ES2102365T3 - Aparato y procedimiento para controlar un proceso utilizando una red adiestrada de procesado distribuido paralelo. - Google Patents

Aparato y procedimiento para controlar un proceso utilizando una red adiestrada de procesado distribuido paralelo.

Info

Publication number
ES2102365T3
ES2102365T3 ES90904112T ES90904112T ES2102365T3 ES 2102365 T3 ES2102365 T3 ES 2102365T3 ES 90904112 T ES90904112 T ES 90904112T ES 90904112 T ES90904112 T ES 90904112T ES 2102365 T3 ES2102365 T3 ES 2102365T3
Authority
ES
Spain
Prior art keywords
network
error
distributed processing
outputs
representative
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
ES90904112T
Other languages
English (en)
Inventor
Aaron James Owens
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
EIDP Inc
Original Assignee
EI Du Pont de Nemours and Co
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by EI Du Pont de Nemours and Co filed Critical EI Du Pont de Nemours and Co
Application granted granted Critical
Publication of ES2102365T3 publication Critical patent/ES2102365T3/es
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only

Landscapes

  • Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Multi Processors (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Feedback Control In General (AREA)
  • General Factory Administration (AREA)
  • Devices For Executing Special Programs (AREA)
  • Control By Computers (AREA)
  • Electrotherapy Devices (AREA)
  • Electrical Discharge Machining, Electrochemical Machining, And Combined Machining (AREA)
  • Preparation Of Compounds By Using Micro-Organisms (AREA)

Abstract

UNA RED DE PROCESO DISTRIBUIDO EN PARALELO (14) ANTERIORMENTE ENSEÑADA PARA SIMULAR UN PROCESO, RESPONDE A ACTIVACIONES DE DATOS DE ENTRADA A (42) PARA PRODUCIR DATOS DE SALIDA Y (40). LAS ACTIVACIONES SON REPRESENTATIVAS DE LOS PARAMETROS DE ENTRADA P (16) DEL PROCESO (12) Y LOS DE SALIDA SON REPRESENTATIVOS DE LAS CARACTERISTICAS C (18) DEL PRODUCTO DEL PROCESO. UN CONJUNTO DE DATOS DE OBJETIVOS (26) CORRESPONDIENTES A LAS CARACTERISTICAS FISICAS DESEADAS D (20) DEL PRODUCTO SON PRODUCIDAS Y UTILIZADAS PARA GENERAR SEÑALES REPRESENTATIVAS DE ERROR E ENTRE LA SEÑAL DE OBJETIVOS G (26) Y LOS DATOS SALIDAS Y (40). SE DETERMINAN LOS VALORES DE LOS DATOS ACTUALIZADOS AU (44) DE LA RED (14) QUE SON NECESARIOS PARA CONDUCIR AL ERROR E (38) A UN MINIMO PREDETERMINADO, Y LOS PARAMETROS REALES FISICOS DE ENTRADA P (16) DEL PROCESO SON ALTERADOS PARA QUE SE CORRESPONDAN CON LOS VALORES DE ENTRADA AU (44), PRODUCIENDOSE UN ERROR MINIMO. ESTA INVENCION PUEDE ACTUALIZARSE EN UNA SITUACION DE UTILIZACION POR LOTES O UNA SITUACION DE PROCESO DE CONTROL SOBRE LA MARCHA.
ES90904112T 1989-02-28 1990-02-28 Aparato y procedimiento para controlar un proceso utilizando una red adiestrada de procesado distribuido paralelo. Expired - Lifetime ES2102365T3 (es)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US31671789A 1989-02-28 1989-02-28

Publications (1)

Publication Number Publication Date
ES2102365T3 true ES2102365T3 (es) 1997-08-01

Family

ID=23230334

Family Applications (1)

Application Number Title Priority Date Filing Date
ES90904112T Expired - Lifetime ES2102365T3 (es) 1989-02-28 1990-02-28 Aparato y procedimiento para controlar un proceso utilizando una red adiestrada de procesado distribuido paralelo.

Country Status (9)

Country Link
EP (1) EP0461158B1 (es)
JP (1) JPH04503724A (es)
AT (1) ATE153788T1 (es)
CA (1) CA2011135C (es)
DE (1) DE69030812T2 (es)
DK (1) DK0461158T3 (es)
ES (1) ES2102365T3 (es)
IL (1) IL93522A0 (es)
WO (1) WO1990010270A1 (es)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5566275A (en) * 1991-08-14 1996-10-15 Kabushiki Kaisha Toshiba Control method and apparatus using two neural networks
JP3242950B2 (ja) * 1991-08-14 2001-12-25 株式会社東芝 予測制御方法
DE4131765A1 (de) * 1991-09-24 1993-03-25 Siemens Ag Regelparameter-verbesserungsverfahren fuer industrielle anlagen
US5353207A (en) * 1992-06-10 1994-10-04 Pavilion Technologies, Inc. Residual activation neural network
US5825646A (en) 1993-03-02 1998-10-20 Pavilion Technologies, Inc. Method and apparatus for determining the sensitivity of inputs to a neural network on output parameters
AU6358394A (en) * 1993-03-02 1994-09-26 Pavilion Technologies, Inc. Method and apparatus for analyzing a neural network within desired operating parameter constraints
DE4416364B4 (de) * 1993-05-17 2004-10-28 Siemens Ag Verfahren und Regeleinrichtung zur Regelung eines Prozesses
US6363289B1 (en) 1996-09-23 2002-03-26 Pavilion Technologies, Inc. Residual activation neural network
EP1185697A2 (en) * 1999-04-30 2002-03-13 Qualicon, Inc. Assay based on the analysis of dna melting curves
US8489529B2 (en) * 2011-03-31 2013-07-16 Microsoft Corporation Deep convex network with joint use of nonlinear random projection, Restricted Boltzmann Machine and batch-based parallelizable optimization

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3221151A (en) * 1962-01-22 1965-11-30 Massachusetts Inst Technology Adaptive control system using a performance reference model
FR2423806A1 (fr) * 1977-05-26 1979-11-16 Anvar Procede de regulation a modele de reference et regulateur mettant en oeuvre ce procede
DE3390539C2 (de) * 1983-10-14 1990-03-08 Ford Werke Ag Verfahren zum Betreiben eines adaptiv gesteuerten technischen Prozesses

Also Published As

Publication number Publication date
CA2011135A1 (en) 1990-08-31
ATE153788T1 (de) 1997-06-15
DE69030812T2 (de) 1997-10-16
DK0461158T3 (da) 1997-07-14
EP0461158B1 (en) 1997-05-28
IL93522A0 (en) 1990-11-29
JPH04503724A (ja) 1992-07-02
EP0461158A4 (en) 1992-08-12
WO1990010270A1 (en) 1990-09-07
EP0461158A1 (en) 1991-12-18
CA2011135C (en) 2001-03-13
DE69030812D1 (de) 1997-07-03

Similar Documents

Publication Publication Date Title
CA2066237A1 (en) Computer neural network regulatory process control system and method
AU1827088A (en) A block diagram simulator
ES2102365T3 (es) Aparato y procedimiento para controlar un proceso utilizando una red adiestrada de procesado distribuido paralelo.
ATE118282T1 (de) Regelungsverfahren und -vorrichtung mit verschiebung des sollwertes.
JPS57199004A (en) Sample value adaptive process controller
AU1453999A (en) Multiple scale signal processing and control system
DK0760604T3 (da) Apparat og fremgangsmåde til fremstilling af flere komplekst mønstrede esktrudater
GB2157459A (en) Selective parametric self- calibrating control system
EP0367569A3 (en) Sound effect system
DE3877897D1 (de) Verfahren und vorrichtung zur erzeugung von verbesserten russen und erhaltenes produkt.
EP0378093A3 (en) Method and system for acquiring parameters in process control
ATE127638T1 (de) Logische schaltung und verfahren zur verwendung.
CA2087750A1 (en) Method of simulating an industrial process, and use thereof for testing the operation of a controller
NO308692B1 (no) FremgangsmÕte ved fremstilling av et melkebasert matvareprodukt, et melkebasert matvareprodukt og anvendelse av dette
ES2046038T3 (es) Dispositivo de apriete para establecer una conexion electrica de lineas.
IT1250692B (it) Procedimento per la preparazione di demetilepipodofillotossina- beta-d-glucosidi.
DE59009325D1 (de) Adaptiver Regler.
EP0289359A3 (en) A multibit digital threshold comparator
ATE76988T1 (de) Einrichtung zum identifizieren von uebertragungsstrecken,insbesondere von regelstrecken.
JPS5759201A (en) Decentralized process controller
JPS6442734A (en) Arithmetic circuit
DE3782932D1 (de) Im echtzeitbetrieb arbeitende lokale videobildverbesserung mit trennbaren zweidimensionalen filtern.
JPS5723105A (en) Process controller
NL7804078A (en) Machine tool servo control with central processor - has processing unit for each function linked to centre, has facility for recording performance and includes three ROM and three RAM units
JPS643703A (en) Process control system

Legal Events

Date Code Title Description
FG2A Definitive protection

Ref document number: 461158

Country of ref document: ES