一种面向时变射频干扰的时频特征预测网络  

A time-frequency feature prediction network for time-varying radio frequency interference

作　　者：万鹏程 冯为可 童宁宁[2] 韦伟[3] WAN Pengcheng;FENG Weike;TONG Ningning;WEI Wei(Aviation University of Air Force,Changchun 130000,China;College of Air and Missile Defense,Air Force Engineering University,Xi′an 710051,China;Air Force Logistics Academy,Xuzhou 221000,China)

机构地区：[1]空军航空大学,吉林长春130000 [2]空军工程大学防空反导学院,陕西西安710051 [3]空军勤务学院,江苏徐州221000

出　　处：《西北工业大学学报》2023年第3期587-594,共8页Journal of Northwestern Polytechnical University

基　　金：国家自然科学基金面上项目(62001507)资助。

摘　　要：时变射频干扰非线性强,难以用线性方法进行有效预测,进而使抗干扰决策缺少信息支撑。针对该问题提出了基于时频相关特征的频谱预测递归神经网络,通过滑窗模型表征时频序列的二维相关性,将频谱预测问题转化为类似于空时序列预测的问题,增加跨时间帧的梯度桥结构以减轻梯度在长时间、多层级网络传播时的衰减现象,用匹配性更高的损失函数提高训练效率和网络性能。仿真和实验结果验证了该网络预测结果的有效性。The time-varying radio frequency interference has strong nonlinear dynamic characteristics,which is difficult to be predicted by linear method effectively,making the anti-interference decision without sufficient information support.To solve this problem,a recurrent neural network for spectrum prediction based on time-frequency correlation features is proposed.A sliding window is used to characterize the two-dimensional correlation of time-frequency series,and the spectrum prediction problem is transformed into a problem similar to spatiotemporal sequence prediction.A gradient bridge structure across time frames is added to reduce the attenuation of the gradient in the long time and multi-level network propagation.The training efficiency and network performance are improved by the loss function with better matching.Simulation and experimental results verify the validity of the network prediction results.

关 键 词：频谱预测 射频干扰 深度神经网络 循环神经网络 

分 类 号：TN95[电子电信—信号与信息处理]