In this article, a noise-suppression variable-parameter zeroing neural network (NSVPZNN) is proposed to handle the dynamic Sylvester equation. Differing from the previous zeroing neural networks (ZNNs), a new nonlinear activation function and an especially constructed time-variant parameter are developed to construct the novel NSVPZNN model. Therefore, the NSVPZNN model can achieve faster predefined-time convergence without noise disturbance and have stronger robust performance under multiple noises. Furthermore, the convergence upper bound of the NSVPZNN model is theoretically calculated, and a detailed proof of guaranteeing noise-tolerance performance is given. Numerical simulations verify that the NSVPZNN has better performance than the ZNN, the finite-time convergence ZNN model, the predefined-time convergence ZNN model, and the other variable-parameter ZNN when handling the dynamic Sylvester equation. Finally, the design method of the NSVPZNN is applied to the wheeled manipulator for tracking the butterfly trajectory, which further illustrates the model's reliability.

中文翻译：

---

动态 Sylvester 方程带新变量的噪声抑制 ZNN 模型

在本文中，提出了一种噪声抑制可变参数归零神经网络 (NSVPZNN) 来处理动态 Sylvester 方程。与之前的归零神经网络 (ZNN) 不同，开发了一种新的非线性激活函数和专门构造的时变参数来构建新的 NSVPZNN 模型。因此，NSVPZNN 模型可以在没有噪声干扰的情况下实现更快的预定义时间收敛，并且在多重噪声下具有更强的鲁棒性能。此外，从理论上计算了NSVP​​ZNN模型的收敛上限，并给出了保证噪声容限性能的详细证明。数值模拟验证了NSVP​​ZNN比ZNN、有限时间收敛ZNN模型、预定义时间收敛ZNN模型具有更好的性能，以及处理动态 Sylvester 方程时的另一个可变参数 ZNN。最后，将NSVPZNN的设计方法应用到轮式机械手跟踪蝴蝶轨迹，进一步说明了模型的可靠性。