基于对角递归神经网络盲均衡算法的研究

Research of Blind Equalization Algorithm Based on Diagonal Recurrent Neural Networks

提出了一种基于对角递归神经网络的盲均衡算法。利用对角递归神经网络结构简单、计算量少的优点,结合传统的恒模盲均衡算法定义了代价函数,用最速梯度下降法推导出了其算法迭代公式。计算机仿真表明,该算法收敛速度较快,误码率较小。

A new blind equalization algorithm based on diagonal recurrent neural networks(DRNN) is proposed.The algorithm has the advantages of simple structure and less computational requirement.Combined with the conventional constant modulus algorithm(CMA),a new cost function is proposed,then the steepest descent method is used in DRNN training.Simulation results show that this algorithm could converge quickly and had less bit error ratio.