Model inversion tracking control for UltraLITE using neural networks

Jesse Leitner; Keith K. Denoyer

doi:10.1117/12.332478

8 December 1998 Model inversion tracking control for UltraLITE using neural networks

Jesse Leitner, Keith K. Denoyer

Proceedings Volume 3430, Novel Optical Systems and Large-Aperture Imaging; (1998) https://doi.org/10.1117/12.332478
Event: SPIE's International Symposium on Optical Science, Engineering, and Instrumentation, 1998, San Diego, CA, United States

Abstract

This paper presents the analytical methodology and initial numerical simulation results for autonomous neural control of the Ultra-Lightweight Imaging Technology Experiment (UltraLITE) Phase I test article. The UltraLITE Phase I test article is a precision deployable structure currently under development at the United States Air Force Research Laboratory (AFRL). Its purpose is to examine control and hardware integration issues related to large deployable sparse optical array spacecraft systems. In this paper, a multi-stage control architecture is examined which incorporates artificial neural networks for model inversion tracking control. The emphasis in the control design approach is to exploit the known nonlinear dynamics of the system in the synthesis of a model inversion tracking controller and to augment the nonlinear controller with an adaptive neuro-controller to accommodate for changing dynamics, failures, and model uncertainties.

Citation Download Citation

Jesse Leitner and Keith K. Denoyer "Model inversion tracking control for UltraLITE using neural networks", Proc. SPIE 3430, Novel Optical Systems and Large-Aperture Imaging, (8 December 1998); https://doi.org/10.1117/12.332478

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