• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Applied Computational Electromagnetics Society journal >A New Method for Stranded Cable Crosstalk Estimation Based on BAS-BP Neural Network Algorithm Combined with FDTD Method
【24h】

A New Method for Stranded Cable Crosstalk Estimation Based on BAS-BP Neural Network Algorithm Combined with FDTD Method

机译：基于BAS-BP神经网络算法和FDTD方法的电缆串扰估计新方法

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

In this paper, based on the research of back propagation (BP) neural network algorithm optimized by the beetle antennae search (BAS) algorithm, a new method for predicting stranded cable crosstalk is proposed. Firstly, the stranded wire model and the equivalent multiconductor transmission lines model are both established. Then, the extraction network of the stranded wire electromagnetic parameter matrix is constructed by using the BAS-BP neural network algorithm. Finally, the network is combined with the finite difference time domain (FDTD) method to solve the near end crosstalk (NEXT) and far end crosstalk (FEXT) of a specific three-core stranded model. The new method has good agreement with the crosstalk results obtained by the electromagnetic field numerical method. The validity of the new method is verified.
机译：本文在基于甲虫天线搜索（BAS）算法优化的BP神经网络算法研究的基础上，提出了一种预测电缆绞合串扰的新方法。首先，建立了绞合线模型和等效多导体传输线模型。然后，利用BAS-BP神经网络算法构造绞线电磁参数矩阵的提取网络。最后，将网络与时差有限差分法（FDTD）相结合，以解决特定三芯绞合模型的近端串扰（NEXT）和远端串扰（FEXT）。新方法与电磁场数值方法获得的串扰结果吻合良好。验证了新方法的有效性。

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