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

Long Zhao; Zhe Chen

doi:10.1117/12.522208

2 September 2003 Hopfield-neural-network-based filter design for INS/DS integrated navigation system

Long Zhao, Zhe Chen

Proceedings Volume 5253, Fifth International Symposium on Instrumentation and Control Technology; (2003) https://doi.org/10.1117/12.522208
Event: Fifth International Symposium on Instrumentation and Control Technology, 2003, Beijing, China

Abstract

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.

Citation Download Citation

Long Zhao and Zhe Chen "Hopfield-neural-network-based filter design for INS/DS integrated navigation system", Proc. SPIE 5253, Fifth International Symposium on Instrumentation and Control Technology, (2 September 2003); https://doi.org/10.1117/12.522208

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available