Research on PRS/IRS Time Registration Based on Fully connected Neural Network

Aiming at the problem that the sampling frequency of two sensors is not consistent in the data fusion of PRS/IRS composite seeker, the time is not synchronized, a time registration method based on fully connected neural network is proposed, the principle of fully connected neural network fitting expounded, the factors of affecting the fitting time and the fitting precision analyzed, the optimum time registration scheme presented, which meets the requirements of real-time and fitting precision in a particular situation. The simulation analysis performed by using Pycharm, and the simulation results demonstrate that the proposed algorithm is of availability.