混沌粒子群算法的盲源信号分离仿真研究

RESEARCH ON SIMULATING BLIND SOURCE SEPARATION BASED CHAOTIC PARTICLE SWARM OPTIMISATION

针对传统盲源分离算法存在收敛速度慢、易陷入局部最优等缺陷,提出一种混沌粒子群算法的盲源分离方法。采用信号的峰度值作为盲源信号分离目标函数,然后采用混沌粒子算法对目标函数进行求解,并对粒子群体进行混沌扰动,保持粒子群的多样性,最后采用最优解对信号进行盲源分离。结果表明,混沌粒子群算法有效提高了盲源信号分离速度,信号分离精度更高。

Because traditional blind source separation algorithms have the defects of slow convergence,easily to fall into local optimum and so on,in this paper we propose a blind source separation algorithm based on chaos particle swarm optimisation.The kurtosis value of the signal is used as the objective function of the blind source signal separation,and then the chaos particle algorithm is used to solve the objective function,and the particle swarm is executed the chaos disturbance to keep the diversity of the particle swarm,finally the optimal solution is used to separate the blind source signal.Results show that the proposed algorithm improves the separation speed of blind source signal with higher separation accuracy.