自适应格形联合估计算法的收敛性能

The Convergence Property of the Adaptive Lattice Joint Estimation Algorithm

本文应用随机算子方法,分析了自适应格形联合估计算法的均方收敛性能,讨论了有关超量失调的问题,建立了自适应情况下格形算法的超量失调级联模型,推导了估算公式.计算机模拟结果和分析基本符合.

The stochastic operator method is used to analyze the mean square convergence property of the normalized adaptive gradient lattice joint estimation algorithm. The condition for convergence and the learning curve of the algorithm are discussed. In particular, a cascade model for the mis-adjustment noise of algorithm is studied and the corresponding formulae are derived. It is shown that the results of computer simulation are in agreement with the conclusions drawn from a theoretical analysis.