论文部分内容阅读
本文概述了最小平方网格(LSL)算法的主要优点,给出了将它用于非平稳信号反褶积的试验结果,实验说明对时变信号反褶积它优于传统的Levinson及Burg算法。文章指出LSL算法比其他自适应算法跟踪能力强的关键是其修正公式中多了一个参数——似然变量,本文详细分析了似然变量的物理意义及作用,提出了利用似然变量改善LSL算法反褶积中存在的问题的具体方法。实验说明所提方法是有效的。
This paper summarizes the main advantages of Least Squares Least Squares (LSL) algorithm and gives the results of its experiments on non-stationary signal deconvolution. Experiments show that it is superior to the traditional Levinson and Burg algorithms for deconvolution of time-varying signals . The article points out that the key of LSL algorithm to track the ability of other adaptive algorithms is that there is more parameter-likelihood variable in the correction formula. In this paper, the physical meaning and function of the likelihood variable are analyzed in detail. The specific method of the problems in the algorithm deconvolution. The experimental results show that the proposed method is effective.