...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Physica Scripta: An International Journal for Experimental and Theoretical Physics >New stability and stabilization criteria for fuzzy neural networks with various activation functions
【24h】

New stability and stabilization criteria for fuzzy neural networks with various activation functions

机译：具有各种激活函数的模糊神经网络的新稳定性和稳定准则

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, the stability analysis and control design of Takagi-Sugeno (TS) fuzzy neural networks with various activation functions and continuously distributed time delays are addressed. By implementing the delay-fractioning technique together with the linear matrix inequality (LMI) approach, a new set of sufficient conditions is derived in terms of linear matrix inequalities, which ensure the stability of the considered fuzzy neural networks. Further, based on the above-mentioned techniques, a control law with an appropriate gain control matrix is derived to achieve stabilization of the fuzzy neural networks. In addition, the results are extended to the study of the stability and stabilization results for TS fuzzy uncertain neural networks with parameter uncertainties. The stabilization criteria are obtained in terms LMIs and hence the gain control matrix can be easily determined by the MATLAB LMI control toolbox. Two numerical examples with simulation results are given to illustrate the effectiveness of the obtained result.
机译：本文研究了具有多种激活函数和连续分布的时滞的高木-Sugeno（TS）模糊神经网络的稳定性分析和控制设计。通过将延迟分割技术与线性矩阵不等式（LMI）方法一起实施，就线性矩阵不等式得出了一组新的充分条件，这确保了所考虑的模糊神经网络的稳定性。此外，基于上述技术，推导具有适当增益控制矩阵的控制律以实现模糊神经网络的稳定。此外，该结果还扩展到具有参数不确定性的TS模糊不确定神经网络的稳定性和稳定性结果的研究。可以使用LMI来获得稳定标准，因此可以通过MATLAB LMI控制工具箱轻松确定增益控制矩阵。给出了两个数值示例，并带有仿真结果来说明所获得结果的有效性。

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