基于变步长等变化自适应盲源分离算法

对于基于梯度自适应的盲源分离算法，认真选择步长参数以达到好的分离性能是非常必要的。如果为加快收敛速度而增大步长因子，将会导致大的稳态误差，甚至引起算法发散，因此固定步长因子无法解决收敛速度和稳态误差之间的矛盾。本文为EASI算法提出了一种变步长的解决方案。通过建立步长因子与分离矩阵相互差异之间的非线性关系，加快了收敛速度，减小了失调误差。计算机仿真结果与理论分析相一致，证实了该算法明显优于传统的EASI算法。

Equivariant Adaptive Blind Source Separation Algorithm Based on Variable Step Size

Careful selection of step size parameters is often necessary to obtain good performance from gradient-based adaptive algorithms for blind source separation.In order to speed up the convergence processs,one can increase the step size,but at the same time,the steady state error will be larger and even the algorithm may become unstable.Fixed step size cannot realize fast convergence speed and low residual error simultaneously.In this paper a solution based on variable step size for EASI algorithm is proposed.By building a nonlinear function relationship between step size and the difference among separating matrixes,the method can speed up convergence speed and reduce the misadjustment error in the steady state simultaneously.Computer simulations confirm the theoretical analysis and show the algorithms performance is superior to the usual EASI algorithm.