US 5,367,612 AGranted

Neurocontrolled adaptive process control system

AssigneeScience Applications International Corporation

InventorsDaniel J. Bozich, H. Bruce MacKay, Jay A. Eggert, Ernest E. Muenchau

Life of this patent

Estimating the term…

Loading patent…

Abstract

An adaptive process control system selectively controls vibrations in a given medium in real time. Unwanted vibrations present at a point being monitored in a given medium are sensed, and the system generates an appropriate offsetting vibration that is applied to the medium at a convenient location, which may be remote from the monitored point. The system includes a vibration sensor, such as one or more accelerometers, that sense both input and output vibrations present within the medium; at least one vibration generator, such as an electromagnetic shaker, that generates appropriate offsetting vibrations that are applied to the medium at one or more appropriate locations; and a neural network controller that controls the vibration generator(s) so as to force the sensed vibration at the monitored point(s) to a desired level. The adaptive vibration cancellation provided by the invention takes place in real time, and without the need to process time-consuming complex mathematical algorithms. A specific embodiment of the neural network controller includes a plurality of 4-layer neural networks configured in an adaptive filtered-x configuration.

Claims17

Dependent claims

A vibration control system comprising:

a medium through which vibrations may be transmitted;
sensing means for sensing vibrations at a plurality of monitoring locations within said medium;
transducer means for applying a plurality of forced vibrations to said medium in response to a respective plurality of control signals;
controller means for controlling said transducer means, said controller means including
a first pair of neural networks that emulate said sensed vibrations by generating an emulated vibration signal for each vibration sensed by said sensing means,
error signal generating means for generating error signals representative of the difference between said emulated vibration signal generated by said first pair of neural networks and a specified reference signal, and
a second pair of neural networks that control said transducer means by generating said plurality of control signals in response to said error signals so as to force vibrations sensed by said sensing means at least one of said plurality of monitoring locations to a specified level by controlling said transducer means such that all vibrations present at said at least one monitoring location, including vibrations generated by said transducer means and any input vibrations that may be present in said medium, cooperate to produce a vibration of said specified level at said at least one monitoring location within said medium.

4 more elements

A method of controlling vibrations at a specified point in a medium comprising:

(a) sensing the vibrations present at the specified point in the medium;
(b) emulating the sensed vibrations by generating an emulated vibration signal using a neuro-emulator system;
(c) comparing the emulated vibration signal generated by the neuro-emulator system to a reference signal to determine an error signal;
(d) applying the error signal to a neuro-controller system and operating said neuro-controller system to generate a control signal as a function of said error signal;
(e) applying the control signal generated by the neuro-controller system to a transducer, said transducer being coupled to said medium, said transducer responding to said control signal by generating offsetting vibrations within said medium;
and
(f) training said neuro emulator system and said neuro-controller system to alter the generation of the emulated vibration signal and the control signal until the vibrations sensed at the specified point in step (a) assume a specified level.

4 more elements

Dependencies are inferred from the claim text.

Facts

Application: 07/605,585Filed 30 Oct 1990
Granted: 22 Nov 1994
Term ends: Not estimatedThe source records don’t support an estimate.

Classification22 codes

G05D 19/02
Control of mechanical oscillations, e.g. of amplitude, of frequency, of phase: characterised by the use of electric means
F16F 15/02
Suppression of vibrations in systems ; Means or arrangements for avoiding or reducing out-of-balance forces, e.g. due to motion: suppression of…
G01N 29/30
Details , e.g. general constructional or apparatus details: arrangements for calibrating or comparing, e.g. with standard objects
G05B 13/027
The criterion being a learning criterion: using neural networks only