WO2006037732A1 - Procede pour pronostiquer la consommation d'energie d'une installation de production industrielle, dispositif pour mettre ledit procede en oeuvre et progiciel correspondant et support pouvant etre lu par ordinateur - Google Patents
Procede pour pronostiquer la consommation d'energie d'une installation de production industrielle, dispositif pour mettre ledit procede en oeuvre et progiciel correspondant et support pouvant etre lu par ordinateur Download PDFInfo
- Publication number
- WO2006037732A1 WO2006037732A1 PCT/EP2005/054765 EP2005054765W WO2006037732A1 WO 2006037732 A1 WO2006037732 A1 WO 2006037732A1 EP 2005054765 W EP2005054765 W EP 2005054765W WO 2006037732 A1 WO2006037732 A1 WO 2006037732A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- production
- time series
- data
- prognosis
- energy consumption
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Definitions
- a method for prognosis of the energy consumption of an indus ⁇ -industrial production system apparatus for performing the method, and associated computer program product and computer-readable medium
- the invention relates to a method for the prognosis of the energy consumption of an industrial production plant, WO-in from the information of a scheduled production process input data for a forecasting system can be obtained which outputs, as output data of the energy consumption of the ge ⁇ planned production process.
- a forecast of energy consumption in the industrial sector both for companies in the energy supply as a matter cher also for companies in the manufacturing industries of out.
- An energy supply company needs the expected load of its energy consumers, ie the time course of energy consumption over a day in order to cover the requested energy needs as accurately as possible.
- a production company is interested in an energy consumption prognosis, for example for reasons of business economy, in order to obtain good conditions from an early notification of its load profile for the following day at the energy supply company.
- neural networks are parallel data processing structures that can change themselves, and are assumed to be known here.
- Such neural networks are trained on the basis of historical data, that is, tries to mimic a predetermined from historical data input / output behavior nachzu ⁇ and develop interpolation properties.
- the number of input data is with energy supply companies 200416501
- the invention is therefore based on the object to provide a method of the type mentioned, in which the production information contained in production plans can be used for a short-term energy consumption forecast.
- the object is inventively achieved by a gattungsge ⁇ mäßes method in which the forecast for a forecast time ⁇ space from the near future will be created and the Prognosesys ⁇ system uses a neural network, from the production ⁇ information first time series of production data gebil- det are, where subsequently the time series of producti ⁇ onsoire by weighted summary of the time series of aggregated production data compressed, whereby the 200416501
- the neural network from the time series of aggregated algorithmsi ⁇ onsander a time series of energy consumption for the Prog ⁇ nose period determined.
- all information relevant for the planned production process ie production plans and plant-technical knowledge, can be introduced.
- weighted summation of the number of producti ⁇ is intelligent onsquel reduced, so that this data as input ⁇ are suitable for a neural network.
- the weight ⁇ factors for this were averages ER in training the neural network.
- the time series is thus a temporal sorting of the production data over the forecasting period, that is, for example, over a day with hourly resolution.
- the forecasting method is thus capable of calculating short-term forecasts for the energy consumption, for example, of the following day.
- data from production plans and plant-specific data are used as production information.
- production schedules planned producti ⁇ example onsmengen by specifying machine running times and their Aus ⁇ utilization rate and downtime, supply about at Maschinenreini ⁇ contain.
- technical know-how on the behavior of the plant components for example the start-up behavior of a production machine or its after-run after the end of production, is taken into account.
- a time series of production data is formed from the production information for each production line and / or for each product. It has proven to be expedient to carry out a certain summary of data at this point, for example by aggregating all machines of a production line or all production lines of a product. 200416501
- time series are duktlinien of production data for Pro ⁇ and / or products with similar power consumption characteristics ⁇ by weighted Summary condensed into the time series of aggregated production data.
- energy consumers come into question their power propor ⁇ tional to the production volume, but also consumers with high basic power consumption as well as products that require aufwen ⁇ ended pre- or post-processing.
- the weighting factors for the weighted aggregation of the time series are determined on the basis of historical input and output data. The calculation of the weighting factors must be carried out once. For this, a Gleichungssys ⁇ tem placed in the known time series for Produk ⁇ tion volumes and enter into energy consumption. Since this slip has ⁇ monitoring system many more equations than unknowns, it is m istsproblem supplemented by a target condition to a non-linear optimization. After this weighted summary, input data are then available which reflect the complex production planning and are suitable for the prognosis system with a neural network.
- Input data entered into the neural network are data on the temperature history, the humidity, the degree of coverage, the times of sunrise and -sunset as well as energy consumption of the previous day into consideration. The consideration of this additional information gives the energy consumption forecast a higher accuracy.
- the method according to the invention is advantageously carried out on a suitably designed device, in particular a computer device.
- This computer device which contains the forecasting system, can be part of a control and automation system of the production plant for which an energy consumption forecast is to be carried out.
- the invention also leads to a Computerpro ⁇ program product which can be stored on a computer readable medium and a software code portion, which is suitable for the computer apparatus called lead to cause the method for throughput when the product running on the computer device.
- the invention also leads to a computer-readable medium on which said computer program product is stored and which is designed, for example, as a DVD (Digital Versatile Disc).
- DVD Digital Versatile Disc
- input data for a prognosis system are obtained from production information about a planned production process.
- production information data from production plans PPL 1 but also plant-specific data ANL 1 are used, with the running index i numbering the products or production lines.
- the production plan PPL 1 to 1 product information about the start of production contains (5:30), the end of production (22:00) and the production ⁇ mass (11.00).
- the production plan PPL x contains the information that a cleaning of the product 1 manufacturing machine is provided between 12:00 and 13:00.
- ANL x flows over the the product 1 unjustifiable system, after which this production system before starting ⁇ having a one-hour start-up phase as well as a two-hour cooling phase after the end of production.
- first time series of production data pm i: 1 are formed, which have hourly values for production quantities for a prognosis period of one day.
- the time series of production data pitti- is shown in FIG t 1 as a graph over time, where j is a 1-24 running count index for the time series Glienicke ⁇ is.
- FIG 2 illustrates the present invention prediction method for a production facility with two production lines, namely lent a pre VOR with three precursors I 1 to 3 ', and a final product with five end products 1 described to 5.
- Figure 1 are first ⁇ option plans from the producti PPLI. to PPL 3 .
- D formed;
- the forecasting system compresses the time series of production data for each of the two production lines VOR, END by weighted summary to time series of aggregated production data pm ⁇ OIr] for the pre-production VOR and pm end , D for the final production END.
- the weighting factors X 1 for the weighted summary of the time series are determined on the basis of historical input and output data.
- the high number of data from the production plans PPL 1 has been reduced to two time series of aggregated production data pm vorr] and pm end (] , ie for pre- and final production.
- a prognosis system SYS which has a neural network NEW, since the number of input data has been sufficiently reduced.
- the temperature profile T 3 on the prognosis day and a time series of energy consumption ev 'of the previous day are taken into account as further input data for the prediction system SYS.
- energiesrele--relevant input data, the humidity, the Bede ⁇ ckungsgrad, the times of sunrise and sunset are considered.
- the prediction system SYS, or its artificial neural network NEW calculates from these input data a time series of predicted energy consumption, for example, with hourly resolution.
- the use of the neuronal network NEW for energy consumption forecasts for a prognosis period from the near future, for example the following day, has become possible only through the invention, because the complex production information has been suitably pre-processed and condensed so that it can be counted in number and type NEW are suitable as input data for a neural network.
- the time series of energy consumption with embark ⁇ resolution to interpolate by spline functions to examples play winnen a finer resolution in quarters of an hour to ge ⁇ .
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE200410048235 DE102004048235A1 (de) | 2004-10-04 | 2004-10-04 | Verfahren zur Prognose des Energieverbrauchs einer industriellen Produktionsanlage, Vorrichtung zum Durchführen des Verfahrens sowie zugehöriges Computerprogramm-Produkt und computerlesbares Medium |
DE102004048235.7 | 2004-10-04 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2006037732A1 true WO2006037732A1 (fr) | 2006-04-13 |
Family
ID=35385665
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2005/054765 WO2006037732A1 (fr) | 2004-10-04 | 2005-09-23 | Procede pour pronostiquer la consommation d'energie d'une installation de production industrielle, dispositif pour mettre ledit procede en oeuvre et progiciel correspondant et support pouvant etre lu par ordinateur |
Country Status (2)
Country | Link |
---|---|
DE (1) | DE102004048235A1 (fr) |
WO (1) | WO2006037732A1 (fr) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102015202412A1 (de) * | 2015-02-11 | 2016-08-11 | Siemens Aktiengesellschaft | Betriebsverfahren zum Lastmanagement einer Anlage und zugehöriger Betriebsmittelagent |
CN110058526B (zh) * | 2019-05-20 | 2021-11-30 | 杭州电子科技大学 | 一种基于区间二型t-s模型的中立型系统的控制方法 |
EP4312096A1 (fr) * | 2022-07-25 | 2024-01-31 | Siemens Aktiengesellschaft | Procédé d'estimation d'une consommation d'énergie lors d'une génération d'un produit, produit programme informatique, support d'enregistrement lisible par ordinateur et dispositif électronique de calcul |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5873251A (en) * | 1995-09-13 | 1999-02-23 | Kabushiki Kaisha Toshiba | Plant operation control system |
US6577962B1 (en) * | 2000-09-28 | 2003-06-10 | Silicon Energy, Inc. | System and method for forecasting energy usage load |
US20040102937A1 (en) * | 2002-11-21 | 2004-05-27 | Honeywell International Inc. | Energy forecasting using model parameter estimation |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE4235274C2 (de) * | 1992-10-20 | 1994-07-14 | Rwe Energie Ag | Verfahren zur Einrichtung und zum Betrieb eines Verbundes von elektrischen Geräten |
EP0883075A3 (fr) * | 1997-06-05 | 1999-01-27 | Nortel Networks Corporation | Procédé et dispositif de prédiction des valeurs futurs d'une série chronologique |
-
2004
- 2004-10-04 DE DE200410048235 patent/DE102004048235A1/de not_active Ceased
-
2005
- 2005-09-23 WO PCT/EP2005/054765 patent/WO2006037732A1/fr active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5873251A (en) * | 1995-09-13 | 1999-02-23 | Kabushiki Kaisha Toshiba | Plant operation control system |
US6577962B1 (en) * | 2000-09-28 | 2003-06-10 | Silicon Energy, Inc. | System and method for forecasting energy usage load |
US20040102937A1 (en) * | 2002-11-21 | 2004-05-27 | Honeywell International Inc. | Energy forecasting using model parameter estimation |
Non-Patent Citations (1)
Title |
---|
MAZARKO J ET AL: "APPLICATION OF STATISTICAL AND NEURAL APPROACHES TO THE DAILY LOAD PROFILES MODELLING IN POWER DISTRIBUTION SYSTEMS", 1999 IEEE TRANSMISSION AND DISTRIBUTION CONFERENCE. NEW ORLEANS, LA, APRIL 11 16, 1999, IEEE TRANSMISSION AND DISTRIBUTION CONFERENCE, NEW YORK, NY : IEEE, US, vol. VOL. 1, 11 April 1999 (1999-04-11), pages 320 - 325, XP000955041, ISBN: 0-7803-5516-4 * |
Also Published As
Publication number | Publication date |
---|---|
DE102004048235A1 (de) | 2006-04-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP1748529B1 (fr) | Procédé et système pour le pronostic des quantités d'énergie demandées par un consommateur, en particulier un consommateur industriel, à un producteur ou fournisseur d'énergie, et dispositif pour le pronostic de ces besoins en énergie | |
DE602005002839T2 (de) | Ablaufplanung von industriellen produktionsprozessen | |
DE102010048409A1 (de) | Verfahren und Vorrichtung zur Optimierung eines Produktionsprozesses | |
DE10146398A1 (de) | System zum Steuern von Lichtsignalgebern an Kreuzungen | |
DE102015206510A1 (de) | Koordination eines Leistungsaustauschs zwischen einem Verbraucher und einem Versorgungsnetz unter Verwendung von Energiebedarfs-/Energieerzeugungsprognosen | |
WO2013143585A1 (fr) | Procédé et dispositif d'aide à la constitution d'une séquence de commande à bon rendement énergétique | |
WO2006037732A1 (fr) | Procede pour pronostiquer la consommation d'energie d'une installation de production industrielle, dispositif pour mettre ledit procede en oeuvre et progiciel correspondant et support pouvant etre lu par ordinateur | |
DE102011081547A1 (de) | Einstellung einer industriellen Anlage | |
EP3635651B1 (fr) | Procédé pour faire fonctionner une pluralité d'unités techniques en tant qu'ensemble sur un réseau de distribution électrique, ainsi que dispositif de commande et dispositif électrique | |
EP2577829B1 (fr) | Procédé et dispositif pour adapter un plan de déroulement de production pour un processus de production | |
Li | Design and analysis of robust kanban system in an uncertain environment | |
DE102018213862A1 (de) | Verfahren zum Steuern eines Austauschs von Energie zwischen Energiesubsystemen zu angeglichenen Konditionen; Steuerungszentrale; Energiesystem; Computerprogramm sowie Speichermedium | |
EP2120118A1 (fr) | Procédé destiné au fonctionnement d'une installation technique de procédé | |
EP3352326A1 (fr) | Système de génération d'informations en temps réel et de prévision de réglage de la puissance en fonction de la congestion du réseau dans un réseau électrique | |
DE102004048236B4 (de) | Verfahren zur Prognose des Energieverbrauchs einer industriellen Produktionsanlage, Computervorrichtung zum Durchführen des Verfahrens sowie zugehöriges Computerprogramm-Produkt und computerlesbares Medium | |
EP3528063B1 (fr) | Procédé de création assistée par ordinateur d'un modèle pronostique destiné au pronostic d'une ou plusieurs grandeurs cibles | |
EP3909011A1 (fr) | Création efficace d'une configuration de bâtiment | |
EP2808977A2 (fr) | Système de stabilisation de réseaux d'électricité | |
WO2004015599A1 (fr) | Procede de commande assistee par ordinateur de processus de production | |
EP1093038B1 (fr) | Dispositif et procédé de traitement des données importantes pour contrôler le processus d'une installation technique | |
EP4012514A1 (fr) | Procédé de génération d'un plan opérationnel de commande des composants énergétiques d'une infrastructure de bâtiment | |
EP4312096A1 (fr) | Procédé d'estimation d'une consommation d'énergie lors d'une génération d'un produit, produit programme informatique, support d'enregistrement lisible par ordinateur et dispositif électronique de calcul | |
DE112021006498T5 (de) | Teilebeschaffungsrisiko-und wertberechnungsvorrichtung und teilebeschaffungsrisiko-und wertberechnungsprogramm | |
DE102021210234A1 (de) | System, Verfahren und Computerprogramm zur Optimierung eines Herstellungsprozesses in einer industriellen Produktionsanlage, insbesondere einer Anlage der metallerzeugenden Industrie, der nicht-Eisen- oder Stahlindustrie oder der Vorlegierungsherstellung | |
AT503313A2 (de) | Verfahren zur selektion der einflussgrössen eines prognoseverfahrens |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KM KP KR KZ LC LK LR LS LT LU LV LY MA MD MG MK MN MW MX MZ NA NG NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU LV MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
DPEN | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed from 20040101) | ||
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 05794642 Country of ref document: EP Kind code of ref document: A1 |