Anewfault location algorithmfor double-circuit transmissionlines is described inthis paper.Theproposed method uses data extractedfromtwo ends of the transmissionlines andthus eliminates the effects ofthe source impeda...Anewfault location algorithmfor double-circuit transmissionlines is described inthis paper.Theproposed method uses data extractedfromtwo ends of the transmissionlines andthus eliminates the effects ofthe source impedance andthe fault resistance.The distributed parameter model and the modal transformationare also employed.Depending on modal transformation,the coupled equations of the lines are converted intodecoupled ones.Inthis way,the mutual coupling effects between adjacent circuits of the lines are eliminatedandtherefore an accurate fault location can be achieved.The proposed methodis tested via digital simulationusing EMTP in conjunction with MATLAB.The test results corroborate the high accuracy of the proposedmethod.展开更多
In recent years,several failures of double circuit transmission line on the same tower due to lightning were happened in Beijing power grid.Although it can be reclosed successful,the lightning strike caused a grave th...In recent years,several failures of double circuit transmission line on the same tower due to lightning were happened in Beijing power grid.Although it can be reclosed successful,the lightning strike caused a grave threat to the power grid security.The cause of the accident and the accident process were studied for the sake of further understanding of the impact of lightning on power grid.As an example,110 kV double circuit transmission line(Xilong-line) was analyzed.At first,the system topology was given.Through the analysis on relay protection actions and the fault recorder data,over voltage on the insulator strings was calculated.Based on the analysis and the calculation,accident cause and the process were presented respectively.Secondly,it comes to the conclusion that the lightning failure was caused by counterattack.The wave of the lightning over voltage would spread to the not grounded neutral point of the transformers,and make the neutral protective gap breakdown,then cause freewheeling with the frequency of 50 Hz.As results of the relay protection,the double circuit transmission line all tripped out.Finally,the causes of the accident were proposed that included terrain features,large corner towers,strong thunderstorm weather and poor grounded contact of the tower.展开更多
为解决传统特高压直流保护对高阻故障检测准确率不高、故障检测时间过长以及故障选极不完善的问题,提出基于长短时记忆(long short term memory,LSTM)循环神经网络(recurrent neural network,RNN)的特高压直流输电线路继电保护故障检测...为解决传统特高压直流保护对高阻故障检测准确率不高、故障检测时间过长以及故障选极不完善的问题,提出基于长短时记忆(long short term memory,LSTM)循环神经网络(recurrent neural network,RNN)的特高压直流输电线路继电保护故障检测方法。首先,基于快速傅里叶变换分析特高压直流输电系统暂态故障特征,使用相模变换和小波变换提取出故障特征量作为输入数据。其次,将输入数据输入到LSTM-RNN中进行前向传播,对系统故障特征进行深度学习,同时使用反向传播方式更新网络参数,将深层的特征量输入到Softmax分类器中进行分类,把故障识别分成区外故障、母线故障和线路故障,故障分类为正极故障、负极故障和双极故障,并输出识别结果。最后,在PSCAD/EMTDC仿真条件下,搭建特高压直流输电模型。验证结果表明:所提的方法在特高压直流输电线路继电保护的故障检测、故障选极上具有更好的效果,相比于人工神经网络、卷积神经网络、支持向量机,故障识别准确率分别提升4.71%、6.57%、9.32%。展开更多
文摘Anewfault location algorithmfor double-circuit transmissionlines is described inthis paper.Theproposed method uses data extractedfromtwo ends of the transmissionlines andthus eliminates the effects ofthe source impedance andthe fault resistance.The distributed parameter model and the modal transformationare also employed.Depending on modal transformation,the coupled equations of the lines are converted intodecoupled ones.Inthis way,the mutual coupling effects between adjacent circuits of the lines are eliminatedandtherefore an accurate fault location can be achieved.The proposed methodis tested via digital simulationusing EMTP in conjunction with MATLAB.The test results corroborate the high accuracy of the proposedmethod.
文摘In recent years,several failures of double circuit transmission line on the same tower due to lightning were happened in Beijing power grid.Although it can be reclosed successful,the lightning strike caused a grave threat to the power grid security.The cause of the accident and the accident process were studied for the sake of further understanding of the impact of lightning on power grid.As an example,110 kV double circuit transmission line(Xilong-line) was analyzed.At first,the system topology was given.Through the analysis on relay protection actions and the fault recorder data,over voltage on the insulator strings was calculated.Based on the analysis and the calculation,accident cause and the process were presented respectively.Secondly,it comes to the conclusion that the lightning failure was caused by counterattack.The wave of the lightning over voltage would spread to the not grounded neutral point of the transformers,and make the neutral protective gap breakdown,then cause freewheeling with the frequency of 50 Hz.As results of the relay protection,the double circuit transmission line all tripped out.Finally,the causes of the accident were proposed that included terrain features,large corner towers,strong thunderstorm weather and poor grounded contact of the tower.
文摘为解决传统特高压直流保护对高阻故障检测准确率不高、故障检测时间过长以及故障选极不完善的问题,提出基于长短时记忆(long short term memory,LSTM)循环神经网络(recurrent neural network,RNN)的特高压直流输电线路继电保护故障检测方法。首先,基于快速傅里叶变换分析特高压直流输电系统暂态故障特征,使用相模变换和小波变换提取出故障特征量作为输入数据。其次,将输入数据输入到LSTM-RNN中进行前向传播,对系统故障特征进行深度学习,同时使用反向传播方式更新网络参数,将深层的特征量输入到Softmax分类器中进行分类,把故障识别分成区外故障、母线故障和线路故障,故障分类为正极故障、负极故障和双极故障,并输出识别结果。最后,在PSCAD/EMTDC仿真条件下,搭建特高压直流输电模型。验证结果表明:所提的方法在特高压直流输电线路继电保护的故障检测、故障选极上具有更好的效果,相比于人工神经网络、卷积神经网络、支持向量机,故障识别准确率分别提升4.71%、6.57%、9.32%。
