【24h】

Improvement of Targeting Efficiency in Chaos Control Using Clustering

机译:利用聚类提高混沌控制的目标效率

获取原文
获取原文并翻译 | 示例

摘要

In this paper an improved version of the previously presented ECR (Extended Control Regions) targeting method is proposed, where the system data is first pre-processed and subdivided into clusters, and then one artificial neural network is assigned to each such cluster. Furthermore, an analytical criterion for determining the region of the current system state during targeting is introduced, whereas in the original ECR method the region information was hidden in the neural networks. Simulation results on several chaotic systems show that this modified version of the ECR method reduces the average reaching time and in general also the training time of the neural networks.
机译:在本文中,提出了先前提出的ECR(扩展控制区域)目标定位方法的改进版本,该方法首先对系统数据进行预处理并细分为群集,然后为每个此类群集分配一个人工神经网络。此外,介绍了一种用于确定目标期间当前系统状态区域的分析标准,而在原始ECR方法中,区域信息隐藏在神经网络中。在几个混沌系统上的仿真结果表明,这种改进的ECR方法版本减少了平均到达时间,并且通常还减少了神经网络的训练时间。

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