基于源数估计的机械源信号盲分离方法研究

BLIND SEPARATION OF MECHANICAL SOURCE SIGNALS BASED ON THE ESTIMATION OF SOURCE NUMBERS

传统的机械源分离方法往往事先假设源信号的个数已知,否则无法进行机械源信号分离。然而,在实际中源信号的个数往往是是未知的。针对此不足,结合变分贝叶斯独立变量分析和自相关测定,提出一种机械源数的最佳估计方法,它是通过比较不同模型的信度来确定出信源的个数。仿真和实验结果表明该方法是有效的,并具有很好的鲁棒性。

In the traditional blind separation method of mechanical sources,the number of mechanical sources is always assumed to be known.However,the mechanical sources do not suffice to this condition.In order to overcome this deficiency,combining of Bayesian inferring and automatic relevance determination （ARD）,a new estimation method of mechanical sources based on Bayesian independent component analysis is proposed.In the proposed method,the optimal number of mechanical sources is determined by the evidence comparison of different models.The simulation and experiment results show that the proposed method is very effective and has good robustness.