6 November 2006 Research on the application of ensemble neural network in integrated navigation system
Author Affiliations +
The conventional Kalman filter assumes that the system model and the observation model is linearity. Also the noise in system and observation model is white noise. However the practical environment is very complex. When we use Kalman filter to estimate, we can not got the transcendent information. The paper considers the characteristic of aircraft, research the structure and scheme of INS/CNS/GPS integrated navigation system. The error model of integrated navigation system has been set up. The status of navigation system has been estimated with Kalman filter, and the simulation calculation has been progressed. The paper presents a method, which use neural network ensembles to deal with the Kalman filter. This method improves the generalization and stabilization ability. The simulation shows that the arithmetic has high precision.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fan Xu, Fan Xu, Jiancheng Fang, Jiancheng Fang, "Research on the application of ensemble neural network in integrated navigation system", Proc. SPIE 6357, Sixth International Symposium on Instrumentation and Control Technology: Signal Analysis, Measurement Theory, Photo-Electronic Technology, and Artificial Intelligence, 63575E (6 November 2006); doi: 10.1117/12.717599; https://doi.org/10.1117/12.717599


Back to Top