一种变正则化矩阵的改进多带结构子带自适应滤波算法
发布时间：2018-09-13 11:44
【摘要】：定正则化因子的改进多带结构子带自适应滤波(IMSAF)算法在取得收敛速度快和稳态失调误差小之间存在冲突.根据系统噪声抵消原理,设定子带后验误差功率等于子带噪声功率,本文提出了变正则化矩阵的IMSAF算法来解决这一问题.仿真结果证明,所提算法可以同时达到收敛速度快、稳态失调误差小以及追踪速度快等优势.
[Abstract]:The modified multiband subband adaptive filtering (IMSAF) algorithm with definite regularization factor has a conflict between fast convergence and small steady-state misalignment error. According to the principle of system noise cancellation, the posteriori error power of the subband is equal to the noise power of the subband. In this paper, a variable regularization matrix IMSAF algorithm is proposed to solve this problem. The simulation results show that the proposed algorithm can achieve the advantages of high convergence rate, small steady-state misalignment error and fast tracking speed.
【作者单位】： 中国科学院噪声与振动重点实验室(声学研究所);中国科学院大学;
【基金】：国家自然科学基金(No.61501449,No.11404367) 中国科学院先导专项项目(No.XDA06040501)
【分类号】：TN713;TN911.7
，
本文编号：2241074
[Abstract]:The modified multiband subband adaptive filtering (IMSAF) algorithm with definite regularization factor has a conflict between fast convergence and small steady-state misalignment error. According to the principle of system noise cancellation, the posteriori error power of the subband is equal to the noise power of the subband. In this paper, a variable regularization matrix IMSAF algorithm is proposed to solve this problem. The simulation results show that the proposed algorithm can achieve the advantages of high convergence rate, small steady-state misalignment error and fast tracking speed.
【作者单位】： 中国科学院噪声与振动重点实验室(声学研究所);中国科学院大学;
【基金】：国家自然科学基金(No.61501449,No.11404367) 中国科学院先导专项项目(No.XDA06040501)
【分类号】：TN713;TN911.7
，
本文编号：2241074
本文链接：https://www.wllwen.com/kejilunwen/xinxigongchenglunwen/2241074.html
