基于动量梯度下降的自适应干扰对消算法  

Adaptive Self-Interference Cancel Algorithm Based on Momentum Gradient Descent

作　　者：杨启伦 张续莹 李含超 杜冶 YANG Qilun;ZHANG Xuying;LI Hanchao;DU Ye(Science and Technology on Electronic Information Control Laboratory,Chengdu 610036,China)

机构地区：[1]电子信息控制重点实验室,成都610036

出　　处：《电子信息对抗技术》2022年第2期30-32,共3页Electronic Information Warfare Technology

摘　　要：在同时同频收发系统中,发射信号会泄露到接收通道导致有用的接收信号被淹没。针对同时同频收发系统干扰对消的需求,在传统随机梯度算法的基础上,研究动量梯度下降算法。该方法将历史梯度信息进行指数衰减和平滑,再结合当前梯度估计来更新权重系数,可以解决噪声引起梯度估计的大小和方向不准确从而导致收敛速度慢的困难。最后通过仿真证明本方法具有比传统随机梯度算法更好的收敛性能。In the co-time co-frequency transmit-receive system,the transmitted signal will leak to the receiving channel,and the valid receiving signal would be submerged.For the requirement of jamming cancelling in the co-time co-frequency transmit-receive system,the momentum gra-dient descent algorithm is proposed based on the traditional stochastic descent algorithm.The historical gradient information could be attenuated exponentially and smoothed,and then the cur-rent gradient estimation is combined together to update the weight coefficient.The problem that convergence velocity is slow for gradient estimation not accurate could be solved.Finally,it is demonstrated that the convergence velocity could be speeded up more than 6 times under the same learning rate.

关 键 词：同时同频收发系统 自适应干扰对消 动量梯度下降 历史梯度信息 收敛速度 

分 类 号：TN971.1[电子电信—信号与信息处理]