基于VMD样本熵和KELM的输电线路故障诊断
|
摘要
针对输电线路短路故障危害大,故障识别率较低的情况,提出基于变分模态分解(VMD)样本熵与核极端学习机(KELM)相结合的输电线路故障诊断方法,提高输电线路故障诊断的正确率。首先,采用VMD对故障后的三相电压进行分解,得到一系列三相平稳的模态分量;其次分别计算每组各分量的样本熵值,作为输电线路故障提取特征,组成样本库;以提取的输电线路故障特征输入到核极端学习机进行训练,获取诊断模型,然后比较其与极限学习机(ELM)、支持向量机(SVM)和BP神经网络的诊断效果。仿真结果表明,VMD样本熵+KELM的输电线路故障诊断模型精度高于其他3种算法,且运算速率更快,噪声鲁棒性更好。
The fault diagnosis method based on the variational mode decomposition( VMD) sample entropy and kernel extreme learning machine( KELM) is proposed to improve the accuracy of the transmission line fault diagnosis,aiming at the damage of transmission line short-circuit fault and the low recognition rate. Firstly,the three-phase voltage after the fault is decomposed by VMD and three groups of stationary modal components are obtained. Secondly,the entropy of each component of each component is calculated,the feature extraction of the transmission line fault is completed and the sample library is formed. Finally,the KELM is used to diagnose transmission line fault and compared with the extreme learning machine( ELM),support vector machine( SVM) and BP algorithm. The simulation results show that the transmission line fault diagnosis of VMD sample entropy and KELM is not affected by the fault time,fault type and transition resistance,and the correct rate is higher than the ELM,SVM and BP algorithms. It can better realize the fault diagnosis of transmission lines,have better generalization ability,and the running time is far less than the other three kinds of algorithms. Experiments show that the fault diagnosis model of VMD sample entropy and KELM is more accurate than the other three algorithms,with faster operation rate and better noise robustness.
The fault diagnosis method based on the variational mode decomposition( VMD) sample entropy and kernel extreme learning machine( KELM) is proposed to improve the accuracy of the transmission line fault diagnosis,aiming at the damage of transmission line short-circuit fault and the low recognition rate. Firstly,the three-phase voltage after the fault is decomposed by VMD and three groups of stationary modal components are obtained. Secondly,the entropy of each component of each component is calculated,the feature extraction of the transmission line fault is completed and the sample library is formed. Finally,the KELM is used to diagnose transmission line fault and compared with the extreme learning machine( ELM),support vector machine( SVM) and BP algorithm. The simulation results show that the transmission line fault diagnosis of VMD sample entropy and KELM is not affected by the fault time,fault type and transition resistance,and the correct rate is higher than the ELM,SVM and BP algorithms. It can better realize the fault diagnosis of transmission lines,have better generalization ability,and the running time is far less than the other three kinds of algorithms. Experiments show that the fault diagnosis model of VMD sample entropy and KELM is more accurate than the other three algorithms,with faster operation rate and better noise robustness.
引文
[1]陆佳政,周特军,吴传平,等.某省级电网220 k V及以上输电线路故障统计与分析[J].高电压技术,2016,42(1):200-207.LU J ZH,ZHOU T J,WU CH P,et al.Fault statistics and analysis of 220 k V and above power transmission line in province-level power grid[J].High Voltage Engineering,2016,42(1):200-207.
[2]陈仕龙,谢佳伟,毕贵红,等.一种特高压直流输电线路神经网络双端故障测距新方法[J].电工技术学报,2015,30(4):257-264.CHEN SH L,XIE J W,BI G H,et al.A novel two terminal fault location method used ANN for UHVDC transmission line[J].Transactions of China Electrotechnical Socirty,2015,30(4):257-264.
[3]魏东,龚庆武,来文青,等.基于卷积神经网络的输电线路区内外故障判断及故障选相方法研究[J].中国电机工程学报,2016,36(S1):21-28.WEI D,GONG Q W,LAI W Q,et al.Research on internal and external fault diagnosis and fault-selection of transmission line based on convolutional neural network[J].Proceedings of the CSEE,2016,36(S1):21-28.
[4]符玲,何正友,钱清泉.超高压输电线路的故障暂态特征提取及故障类型判断[J].中国电机工程学报,2010,30(22):100-106.FU L,HE ZH Y,QIAN Q Q.Feature extraction of fault transientand fault type determination for EHVtransmission lines[J].Proceedings of the CSEE,2010,30(22):100-106.
[5]蔡剑华,肖永良.Hilbert-Huang变换与傅里叶变换在大地电磁数据处理中的适用性分析[J].地球物理学进展,2017,32(4):1548-1555.CAI J H,XIAO Y L.Applica-bility analysis of Fourier transform and Hilbert-Huang transform in the procession of magnetotelluric signal[J].Progress in Geophpysics,2017,32(4):1548-1555.
[6]ZHANG J M,ZHANG Y B,GUAN Y G.Analysis of timedomain reflecto-metry combined with wavelet transform for fault detection in aircraft shielded cables[J].IEEESensors Journal,2016,16(11):4579-4586.
[7]张淑清,翟欣沛,董璇,等.EMD及Duffing振子在小电流系统故障选线方法中的应用[J].中国电机工程学报,2013,33(10):161-167.ZHANG SH Q,ZHAI X P,DONG X,et al.Application of EMD and Duffing oscillator to fault line detection in uneffectively grounded system[J].Proceedings of the CSEE,2013,33(10):161-167.
[8]贺利芳,曹莉,张天琪.Levy噪声中EMD降噪的随机共振研究[J].电子测量与仪器学报,2017,31(1):21-27.HE L F,CAO L,ZHANG T Q.Stochastic resonance research with EMD de-nosing under Levy noise[J].Journal of Electronic Measurement and Insrtumention,2017,31(01):21-27.
[9]李舜酩,郭海东,李殿荣.振动信号处理方法综述[J].仪器仪表学报,2013,34(8):1907-1915.LI S M,GUO H D,LI D R.Review of vibration signal procesing methods[J].Chinese Journal of Scientific Instrument,2013,34(8):1907-1915.
[10]禹建丽,卞帅.基于BP神经网络的变压器故障诊断模型[J].系统仿真学报,2014,26(6):1343-1349.YU J L,BIAN SH.Fault diagnosis model of transformer based on BP neural network[J].Journal of System Simulation,2014,26(6):1343-1349.
[11]王新,闫文源.基于变分模态分解和SVM的滚动轴承故障诊断[J].振动与冲击,2017,36(18):252-256.WANG X,YAN W Y.Fault diagnosis of roller bearings based on the variational mode decomposition and SVM[J].Journal of Vibration and Shock,2017,36(18):252-256.
[12]KONSTANTIN D,DONMINIQUE Z.Veriational mode decomposition[J].IEEE Transactions on Signal Peocessing,2014,62(3):531-544.
[13]ANEESH.C,SACHIN K,HISHAM P M,et al.Performance comparison of variational mode decomposition over emprirical wavelet transform for classification of power quality disturbances using support vector machine[J].Procedia Computer Science,2015(46):372-380.
[14]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 Y F,ZHU Y L,WANG L W,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.
[15]张学清,梁军,张熙,等.基于样本熵和极端学习机的超短期风电功率组合预测模型[J].中国电机工程学报,2013,33(25):33-40.ZHANG X Q,LIANG J,ZHANG X,et al.Combined model for ultra short-term wind power prediction based on sample entropy and extreme learning machine[J].Proceedings of the CSEE,2013,33(25):33-40.
[16]单亚峰,汤月,任仁,等.基于邻域粗糙集与支持向量极端学习机的瓦斯传感器故障诊断[J].传感技术学报,2016,29(9):1400-1404.SHAN Y F,TANG Y,REN R,et al.Gas sensor fault diagnosis based on neighborhood rough set combined with support vector machine[J].Chinese Journal of Sensor and Actuators,2013,33(25):33-40.
[17]HUANG G B.An insight into extreme learning machine:random features and kernels[J].Congnitive Computing,2014,6(3):376-390.
[18]HUANG G B,DING X J,ZHOU H M.Optimization method based extreme learning machine for classification[J].Neurocomputing,2010(74):155-163.
[19]RICHMAN J S,MOORMAN J R.Physiological time-series analysis using approximate entropy and sample entropy[J].American Journal of Physiological Heat and Circulatory Physiology,2000,278(6):2039-2049.
[20]谢国民,丁会巧,付华,等.基于FRS与GA-ELM的煤与瓦斯突出预测研究[J].传感技术学报,2015,28(11):1670-1675.XIE G M,DING H Q,FU H,et al.Prediction of coal and gas outburst based on FRS and GA-ELM[J].Chinese Journal of Sensor and Actuators,2015,28(11):1670-1675.
[21]汤宝平,刘文艺,蒋永华.基于交叉验证法优化参数的Morlet小波消噪方法[J].重庆大学学报,2010,33(1):1-6.TAO B P,LIU W Y,JIANG Y H Yonghua.Parameter optimized Morlet wavelet denoising method based on cross validation method[J].Journal of Chongqing University,2010,33(1):1-6.
[22]朱霄珣,韩中合.基于PSO参数优化的LS-SVM风速预测方法研究[J].中国电机工程学报,2016,36(23):6337-6342,6598.ZHU X X,HAN ZH H.Research on LS-SVM wind speed prediction method based on PSO[J].Proceedings of the CSEE,2016,36(23):6337-6342,6598.
[2]陈仕龙,谢佳伟,毕贵红,等.一种特高压直流输电线路神经网络双端故障测距新方法[J].电工技术学报,2015,30(4):257-264.CHEN SH L,XIE J W,BI G H,et al.A novel two terminal fault location method used ANN for UHVDC transmission line[J].Transactions of China Electrotechnical Socirty,2015,30(4):257-264.
[3]魏东,龚庆武,来文青,等.基于卷积神经网络的输电线路区内外故障判断及故障选相方法研究[J].中国电机工程学报,2016,36(S1):21-28.WEI D,GONG Q W,LAI W Q,et al.Research on internal and external fault diagnosis and fault-selection of transmission line based on convolutional neural network[J].Proceedings of the CSEE,2016,36(S1):21-28.
[4]符玲,何正友,钱清泉.超高压输电线路的故障暂态特征提取及故障类型判断[J].中国电机工程学报,2010,30(22):100-106.FU L,HE ZH Y,QIAN Q Q.Feature extraction of fault transientand fault type determination for EHVtransmission lines[J].Proceedings of the CSEE,2010,30(22):100-106.
[5]蔡剑华,肖永良.Hilbert-Huang变换与傅里叶变换在大地电磁数据处理中的适用性分析[J].地球物理学进展,2017,32(4):1548-1555.CAI J H,XIAO Y L.Applica-bility analysis of Fourier transform and Hilbert-Huang transform in the procession of magnetotelluric signal[J].Progress in Geophpysics,2017,32(4):1548-1555.
[6]ZHANG J M,ZHANG Y B,GUAN Y G.Analysis of timedomain reflecto-metry combined with wavelet transform for fault detection in aircraft shielded cables[J].IEEESensors Journal,2016,16(11):4579-4586.
[7]张淑清,翟欣沛,董璇,等.EMD及Duffing振子在小电流系统故障选线方法中的应用[J].中国电机工程学报,2013,33(10):161-167.ZHANG SH Q,ZHAI X P,DONG X,et al.Application of EMD and Duffing oscillator to fault line detection in uneffectively grounded system[J].Proceedings of the CSEE,2013,33(10):161-167.
[8]贺利芳,曹莉,张天琪.Levy噪声中EMD降噪的随机共振研究[J].电子测量与仪器学报,2017,31(1):21-27.HE L F,CAO L,ZHANG T Q.Stochastic resonance research with EMD de-nosing under Levy noise[J].Journal of Electronic Measurement and Insrtumention,2017,31(01):21-27.
[9]李舜酩,郭海东,李殿荣.振动信号处理方法综述[J].仪器仪表学报,2013,34(8):1907-1915.LI S M,GUO H D,LI D R.Review of vibration signal procesing methods[J].Chinese Journal of Scientific Instrument,2013,34(8):1907-1915.
[10]禹建丽,卞帅.基于BP神经网络的变压器故障诊断模型[J].系统仿真学报,2014,26(6):1343-1349.YU J L,BIAN SH.Fault diagnosis model of transformer based on BP neural network[J].Journal of System Simulation,2014,26(6):1343-1349.
[11]王新,闫文源.基于变分模态分解和SVM的滚动轴承故障诊断[J].振动与冲击,2017,36(18):252-256.WANG X,YAN W Y.Fault diagnosis of roller bearings based on the variational mode decomposition and SVM[J].Journal of Vibration and Shock,2017,36(18):252-256.
[12]KONSTANTIN D,DONMINIQUE Z.Veriational mode decomposition[J].IEEE Transactions on Signal Peocessing,2014,62(3):531-544.
[13]ANEESH.C,SACHIN K,HISHAM P M,et al.Performance comparison of variational mode decomposition over emprirical wavelet transform for classification of power quality disturbances using support vector machine[J].Procedia Computer Science,2015(46):372-380.
[14]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 Y F,ZHU Y L,WANG L W,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.
[15]张学清,梁军,张熙,等.基于样本熵和极端学习机的超短期风电功率组合预测模型[J].中国电机工程学报,2013,33(25):33-40.ZHANG X Q,LIANG J,ZHANG X,et al.Combined model for ultra short-term wind power prediction based on sample entropy and extreme learning machine[J].Proceedings of the CSEE,2013,33(25):33-40.
[16]单亚峰,汤月,任仁,等.基于邻域粗糙集与支持向量极端学习机的瓦斯传感器故障诊断[J].传感技术学报,2016,29(9):1400-1404.SHAN Y F,TANG Y,REN R,et al.Gas sensor fault diagnosis based on neighborhood rough set combined with support vector machine[J].Chinese Journal of Sensor and Actuators,2013,33(25):33-40.
[17]HUANG G B.An insight into extreme learning machine:random features and kernels[J].Congnitive Computing,2014,6(3):376-390.
[18]HUANG G B,DING X J,ZHOU H M.Optimization method based extreme learning machine for classification[J].Neurocomputing,2010(74):155-163.
[19]RICHMAN J S,MOORMAN J R.Physiological time-series analysis using approximate entropy and sample entropy[J].American Journal of Physiological Heat and Circulatory Physiology,2000,278(6):2039-2049.
[20]谢国民,丁会巧,付华,等.基于FRS与GA-ELM的煤与瓦斯突出预测研究[J].传感技术学报,2015,28(11):1670-1675.XIE G M,DING H Q,FU H,et al.Prediction of coal and gas outburst based on FRS and GA-ELM[J].Chinese Journal of Sensor and Actuators,2015,28(11):1670-1675.
[21]汤宝平,刘文艺,蒋永华.基于交叉验证法优化参数的Morlet小波消噪方法[J].重庆大学学报,2010,33(1):1-6.TAO B P,LIU W Y,JIANG Y H Yonghua.Parameter optimized Morlet wavelet denoising method based on cross validation method[J].Journal of Chongqing University,2010,33(1):1-6.
[22]朱霄珣,韩中合.基于PSO参数优化的LS-SVM风速预测方法研究[J].中国电机工程学报,2016,36(23):6337-6342,6598.ZHU X X,HAN ZH H.Research on LS-SVM wind speed prediction method based on PSO[J].Proceedings of the CSEE,2016,36(23):6337-6342,6598.