WO2022176366A1 - 鋼板の形状予測方法、形状制御方法、製造方法、形状予測モデルの生成方法、及び製造設備 - Google Patents
鋼板の形状予測方法、形状制御方法、製造方法、形状予測モデルの生成方法、及び製造設備 Download PDFInfo
- Publication number
- WO2022176366A1 WO2022176366A1 PCT/JP2021/046560 JP2021046560W WO2022176366A1 WO 2022176366 A1 WO2022176366 A1 WO 2022176366A1 JP 2021046560 W JP2021046560 W JP 2021046560W WO 2022176366 A1 WO2022176366 A1 WO 2022176366A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- cooling
- steel plate
- shape
- water
- steel sheet
- Prior art date
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 527
- 239000010959 steel Substances 0.000 title claims abstract description 527
- 238000000034 method Methods 0.000 title claims abstract description 91
- 238000004519 manufacturing process Methods 0.000 title claims description 35
- 238000001816 cooling Methods 0.000 claims abstract description 447
- 230000000452 restraining effect Effects 0.000 claims abstract description 86
- 239000000498 cooling water Substances 0.000 claims abstract description 85
- 238000010801 machine learning Methods 0.000 claims abstract description 25
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 151
- 238000005096 rolling process Methods 0.000 claims description 44
- 230000008569 process Effects 0.000 claims description 35
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000005507 spraying Methods 0.000 abstract description 4
- 238000010438 heat treatment Methods 0.000 description 81
- 230000007547 defect Effects 0.000 description 33
- 238000003825 pressing Methods 0.000 description 26
- 230000009466 transformation Effects 0.000 description 22
- 238000010926 purge Methods 0.000 description 19
- 238000009826 distribution Methods 0.000 description 18
- 230000008859 change Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 13
- 238000002347 injection Methods 0.000 description 12
- 239000007924 injection Substances 0.000 description 12
- 239000000463 material Substances 0.000 description 12
- 239000011295 pitch Substances 0.000 description 12
- 238000011144 upstream manufacturing Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 11
- 238000010791 quenching Methods 0.000 description 9
- 230000000171 quenching effect Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000005259 measurement Methods 0.000 description 8
- 230000007246 mechanism Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 238000005098 hot rolling Methods 0.000 description 7
- 239000000203 mixture Substances 0.000 description 7
- 239000000126 substance Substances 0.000 description 6
- 230000008602 contraction Effects 0.000 description 4
- 239000010410 layer Substances 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 239000007921 spray Substances 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 239000002436 steel type Substances 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000005452 bending Methods 0.000 description 2
- 238000009835 boiling Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 229910000734 martensite Inorganic materials 0.000 description 2
- 239000012299 nitrogen atmosphere Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 229910001566 austenite Inorganic materials 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000005489 elastic deformation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003303 reheating Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 238000002791 soaking Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- 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
- C21D9/46—Heat treatment, e.g. annealing, hardening, quenching or tempering, adapted for particular articles; Furnaces therefor for sheet metals
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B45/00—Devices for surface or other treatment of work, specially combined with or arranged in, or specially adapted for use in connection with, metal-rolling mills
- B21B45/02—Devices for surface or other treatment of work, specially combined with or arranged in, or specially adapted for use in connection with, metal-rolling mills for lubricating, cooling, or cleaning
- B21B45/0203—Cooling
-
- 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
- B21B37/28—Control of flatness or profile during rolling of strip, sheets or plates
- B21B37/44—Control of flatness or profile during rolling of strip, sheets or plates using heating, lubricating or water-spray cooling of the product
-
- 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
- C21D1/00—General methods or devices for heat treatment, e.g. annealing, hardening, quenching or tempering
- C21D1/56—General methods or devices for heat treatment, e.g. annealing, hardening, quenching or tempering characterised by the quenching agents
- C21D1/60—Aqueous agents
-
- 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
- C21D8/00—Modifying the physical properties by deformation combined with, or followed by, heat treatment
- C21D8/12—Modifying the physical properties by deformation combined with, or followed by, heat treatment during manufacturing of articles with special electromagnetic properties
- C21D8/1244—Modifying the physical properties by deformation combined with, or followed by, heat treatment during manufacturing of articles with special electromagnetic properties the heat treatment(s) being of interest
-
- 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
- C21D9/0062—Heat-treating apparatus with a cooling or quenching zone
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- B21B37/58—Roll-force control; Roll-gap control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
Definitions
- the present invention relates to a steel plate shape prediction method, shape control method, manufacturing method, shape prediction model generation method, and manufacturing equipment.
- quenching refers to a steel sheet after hot rolling at a temperature equal to or higher than the Ac3 transformation point, which is the completion temperature of austenite transformation, and after cooling after hot rolling, heating again to a temperature equal to or higher than the Ac3 transformation point in a heating furnace or the like. It refers to a heat treatment method in which the steel sheet is rapidly cooled to a temperature below the martensitic transformation start temperature (Ms point) in a cooling facility. Quenching is widely used as a method of manufacturing particularly high-strength steel sheets. Further, quenching without cooling or reheating the hot-rolled steel sheet is particularly called direct quenching. On the other hand, in some cases, a steel sheet once cooled after hot rolling is quenched using a heat treatment facility comprising a heating furnace and a cooling facility located separately from the rolling line.
- a heat treatment facility comprising a heating furnace and a cooling facility located separately from the rolling line.
- FIGS. 9(a) to 9(d) show Typical forms of shape defects.
- Fig. 9(a) shows a shape in which the width direction both ends and the width direction central part of the steel plate have different heights (called a C warp shape or width warp shape), and
- Fig. 9(b) shows A shape in which a wavy shape is seen (referred to as an edge wave shape or an end-extended shape),
- FIG. 9(d) shows a shape obtained by combining these shapes (referred to as a composite shape).
- Patent Document 1 a water cooling device for a steel plate is provided, and the warpage shape of the steel plate during cooling or downstream of the water cooling device is predicted based on the chemical composition of the steel plate and the rolling conditions of the rolling process performed prior to the water cooling of the steel plate. It describes how to do it.
- the warp shape in this case is the C warp shape shown in FIG.
- Patent Literature 2 discloses a steel plate cooling facility that includes a water cooling device that sprays cooling water onto a steel plate and a restraint device that restrains the steel plate being cooled by a plurality of roll pairs, thereby suppressing shape defects of the steel plate.
- Patent Document 2 describes a method of predicting the corrugated shape of a steel sheet according to the speed at which the steel sheet passes through cooling equipment, the cooling rate of the steel sheet, the roll pitch of the restraining device, the thickness and width of the steel sheet. ing.
- the wave shape in this case is the ear wave shape shown in FIG. 9(b).
- Patent Document 3 in a steel plate manufacturing facility equipped with a controlled cooling device as a steel plate water cooling device and a hot straightening machine arranged upstream of the steel plate manufacturing facility, controlled cooling is performed according to the predicted shape of the steel plate after controlled cooling. It describes a method of controlling at least one of the amount of cooling water in the apparatus and the amount of bending in the hot straightening machine to suppress the shape defects of the steel sheet. Further, Patent Document 3 describes prediction of a shape defect of a steel sheet based on the measured cooling stop temperature of the steel sheet, the temperature distribution in the width direction, the front and rear surface temperatures during cooling, and a preset classification table. ing. The shape defects in this case are the C warp shape shown in FIG. 9(a), the selvage shape shown in FIG. 9(b), and the middle stretch shape shown in FIG. 9(c). It is determined which shape defect is based on.
- Patent Document 1 the method described in Patent Document 1 is intended for equipment equipped with only a water cooling device as a steel plate cooling equipment, and although it is considered effective to some extent when there is no steel plate restraining device, cooling equipped with a restraining device There is room for improvement in steel plate shape prediction in equipment. Further, the shape defect to be predicted is the C-warp shape, not the wave shape (edge wave shape or middle elongation shape) that is likely to occur in a thin steel plate.
- Patent Literature 2 describes a method for suppressing the serpentine shape of a steel sheet in a cooling facility equipped with a water cooling device and a restraining device.
- the provision of a restraining device can improve the shape defect of the steel plate to some extent, and the shape defect can be improved by passing the steel plate through the cooling equipment at a predetermined speed.
- the target shape defect is the serpentine shape, and is not intended to suppress the shape defect due to the C-curved shape shown in FIG. 9(a) or the middle stretched shape shown in FIG. 9(c). Therefore, there is room for improvement in suppressing the occurrence of a complex shape as shown in FIG. 9(d).
- Patent Document 3 predicts the shape defects of the steel sheet based on the temperature information of the steel sheet measured in the cooling equipment and a preset classification table.
- non-uniformity in temperature is not the only cause of shape defects in steel sheets that occur in cooling equipment.
- a shape defect of a steel sheet may occur due to volume change due to thermal contraction or phase transformation during cooling of the steel sheet. Therefore, even if a classification table is set based on operational experience, it is not always possible to accurately predict shape defects in steel sheets that appear in various forms due to many causes.
- the present invention has been made in view of the above problems, and its object is to provide a method for predicting the shape of a steel plate that can accurately predict the shape information of the steel plate after passing through the cooling equipment. Another object of the present invention is to provide a method for controlling the shape of a steel plate that can precisely control the shape of a steel plate within an allowable range after passing through cooling equipment. Another object of the present invention is to provide a method for generating a shape prediction model for a steel plate that can accurately predict the shape information of a steel plate after passing through a cooling facility. Another object of the present invention is to provide a steel plate manufacturing method and manufacturing equipment capable of manufacturing a steel plate with good flatness.
- a steel plate shape prediction method includes a water cooling device that cools the steel plate by spraying cooling water on the heated steel plate, a restraining device that restrains the steel plate during cooling with at least one pair of restraining rolls, wherein at least one operation parameter selected from each of the operation parameter of the water cooling device and the operation parameter of the restraint device is input data and passed through the cooling facility Predicting the shape information of the steel plate after passing through the cooling equipment using a shape prediction model generated by machine learning using the shape information of the steel plate after cooling as output data.
- the shape prediction model preferably includes, as the input data, an attribute information parameter selected from the attribute information of the steel plate.
- the operation parameters of the water cooling device preferably include at least one of the cooling water amount, the ratio of the cooling water to upper and lower water amounts, the cooling rate of the steel sheet, and the conveying speed of the steel sheet in the cooling equipment.
- the operating parameters of the restraining device preferably include at least one of the rolling position and rolling force of the restraining rolls.
- the steel plate shape control method according to the present invention uses the steel plate shape prediction method according to the present invention to predict the shape of the steel plate after passing through the cooling equipment, and the predicted shape is within a preset allowable range. resetting at least one operational parameter selected from the operational parameters of the water cooling system and the restraint system such that the
- a steel sheet manufacturing method includes a step of manufacturing a steel sheet using the steel sheet shape control method according to the present invention.
- a steel sheet manufacturing method uses the steel sheet shape prediction method according to the present invention to predict the shape of the steel sheet after passing through the cooling facility, and based on the predicted shape, the steel sheet determining the treatment steps of
- a method for generating a shape prediction model for a steel sheet according to the present invention includes a water cooling device that cools the steel sheet by injecting cooling water onto the heated steel sheet, and restraint that restrains the steel sheet being cooled by at least one pair of restraint rolls.
- a method for generating a steel plate shape prediction model in a steel plate cooling facility comprising: By machine learning using a plurality of learning data, with information including input performance data and shape information of the steel plate after passing through the cooling facility corresponding to the input performance data as output performance data, the cooling facility It includes the step of generating a shape prediction model of the steel plate after passing.
- machine learning it is preferable to use machine learning selected from neural network, decision tree learning, random forest, and support vector regression.
- the steel sheet manufacturing facility includes a water cooling device that cools the steel sheet by injecting cooling water onto the heated steel sheet, and a restraining device that restrains the steel sheet being cooled by at least one pair of restraining rolls. and a shape prediction unit for outputting shape information of the steel plate after passing through the cooling equipment, wherein the shape prediction unit determines the operation parameters of the water cooling device and the operation parameters of the restraint device, respectively.
- a machine learning model in which at least one operation parameter selected from is input data and shape information of the steel sheet after passing through the cooling equipment is output data.
- the steel sheet shape prediction method it is possible to accurately predict the shape information of the steel sheet after it has passed through the cooling equipment.
- the shape of the steel sheet after passing through the cooling equipment can be accurately controlled within an allowable range.
- the shape information of the steel sheet after passing through the cooling equipment can be accurately predicted.
- a steel sheet having good flatness can be manufactured.
- FIG. 1 is a diagram showing a schematic configuration of a heat treatment facility including a steel plate cooling facility, which is an embodiment of the present invention.
- FIG. 2 is a diagram showing the configuration of the cooling equipment shown in FIG.
- FIG. 3 is a block diagram showing the configuration of the control computer shown in FIG.
- FIG. 4 is a block diagram showing the configuration of a shape prediction model generation unit that is one embodiment of the present invention.
- FIG. 5 is a diagram for explaining the configuration of the shape determining unit shown in FIG. 1;
- FIG. 6 is a flow chart showing the flow of shape control processing, which is an embodiment of the present invention.
- FIG. 7 is a diagram in which the pass/fail of the shape of the steel plate obtained by prior confirmation is organized by the conveying speed and the amount of cooling water.
- FIG. 8 is a diagram showing the configuration of the hot rolling line of the example.
- FIG. 9 is a schematic diagram showing the form of a typical shape defect of a steel plate.
- a steel plate shape prediction method, shape control method, manufacturing method, shape prediction model generation method, and manufacturing equipment according to an embodiment of the present invention will be described below with reference to the drawings.
- FIG. 1 is a diagram showing a schematic configuration of a heat treatment facility including a steel plate cooling facility, which is one embodiment of the present invention.
- a heat treatment facility 1 including a steel plate cooling facility which is an embodiment of the present invention, is an off-line type heat treatment facility, and is a heating furnace that heats a steel plate S at a temperature of 100 ° C. or less to a predetermined temperature.
- It has a control computer 10 as a main component.
- the cooling equipment 3 includes a water cooling device 5 that sprays cooling water onto the steel plate S and a restraining device 6 that restrains the steel plate S from above and below during cooling.
- a steel sheet S that has been hot-rolled to a predetermined thickness (eg, 30 mm) and width (eg, 2000 mm) in a hot rolling line located at a location different from the heat treatment facility 1 and cooled to about room temperature. is loaded.
- the steel plate S is heated to a predetermined temperature (eg, 910° C.) in the heating furnace 2 .
- the steel sheet S extracted from the heating furnace 2 is cooled by the cooling equipment 3 while being conveyed by a plurality of table rolls 7 installed on the delivery side of the heating furnace 2 .
- the cooling equipment 3 is drawn larger than the heating furnace 2 in order to explain the cooling equipment 3 in detail.
- the length of the heating furnace 2 is about 60 to 80 m
- the length of the cooling equipment 3 is about 20 to 25 m.
- the steel plate S is extracted from the heating furnace 2 and conveyed at a substantially constant speed until it is cooled by the cooling equipment 3. small. That is, if the heating temperature of the steel sheet S is T0, the distance from the heating furnace 2 to the cooling equipment 3 is L0, and the conveying speed of the steel sheet S is V0, the tip of the steel sheet S is extracted at the temperature T0 and the cooling time is L0/ Cooled through V0.
- the off-line heat treatment equipment since the distance L0 from the heating furnace 2 to the cooling equipment 3 is short, even if the tip of the steel plate S is extracted from the heating furnace 2 and reaches the entrance of the cooling equipment 3, the tail end of the steel plate S The part is kept at a temperature T0 inside the heating furnace 2 . Therefore, the tail end of the steel plate S is extracted at the temperature T0 in the same manner as the tip end, and is cooled after the cooling time L0/V0.
- the off-line heat treatment equipment is advantageous for producing a steel plate with a small in-plane temperature deviation, as opposed to a thin steel plate whose temperature tends to drop due to cooling, and as a result, the flatness of the steel plate S can be improved. is easy to control.
- the heat treatment equipment 1 also includes a thermometer 81 for measuring the temperature of the steel sheet S at the entry side of the heating furnace 2, a thermometer 82 for measuring the cooling start temperature, and a thermometer 83 for measuring the cooling end temperature. may be placed. These temperature measurement results are sent to the control computer 10 as information for setting the heating conditions and cooling conditions of the steel plate S and specifying the operation results.
- the present invention includes a heating facility that heats the steel sheet S, a water cooling device that cools the steel sheet S by injecting cooling water onto the steel sheet S heated by the heating facility, and at least one pair of restraint rolls. and a restraining device for restraining the steel plate S during cooling.
- the present invention can also be applied to on-line heat treatment equipment.
- the steel plate S is heated to a high temperature on the entry side of the cooling equipment, which is the same as in the off-line type cooling equipment.
- the heating furnace 2 is not arranged in the vicinity of the cooling equipment. and the tail end are left to cool. Therefore, the cooling time until the start of cooling is longer for the tail end of the steel plate S than for the tip end. There is a cooling time difference of time L/V. Therefore, even if the temperature of the steel sheet after rolling is uniform, the trailing edge is allowed to cool by the difference in cooling time. temperature distribution tends to occur in the longitudinal direction. For this reason, the on-line type heat treatment equipment is a condition in which the shape defects of the steel sheet S are more likely to occur.
- the shape of the steel plate S on the downstream side of the cooling equipment is predicted at a plurality of locations along the longitudinal direction of the steel plate S by a shape prediction model described later, and the shape that can change in the longitudinal direction of the steel plate S is calculated. It is preferable to change the operating conditions in the cooling equipment 3 as appropriate.
- the cooling facility 3 is a facility that includes a water cooling device 5 and a restraining device 6 that water-cool the steel plate S under predetermined cooling conditions. These configurations will be described in detail with reference to FIG.
- a water cooling device 5 that constitutes the cooling equipment 3 includes a plurality of water cooling nozzles 51a and 51b that are arranged along the conveying direction of the steel plate S so as to form a pair in the vertical direction of the steel plate S. As shown in FIG.
- the water-cooled nozzle 51a jets cooling water W toward the upper surface of the steel plate S downward.
- the water cooling nozzle 51b jets the cooling water W upward toward the lower surface of the steel plate S.
- the water-cooled nozzles 51a and 51b constitute a pair of upper and lower water-cooled nozzles, and a cooling section with this as a unit is called a cooling zone, and a set of one or more cooling zones is called an area.
- the cooling area (the area to be water-cooled by the water cooling device 5) is composed of seven cooling zones, and in the example shown in FIG. 2, the cooling area is composed of four cooling zones.
- the cooling area may be composed of a plurality of cooling zones, and each cooling zone may be separated by an air-cooling section in which no water-cooling nozzles are arranged.
- the water-cooled nozzles 51a and 51b have a cooling flow rate adjustment valve so that the amount of cooling water W sprayed toward the steel plate S from each water-cooled nozzle can be adjusted. This makes it possible to adjust the flow rate of the cooling water injected for each cooling zone. Moreover, it is preferable that the amount of the cooling water W sprayed toward the steel plate S from the water-cooled nozzles 51a and 51b, which are paired vertically, can be adjusted to different values. The amount of cooling water W injected from each water-cooled nozzle is controlled for each water-cooled nozzle by the water-cooled flow control device 11 based on the water amount setting value set by the control computer 10 .
- the operating parameters of the water cooling device 5 include the amount of cooling water W jetted from at least a pair of water cooling nozzles 51a and 51b (cooling water amount) and the speed of the steel sheet S conveyed by the table rolls 7 (conveying speed).
- cooling water amount the amount of cooling water increases, the cooling rate and the amount of temperature drop of the steel sheet S can be increased.
- the smaller the conveying speed of the steel sheet S the larger the amount of temperature decrease of the steel sheet S can be.
- the cooling stop temperature and cooling rate are controlled as cooling conditions for obtaining a desired material quality.
- the operation parameters of the water cooling device 5 include the balance of the amount of cooling water for each cooling zone (for example, increasing the amount of cooling water in the cooling zone on the upstream side and decreasing the amount of cooling water in the cooling zone on the downstream side). is included.
- the balance of the amount of cooling water for each cooling zone can be represented by the ratio of the amount of cooling water injected in each cooling zone. This is because the cooling rate can be controlled according to the temperature range of the steel sheet S.
- the number of cooling zones into which cooling water W is injected may be changed. Different cooling stop temperatures can be controlled with the same cooling rate depending on the number of cooling zones used.
- the cooling zones to be used may be specified using codes or numerical values for determining whether each cooling zone is used or not, and these codes or numerical values may be used as operation parameters of the water cooling device 5 .
- the material of the steel sheet S can be controlled by adjusting the cooling rate by adjusting the amount of cooling water.
- a slit-type nozzle capable of uniformly spraying a large amount of cooling water W in the width direction, or a flat spray nozzle can be used.
- a multi-hole jet nozzle or a mist nozzle may be used.
- the water-cooled nozzles 51a and 51b do not necessarily have to be able to adjust the amount of cooling water for each water-cooled nozzle. This is because if the water cooling device has a plurality of cooling zones, the cooling conditions can be changed by changing the number of cooling zones into which the cooling water W is injected.
- the cooling equipment 3 includes a restraining device 6 having at least a pair of restraining rolls that restrain the steel plate S while the steel plate S is being cooled by the water cooling device 5 .
- a configuration of the restraining device 6 will be described in detail with reference to FIG.
- the restraint device 6 is arranged in the cooling area and installed adjacent to the water cooling zone.
- adjacent means an area where the steel sheet S is directly cooled by the cooling water W jetted from the water-cooled nozzle 51a or the water-cooled nozzle 51b, or an area where the cooling water W rides on the upper surface of the steel sheet S.
- restraint rolls 61 a and 61 b are arranged on the inlet side of the cooling equipment 3 . That is, the restraint rolls 61a and 61b are arranged at positions where the cooling water W jetted from the water-cooled nozzles 51a in the most upstream cooling area becomes water and comes into contact with the restraint roll 61a.
- constraining rolls are arranged at positions where part of the cooling water W jetted from the water-cooled nozzles 51a or 51b comes into contact.
- the restraint roll 61a and the restraint roll 61b are arranged so as to be substantially perpendicular to the conveying direction of the steel plate S so that the steel plate S is restrained by a pair of upper and lower rolls.
- the steel plate S undergoes strain due to thermal contraction and phase transformation during cooling by the water cooling device 5, but the restraint rolls 61a and 61b prevent the steel plate S from buckling due to such strain. installed to restrain the Therefore, it is preferable to arrange the constraining rolls at positions where the steel sheet S is likely to be distorted, and this is the reason why the constraining rolls are arranged adjacent to the water cooling zone.
- the constraining rolls 61a and 61b are installed corresponding to all the cooling zones. It is not always necessary to arrange the restraint rolls 61a, 61b in the zones. In the example shown in FIG. 2, five pairs of constraining rolls are arranged for four cooling zones, but it is not always necessary to arrange constraining rolls on the most upstream side and the most downstream side of the cooling equipment 3. . However, as in the example shown in FIG. 2, by arranging the restraint rolls on the most upstream side of the cooling equipment 3, the cooling water W injected onto the steel plate S in the cooling zone will flow out to the upstream side of the cooling equipment 3. can be suppressed, it is possible to have a function as a draining roll in addition to the function of restraining the steel plate S. The same applies to the case of arranging the constraining rolls on the most downstream side of the cooling equipment 3 .
- the restraint rolls 61a and 61b that constitute the restraint device 6 are provided with a mechanism capable of adjusting the gap between the upper and lower rolls.
- a mechanism can be used in which the upper constraining roll 61a is moved up and down while the position of the lower constraining roll 61b in the vertical direction is fixed.
- the restraint roll 61b on the lower side may also function as the table roll 7. As shown in FIG.
- the restraint roll control device 12 sets the pressing position of each restraint roll based on the restraint conditions of the restraint device 6 set by the control computer 10 .
- the constrained roll control device 12 outputs a screw position command to a screw down control device 13 that changes the position of the constrained roll using a power source such as hydraulic pressure, pneumatic pressure, or an electric motor.
- the screw down position of the constraining roll is measured by the screw down position measuring device 14 .
- the constraining roll control device 12 corrects the rolling position command to the rolling control device 13 based on the measurement result of the rolling position, and controls the rolling positions of the binding rolls 61a and 61b.
- a method of controlling the rolling force may be used instead of the rolling position of the constraining rolls 61a and 61b.
- the control computer 10 sends a set value of the rolling force to be applied to the steel sheet S by the restraining rolls paired above and below.
- a load detector using a load cell is installed in a support mechanism such as a housing that supports the top-side constraining roll 61a or the bottom-side constraining roll 61b.
- a screw position command is output to.
- a load detector based on a load cell plays that role.
- the pressing force of the restraint rolls 61a and 61b against the steel plate S is preferably 39 kN or more, more preferably 59 kN or more, and still more preferably 78 kN or more. good.
- the pressing force is preferably 196 kN or less.
- the appropriate pressing force by the restraint rolls 61a and 61b depends on the thickness, width, steel grade, strength, amount of cooling water in the water cooling device 5, conveying speed of the steel plate S, cooling stop temperature, cooling speed, etc. of the steel plate S to be heat-treated.
- the appropriate condition range differs depending on the heat treatment conditions.
- the mechanism for applying the pressing force by the restraint rolls 61a and 61b may be either a spring type such as a spring or a mechanism capable of applying a constant pressing force such as air pressure or hydraulic pressure.
- a mechanism capable of maintaining a constant pressing force is preferable, and a mechanism having responsiveness such that the pressing force can be changed in the longitudinal direction of the steel plate S is preferable.
- the drain purge nozzle 15 is installed on the downstream side of the restraint roll 61a on the most downstream side of the cooling equipment 3.
- the draining purge nozzle 15 is angled toward the constraining roll 61a so that the cooling water W leaking from the gap formed at the contact portion between the constraining roll 61a and the steel plate S does not flow further downstream. Inject.
- the drain purge 15a sprayed onto the upper surface of the steel sheet S is also sprayed at an angle in the width direction so that the cooling water W on the steel sheet S is discharged toward the widthwise end portion direction.
- the draining purge 15a may be liquid or gas, or a mixed fluid thereof may be jetted.
- the drainage purge 15a has the effect of suppressing the temperature deviation of the steel sheet S from increasing and suppressing the deterioration of the shape of the steel sheet S.
- increasing the injection pressure and injection amount of the drain purge 15a increases the energy consumption of the pressure supply source for injection.
- the cooling water W that has passed through the restraint roll 61a is caused by the air injected toward the contact portion between the restraint roll 61a arranged on the most downstream side of the cooling equipment 3 and the steel sheet S. may scatter around the steel plate S and cause local temperature non-uniformity in the steel plate S.
- water is used for the drain purge 15a
- the surface of the steel sheet S may have a temperature deviation. Therefore, it is necessary to set an appropriate injection pressure and injection amount of the drain purge 15a according to the amount of cooling water W leaking to the downstream side of the restraining roll 61a.
- the control computer 10 receives information from the host computer 16 such as the heating temperature, thickness, width, and weight of the steel sheet S, as well as the target range of the cooling stop temperature (target cooling stop temperature) necessary to obtain the desired material quality. and the target range of cooling rate (target cooling rate). Then, the control computer 10 calculates operating conditions for realizing such conditions and determines operating parameters for each device of the cooling equipment 3 .
- FIG. 3 is a block diagram showing the configuration of the control computer 10 in this embodiment.
- the control computer 10 acquires attribute information of the steel sheet S to be heat-treated from the host computer 16 .
- the attribute information of the steel sheet S includes information on the dimensions of the steel sheet S such as the thickness, width, and length (or weight) of the steel sheet S, as well as information on the chemical composition of the steel sheet S (the C content of the steel sheet S, Si content, Mn content, Cr content, Mo content, etc.) and target values of mechanical properties of steel sheet S after heat treatment (yield stress, tensile strength, elongation, toughness, hardness, etc.).
- the control computer 10 acquires information about the target cooling stop temperature and the target cooling rate from the host computer 16 in addition to the attribute information of the steel plate S. Then, the control computer 10 performs heat transfer calculation based on the internal model in the water cooling condition calculation unit 10a, and the water cooling nozzles in the cooling area are adjusted so as to satisfy the target cooling stop temperature and target cooling rate set as the cooling conditions.
- the operating conditions of the water cooling device 5 including the flow rate of the cooling water W of 51a and 51b, the cooling zone for spraying the cooling water W, and the conveying speed of the steel plate S within the cooling equipment 3 are determined.
- the operating conditions of the water cooling device 5 set by the water cooling condition calculation unit 10 a are sent to the water cooling flow control device 11 .
- the water-cooling flow control device 11 controls the operating pressure and the number of operating cooling water pumps, the number of headers provided upstream of the piping system of the water-cooling nozzles 5a and 51b, the opening degree of the flow control valve, and the table roll 7.
- a command for the rotational speed of the motor is generated, and the operating conditions for the water cooling device 5 are set.
- the control computer 10 also includes a constraint condition setting unit 10b, which sets the pressing position or pressing force of the restricting rolls 61a and 61b according to the attribute information of the steel plate. Normally, the set value of the rolling position and the rolling force of each constraining roll is set as a table value associated with the attribute information of the steel sheet S based on past operational experience.
- the pressing position or pressing force of the restricting roll set in the restricting condition setting unit 10b becomes the operating condition of the restricting device 6 and the control target value of the restricting roll control device 12.
- the constraining roll control device 12 outputs a control command to the power source of the rolling mechanism of the constraining rolls, and constrains the steel sheet S being water-cooled by the constraining rolls based on the measured value of the rolling position or rolling force.
- the shape meter 4 is installed on the outlet side of the cooling equipment 3 and measures the shape of the steel plate S cooled by the cooling equipment 3 .
- the shape meter 4 is a device that measures the height distribution in the plane of the steel plate S. As shown in FIG. Specifically, the shape meter 4 scans a laser beam in the width direction of the steel sheet S to measure the height distribution of the steel sheet S in the width direction. Measure the height distribution in the width direction at each position. By repeating this from the front end portion to the tail end portion of the steel plate S in the longitudinal direction, the in-plane height distribution of the steel plate S can be obtained. When measuring the shape of the steel plate S, the finer the measurement pitch, the better. This is because the measurement accuracy for the various shapes shown in FIG.
- the shape meter 4 may arrange a plurality of laser rangefinders in the width direction of the steel sheet S to measure the height distribution in the width direction by the plurality of rangefinders. In this case, it is preferable to arrange the laser rangefinders in the width direction of the steel sheet S at a pitch of 40 to 200 mm.
- the shape meter 4 does not necessarily need to be arranged on the extension line in the conveying direction of the steel plate S in the cooling equipment 3 as shown in FIG.
- a cooling bed or the like that can measure the shape of the steel sheet S after passing through the cooling equipment 3 may be installed so that the measurement can be performed off-line.
- the shape meter 4 a specific optical pattern is projected onto the steel plate S, and the shape of the steel plate S is estimated from the amount of distortion of the projected pattern. It may be one that measures the shape.
- the shape data of the steel plate S measured by the shape meter 4 is converted into shape information by the shape information generation unit 17.
- Any information representative of shape data can be used as the shape information.
- the shape information the difference between the maximum and minimum heights in the width direction of the steel sheet S at any one of the tip, center, and tail in the longitudinal direction, and the height distribution standard It can be defined by deviation.
- the difference between the maximum and minimum values of the in-plane height of the steel plate S, the standard deviation of the height distribution, or each position in the longitudinal direction A value obtained by averaging the difference between the maximum and minimum heights at .
- a curve representing the relationship between the in-plane position and height of the steel plate extracted by an arbitrary filtering method such as a bandpass filter, or a curve obtained by an arbitrary transformation method such as Gaussian curvature transformation can be used as shape information.
- the curve thus obtained may be function-approximated, and a parameter that can specify the function-approximated function may be used as the shape information.
- a two-dimensional image in which the in-plane height distribution of the steel plate S is color-coded into contour lines may be used as the shape information.
- the shape information about the C warp shape shown in FIG. 9A is based on the height information of the steel plate S acquired by the shape meter 4, and the difference between the maximum height and the minimum height of the steel plate S in the width direction (C warp height can be identified by finding the In this case, the C-warp height at a preset position in the longitudinal direction of the steel sheet S can be defined as shape information related to the C-warp shape of the steel sheet S. Further, the maximum C-warp height measured in the longitudinal direction of the steel sheet S may be used as the shape information regarding the C-warp shape of the steel sheet S.
- the selvage shape shown in FIG. 9(b) is a shape defect that occurs when the material length at the end of the width of the steel sheet S is longer than the material length at the center of the width of the steel sheet S. Waveform shape information can be used.
- the medium elongation shape shown in FIG. 9(c) is a shape defect that occurs when the material length in the width direction central portion of the steel plate S is longer than the material length in the width direction end portions. It can be the shape information of the shape.
- the pitch and wave height of the unevenness are calculated from the height distribution along the longitudinal direction of the width direction end of the steel plate S, and the wave height of the wave shape is calculated as the pitch You may specify by the value divided by.
- the value calculated in this manner is called a steepness, and can be used as shape information of the edge wave shape of the steel sheet S.
- the steepness of the ear wave shape is called ear wave steepness.
- the steepness which is a value obtained by dividing the height by the pitch, may be used as the shape information of the medium elongation shape of the steel sheet S.
- the steepness of the medium elongation shape is called the medium elongation steepness.
- the composite shape shown in FIG. 9D is a shape defect that is a combination of the above shape defects
- the values of the C warpage height, the ear wave steepness, and the middle elongation steepness calculated by the above method are
- the shape information of the steel plate S can be used as a set of data sets. Further, a diagram obtained by plotting the distribution of the material length in the longitudinal direction of the steel sheet S at each position with respect to the position in the width direction of the steel sheet S, or a curve obtained by functionally approximating the distribution shape may be used as the shape information of the steel sheet S. good.
- the cooling equipment 3 information including at least one operation result data selected from each of the operation result data of the water cooling device 5 and the operation result data of the restraint device 6 is input.
- FIG. 4 shows the configuration of the shape prediction model generation unit 18, which is one embodiment of the present invention.
- the shape prediction model generation unit 18, which is one embodiment of the present invention includes a database unit 18a and a machine learning unit 18b.
- the database unit 18a acquires the operation performance data of the water cooling device 5 and the operation performance data of the restraint device 6, and passes through the cooling equipment 3 of the steel plate S that has been heat-treated under the operating conditions under which the operation performance data was acquired. Get later shape information.
- the database unit 18a acquires parameters relating to the attribute information of the steel sheet S acquired from the host computer 16 or the control computer 10 as necessary.
- the plurality of types of data stored in the database unit 18a are associated based on unique information that can identify the steel sheet S, such as the production number of the steel sheet S to be heat-treated.
- the shape prediction model generation unit 18 may be inside the control computer 10, or may be configured by separate hardware that can communicate with the control computer 10. Moreover, it can be provided in the shape determination unit 19 to be described later.
- the amount of cooling water by the water cooling device 5 and the ratio of the upper and lower water amounts of the cooling water W can be used.
- the amount of cooling water by assigning an identification number to each water cooling zone and the upper and lower water cooling nozzles, the amount of cooling water for each water cooling nozzle can be used as the actual operation data of the water cooling device 5 .
- the sum of the amounts of cooling water in the water cooling zones or the sum of the amounts of cooling water in a plurality of water cooling zones arbitrarily selected from the water cooling zones may be used as the actual operation data of the water cooling device 5 .
- the temperature change of the steel plate S is large, and the shape of the steel plate S is greatly affected.
- the sum of the cooling water amounts may also be used.
- the operation performance data of the water-cooling device 5 is acquired by the flowmeters. Actual data may be used. However, the set value of the cooling water amount set in the water cooling condition calculation unit 10a may be used. This is because if the set value and the actual value of the water cooling nozzle are compared in advance, it is considered that the actual amount of cooling water is less likely to greatly deviate from the set value.
- the ratio of the upper and lower water amounts of the cooling water W is used as the actual operation data of the water cooling device 5
- the ratio of the flow rates of the upper and lower water cooling nozzles that form a pair in the water cooling zone is used. This is because if a temperature difference occurs between the upper and lower surfaces of the steel sheet S during cooling due to the water volume ratio between the upper and lower surfaces, the amount of heat shrinkage on the upper and lower surfaces will differ, and the shape of the steel sheet S will be affected.
- the cooling speed of the steel plate S and the conveying speed of the steel plate S in the cooling equipment 3 may be used as the operation performance data of the water cooling device 5 .
- the cooling rate of the steel sheet S can be calculated from the difference between the cooling start temperature and the cooling end temperature, the distance between these thermometers, and the conveying speed of the steel sheet S. This is because the cooling rate of the steel sheet S changes the temperature gradient occurring in the longitudinal direction of the steel sheet S and changes the strain gradient in the longitudinal direction, thereby affecting the shape of the steel sheet S.
- the conveying speed of the steel sheet S also affects the shape of the steel sheet S by changing the temperature gradient generated in the longitudinal direction of the steel sheet S.
- the operation performance data of the water cooling device 5 may include the cooling stop temperature of the steel plate S in addition to the above. This is because, when the cooling stop temperature is low, the cooling region of nucleate boiling is entered, and the temperature deviation is likely to occur, so that the shape of the steel sheet S may be deteriorated.
- the operation performance data of the water cooling device 5 includes at least one of the cooling water amount, the upper and lower water amount ratio of the cooling water W, the cooling speed of the steel plate S, and the conveying speed of the steel plate S in the cooling equipment 3. is preferable, and it is more preferable to include a plurality of operational performance data out of these. This is because it is advantageous in predicting complex shape defects caused by multiple causes.
- the operation performance data of the restraining device 6 include at least one of the rolling position and rolling force of the restraining rolls.
- the screw down position of the constraining roll the actual value of the screw down position measured by the screw down position measuring device 14 can be used.
- a set value set in the restraint roll control device 12 may be used.
- the rolling force of the constraining roll the actual value of the rolling force measured by the load cell can be used.
- a set value set by the restraint roll control device 12 may be used. If a load cell-based load detector capable of measuring the rolling force of the restraining rolls is also arranged, both the rolling position and the rolling force can be used as the operation performance data of the restraining device 6 . This is because the shape of the steel sheet S after cooling is affected by the magnitude of the restraining force on the steel sheet S during cooling.
- the operation data of any of the restraint rolls can be used as the operation result data of the restraint device 6 .
- the sum of the rolling forces of a plurality of pairs of restraint rolls may be used as the operation performance data of the restraint device 6 .
- the temperature change of the steel sheet S is large, so the operating conditions of the restraint rolls have a great influence on the shape of the steel sheet S. For this reason, the sum of rolling forces by two to three pairs of restraint rolls arranged on the front stage side of the cooling area may be used.
- the average position of the roll-down positions of a plurality of arbitrarily selected restraint rolls can be used as the operation performance data of the restraint device 6. This is because the extent to which the steel plate S is constrained changes according to the value of the average rolling position of the plurality of constraining rolls.
- the difference in the rolling position and the difference in the rolling force at the positions of both ends supporting the restraining roll may be used. This is because the asymmetrical restraint in the width direction of the steel plate S affects the shape.
- information for identifying which restraining roll is used to restrain the steel sheet S or whether the restraining roll is released to perform no restraint may be used.
- a string of numbers corresponding to the identification numbers of the restraining rolls may be used as the operation performance data of the restraining device 6, with a code such as "1" being assigned to the restraining roll that restrains the steel plate S and "0" being assigned to the restraining roll that is released.
- the thinner the sheet thickness and the wider the sheet width the more likely the steel sheet S is to undergo out-of-plane buckling, which affects the shape of the steel sheet after passing through the cooling device. Also, this is because there is a tendency that the wider the sheet width, the larger the height of the sheet width end portion in the C-warp shape. Furthermore, since whether or not plastic deformation occurs due to buckling may be affected by mechanical properties such as the yield stress of the steel sheet S, attribute information representing the mechanical properties of the steel sheet S should be used as input data. is preferred.
- the chemical composition of the steel sheet S affects the phase transformation in the cooling process, and the volume change due to the phase transformation affects the shape of the steel sheet S.
- Information about the composition is preferably used as input data for the shape prediction model M.
- the chemical composition of the steel sheet S can be used as a parameter related to the attribute information of the steel sheet S by expressing the C content, Si content, Mn content, Cr content, and Mo content of the steel sheet in wt%.
- the input data of the shape prediction model M is not limited to the above, but actual values or set values such as actual temperatures and residence times in each zone such as the heating zone and soaking zone in the heating furnace 2 of the heat treatment equipment 1. may include operating parameters of the heating furnace 2.
- the surface roughness of the steel sheet, the state of oxides, etc. also affect the wettability of the cooling water W, and the temperature distribution in the surface of the steel sheet S during cooling changes, indirectly affecting the shape of the steel sheet S. is.
- the injection pressure and the injection amount of the draining purge 15a may be used as input data for the shape prediction model M as operation parameters of the draining purge nozzle 15. This is because the injection pressure and injection amount of the draining purge 15a can affect the shape of the steel sheet S.
- the operation performance data of the water cooling device 5, the operation performance data of the restraint device 6, the shape information of the steel plate S after passing through the cooling equipment 3, and the attribute information of the steel plate S acquired as necessary The operation performance data of the operation parameters of the heating furnace 2 and the operation parameters of the drain purge nozzle 15 form one data set for each steel plate S, and are stored in the storage device of the database unit 18a.
- the database unit 18a accumulates 20 or more data sets for each category of the same standard, steel grade, and size.
- the number is preferably 100 or more, more preferably 500 or more.
- the steel plate S is divided in the longitudinal direction, and the operation performance data is obtained for each section.
- shape information calculated for each corresponding section may be associated with the data.
- a plurality of data sets are generated for one steel sheet S and stored in the database section 18a.
- the data accumulated in the database unit 18a may be screened as necessary, and data indicating abnormal values may be removed. This is because highly reliable data is accumulated and the accuracy of shape prediction is improved.
- the data sets accumulated in the database unit 18a may be appropriately updated within the upper limit of a certain number of data sets.
- the machine learning unit 18b uses the data set accumulated in the database unit 18a to obtain information including at least one piece of operation result data selected from each of the operation result data of the water cooling device 5 and the operation result data of the restraint device 6. is input performance data, and the shape information of the steel plate S after passing through the cooling facility 3 corresponding to these input performance data is used as output performance data. A shape prediction model M of the steel plate S after the processing is generated.
- machine learning is performed by including the attribute information parameters of the steel sheet S, the operation performance data of the heating furnace 2, and the operation performance data of the draining purge nozzle 15, which are accumulated in the database unit 18a as necessary, in the input performance data. good too.
- the machine learning model for generating the shape prediction model M can be any machine learning model as long as it has a practically sufficient shape prediction accuracy.
- generally used neural networks including deep learning, convolutional neural networks, etc.
- decision tree learning including deep learning, convolutional neural networks, etc.
- random forest including a forest of a plurality of models
- support vector regression etc.
- an ensemble model combining a plurality of models may be used.
- the shape prediction model M is not a regression model that numerically outputs the shape information of the steel sheet S, but determines whether or not the shape is within a predetermined allowable range, and binarizes the result as pass/fail.
- a machine learning model may be used in which the obtained data is used as the actual output data.
- Classification models such as the k-nearest neighbor method and logistic regression can be used.
- the shape prediction model M may be updated to a new model by re-learning, for example, every month or every year. This is because the more data stored in the database unit 18a, the more accurate the shape prediction becomes. By updating the shape prediction model M based on the latest data, changes in operating conditions over time are reflected. This is because the shape predictive model M can be generated.
- the shape prediction model M generated as described above includes at least one operation parameter selected from each of the operation parameter of the water cooling device 5 and the operation parameter of the restraint device 6 in the input data, and passes through the cooling equipment 3.
- the shape information of the steel plate after the processing is used as output data.
- the cooling equipment 3 has the restraining device 6 in addition to the water cooling device 5 .
- the shape defect observed on the downstream side of the cooling equipment 3 is often the C warp shape shown in FIG. 9(a). This is because the cause of the shape defect is mainly due to the difference in the cooling state between the upper and lower surfaces of the steel sheet S, and the conditions make it difficult for the longitudinal expansion rate to occur at each position in the width direction of the steel sheet S. In that case, since the steel sheet S is not restrained during cooling, a very large warpage may occur as a C-warp shape.
- the restraining roll restrains the steel plate S during cooling from above and below, and although the C warp shape of the steel plate S is suppressed, the upper and lower surfaces of the steel plate S
- the strain difference may change to the longitudinal elongation difference at each position in the width direction. That is, in the equipment including the water cooling device 5 and the restraint device 6 as the cooling equipment 3, although the large C-warp shape is suppressed, the edge wave shape shown in FIG. shape tends to occur. In this case, depending on the combination of the operating conditions of the water cooling device 5 and the operating conditions of the restraint device 6, it is possible to have a complex shape as shown in FIG. 9(d).
- the strain gradient in the longitudinal direction of the steel sheet S due to thermal contraction changes depending on the operating conditions of the water cooling device 5 .
- a temperature difference occurs between the widthwise end portion and the widthwise central portion of the steel plate S, and as a result, a temperature distribution occurs within the surface of the steel plate S, resulting in an in-plane strain. Distribution may occur.
- a local volume change occurs due to phase transformation, strain distribution occurs in the surface of the steel sheet S, and the shape of the steel sheet S may deteriorate. .
- the shape defect of the steel sheet S that occurs during water cooling causes a large C warp when the restraining device 6 is not provided.
- the directional displacement is suppressed, the shape of the steel plate S changes intricately due to various factors. Therefore, when trying to predict the shape of the steel sheet S that appears in such various forms, it is necessary to consider both the operating parameters of the water cooling device 5 and the operating parameters of the restraining device 6 .
- the restraint roll is not bent as the operation condition of the restraint device 6.
- the gap between the steel plate S and the restraint roll is distributed.
- water on the upper surface of the steel sheet S becomes non-uniform in the width direction, and cooling unevenness occurs within the surface of the steel sheet S.
- Such uneven cooling caused by water on the steel sheet S causes distortion in the plane of the steel sheet S, which causes shape defects.
- the operation condition of the water cooling device 5 is such that the transition boiling region is locally formed in the surface of the steel plate S. If such water cooling conditions are set, a shape defect occurs due to cooling strain. In this case, the force acting from the steel plate S to the constraining rolls is distributed, and as a result, the constraining rolls are bent, and the shape of the steel plate S may be deteriorated.
- the behavior of the phase transformation that occurs during cooling of the steel sheet S also affects the shape defects of the steel sheet S.
- the pressing force of restraining rolls positioned in a cooling zone at which the temperature at which phase transformation occurs during cooling of the steel sheet S may be set larger than that of other cooling zones. This is for suppressing strain occurring in the steel sheet S due to volume change due to phase transformation.
- phase transformation may occur at a position different from the cooling zone where the phase transformation is expected to occur.
- the pressing force of the constraining rolls positioned in the cooling zone where the phase transformation actually occurred is set to be small, and the pressing force of the constraining rolls positioned in the cooling zone where the phase transformation is predicted to occur is set to be excessive.
- the operating parameters of the restraint device 6 may become inappropriate, and a shape defect may occur.
- the flow of cooling water discharged from the corresponding cooling zone to another cooling zone changes, thereby changing the temperature history of the steel sheet S.
- the cooling zone where the phase transformation starts may change to a position different from the previously assumed cooling zone.
- the steel plate shape is affected by the operation parameters of the water cooling device 5 and the restraining device 6 respectively. Furthermore, in particular, regarding the C warp shape caused by the drainability of the steel sheet S, the shape change caused by the volume change of the steel sheet S in the transformation temperature range, or the flow behavior of the cooling water W in the cooling zone, the operation of the water cooling device 5 The parameters and operating parameters of the restraint device 6 are interrelated.
- the steel plate shape control apparatus includes a shape determination unit 19 attached to the control computer 10.
- FIG. 5 is a diagram for explaining the configuration of the shape determining section 19.
- the shape prediction model M used by the shape determination unit 19 is the shape prediction model M generated by the shape prediction model generation unit 18 described above.
- the operating conditions of the water cooling device 5 and the operating conditions of the restraint device 6 set by the control computer 10, and the attribute information parameters of the steel plate S as necessary, are set by the shape determination unit 19.
- the shape determining unit 19 predicts the shape of the steel plate S on the delivery side of the cooling equipment 3, and the operating condition resetting unit 19a adjusts the shape so that the predicted shape is within a preset allowable range (shape allowable range) At least one operational parameter selected from the operational parameters of the water cooling device 5 and the restraining device 6 is reset.
- FIG. 6 is a flowchart showing the flow of shape control processing, which is one embodiment of the present invention.
- the constraint condition setting unit 10b starts the operation conditions of the water cooling device 5 and the constraint device 6, and the shape control process proceeds to step S1.
- step S1 the water cooling condition calculation unit 10a acquires the operating conditions of the water cooling device 5, such as the amount of cooling water and the conveying speed of the table roll, which are set so as to satisfy the target cooling conditions. Thereby, the process of step S1 is completed, and the shape control process proceeds to the process of step S2.
- step S2 the constraint condition setting unit 10b acquires initial conditions for the pressing position and pressing force of the restricting rolls, which are set in advance according to the classification of the steel plate S such as the size. Thereby, the process of step S2 is completed, and the shape control process proceeds to the process of step S3.
- step S3 the shape determining unit 19 uses the operating conditions of the water cooling device 5 and the operating conditions of the restraint device 6 acquired in the processing of steps S1 and S2 as input data, and uses the shape prediction model M to determine the shape of the cooling equipment 3. A shape prediction result of the steel plate S on the downstream side is calculated. Thereby, the processing of step S3 is completed, and the shape control processing proceeds to the processing of step S4.
- the shape determination unit 19 converts the shape prediction result calculated in the process of step S3 into a predetermined allowable value obtained from the host computer 16 or the control computer 10 according to the steel type, size, and the like. Compare to range to determine if expected shape is within tolerance.
- the allowable range is strictly set to 35 mm or less when the shape information is defined by the difference between the maximum height and the minimum height in the plane of the steel plate S, 25 mm or less when defined by the standard deviation, and 15 mm or less of the standard deviation. By doing so, it becomes possible to manufacture a flatter steel plate S.
- the allowable range varies depending on the specifications of the steel plate S to be manufactured.
- step S4 determines the operating conditions of the water cooling device 5 and the restraint device 6 acquired in the processing of steps S1 and S2. The operating conditions are sent to the control computer 10, and a series of shape control processing ends. On the other hand, if the predicted shape does not fall within the allowable range (step S4: No), the shape determination unit 19 advances the shape control process to step S5.
- the operating condition resetting unit 19a of the shape determining unit 19 resets the operating conditions of the water cooling device 5 and the restraining device 6 so that the shape of the steel plate S falls within the allowable range. Then, the shape determining section 19 sends the reset operational conditions to the control computer 10 .
- the operating conditions to be reset are desirably at least one of the amount of cooling water, the conveying speed, the water volume ratio, the reduction amount of the constraining rolls, and the reduction load. Accordingly, appropriate operating conditions can be realized according to the attributes of the steel sheet S and manufacturing conditions. This completes the series of shape control processes.
- the shape control process is not limited to one in which the operating conditions are set under constant conditions in the longitudinal direction of the steel plate S.
- the shape of the steel plate S predicted from the shape prediction model M when generating the shape prediction model M for predicting the shape at several points such as the tip, the center, and the tail, The operating conditions of the water cooling device 5 may be changed according to the shape of the steel plate S expected in the direction.
- the shape meter 4 When the shape meter 4 is installed on the entrance side of the heating furnace 2 or between the heating furnace 2 and the cooling equipment 3, the information obtained by the shape meter 4 before heating or cooling is added to the input data of the shape prediction model M. may be added. Thereby, it becomes possible to consider the influence on the cooling behavior in the cooling equipment 3 according to the shape information before heating or before cooling, and the shape prediction accuracy of the steel plate S is improved.
- the steel sheet S that has been heat-treated by the heat treatment equipment 1 shown in FIG. 2 may then be sent to a leveler process or a press straightening process, which is a shape correction process for the steel sheet S after cooling.
- a process of correcting the shape of the steel sheet S after heat treatment and cooling is called a treatment process.
- the leveler process is a process of repeatedly bending and unbending deformation of the steel sheet S along the longitudinal direction using a roller leveler, and is a process for flattening the shape of the steel sheet S as a whole.
- the in-plane part of the steel plate S is straightened in response to the strain that occurs only in the front end and tail end of the steel plate S, only in the width direction end, and only in a part of the plane. It is a process for Therefore, using the shape information of the steel sheet S predicted by the shape prediction model M, it is possible to determine whether the steel sheet S should be sent to either the leveler process or the press straightening process as the next process after the heat treatment process, or not to be sent to any shape straightening process. can be determined. By predicting the shape information of the steel sheet S using the shape prediction model M in this way, an appropriate treatment process can be selected and a steel sheet with good flatness can be manufactured. It is also possible to shorten the downtime in the manufacturing process of the steel plate S and improve the production efficiency.
- the present embodiment has been described with reference to off-line heat treatment equipment, it goes without saying that it can be applied to on-line heat treatment equipment.
- the shape prediction model M preferably predicts the shape of the steel sheet S at multiple positions in the longitudinal direction.
- the shape of the steel sheet S conveyed in the cooling equipment 3 can be improved along the longitudinal direction, and the steel sheet S can be manufactured with little change in shape in the longitudinal direction.
- the cooling equipment 3 is arranged on the downstream side of the heating furnace 2, and seven pairs of water-cooling nozzles 51a, 51b and eight pairs of restraint rolls 61a, 61b constituting the water-cooling device 5 are arranged therein. Each water cooling nozzle 51a and each restraint roll 61a can be raised and lowered independently.
- the shape information which is the output data of the shape prediction model M, is the difference between the maximum height and the minimum height in the plane of the steel sheet S, which is measured based on the height data of the steel sheet S measured by the shape meter 4.
- the control computer 10 controls the amount of cooling water for each water cooling zone of the water cooling device 5 and The initial setting of the W injection cooling zone was performed. Then, the shape at each longitudinal position of the steel plate S was measured by the shape meter 4, and the in-plane height distribution of the steel plate S was measured. Of the in-plane heights measured over the entire surface of the steel plate S, the value obtained by subtracting the minimum value from the maximum value was evaluated as the shape output value of the steel plate S, and the condition where the shape output value was 15 mm or less was passed. , the condition exceeding 15 mm was plotted on the graph as failure "x".
- Fig. 7 is a diagram in which the pass/fail of the shape of the steel plate S obtained by prior confirmation is organized by the conveying speed and the amount of cooling water.
- FIG. 7 it can be seen that in both cases of a plate thickness of 6 mm and a plate thickness of 12 mm, the higher the amount of cooling water, the higher the transport speed required for the shape to pass. This is thought to be because the cooling rate of the steel sheet S increases with an increase in the amount of cooling water, the gradient of the amount of thermal contraction in the longitudinal direction of the steel sheet S increases, and the steel sheet S becomes more susceptible to buckling.
- the sheet thickness of 12 mm is lower than that of the sheet thickness of 6 mm, at which the shape becomes acceptable even with the same amount of cooling water. It is considered that this is because the thicker the steel sheet S, the larger the geometrical moment of inertia, and the harder the steel sheet S is to deform. From the above, it was confirmed that there is a correlation between the operation parameters of the water cooling device 5 and the shape information of the steel plate S after passing through the cooling equipment 3 .
- the failure condition occurs again in the upper left part of the graph, that is, in the case of low cooling water amount and high conveying speed.
- the cooling rate is slow and the conveying speed is high, so that the martensite transformation region of the steel sheet S moves to the downstream side where there is no restraint by the restraining rolls, and the out-of-plane deformation of the steel sheet S is caused by the initial setting of the restraining rolls.
- This is thought to be due to the inability to control
- the thicker the steel sheet S the longer the cooling time required, so it is considered that the 12 mm thick steel sheet has a wider rejection area in the upper left part of the graph.
- each restraining roll constituting the restraining device 6 is an operational parameter of the restraining device 6, and there is a correlation between the operational parameter of the restraining device 6 and the shape information of the steel plate S after passing through the cooling equipment 3. is presumed to exist.
- the relationship between the manufacturing conditions and the shape was confirmed with respect to the conditions enclosed by the dotted line in FIG. 7(b).
- the setting of the number of cooling zones for injecting the cooling water W is appropriately changed so that the steel plate S is cooled to room temperature, and the restraining device is used.
- the setting of the number of roll pairs used for restraining No. 6 was appropriately changed, and the steel sheet S was heat-treated. Under the condition surrounded by the dotted line in FIG.
- the speed was selected, the number of roll pairs used for restraining the steel plate S was selected as the operation parameter of the restraining device 6, and learning data was acquired. Then, a shape prediction model M using a neural network was created in which these operation parameters were used as input data and shape information was used as output data. As the shape information, a value obtained by subtracting the minimum value from the maximum value among the in-plane heights measured over the entire surface of the steel plate S was used.
- the shape of the steel sheet after passing through the cooling equipment was predicted for various input values. It was anticipated that more would be required.
- the conveying speed was less than 12 mpm, the shape was rejected, and the specific shape output value was predicted to be 20 to 32 mm.
- the conveying speed was 12 mpm, the shape was predicted to be acceptable, and the specific shape output value was 3 to 11 mm.
- the number of restraining rolls used for restraining the steel plate S is reset so that the shape of the steel plate S after passing through the cooling equipment predicted using the shape prediction model is 15 mm or less, which is set as an allowable range. Then, the steel plate S was heat-treated. As a result, even when the steel plate speed was increased to 30 mpm, a good shape could be obtained, which contributed to the expansion of productivity due to the expansion of the appropriate operation range and the improvement of the conveying speed.
- the steel plate shape prediction method according to the present embodiment is applied to an off-line heat treatment facility, and the water cooling device 5 and the restraint device 6 are used so that the predicted steel plate shape is within a preset allowable range.
- a steel plate was produced by resetting the operating parameters of The heat treatment equipment including the steel plate cooling equipment used in this example has seven cooling zones as shown in FIG.
- the steel sheet to be heat-treated has a thickness of 6 mm, a width of 2500 mm and a length of 8 m, a heating temperature of 920 ° C., a target cooling stop temperature of 200 ° C., and a target cooling rate of the surface layer of the steel plate in the range of 10 to 40 ° C./s.
- the target is the one for which the manufacturing specification is set so that
- the shape prediction model M of the steel sheet used in this example is the steel sheet of the same steel type (the control range of the chemical composition of the steel sheet is common) manufactured in the offline type heat treatment equipment and having a thickness of 6 mm.
- Performance data, operation performance data of the restraining device 6, and shape information of the steel plate after passing through the cooling equipment 3 were obtained as output performance data.
- the acquired performance data were accumulated in the database unit 18a of the shape prediction model generation unit 18 as a data set associated with the manufacturing number of the steel plate.
- the operation parameters of the water cooling device 5 the conveying speed of the steel plate in the cooling equipment 3, the total amount of cooling water sprayed in the water cooling zone, and the flow rate ratio of the upper and lower water cooling nozzles are used.
- the rolling force of all the restraining rolls was set to the same value for the restraining device 6, and the rolling force of the restraining rolls was selected as an operating parameter of the restraining device 6.
- the maximum in-plane height of the steel plate which is specified based on the height data of the steel plate measured by the shape meter 4, is used.
- the shape prediction model M was generated by the machine learning unit 18b.
- a neural network was used as a machine learning algorithm, and the number of intermediate layers of the neural network was set to 3 layers, and the number of nodes was set to 5 each.
- a sigmoid function was used as the activation function.
- the machine learning unit 18b generates a shape prediction model M using the 80 data sets accumulated in the database unit 18a as teacher data, and evaluates the accuracy of the shape prediction model M generated using the remaining 20 data sets as test data. verified. As a result, the prediction accuracy of the maximum height of the steel sheet by the generated shape prediction model M was 1.5 mm in terms of standard deviation.
- operating conditions of the water cooling device 5 and the restraining device 6 are set in advance in the control computer 10 of the off-line type heat treatment equipment.
- the conveying speed of the steel plate in the cooling equipment 3 is 40 m/min
- the total amount of cooling water injected in the water cooling zone is 2300 L/m 2 min.
- the flow rate ratio of the upper and lower water-cooled nozzles was 1.5
- the pressing force of the restraint roll was 20 kN.
- the water-cooled nozzle flow rate ratio (upper/lower water amount ratio) refers to the ratio of the amount of cooling water injected from the upper water-cooled nozzle to the amount of cooling water injected from the lower water-cooled nozzle.
- the maximum in-plane height of the steel plate was 40 mm, and the allowable range of the shape (the maximum height of the steel plate used in this example was 15 mm or less). was far from Therefore, the operation was performed under the conditions of setting example 2 in which the set value of the pressing force of the restraint rolls was changed to 80 kN in order to suppress the strain during cooling of the steel plate. As a result, the maximum in-plane height of the steel plate was 17 mm, which was improved compared to the conditions of setting example 1, but could not satisfy the allowable range of the shape.
- the shape prediction model M generated by the shape prediction model generation unit 18 is installed in the shape determination unit 19 shown in FIG. set as Then, before the steel plate is cooled by the cooling equipment 3, the shape determination unit 19 predicts the shape of the steel plate on the delivery side of the cooling equipment 3, and makes sure that the predicted shape of the steel plate is within a preset allowable range. Then, the operating parameters of the water cooling device 5 were reset by the operating condition resetting unit 19a.
- Example 1 shown in Table 1 as the operation parameter of the water cooling device 5 to be reset, the conveying speed of the steel plate in the cooling equipment 3 and the total amount of cooling water injected in the water cooling zone are selected.
- Example 2 shown in Table 1 the flow rate ratio of the upper and lower water cooling nozzles is selected as the operational parameter of the water cooling device 5 to be reset.
- Table 1 shows the maximum height of the steel plates according to Examples 1 and 2. As shown in Table 1, according to Examples 1 and 2, by resetting the operating conditions of the water cooling device 5 by the operating condition resetting unit 19a, the allowable range of the maximum height and shape of the steel plate was reduced. confirmed to be satisfactory.
- Example 3 the steel plate shape prediction method according to the present embodiment was applied to an online heat treatment facility, and direct quenching was performed on a plurality of steel plates of the same steel type (with a common control range of the chemical composition of the steel plate).
- the cooling equipment used in this example is arranged in the hot rolling line as shown in FIG.
- the hot rolling line shown in FIG. 8 includes a heating furnace 2 , a rolling mill 20 and cooling equipment 3 .
- the cast slab is heated to a predetermined temperature.
- the rolling mill 20 is a reverse type rolling mill, and is equipment for performing multiple passes of rolling so that the steel plate has a predetermined thickness and width.
- the steel sheet that has been rolled to a predetermined size by the rolling mill 20 is in a state of being heated to a high temperature, and is then subjected to a heat treatment process using the cooling equipment 3 .
- an entry-side thermometer 82 for measuring the temperature of the steel plate is installed at a position 3 m away from the entrance of the cooling equipment 3 on the upstream side of the cooling equipment 3.
- the temperature data of the steel sheet measured by the entry-side thermometer 82 is sent to the control computer 10 .
- a descaling device 9 is arranged upstream of the entry-side thermometer 82, and the descaling device 9 removes the oxide scale generated on the surface of the steel sheet. Thereby, the measurement error of the temperature data measured by the entry-side thermometer 82 can be reduced.
- the same cooling equipment 3 as shown in FIG. 1 can be used for the cooling equipment 3 arranged in the on-line heat treatment equipment. That is, the cooling equipment 3 includes a water cooling device 5 and a restraining device 6 that water-cool the steel plate under predetermined cooling conditions.
- the steel plate temperature changes in the longitudinal direction on the entry side of the cooling equipment 3 when the steel plate that has been completely rolled by the rolling mill 20 passes through the cooling equipment 3 at a predetermined conveying speed. In this respect, it differs from the heat treatment equipment on the offline side.
- the conveying speed of the steel plate in the cooling equipment 3 As inputs for the steel plate shape prediction model M, the conveying speed of the steel plate in the cooling equipment 3, the total amount of cooling water injected in the water cooling zone, the upper and lower water cooling nozzles The flow ratio and the pressing force of the constraining rolls were selected.
- the temperature information measured by the entry-side thermometer 82 which is an operation parameter of the water cooling device 5, is selected.
- the temperature information of the steel sheet measured by the entry-side thermometer 82 is information corresponding to the cooling start temperature, which is the temperature when cooling of the steel sheet is started.
- the online heat treatment equipment shown in FIG. A steel plate having a width of 2800 mm and a length of about 80 m was used.
- the steel plate was heat-treated by passing the steel plate through the cooling equipment 3, and the shape information of the steel plate was obtained by a shape meter arranged on the outlet side of the cooling equipment.
- the shape of the steel plate often changes in the longitudinal direction.
- Got information In this case, the shape information of the steel sheet is the maximum height in the sheet width direction obtained at a predetermined position along the longitudinal direction of the steel sheet.
- the positions were specified at 10m pitches from the tip of the steel plate, and the operation performance data corresponding to each position was acquired.
- the cooling start temperature of the steel plate was measured at intervals of 10 m with the entry-side thermometer 82 of the cooling equipment 3 .
- the conveying speed of the steel plate in the cooling equipment 3 the total amount of cooling water sprayed in the water cooling zone, the set value of the flow rate ratio of the upper and lower water cooling nozzles, and the actual value of the pressing force of the restraint roll were also measured. Acquired at a pitch of 10 m along the longitudinal direction.
- these operational performance data were acquired in synchronization with the timing at which temperature information was acquired by the entry-side thermometer 82 .
- the acquired operation performance data was stored in the database unit 18a in association with the shape information of the steel plate at the corresponding position. That is, for one steel plate, a plurality of data sets corresponding to the longitudinal position of the steel plate were accumulated.
- the shape prediction model M was generated by the machine learning unit 18b at the stage when data sets for 50 steel plates were accumulated in the database unit 18a.
- a neural network was used as a machine learning algorithm, and the number of intermediate layers of the neural network was set to 3 layers, and the number of nodes was set to 5 each.
- a sigmoid function was used as the activation function.
- the machine learning unit 18b generates a shape prediction model M using a data set obtained from the 35 steel plates accumulated in the database unit 18a as training data, and generates a data set obtained from the remaining 15 steel plates as test data.
- the accuracy of the shape prediction model M was verified. As a result, the prediction accuracy of the maximum height of the steel sheet by the generated shape prediction model M was 2.5 mm in terms of standard deviation.
- operating conditions of the water cooling device 5 and the restraining device 6 are set in advance in the control computer 10 of the online type heat treatment equipment.
- the conveying speed of the steel plate in the cooling equipment 3 is 20 m/min
- the total amount of cooling water sprayed in the water cooling zone is 2300 L/m 2 min
- the flow rate ratio of the upper and lower water cooling nozzles is 1.5
- the pressing force of the constraining rolls was 80 kN.
- these set values were set to constant values regardless of the cooling start temperature of the steel sheet (setting example 3).
- the maximum in-plane height of the steel plate was 29 mm, and the allowable range of the shape (the maximum height of the steel plate used in this example was 15 mm or less). was far from In particular, the shape of the tail end of the steel plate deteriorated.
- the shape prediction model M generated by the shape prediction model generation unit 18 is installed in the shape determination unit 19 shown in FIG. did.
- the shape determination unit 19 measured the cooling start temperature of the steel sheet at intervals of 10 m along the longitudinal direction from the stage when the tip of the steel sheet reached the entry-side thermometer 82 of the cooling equipment 3 .
- the measured temperature data, along with operational data such as the conveying speed of the steel plate in the cooling equipment 3, the total amount of cooling water sprayed in the water cooling zone, the flow rate ratio of the upper and lower water cooling nozzles, and the rolling force of the restraint roll, 19 shape prediction model M, and the shape information of the steel plate was predicted.
- the shape of the steel plate on the exit side of the cooling equipment 3 is predicted at any time when that portion reaches the entry-side thermometer 82 at intervals of 10 m along the longitudinal direction of the steel plate, so the predicted shape is within the allowable range.
- the operating parameters of the water cooling device 5 were reset as needed by the operating condition resetting unit 19a so that the operating parameters were within.
- the operation parameter of the water cooling device 5 reset in this embodiment is the total amount of cooling water injected in the water cooling zone. As a result, it was confirmed that the maximum in-plane height of the steel plate was reduced to 8 mm, satisfying the allowable range of shape.
- the present invention it is possible to provide a method for predicting the shape of a steel sheet that can accurately predict the shape information of the steel sheet after passing through the cooling equipment. Further, according to the present invention, it is possible to provide a method for controlling the shape of a steel plate that can accurately control the shape of the steel plate after passing through the cooling equipment within an allowable range. Further, according to the present invention, it is possible to provide a method for generating a shape prediction model of a steel sheet that can accurately predict the shape information of the steel sheet after passing through the cooling equipment. In addition, according to the present invention, it is possible to provide a steel plate manufacturing method and manufacturing equipment capable of manufacturing a steel plate with good flatness.
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Manufacturing & Machinery (AREA)
- Electromagnetism (AREA)
- Heat Treatment Of Strip Materials And Filament Materials (AREA)
Abstract
Description
まず、図1を参照して、本発明の一実施形態である鋼板の冷却設備の構成について説明する。
本実施例では、図1に示す熱処理設備1において、予めショットブラスト加工でスケールを除去した室温状態の鋼板Sを加熱炉2で920℃まで窒素雰囲気で加熱した後、加熱炉2からL0(=2.0m)離れた位置にある冷却設備3で冷却し、調質鋼を製造した。冷却設備3は加熱炉2の下流側に配置されており、その内部には水冷装置5を構成する7対の水冷ノズル51a,51bと8対の拘束ロール61a,61bが配置されている。各水冷ノズル51a及び各拘束ロール61aは、独立に昇降できるようになっている。水冷ノズル51a,51bとしてフラットスプレーノズルを用いた。また、冷却設備3の出口から下流側に5.0m離れた位置に形状計4を設置し、鋼板Sの冷却設備を通過した後の形状を計測した。
本実施例では、本実施形態に係る鋼板の形状予測方法をオフライン型の熱処理設備に適用し、予測された鋼板の形状が予め設定された許容範囲内になるように水冷装置5と拘束装置6の操業パラメタを再設定して鋼板を製造した。本実施例で用いた鋼板の冷却設備を含む熱処理設備は、図1に示すように冷却ゾーンを7ゾーンとする設備である。熱処理を行う鋼板は、板厚6mm、板幅2500mm、長さ8mであり、加熱温度920℃、目標冷却停止温度200℃であり、目標冷却速度は鋼板の表層で10~40℃/sの範囲となるように製造仕様が設定されているものを対象とした。
本実施例では、本実施形態に係る鋼板の形状予測方法をオンライン型の熱処理設備に適用し、同一鋼種(鋼板の成分組成の管理範囲が共通)の複数の鋼板について直接焼入れを実行した。本実施例に用いた冷却設備は、図8に示すように熱間圧延ラインに配置されている。図8に示す熱間圧延ラインは、加熱炉2、圧延機20、及び冷却設備3を備えている。加熱炉2では、鋳造後のスラブが所定温度まで加熱される。圧延機20は、レバース式圧延機であり、鋼板を所定の板厚及び板幅になるように複数パスの圧延を行う設備である。圧延機20によって所定の寸法に圧延された鋼板は、高温状態に加熱された状態にあり、その後冷却設備3を用いた熱処理工程が施される。また、冷却設備3の上流側の冷却設備3の入口から3m離れた位置には、鋼板の温度を測定する入側温度計82が設置されている。入側温度計82により測定された鋼板の温度データは、制御用コンピュータ10に送られる。なお、入側温度計82の上流側には、デスケーリング装置9が配置されており、デスケーリング装置9によって鋼板の表面に生成された酸化スケールが除去される。これにより、入側温度計82によって測定される温度データの測定誤差を低減できる。オンライン型の熱処理設備に配置される冷却設備3も、図1に示すものと同様のものを用いることができる。すなわち、冷却設備3は、鋼板を所定の冷却条件で水冷する水冷装置5及び拘束装置6を含む。但し、オンライン型の熱処理設備では、圧延機20による圧延が完了した鋼板が、所定の搬送速度で冷却設備3を通過する際に冷却設備3の入側において長手方向で鋼板温度が変化する。この点で、オフライン側の熱処理設備とは異なる。
2 加熱炉
3 冷却設備
4 形状計
5 水冷装置
6 拘束装置
7 テーブルロール
10 制御用コンピュータ
10a 水冷条件演算部
10b 拘束条件設定部
11 水冷流量制御装置
12 拘束ロール制御装置
13 圧下制御装置
14 圧下位置測定器
15 水切りパージノズル
15a 水切りパージ
16 上位計算機
17 形状情報生成部
18 形状予測モデル生成部
18a データベース部
18b 機械学習部
19 形状判定部
19a 操業条件再設定部
20 圧延機
51a,51b 水冷ノズル
61a,61b 拘束ロール
81,82,83 温度計
M 形状予測モデル
S 鋼板
W 冷却水
Claims (10)
- 加熱された鋼板に冷却水を噴射することによって鋼板を冷却する水冷装置と、前記冷却中の鋼板を少なくとも1対の拘束ロールによって拘束する拘束装置と、を備える鋼板の冷却設備における鋼板の形状予測方法であって、
前記水冷装置の操業パラメタと前記拘束装置の操業パラメタとのそれぞれから選択される少なくとも1つの操業パラメタを入力データ、前記冷却設備を通過した後の鋼板の形状情報を出力データとした機械学習によって生成された形状予測モデルを用いて、前記冷却設備を通過した後の前記鋼板の形状情報を予測するステップを含む、
鋼板の形状予測方法。 - 前記形状予測モデルは、前記入力データとして、前記鋼板の属性情報から選択される属性情報パラメタを含む、請求項1に記載の鋼板の形状予測方法。
- 前記水冷装置の操業パラメタには、冷却水量、冷却水の上下水量比、鋼板の冷却速度、及び冷却設備内での鋼板の搬送速度のうちの少なくとも1つが含まれる、請求項1又は2に記載の鋼板の形状予測方法。
- 前記拘束装置の操業パラメタには、前記拘束ロールの圧下位置及び圧下力のうちの少なくとも1つが含まれる、請求項1~3のうち、いずれか1項に記載の鋼板の形状予測方法。
- 請求項1~4のうち、いずれか1項に記載の鋼板の形状予測方法を用いて前記冷却設備を通過した後の鋼板の形状を予測し、予測した形状が予め設定された許容範囲内になるように前記水冷装置及び前記拘束装置の操業パラメタから選択した少なくとも1つの操業パラメタを再設定するステップを含む、鋼板の形状制御方法。
- 請求項5に記載の鋼板の形状制御方法を用いて鋼板を製造するステップを含む、鋼板の製造方法。
- 請求項1~4のうち、いずれか1項に記載の鋼板の形状予測方法を用いて前記冷却設備を通過した後の鋼板の形状を予測し、予測した形状に基づいて前記鋼板の処置工程を決定するステップを含む、鋼板の製造方法。
- 加熱された鋼板に冷却水を噴射することによって鋼板を冷却する水冷装置と、前記冷却中の鋼板を少なくとも1対の拘束ロールによって拘束する拘束装置と、を備える鋼板の冷却設備における鋼板の形状予測モデルの生成方法であって、
前記水冷装置の操業実績データと前記拘束装置の操業実績データとのそれぞれから選択される少なくとも一つの操業実績データを含む情報を入力実績データ、前記入力実績データに対応する前記冷却設備を通過した後の鋼板の形状情報を出力実績データとした、複数の学習用データを用いた機械学習によって、前記冷却設備を通過した後の鋼板の形状予測モデルを生成するステップを含む、
鋼板の形状予測モデルの生成方法。 - 前記機械学習として、ニューラルネットワーク、決定木学習、ランダムフォレスト、及びサポートベクター回帰の中から選択した機械学習を用いる、請求項8に記載の鋼板の形状予測モデルの生成方法。
- 加熱された鋼板に冷却水を噴射することによって鋼板を冷却する水冷装置と、前記冷却中の鋼板を少なくとも1対の拘束ロールによって拘束する拘束装置と、を備える冷却設備と、
前記冷却設備を通過した後の鋼板の形状情報を出力する形状予測部と、
を備え、
前記形状予測部は、前記水冷装置の操業パラメタと前記拘束装置の操業パラメタとのそれぞれから選択される少なくとも1つの操業パラメタを入力データ、前記冷却設備を通過した後の鋼板の形状情報を出力データとした機械学習モデルである、
鋼板の製造設備。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2022522010A JPWO2022176366A1 (ja) | 2021-02-18 | 2021-12-16 | |
KR1020237024562A KR20230121885A (ko) | 2021-02-18 | 2021-12-16 | 강판의 형상 예측 방법, 형상 제어 방법, 제조 방법,형상 예측 모델의 생성 방법, 및 제조 설비 |
CN202180094041.XA CN117083133A (zh) | 2021-02-18 | 2021-12-16 | 钢板的形状预测方法、形状控制方法、制造方法、形状预测模型的生成方法以及制造设备 |
EP21926790.3A EP4275806A1 (en) | 2021-02-18 | 2021-12-16 | Method for predicting shape of steel sheet, shape control method, manufacturing method, method for generating shape prediction model, and manufacturing equipment |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021-024366 | 2021-02-18 | ||
JP2021024366 | 2021-02-18 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022176366A1 true WO2022176366A1 (ja) | 2022-08-25 |
Family
ID=82930486
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/046560 WO2022176366A1 (ja) | 2021-02-18 | 2021-12-16 | 鋼板の形状予測方法、形状制御方法、製造方法、形状予測モデルの生成方法、及び製造設備 |
Country Status (5)
Country | Link |
---|---|
EP (1) | EP4275806A1 (ja) |
JP (1) | JPWO2022176366A1 (ja) |
KR (1) | KR20230121885A (ja) |
CN (1) | CN117083133A (ja) |
WO (1) | WO2022176366A1 (ja) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH02179826A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH02179827A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH02179828A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH02179829A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH02179819A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH08187505A (ja) * | 1995-01-05 | 1996-07-23 | Kobe Steel Ltd | 熱間圧延鋼板の形状予測方法 |
JPH105868A (ja) | 1996-06-18 | 1998-01-13 | Nippon Steel Corp | 制御冷却鋼板の形状制御方法 |
JP2006150411A (ja) | 2004-11-30 | 2006-06-15 | Jfe Steel Kk | 熱延鋼板の冷却方法 |
JP2018144050A (ja) | 2017-03-02 | 2018-09-20 | Jfeスチール株式会社 | 鋼板の冷却方法および鋼板の冷却装置ならびに鋼板の製造方法 |
JP2020157327A (ja) * | 2019-03-26 | 2020-10-01 | Jfeスチール株式会社 | 鋼板の仕上出側温度制御方法、鋼板の仕上出側温度制御装置、及び鋼板の製造方法 |
-
2021
- 2021-12-16 JP JP2022522010A patent/JPWO2022176366A1/ja active Pending
- 2021-12-16 KR KR1020237024562A patent/KR20230121885A/ko unknown
- 2021-12-16 WO PCT/JP2021/046560 patent/WO2022176366A1/ja active Application Filing
- 2021-12-16 CN CN202180094041.XA patent/CN117083133A/zh active Pending
- 2021-12-16 EP EP21926790.3A patent/EP4275806A1/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH02179826A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH02179827A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH02179828A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH02179829A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH02179819A (ja) * | 1988-12-28 | 1990-07-12 | Nippon Steel Corp | 熱間圧延鋼板の冷却制御装置 |
JPH08187505A (ja) * | 1995-01-05 | 1996-07-23 | Kobe Steel Ltd | 熱間圧延鋼板の形状予測方法 |
JPH105868A (ja) | 1996-06-18 | 1998-01-13 | Nippon Steel Corp | 制御冷却鋼板の形状制御方法 |
JP2006150411A (ja) | 2004-11-30 | 2006-06-15 | Jfe Steel Kk | 熱延鋼板の冷却方法 |
JP2018144050A (ja) | 2017-03-02 | 2018-09-20 | Jfeスチール株式会社 | 鋼板の冷却方法および鋼板の冷却装置ならびに鋼板の製造方法 |
JP2020157327A (ja) * | 2019-03-26 | 2020-10-01 | Jfeスチール株式会社 | 鋼板の仕上出側温度制御方法、鋼板の仕上出側温度制御装置、及び鋼板の製造方法 |
Non-Patent Citations (1)
Title |
---|
YOSHIZAWA ET AL.: "Automatic 3D Measurement of Shape by Grating Projection Method", JOURNAL OF THE JAPAN SOCIETY OF PRECISION ENGINEERING, vol. 53, no. 3, 1987, pages 422 - 426 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2022176366A1 (ja) | 2022-08-25 |
EP4275806A1 (en) | 2023-11-15 |
CN117083133A (zh) | 2023-11-17 |
KR20230121885A (ko) | 2023-08-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7147904B2 (ja) | 形鋼の曲がり予測方法、形鋼の製造方法、学習済の機械学習モデルの生成方法および形鋼の曲率予測装置 | |
JP5310965B1 (ja) | 熱延鋼板冷却方法 | |
WO2022176366A1 (ja) | 鋼板の形状予測方法、形状制御方法、製造方法、形状予測モデルの生成方法、及び製造設備 | |
WO2021229949A1 (ja) | 厚鋼板の温度偏差予測方法、厚鋼板の温度偏差制御方法、厚鋼板の温度偏差予測モデルの生成方法、厚鋼板の製造方法、及び厚鋼板の製造設備 | |
JP6897609B2 (ja) | 熱間圧延装置及び熱延鋼板の製造方法 | |
JP5482365B2 (ja) | 鋼板の冷却方法、製造方法および製造設備 | |
EP3922371B1 (en) | Method of cooling control for thick steel plate, cooling control device, and method of producing thick steel plate | |
KR101528690B1 (ko) | 강판 제조 방법 | |
WO2024062766A1 (ja) | 金属帯の反り形状予測方法、金属帯の反り形状制御方法、金属帯の製造方法、反り形状予測モデルの生成方法及び金属帯の反り形状制御装置 | |
WO2024062765A1 (ja) | 金属帯の反り形状制御方法、金属帯の製造方法及び金属帯の反り形状制御装置 | |
JP7424554B1 (ja) | 金属帯の製造設備、金属帯の合否判定方法及び金属帯の製造方法 | |
WO2024042825A1 (ja) | 金属帯の製造設備、金属帯の合否判定方法及び金属帯の製造方法 | |
JP7294242B2 (ja) | 表面粗さの予測方法、鋼帯の製造方法および学習済の機械学習モデルの生成方法 | |
JP7294243B2 (ja) | 熱処理レールの硬度予測方法、熱処理方法、硬度予測装置、熱処理装置、製造方法、製造設備、並びに、硬度予測モデルの生成方法 | |
JP7298529B2 (ja) | H形鋼の製造方法 | |
WO2022209320A1 (ja) | 鋼板の材質予測モデルの生成方法、材質予測方法、製造方法、及び製造設備 | |
JP7298645B2 (ja) | 形鋼の断面寸法変化量予測モデルの生成方法、形鋼の断面寸法変化量予測モデルの生成装置、形鋼の断面寸法の予測方法、形鋼の断面寸法の制御方法、および形鋼の製造方法 | |
JP6569691B2 (ja) | 不等辺不等厚山形鋼の製造方法 | |
JP7401040B1 (ja) | 金属帯の反り形状推定方法、金属帯の合否判定方法、金属帯の製造方法及び金属帯の反り形状推定設備 | |
JP6551282B2 (ja) | 熱間仕上圧延方法 | |
JP2023007380A (ja) | 熱延板の温度予測モデルおよび熱延板の変態エンタルピ予測モデルの生成方法、熱延板の巻取温度予測方法、温度制御方法、製造方法 | |
KR20220080174A (ko) | 강판의 제조 설비 및 제조 방법 | |
JP2001316757A (ja) | 鋼板、鋼板製造方法及び鋼板製造装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2022522010 Country of ref document: JP Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21926790 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20237024562 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202180094041.X Country of ref document: CN |
|
ENP | Entry into the national phase |
Ref document number: 2021926790 Country of ref document: EP Effective date: 20230811 |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112023016123 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112023016123 Country of ref document: BR Kind code of ref document: A2 Effective date: 20230810 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |