JP7156317B2 - Rolling mill control method, rolling mill control device, and steel plate manufacturing method - Google Patents

Description

The present invention relates to a rolling mill control method, a rolling mill control device, and a steel plate manufacturing method.

Generally, in a hot rolling process, a material to be rolled heated in a heating furnace is width-reduced by a width reduction device and then rolled to a predetermined thickness by a group of rolling mills. In a width reduction device, it is known that camber and wedge occur due to the temperature deviation in the width direction of the material to be rolled and the amount of off-center at the entry side during width reduction. Camber and wedge after width reduction and temperature deviation in the width direction of the material to be rolled, which are factors of left-right asymmetry, cause camber in the material to be rolled in the rolling mill, which causes damage to equipment such as roll flaws and side guides. In addition, it leads to a decrease in product yield and quality, as well as a decrease in the operating rate of the line. In addition, even in a hot rolling process that does not include a width reduction process, the temperature deviation in the width direction of the material to be rolled is cited as a factor that causes camber to occur in the material to be rolled on the delivery side of the rolling mill group in the rolling process. be done. This temperature deviation in the sheet width direction is caused by cooling from the extracting side by outside air flowing in when the extracting door is opened when extracting the material to be rolled that has been heated in the heating furnace. Therefore, in the rolling process, various techniques for suppressing the camber of the material to be rolled have been conventionally proposed.

In Patent Document 1, the amount of camber measured at the entrance and exit side of the rolling mill, at least the cast strand information of the material to be rolled, and the heating furnace that heats the material to be rolled. Rolling to set the leveling value of the rolling mill by accumulating the data of the distance between the inner materials, and assuming that the cast strand information and the material to be rolled that can be regarded as having the same distance between the materials in the furnace have the same temperature deviation in the width direction. A method for setting aircraft leveling is disclosed.

In Patent Document 2, the leveling value of the rolling mill is calculated based on the residence time of the material to be rolled in the soaking zone of the heating furnace, the interval between adjacent materials to be rolled in the heating furnace, and the width of the material to be rolled. A method for setting rolling mill leveling is disclosed.

Patent Document 3 describes the measured camber amount of the preceding material on the entry side of the rolling mill, the wedge of the preceding material on the entry side of the rolling mill, the camber amount of the preceding material on the exit side of the rolling mill, and the amount of camber calculated from these Using the calculated leveling amount, the amount of camber on the entrance side of the rolling mill of the material in question, and the wedge on the entrance side of the rolling mill, the amount of camber on the exit side of each rolling pass is predicted, and a predetermined influence coefficient is used. , a rolling mill leveling setting method for setting the leveling value for each rolling pass is disclosed.

JP 2017-225989 A Japanese Patent No. 6269536 JP 2018-153831 A

However, in the method described in Patent Document 1, the leveling setting of the rolling mill is only performed in consideration of the difference in deformation resistance in the width direction due to the temperature deviation in the width direction of the material to be rolled before the start of rolling. , cannot be applied when the material to be rolled has camber before the start of rolling.

In addition, the method described in Patent Document 2 only sets the leveling of the rolling mill in consideration of the heating conditions, and cannot be applied when the conditions of the steelmaking process, the width reduction process, and the rolling process change. .

In the method described in Patent Document 3, it is necessary to use pre-identified influence coefficients, and unless each influence coefficient table is sufficiently identified and managed, sufficient accuracy cannot be obtained and camber cannot be predicted with high accuracy. Even if it is possible, an error occurs in the calculated leveling amount.

In addition, even in the hot rolling process that does not include the width reduction process as described above, due to the temperature deviation in the width direction of the material to be rolled in the heating process, the material to be rolled on the delivery side of the group of rolling mills in the rolling process camber may occur. Therefore, it is desired to be applicable to a hot rolling process that does not include a width reduction process.

The present invention has been made in view of the above circumstances, and even if camber occurs due to steelmaking conditions, heating conditions, and rolling conditions, it is possible to reduce the impact on the delivery side of a group of rolling mills in the rolling process. It is an object of the present invention to provide a rolling mill control method, a rolling mill control device, and a steel plate manufacturing method that can suppress camber of a rolled material.

A method for controlling a rolling mill according to the present invention is a method of controlling a rolling mill when rolling a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace using a rolling mill comprising a plurality of rolling mills. A control method, wherein at least one operation parameter from each of an operation parameter group related to the steelmaking process of the material to be rolled, an operation parameter group related to the heating process, and an operation parameter group related to the rolling process is used to determine the roll reduction leveling amount of each rolling mill. and a control step of controlling each rolling mill based on the calculated roll reduction leveling amount of each rolling mill.

In the rolling mill control method according to the present invention, in the above invention, the calculating step includes at least a silicon equivalent as an operational parameter related to the steelmaking process, a soaking zone residence time as an operational parameter related to the heating process, and the rolling process As the operation parameters for the rolling equipment, the camber performance of the previous material with respect to the material to be rolled at the final rolling pass delivery side of the rolling device, and the reduction leveling amount of each rolling mill when rolling the previous material, are used in advance. Calculate the roll reduction leveling amount of each rolling mill using a regressor machine-learned so as to calculate the roll reduction leveling amount of each rolling mill that can control the camber amount on the delivery side of the sampling rolling pass to the control target value. A step is included.

In the method for controlling a rolling mill according to the present invention, in the above invention, the calculating step includes at least the width of the material to be rolled, the thickness of the material to be rolled, and the carbon content of the material to be rolled as operation parameters related to the steelmaking process. , the silicon equivalent of the material to be rolled, and the number of the casting machine in which the material to be rolled was refined and cast, the operation parameters related to the heating process, the soaking furnace residence time, and the extraction temperature, and the operation parameters related to the rolling process, to be rolled Actual camber on the delivery side of the final rolling pass of the rolling device in the preceding material one before the material, actual camber on the delivery side of the final rolling pass of the rolling device in the preceding material two lines before the material to be rolled, rolled The actual camber on the delivery side of the final rolling pass of the rolling mill for the preceding material three rolls before the material, the leveling amount of each rolling mill, the roll cumulative rolling amount of each rolling mill, the width of the material to be rolled before rolling, and the thickness of the material to be rolled. A regressor machine-learned to calculate the roll-down leveling amount of each rolling mill that can control the camber amount at the delivery side of the final rolling pass of the rolling mill to the control target value in advance using the thickness of the rolled material before rolling. is used to calculate the roll reduction leveling amount of each rolling mill.

A method for controlling a rolling mill according to the present invention is, in the above-described invention, wherein the rolling mill rolls the material to be rolled that has been width-reduced using a width reduction device in the width reduction step in the width reduction step after the heating step, and The calculating step uses at least one operation parameter from each of the operation parameter group related to the steelmaking process, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process. It is characterized by including a step of calculating a roll-down leveling amount of the machine.

In the rolling mill control method according to the present invention, in the above invention, the calculating step includes at least a silicon equivalent as an operational parameter related to the steelmaking process, and a soaking zone residence time and the width reduction as operational parameters related to the heating process. As operation parameters related to the process, the amount of width reduction, as operation parameters related to the rolling process, the actual camber of the previous material to the material to be rolled on the delivery side of the final rolling pass of the rolling mill, and each when the previous material was rolled Using the roll reduction leveling amount of the rolling mill, a regressor machine-learned so as to calculate the roll reduction leveling amount of each rolling mill that can control the camber amount on the exit side of the sampling rolling pass of the rolling mill to the control target value in advance. and calculating the roll reduction leveling amount of each rolling mill.

In the method for controlling a rolling mill according to the present invention, in the above invention, the calculating step includes at least the width of the material to be rolled, the thickness of the material to be rolled, and the carbon content of the material to be rolled as operation parameters related to the steelmaking process. , the silicon equivalent of the material to be rolled, and the number of the casting machine in which the material to be rolled was refined and cast, the operating parameters related to the heating process, the soaking furnace dwell time, and the extraction temperature, and the operating parameters related to the width reduction process, the width The amount of reduction, the amount of mold used, and the operation parameters related to the rolling process are the actual camber on the delivery side of the final rolling pass of the rolling mill in the preceding material one roll before the material to be rolled, and the The actual camber on the exit side of the final rolling pass of the rolling mill for the preceding material, the actual camber on the exit side of the final rolling pass of the rolling mill for the preceding material three rolls before the material to be rolled, the leveling amount of each rolling mill, each The amount of camber at the exit side of the final rolling pass of the rolling mill can be controlled to a control target value in advance by using the cumulative rolling amount of rolls of the rolling mill, the width of the material to be rolled before rolling, and the thickness of the material to be rolled before rolling. a step of calculating the roll reduction leveling amount of each rolling mill using a regressor machine-learned so as to calculate the roll reduction leveling amount of each rolling mill.

A control device for a rolling mill according to the present invention rolls a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace, using a rolling mill comprising a plurality of rolling mills. Using at least one operation parameter from each of the operation parameter group related to the steelmaking process of the rolled material, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process, It is characterized by comprising an arithmetic processing unit that calculates the roll reduction leveling amount of each rolling mill, and a control unit that controls each rolling mill based on the calculated roll reduction leveling amount of each rolling mill.

In the control device for a rolling mill according to the present invention, in the above invention, the arithmetic processing unit includes at least a silicon equivalent as an operational parameter related to the steelmaking process, a soaking zone residence time as an operational parameter related to the heating process, and the rolling As the operation parameters related to the process, the camber performance at the final rolling pass exit side of the rolling device of the previous material with respect to the material to be rolled, and the reduction leveling amount of each rolling mill when rolling the previous material are used, and the rolling is performed in advance. It has a machine-learned regressor to calculate the roll reduction leveling amount of each rolling mill that can control the camber amount on the delivery side of the final rolling pass of the device to the control target value, and the roll reduction leveling amount of each rolling mill is calculated. It is characterized in that the roll reduction leveling amount of each rolling mill is calculated using the regressor at the time of calculation.

In the control device for a rolling mill according to the present invention, in the above-described invention, the arithmetic processing unit includes at least a width of the material to be rolled, a thickness of the material to be rolled, a carbon amount, the silicon equivalent of the material to be rolled, and the number of the casting machine where the material to be rolled was refined and cast, the operating parameters related to the heating process, the time in the soaking furnace, and the extraction temperature, the operating parameters related to the rolling process, Actual camber on the delivery side of the final rolling pass of the rolling device in the preceding material one before the rolled material, actual camber on the delivery side of the final rolling pass of the rolling device in the preceding material two before the material to be rolled, The actual camber on the delivery side of the final rolling pass of the rolling mill for the preceding material three rolls before the rolled material, the leveling amount of each rolling mill, the roll cumulative rolling amount of each rolling mill, the width of the material to be rolled before rolling, and Regression machine-learned to calculate the roll-down leveling amount of each rolling mill that can control the camber amount on the delivery side of the final rolling pass of the rolling mill to the control target value in advance using the thickness of the material to be rolled before rolling. and calculating the roll reduction leveling amount of each rolling mill using the regressor when calculating the roll reduction leveling amount of each of the rolling mills.

A control device for a rolling mill according to the present invention is, in the above invention, wherein the rolling mill rolls the material to be rolled which has been width-reduced using a width reduction device in the width reduction step in the width reduction step after the heating step, and The arithmetic processing unit uses at least one operational parameter from each of the operational parameter group related to the steelmaking process, the operational parameter group related to the heating process, the operational parameter group related to the width reduction process, and the operational parameter group related to the rolling process to It is characterized by calculating the roll reduction leveling amount of the rolling mill.

In the rolling mill control device according to the present invention, in the above invention, the arithmetic processing unit includes at least a silicon equivalent as an operational parameter related to the steelmaking process, and a soaking zone residence time and the width as operational parameters related to the heating process. As operation parameters related to the reduction process, the amount of width reduction, and as operation parameters related to the rolling process, the actual camber of the previous material on the delivery side of the final rolling pass of the rolling device for the material to be rolled, and the camber when the previous material was rolled. A regression machine that is machine-learned to calculate the roll reduction leveling amount of each rolling mill that can control the camber amount on the delivery side of the final rolling pass of the rolling mill to the control target value in advance using the roll reduction leveling amount of each rolling mill. and calculating the roll reduction leveling amount of each rolling mill using the regressor when calculating the roll reduction leveling amount of each rolling mill.

In the control device for a rolling mill according to the present invention, in the above-described invention, the arithmetic processing unit includes at least a width of the material to be rolled, a thickness of the material to be rolled, a carbon amount, the silicon equivalent of the material to be rolled, and the number of the casting machine in which the material to be rolled was refined and cast, as operational parameters related to the heating process, the soaking zone residence time and extraction temperature, as operational parameters related to the width reduction process, The amount of width reduction, the amount of mold used, and the operation parameters related to the rolling process are the actual camber on the delivery side of the final rolling pass of the rolling device in the preceding material one roll before the material to be rolled, and the camber performance on the delivery side of the final rolling pass for the material to be rolled. The actual camber on the delivery side of the final rolling pass of the rolling mill in the preceding material, the actual camber on the delivery side of the final rolling pass of the rolling mill in the preceding material three rolls before the material to be rolled, the leveling amount of each rolling mill, The amount of camber at the delivery side of the final rolling pass of the rolling mill is controlled in advance to a control target value using the accumulated roll rolling amount of each rolling mill, the width of the material to be rolled before rolling, and the thickness of the material to be rolled before rolling. It has a regressor machine-learned so as to calculate the possible roll reduction leveling amount of each rolling mill, and the roll reduction leveling amount of each rolling mill is used when calculating the roll reduction leveling amount of each rolling mill. is characterized by calculating

A method for manufacturing a steel sheet according to the present invention is characterized by including the step of manufacturing a steel sheet using the method for controlling a rolling mill according to the above-described invention.

According to the present invention, a material to be rolled that has been refined and cast in a steelmaking process is heated in a heating furnace and rolled by a group of rough rolling mills to produce a steel sheet in a hot rolling process. It is possible to suppress the camber of the material to be rolled on the delivery side.

Drawing 1 is a figure showing an example of composition of a rolling mill and a control device in an embodiment. FIG. 2 is a diagram for explaining the roll reduction leveling amount of the rolling mill. FIG. 3 is a diagram for explaining the amount of camber of the material to be rolled. FIG. 4 is a flow chart showing an example of a method for controlling the rolling mill according to the embodiment. FIG. 5 is a diagram showing an example of experimental results using a model constructed using a neural network. FIG. 6 is a diagram showing an example of experimental results using a model constructed using XGBoost.

Hereinafter, a method for controlling a rolling mill, a control device for a rolling mill, and a method for manufacturing a steel sheet according to an embodiment of the present invention will be described with reference to the drawings. In the following embodiments, as an example of a rolling apparatus to which the present invention is applied, a rough rolling apparatus for a hot rolling line will be exemplified, but the present invention is not limited by the embodiments. Also, it should be noted that the drawings are schematic, and the dimensional relationship of each element, the ratio of each element, and the like may differ from the actual ones. Even between the drawings, there are cases where portions with different dimensional relationships and ratios are included. Moreover, in each drawing, the same code|symbol is attached|subjected to the same component.

[1. hot rolling line]
Drawing 1 is a figure showing an example of composition of a rolling mill and a control device in an embodiment. The control device 1 controls the roll reduction leveling amount of each rolling pass of the rough rolling device 10 that sequentially rolls a plurality of rolled materials 20 in a hot rolling line 100 . In the hot rolling line 100, the width reduction device 30, the heating furnace 40, and the continuous casting machine 50 are arranged on the upstream side of the rough rolling mill 10 on the conveying path, and the rough rolling mill 10 is arranged on the downstream side. Equipment such as finishing mills (not shown) are included. Continuous casting using the continuous casting machine 50 is included in the steelmaking process. The steelmaking process is a treatment process performed in the order of hot metal pretreatment, converter, secondary refining, and continuous casting.

For example, the material 20 to be rolled that has been refined and cast by the continuous casting machine 50 is heated in the heating furnace 40, then conveyed along the conveying route, passes through the width reduction device 30, and is then passed through the rough rolling device 10. Rolling is performed. The material 20 to be rolled after multiple pass rolling (rough rolling) in the hot rolling process passes through various equipment of the hot rolling line 100 such as a finishing rolling device, and is then coiled by a coiler (not shown). . The conveying path is for sequentially conveying a plurality of rolled materials 20 in the hot rolling line 100, and is composed of a plurality of conveying rolls (not shown).

In the hot rolling line 100, due to various factors such as temperature deviation and plate thickness deviation in the width direction of the material 20 to be rolled, and uneven opening of the rolling rolls in the width direction, the material 20 to be rolled bends in the horizontal direction, So-called camber may occur. If the amount of camber of the material to be rolled 20 is large, equipment such as rolling rolls and side guides may be damaged. Further, when the amount of camber caused by rough rolling is large, when the trailing end of the material 20 to be rolled hits the side guide in the finishing mill (not shown), the material 20 to be rolled collides with the edge portion. A rolling trouble called "restriction" may occur in which the roll is rolled in a folded state.

In the width reduction device 30, the main factors that cause camber are the temperature deviation in the plate width direction and the off-center to the press die. The temperature deviation in the strip width direction is caused by cooling from the extracting side by outside air flowing in when the extraction door is opened when the heated material 20 to be rolled is extracted in the heating furnace 40 . In addition, in the heating furnace 40, depending on the position where the material 20 to be rolled, which is different in length, is placed next to each other or the material to be rolled 20 is charged in the longitudinal direction, the heating state at the front and tail ends differs from that at the central part in the longitudinal direction. A directional temperature deviation occurs. In addition, the material 20 to be rolled is transported off-center with respect to the press die and subjected to width reduction, which causes laterally uneven reduction, resulting in camber and wedge.

In the rough rolling mill 10 , the camber and wedge of the material to be rolled 20 generated in the width reduction device 30 can be cited as factors that cause camber on the delivery side of the rolling mill. Further, the temperature deviation in the width direction of the material 20 to be rolled during the width reduction causes not only camber generation during the width reduction, but also camber generation in the rolling mill. Incidentally, when simply described as the delivery side of the rolling mill, it means the delivery side of the final rolling pass of the roughing mill 10 .

On the other hand, in order to suppress the camber, it is necessary to comprehensively consider the temperature difference in the width direction of the material 20 to be rolled and the operation parameters in the steelmaking process, heating process, width reduction process, and rolling process of the material 20 to be rolled. be. However, the parameters that can be used directly as a physical model are very limited among the operational parameters. Conventionally, the camber amount at the delivery side of the rolling mill is predicted using the temperature deviation of the material 20 to be rolled in the width direction, the camber amount that changes according to the leveling operation in the rolling mill, and the like. However, when a physical model is used, prediction is performed using only a limited set of parameters, and the prediction accuracy of the camber amount is insufficient.

Therefore, the present inventors have analyzed in detail the relationship between the occurrence of camber in rough rolling in the hot rolling process and the operating conditions during rolling, and earnestly studied methods for preventing camber. As a result of the study, using the operation parameter group related to the steelmaking process, heating process, width reduction process, and rolling process of the material 20 to be rolled, the camber amount at the delivery side of the rolling mill can be controlled to the control target value. By constructing a machine-learned regressor to calculate the roll reduction leveling amount and controlling each rolling mill based on the roll reduction leveling amount calculated using this regressor, the rolled product at the delivery side of the rolling mill It was found that the camber of the material 20 can be suppressed. In other words, in the present invention, by predicting the amount of camber and setting the leveling using a regressor that can comprehensively consider each operational parameter of the material to be rolled 20, it was confirmed that the accuracy was improved unlike before. .

[1-1. Rolling mill to be controlled]
The rough rolling device 10 performs multi-pass rolling (rough rolling of a plurality of rolling passes) of the total number of rolling passes N on the material 20 to be rolled, and the multi-pass rolling is performed by a plurality of rolling mills. It is configured. As shown in FIG. 1, the rough rolling mill 10 is a rolling mill group consisting of rolling mills 11 to 14 with a total of four stands. , a second rolling mill 12 , a third rolling mill 13 and a fourth rolling mill 14 . Each of the first to fourth rolling mills 11 to 14 is a four-high rolling mill having a pair of rolling rolls and a pair of backup rolls. The pair of rolling rolls are arranged at positions facing each other in the thickness direction D1 of the material to be rolled 20 with a carrier roll (not shown) interposed therebetween. The conveying direction of the material 20 to be rolled is the same as the longitudinal direction D2 of the material 20 to be rolled.

The first to fourth rolling mills 11 to 14 are provided with first to fourth rolling devices 11a to 14a, respectively. Each screw-down device 11a, 12a, 13a, 14a adjusts the screw-down leveling amount of the corresponding rolling mills 11, 12, 13, 14, respectively. As shown in FIG. 2, the reduction leveling amount Lv _i is defined as the difference in the reduction amount (reduction level) between both ends in the roll axial direction of the rolling rolls 11b and 11c that roll the material 20 to be rolled. The definition of the roll reduction leveling amount Lv _i is the same for the first to fourth rolling mills 11 to 14 . For example, when adjusting the reduction leveling amount of the first rolling mill 11, the first reduction device 11a is controlled, and when adjusting the reduction leveling amount of the second rolling mill 12, the second reduction device 12a is controlled. That is, the control device 1 can individually control the roll reduction leveling amounts of the rolling mills 11 to 14 .

[1-2. Control device]
The control device 1 includes a camber amount measuring section 2 , an arithmetic processing section 3 and a control section 4 .

The camber amount measuring unit 2 measures the amount of camber at the delivery side of the final rolling pass of the roughing mill 10 consisting of a plurality of rolling mills 11 to 14 to be controlled. It is optically detected by a device or the like and transmitted to the arithmetic processing section 3 . For example, the curvature of the camber of the material 20 to be rolled can be distinguished such that the curvature toward the working side of the rolls of the rolling mill is positive, and the curvature toward the drive side is negative. The details of the camber amount will be described later with reference to FIG.

The arithmetic processing unit 3 receives operation parameters (characteristic amounts) when manufacturing the material 20 to be rolled, and controls the rolling mills 11 to 14 so as to suppress camber on the delivery side of the final rolling pass of the roughing mill. It has a machine-learned regressor to output the leveling amount. When the material 20 to be rolled is rolled in a plurality of passes by the roughing mill 10 in the rolling process, the arithmetic processing unit 3 selects an operation parameter included in the operation parameter group and inputs it to the regressor, so that the rolling mill delivery side Obtain the roll-down leveling amount in each rolling mill that can control the camber amount at the control target value.

For example, the arithmetic processing unit 3 predicts the camber amount on the delivery side of the rolling mill constructed using a regressor and the relational expression between the leveling set value of the rolling mill at that time and each operation parameter. A camber amount and a leveling amount by each pass rolling in the rough rolling mill 10 are calculated. That is, the arithmetic processing unit 3 calculates (sets) the leveling amount for each rolling pass.

The control unit 4 executes roll-down leveling control for each rolling pass of the roughing mill 10 that performs a plurality of rolling passes on the material 20 to be rolled. Based on the leveling amount of each rolling mill calculated by the arithmetic processing unit 3, the control unit 4 controls the reduction devices 11a-14a of the rolling mills 11-14. The control unit 4 controls the reduction leveling amount of each rolling pass during multi-pass rolling by the roughing mill 10 through the control of the plurality of reduction devices 11a to 14a.

[2. Camber amount of rolled material]
Here, the camber amount will be described with reference to FIG. FIG. 3 is a diagram for explaining the camber amount Cam _i of the material 20 to be rolled. The longitudinal direction D2 of the material to be rolled 20 is the same as the conveying direction of the material to be rolled 20, and the front end side (forward direction) of the material to be rolled 20 is positive, and the tail end side (reverse direction) is negative. . The width direction D3 of the material to be rolled 20 is the same as the roll axial direction of the transport rolls and the roll axial direction of each of the rolling rolls of the rolling mills 11-14. Further, in the width direction D3, the left side (working side) is positive and the right side (driving side) is negative toward the positive side of the longitudinal direction D2. Moreover, the thickness direction (thickness direction) D1, the longitudinal direction D2, and the width direction D3 are directions perpendicular to each other.

As shown in FIG. 3, the camber amount _Cami of the material 20 to be rolled is the bending amount on the positive side or the negative side in the width direction D3 with respect to the longitudinal direction D2 of the material 20 on the delivery side of each rolling pass in multiple-pass rolling. Defined. Specifically, the camber amount Cam _i is defined as the maximum value of the distance between the width direction center position S1 of the material 20 to be rolled and the reference position S2 of the material 20 to be rolled on the delivery side of the i-th rolling pass.

The positive or negative sign of the camber amount Cam _i (camber generation direction) is determined by the relationship between the direction of positional deviation of the widthwise center position S1 from the reference position S2 of the material to be rolled 20 and the widthwise direction D3. In the material 20 to be rolled shown in FIG. 3, the center position S1 in the width direction is shifted to the positive side (working side) in the width direction D3 with respect to the reference position S2, so the camber amount Cam _i is a positive value. become. That is, although not shown, when the center position S1 in the width direction is shifted to the negative side in the width direction D3 with respect to the reference position S2, the camber amount _Cami becomes a negative value. The reference position S2 is represented by a straight line (reference line) passing through the widthwise center position Wa of the leading end portion 20a of the material 20 to be rolled and the widthwise center position Wb of the trailing end portion 20b. The amount of camber Cam _i is the distance between the widthwise center position S1 at the center position of the material 20 to be rolled in the longitudinal direction D2 and the reference position S2.

[3. Method of controlling rolling equipment]
Next, a method of controlling the rolling mill will be described with reference to FIG. FIG. 4 is a flow chart showing an example of a method for controlling the rolling mill according to the embodiment. The control method for the rolling mill shown in FIG. 4 is executed by the control device 1 . The control device 1 sequentially executes steps S101 to S103 shown in FIG.

As shown in FIG. 4, the control device 1 inputs each operation parameter of the material to be rolled 20 to the arithmetic processing unit 3 (step S101). In step S<b>101 , the actual camber obtained by the process computer or the camber amount measuring unit 2 is input to the arithmetic processing unit 3 .

After executing step S101, the control device 1 calculates the reduction leveling amount of each rolling pass during multi-pass rolling by the roughing mill 10 (step S102).

In this embodiment, in step S102, as a feature amount used when calculating the camber amount of the material 20 to be rolled on the delivery side of the roughing mill 10 and setting the roll reduction leveling amount of each of the rolling mills 11 to 14, The camber amount after rolling of the material 20 to be rolled and the rough rolling device are calculated using the operation parameter group related to each specification, steelmaking process, heating process, width reduction process, and rolling process obtained when the material 20 is extracted from the heating furnace 40. A relational expression is constructed to determine the roll reduction leveling amount of each of the rolling mills 11 to 14 that can control the camber amount on the delivery side of the final rolling pass of 10 to the control target value. Note that all feature amounts may be used to construct the relational expression, or feature amounts may be selected using techniques such as principal component analysis and contribution analysis. Moreover, not only quantitative variables such as temperature and dimensions, but also qualitative variables such as extraction furnace numbers, casting strand numbers, and steel grades can be used as feature quantities.

For example, by machine learning using XGBoost, which is one of machine learning techniques, the following feature amounts are selected from the importance of variables.

Specifically, the operational parameters relating to the steelmaking process include the number of the continuous caster that refined and cast the material 20 to be rolled, the carbon equivalent (C equivalent), and the silicon equivalent (Si equivalent). Operational parameters relating to the heating process include soaking furnace time, extraction furnace number, and extraction temperature. Operational parameters relating to the width reduction process include width reduction amount and accumulated mold usage amount. As operation parameters related to the rolling process, the actual camber on the delivery side of the final rolling pass of the rough rolling device 10 in the preceding material (previous material) one before the material to be rolled 20, and the preceding material two before the material to be rolled 20 The actual camber on the delivery side of the final rolling pass of the rough rolling mill 10, the camber performance on the delivery side of the final rolling pass of the rough rolling mill 10 in the preceding material three before the material to be rolled 20, each rolling mill 11 ~ 14 roll reduction leveling amount, roll cumulative rolling amount of each of the rolling mills 11 to 14, the width of the material 20 to be rolled before rolling, and the thickness of the material 20 to be rolled before rolling.

Among the above-mentioned operation parameter groups, as the feature values that contributed highly in each process, the silicon equivalent as an operation parameter in the steelmaking process, the soaking zone furnace time as an operation parameter in the heating process, and the operation parameter in the width reduction process , the width reduction amount, and as the operation parameters in the rolling process, the actual camber on the delivery side of the final rolling pass of the rough rolling device 10 in the preceding material one roll before the material 20 to be rolled, and the one before the material 20 to be rolled The reduction leveling amount of each rolling mill 11 to 14 in the preceding material can be mentioned.

Next, these feature values (operation parameters) were input to a regression machine, and a relational expression between each feature value and the amount of camber after rolling was created using a neural network. Furthermore, a relational expression for calculating a roll-down leveling amount that can control the predicted amount of camber corresponding to each operation parameter obtained from the similar feature amount and the obtained relational expression to the control target value was constructed. Here, the number of intermediate layers is set to three, and the number of nodes is set to 100 each. A sigmoid function was used as the activation function. The input data was normalized at the maximum and minimum values, and learning was performed with 7,000 coils in the operation data of 10,000 coils, and the model prediction accuracy was verified with the remaining 3,000 coils. The camber amount on the delivery side of the rolling mill for 10,000 coils had an error average of 10.1 mm and a standard deviation of 24.2 mm. The model prediction accuracy was an error average of 0.3 mm and a standard deviation of 15.1 mm.

Also, a relational expression for obtaining the amount of camber and the amount of reduction leveling after rolling of the material 20 to be rolled was created using XGBoost. Here, the learning rate is 0.2, the minimum value of loss reduction is 0.1, the maximum value of tree depth is 12, the minimum weight of child nodes is 1, and the number of times of boosting is 500. In the operation data for 10,000 coils, learning was performed with 7,000 coils, and the model prediction accuracy was verified with the remaining 3,000 coils. The camber amount on the delivery side of the rolling mill for 10,000 coils was 10.1 mm on average and 24.2 mm on the standard deviation. The model prediction accuracy was an error average of 0.2 mm and a standard deviation of 10.6 mm. From this result, prediction using XGBoost was superior as a regressor for predicting the amount of camber after rolling using each feature amount.

However, the regressor using machine learning is not particularly limited to that method. For example, decision trees, random forests, support vector regression, Gaussian processes, neural nets, XGBboost, etc. can be used. Furthermore, ensemble machine learning in which at least two or more regressors are combined can also be used.

In the embodiment, the settable range of the roll reduction leveling amount of the rough rolling mill 10 is the settable range of the roll reduction leveling amount of each of the first to fourth rolling mills 11 to 14 (hereinafter referred to as "settable range of roll reduction leveling amount" as appropriate abbreviated). That is, there are upper and lower limit values that can be set for each roll reduction leveling amount of each rolling mill based on the structure (equipment specifications) of each rolling mill. The settable range of the roll-down leveling amount is a finite range below the value and above the lower limit. Therefore, the arithmetic processing unit 3 calculates the roll-down leveling amount that can be executed within such a settable range of the roll-down leveling amount.

After executing step S102, the control device 1 controls the reduction leveling amount of each rolling pass when the material 20 to be rolled is rolled in a plurality of passes by the roughing mill 10 (step S103). In step S103, the control unit 4 controls the respective rolling devices 11a, 12a, 13a, and 14a based on the rolling pass leveling amount calculated in step S102 described above to The roll reduction leveling amount of each rolling pass during pass rolling is controlled. After executing step S103, the control device 1 terminates this process. Further, the present invention can also be implemented as a method of manufacturing a steel plate, for example, by rolling the material 20 to be rolled in the hot rolling process by the control method of the rolling apparatus in the above-described embodiment. That is, the steel sheet manufacturing method in the embodiment includes a step of manufacturing a steel sheet using the above-described control method for the rolling mill.

Note that the hot rolling line 100 may not include the width reduction device 30 . In this case, it is possible to carry out the calculation process described above without using the operation parameters relating to the width reduction process. For example, it is a hot rolling line obtained by removing the width reduction device 30 from the hot rolling line 100 shown in FIG. In the hot rolling line 100 without the width reduction device 30, the width reduction process is not performed. , may be determined by comprehensively considering operation parameters in the rolling process. That is, the operation parameter group related to the width reduction process is omitted from the feature amount when calculating the camber amount of the material 20 to be rolled on the delivery side of the rough rolling mill 10 and setting the reduction leveling amount of each of the rolling mills 11 to 14. . In short, using a group of operation parameters related to the steelmaking process, heating process, and rolling process of the material to be rolled 20, the amount of roll reduction leveling in each rolling mill that can control the camber amount on the delivery side of the rolling mill to the control target value is calculated. A machine-learned regressor is constructed in , and each rolling mill is controlled based on the roll-down leveling amount calculated using this regressor.

In the hot rolling line 100 without the width reduction device 30, the temperature deviation in the strip width direction is one of the factors that cause camber to occur on the delivery side of the rolling mill in the roughing mill 10. FIG. Even if the width reduction device 30 is not provided, the temperature deviation in the strip width direction is cooled from the extraction side by the outside air that flows in when the extraction door opens when the material 20 heated in the heating furnace 40 is extracted. caused by being Furthermore, in the heating furnace 40, the strip width is determined by the difference in the heating state at the leading and trailing ends compared to the longitudinal central portion due to the adjacency of the strips 20 having different lengths or the charging position of the strips 20 in the longitudinal direction. A directional temperature deviation occurs.

Here, the effects of the present invention will be described with reference to a verification example (Example 1) assuming the case where the embodiment in the hot rolling process described above is applied.

(Example 1)
The present invention was verified on a hot rolling line 100 having a width reduction device 30 equipped with a die for reducing the width of the material 20 to be rolled, and a four-high rolling mill consisting of work rolls and backup rolls. In Example 1, the object to be rolled is a slab having a length of 6000 to 8000 mm, a thickness of 260 mm, and a width of 900 to 1500 mm. The plate thickness is 30-40 mm.

In Table 1, as a prior art, the initial value is the roll gap leveling amount set so that there is no difference in the roll gap difference between the drive side and the work side when no load is applied before the start of rolling, and the roll gap leveling amount during rolling is is kept constant (conventional example: constant), and a method of performing a leveling operation based on visual information by an operator (conventional example: manual intervention). Furthermore, in Table 1, as an example using machine learning, the leveling setting of the rolling mill using all the feature values shown in the embodiment after extraction of the heating furnace and before the start of rolling for the target material whose camber should be controlled (Example: Neural network: all feature values), and a method of setting the leveling of the rolling mill using a model constructed using a neural network and a model constructed using XGBoost (Example: XGBoost: total feature quantity), among the selected feature quantities, as feature quantities that contribute highly in each process, the silicon equivalent in the steelmaking process, the soaking furnace time in the heating process, the width reduction amount in the width reduction process, the rolling process A method of setting the roll reduction leveling amount of the rolling mill using a prediction model constructed using XGBoost limited to the camber performance on the exit side of the final rolling pass of the previous material used as the current material (Example: XGBoost: limited) is exemplified.

In the example shown in Table 1, the control target value is 0 mm. As shown in Table 1, when the present invention was applied and a total of 500 coils were rolled, the leveling setting method using all feature amounts by XGBoost was the best, with an average camber amount of 0 mm and a standard deviation of 13 mm. . As described above, according to Example 1, by applying the hot rolling method according to the present invention, it was confirmed that the amount of camber can be controlled according to the control target value and that the number of strip threading failures associated with this leveling setting is reduced. did. As shown in FIGS. 5 and 6, the result of the model constructed using XGBoost (illustrated in FIG. 6) is better than the result of the model constructed using the neural network (illustrated in FIG. 5). , indicates that the amount of camber can be suppressed.

(Example 2)
As in Example 1, a hot rolling line 100 having a width reduction device 30 equipped with a die for reducing the width of the material 20 to be rolled, and a four-high rolling mill consisting of work rolls and backing rolls. The invention was verified. In Example 2, the object to be rolled is a slab having a length of 6000 to 8000 mm, a slab thickness of 230 mm and a width of 900 to 1500 mm. has a plate thickness of 30 to 40 mm.

In Table 2, as a prior art, the initial value is the roll gap leveling amount set so that there is no difference in the roll gap difference between the driving side and the working side when no load is applied before the start of rolling, and the roll gap leveling amount during rolling is is kept constant (conventional example: constant) and a method of performing a leveling operation based on visual information by an operator (conventional example: manual intervention). Furthermore, in Table 2, as an example using machine learning, using XGBoost, a camber prediction model constructed using all the feature values described in the embodiment and the leveling setting value of the rolling mill are used for roll reduction leveling A method for setting the amount (example: XGBoost: total feature amount) is exemplified.

In the example shown in Table 2, the control target value is 0 mm. As shown in Table 2, when this technology was applied and a total of 500 coils were rolled, the leveling setting method by XGBoost was the best, with an average camber amount of 1 mm and a standard deviation of 13 mm. As described above, according to Example 2, it was confirmed that by applying the hot rolling method according to the present invention, the camber amount can be controlled according to the control target value even when the rolling conditions are different. Therefore, the camber amount can be controlled to a low level according to the invention, and as a result, it is possible to reduce a decrease in the operation rate and equipment damage due to defective strip threading.

(Example 3)
As in Example 1, a hot rolling line 100 having a width reduction device 30 equipped with a die for reducing the width of the material 20 to be rolled, and a four-high rolling mill consisting of work rolls and backing rolls. The invention was verified. In Example 3, the object to be rolled is a slab having a length of 6000 to 8000 mm, a slab thickness of 260 mm, and a width of 900 to 1500 mm. The plate thickness at the exit side of the final rolling pass of the apparatus 10 was set to 30 to 40 mm. In other words, Example 3 is an example for a manufacturing process in which the width reduction process is not essential, that is, the hot rolling line 100 without the width reduction device 30 .

In Table 3, as a prior art, the initial value is the roll gap leveling amount set so that there is no difference in the roll gap difference between the driving side and the working side when no load is applied before the start of rolling, and the roll gap leveling amount during rolling is is kept constant (conventional example: constant) and a method of performing a leveling operation based on visual information by an operator (conventional example: manual intervention). Furthermore, in Table 3, as an example using machine learning, XGBoost is used, and the camber prediction model constructed using all the feature values described in the embodiment and the leveling setting value of the rolling mill are used for reduction leveling A method for setting the amount (example: XGBoost: total feature amount) is exemplified.

In the example shown in Table 3, the control target value is 0 mm. As shown in Table 3, when this technology was applied and a total of 500 coils were rolled, the leveling setting method by XGBoost was the best, with an average camber amount of −1 mm and a standard deviation of 12 mm. As described above, according to Example 3, it was confirmed that the amount of camber can be controlled according to the control target value by applying the hot rolling method according to the present invention.

As described above, according to the embodiment, the material 20 to be rolled that has been refined and cast in the steelmaking process is heated in a heating furnace and rolled by the rough rolling device 10 to manufacture a steel plate. , it is possible to suppress the camber of the material to be rolled 20 on the delivery side of the final rolling pass.

It should be noted that the present invention is not limited to the above-described embodiments, and can be modified as appropriate without departing from the scope of the present invention. For example, the rolling mill to be controlled is not limited to the roughing mill, and may be a rolling mill other than the roughing mill, such as a finishing mill.

Further, the rolling mill to be controlled (rough rolling mill 10) is not limited to a configuration including rolling mills with all four stands or all five stands. The number of rolling mills (the number of stands) constituting the rolling mill to be controlled may be one or plural as long as the material 20 to be rolled can be rolled in multiple passes. That is, in the present invention, the number of stands of the rolling mills constituting the rolling mill to be controlled is not particularly limited. In addition, the number of stages of each roll of the rolling mill is not limited to four, and may be any desired number. That is, the number of roll stages of the rolling mill and the total number of rolling passes in multi-pass rolling are not particularly limited.

Furthermore, the rolling mill that constitutes the rolling device is a rolling mill that rolls the material 20 in the forward direction (non-reversible rolling mill), or rolls the material 20 in the forward direction and in the reverse direction. Whether or not the rolling mill (reversible rolling mill) is used for the rolled material 20 is not particularly limited. That is, in the present invention, the rolling mills to be controlled may be configured such that all of a plurality of rolling mills are non-reversible or reversible, or one or more non-reversible rolling mills and one or more reversible rolling mills. It may be provided with a rolling mill of the type. Not only when the first rolling mill is a reversible rolling mill as in Example 2 described above, but when the second and subsequent rolling mills are a reversible rolling mill, the reversible rolling mill The rolling in the forward direction and the rolling in the reverse direction may be performed in any rolling pass of multiple pass rolling on the material 20 to be rolled. In this way, regardless of whether the rolling mill is a reversible type or a non-reversible type, if the camber amount of the material 20 to be rolled is measured at the entry side of the first rolling pass in the rolling mill, the camber in subsequent multiple-pass rolling can be determined. quantity can be predicted.

Further, the definition of positive and negative of the amount of camber (definition of the direction in which camber is generated) may be negative on the working side and positive on the driving side, contrary to the above-described embodiment. In other words, the curvature of the camber of the material 20 to be rolled may be distinguished such that the curvature toward the drive side of the rolls of the rolling mill is positive, and the curvature toward the work side is negative.

Furthermore, the present invention also includes a configuration in which the above-described constituent elements are appropriately combined. In addition, other embodiments, examples, operation techniques, etc. made by those skilled in the art based on the above-described embodiments are all included in the scope of the present invention.

1 control device 2 camber amount measuring unit 3 arithmetic processing unit 4 control unit 10 rough rolling device 11, 12, 13, 14 first to fourth rolling mills 11a, 12a, 13a, 14a first to fourth reduction devices 20 to be rolled Material 30 width reduction device 40 heating furnace 50 continuous casting machine 100 hot rolling line

Claims (9)

A method for controlling a rolling mill when rolling a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace using a rolling mill comprising a plurality of rolling mills,
a calculation step of calculating a roll reduction leveling amount of each rolling mill using at least one operation parameter from each of an operation parameter group related to the steelmaking process of the material to be rolled, an operation parameter group related to the heating process, and an operation parameter group related to the rolling process; ,
and a control step of controlling each rolling mill based on the calculated roll reduction leveling amount of each rolling mill ,
The calculation step includes at least silicon equivalent as an operational parameter related to the steelmaking process, a soaking furnace time as an operational parameter related to the heating process, and the rolling of the previous material with respect to the material to be rolled as an operational parameter related to the rolling process. Using the actual camber on the delivery side of the final rolling pass of the device and the roll reduction leveling amount of each rolling mill when rolling the previous material, the camber amount on the delivery side of the final rolling pass of the rolling device is set to the control target value in advance. Calculating a roll leveling amount for each controllable rolling mill using a regressor that is machine-learned to calculate a roll leveling amount for each controllable rolling mill.
A rolling mill control method characterized by: A method for controlling a rolling mill when rolling a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace using a rolling mill comprising a plurality of rolling mills,
a calculation step of calculating a roll reduction leveling amount of each rolling mill using at least one operation parameter from each of an operation parameter group related to the steelmaking process of the material to be rolled, an operation parameter group related to the heating process, and an operation parameter group related to the rolling process; ,
and a control step of controlling each rolling mill based on the calculated roll reduction leveling amount of each rolling mill,
In the calculating step, at least as operation parameters related to the steelmaking process, the width of the material to be rolled, the thickness of the material to be rolled, the carbon content of the material to be rolled, the silicon equivalent of the material to be rolled, and the refining and Casting machine number, operating parameters related to the heating process, soaking zone residence time, and extraction temperature, operating parameters related to the rolling process, final rolling of the rolling device in the preceding material one before the material to be rolled Camber performance on the delivery side of the pass, camber performance on the delivery side of the final rolling pass of the rolling mill in the preceding material two strips before the material to be rolled, final rolling of the rolling mill in the preceding material three strips before the material to be rolled Using the actual camber on the pass delivery side, the leveling amount of each rolling mill, the roll cumulative rolling amount of each rolling mill, the width of the material to be rolled before rolling, and the thickness of the material to be rolled before rolling, A step of calculating the roll reduction leveling amount of each rolling mill using a regressor machine-learned so as to calculate the roll reduction leveling amount of each rolling mill capable of controlling the camber amount on the delivery side of the final rolling pass to the control target value. A method of controlling a rolling mill , comprising: A method for controlling a rolling mill when rolling a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace using a rolling mill comprising a plurality of rolling mills,
a calculation step of calculating a roll reduction leveling amount of each rolling mill using at least one operation parameter from each of an operation parameter group related to the steelmaking process of the material to be rolled, an operation parameter group related to the heating process, and an operation parameter group related to the rolling process; ,
and a control step of controlling each rolling mill based on the calculated roll reduction leveling amount of each rolling mill,
The rolling device rolls the material to be rolled that has been width-reduced using the width reduction device in the width reduction step after the heating step,
The calculating step includes:
Reduction leveling of each rolling mill using at least one operation parameter from each of the operation parameter group related to the steelmaking process, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process. calculating the amount;
At least, as an operational parameter related to the steelmaking process, the silicon equivalent, as an operational parameter related to the heating process, a soaking zone residence time, as an operational parameter related to the width reduction process, a width reduction amount, and as an operational parameter related to the rolling process, the subject Using the actual camber of the previous material on the delivery side of the final rolling pass of the rolling mill for the rolled material and the amount of roll reduction leveling of each rolling mill when rolling the previous material, calculating the roll reduction leveling amount of each rolling mill using a regressor machine-learned to calculate the roll reduction leveling amount of each rolling mill that can control the camber amount of the control target value. A control method for a rolling mill characterized by: A method for controlling a rolling mill when rolling a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace using a rolling mill comprising a plurality of rolling mills,
a calculation step of calculating a roll reduction leveling amount of each rolling mill using at least one operation parameter from each of an operation parameter group related to the steelmaking process of the material to be rolled, an operation parameter group related to the heating process, and an operation parameter group related to the rolling process; ,
and a control step of controlling each rolling mill based on the calculated roll reduction leveling amount of each rolling mill,
The rolling device rolls the material to be rolled that has been width-reduced using the width reduction device in the width reduction step after the heating step,
The calculating step includes:
Reduction leveling of each rolling mill using at least one operation parameter from each of the operation parameter group related to the steelmaking process, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process. calculating the amount;
At least, as operation parameters related to the steelmaking process, the width of the material to be rolled, the thickness of the material to be rolled, the carbon content of the material to be rolled, the silicon equivalent of the material to be rolled, and the casting machine in which the material to be rolled was refined and cast number, the soaking zone residence time and extraction temperature as operation parameters related to the heating process, the amount of width reduction and the amount of mold used as operation parameters related to the width reduction process, and the material to be rolled as operation parameters related to the rolling process Actual camber on the delivery side of the final rolling pass of the rolling device in the preceding material one before, Camber performance on the delivery side of the final rolling pass of the rolling device in the preceding material two before the material to be rolled, Material to be rolled The actual camber on the delivery side of the final rolling pass of the rolling mill in the preceding material three years before, the leveling amount of each rolling mill, the roll cumulative rolling amount of each rolling mill, the width of the material to be rolled before rolling, and the rolling Using the plate thickness before rolling of the material, a regression machine that has been machine-learned so as to calculate the roll-down leveling amount of each rolling mill that can control the camber amount on the delivery side of the final rolling pass of the rolling mill to the control target value in advance. A method of controlling a rolling mill , comprising a step of calculating a roll reduction leveling amount of each rolling mill using a rolling mill. A control device for a rolling mill that rolls a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace using a rolling mill comprising a plurality of rolling mills,
Reduction of each rolling mill using at least one operation parameter from each of the operation parameter group related to the steelmaking process of the material to be rolled, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process. an arithmetic processing unit that calculates the amount of leveling;
a control unit that controls each rolling mill based on the calculated roll reduction leveling amount of each rolling mill ;
with
The arithmetic processing unit includes at least silicon equivalent as an operational parameter related to the steelmaking process, a soaking zone residence time as an operational parameter related to the heating process, and a prior material to the material to be rolled as an operational parameter related to the rolling process. Using the actual camber on the exit side of the final rolling pass of the rolling mill and the roll reduction leveling amount of each rolling mill when rolling the previous material, the camber amount on the exit side of the final rolling pass of the rolling mill is set to a control target value in advance. has a regressor machine-learned so as to calculate the roll reduction leveling amount of each rolling mill that can be controlled by the rolling mill, and the roll reduction of each rolling mill is used when calculating the roll reduction leveling amount of each rolling mill. Calculate leveling amount
A control device for a rolling mill characterized by: A control device for a rolling mill that rolls a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace using a rolling mill comprising a plurality of rolling mills,
Reduction of each rolling mill using at least one operation parameter from each of the operation parameter group related to the steelmaking process of the material to be rolled, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process. an arithmetic processing unit that calculates the amount of leveling;
a control unit that controls each rolling mill based on the calculated roll reduction leveling amount of each rolling mill;
with
The arithmetic processing unit has at least the operation parameters related to the steelmaking process, the width of the material to be rolled, the thickness of the material to be rolled, the carbon content of the material to be rolled, the silicon equivalent of the material to be rolled, and the refining of the material to be rolled. And the number of the casting machine that was cast, the operation parameters related to the heating process, the soaking zone residence time, and the extraction temperature, and the operation parameters related to the rolling process, the final of the rolling mill in the preceding material one before the material to be rolled. Actual camber on the delivery side of the rolling pass, actual camber on the delivery side of the final rolling pass of the rolling mill in the preceding material two strips before the material to be rolled, final camber performance of the rolling mill in the preceding material three strips before the material to be rolled Using the actual camber on the delivery side of the rolling pass, the leveling amount of each rolling mill, the roll cumulative rolling amount of each rolling mill, the width of the material to be rolled before rolling, and the thickness of the material to be rolled before rolling, the rolling equipment It has a machine-learned regressor to calculate the roll reduction leveling amount of each rolling mill that can control the camber amount on the delivery side of the final rolling pass to the control target value, and calculates the roll reduction leveling amount of each rolling mill. A control device for a rolling mill , wherein the roll reduction leveling amount of each rolling mill is calculated using the regressor when rolling. A control device for a rolling mill that rolls a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace using a rolling mill comprising a plurality of rolling mills,
Reduction of each rolling mill using at least one operation parameter from each of the operation parameter group related to the steelmaking process of the material to be rolled, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process. an arithmetic processing unit that calculates the amount of leveling;
a control unit that controls each rolling mill based on the calculated roll reduction leveling amount of each rolling mill;
with
The rolling device rolls the material to be rolled that has been width-reduced using the width reduction device in the width reduction step after the heating step,
The arithmetic processing unit is
Reduction leveling of each rolling mill using at least one operation parameter from each of the operation parameter group related to the steelmaking process, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process. calculate the amount of
At least, as an operational parameter related to the steelmaking process, the silicon equivalent, as an operational parameter related to the heating process, a soaking zone residence time, as an operational parameter related to the width reduction process, a width reduction amount, and as an operational parameter related to the rolling process, the subject Using the actual camber of the previous material on the delivery side of the final rolling pass of the rolling mill for the rolled material and the amount of roll reduction leveling of each rolling mill when rolling the previous material, It has a regressor machine-learned so as to calculate the roll reduction leveling amount of each rolling mill that can control the camber amount of to the control target value, and when calculating the roll reduction leveling amount of each of the rolling mills, the regressor is used A control device for a rolling mill , characterized in that it calculates a roll reduction leveling amount of each rolling mill using a rolling mill. A control device for a rolling mill that rolls a material to be rolled that has been refined and cast in a steelmaking process and heated in a heating furnace using a rolling mill comprising a plurality of rolling mills,
Reduction of each rolling mill using at least one operation parameter from each of the operation parameter group related to the steelmaking process of the material to be rolled, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process. an arithmetic processing unit that calculates the amount of leveling;
a control unit that controls each rolling mill based on the calculated roll reduction leveling amount of each rolling mill;
with
The rolling device rolls the material to be rolled that has been width-reduced using the width reduction device in the width reduction step after the heating step,
The arithmetic processing unit is
Reduction leveling of each rolling mill using at least one operation parameter from each of the operation parameter group related to the steelmaking process, the operation parameter group related to the heating process, the operation parameter group related to the width reduction process, and the operation parameter group related to the rolling process. calculate the amount of
At least, as operation parameters related to the steelmaking process, the width of the material to be rolled, the thickness of the material to be rolled, the carbon content of the material to be rolled, the silicon equivalent of the material to be rolled, and the casting machine in which the material to be rolled was refined and cast number, the soaking zone residence time and extraction temperature as operation parameters related to the heating process, the amount of width reduction and the amount of mold used as operation parameters related to the width reduction process, and the material to be rolled as operation parameters related to the rolling process Actual camber on the delivery side of the final rolling pass of the rolling device in the preceding material one before, Camber performance on the delivery side of the final rolling pass of the rolling device in the preceding material two before the material to be rolled, Material to be rolled The actual camber on the delivery side of the final rolling pass of the rolling mill in the preceding material three years before, the leveling amount of each rolling mill, the roll cumulative rolling amount of each rolling mill, the width of the material to be rolled before rolling, and the rolling Using the plate thickness before rolling of the material, a regression machine that has been machine-learned so as to calculate the roll-down leveling amount of each rolling mill that can control the camber amount on the delivery side of the final rolling pass of the rolling mill to the control target value in advance. and calculating the roll reduction leveling amount of each rolling mill using the regressor when calculating the roll reduction leveling amount of each of the rolling mills . A method for manufacturing a steel plate, comprising the step of manufacturing a steel plate using the method for controlling a rolling mill according to any one of claims 1 to 4 .

Images