Using a neural network learning algorithm suitable for the best estimation of nonlinear system

• Published in: Proceedings of the 4th World Congress on Intelligent Control and Automation (Cat. No.02EX527) Vol. 3; pp. 2030 - 2034 vol.3
• Main Authors: Wang Xinlong, Jin Zhenshan, Shen Gongxun, Tang Delin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2002
• Subjects: Automation; Intelligent control; Neural networks; Nonlinear systems
• ISBN: 0780372689; 9780780372689
• DOI: 10.1109/WCICA.2002.1021441

A learning algorithm for the multiplayer neural network based on the Kalman filter theory is studied. The theoretical proof and procedure of the algorithm are described in details, and the algorithm is used for the initial alignment of inertial systems. Simulation results prove that the availability of the neural network algorithm for initial alignment of nonlinear inertial systems, not only can obtain the alignment accuracy similar to that of the Kalman filter, but also reduce the alignment time considerably. Consequently, a available algorithm of the neural network for the initial alignment of nonlinear inertial systems is established.