基于参数估计和Kalman滤波的单通道盲源分离算法

Single-channel blind source separation algorithm based on parameter estimation and Kalman filter

针对存在频谱混叠通信信号的单通道盲源分离(single channel blind source separation,SCBSS)问题,提出一种基于参数估计和Kalman滤波的SCBSS算法。首先,针对根多重信号分类(root multiple signal classification,Root-MUSIC)算法在相近载频估计方面的局限性,提出一种自适应的Root-MUSIC算法,对接收到的盲混合信号的源信号数目和载频进行估计;其次,将Kalman滤波的思想引入到SCBSS算法中,根据估计得到的源信号参数构造信号模型,将其作为Kalman滤波系统的观测向量,执行“时间更新”和“测量更新”两个过程,得到源信号的最佳估计,实现单通道盲源分离。仿真结果表明,所提算法能够有效地从存在频谱混叠的单路接收信号中准确地分离出多路源信号,比传统的算法分离精度高,运算速度快。

Aiming at the problem of single channel blind source separation(SCBSS)for communication signals with spectrum aliasing,a SCBSS algorithm based on parameter estimation and Kalman filtering is proposed.Firstly,in view of the limitation of root multiple signal classification(Root-MUSIC)algorithm in the estimation of similar carrier frequencies,an adaptive Root-MUSIC algorithm is proposed to estimate the number of source signals and carrier frequencies of the received blind mixed signals.Secondly,the idea of Kalman filtering is introduced into the SCBSS algorithm,and the signal model is constructed according to the estimated source signal parameters,which is used as the observation vector of the Kalman filtering system,and the two processes of“time update”and“measurement update”are performed to obtain the best estimation of the source signals and realize the single channel blind source separation.Simulation results show that the proposed algorithm can effectively and accurately separate multi-channel source signals from single channel received signal with spectrum aliasing,and has higher separation accuracy and faster operation speed than traditional algorithms.