基于高阶累积量的Hammerstein模型记忆效应辨识

旨在研究存在加性高斯噪声时，Hammcrstcin模型的记忆效应辫识问题。在输入信号统计量和Hammcrstein模型的无记忆非线性效应均未知的情况下，利用模型输出信号的高阶累积量建立两种线性方程组，并从理论上证明了两种线性方程组均具有唯一解;提出将两个线性方程组结合使用的系数提取方法，其过程不受Hammerstein模型的无记忆非线性模块影响。最后的仿真结果表明，在高斯(有色或无色)噪声存在的情况下，此类辫识方法比直接提取参数法具有更好的数值鲁棒性。

Higher-Order-Cumulant Based Memory Effect Identification of Hammerstein Model

This paper focused on memory effect identification of Hammerstein model in Uaussian noise. When input statistics and nonlincarity of Hammerstcin arc unknown, by using higher order cumulant of output signal, two sets linear cquations were proposed to extract coefficients of linear block with memory. Theoretical derivation shows that those two sets of linear equations have unique solutions. I}hey could be used alternately to identify the memory effect of Hammerstein model, and the identification process is not affected by memoryless nonlinear block. Finally, simulations verify that the new developments have higher performance than direct extraction method.