基于经验模态分解的单通道盲源分离算法

为了提高单通道盲源分离性能，首先由单路信号利用经验模态分解得到一系列本征模函数分量组合成多路信号；其次针对存在模态混叠的本征模函数分量，提出利用信号周期性构造其多路信号、并利用独立分量分析消除模态混叠的有效方法；然后利用互相关性消除上述所得到的多路信号中的虚假分量，并将剩余的分量信号与观测信号构成新的多路信号；最后利用Fast-ICA(fast-independent component analysis)算法分离得到源信号。仿真实验表明该算法能够有效分离源信号，分离性能优于目前已有的基于经验模态分解的单通道盲源分离算法。

Single-channel Blind Source Separation Algorithm based on Empirical Mode Decomposition

In order to improve the performance of single channel blind source separation, firstly the empirical mode decomposition is applied to single-channel observation signal to obtain a series of intrinsic mode function and residue, which reconstruct multi-channel signals. Secondly, according to the existing mixed modes intrinsic mode function, the multi-channel signals are constructed by using the signal periodicity, and the modal mixing is eliminated by using independent component analysis. And the false components of the above obtained multi-channel signals are cancelled out on the basis of correlation, then the new multi-channel signals are got by the remaining signals and observed signal. Finally, the source signals are separated by using the Fast-ICA algorithm. The simulation results show that the algorithm can effectively separate the source signals, the separation performance is better than the existing single channel blind source separation algorithms based on empirical mode decomposition.