基于EKF神经网络的扩频系统抗窄带干扰技术

Narrowband interference suppression in spread spectrum system based on EKF neural network

针对消除扩频系统中的窄带干扰问题,文章提出了一种基于扩展卡尔曼滤波(EKF)的递归神经网络预测器(RNNP)。扩展卡尔曼滤波被用于反馈修改递归神经网络的权值系数,从而准确地估计干扰信号,具有收敛速度快、预测精度高和适用于非线性处理的优点。仿真结果表明:基于EKF学习算法的RNNP相对于自适应线性最小均方差(LMS)干扰预测器、自适应近似条件均值(ACM)干扰预测器和基于实时递推学习(RTRL)算法的RNNP在预测误差的均方误差、收敛速度、信噪比改善量方面上有不同程度的改进。

A recurrent neural network predictor based on the extended Kalman filter to eliminate the narrowband interference was proposed in the spread spectrum in this paper. The extended Kalman filter was used to modify the weights of the RNNP and precisely estimate the interference, with the virtue of rapid convergence rate, high prediction precision and suiting for nonlinear disposition. Simulation results showed that the RNNP based on EKF learning algorithm had improvement to different extent on interference elimination capability compared to the adaptive linear least mean square （LMS） interference predictor, the adaptive approximate conditional mean （ACM） interference predictor and the RNNP based on real time recurrent learning （RTRL） arithmetic.