Rolling mill thickness control device

Abstract

This plate thickness control device of a rolling mill, which rolls a material-to-be-rolled to obtain a target plate thickness of a product, comprises a thickness deviation learning unit and a gap correction amount calculation unit. The plate thickness deviation learning unit learns a tendency of a plate thickness deviation that is the difference between the plate thickness of a product and the actual plate thickness of a material-to-be-rolled, which is measured in the outlet side of the rolling mill. In addition, the plate thickness deviation learning unit adopts, as the material-to-be-rolled, a material-to-be-rolled intended to be rolled by means of the rolling mill, and predicts, before rolling the material-to-be-rolled, the plate thickness deviation of the material-to-be-rolled on the basis of product information including the kind of steel and the plate thickness of a product of the material-to-be-rolled, and a value of the material-to-be-rolled measured at the upstream side of the rolling mill. The gap correction amount calculation unit calculates a gap correction amount for correcting a roll gap of the rolling mill so as to negate the plate thickness deviation predicted by the plate thickness deviation learning unit. The plate thickness control device of the rolling mill adjusts the roll gap of the rolling mill on the basis of the gap correction amount calculated by the gap correction amount calculation unit before rolling the material-to-be-rolled.

Description

[Technical Field]

[0001] The present disclosure relates to a plate thickness control device for a rolling mill, and more particularly to a plate thickness control device for a tandem rolling mill having multiple stands. [Background technology]

[0002] For example, in a hot rolling process, the thickness of the material being rolled is controlled to the product thickness (set thickness) by appropriately adjusting the gap between the upper and lower work rolls of the rolling mill (hereinafter referred to as the "roll gap") using a reduction device. Known examples of this type of control include monitor AGC (Automatic Gauge Control) and absolute value AGC.

[0003] Monitor AGC is a feedback control based on measurements from a thickness gauge installed behind the rolling mill in the direction of conveyance of the rolled material. Monitor AGC has the advantage of being able to use highly reliable thickness measurements. However, with Monitor AGC, there is a delay in the measurements from the thickness gauge installed behind the rolling mill, which causes a delay in control, making it difficult to eliminate thickness deviations at the leading edge of the rolled material (deviation between the product thickness and the actual thickness).

[0004] Absolute value AGC is a feedback control that uses the rolling mill delivery thickness predicted (estimated) by a gauge meter method based on the measured values ​​of the load generated during rolling and the roll gap. Absolute value AGC can reduce control delays because it can use the rolling load and roll gap, which do not cause measurement delays. However, if the thickness prediction accuracy is low, it can become a factor that causes thickness fluctuations.

[0005] However, immediately after the start of rolling, the measured values ​​used in the thickness control are unstable. This makes it difficult to accurately control the thickness of the tip of the rolled material. For example, the temperature at the tip of the rolled material fluctuates greatly, making it difficult to suppress thickness deviations caused by temperature fluctuations through the thickness control. As a result, the product thickness deviates from the tolerance, resulting in a decrease in yield.

[0006] Patent Document 1 listed below discloses a method for manufacturing a hot-rolled sheet, which is a material to be rolled. In this method, a thickness chart for the leading edge of the hot-rolled sheet is recorded in advance for each steel type and thickness. Then, a thickness chart for the same steel type and thickness as the hot-rolled sheet to be rolled is read out, and the roll gap is adjusted taking into account the read thickness chart and tolerances, thereby shortening the thickness deviation length at the leading edge, and as a result, improving the yield.

[0007] Furthermore, Patent Document 2 below discloses an automatic thickness control method for a rolling mill. This method is a feedforward AGC that corrects the roll gap based on the measurement value of a thickness gauge installed on the entry side of the rolling mill. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Japanese Patent Publication No. 2013-198920 [Patent Document 2] Japanese Patent Publication No. 1-154814 Summary of the Invention [Problem to be solved by the invention]

[0009] However, in Patent Document 1, the factors that cause thickness deviation are limited to the steel type and the thickness, and therefore thickness deviations that may occur due to other factors cannot be suppressed. Furthermore, Patent Document 2 cannot be applied to cases where a thickness gauge is not installed on the entry side of the rolling mill. In the case of a tandem rolling mill, it is known that the thickness measured by the thickness gauge on the entry side of the rolling mill does not contribute much to suppressing thickness deviations.

[0010] The present disclosure has been made to solve the above-mentioned problems, and aims to provide a rolling mill thickness control device that can improve thickness accuracy by suppressing thickness deviations that may occur due to factors that cause thickness deviations other than steel type and thickness. [Means for solving the problem]

[0011] The first aspect relates to a thickness control device for a rolling mill that rolls a material to be rolled to a target product thickness. The thickness control device includes a thickness deviation learning unit and a gap correction amount calculation unit. The thickness deviation learning unit learns the trend of thickness deviation, which is the difference between the product thickness and the actual thickness of the material measured at the delivery side of the rolling mill. The thickness deviation learning unit predicts the thickness deviation of the material to be rolled based on product information including the product thickness and steel type of the material and measurement values ​​of the material measured upstream of the rolling mill, before rolling the material. The gap correction amount calculation unit calculates a gap correction amount for correcting the roll gap of the rolling mill so as to cancel out the thickness deviation predicted by the thickness deviation learning unit. The thickness control device for the rolling mill adjusts the roll gap of the rolling mill based on the gap correction amount calculated by the gap correction amount calculation unit before rolling the material. The measured value of the rolled material is the temperature of the rolled material measured upstream of the rolling mill.

[0013] No. 2 The first perspective is To the point In addition, the present invention further has the following features: The thickness deviation learning unit learns a learning thickness deviation obtained by adding an actual thickness deviation determined from the actual thickness of the rolled material to the predicted thickness deviation of the rolled material.

[0014] No. 3 The first perspective is To the point In addition, the present invention further has the following features: It is further provided with a thickness deviation average calculation unit that calculates an average value of the thickness deviation at the tip end of the rolled material predicted by the thickness deviation learning unit, and the gap correction amount calculation unit calculates a gap correction amount so as to cancel out the average value calculated by the thickness deviation average calculation unit. [Effects of the Invention]

[0015] In the first aspect, a thickness deviation learning unit is used to predict thickness deviation based on not only the product thickness and steel grade but also measurements taken upstream of the rolling mill, and the roll gap of the rolling mill is adjusted to cancel out the predicted thickness deviation, thereby suppressing thickness deviations that may occur due to factors other than the product thickness and steel grade. As a result, the thickness accuracy of the rolled material can be improved.

[0016] According to the second aspect, by predicting the thickness deviation of the rolled material taking into account the temperature of the rolled material measured upstream of the rolling mill, it is possible to suppress the thickness deviation that occurs due to this temperature as a factor causing the thickness deviation.

[0017] According to the third aspect, the learning value of the thickness deviation learning unit is updated by the learning thickness deviation, thereby improving the accuracy of predicting the thickness deviation by the thickness deviation learning unit, thereby further improving the thickness accuracy of the rolled material.

[0018] According to the fourth aspect, it is possible to improve the yield at the tip end of the rolled material. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 1 is a schematic diagram for explaining a system configuration of a rolling plant. [Figure 2] 1 is a schematic diagram showing the configuration of a plate thickness control device for a rolling mill according to a first embodiment. [Figure 3] FIG. 10 is a diagram showing an example of calculation of the amount of change in reduction rate of each stand. [Figure 4] FIG. 1 is a diagram illustrating an example of a hardware configuration of a process control computer that implements a plate thickness control device. [Figure 5] FIG. 10 is a schematic diagram showing the configuration of a plate thickness control device for a rolling mill according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0020] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Note that elements common to the various drawings will be assigned the same reference numerals and redundant explanations will be omitted.

[0021] Embodiment 1 1 is a schematic diagram showing the configuration of a rolling plant 1. The rolling plant 1 takes steel or other metallic material as a material to be rolled M and hot rolls the material M into a plate shape.

[0022] The rolling plant 1 is equipped with, as its main equipment, a heating furnace 2, a roughing mill 3, a crop shear 4, a finishing mill 5 as a hot rolling mill, a cooling device 6, and a winder 7. In this embodiment, an example will be described in which the plate thickness at the delivery side of the finishing mill 5 as a hot rolling mill is controlled to the product plate thickness (for example, 3.0 mm).

[0023] The heating furnace 2 is configured to heat a slab, which is a material M to be rolled before rolling, to a predetermined temperature. The heating temperature is, for example, 1200°C. La The tube is, for example, a rectangular parallelepiped with a thickness of 200 to 250 mm, a width of 800 to 2000 mm, and a length of 5 to 12 m.

[0024] The roughing mill 3 has at least one, usually one to three, rolling stands, and is configured to roll the material M heated in the heating furnace 2 in a forward direction (from the upstream side to the downstream side of the rolling line) and a reverse direction (from the downstream side to the upstream side of the rolling line) in multiple passes. The roughing mill 3 may be equipped with a width adjustment device called an edger (not shown).

[0025] The crop shear 4 is configured to cut off any defective shape portions present at the leading or trailing end of the material M to be rolled using upper and lower blades based on the shape measured by a shape detector 81 described later.

[0026] The finishing mill 5 corresponds to the rolling mill of this embodiment. The finishing mill 5 is a tandem rolling mill equipped with a plurality of rolling stands (hereinafter referred to as "stands") F i (1≦i≦N) arranged side by side in the conveying direction of the rolled material M. i is the stand number. In this embodiment, the case where N=7, i.e., seven stands F1 to F7 are arranged side by side, will be described as an example. Each stand F1 to F7 is equipped with two upper and lower work rolls 51, two upper and lower backup rolls 52, and an electric motor 53 for roll rotation. The backup rolls 52 are provided with a screw down device 54, which is configured to adjust the roll gap between the upper and lower work rolls 51. The rolling load of each stand F1 to F7 is measured by a rolling load sensor 55. The rolling load sensor 55 is, for example, a load cell. The roll gap of each rolling stand F1 to F7 can be measured by a magnescale (not shown).

[0027] The cooling device 6 is provided on a run-out table (not shown). The cooling device 6 is configured to be able to cool the rolled material M by injecting water into the rolled material M using a cooling bank. The cooled rolled material M is wound into a coil by a winding machine 7.

[0028] Various sensors serving as various measuring instruments are installed at key points in the rolling plant 1. Key points in the rolling plant 1 include, for example, the outlet side of the heating furnace 2, the outlet side of the roughing mill 3, the outlet side of the finishing mill 5, and the inlet side of the winder 7. Various sensors may also be installed between stands F1 to F7 of the finishing mill 5. The various sensors include a shape detector 81 capable of measuring the shape (including width) of the material M to be rolled at the outlet side of the roughing mill 3, a thermometer 82 that measures the surface temperature of the material M to be rolled at the upstream side of the finishing mill 5, a thickness gauge 83 that measures the actual thickness of the material M to be rolled at the outlet side of the finishing mill 5, and the rolling load sensor 55 that measures the rolling load at each of the stands F1 to F7. The various sensors sequentially measure the material M to be rolled and the status of each piece of equipment.

[0029] The rolling plant 1 is operated (commissioned) by a control system using a computer. The computer includes a host computer 10 and a process control computer 11, which are connected to each other via a network. The host computer 10 calculates a thickness schedule for realizing the product thickness of the material M to be rolled. The calculated thickness schedule includes the thickness at the outlet of each stand Fi. The host computer 10 further calculates the roll gap of each stand Fi for realizing the thickness at the outlet of each stand Fi. The calculated roll gap of each stand Fi is input as a setting calculation to a thickness control unit 113, which will be described later. An interface screen 12, which is an operation screen for an operator, is connected to the process control computer 11 via the network. The operator can perform operations such as inputting control conditions on the interface screen 12.

[0030] The process control computer 11 executes setting calculations and controls of control targets in a series of rolling processes. The process control computer 11 also has a function of correcting the roll gap of each of the stands F1 to F7. Product information is input to the process control computer 11 from the host computer 10. The product information includes target information (product target) such as the product thickness and product width of the rolled material M heated in the heating furnace 2, as well as the steel type.

[0031] The process control computer 11 appropriately controls each piece of equipment based on the target information and control conditions provided from the interface screen 12. When the material to be rolled M is transported to a predetermined position in the rolling plant 1, the process control computer 11 calculates the settings for each piece of equipment that will achieve the target information, and operates the actuators of each piece of equipment based on these setting values. While each piece of equipment is operating, the operation of the actuators is corrected according to values ​​obtained from various measuring instruments. The process control computer 11 adjusts the roll gap of each stand F1 to F7 of the finishing rolling mill 5 according to the rolling load and actual thickness so that the actual thickness of the material to be rolled M matches the product thickness (i.e., so as to cancel out thickness deviations).

[0032] 2 is a schematic diagram showing the configuration of a process control computer 11 which is a strip thickness control device for a rolling mill according to embodiment 1. The process control computer 11 includes a strip thickness deviation learning unit 111, a gap correction amount calculation unit 112, and a strip thickness control unit 113.

[0033] After rolling, the thickness deviation learning unit 111 learns the trend of thickness deviation, which is the difference between the actual thickness measured by the thickness gauge 83 on the exit side of the finishing mill 5 and the product thickness. Thickness deviation learning is performed based on (associated with) product information and measurement values ​​measured upstream of the finishing mill 5. The product information includes, for example, at least the product thickness and steel grade, and may further include product width. The measurement values ​​are factors that cause thickness deviation other than the steel grade and thickness, and may include, for example, at least the temperature of the material M to be rolled measured by the thermometer 82 on the entry side of the finishing mill 5 (hereinafter also referred to as "finishing entry temperature"), and the width of the material M to be rolled measured by the shape detector 81 on the entry side of the finishing mill 5. Furthermore, the thickness deviation for learning to be learned after rolling can be the thickness deviation for each meter predicted by the thickness deviation learning unit 111 before rolling plus the actual thickness deviation calculated from the actual thickness at the corresponding position of the rolled material M measured by the thickness meter 83. Learning accuracy is improved by updating the learning value each time the rolled material M is rolled. Online learning can be performed by configuring the thickness deviation learning unit 111 with a neural network, which will be described later.

[0034] The thickness deviation learning unit 111 uses a machine learning function to predict the thickness deviation for each predetermined length (e.g., 1 m) of the material M to be rolled (hereinafter also referred to as "the material M to be rolled") to be rolled by the finishing rolling mill 5 before rolling. As the machine learning function, for example, the above-mentioned neural network or the like can be used. In this case, the input layer can be items related to thickness deviation, such as product thickness, product width, finishing entry temperature, and rolling distance, and the output layer can be the predicted thickness deviation of the material M to be rolled (hereinafter also referred to as "predicted thickness deviation").

[0035] The gap correction amount calculation unit 112 has a function of calculating the correction amount of the roll gap so as to cancel out the predicted thickness deviation of the rolled material M predicted by the thickness deviation learning unit 111. The gap correction amount calculation unit 112 first calculates the thickness correction amount due to roll gap correction. The thickness correction amount is calculated based on the change in the reduction rate of each stand Fi based on the delivery thickness of each stand Fi in the thickness schedule calculated by the host computer 10. The reduction rate is defined by the following equation (1).

[0036]

number

[0037] where i represents the stand number and r i teeth each Stan DoF represents the reduction ratio of i, and h i represents the delivery thickness of each stand F in the thickness schedule. The change in the reduction rate is expressed by the following equation (2).

[0038]

number

[0039] where Δr i represents the change in the reduction rate of stand Fi, and Δh i represents the thickness correction amount in stand F. If the total number of stands is N (N=7 in this embodiment), the thickness correction amount Δh of the final stand FN (F7 in this embodiment) is N represents the predicted thickness deviation.

[0040] By the way, the plate thickness correction amount Δh of the final stand FN N is significantly larger than the other stands (F1 to F6 in this embodiment), that is, when the plate thickness is rapidly reduced in the final stand FN, there is a risk of a loop occurring between the final stand FN and the stand F(N-1) on the upstream side thereof. In this case, even if a looper is provided, it will be impossible to control the loop, and the stability of the rolling will be impaired.

[0041] Therefore, the gap correction amount calculation unit 112 calculates the thickness correction amount Δh of each stand Fi. i is calculated so as to satisfy the following relational expression (3).

[0042]

number

[0043] where ξ i represents the ratio of the rolling reduction change of stand Fi, and each ratio ξ i is given an arbitrary value greater than 0 that is predetermined. For example, if the ratio ξ1 of stand F1 is set to 2 and the ratio ξ4 of stand F4 is set to 1, this means that the change in the reduction rate Δr1 of stand F1 is twice the change in the reduction rate Δr4 of stand F4. Furthermore, if the ratios ξ1 to ξ7 of all stands F1 to F7 are set to the same value, the change in the reduction rate of all stands F1 to F7 can be made equal. In this way, by setting the ratio ξi given to each stand Fi, the plate thickness can be gradually reduced in each stand F1 to F7, improving the stability of rolling.

[0044] Fig. 3 is a diagram showing an example of calculation of the reduction and reduction change amount of each stand F. The calculation conditions are a total number of stands of 7, a product thickness of 3 mm, and a predicted thickness deviation of 0.1 mm. In addition, the ratios ξ1 to ξ3 of the front stands F1 to F3 are set to 2, and the ratios ξ4 to ξ7 of the rear stands F4 to F7 are set to 1. As a result, the change amount of the reduction amount of the front stands F1 to F3, which have relatively high rolling stability, is higher (twice as much) than the change amount of the reduction amount of the rear stands F4 to F7, which have relatively low rolling stability, further improving rolling stability.

[0045] The gap correction amount calculation unit 112 calculates a thickness correction amount Δh for each thickness deviation per meter predicted by the thickness deviation learning unit 111. i After calculating the target thickness correction amount Δh for each stand Fi calculated every 1 m i Using the following equation (4), which is called the gauge meter equation, the gap correction amount ΔS of each stand Fi is calculated.comp,i is calculated and output to the finishing rolling mill 5.

[0046]

number

[0047] where M i is Mill's constant, Q i represents the plasticity coefficient, which is calculated by the host computer 10 through a set calculation.

[0048] According to the rolling distance of each stand Fi, the gap correction amount ΔS comp,i In this embodiment, the roll gap of each stand Fi is adjusted by the gap correction amount ΔS comp,i is calculated for each meter based on the length standard on the exit side of the finishing rolling mill 5, but considering that the length of the material M to be rolled changes in each stand Fi, the length standard on the exit side of the finishing rolling mill 5 is converted to the length standard on the exit side of each stand Fi, and the roll gap of each stand Fi is adjusted.

[0049] The thickness control unit 113 has a function of controlling the roll gap of each stand Fi based on the setting calculation input from the host computer 10, thereby controlling the thickness of the sheet at the outlet of each stand Fi. Before rolling, the gap correction amount ΔS output from the gap correction amount calculation unit 112 is added to the control signal output from the thickness control unit 113. comp,i are added together, and the control signal after the addition is input to each of the screw down devices 54 of each stand Fi of the finishing rolling mill 5. In this way, the roll gap of each stand Fi is adjusted before rolling. When rolling starts, the thickness control unit 113 feedback-controls the roll gap of each rolling stand Fi based on the actual thickness input from the thickness gauge 83.

[0050] The specific structure of the process control computer 11 is not limited, and may be as follows, for example. FIG. 4 is a diagram showing an example of the hardware configuration of the process control computer 11. The functions of the process control computer 11 can be realized by the processing circuit shown in FIG. 4. This processing circuit may be dedicated hardware 20a. This processing circuit may include a processor 20b and a memory 20c. This processing circuit may be partially formed as dedicated hardware 20a, and may further include a processor 20b and a memory 20c. In the example of FIG. 4, part of the processing circuit is formed as dedicated hardware 20a, and the processing circuit also includes a processor 20b and a memory 20c.

[0051] At least a portion of the processing circuitry may be at least one dedicated hardware 20a, such as a single circuit, multiple circuits, programmed processors, parallel programmed processors, ASICs, FPGAs, or any combination thereof.

[0052] The processing circuit may include at least one processor 20b and at least one memory 20c. In this case, each function of the process control computer 11 is realized by software, firmware, or a combination of software and firmware. The software and firmware are written as programs and stored in the memory 20c. The processor 20b realizes the functions of each unit by reading and executing the programs stored in the memory 20c.

[0053] The processor 20b is also called a CPU (Central Processing Unit), central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, or DSP. The memory 20c corresponds to, for example, a non-volatile or volatile semiconductor memory such as RAM, ROM, flash memory, EPROM, or EEPROM.

[0054] In this way, the processing circuit can realize each function of the process control computer 11 by hardware, software, firmware, or a combination of these.

[0055] Next, a method for controlling the thickness of the finishing mill 5, which is carried out by the process control computer 11, will be described.

[0056] Before rolling the material M to be rolled, when the process control computer 11 receives input from the host computer 10, the thickness deviation learning unit 111 predicts the thickness deviation of the material M to be rolled by machine learning function, and outputs the predicted thickness deviation to the gap correction amount calculation unit 112. The gap correction amount calculation unit 112 calculates a gap correction amount ΔS so as to cancel out the predicted thickness deviation of the material M to be rolled. comp,i As described above, the gap correction amount calculation unit 112 calculates the thickness correction amount Δh of the rolled material M. i Calculate the plate thickness correction amount Δh i Using the gap correction amount ΔS comp,i Calculate the gap correction amount ΔS comp,i to the finishing mill 5. Furthermore, the plate thickness control unit 113 outputs the setting calculation input from the host computer 10, i.e., the roll gap setting value of each stand Fi, to the finishing mill 5. The roll gap setting value output from the plate thickness control unit 113 is multiplied by the gap correction amount ΔS output from the gap correction amount calculation unit 112. comp,i is input to the finishing rolling mill 5. In the finishing rolling mill 5, the roll gap is adjusted by the screw down device 54 of each stand Fi in accordance with the input signal. In this way, before rolling the material M to be rolled, the roll gap of each stand Fi is adjusted in a feedforward manner. Then, when rolling of the material to be rolled is started and the actual thickness is input from the thickness gauge 83 to the thickness control unit 113, the thickness control unit 113 executes feedback control.

[0057] After rolling the rolled material M, the process control computer 11 calculates the actual thickness deviation, which is the difference between the actual thickness measured by the thickness gauge 83 and the predicted product thickness, and calculates a learning thickness deviation by adding the calculated actual thickness deviation to the predicted thickness deviation predicted by the thickness deviation learning unit 111. The thickness deviation learning unit 111 then learns the calculated learning thickness deviation, thereby updating the learned value of the thickness deviation learning unit 111. This is done in association with the product thickness, product width, and finishing entry temperature.

[0058] According to this embodiment, a configuration is adopted in which, before rolling, the thickness deviation learning unit 111 predicts a thickness deviation based on not only the product thickness and steel grade but also the temperature of the material M to be rolled measured upstream of the finishing rolling mill 5, and the roll gap of each stand Fi of the finishing rolling mill 5 is adjusted so as to cancel out the predicted thickness deviation. This makes it possible to suppress thickness deviations that may occur due to factors that cause thickness deviations other than the product thickness and steel grade. As a result, the thickness accuracy of the material M to be rolled can be improved.

[0059] In addition, by having the thickness deviation learning unit 111 learn the learning thickness deviation, the accuracy of predicting the thickness deviation by the thickness deviation learning unit 111 is improved, thereby further improving the thickness accuracy of the rolled material M.

[0060] Embodiment 2 Fig. 5 is a schematic diagram showing the configuration of a thickness control device for a rolling mill according to embodiment 2. Embodiment 2 differs from embodiment 1 in that it includes a thickness deviation average calculation unit 114 and a gap setting calculation unit 115. Note that in embodiment 2, parts that overlap with embodiment 1 will not be mentioned.

[0061] Before rolling the material M to be rolled, the thickness deviation average calculation unit 114 calculates the average value of the thickness deviation at the tip of the material M to be rolled, among the thickness deviations predicted by the thickness deviation learning unit 111. The tip is set, for example, to a range where the temperature measured by the thermometer 82 is relatively unstable, that is, a range where the accuracy of thickness control per meter is expected to be relatively low, and is set, for example, to a length range of 5 m to 10 m from the tip of the material M to be rolled.

[0062] The gap correction amount calculation unit 112 calculates the gap correction amount ΔS from the average thickness deviation value calculated by the average thickness deviation calculation unit 114. comp,i Calculate the gap correction amount ΔS comp,i For the calculation, the above equation (4) can be used, as in the first embodiment.

[0063] The gap setting calculation unit 115 calculates the roll gap setting value of each stand Fi of the finishing mill 5 before rolling the material M to be rolled. The roll gap setting value calculated by the gap setting calculation unit 115 is calculated based on the gap correction amount ΔS calculated by the gap correction amount calculation unit 112. comp,i The corrected set value is input to the finishing rolling mill 5. Based on the corrected set value, the roll gap of each stand Fi is adjusted before rolling the material M to be rolled.

[0064] According to this embodiment, the plate thickness controllability at the tip end of the rolled material M is improved, which has the effect of improving the yield at the tip end. In addition, the roll gap setting calculation unit 115 provided in the process control computer 11 calculates the roll gap setting value, and by correcting the calculated setting value, the roll gap of each stand Fi can be reliably adjusted before rolling the rolled material M.

[0065] It should be noted that the above-described first embodiment can be used in combination with the control of the thickness of the rolled material M from its leading end onward.

[0066] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments and can be implemented in various modifications without departing from the spirit of the present invention. When the numbers, quantities, amounts, ranges, etc. of each element are mentioned in the above-described embodiments, the present invention is not limited to the mentioned numbers unless otherwise specified or clearly specified in principle. Furthermore, the structures, etc. described in the above-described embodiments are not necessarily essential to the present invention unless otherwise specified or clearly specified in principle. [Explanation of symbols]

[0067] 5... Finishing rolling mill (rolling mill), 11... Plate thickness control device, process control computer, 111... Plate thickness deviation learning unit, 112... Gap correction amount calculation unit, M... Rolled material

Claims

1. In a plate thickness control device of a rolling mill that rolls a rolled material to a target product plate thickness, a thickness deviation learning unit that learns the tendency of thickness deviation, which is the difference between the product thickness and the actual thickness of the rolled material measured on the delivery side of the rolling mill, and that predicts the thickness deviation of the rolled material based on product information including the product thickness and steel type of the rolled material and measurement values ​​of the rolled material measured on the upstream side of the rolling mill, using the rolled material to be rolled by the rolling mill as the rolled material, before rolling the rolled material; A gap correction amount calculation unit calculates a gap correction amount for correcting the roll gap of the rolling mill so as to cancel the plate thickness deviation predicted by the plate thickness deviation learning unit, before rolling the rolled material, adjusting the roll gap of the rolling mill based on the gap correction amount calculated by the gap correction amount calculation unit; A plate thickness control device for a rolling mill, wherein the measured value of the rolled material is the temperature of the rolled material measured upstream of the rolling mill.

2. A plate thickness control device for a rolling mill as described in claim 1, wherein the plate thickness deviation learning unit learns a learning plate thickness deviation obtained after rolling the rolled material by adding an actual plate thickness deviation determined from the actual plate thickness of the rolled material to the plate thickness deviation of the rolled material predicted before rolling the rolled material.

3. Further provided is a thickness deviation average calculation unit that calculates the average value of the thickness deviation at the tip end of the rolled material predicted by the thickness deviation learning unit before rolling the rolled material, 2. The plate thickness control device for a rolling mill according to claim 1, wherein the gap correction amount calculation unit calculates the gap correction amount so as to cancel out the average value calculated by the plate thickness deviation average calculation unit before rolling the rolled material.

Images