为了解决CMA盲均衡算法收敛速度缓慢、稳态误差大的问题,考虑到初始化权值对CMA算法的重要影响,利用了遗传算法对CMA算法进行有效改进,引入了小样本重用的思想,给出了一种新的适用于水声信道的常模类盲均衡算法,计算机仿真研究证明,该算法不仅大大加快了收敛速度,而且有效的降低了稳态误差。 In order to solve the problem of slow convergence speed and large steady-state error of CMA blind equalization algorithm, taking into account the important influence of initialization weight on CMA algorithm, genetic algorithm is used to improve CMA algorithm effectively, and the idea of ​​small sample reuse is introduced. A new type of norm-blind blind equalization algorithm for underwater acoustic channel is proposed. Computer simulation results show that this algorithm not only greatly speeds up the convergence but also reduces the steady-state error effectively.