首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Sampled-Data Synchronization Analysis of Markovian Neural Networks With Generally Incomplete Transition Rates
【24h】

Sampled-Data Synchronization Analysis of Markovian Neural Networks With Generally Incomplete Transition Rates

机译:过渡率一般不完整的马尔可夫神经网络的采样数据同步分析

获取原文
获取原文并翻译 | 示例

摘要

This paper investigates the problem of sampled-data synchronization for Markovian neural networks with generally incomplete transition rates. Different from traditional Markovian neural networks, each transition rate can be completely unknown or only its estimate value is known in this paper. Compared with most of existing Markovian neural networks, our model is more practical because the transition rates in Markovian processes are difficult to precisely acquire due to the limitations of equipment and the influence of uncertain factors. In addition, the time-dependent Lyapunov–Krasovskii functional is proposed to synchronize drive system and response system. By applying an extended Jensen’s integral inequality and Wirtinger’s inequality, new delay-dependent synchronization criteria are obtained, which fully utilize the upper bound of variable sampling interval and the sawtooth structure information of varying input delay. Moreover, the desired sampled-data controllers are obtained. Finally, two examples are provided to illustrate the effectiveness of the proposed method.
机译:本文研究了过渡速率通常不完全的马尔可夫神经网络的采样数据同步问题。与传统的马尔可夫神经网络不同,本文中的每个跃迁速率可能是完全未知的,或者只有其估计值是已知的。与大多数现有的马尔可夫神经网络相比,我们的模型更加实用,因为由于设备的限制和不确定因素的影响,马尔可夫过程的跃迁率很难精确获得。另外,提出了时间相关的Lyapunov–Krasovskii功能来同步驱动系统和响应系统。通过应用扩展的Jensen积分不等式和Wirtinger不等式,获得了新的依赖于延迟的同步标准,该标准充分利用了可变采样间隔的上限以及变化的输入延迟的锯齿结构信息。而且,获得了期望的采样数据控制器。最后,提供了两个例子来说明所提方法的有效性。

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