自适应陷波器级联神经网络抗干扰算法

发布时间：2018-03-27 14:29

  本文选题：全球定位系统　切入点：神经网络　出处：《西安电子科技大学学报》2017年06期

【摘要】：针对卫星导航信号容易受到窄带干扰影响而降低导航性能的问题,提出了一种基于神经网络的全球定位系统接收机抗干扰方法.该方法通过自适应陷波器与反向传播神经网络级联,利用二阶格型无限脉冲响应自适应陷波器滤除带外干扰,再结合反向传播神经网络预测器来估计并消除干扰.从捕获卫星数、信噪比提升值和迭代次数对算法性能进行仿真比较,结果表明,文中方法可有效抑制窄带干扰,并且有更强的抗窄带能力、更快的收敛速度.
[Abstract]:In view of the problem that satellite navigation signal is vulnerable to narrowband interference and reduces navigation performance, An anti-jamming method for GPS receiver based on neural network is proposed, in which adaptive notch filter and backpropagation neural network are used to filter out out-of-band interference by using second-order latticed infinite impulse response adaptive notch filter. Then the backpropagation neural network predictor is used to estimate and eliminate the interference. The performance of the algorithm is simulated and compared from the number of captured satellites, the increase of SNR and the number of iterations. The results show that the proposed method can effectively suppress narrowband interference. And has stronger ability to resist narrow band, faster convergence speed.
【作者单位】： 西北工业大学电子信息学院;
【基金】：国家自然科学基金资助项目(61571370)
【分类号】：P228.4;TP183
，

本文编号：1671911