WO1999013999A1 - Method and device for cooling metals in a metal works - Google Patents
Method and device for cooling metals in a metal works Download PDFInfo
- Publication number
- WO1999013999A1 WO1999013999A1 PCT/DE1998/002602 DE9802602W WO9913999A1 WO 1999013999 A1 WO1999013999 A1 WO 1999013999A1 DE 9802602 W DE9802602 W DE 9802602W WO 9913999 A1 WO9913999 A1 WO 9913999A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- temperature
- metal
- cooling
- strip
- temperature model
- Prior art date
Links
- 238000001816 cooling Methods 0.000 title claims abstract description 51
- 229910052751 metal Inorganic materials 0.000 title claims abstract description 43
- 239000002184 metal Substances 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 19
- 150000002739 metals Chemical class 0.000 title description 2
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 24
- 239000010959 steel Substances 0.000 claims abstract description 24
- 238000005096 rolling process Methods 0.000 claims abstract description 5
- 238000013528 artificial neural network Methods 0.000 claims description 23
- 239000000956 alloy Substances 0.000 claims description 9
- 229910045601 alloy Inorganic materials 0.000 claims description 9
- 239000002826 coolant Substances 0.000 claims description 7
- 239000000498 cooling water Substances 0.000 claims description 5
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 3
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 claims description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 claims description 3
- RTAQQCXQSZGOHL-UHFFFAOYSA-N Titanium Chemical compound [Ti] RTAQQCXQSZGOHL-UHFFFAOYSA-N 0.000 claims description 3
- 229910052799 carbon Inorganic materials 0.000 claims description 3
- 229910052804 chromium Inorganic materials 0.000 claims description 3
- 239000011651 chromium Substances 0.000 claims description 3
- WPBNNNQJVZRUHP-UHFFFAOYSA-L manganese(2+);methyl n-[[2-(methoxycarbonylcarbamothioylamino)phenyl]carbamothioyl]carbamate;n-[2-(sulfidocarbothioylamino)ethyl]carbamodithioate Chemical compound [Mn+2].[S-]C(=S)NCCNC([S-])=S.COC(=O)NC(=S)NC1=CC=CC=C1NC(=S)NC(=O)OC WPBNNNQJVZRUHP-UHFFFAOYSA-L 0.000 claims description 3
- 229910052758 niobium Inorganic materials 0.000 claims description 3
- 239000010955 niobium Substances 0.000 claims description 3
- GUCVJGMIXFAOAE-UHFFFAOYSA-N niobium atom Chemical compound [Nb] GUCVJGMIXFAOAE-UHFFFAOYSA-N 0.000 claims description 3
- 229910052710 silicon Inorganic materials 0.000 claims description 3
- 239000010703 silicon Substances 0.000 claims description 3
- 239000010936 titanium Substances 0.000 claims description 3
- 229910052719 titanium Inorganic materials 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 abstract 1
- 230000006978 adaptation Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
- B21B37/74—Temperature control, e.g. by cooling or heating the rolls or the product
- B21B37/76—Cooling control on the run-out table
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D11/00—Process control or regulation for heat treatments
- C21D11/005—Process control or regulation for heat treatments for cooling
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D9/00—Heat treatment, e.g. annealing, hardening, quenching or tempering, adapted for particular articles; Furnaces therefor
- C21D9/52—Heat treatment, e.g. annealing, hardening, quenching or tempering, adapted for particular articles; Furnaces therefor for wires; for strips ; for rods of unlimited length
- C21D9/54—Furnaces for treating strips or wire
- C21D9/56—Continuous furnaces for strip or wire
- C21D9/573—Continuous furnaces for strip or wire with cooling
Definitions
- the invention relates to a method and a device for cooling steel strips at the exit of a finishing block in a rolling mill, the cooling being carried out by means of a temperature model of the steel strip to be cooled or the cooling device.
- a temperature model of the steel strip to be cooled or the cooling device To e.g. To regulate the outlet temperature of a steel strip, it is necessary to predict the expected outlet temperature for a given cooling by means of a temperature model and to regulate the cooling with this predicted value. A control intervention to influence the outlet temperature at the point in time at which the outlet temperature can be measured is no longer possible, because at this point the metal has already left the cooling section.
- the quality of the temperature control essentially depends on the precision of the values supplied by the temperature model. It is therefore important that the temperature model models the thermal conditions in the metal and the cooling process well. However, it has been shown that with the large number of parameters of such a temperature model, a good adaptation to the real cooling conditions is very difficult.
- the object is achieved according to the invention by a method according to claim 1 or a device according to claim 11.
- the cooling is set as a function of the temperature of the metal or steel strip in such a way that it reaches a desired target temperature, and the temperature of the metal or steel strip is determined using a temperature model or is estimated, and the parameters of the temperature model, in particular heat transfer coefficients, specific heat and thermal conductivity of the metal or correction values for parameters of the temperature model, are determined by means of a neural network. In this way, the parameters of the cooling model can be calculated particularly precisely. If the cooling is set as a function of the outlet temperature of the metal or steel strip from the finished block, which is determined or estimated using the temperature model, this results in a particularly precise regulation of the outlet temperature of the metal or steel strip.
- correction values for the parameters of the temperature model are determined instead of the parameters of the temperature model, it has proven to be particularly advantageous to multiply correction values for the parameters of the temperature model by the corresponding parameters of the temperature model, the result being a corrected parameter of the temperature model.
- corrected parameters of the temperature model can also be determined directly by the neural network.
- the neural network forms the parameters of the temperature model or the correction values for the parameters of the temperature model as a function of at least one of the sizes strip thickness, strip width, strip temperature before the cooling section, strip temperature after the cooling section, strip speed, temperature of the coolant, in particular cooling water , and the sum of the alloy proportions, carbon, manganese, chromium, silicon, niobium and titanium being taken into account in particular. It has also proven to be advantageous to adapt the neural network to the actual process by means of online adaptation.
- the method according to the invention and the device according to the invention have proven to be particularly advantageous when used for the cooling of metal sheets which are wound onto a reel after they have left a cooling section, since it is particularly important during reeling that the reeled-up metal has the right temperature. If there are too large deviations from the desired target temperature, the quality of the metal is impaired.
- FIG. 1 shows a device for cooling a metal strip 2 shows an advantageous structure of the cooling method according to the invention
- FIG. 1 shows a device for cooling a steel or metal strip 1, 2, 3, which runs out of a finishing train 8 in the direction of the arrow identified by reference number 4 and that is wound on a reel 5.
- a cooling section which has cooling nozzle arrangements 6 and 7, lies between the finishing train 8 and the reel 5. Coolant, in particular water, emerges from the cooling nozzles, by means of which the steel strip 1, 2, 3 is cooled.
- the cooling nozzle blocks 6 and 7 are controlled or regulated by means of a computing device 90 to which they are connected by means of a data line 92.
- the computing device 90 also receives measured values about the outlet temperature of the metal strips 3, which is measured by means of a measuring device 91.
- the computing device 90 can be made in one or more pieces.
- the regulation or control of the outlet temperature of the metal strip is a temperature model, a neural network for correcting selected parameters of the temperature model and the adaptation of a neural network for correcting parameters of the temperature model on one and the same hardware Platform implemented.
- these tasks are only partially implemented on the same hardware. It is advantageously provided that all parameters of the temperature model are not necessarily corrected by means of the neural network. In some cases it is sufficient to correct only a few parameters of the correction model, in particular the heat transfer coefficient between metal and coolant. Provision can also be made to optimize the temperature model beforehand using genetic algorithms.
- a cooling section 16, into which metal 17 runs and cooled metal 18 runs out, is regulated by means of a control 9, which specifies setpoints 13 for cooling. These setpoints 13 for the cooling are regulated by the control 9 as a function of the desired setpoint outlet temperature 19 of the cooled metal 18 and an estimated outlet temperature 10 of the metal 18.
- the estimated outlet temperature 10 is determined by means of a temperature model 11 as a function of the setpoints 13 for cooling.
- the parameters of the temperature model are corrected using correction values 14 or corrected parameters 14 of the temperature model 11 are determined. All parameters of the temperature model 11 can be corrected. However, it has proven to be advantageous to correct only a selection of parameters of the temperature model 11.
- the correction values 14 of the parameters of the temperature model 11 are formed as a function of the input variables 15 of a neural network 12.
- the input variables 15 of the neural network can be parameters of the metal or the cooling section, such as the strip thickness, the strip width, the strip temperature before the cooling section, the strip temperature after the cooling section, the strip speed, the temperature of the cooling water, alloy fractions, in particular of carbon, manganese, Chromium, silicon, niobium or titanium, as well as the sum of all alloys.
- the parameters can be measured variables, such as the strip temperature before the cooling section, the strip temperature after the cooling section or the temperature of the cooling water, or data that come from a higher-level system and are stored, for example, in pass schedules.
- Such sizes which are known to a higher-level system, are, for example, the strip thickness, the strip width, the strip speed and the alloy proportions.
- the neural network has a layer with input nodes 20, a layer with hidden nodes 21 and a layer with output nodes 22.
- the inputs for the input nodes 20 can be the bandwidth, the strip thickness, the strip temperature before the cooling section, the strip temperature after the cooling section, the strip speed and the alloy components.
- An output node 22 is provided in the present exemplary embodiment. This outputs, for example, a corrected heat transfer coefficient or a corresponding correction value.
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Control Of Metal Rolling (AREA)
- Heat Treatment Of Strip Materials And Filament Materials (AREA)
Abstract
The invention relates to a method and a device for cooling metal or steel strips at the exit of a finishing block of a rolling mill. According to the invention, the cooling is adjusted according to the temperature of the metal or steel strip, in such a way that said band reaches a desired temperature. The temperature of the metal or steel strip is determined or predicted using a temperature model. The parameters of said temperature model, especially the heat transfer coefficients, the specific heat and the heat conductivity of the metal, or corrected values for parameters of the temperature model are determined by means of a neuronal network.
Description
Beschreibung description
Verfahren und Einrichtung zur Kühlung von Metallen m einem HüttenwerkMethod and device for cooling metals in a steel mill
Die Erfindung betrifft ein Verfahren bzw. eine Einrichtung zur Kühlung von Stahlbandern am Ausgang eines Fertigblocks in einer Walzstraße, wobei die Kühlung mittels eines Temperaturmodells des zu kühlenden Stahlbandes bzw. der Kühlemπchtung erfolgt. Um z.B. die Auslauftemperatur eines Stahlbandes zu regeln ist es notwendig, die zu erwartende Auslauftemperatur bei vorgegebener Kühlung mittels eines Temperaturmodells vorherzusagen und mit diesem Vorhersagewert die Kühlung zu regeln. Ein Regeleingriff zur Beeinflussung der Auslauf empera- tur zu dem Zeitpunkt, an dem die Auslauftemperatur meßbar ist, ist nicht mehr möglich, denn zu diesem Zeitpunkt hat das Metall bereits die Kuhlstrecke verlassen.The invention relates to a method and a device for cooling steel strips at the exit of a finishing block in a rolling mill, the cooling being carried out by means of a temperature model of the steel strip to be cooled or the cooling device. To e.g. To regulate the outlet temperature of a steel strip, it is necessary to predict the expected outlet temperature for a given cooling by means of a temperature model and to regulate the cooling with this predicted value. A control intervention to influence the outlet temperature at the point in time at which the outlet temperature can be measured is no longer possible, because at this point the metal has already left the cooling section.
Es hat sich gezeigt, daß die Qualität der Temperaturregelung wesentlich von der Präzision der von dem Temperaturmodell gelieferten Werte abhangt. Deshalb ist es wichtig, daß das Temperaturmodell die thermischen Verhaltnisse m Metall sowie des Kühlvorgangs gut modelliert. Es hat sich jedoch gezeigt, daß bei der Vielzahl der Parameter eines derartigen Tempera- turmodells eine gute Adaption an die realen Kühlverhältnisse sehr schwierig ist.It has been shown that the quality of the temperature control essentially depends on the precision of the values supplied by the temperature model. It is therefore important that the temperature model models the thermal conditions in the metal and the cooling process well. However, it has been shown that with the large number of parameters of such a temperature model, a good adaptation to the real cooling conditions is very difficult.
Entsprechend ist es Aufgabe der Erfindung, ein Verfahren bzw. eine Einrichtung anzugeben, die es ermöglicht, die Kühlung von Stahlb ndern am Ausgang eines Fertigblocks derart zu verbessern, daß die Abweichung der Temperatur des Metalls von einer gewünschten Solltemperatur gegenüber dem bekannten Kuhlverfahren verringert wird. So ist es z.B. wünschenswert, die Abweichung der Auslauftemperatur eines Metalls aus einer
Kühlstrecke von einer vorgegebenen gewünschten Solltemperatur möglichst gering zu halten.Accordingly, it is an object of the invention to provide a method or a device which makes it possible to improve the cooling of steel strips at the exit of a finished block in such a way that the deviation of the temperature of the metal from a desired target temperature is reduced compared to the known cooling method. For example, it is desirable to measure the deviation of a metal's outlet temperature from a To keep the cooling section as low as possible from a predetermined desired temperature.
Die Aufgabe wird erfindungsgemäß durch ein Verfahren gemäß Anspruch 1 bzw eine Einrichtung gemäß Anspruch 11 gelost.The object is achieved according to the invention by a method according to claim 1 or a device according to claim 11.
Dabei wird zur Kühlung von Metall- bzw. Stahlbändern am Ausgang eines Fertigblocks einer Walzstraße die Kühlung m Abhängigkeit der Temperatur des Metall- oder Stahlbandes derart eingestellt, daß es eine gewünschte Solltemperatur erreicht, und wobei die Temperatur des Metall- oder Stahlbandes mittels eines Temperaturmodells ermittelt bzw. vorausgeschätzt wird, und wobei die Parameter des Temperaturmodells, insbesondere Warmeübergangskoefflzienten, spezifische Wärme und Wärmeleit- fahigkeit des Metalls bzw. Korrekturwerte für Parameter des Temperaturmodells, mittels eines neuronalen Netzes ermittelt werden. Auf diese Weise lassen sich die Parameter des Kühlmodells besonders präzise errechnen. Wird die Kühlung m Abhängigkeit der Auslauftemperatur des Metall- bzw. Stahlbandes aus dem Fertigblock, die mittels des Temperaturmodells ermittelt bzw. vorausgeschätzt wird, eingestellt, so ergibt sich eine besonders präzise Regelung der Auslauftemperatur des Metall- bzw. Stahlbandes.To cool metal or steel strips at the exit of a finishing block of a rolling mill, the cooling is set as a function of the temperature of the metal or steel strip in such a way that it reaches a desired target temperature, and the temperature of the metal or steel strip is determined using a temperature model or is estimated, and the parameters of the temperature model, in particular heat transfer coefficients, specific heat and thermal conductivity of the metal or correction values for parameters of the temperature model, are determined by means of a neural network. In this way, the parameters of the cooling model can be calculated particularly precisely. If the cooling is set as a function of the outlet temperature of the metal or steel strip from the finished block, which is determined or estimated using the temperature model, this results in a particularly precise regulation of the outlet temperature of the metal or steel strip.
Werden anstelle der Parameter des Temperaturmodells Korrekturwerte für die Parameter des Temperaturmodells bestimmt, so hat es sich als besonders vorteilhaft erwiesen, Korrekturwerte für die Parameter des Temperaturmodells mit den entsprechenden Parametern des Temperaturmodells zu multiplizieren, wobei das Ergebnis ein korrigierter Parameter des Temperaturmodells ist. Alternativ können korrigierte Parameter des Temperaturmodells auch direkt durch das neuronale Netz ermittelt werden .
In vorteilhafter Ausgestaltung der Erfindung bildet das neuronale Netz die Parameter des Temperaturmodells bzw. die Korrekturwerte für die Parameter des Temperaturmodells in Abhängigkeit zumindest einer der Größen Banddicke, Bandbreite, Bandtemperatur vor der Kühlstrecke, Bandtemperatur nach der Kühlstrecke, Bandgeschwindigkeit, Temperatur des Kühlmittels, insbesondere Kühlwassers, sowie der Summe der Legierungsanteile, wobei insbesondere Kohlenstoff, Mangan, Chrom, Silizium, Niob und Titan berücksichtigt werden. Es hat sich weiter- hin als vorteilhaft erwiesen, das neuronale Netz durch online Adaption an das tatsächliche Prozeßgeschehen zu adaptieren .If correction values for the parameters of the temperature model are determined instead of the parameters of the temperature model, it has proven to be particularly advantageous to multiply correction values for the parameters of the temperature model by the corresponding parameters of the temperature model, the result being a corrected parameter of the temperature model. Alternatively, corrected parameters of the temperature model can also be determined directly by the neural network. In an advantageous embodiment of the invention, the neural network forms the parameters of the temperature model or the correction values for the parameters of the temperature model as a function of at least one of the sizes strip thickness, strip width, strip temperature before the cooling section, strip temperature after the cooling section, strip speed, temperature of the coolant, in particular cooling water , and the sum of the alloy proportions, carbon, manganese, chromium, silicon, niobium and titanium being taken into account in particular. It has also proven to be advantageous to adapt the neural network to the actual process by means of online adaptation.
Das erfindungsgemäße Verfahren bzw. die erfindungsgemäße Ein- richtung hat sich besonders vorteilhaft bei der Verwendung für die Kühlung von Blechen, die nach Auslauf aus einer Kühlstrecke auf einen Haspel aufgehaspelt werden, erwiesen, da es beim Haspeln besonders wichtig ist, daß das aufgehaspelte Metall die richtige Temperatur hat. Bei zu großen Ab- weichungen von der gewünschten Solltemperatur kommt es zu Beeinträchtigungen der Qualität des Metalls.The method according to the invention and the device according to the invention have proven to be particularly advantageous when used for the cooling of metal sheets which are wound onto a reel after they have left a cooling section, since it is particularly important during reeling that the reeled-up metal has the right temperature. If there are too large deviations from the desired target temperature, the quality of the metal is impaired.
Weitere Vorteile und Einzelheiten ergeben sich aus der nachfolgenden Beschreibung eines Ausführungsbeispiels, anhand der Zeichnungen und in Verbindung mit den Unteransprüchen. Im einzelnen zeigen:Further advantages and details emerge from the following description of an exemplary embodiment, using the drawings and in conjunction with the subclaims. In detail show:
FIG 1 eine Einrichtung zum Kühlen eines Metallbandes FIG 2 eine vorteilhafte Struktur des erfindungsgemäßen Kühlverfahrens1 shows a device for cooling a metal strip 2 shows an advantageous structure of the cooling method according to the invention
FIG 3 ein neuronales Netz3 shows a neural network
FIG 1 zeigt eine Einrichtung zum Kühlen eines Stahl- bzw. Metallbandes 1, 2, 3, das aus einer Fertigstraße 8 in Richtung des mit Bezugszeichen 4 gekennzeichneten Pfeils ausläuft und
das auf einen Haspel 5 aufgewickelt wird. Zwischen der Fer- tigstraße 8 und dem Haspel 5 liegt eine Kühlstrecke, die Kühldüsenanordnungen 6 und 7 aufweist. Aus den Kühldüsen tritt Kühlmittel, insbesondere Wasser, aus, mittels dessen das Stahlband 1, 2, 3 gekühlt wird. Die Kühldüsenblöcke 6 und 7 werden mittels einer Recheneinrichtung 90, mit der sie mittels einer Datenleitung 92 verbunden sind, gesteuert oder geregelt. Dazu erhält die Recheneinrichtung 90 außerdem Meßwerte über die Auslauftemperatur der Metallbänder 3, die mittels eines Meßgeräts 91 gemessen wird. Die Recheneinrichtung 90 kann ein- oder mehrstückig ausgeführt sein. Bei einstückiger Ausführung der Recheneinrichtung 90 ist die Regelung bzw. die Steuerung der Auslauftemperatur des Metallbandes , ein Temperaturmodell, ein neuronales Netz zur Korrektur von ausgewahl- ten Parametern des Temperaturmodells sowie die Adaption eines neuronalen Netzes zur Korrektur von Parametern des Temperaturmodells auf ein und derselben Hardware-Plattform implementiert. Es kann jedoch auch vorgesehen werden, diese Aufgaben nur zum Teil auf ein und derselben Hardware zu implementie- ren . Vorteilhafterweise wird vorgesehen, nicht zwingend alle Parameter des Temperaturmodells mittels des neuronalen Netzes zu korrigieren. Es ist zum Teil ausreichend, nur einige Parameter des Korrekturmodells, insbesondere den Wärmeübergangs- koeffizienten zwischen Metall und Kühlmittel zu korrigieren. Ferner kann vorgesehen werden, das Temperaturmodell mittels genetischer Algorithmen vorweg zu optimieren.1 shows a device for cooling a steel or metal strip 1, 2, 3, which runs out of a finishing train 8 in the direction of the arrow identified by reference number 4 and that is wound on a reel 5. A cooling section, which has cooling nozzle arrangements 6 and 7, lies between the finishing train 8 and the reel 5. Coolant, in particular water, emerges from the cooling nozzles, by means of which the steel strip 1, 2, 3 is cooled. The cooling nozzle blocks 6 and 7 are controlled or regulated by means of a computing device 90 to which they are connected by means of a data line 92. For this purpose, the computing device 90 also receives measured values about the outlet temperature of the metal strips 3, which is measured by means of a measuring device 91. The computing device 90 can be made in one or more pieces. In the case of a one-piece design of the computing device 90, the regulation or control of the outlet temperature of the metal strip is a temperature model, a neural network for correcting selected parameters of the temperature model and the adaptation of a neural network for correcting parameters of the temperature model on one and the same hardware Platform implemented. However, it can also be provided that these tasks are only partially implemented on the same hardware. It is advantageously provided that all parameters of the temperature model are not necessarily corrected by means of the neural network. In some cases it is sufficient to correct only a few parameters of the correction model, in particular the heat transfer coefficient between metal and coolant. Provision can also be made to optimize the temperature model beforehand using genetic algorithms.
FIG 2 zeigt die Struktur des erfindungsgemäßen Kühlverfahrens. Dabei wird eine Kühlstrecke 16, in die Metall 17 ein- läuft und gekühltes Metall 18 hinausläuft, mittels einer Regelung 9 geregelt, die Sollwerte 13 für die Kühlung vorgibt. Diese Sollwerte 13 für die Kühlung werden von der Regelung 9 in Abhängigkeit der gewünschten Sollauslauf emperatur 19 des gekühlten Metalls 18 und einer geschätzten Auslauftemperatur 10 des Metalls 18 geregelt. Die geschätzte Auslauftemperatur
10 wird mittels eines Temperaturmodells 11 in Abhängigkeit der Sollwerte 13 für die Kühlung ermittelt. Die Parameter des Temperaturmodells werden mittels Korrekturwerten 14 korrigiert oder es werden korrigierte Parameter 14 des Temperatur- modells 11 ermittelt. Dabei können alle Parameter des Te pe- raturmodells 11 korrigiert werden. Es hat sich jedoch als vorteilhaft erwiesen, nur eine Auswahl von Parametern des Temperaturmodells 11 zu korrigieren. Besonders vorteilhaft ist es, den Wärmeübergangskoeffizienten von Metall, insbeson- dere Stahl, zum Kühlmittel Wasser zu korrigieren. In Ergänzung ist es vorteilhaft, auch die spezifische Wärme des Metalls bzw. des Kühlmittels sowie die Wärmeleitfähigkeit des Metalls zu korrigieren. Die Korrekturwerte 14 der Parameter des Temperaturmodells 11 werden in Abhängigkeit der Eingangs- großen 15 eines neuronalen Netzes 12 gebildet. Die Eingangsgrößen 15 des neuronalen Netzes können Kenngrößen des Metalls oder der Kühlstrecke sein, wie die Banddicke, die Bandbreite, die Bandtemperatur vor der Kühlstrecke, die Bandtemperatur nach der Kühlstrecke, die Bandgeschwindigkeit, die Temperatur des Kühlwassers, Legierungsanteile, insbesondere von Kohlenstoff, Mangan, Chrom, Silizium, Niob oder Titan, sowie die Summe aller Legierungen. Die Kenngrößen können Meßgrößen sein, wie z.B. die Bandtemperatur vor der Kühlstrecke, die Bandtemperatur nach der Kühlstrecke oder die Temperatur des Kühlwasser, oder Daten, die von einem übergeordneten System stammen und z.B. in Stichplänen abgelegt sind. Derartige Größen, die einem übergeordneten System bekannt sind, sind z.B. die Banddicke, die Bandbreite, die Bandgeschwindigkeit und die Legierungsanteile. Es hat sich aber auch gezeigt, daß an- stelle der Meßwerte für Bandtemperatur vor der Kühlstrecke und Temperatur des Kühlwassers entsprechende in einem übergeordneten System bekannte Sollwerte verwendet werden können.2 shows the structure of the cooling method according to the invention. A cooling section 16, into which metal 17 runs and cooled metal 18 runs out, is regulated by means of a control 9, which specifies setpoints 13 for cooling. These setpoints 13 for the cooling are regulated by the control 9 as a function of the desired setpoint outlet temperature 19 of the cooled metal 18 and an estimated outlet temperature 10 of the metal 18. The estimated outlet temperature 10 is determined by means of a temperature model 11 as a function of the setpoints 13 for cooling. The parameters of the temperature model are corrected using correction values 14 or corrected parameters 14 of the temperature model 11 are determined. All parameters of the temperature model 11 can be corrected. However, it has proven to be advantageous to correct only a selection of parameters of the temperature model 11. It is particularly advantageous to correct the heat transfer coefficient of metal, in particular steel, to the coolant water. In addition, it is advantageous to also correct the specific heat of the metal or the coolant and the thermal conductivity of the metal. The correction values 14 of the parameters of the temperature model 11 are formed as a function of the input variables 15 of a neural network 12. The input variables 15 of the neural network can be parameters of the metal or the cooling section, such as the strip thickness, the strip width, the strip temperature before the cooling section, the strip temperature after the cooling section, the strip speed, the temperature of the cooling water, alloy fractions, in particular of carbon, manganese, Chromium, silicon, niobium or titanium, as well as the sum of all alloys. The parameters can be measured variables, such as the strip temperature before the cooling section, the strip temperature after the cooling section or the temperature of the cooling water, or data that come from a higher-level system and are stored, for example, in pass schedules. Such sizes, which are known to a higher-level system, are, for example, the strip thickness, the strip width, the strip speed and the alloy proportions. However, it has also been shown that instead of the measured values for the strip temperature upstream of the cooling section and the temperature of the cooling water, corresponding setpoints known in a higher-level system can be used.
FIG 3 zeigt ein neuronales Netz zur Ermittlung von korrigier- ten Parametern 14 des Temperaturmodells 11 bzw. zur Ermitt-
lung von Korrekturwerten 14 für die Parameter des Temperaturmodells. Das neuronale Netz weist eine Schicht mit Eingangs- knoten 20, eine Schicht mit verdeckten Knoten 21 sowie eine Schicht mit Ausgangsknoten 22 auf. Die Eingänge für die Ein- gangsknoten 20 können sein, die Bandbreite, die Banddicke, Bandtemperatur vor der Kühlstrecke, Bandtemperatur nach der Kühlstrecke, Bandgeschwindigkeit sowie Legierungsanteile. Im vorliegenden Ausführungsbeispiel ist ein Ausgangsknoten 22 vorgesehen. Dieser gibt z.B. einen korrigierten Wärmeüber- gangskoeffizienten bzw. einen entsprechenden Korrekturwert aus. Für die Ermittlung mehrerer Parameter des Temperaturmodells bzw. entsprechender Korrekturwerte können separate neuronale Netze mit einem Ausgangsknoten oder ein neuronales Netz mit mehreren Ausgangsknoten vorgesehen werden.
3 shows a neural network for determining corrected parameters 14 of the temperature model 11 or for determining correction values 14 for the parameters of the temperature model. The neural network has a layer with input nodes 20, a layer with hidden nodes 21 and a layer with output nodes 22. The inputs for the input nodes 20 can be the bandwidth, the strip thickness, the strip temperature before the cooling section, the strip temperature after the cooling section, the strip speed and the alloy components. An output node 22 is provided in the present exemplary embodiment. This outputs, for example, a corrected heat transfer coefficient or a corresponding correction value. Separate neural networks with one output node or a neural network with several output nodes can be provided for determining several parameters of the temperature model or corresponding correction values.
Claims
1. Verfahren zur Kühlung eines Metall- bzw. Stahlbandes (1,2,3) am Ausgang eines Fertigblocks (8) einer Walzstraße,1. A method for cooling a metal or steel strip (1, 2, 3) at the exit of a finishing block (8) from a rolling mill,
5 wobei die Kühlung in Abhängigkeit der Temperatur des Metalloder Stahlbandes (1,2,3) derart eingestellt wird, daß es eine gewünschte Solltemperatur (19) erreicht, und wobei die Temperatur des Metall- oder Stahlbandes (1,2,3) mittels eines Temperaturmodells (11) ermittelt oder vorausgeschätzt wird, 0 d a d u r c h g e k e n n z e i c h n e , daß Parameter (14) des Temperaturmodells (11), insbesondere Wärmeübergangskoeffizienten, spezifische Wärme und Wärmeleitfähigkeit des Metalls bzw. Korrekturwerte (14) für Parameter des Temperaturmodells (11) , mittels eines neuronalen Netzes 5 (12) ermittelt werden.5 wherein the cooling as a function of the temperature of the metal or steel strip (1,2,3) is set such that it reaches a desired target temperature (19), and wherein the temperature of the metal or steel strip (1,2,3) by means of a Temperature model (11) is determined or predicted, 0 characterized in that parameters (14) of the temperature model (11), in particular heat transfer coefficients, specific heat and thermal conductivity of the metal or correction values (14) for parameters of the temperature model (11), by means of a neural network 5 (12) can be determined.
2. Verfahren nach Anspruch 1, d a d u r c h g e k e n n z e i c h n e t, daß die Kühlung in Abhängigkeit der Auslauftemperatur (10) 0 des Metall- bzw. Stahlbandes (1,2,3) aus dem Fertigblock (8), die mittels des Temperaturmodells (11) ermittelt bzw. vorausgeschätzt wird, erfolgt.2. The method according to claim 1, characterized in that the cooling as a function of the outlet temperature (10) 0 of the metal or steel strip (1,2,3) from the finished block (8), which is determined by means of the temperature model (11) or is estimated.
3. Verfahren nach Anspruch 1 oder 2 , 5 d a d u r c h g e k e n n z e i c h n e t, daß der Korrekturwert (14) für die Parameter des Temperaturmodells (11) mit dem zu korrigierenden Parameter des Tempera- εurmodells (11) multipliziert wird, wobei das Ergebnis ein korrigierter Parameter des Temperaturmodells (11) ist. C3. The method according to claim 1 or 2, 5 characterized in that the correction value (14) for the parameters of the temperature model (11) is multiplied by the parameter of the temperature εur model (11) to be corrected, the result being a corrected parameter of the temperature model ( 11) is. C
4. Verfahren nach Anspruch 1, 2 oder 3, d a u r c h g e k e n n z e i c h n e t, daß das neuronale Netz (12) den korrigierten Parameter (14) des Temperaturmodells (11) bzw. den Korrekturwert (14) für den Parameter des Temperaturmodells (11) in Abhängigkeit zu-
mindest einer der Größen (15) Banddicke, Bandbreite, Bandtemperatur vor der Kuhlstrecke, Bandtemperatur nach der Kühlstrecke, Bandgeschwindigkeit, Temperatur des Kuhlmittels, insbesondere Kühlwassers, sowie der Summe der Legierungsan- teile bildet.4. The method according to claim 1, 2 or 3, characterized in that the neural network (12) the corrected parameter (14) of the temperature model (11) or the correction value (14) for the parameter of the temperature model (11) depending on forms at least one of the sizes (15) strip thickness, strip width, strip temperature before the cooling section, strip temperature after the cooling section, strip speed, temperature of the cooling agent, in particular cooling water, and the sum of the alloy proportions.
5. Verfahren nach Anspruch 1 oder 4, d a d u r c h g e k e n n z e i c h n e t, daß das neuronale Netz (12) den korrigierten Parameter (14) des Temperaturmodells (11) bzw. den Korrekturwert (14) für den Parameter des Temperaturmodells (11) m Abhängigkeit der wichtigsten Legierungsanteile, insbesondere Kohlenstoff, Mangan, Chrom, Silizium, Niob und Titan, bildet.5. The method according to claim 1 or 4, characterized in that the neural network (12) the corrected parameter (14) of the temperature model (11) or the correction value (14) for the parameter of the temperature model (11) as a function of the most important alloy components, especially carbon, manganese, chromium, silicon, niobium and titanium.
6. Verfahren nach Anspruch 4 oder 5, d a d u r c h g e k e n n z e i c h n e t, daß das neuronale Netz (12) den korrigierten Parameter (14) des Temperaturmodells (11) bzw. den Korrekturwert (14) für den Parameter des Temperaturmodells m Abhängigkeit der Band- breite, der Banddicke, der Bandgeschwindigkeit, der Temperatur des Kuhlmediums sowie der wichtigsten Legierungsanteilen bildet .6. The method according to claim 4 or 5, characterized in that the neural network (12) the corrected parameter (14) of the temperature model (11) or the correction value (14) for the parameter of the temperature model m depending on the bandwidth, the band thickness , the belt speed, the temperature of the cooling medium and the most important alloy components.
7. Verfahren nach Anspruch 6, a d u r c g e k e n n z e i c h n e t, daß das neuronale Netz (12) den korrigierten Parameter (14) des Temperaturmodells (11) bzw. den Korrekturwert (14) für den Parameter des Temperaturmodells (11) m Abhängigkeit der Bandtemperatur vor der Kuhlstrecke und der Bandtemperatur nach der Kuhlstrecke sowie der Summe aller Legierungsanteile bilde .7. The method according to claim 6, characterized in that the neural network (12) the corrected parameter (14) of the temperature model (11) or the correction value (14) for the parameter of the temperature model (11) depending on the strip temperature before the cooling section and the strip temperature according to the cooling section and the sum of all alloy components.
8. Verfanren nach einem der vorhergehenden Ansprüche, d a d u r c h g e k e n n z e i c h n e , daß das neuronale Netz (12) ein Mutilayer-Percepron ist.
8. Verschanren according to any one of the preceding claims, characterized in that the neural network (12) is a mutilayer percepron.
9. Verfahren nach einem der vorhergehenden Ansprüche, d a d u r c h g e k e n n z e i c h n e t, daß das Metall- bzw. Stahlband (1,2,3) m mehrere Bandab- schnitte, insbesondere 10 Bandabschnitte, unterteilt wird, denen jeweils ein eigenes neuronales Netz (12) zugeordnet wird.9. The method as claimed in one of the preceding claims, that the metal or steel strip (1, 2, 3) m is divided into several strip sections, in particular 10 strip sections, each of which is assigned its own neural network (12).
10. Verfahren nach einem der vorhergehenden Ansprüche, d a d u r c h g e k e n n z e i c h n e t, daß das neuronale Netz (12) durch on-line-Lernen adaptiert wird.10. The method according to any one of the preceding claims, d a d u r c h g e k e n n z e i c h n e t that the neural network (12) is adapted by online learning.
11. Einrichtung zur Kühlung eines Metall- bzw. Stahlbandes (1,2,3) am Ausgang eines Fertigblocks (8) einer Walzstraße, insbesondere zur Durchfuhrung eines Verfahrens nach einem der vorhergehenden Ansprüche, wobei die Kühlung mittels einer Re- chenemrichtung (90) m Abhängigkeit der Temperatur des Metall- oder Stahlbandes (1,2,3) derart eingestellt wird, daß es eine gewünschte Solltemperatur (19) erreicht, und wobei die Temperatur des Metall- oder Stahlbandes (1,2,3) mittels eines auf der Recheneinrichtung (90) implementierten Temperaturmodells (11) ermittelt bzw. vorausgeschätzt wird, d a d u r c h g e k e n n z e i c h n e t, daß die Recheneinrichtung (90) die Parameter des Temperaturmodells (11), insbesondere Warmeubergangskoefflzienten, spezifische Warme und Wärmeleitf higkeit des Metalls bzw. Korrekturwerte für Parameter des Temperaturmodells (11), mittels eines neuronalen Netzes (12) ermittelnd ausgebildet ist.
11. Device for cooling a metal or steel strip (1, 2, 3) at the exit of a finished block (8) of a rolling mill, in particular for carrying out a method according to one of the preceding claims, the cooling being carried out by means of a computing device (90) m depending on the temperature of the metal or steel strip (1,2,3) is set so that it reaches a desired target temperature (19), and wherein the temperature of the metal or steel strip (1,2,3) by means of a Computing device (90) implemented temperature model (11) is determined or estimated, characterized in that the computing device (90) the parameters of the temperature model (11), in particular heat transfer coefficients, specific heat and thermal conductivity of the metal or correction values for parameters of the temperature model (11 ), is designed to be determined by means of a neural network (12).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE19881325T DE19881325D2 (en) | 1997-09-16 | 1998-09-03 | Method and device for cooling metals in a steel mill |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE1997140691 DE19740691A1 (en) | 1997-09-16 | 1997-09-16 | Method and apparatus for metal cooling in steelworks |
| DE19740691.2 | 1997-09-16 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO1999013999A1 true WO1999013999A1 (en) | 1999-03-25 |
Family
ID=7842514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/DE1998/002602 WO1999013999A1 (en) | 1997-09-16 | 1998-09-03 | Method and device for cooling metals in a metal works |
Country Status (2)
| Country | Link |
|---|---|
| DE (2) | DE19740691A1 (en) |
| WO (1) | WO1999013999A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6860950B2 (en) | 2001-06-20 | 2005-03-01 | Siemens Aktiengesellschaft | Method for cooling a hot-rolled material and corresponding cooling-line models |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19963186B4 (en) * | 1999-12-27 | 2005-04-14 | Siemens Ag | Method for controlling and / or regulating the cooling section of a hot strip mill for rolling metal strip and associated device |
| RU2184632C2 (en) * | 2000-07-27 | 2002-07-10 | Морозов Андрей Андреевич | Method for controlling cooling conditions of rolled pieces |
| RU2183522C1 (en) * | 2001-04-26 | 2002-06-20 | Урцев Владимир Николаевич | Method for controlling process of cooling rolled pieces |
| DE10156008A1 (en) * | 2001-11-15 | 2003-06-05 | Siemens Ag | Control method for a finishing train upstream of a cooling section for rolling hot metal strip |
| DE10251716B3 (en) * | 2002-11-06 | 2004-08-26 | Siemens Ag | Modeling process for a metal |
| JP4767544B2 (en) * | 2005-01-11 | 2011-09-07 | 新日本製鐵株式会社 | Steel sheet cooling control method |
| RU2299916C1 (en) * | 2005-11-24 | 2007-05-27 | Общество с ограниченной ответственностью "СЛОТ" | Rolled bar heat treatment process control method in multisectional thermally strengthening plants |
| FR2897620B1 (en) * | 2006-02-21 | 2008-04-04 | Stein Heurtey | METHOD AND DEVICE FOR COOLING AND STABILIZING BAND IN A CONTINUOUS LINE |
| CN101480669B (en) * | 2008-01-07 | 2011-04-13 | 宝山钢铁股份有限公司 | Stelmor line cooling method and cooling apparatus of high-speed rod-rolling mill |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04232214A (en) * | 1990-12-28 | 1992-08-20 | Nippon Steel Corp | Cooling control method and device for steel plate |
| JPH04339511A (en) * | 1991-05-10 | 1992-11-26 | Nippon Steel Corp | Method for cooling and controlling steel plate |
| JPH07214132A (en) * | 1994-02-07 | 1995-08-15 | Nippon Steel Corp | Winding temperature control method for hot rolled steel strip |
| DE19637916A1 (en) * | 1996-09-17 | 1998-03-19 | Siemens Ag | Process and equipment for cooling a hot rolled strand |
| WO1998049354A1 (en) * | 1997-04-25 | 1998-11-05 | Siemens Aktiengesellschaft | Method and device for cooling metals in a steel works |
-
1997
- 1997-09-16 DE DE1997140691 patent/DE19740691A1/en not_active Withdrawn
-
1998
- 1998-09-03 WO PCT/DE1998/002602 patent/WO1999013999A1/en active Application Filing
- 1998-09-03 DE DE19881325T patent/DE19881325D2/en not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04232214A (en) * | 1990-12-28 | 1992-08-20 | Nippon Steel Corp | Cooling control method and device for steel plate |
| JPH04339511A (en) * | 1991-05-10 | 1992-11-26 | Nippon Steel Corp | Method for cooling and controlling steel plate |
| JPH07214132A (en) * | 1994-02-07 | 1995-08-15 | Nippon Steel Corp | Winding temperature control method for hot rolled steel strip |
| DE19637916A1 (en) * | 1996-09-17 | 1998-03-19 | Siemens Ag | Process and equipment for cooling a hot rolled strand |
| WO1998049354A1 (en) * | 1997-04-25 | 1998-11-05 | Siemens Aktiengesellschaft | Method and device for cooling metals in a steel works |
Non-Patent Citations (5)
| Title |
|---|
| AUZINGER D ET AL: "NEUE ENTWICKLUNGEN BEI PROZESSMODELLEN FUER WERMBREITBANDSTRASSEN", STAHL UND EISEN, vol. 116, no. 7, 15 July 1996 (1996-07-15), pages 59 - 65, 131, XP000629440 * |
| PATENT ABSTRACTS OF JAPAN vol. 016, no. 581 (C - 1012) 21 December 1992 (1992-12-21) * |
| PATENT ABSTRACTS OF JAPAN vol. 017, no. 191 (M - 1396) 14 April 1993 (1993-04-14) * |
| PATENT ABSTRACTS OF JAPAN vol. 095, no. 011 26 December 1995 (1995-12-26) * |
| PICHLER R ET AL: "ON-LINE OPTIMISATION OF THE ROLLING PROCESS - A CASE OF NEURAL NETWORKS", STEEL TIMES - INCORPORATING IRON & STEEL, vol. 224, no. 9, September 1996 (1996-09-01), pages 310/311, XP000633287 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6860950B2 (en) | 2001-06-20 | 2005-03-01 | Siemens Aktiengesellschaft | Method for cooling a hot-rolled material and corresponding cooling-line models |
Also Published As
| Publication number | Publication date |
|---|---|
| DE19740691A1 (en) | 1999-03-18 |
| DE19881325D2 (en) | 2000-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE4416364B4 (en) | Method and control device for regulating a process | |
| DE19522494C2 (en) | Process for rolling a metal strip | |
| DE4338608B4 (en) | Method and device for managing a process in a controlled system | |
| DE19881711C5 (en) | Method and device for controlling a metallurgical plant | |
| EP1624982B2 (en) | Method for regulating the temperature of a metal strip, especially for rolling a metal hot strip in a finishing train | |
| EP0813700A1 (en) | Intelligent computerized control system | |
| DE19508476A1 (en) | Control system for a plant in the basic material or processing industry or similar | |
| EP0534221B1 (en) | Control parameter improvement method for industrial installations | |
| DE4416317B4 (en) | Method and control device for controlling a material processing process | |
| WO1999013999A1 (en) | Method and device for cooling metals in a metal works | |
| DE19644132B4 (en) | Method for optimizing the bandwidth distribution at the ends of a strip passing through a rolling train | |
| DE19618995C2 (en) | Method and device for influencing relevant quality parameters, in particular the profile or the flatness of a rolled strip | |
| DE19881041B4 (en) | Method for controlling and presetting a steelworks or parts of a steelworks | |
| WO2004080628A1 (en) | Continuous casting and rolling installation for producing a steel strip | |
| DE102020214643A1 (en) | Process for adjusting the properties of a hot strip with a specific chemical composition in a hot rolling mill | |
| WO1999024183A1 (en) | Process and device for rolling a rolled strip with a variable thickness | |
| EP4061552B1 (en) | Method, control device and rolling mill for the adjustment of an outlet temperature of a metal strip exiting a rolling train | |
| DE19641432C2 (en) | Method and device for the pre-calculation of previously unknown parameters of an industrial process | |
| EP3934822B1 (en) | Method for producing a metallic strip or plate | |
| EP3974073B1 (en) | Rolling taking into account frequency behaviour | |
| EP1030747B1 (en) | Method and assembly for hot-rolling thin strips of steel | |
| DE19850492A1 (en) | Method and device for hot rolling thin steel strips | |
| DE102023211928A1 (en) | Method for operating a rolling mill | |
| DE19727821A1 (en) | Controlling and presetting roll stand or rolling section | |
| DE112022003044T5 (en) | COOLING SYSTEM FOR A ROLLING MILL |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| AK | Designated states |
Kind code of ref document: A1 Designated state(s): AT CN DE KR RU US |
|
| DFPE | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101) | ||
| NENP | Non-entry into the national phase |
Ref country code: KR |
|
| REF | Corresponds to |
Ref document number: 19881325 Country of ref document: DE Date of ref document: 20001026 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 19881325 Country of ref document: DE |