首页> 外国专利> ARC LIGHT FAULT IDENTIFYING DEVICE AND METHOD BASED ON PANORAMIC INFORMATION

ARC LIGHT FAULT IDENTIFYING DEVICE AND METHOD BASED ON PANORAMIC INFORMATION

机译:基于全景信息的电弧光故障识别装置及方法

摘要

The present invention relates to the technical field of power automation, and relates to an arc light fault identifying method based on panoramic information, thereby realizing arc light identification of a circuit breaker. By analyzing the characteristic change of current in a time domain and a frequency domain when an electric arc fault occurs, extracting an appropriate characteristic value as the input of an error back propagation (BP) neural network, detecting the electric arc fault by using the BP neural network, for the defect of slow convergence of the BP neural network, obtaining an initial weight value of the BP neural network by using a genetic algorithm, and accelerating the training convergence speed of the neural network, the output signal-noise ratio of the method is high, and thus, the accuracy and reliability of fault electric arc detection are improved.
机译:本发明涉及电力自动化技术领域,涉及一种基于全景信息的电弧光故障识别方法,从而实现断路器的电弧光识别。通过分析发生电弧故障时电流在时域和频域中的特征变化,提取适当的特征值作为误差反向传播(BP)神经网络的输入,使用BP检测电弧故障神经网络,针对BP神经网络收敛速度慢的缺陷,通过遗传算法获得BP神经网络的初始权重值,并加快神经网络的训练收敛速度,以提高神经网络的输出信噪比。该方法具有很高的检测率,提高了故障电弧检测的准确性和可靠性。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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