适应衰减直流分量估计的特定神经网络模型
|
摘要
为了估计出曲线函数的参数,提出了一种特定神经网络应用于图形曲线的函数拟合,并针对故障电流信号中包含的指数衰减直流分量降低继电保护操作的精度和效率等问题,构造了一种适应衰减直流分量估计的神经网络模型(decaying DC neural network,DDCNN),推导出基于Levenberg-Marquardt算法的网络权值自适应学习方法.该模型与包含衰减直流分量故障电流信号模型的数学表达式一致,在迭代求解神经网络的权值后,可直接由权值估计出衰减直流分量的所有参数.实验仿真结果及对比分析表明,本文算法能获得比现有算法更高的估计精度,且其计算代价能够满足应用需求.
In this paper,a specific neural network is proposed to function fitting of the graph curve,and then all the parameters of the curve function are estimated.For the fault current signal usually contain a decaying DC component and this component may decrease the accuracy and efficiency of the operation of digital relay protection,a specific neural network model is constructed for estimating decaying DC component,and then an adaptive learning algorithm based on LevenbergMarquardt algorithm is derived.Due to the consistency of the mathematical formulas between the proposed neural network model and the fault currents containing decaying DC component model,parameters of the decaying DC component can be directly calculated using the converged weights of the proposed neural network.Simulation results and comparative analysis validate that this algorithm can achieve a higher accuracy than the state-of-the-art algorithm.Moreover,the time cost of the proposed algorithm can be accepted for digital relay protection.
In this paper,a specific neural network is proposed to function fitting of the graph curve,and then all the parameters of the curve function are estimated.For the fault current signal usually contain a decaying DC component and this component may decrease the accuracy and efficiency of the operation of digital relay protection,a specific neural network model is constructed for estimating decaying DC component,and then an adaptive learning algorithm based on LevenbergMarquardt algorithm is derived.Due to the consistency of the mathematical formulas between the proposed neural network model and the fault currents containing decaying DC component model,parameters of the decaying DC component can be directly calculated using the converged weights of the proposed neural network.Simulation results and comparative analysis validate that this algorithm can achieve a higher accuracy than the state-of-the-art algorithm.Moreover,the time cost of the proposed algorithm can be accepted for digital relay protection.
引文
[1]VATANKULU Y E,爦ENTRK Z,SALOR O.Harmonics and interharmonics analysis of electrical arc furnaces based on spectral model optimization with high resolution windowing[J].IEEE Trans Ind Appl,2017,53(3):2587-2595.
[2]牟澎涛,赵冬梅,金小明,等.一种适用于小信号稳定性分析的参数整定方法[J].扬州大学学报(自然科学版),2016,19(3):45-48.
[3]CHO Y S,LEE C K,JANG G,et al.An innovative decaying DC component estimation algorithm for digital relaying[J].IEEE Trans Power Delivery,2009,24(1):73-78.
[4]WANG Li,SUONAN Jiale.A fast algorithm to estimate phasor in power systems[J].IEEE Trans Power Delivery,2017,32(3):1147-1156.
[5]TAJDINIAN M,JAHROMI M Z,MOHSENI K,et al.An analytical approach for removal of decaying DC component considering frequency deviation[J].Elec Power Syst Res,2016,130:208-219.
[6]GU J C,SHEN K Y,YU S L,et al.Removal of dc offset and subsynchronous resonance in current signals for series compensated transmission lines using a novel Fourier filter algorithm[J].Elec Power Syst Res,2006,76(5):327-335.
[7]HOOSHYAR A,SANAYE-PASAND M.Accurate measurement of fault currents contaminated with decaying DC offset and CT saturation[J].IEEE Trans Power Delivery,2012,27(2):773-783.
[8]SIDHU T S,ZHANG X,ALBASRI F,et al.Discrete-Fourier-transform-based technique for removal of decaying DC offset from phasor estimates[J].IEE ProcGener Transm Distrib,2003,150(6):745-752.
[9]ROSOOWSKI E,I6)ZYKOWSKI J,KASZTENNY B.Adaptive measuring algorithm suppressing a decaying DC component for digital protective relays[J].Elec Power Syst Res,2001,60(2):99-105.
[10]XIAO Xiuchun,LAI Jianhuang,WANG Changdong.Parameter estimation of the exponentially damped sinusoids signal using a specific neural network[J].Neurocomputing,2014,143:331-338.
[11]MAREI M I,EL-SAADANY E F,SALAMA M M A.A processing unit for symmetrical components and harmonics estimation based on a new adaptive linear combiner struture[J].IEEE Trans Power Delivery,2004,19(3):1245-1252.
[12]肖秀春,姜孝华,张雨浓.一种基函数神经网络最优隐神经元数目快速确定算法[J].微电子学与计算机,2010,27(1):57-60.
[2]牟澎涛,赵冬梅,金小明,等.一种适用于小信号稳定性分析的参数整定方法[J].扬州大学学报(自然科学版),2016,19(3):45-48.
[3]CHO Y S,LEE C K,JANG G,et al.An innovative decaying DC component estimation algorithm for digital relaying[J].IEEE Trans Power Delivery,2009,24(1):73-78.
[4]WANG Li,SUONAN Jiale.A fast algorithm to estimate phasor in power systems[J].IEEE Trans Power Delivery,2017,32(3):1147-1156.
[5]TAJDINIAN M,JAHROMI M Z,MOHSENI K,et al.An analytical approach for removal of decaying DC component considering frequency deviation[J].Elec Power Syst Res,2016,130:208-219.
[6]GU J C,SHEN K Y,YU S L,et al.Removal of dc offset and subsynchronous resonance in current signals for series compensated transmission lines using a novel Fourier filter algorithm[J].Elec Power Syst Res,2006,76(5):327-335.
[7]HOOSHYAR A,SANAYE-PASAND M.Accurate measurement of fault currents contaminated with decaying DC offset and CT saturation[J].IEEE Trans Power Delivery,2012,27(2):773-783.
[8]SIDHU T S,ZHANG X,ALBASRI F,et al.Discrete-Fourier-transform-based technique for removal of decaying DC offset from phasor estimates[J].IEE ProcGener Transm Distrib,2003,150(6):745-752.
[9]ROSOOWSKI E,I6)ZYKOWSKI J,KASZTENNY B.Adaptive measuring algorithm suppressing a decaying DC component for digital protective relays[J].Elec Power Syst Res,2001,60(2):99-105.
[10]XIAO Xiuchun,LAI Jianhuang,WANG Changdong.Parameter estimation of the exponentially damped sinusoids signal using a specific neural network[J].Neurocomputing,2014,143:331-338.
[11]MAREI M I,EL-SAADANY E F,SALAMA M M A.A processing unit for symmetrical components and harmonics estimation based on a new adaptive linear combiner struture[J].IEEE Trans Power Delivery,2004,19(3):1245-1252.
[12]肖秀春,姜孝华,张雨浓.一种基函数神经网络最优隐神经元数目快速确定算法[J].微电子学与计算机,2010,27(1):57-60.