Hopfield-neural-network-based filter design for INS/DS integrated navigation system

While INS (Inertia navigation system)/DS (Double-star) integrated navigation system is implemented using Kalman filtering technology the filtering performance is unsatisfactory, because the model error of DS system is unknown and the stability is not good, either. The novel method for state estimation, based on Hopfield neural network, is presented, and is defined as Hopfield-estimation. The mathematical model for INS/DS position integrated navigation system is set up. The state optimal estimation is obtained by minimizing the energy function of the Hopfield neural network in this scheme, and the statistic information for the model error and the observation noise is not required. Simulating experimentation is implemented using practical measurement data of the INS and DS. Simulation results show that the Hopfield state estimation method performs much better than the Kalman filtering in the same simulation conditions.