Recurrent Neural Networks for Robust Vibration Control of Composite Shells

Abstract

A neural network-based control system is developed for self-adapting vibration control of laminated double curved shells with piezoelectric sensors and actuators. A hybrid control system developed in this paper is comprised of a feed-forward neural network identifier and a dynamic recurrent neural network controller. Sensing and actuation is achieved using piezoelectric sensors and actuators. Finite element equations of motion are developed based on shear deformation theory and implemented for the double curved laminated shell. The dynamic effects of the mass and the stiffness of the piezoelectric patches are considered in the model. The performance and robustness of the hybrid control system are examined using different initial conditions, loading and system parameter variations. The hybrid control system is shown to perform effectively in all of these cases.

Department(s)

Mechanical and Aerospace Engineering

Second Department

Electrical and Computer Engineering

Keywords and Phrases

Artificial Intelligence; Neural Networks

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2000 American Society of Mechanical Engineers (ASME), All rights reserved.

Publication Date

01 Jan 2000

This document is currently not available here.

Share

 
COinS