Solution of transfer alignment problem of SINS on moving bases via neural networks

Purpose: In order to accomplish real-time alignment of Shipborne strapdown inertial navigation system (SINS) on moving bases, a novel solution method of utilizing neural networks for rapid transfer alignment of Shipborne SINS was investigated. Design/methodology/approach: The system error state equations and measurement equations of the Shipborne transfer alignment were established. Based on the nonlinear and time-variant SINS model on moving bases, a neural network learning algorithm based on Kalman filtering was presented, and the methods of constructing and training of neural networks input-output sample pairs suitable for Shipborne SINS were proposed. Findings: Velocity and attitude errors between the master and slave inertial navigation system (INS) are chosen as network's inputs, and the information of sample pairs is affluent, which can advance the stability and generalization of the neural networks. The neural networks algorithms based on Kalman filtering not only have the self-learning ability, but also remain recursive optimal estimation capability of Kalman filtering. Through the introducing of the local level trajectory frame, the trained neural networks can be independent on a ship heading, and only dependent on the relative position errors between master with slave INS and the inertial sensor errors. Originality/value: This article presents an innovative solution method of utilizing neural networks for rapid transfer alignment of Shipborne SINS.