Share Email Print
cover

Proceedings Paper

Use of neural networks and sliding modes in vibration damping
Author(s): Sergey V. Drakunov; Umit Ozguner; Layne Lenning
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper discusses a control algorithm for active vibration suppression in flexible structures with distributed actuation. This control algorithm employs an integral transformation of the distributed-parameter system such that the transformed system behaves according to a desired second-order partial differential equation in space and time. Furthermore, a neural network is used to learn and perform this integral transformation which can be very difficult to calculate analytically and which has a kernel that is generally nonlinear. Once the system has been transformed, sliding mode control algorithms may be used to yield a closed-loop system which is insensitive to disturbances or parameter variations. An Euler-Bernoulli beam with piezoelectric actuation will be considered as an illustrative example of this particular strategy.

Paper Details

Date Published: 22 July 1993
PDF: 8 pages
Proc. SPIE 1919, Smart Structures and Materials 1993: Mathematics in Smart Structures, (22 July 1993); doi: 10.1117/12.148409
Show Author Affiliations
Sergey V. Drakunov, The Ohio State Univ. (United States)
Umit Ozguner, The Ohio State Univ. (United States)
Layne Lenning, The Ohio State Univ. (United States)


Published in SPIE Proceedings Vol. 1919:
Smart Structures and Materials 1993: Mathematics in Smart Structures
H. Thomas Banks, Editor(s)

© SPIE. Terms of Use
Back to Top