Robust spline adaptive filtering based on accelerated gradient learning: Design and performance analysis
Robust spline adaptive filtering based on accelerated gradient learning: Design and performance analysis
复制标题
基于加速梯度学习的鲁棒样条自适应滤波：设计与性能分析
DOI：
10.1016/j.sigpro.2021.107965
复制
发表时间：
2021-01-25
影响因子：
4.4
通讯作者：
de Lamare, Rodrigo C.
中科院分区：
文献类型：
--
作者：
Yu, Tao;Li, Wenqi;de Lamare, Rodrigo C.
针对脉冲噪声环境下的非线性系统辨识问题，提出了一种新的样条型自适应滤波算法。该算法结合了对数双曲余弦(LHC)代价函数和改进的Nester ov加速梯度(MNAG)学习方法，称为SAF-LHC-MNAG算法。LHC代价函数可以降低SAF对大的异常值的敏感性，提高对脉冲噪声的鲁棒性。另外，MNAG方法可以在稳态误差较小的前提下进一步加快收敛速度。对该算法进行了性能分析，并进行了仿真。数值结果表明，SAF-LHC-MNAG算法比现有的一些SAF算法具有更好的收敛性能。实验结果证实了SAF-LHC-MNAG对非线性迟滞系统准确辨识的有效性。(C)2021年爱思唯尔B.V.保留所有权利。
This paper proposes a novel spline adaptive filtering (SAF) algorithm for nonlinear system identification under impulsive noise environments. This algorithm combines the logarithmic hyperbolic cosine (LHC) cost function and the modified Nesterov accelerated gradient (MNAG) learning method, which is called the SAF-LHC-MNAG algorithm. The LHC cost function can reduce the sensitivity of SAF to large outliers and improve the robustness to impulsive noises. Additionally, the MNAG method can further accelerate the convergence under the premise of low steady-state error. Performance analysis of this algorithm is carried out and supported by simulations. Numerical results show that the SAF-LHC-MNAG algorithm has better convergence performance than some existing SAF algorithms. Besides, experimental results confirm the effectiveness of SAF-LHC-MNAG for the accurate identification of nonlinear hysteresis system. (C) 2021 Elsevier B.V. All rights reserved.