US5367612A — Neurocontrolled adaptive process control system

Claim 1

Independent Claim 216 words

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.

Claim 2

Dependent Claim 216 words

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.

Claim 3

Dependent Claim 28 words

The vibration control system as set forth in claim 1 wherein said medium comprises a solid medium, such as a physical structure having members that bend or flex.

Claim 4

Dependent Claim 90 words

The vibration control system as set forth in claim 2 wherein said medium includes a rigid frame to which an object to be subjected to vibrations may be secured, and wherein one of said monitoring locations of said sensing means comprises a first location on said frame, and wherein said specified level of said vibration at said first monitoring location varies as a function of time in accordance with a specified waveform shape, whereby said vibration control system comprises a vibration generator that is used to shake test said object.

Claim 5

Dependent Claim 38 words

The vibration control system as set forth in claim 3 wherein said controller means forces vibrations at at least two monitoring locations to assume a specified level, at least one of said monitoring locations being on said object.

Claim 6

Dependent Claim 17 words

The vibration control system as set forth in claim 1 wherein said medium comprises a fluid medium.

Claim 7

Dependent Claim 85 words

The vibration control system as set forth in claim 1 wherein said first pair of neural networks comprise: a first neural network that adaptively trains itself to emulate said sensed vibrations at said at least one monitoring location, said first neural network thereby functioning as a "trainer" neural network, and a second neural network that generates said emulated vibration signals as a function of a most recent trained response of said first neural network, said second neural network thereby functioning as an "executer" neural network.

Claim 8

Dependent Claim 79 words

The vibration control system as set forth in claim 6 wherein said second pair of neural networks comprise: a third neural network that adaptively trains itself to track said error signals, said third neural network thereby also functioning as a "trainer" neural network, and a fourth neural network that generates said control signals as a function of a most recent trained response of said third neural network, said fourth neural network thereby also functioning as an "executer" neural network.

Claim 9

Dependent Claim 164 words

The vibration control system as set forth in claim 7 wherein each of said first, second, third and fourth neural networks functionally comprise layers of neurons, each neuron including at least one input and a single output, the single output of each neuron in a first layer of neurons being multiplied by a respective adaptive coefficient and connected as an input to each neuron of a second layer of neurons, the single output of each neuron in the second layer of neurons being multiplied by a respective adaptive coefficient and connected as an input to each neuron of a third layer, the single output of each neuron in the third layer also being multiplied by a respective adaptive coefficient and connected as an input to each neuron of a fourth layer, said first layer of neurons including at least 20 neurons, said second and third layers of neurons including at least 8 neurons, and said fourth layer of neurons including at least one neuron.

Claim 10

Dependent Claim 36 words

The vibration control system as set forth in claim 8 wherein said neural networks are emulated in a neurocomputer, said neurocomputer including high speed processing means for performing a large number of neuron emulations in parallel.

Claim 11

Dependent Claim 19 words

The vibration control system as set forth in claim 8 wherein said neural networks are realized in integrated circuits.

Claim 12

Independent Claim 159 words

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.

Claim 13

Independent Claim 159 words

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.

Claim 14

Dependent Claim 55 words

The method of controlling vibrations as set forth in claim 11 wherein said reference signal to which said sensed vibrations are compared in step (c) is zero, whereby said error signal comprises whatever vibrations are sensed in step (a), and said method of controlling vibrations becomes a method of canceling vibrations at said specified point.

Claim 15

Dependent Claim 49 words

The method of controlling vibrations as set forth in claim 11 wherein step (b) includes adapting a first neuro-emulator to imitate the sensed vibrations, and controlling a second neuro-emulator with said first neuro-emulator to generate said emulated vibration signal based upon a most recent training of the first neuro-emulator.

Claim 16

Dependent Claim 39 words

The method of controlling vibrations as set forth in claim 13 wherein step (d) includes training a first neuro-controller to respond to said error signal, and controlling a second neuro-controller with said first neuro-controller to generate said control signal.

Claim 17

Dependent Claim 27 words

The method of controlling vibrations as set forth in claim 14 wherein said medium comprises air, said vibrations comprise acoustical signals, and said transducer includes a speaker.

Claim 18

Dependent Claim 52 words

The method of controlling vibrations as set forth in claim 14 wherein said medium comprises a shake table on which an object to be subjected to vibrations is placed, and wherein said specified point is a point on said object, whereby said object is subjected to vibrations defined by said reference signal.

Claim 19

Dependent Claim 141 words

The method of controlling vibrations as set forth in claim 14 wherein step (a) includes sensing vibrations at a plurality of specified points within said medium, step (b) includes generating an emulated vibration signal for each of said plurality of specified points, step (c) includes determining a plurality of error signals based upon comparing each of the emulated vibration signals to a respective reference signal, step (d) includes generating a plurality of control signals based upon the plurality of error signals, step (e) includes applying each of the control signals to respective transducers, each of which is coupled to said medium, and step (f) includes training the neuro-emulator system and the neuro-controller system to alter the generation of the plurality of emulated vibration signals and control signals until the vibrations sensed at the plurality of specified points assumes a specified level.

Annuity Stage	Window Opens	Payment Deadline	Surcharge Period Until	Estimated Fee	Status
3.5 Years (Year 4)	1997-11-21	1998-05-23	1998-11-22	$2000.00	Window Closed / Lapsed
7.5 Years (Year 8)	2001-11-21	2002-05-23	2002-11-22	$3760.00	Window Closed / Lapsed
11.5 Years (Year 12)	2005-11-21	2006-05-23	2006-11-22	$7700.00	Window Closed / Lapsed

Neurocontrolled adaptive process control system

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag