Scholarlink

<p>The zeroing neural network (ZNN) has demonstrated exceptional effectiveness in solving time-varying problems. However, the performance of existing ZNNs is often constrained by their reliance on elementary activation functions, which limits their potential for further advancement. In this paper, we propose a novel activation function based on an integral upper-bound function. Through rigorous theoretical analysis, we establish its stability, predefined-time convergence, and robustness. Numerical experiments and real-world simulation further demonstrate the effectiveness of the proposed model, both in solving the time-varying Sylvester equation and in executing trajectory tracking for a six-degree-of-freedom robotic arm.</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

A novel zeroing neural network with integral upper-bound function for solving time-varying Sylvester equation

  • 期刊论文

  • 发表日期：

    2025年7月22日

查看全文
  • Jiangchuan Zhao,
  • Yanjun Zhang

摘要

The zeroing neural network (ZNN) has demonstrated exceptional effectiveness in solving time-varying problems. However, the performance of existing ZNNs is often constrained by their reliance on elementary activation functions, which limits their potential for further advancement. In this paper, we propose a novel activation function based on an integral upper-bound function. Through rigorous theoretical analysis, we establish its stability, predefined-time convergence, and robustness. Numerical experiments and real-world simulation further demonstrate the effectiveness of the proposed model, both in solving the time-varying Sylvester equation and in executing trajectory tracking for a six-degree-of-freedom robotic arm.