Paper
8 September 1993 Smart structure applications using neurocontrollers
Daniel J. Bozich, H. Bruce MacKay
Author Affiliations +
Abstract
This paper describes a neural network-based digital control system for a wide range of dynamic applications. Two diverse applications of the digital control of smart structural systems are discussed to illustrate the general nature of this neurocontroller. The first application is reduction of vibration in optical mirrors for large high energy laser installations. Under neurocontrol, multiple actuators and sensors reduce the `jitter' caused by cooling water flow and other vibration sources affecting the mirrors within the laser system. Accelerometers provide control parameters. The control and reduction of high intensity acoustic noise is a similar application of neurocontrollers. In this case, multiple acoustic sources are controlled to reduce the measured noise at multiple microphone locations. Both examples used the same neurocontroller with a filtered-x architecture. Minor adjustments to accommodate either the `macro'-scale dynamics of high-intensity acoustics, or the `micro'-scale dynamics of optical mirror vibrations were made as needed. The paper includes results from actual tests.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Daniel J. Bozich and H. Bruce MacKay "Smart structure applications using neurocontrollers", Proc. SPIE 1917, Smart Structures and Materials 1993: Smart Structures and Intelligent Systems, (8 September 1993); https://doi.org/10.1117/12.152789
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Acoustics

Mirrors

Neural networks

Actuators

Smart structures

Intelligence systems

Network architectures

Back to Top