networks used for recognition of partial discharge[J].High Voltage Engineering,1996,22(4):3-7.
[4]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,LIU Youwei,WU Liyuan.Identification of partial discharge in gas insulated switchgears with fractal theory and support vector machine[J].Power System Technology,2011,35(3):135-139.
[5]陈新美,潘笑颜,路光辉,等.基于朴素贝叶斯的局部放电诊断模型[J].计算机应用与软件,2016,33(9):51-55.CHEN Xinmei,PAN Xiaoyan,LU Guanghui,et al.A partial discharge diagnosis model based on naive Bayes[J].Computer Applications and Software,2016,33(9):51-55.
[6]杨志超,范立新,杨成顺,等.基于GK模糊聚类和LS-SVC的GIS局部放电类型识别[J].电力系统保护与控制,2014,42(20):38-45.YANG Zhichao,FAN Lixin,YANG Chengshun,et al.Identification of partial discharge in gas insulated switchgears based on GK fuzzy clustering&LS-SVC[J].Power System Protection and Control,2014,42(20):38-45.
[7]薛禹胜,赖业宁.大能源思维与大数据思维的融合:(一)大数据与电力大数据[J].电力系统自动化,2016,40(1):1-8.DOI:10.7500/AEPS20151208005.XUE Yusheng,LAI Yening.Integration of macro energy thinking and big data thinking:Part one big data and power big data[J].Automation of Electric Power Systems,2016,40(1):1-8.DOI:10.7500/AEPS20151208005.
[8]HINTON G,SALAKHUTDINOV R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[9]TAN J,LU W,AN J,et al.Fault diagnosis method study in roller bearing based on wavelet transform and stacked autoencoder[C]//Chinese Control and Decision Conference,May23-25,2015,Qingdao,China:6p.
[10]ZHU H,RUI T,WANG X,et al.Fault diagnosis of hydraulic pump based on stacked autoencoders[C]//IEEE International Conference on Electronic Measurement&Instruments,July16-18,2015,Qingdao,China:5p.
[11]黄新波,杨璐雅,张烨,等.基于图像增强的瓷质绝缘子灰密程度检测方法[J].电力系统自动化,2018,42(14):151-157.DOI:10.7500/AEPS20170614017.HUANG Xinbo,YANG Luya,ZHANG Ye,et al.Image enhancement based detection method of non-soluble de-posit density levels of porcelain insulator[J].Automation of Electric Power Systems,2018,42(14):151-157.DOI:10.7500/AEPS20170614017.
[12]缪希仁,吴晓梅,石敦义,等.采用HHT振动分析的低压断路器合闸同期辨识[J].电工技术学报,2014,29(11):154-161.MIAO Xiren,WU Xiaomei,SHI Dunyi,et al.Switching synchronism identification of low voltage circuit breaker utilizing HHT analysis to vibration signal[J].Transactions of China Electrotechnical Society,2014,29(11):154-161.
[13]DRAGOMIRETSKIY K,ZOSSO D.Variational mode decomposition[J].IEEE Transactions on Signal Processing,2014,62(3):531-544.
[14]叶吉祥,胡海翔.Hilbert边际能量谱在语音情感识别中的应用[J].计算机工程与应用,2014,50(7):203-207.YE Jixiang,HU Haixiang.Application of Hilbert marginal energy spectrum in speech emotion recognition[J].Computer Engineering and Applications,2014,50(7):203-207.
[15]钟佑明,秦树人,汤宝平.希尔伯特黄变换中边际谱的研究[J].系统工程与电子技术,2004,26(9):1323-1326.ZHONG Youming,QIN Shuren,TANG Baoping.Study on the marginal spectrum in Hilbert-Huang transform[J].Systems Engineering and Electronics,2004,26(9):1323-1326.
[16]蔡剑华,胡惟文,王先春.基于边际谱的功率谱估计方法[J].核电子学与探测技术,2011,31(9):1062-1066.CAI Jianhua,HU Weiwen,WANG Xianchun.Spectrum estimation method based on marginal spectrum[J].Nuclear Electronics&Detection Technology,2011,31(9):1062-1066.
[17]SHIN H,ORTON M,COLLINS D,et al.Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4Dpatient data[J].IEEETransactions on Pattern Analysis&Machine Intelligence,2013,35(8):1930-1943.
[18]赵洪山,刘辉海,刘宏杨,等.基于堆叠自编码网络的风电机组发电机状态监测与故障诊断[J].电力系统自动化,2018,42(11):102-108.DOI:10.7500/AEPS20170730001.ZHAO Hongshan,LIU Huihai,LIU Hongyang,et al.Condition monitoring and fault diagnosis of wind turbine generator based on stacked autoencoders network[J].Automation of Electric Power Systems,2018,42(11):102-108.DOI:10.7500/AEPS20170730001.
[19]孙文珺,邵思羽,严如强.基于稀疏自动编码深度神经网络的感应电动机故障诊断[J].机械工程学报,2016,52(9):65-71.SUN Wenjun,SHAO Siyu,YAN Ruqiang.Induction motor fault diagnosis based on deep neural network of sparse autoencoder[J].Journal of Mechanical Engineering,2016,52(9):65-71.
[20]刘福才,贾亚飞,任丽娜.基于混沌粒子群优化算法的异结构混沌反同步自抗扰控制[J].物理学报,2013,62(12):98-105.LIU Fucai,JIA Yafei,REN Lina.Anti-synchronizing different chaotic systems using active disturbance rejection controller based on the chaos particle swarm optimization algorithm[J].Acta Physica Sinica,2013,62(12):98-105.
[21]时培明,梁凯,赵娜,等.基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断[J].中国机械工程,2017,28(9):1056-1061.SHI Peiming,LIANG Kai,ZHAO Na,et al.Intelligent fault diagnosis for gears based on deep learning feature extraction and partial swarm optimization SVM state identification[J].China Mechanical Engineering,2017,28(9):1056-1061.
[22]贾亚飞,朱永利,王刘旺,等.基于VMD和多尺度熵的变压器内绝缘局部放电信号特征提取及分类[J].电工技术学报,2016,31(19):208-217.JIA Yafei,ZHU Yongli,WANG Liuwang,et al.Feature extraction and classification on partial discharge signals of power transformers based on VMD and multiscale entropy[J].Transactions of China Electrotechnical Society,2016,31(19):208-217.