Multivariable Neural Network based Controllers for Smart Structures

Abstract

Identification and robust control of smart structures are specified using artificial neural networks. To demonstrate the use of artificial neural networks in the control of smart structural systems, two smart structure test articles have been fabricated. Active materials like piezoelectric, polyvinylidene, and shape memory alloys are used as actuators and sensors. The Eigensystem Realization Algorithm (ERA), a structural identification method, has been used to determine a minimal order discrete time state space model of the test articles; the ERA requires the Markov parameters of physical system. The accelerated adaptive learning rate algorithm and the adaptive activation function are used to improve learning characteristics and reduce learning time. Finally, these identified models are then used to design robust controllers of smart structures.

Department(s)

Electrical and Computer Engineering

International Standard Serial Number (ISSN)

1045-389X

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 SAGE Publications, All rights reserved.

Publication Date

01 Jan 1995

Link to Full Text

Share

 
COinS