With the development of large-scale complicated modern power systems, the requirement for the associated protection scheme tends to be more stringent and its combination more complex. However, it is very difficult to ...With the development of large-scale complicated modern power systems, the requirement for the associated protection scheme tends to be more stringent and its combination more complex. However, it is very difficult to figure out the factors of failure of such systems. This paper proposes a Petri net model of a transmission line protection relaying system, including three types of relays as well as an automatic reclosing device, and shows how to diagnose serial failure of the system by analyzing invariant sets of the model. Furthermore, it gives four basic types of failure sequences and its execution is much more intuitive and effective than the traditional method.展开更多
There were many accidents of large-scale wind turbines disconnecting from power grid in 2011.As singlephase-to-ground fault cannot be correctly detected,single-phase-to-ground fault evolved to phase-to-phase fault.Pha...There were many accidents of large-scale wind turbines disconnecting from power grid in 2011.As singlephase-to-ground fault cannot be correctly detected,single-phase-to-ground fault evolved to phase-to-phase fault.Phase-to-phase fault was isolated slowly,thus leading to low voltage.And wind turbines without enough low voltage ride-through capacity had to be disconnected from the grid.After some wind turbines being disconnected from the grid,overvoltage caused by reactive power surplus made more wind turbines disconnect from the grid.Based on the accident analysis,this paper presents solutions to above problems,including travelling waves based single-phase-to-ground protection,adaptive low voltage protection,integrated protection and control,and high impedance fault detection.The solutions lay foundations in theory and technology to prevent large-scale wind turbines disconnecting from the operating power grid.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
针对故障录波大数据传输过程中的重要参数协议数据单元(protocol data unit,PDU)及传输层数据协议单元(transport protocol data unit,TPDU),提出应用长鼻浣熊算法(coati optimization algorithm,COA)优化技术的保信主子站通信方式。基...针对故障录波大数据传输过程中的重要参数协议数据单元(protocol data unit,PDU)及传输层数据协议单元(transport protocol data unit,TPDU),提出应用长鼻浣熊算法(coati optimization algorithm,COA)优化技术的保信主子站通信方式。基于保信系统网络架构及其PDU以及TPDU参数对网络流量的影响,建立考虑录波通信时长约束与瞬时流量约束的最大流量通信模型,同时引入COA算法进行参数优化,实现该背景下最优带宽配置。开展多类别变电站通信业务测试,并考虑极限情况下通信网络压力测试,所提方法能有效提升变电站信息传输能力以及可靠性。展开更多
文摘With the development of large-scale complicated modern power systems, the requirement for the associated protection scheme tends to be more stringent and its combination more complex. However, it is very difficult to figure out the factors of failure of such systems. This paper proposes a Petri net model of a transmission line protection relaying system, including three types of relays as well as an automatic reclosing device, and shows how to diagnose serial failure of the system by analyzing invariant sets of the model. Furthermore, it gives four basic types of failure sequences and its execution is much more intuitive and effective than the traditional method.
基金supported by Major International Collaborative Project of National Natural Science Foundation of China(No.51120175001)Key Project of National Natural Science Foundation of China(No.50937003)
文摘There were many accidents of large-scale wind turbines disconnecting from power grid in 2011.As singlephase-to-ground fault cannot be correctly detected,single-phase-to-ground fault evolved to phase-to-phase fault.Phase-to-phase fault was isolated slowly,thus leading to low voltage.And wind turbines without enough low voltage ride-through capacity had to be disconnected from the grid.After some wind turbines being disconnected from the grid,overvoltage caused by reactive power surplus made more wind turbines disconnect from the grid.Based on the accident analysis,this paper presents solutions to above problems,including travelling waves based single-phase-to-ground protection,adaptive low voltage protection,integrated protection and control,and high impedance fault detection.The solutions lay foundations in theory and technology to prevent large-scale wind turbines disconnecting from the operating power grid.
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%。
文摘针对故障录波大数据传输过程中的重要参数协议数据单元(protocol data unit,PDU)及传输层数据协议单元(transport protocol data unit,TPDU),提出应用长鼻浣熊算法(coati optimization algorithm,COA)优化技术的保信主子站通信方式。基于保信系统网络架构及其PDU以及TPDU参数对网络流量的影响,建立考虑录波通信时长约束与瞬时流量约束的最大流量通信模型,同时引入COA算法进行参数优化,实现该背景下最优带宽配置。开展多类别变电站通信业务测试,并考虑极限情况下通信网络压力测试,所提方法能有效提升变电站信息传输能力以及可靠性。
