...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Power Delivery >An ANN based approach to improve the speed of a differentialequation based distance relaying algorithm
【24h】

An ANN based approach to improve the speed of a differentialequation based distance relaying algorithm

机译：一种基于ANN的方法来提高基于差分方程的距离中继算法的速度

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper presents an artificial neural network (ANN) basednapproach to improve the speed of a differential equation based distancenrelaying algorithm. As the differential equation used for thentransmission line protection is valid only at low frequencies, thendistance relaying algorithm requires a lowpass filter, removingnfrequency components higher than those for relaying. However, thenlowpass filter causes the time delay of the components for relaying.nThus, the calculated resistances and reactances do not converge directlynto the fault distance even after data window occupies post fault data.nFaults with the same fault inception angle have similar shapes ofnimpedance loci. If an ANN is trained with the shape of various impedancenloci for fault distances and fault inception angles, it can predict thenfault distance with some values of calculated resistances and reactancesnbefore they converge to the fault distance. Therefore, the ANN cannimprove the speed of the distance relaying algorithm without affectingnits accuracy. Moreover, the proposed approach can speed up more when anhigher sampling rate is employed. The proposed approach was tested innthree rates of 24, 48 and 96 samples/cycle (s/c) in a 345 (kV)ntransmission system and compared with the conventional distance relayingnalgorithm without ANNs from the speed and accuracy viewpoints. As anresult, the approach can improve the speed of the relaying algorithm
机译：本文提出了一种基于人工神经网络的方法来提高基于微分方程的距离中继算法的速度。由于用于传输线保护的微分方程仅在低频下有效，因此距离中继算法需要一个低通滤波器，以去除高于中继分量的n个频率分量。但是，低通滤波器会导致继电器的延时。n因此，即使在数据窗口占据故障后数据之后，计算出的电阻和电抗也不会直接收敛到故障距离。n具有相同故障起始角的故障具有类似的阻抗轨迹形状。如果用各种阻抗nloci的形状训练ANN来确定故障距离和故障接收角度，则可以在计算出的电阻和电抗值收敛到故障距离之前用计算出的电阻和电抗的一些值预测故障距离。因此，人工神经网络可以提高距离中继算法的速度，而不会影响精度。此外，当采用更高的采样率时，所提出的方法可以加快速度。在345（kV）n传输系统中，以24、48和96个样本/周期（s / c）的三种速率测试了该方法，并从速度和准确性的角度将其与不带ANN的常规距离中继算法进行了比较。结果，该方法可以提高中继算法的速度

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号