Neural network low authority threshold control of linear and nonlinear mechanical systems: theory and experiment

Carole A. Corley; David C. Zimmerman

doi:10.1117/12.148407

22 July 1993 Neural network low authority threshold control of linear and nonlinear mechanical systems: theory and experiment

Carole A. Corley, David C. Zimmerman

Author Affiliations +

Proceedings Volume 1919, Smart Structures and Materials 1993: Mathematics in Smart Structures; (1993) https://doi.org/10.1117/12.148407
Event: 1993 North American Conference on Smart Structures and Materials, 1993, Albuquerque, NM, United States

Abstract

Low Authority Threshold Control (LATC) is an active control strategy resulting in a piecewise continuous, with respect to time, constant gain control law which may be used for the vibration control of flexible structures. The LATC optimal control law gains are dependent on the state vector at the time the gains are applied and are defined by a two-point boundary value problem and a set of integral equality constraints. Because an iterative solution technique is required to determine the optimal gains, the real-time implementation of this control law presented certain difficulties. In this work, a neural network system is trained to determine the optimal gains in real-time for each of two experiments: a cantilevered beam and a nonlinear Duffing oscillator. The optimal gains generated by the neural network system are utilized in an LATC rate feedback control law for the vibration control of these systems.

Citation Download Citation

Carole A. Corley and David C. Zimmerman "Neural network low authority threshold control of linear and nonlinear mechanical systems: theory and experiment", Proc. SPIE 1919, Smart Structures and Materials 1993: Mathematics in Smart Structures, (22 July 1993); https://doi.org/10.1117/12.148407

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