EP1678563A1 - Procede permettant de faire fonctionner une installation technique - Google Patents

Procede permettant de faire fonctionner une installation technique

Info

Publication number
EP1678563A1
EP1678563A1 EP03767395A EP03767395A EP1678563A1 EP 1678563 A1 EP1678563 A1 EP 1678563A1 EP 03767395 A EP03767395 A EP 03767395A EP 03767395 A EP03767395 A EP 03767395A EP 1678563 A1 EP1678563 A1 EP 1678563A1
Authority
EP
European Patent Office
Prior art keywords
operating parameters
operating
technical system
parameters
determined
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.)
Ceased
Application number
EP03767395A
Other languages
German (de)
English (en)
Inventor
Wolfgang Fick
Uwe Gerk
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.)
Siemens AG
Siemens Corp
Original Assignee
Siemens AG
Siemens Corp
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 Siemens AG, Siemens Corp filed Critical Siemens AG
Publication of EP1678563A1 publication Critical patent/EP1678563A1/fr
Ceased 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
    • G05B13/0205—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system
    • G05B13/026—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system using a predictor
    • 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
    • G05B13/0295—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 fuzzy logic and expert systems

Definitions

  • the invention relates to a method for operating a technical system, in particular a power plant.
  • Modern industrial plants generally have a large number of plant parts that interact with each other in a highly complex manner.
  • operating parameters are usually sensed at least in the important plant parts and fed to an automation and / or process control system.
  • These operating parameters can e.g. are input parameters which are set by an operator in order to operate a plant part in a desired manner.
  • the fuel and air supply to a combustion chamber must be adjusted in order to call up a desired power of the gas turbine.
  • This power is also an operating parameter of the gas turbine, which can be understood as an output parameter.
  • a generator and numerous other auxiliary operations are also connected to the gas turbine.
  • Each part of the system has numerous operating parameters which have to be set by an operator of the system or which result from such settings as output parameters.
  • One of the main difficulties is to recognize correlations in the abundance of data based on operating parameters in order to be able to positively influence the operation of the system as a whole.
  • One solution from the prior art is to simulate the technical system using a model in order to find out which changes in operating parameters lead to which changes in other operating parameters in order to understand the interactions between the system parts or also within a system part.
  • the invention is therefore based on the object of specifying a method for operating a technical system, by means of which the operating mode of a technical system is determined in a simple manner.
  • the object is achieved according to the invention by a method for operating a technical system, during which
  • Time intervals of a freely selectable size operating parameters of at least one plant part are recorded and from the temporal behavior of these operating parameters using methods of artificial intelligence comprising at least one method from the group ⁇ neural network, fuzzy logic, combined neuro-fuzzy method, genetic algorithm ⁇ Operation and / or operation of the technical system is determined.
  • the operating parameters also include variables such as those of condition monitoring systems such as a vibration analysis as measured variables or derived variables and determined and made available.
  • the invention is based on the consideration that a temporal behavior of operating parameters, which are recorded and stored during a time interval, allows conclusions to be drawn about the current operating mode of the technical system without a detailed knowledge of the interdependencies of the operating parameters is necessary. In particular, no model of the technical system is required to be able to make these statements.
  • the temporal behavior of the operating parameters can be recorded, for example, by simultaneously recording a number of operating parameters at a current and a later (or also historical) point in time and combining them to form a snapshot / fingerprint, which can then be compared.
  • this connection is detected and quantified using methods of artificial intelligence, without a model equation having to be available or having to be determined beforehand, for example.
  • the known methods of artificial intelligence can relate relationships between operating parameters within a data Learn the amount of operating parameters by analyzing their behavior over time. The correlations found and their quantification become better the larger the amount of data to be examined in terms of operating parameters. As soon as a relationship between certain operating parameters has been identified and quantified, the methods of artificial intelligence are still able to indicate which behavior is more dependent on such operating parameters and their changes, for which no image of the operating parameters has already been recorded other operating parameters can be expected.
  • Modeling of the technical function of the system must be known.
  • the operation and / or mode of operation is determined by the described analysis of the behavior of the operating parameters and their mutual dependencies.
  • the operating parameters recorded during the time interval can be understood as snapshots or inventories or also characterization of the plant part or the plant (“fingerprint” of the plant part or the plant).
  • a fingerprint replaces a classic model, whereby according to the inventive method the behavior of the Operating parameters of the operation and / or functioning of the technical system can be inferred using methods of artificial intelligence
  • fingerprints for start-up and shutdown as well as normal operation can be recorded, for example, in order to get to know and identify the respective operating mode.
  • the operating parameters are recorded during at least two time intervals which are separated from one another in time, in each case the operating parameters recorded as a data set are compared with one another and comprehensively using methods of artificial intelligence
  • At least one method from the group ⁇ neural network, fuzzy logic, combined neuro-fuzzy method, genetic algorithm ⁇ is used to determine how the operating parameters are to be set in order to achieve a desired mode of operation of the technical system.
  • At least two fingerprints are compared, for example the operating parameters that change most in comparison are specifically examined. This comparison helps to determine which changes to certain operating parameters are necessary in order to influence certain other operating parameters in a targeted manner.
  • a power plant for example, can be in normal operation for days and suddenly the power output drops.
  • a comparison of fingerprints from the history of the technical system shows what has changed (e.g. the operating parameters for outside air pressure indicate a significant drop) and also how to counteract this in order to at least maintain performance '(e.g. the operating parameters for the combustion air pressure also drops).
  • a prediction is determined in that a desired mode of operation of the power plant system is determined by specifically setting selected operating parameters.
  • the prediction preferably includes the specification of the operating parameters to be changed and their setting values as a data set in order to achieve the desired operating mode.
  • the comparison can also include the comparison of fingerprints of identical but different systems and the comparison of fingerprints of systems that are only similar to one another.
  • a measure of confidence which represents a probability that the operating parameters will be set ⁇ leads to the desired mode of operation according to the prediction.
  • a degree of trust of 100% means that it can be expected with the greatest certainty that an adjustment of the operating parameters in accordance with the prediction will lead to the desired operating mode of the technical system.
  • Such a high degree of trust arises when the currently desired mode of operation of the technical system and any boundary conditions (e.g. environmental factors) have already been realized or have occurred in the past and the setting values used for the operating parameters are also known as a fingerprint.
  • a degree of trust of, for example, 60% can mean that, compared to the currently desired operating mode of the technical system, there is no historical operating mode corresponding to this desired operating mode as a fingerprint. However, there was a similar mode of operation, so that it cannot be assumed with the greatest certainty that the setting values for the operating parameters given by the prediction will achieve the desired mode of operation, but that there is still a good chance.
  • a degree of confidence close to 0% can, for example, furthermore indicate that a comparable desired operating mode of the technical system has never come close to being and consequently the setting values for the operating parameters determined in the prediction are associated with great uncertainty with regard to achieving the desired operating mode.
  • the operating mode of the technical system is advantageously determined by means of a correlation analysis of the operating parameters. averaged, the effects of changes in operating parameters corresponding to input parameters being determined on operating parameters corresponding to output parameters.
  • effects of a change in input parameters on output parameters dependent thereon are specifically detected and quantified.
  • Input parameters are usually operating parameters, the values of which either have to be set by an operator of the technical system or which are determined by boundary conditions, for example environmental influences.
  • Output parameters are those operating parameters which result from a setting of the input parameters and are consequently dependent on them; the correlation analysis examines the type of connection and quantifies it.
  • the operating parameters of all essential system parts are recorded in a technical system, so that the method of operation of the entire technical system can be determined and set in a simple manner by means of a method according to the invention; the method according to the invention can form a control system by means of which one or more system parts and the entire technical system are controlled by means of closed control loops.
  • a database image of operating parameters is generated. This image allows the operator of the technical system to derive correlations between operating parameters and the operating mode of the technical system, to compare their own knowledge with the recorded data and to control the desired operating modes of the technical system.
  • a plurality of fingerprints are preferably compared with one another in order to identify which knowledge is transferred from one operating mode to another operating mode can be. The corresponding results and predictions can easily be saved as data sets and called up at any time if required.
  • FIG shows a processing system for performing the method according to the invention.
  • a processing system 1 is shown in the figure, comprising a processing unit 10 for carrying out the method according to the invention.
  • the processing unit 10 is supplied with operating parameters 5 of a technical system, which include input parameters 15 and output parameters 20.
  • a timer 25 is used to select a time interval of interest during which the operating parameters 5 are to be recorded.
  • the temporal behavior of the operating parameters 5 during the time interval is examined by means of a neural network 30 and / or a neuro-fuzzy functional unit 35 and / or one or more genetic algorithms 40 and from this a relationship between at least part of the input parameters 15 and at least part the output parameter 20 is detected and quantified.
  • Knowledge of this relationship finally allows the provision of a data record 50, which includes setting values for at least some of the operating parameters 5, in order to achieve a desired mode of operation of a system part of a technical system.
  • This data record 50 represents a prediction of how certain operating parameters are to be set in order to implement the desired operating mode of the technical system.
  • the processing unit 10 output measure 55 which represents a probability that setting the operating parameters according to the data in data set 50 leads to the desired operating mode.
  • a correlation analysis takes place within the processing unit 10 between the input parameters 15 and the output parameters 20, so that the operation and functioning of the technical system is possible on the basis of knowledge of the temporal behavior of the input parameters 15 and the associated output parameters 20 and data records 50 can be provided for desired operating modes of the technical system, for which no operating parameters 5 with the corresponding input parameters 15 and output parameters 20 have been recorded in the past.
  • the processing unit 10 is capable of interpolation.

Landscapes

  • Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Feedback Control In General (AREA)

Abstract

Procédé permettant de faire fonctionner une installation technique qui comporte le relevé de paramètres de fonctionnement pendant un certain laps de temps, un mode de fonctionnement et / ou un type de fonction de l'installation technique étant déterminé à partir du comportement dans le temps de ces paramètres de fonctionnement, à l'aide de méthodes d'intelligence artificielle.
EP03767395A 2003-10-29 2003-10-29 Procede permettant de faire fonctionner une installation technique Ceased EP1678563A1 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/DE2003/003584 WO2005045535A1 (fr) 2003-10-29 2003-10-29 Procede permettant de faire fonctionner une installation technique

Publications (1)

Publication Number Publication Date
EP1678563A1 true EP1678563A1 (fr) 2006-07-12

Family

ID=34558674

Family Applications (1)

Application Number Title Priority Date Filing Date
EP03767395A Ceased EP1678563A1 (fr) 2003-10-29 2003-10-29 Procede permettant de faire fonctionner une installation technique

Country Status (7)

Country Link
US (1) US20070078532A1 (fr)
EP (1) EP1678563A1 (fr)
JP (1) JP2007510187A (fr)
CN (1) CN100430845C (fr)
AU (1) AU2003291924B2 (fr)
DE (1) DE10394362D2 (fr)
WO (1) WO2005045535A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7643974B2 (en) * 2005-04-22 2010-01-05 Air Liquide Large Industries U.S. Lp Pipeline optimizer system
DE102005060635A1 (de) 2005-12-13 2007-06-14 Siemens Ag Steuerungsverfahren zur Kühlung einer technischen Anlage
JP7090243B2 (ja) * 2018-05-08 2022-06-24 千代田化工建設株式会社 プラント運転条件設定支援システム、学習装置、及び運転条件設定支援装置
CN115037608B (zh) * 2021-03-04 2024-09-06 维沃移动通信有限公司 量化的方法、装置、设备及可读存储介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4130164A1 (de) * 1991-09-11 1993-03-18 Bodenseewerk Geraetetech Regler, insbesondere flugregler
US5598076A (en) * 1991-12-09 1997-01-28 Siemens Aktiengesellschaft Process for optimizing control parameters for a system having an actual behavior depending on the control parameters
CN1075219A (zh) * 1992-11-19 1993-08-11 北方工业大学 模糊控制方法和模糊控制器
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
US5566065A (en) * 1994-11-01 1996-10-15 The Foxboro Company Method and apparatus for controlling multivariable nonlinear processes
US5598075A (en) * 1995-09-13 1997-01-28 Industrial Technology Research Institute Servo control method and apparatus for discharging machine
US6381504B1 (en) * 1996-05-06 2002-04-30 Pavilion Technologies, Inc. Method for optimizing a plant with multiple inputs
US6603795B2 (en) * 2001-02-08 2003-08-05 Hatch Associates Ltd. Power control system for AC electric arc furnace
WO2003017745A2 (fr) * 2001-08-23 2003-03-06 Sciperio, Inc. Instrument d'architecture et procedes d'utilisation
AU2003262893A1 (en) * 2002-08-21 2004-03-11 Neal Solomon Organizing groups of self-configurable mobile robotic agents

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO2005045535A1 *

Also Published As

Publication number Publication date
JP2007510187A (ja) 2007-04-19
CN1860419A (zh) 2006-11-08
DE10394362D2 (de) 2006-09-21
WO2005045535A1 (fr) 2005-05-19
CN100430845C (zh) 2008-11-05
AU2003291924A1 (en) 2005-05-26
AU2003291924B2 (en) 2009-05-28
US20070078532A1 (en) 2007-04-05

Similar Documents

Publication Publication Date Title
EP0895197B1 (fr) Procédé pour surveiller des installations avec des composants mécaniques
DE3421522C2 (de) Verfahren und Einrichtung zur Diagnose eines Wärmekraftwerks
EP2108139B1 (fr) Procédé de régulation et/ou de contrôle assisté par ordinateur d'un système technique, en particulier d'une turbine à gaz
EP1543394B1 (fr) Procede et dispositif pour surveiller une installation technique comprenant plusieurs systemes, notamment une centrale electrique
EP0789861B1 (fr) Procede d'analyse des donnees d'operations d'une installation technique
EP3279756B1 (fr) Dispositif de diagnostic et procédé de surveillance du fonctionnement d'une installation technique
EP0789864B1 (fr) Systeme de controle pour installation industrielle
EP2706422B1 (fr) Procédé de surveillance assistée par ordinateur du fonctionnement d'un système technique, en particulier d'une installation de production d'énergie électrique
DE10241746B4 (de) Verfahren zur zyklischen Qualitätsbewertung und Prozessüberwachung bei periodischen Produktionsprozessen
EP3232282B1 (fr) Dispositif de diagnostic et procede de surveillance du fonctionnement d'une installation technique
DE102011102034A1 (de) Online-Abbgleich eines prozessanalytischen Modells mit effektivem Prozessbetrieb
EP1779203A1 (fr) Identification de parametres d'appareils de terrain dans la technique d'automatisation
EP2971768A1 (fr) Développement d'un modèle d'ordre supérieur
EP3056957A1 (fr) Procédé et dispositif de diagnostic destinés à la surveillance du fonctionnement d'un circuit régulateur
EP1055180B1 (fr) Procede et dispositif de conception d'un systeme technique
EP3542229B1 (fr) Dispositif et procédé de détermination des paramètres d'un dispositif de réglage
EP4268029B1 (fr) Procédé et système de supervision du fonctionnement d'une installation technique
EP2971769B1 (fr) Entrée de schéma r&i pour un procédé de contrôle et/ou de surveillance d'un système de compresseurs
EP1678563A1 (fr) Procede permettant de faire fonctionner une installation technique
EP3623890A1 (fr) Procédé de surveillance d'une pluralité d'installations techniques
EP1431927A1 (fr) Méthode pour estimer la durée de vie résiduelle d'un appareil
EP3686697B1 (fr) Optimisation du régulateur pour un système de commande d'une installation technique
DE102020109858A1 (de) Verfahren zum Betreiben eines Systems
EP1157317B1 (fr) Procede et dispositif pour la reduction d'une pluralite de valeurs mesurees d'un systeme industriel
EP3928033B1 (fr) Procédé de commande d'une turbine à gaz

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20060428

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LI LU MC NL PT RO SE SI SK TR

DAX Request for extension of the european patent (deleted)
17Q First examination report despatched

Effective date: 20070608

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED

18R Application refused

Effective date: 20090902