利用BP网络校正跟踪接收机的相位漂移

针对跟踪接收机不同通道之间相位差的漂移问题,提出利用BP神经网络作为校正环节来消除此相位漂移。通过原理分析用数学方法描述跟踪接收机存在的相位漂移问题,介绍BP神经网络的网络模型和一种动态全参数自适应学习算法,进而提出基于BP神经网络的相位漂移校正算法。仿真结果表明,该方法的相位校正效果较好,不仅保证了系统的角跟踪精度,而且实现了高度的自动化。

Adjustment of the Tracking Receiver's Phase Shift by BP Neural Network

In this paper,the BP Neural Network is used as a calibrating process to eliminate the phase shift which exists between the different channels of the tracking receiver.The principle of the phase shift is firstly described by mathematic analysis.The model of BP Neural Network and an adaptive study algorithm of dynamic-all-parameter are introduced in detail.Then the algorithm of the phase shift calibration is proposed.The simulation results demonstrate that this method of the phase calibration is good.Not only the accuracy of the angle tracking system is guaranteed,but also the high automation is realized.