Scholarlink

<p>This study considers the issue of nonfragile state estimation (SE) for memristor-based bidirectional associative memory (MBAM) neural networks with probabilistic time-varying delays. The primary objective is to develop an effective estimator for accurately assessing neuron states, which are crucial in various engineering applications. Furthermore, we consider a scenario in which the measurement outputs of the neural networks may be influenced by abnormal disturbances, which could have a negative impact on the performance of the estimator. In this case, a factitious saturation constraint is introduced to mitigate the adverse effects on the designed outlier-resistant estimator, thereby improving the reliability of the estimator. Through constructing sensible Lyapunov–Krasovskii functional (LKF), a delay-dependent criterion is derived to guarantee the exponential stability of the augmented system. Finally, the effectiveness of the desired estimation scheme is demonstrated via two simulation examples.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Outlier-resistant state estimation for memristor-based BAM neural networks with probabilistic time-varying delays

  • 期刊论文

  • 发表日期：

    2025年1月10日

查看全文
  • Xiaoguang Shao,
  • Jie Zhang,
  • Ming Lyu,
  • Yanjuan Lu

摘要

This study considers the issue of nonfragile state estimation (SE) for memristor-based bidirectional associative memory (MBAM) neural networks with probabilistic time-varying delays. The primary objective is to develop an effective estimator for accurately assessing neuron states, which are crucial in various engineering applications. Furthermore, we consider a scenario in which the measurement outputs of the neural networks may be influenced by abnormal disturbances, which could have a negative impact on the performance of the estimator. In this case, a factitious saturation constraint is introduced to mitigate the adverse effects on the designed outlier-resistant estimator, thereby improving the reliability of the estimator. Through constructing sensible Lyapunov–Krasovskii functional (LKF), a delay-dependent criterion is derived to guarantee the exponential stability of the augmented system. Finally, the effectiveness of the desired estimation scheme is demonstrated via two simulation examples.