Recursive second-order Volterra filter based on Dawson function for chaotic memristor system identification
Recursive second-order Volterra filter based on Dawson function for chaotic memristor system identification
复制标题
基于Dawson函数的递归二阶Volterra滤波器混沌忆阻器系统辨识
DOI：
10.1007/s11071-019-05459-8
复制
发表时间：
2020
影响因子：
5.6
通讯作者：
Yu Yi
中科院分区：
文献类型：
--
作者：
Lu Lu;Yang Xiaomin;Wang Wenyuan;Yu Yi
在本文中，我们提出了一种改进的指数代价函数来提高自适应算法的稳定性，其中递归算法是基于Dawson函数的。将二阶Volterra(SOV)滤波器引入到所提出的递推算法中，得到了SOV-ExRLS算法，以实现在稳定和高斯环境下的性能改善。此外，还分析了SOV-ExRLS算法的均方和均方行为。特别地，将cExRLS-IDLMS方法与函数链人工神经网络滤波器凸结合起来，灵活地对混沌记忆阻器系统进行建模。仿真研究验证了分析结果，并表明所提出的算法比现有的非线性算法具有更好的辨识性能。
In this paper, we propose a modified version of exponential cost function to improve the stability of adaptive algorithm, where the recursive algorithm is based on the Dawson function. The second-order Volterra (SOV) filter is incorporated into the proposed recursive algorithm, resulting the SOV-ExRLS algorithm, to achieve the improved performance in both-stable and Gaussian environments. Moreover, the mean and mean-square behavior of the SOV-ExRLS algorithm is analyzed. In particular, the proposed cExRLS-IDLMS method is convexly combined with the functional link artificial neural network filter to flexibly model the chaotic memristor system. Simulation studies verify the analytical findings and reveal enhanced identification performance of the proposed algorithms over the existing nonlinear algorithms.