Prediction of SINS/GPS Navigation Information by ELM Algorithm during GPS outages

Abstract

SINS/GPS integrated navigation has received great attention recently due to its impressive navigation accuracy on missile-borne platforms. However, it remains an ongoing challenge to address the problem of GPS signal loss. Furthermore, the limited space and power consumption of a projectile have made it challenging to carry out time-consuming iterative calculations. In this paper, ELM is proposed for the first time to predict the navigation information on the missile-borne platform for its simpler neural network structure and no iterative calculation. Comparing it with the algorithms of BP and GABP, the simulation results reveal that the ELM algorithm is more time-saving with higher prediction accuracy than the others. More importantly, the number of parameters needed to be set is much less than those of the other two algorithms, which is beneficial for its practical application.