WO2024023910A1 - タンデム圧延機の板厚スケジュール計算方法及び圧延プラント - Google Patents
タンデム圧延機の板厚スケジュール計算方法及び圧延プラント Download PDFInfo
- Publication number
- WO2024023910A1 WO2024023910A1 PCT/JP2022/028727 JP2022028727W WO2024023910A1 WO 2024023910 A1 WO2024023910 A1 WO 2024023910A1 JP 2022028727 W JP2022028727 W JP 2022028727W WO 2024023910 A1 WO2024023910 A1 WO 2024023910A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- rolling
- limit value
- value
- calculated
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
- B21B37/16—Control of thickness, width, diameter or other transverse dimensions
- B21B37/18—Automatic gauge control
- B21B37/20—Automatic gauge control in tandem mills
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
- B21B37/58—Roll-force control; Roll-gap control
Definitions
- the present disclosure relates to a plate thickness schedule calculation method and a rolling plant for a tandem rolling mill in which a plurality of rolling stands are arranged side by side.
- a load ratio distribution method is used as a method for calculating the plate thickness schedule, and the plate thickness schedule is calculated based on the distribution ratio ⁇ i of the load Pi in each rolling stand.
- the exit plate thickness hi and roll circumferential speed Vi of each rolling stand must satisfy the law of constant volume velocity (also referred to as the "constant mass flow law") in order to maintain uniform speed between the rolling stands.
- the relational expression obtained from both the relationship between the rolling load and load ratio of each stand and the constant mass flow law, and the same number of unknowns as the relational expression, are numerically solved using the Newton-Raphson method etc. .
- a limit check also referred to as "parameter limit” is performed on parameters such as the rolling reduction rate, rolling load, and rolling torque of each rolling stand. If the limit value of the limit check is exceeded, the plate thickness schedule is automatically corrected by lowering the target load ratio of the relevant rolling stand.
- This plate thickness schedule calculation method has a problem in that calculation performance deteriorates depending on the number of rolling stands to be corrected or the amount of correction.
- deterioration in calculation performance means that, for example, when there are more than half of the rolling stands to be corrected or when the amount of correction is large to a certain extent, the calculation load becomes high or it becomes difficult for repeated calculations to converge. include.
- Patent Document 2 discloses a technique for appropriately modifying the calculation contents by changing the function used for calculation when a parameter related to rolling exceeds a limit value.
- Patent Document 1 neither Patent Document 1 nor Patent Document 2 clearly describes what kind of numerical value the limit value used for the limit check is, including how to set it. If a sufficiently large value is set as the limit value, the limit check itself will no longer function. On the other hand, if a relatively small numerical value is set as the limit value, the limit value will be exceeded more frequently, and the plate thickness schedule calculation will not converge. In either case, there is a risk of causing rolling troubles, resulting in poor yield and increased downtime.
- the current limit value is a common (same) value used for all materials regardless of steel type or size, and this common value is not the limit value suitable for rolled materials. I can not say.
- the present disclosure has been made in order to solve the above-mentioned problems, and it is possible to calculate and set a limit value for a limit check suitable for maintaining stable rolling and operating conditions with few rolling troubles.
- the purpose of the present invention is to provide a method for calculating a plate thickness schedule and a rolling plant.
- the first aspect is related to a method for calculating a plate thickness schedule for a tandem rolling mill in which rolling is performed continuously by a plurality of rolling stands.
- the plate thickness schedule calculation method includes a calculation step of calculating a plate thickness schedule based on rolling load or motor power using a rolling model formula including an advanced rate model and a rolling load model.
- the calculation process includes a calculation process of calculating at least one of the upper limit and lower limit of the rolling reduction at each rolling stand for each product specification including the steel type classification and sheet thickness classification to be rolled, based on past rolling data;
- the method includes a setting step of setting at least one of the upper limit value and the lower limit value calculated in the step as a limit value of a limit check for the rolling reduction rate.
- the calculation process includes a process of extracting rolling data when rolling was possible without causing any rolling troubles from past rolling data, and calculating the set calculated value and actual value of the rolling reduction of the extracted rolling data. It is configured to calculate at least one of the upper limit value and the lower limit value by statistical analysis from at least one of the upper limit values and the lower limit value.
- the calculation process includes a step of extracting rolling data from past rolling data when the deviation between the set calculation value of the rolling reduction ratio and the actual value is smaller than a reference value, and setting the rolling reduction ratio of the extracted rolling data. It is configured to calculate at least one of the upper limit value and the lower limit value by statistical analysis from at least one of the calculated value and the actual value.
- the fourth aspect further has the following characteristics.
- machine learning is used that takes as input at least one of past set calculation values and actual values when rolling was possible without causing rolling troubles among past rolling data, and outputs the rolling reduction rate. It is configured to calculate at least one of the upper limit value and the lower limit value by sequentially calculating the rolling reduction rate and adding or subtracting a certain numerical value to the calculated rolling reduction rate.
- the fifth aspect further has the following characteristics.
- the calculation process at least one of the past set calculation value and the actual value when the deviation between the set calculation value and the actual value of the rolling reduction ratio is smaller than the reference value among the past rolling data is input, and the rolling reduction ratio is output. It is configured to calculate at least one of the upper limit value and the lower limit value by sequentially calculating the rolling reduction rate using machine learning, and adding or subtracting a certain numerical value to the calculated rolling reduction rate.
- the sixth aspect further has the following characteristics.
- the rolling data of the classification where rolling trouble occurred is extracted from the past rolling data, and the average value of the rolling reduction of the set calculation is calculated using the rolling data when rolling was possible without any rolling trouble.
- the computer is configured to calculate at least one of the two.
- the seventh aspect further has the following characteristics. If at least one of the upper limit value and lower limit value calculated at the downstream rolling stand is larger than the upper limit value of the rolling stand one upstream side, the upper limit value of the downstream rolling stand is set as the upper limit value of the rolling stand one upstream side. It is configured to replace the upper limit value, or to replace the upper limit value of the downstream rolling stand with a value obtained by subtracting a certain value from the upper limit value of the stand one upstream side.
- the eighth aspect further has the following characteristics in addition to the first aspect.
- the rolling reduction rate calculated in advance is configured to be set as the limit value.
- the rolling data is calculated from at least one of the set calculated value and actual value of the rolling reduction rate of the rolling data calculated by statistical analysis. At least one of the upper limit value and the lower limit value calculated by statistical analysis is set as a limit value.
- the upper and lower limits are calculated by adding or subtracting a certain value to the rolling reduction calculated using machine learning. At least one of the values is configured to be set as a limit value.
- the ninth aspect is a plurality of rolling stands, a rolling device provided in each rolling stand of the plurality of rolling stands, an electric motor that rotates the rolls of each rolling stand, a rolling load ratio of the rolling device, and a motor of the electric motor. It is equipped with a process calculator constructed to calculate the plate thickness schedule for each rolling stand based on one of the power ratios and a database that stores past rolling data.
- the process calculator calculates at least one of the upper and lower limits of the rolling reduction at each rolling stand based on the process of performing a limit check on the rolling reduction of each rolling stand and the past rolling data accumulated in the database.
- the system is constructed to perform calculations for each product specification, including steel type classification and plate thickness classification, and processing to set at least one of the calculated upper and lower limits as a limit value for limit check for rolling reduction. Ru.
- the Limit values can be set and rolling troubles can be avoided. As a result, it is possible to improve the yield and shorten the operation stop time.
- At least one of the upper limit value and the lower limit value of the rolling reduction ratio can be determined with high accuracy.
- At least one of the upper limit value and the lower limit value of the rolling reduction ratio can be calculated even when using the rolling data of the section in which rolling trouble has occurred.
- the seventh aspect by preventing the reversal of the rolling reduction ratio, it is possible to prevent the rolling balance from collapsing and causing rolling troubles.
- the limit value can be set in stages according to the number of rolling data.
- FIG. 1 is a schematic diagram showing the configuration of a rolling plant according to an embodiment. It is a diagram showing an example of the hardware configuration of a process computer included in a rolling plant.
- 3 is a flowchart for explaining the flow of plate thickness schedule calculation in Example 1.
- FIG. 7 is a flowchart for explaining the flow of plate thickness schedule calculation in Example 2.
- 7 is a flowchart for explaining the flow of plate thickness schedule calculation in Example 3.
- 12 is a flowchart for explaining the flow of plate thickness schedule calculation in Example 4.
- FIG. 1 is a schematic diagram showing the configuration of a rolling plant 1 according to an embodiment.
- the rolling plant 1 uses steel or other metal materials as a material to be rolled 10, and hot-rolls the material to be rolled 10 into a plate shape.
- the material to be rolled 10 is a material that is rolled in the rolling plant 1 .
- the rolling plant 1 may be configured to cold-roll the material 10 to be rolled into a plate shape.
- the rolling plant 1 includes a heating furnace 2, a rough rolling mill 3, a finishing rolling mill 4, a cooling device 5, a winding machine 6, and a roller table (not shown) that conveys the rolled material 10 between them. ).
- the heating furnace 2 heats the material to be rolled 10 and raises its temperature.
- the rough rolling mill 3 has one or more rolling stands.
- the rolling stand has a plurality of rolls 31, a rolling device 32, and an electric motor 33 for rotating the rolls.
- the finishing rolling mill 4 is a tandem rolling mill that includes a plurality of rolling stands F1 to F5 that are arranged in series in the conveying direction of the material to be rolled 10.
- Each of the rolling stands F1 to F5 includes a plurality of rolls 41, a rolling device 42, and an electric motor 43 for rotating the rolls.
- the rolling stand may be referred to as i or i-1.
- the number of rolling stands of the heating furnace 1, the winding machine 6, the rough rolling mill 3, and the finishing rolling mill 4 is not particularly limited.
- a rolling plant 1 having one stand, five rolling stands F1 to F5 of a finishing rolling mill 4, and one winding machine 6 is taken as an example.
- the rolling devices 32, 42, electric motors 33, 43, etc. of each of the rolling mills 3, 4 described above may be referred to as "equipment" of the rolling plant 1 for convenience.
- the equipment may include various other items such as actuators (not shown), depending on the specific structure of each rolling mill 3, 4. .
- Important points of the rolling plant 1 include, for example, the outlet side of the heating furnace 2, the outlet side of the rough rolling mill 3, the outlet side of the finishing mill 4, and the inlet side of the winder 6.
- Various sensors may also be provided between the rolling stands F1 to F5 of the finishing rolling mill 4.
- the various sensors include a thermometer (Pyrometer) 71 that measures the surface temperature of the material to be rolled 10 on the entry side of the finishing rolling mill 4, and a plate thickness gauge 72 that measures the thickness and width of the material to be rolled 10.
- thermometer 73 that measures the surface temperature of the rolled material 10 on the exit side of the finishing rolling mill 4
- rolling load sensor 74 that measures the rolling load at each rolling stand F1 to F5, and an entry side of the winder 6. It includes a thermometer 75 for measuring the surface temperature of the rolled material 10.
- Various sensors sequentially measure the condition of the rolled material 10 and each device.
- the rolling plant 1 is operated (operated) by a control system using a computer.
- the computer includes a host computer 20 and a process computer 21 that are connected to each other via a network.
- An interface screen 21a which is an operation screen, and a database 23 are connected to the process computer 21 via a network.
- Past rolling data is sequentially stored in the database 23.
- the past rolling data includes set values and actual values of the rolling reduction of each rolling stand F1 to F5.
- the host computer 20 instructs the process computer 21 to issue rolling instructions based on a preset production plan.
- the rolling command includes, for example, target dimensions and target temperatures of each rolled material 10.
- the target dimensions include, for example, target plate thickness, target plate width, and target crown.
- the target temperature includes, for example, the outlet temperature of the rough rolling mill 3, the outlet temperature of the finishing mill 4, the inlet temperature of the winder 6, and the like.
- the process computer 21 calculates setting values for each equipment of the rolling plant 1 according to the rolling command from the host computer 20.
- the process computer 21 outputs the calculated set value to the controller 22.
- the set values include the rolling position of the rolling device 42, roll rotation speed, bending force, work roll shift amount, cooling water amount of the cooling device 5, and the like.
- the controller 22 When the rolled material 10 is transported to a predetermined position in front of each piece of equipment, the controller 22 operates the actuator (not shown) of each piece of equipment in the rolling plant 1 based on the set values. When rolling is started, the controller 22 adjusts the target dimensions and target temperature of the material to be rolled 10 to match the rolling command based on sensor measurements such as a radiation thermometer, an X-ray plate thickness gauge, and a load cell. Operate each actuator sequentially.
- FIG. 2 is a diagram showing an example of the hardware configuration of the process computer 21 included in the rolling plant 1.
- the arithmetic processing function of the process computer 21 can be realized by the processing circuit shown in FIG.
- 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 further include a processor 20b and a memory 20c.
- part of the processing circuit is formed as dedicated hardware 20a, and the processing circuit also includes a processor 20b and a memory 20c.
- At least a portion of the processing circuitry may be at least one piece of dedicated hardware 20a.
- the processing circuit can be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.
- the processing circuit may include at least one processor 20b and at least one memory 20c.
- each function of the process computer 21 is realized by software, firmware, or a combination of software and firmware.
- Software and firmware are written as programs and stored in the memory 20c.
- the processor 20b realizes the functions of each section by reading and executing programs stored in the memory 20c.
- 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 is, for example, a nonvolatile or volatile semiconductor memory such as RAM, ROM, flash memory, EPROM, EEPROM, or the like. Note that it is also possible to configure the memory 20c to also serve as the database 23.
- the processing circuit can realize each function of the process computer 21 using hardware, software, firmware, or a combination thereof.
- the functions of the process computer 21 also include a machine learning function, which will be described later.
- the material to be rolled 10 is heated in the heating furnace 2 and then extracted onto a roller table (not shown) of the rolling line.
- the material to be rolled 10 at this stage is, for example, a steel billet.
- the material to be rolled 10 at this stage is a bar having a thickness of, for example, several tens of millimeters.
- the material to be rolled 10 is rolled while being sequentially bitten by the rolling stands F1 to F5 of the finishing rolling mill 4 to obtain a desired thickness.
- the rolled material 10 at this stage is also called a strip.
- the rolled material 10 is cooled by the cooling device 5.
- the cooled rolled material 10 is wound up by a winding machine 6 to obtain a coiled product.
- the process computer 21 calculates a plate thickness schedule to be executed in the finishing mill 4.
- the plate thickness schedule is calculated using a mathematical model.
- the plate thickness schedule includes the outlet side plate thickness of each rolling stand F1 to F5.
- This mathematical model is a group of mathematical equations for predicting the temperature, rolling load, rolling torque, etc. of each rolling stand F1 to F5.
- the load ratio ⁇ i is used.
- the load ratio ⁇ i is the distribution ratio of the load P i in each rolling stand F1 to F5.
- the rolling load of the "load ratio distribution method” is one of the factors that changes the plate crown, and the higher the rolling load of a certain rolling stand, the larger the plate crown on the exit side of the rolling stand. . Therefore, in order to reduce the crown ratio change and maintain good flatness, it is desirable that the rolling load changes in the same way on each stand. However, the rolling load changes moment by moment for each rolled material and for each stand due to fluctuations in the temperature of the rolled material, and this may deteriorate the flatness.
- a method for calculating a plate thickness schedule was devised that automatically adjusts the plate thickness at the exit side of each stand and keeps the rolling load ratio (i.e., rolling load ratio) as constant as possible even if there are fluctuations in the temperature of the rolled material. has been done.
- rolling load ratio i.e., rolling load ratio
- Such a plate thickness schedule calculation method is called the "load ratio distribution method.”
- the method of calculating the plate thickness schedule itself, excluding the calculation and setting of limit values for limit checks to be described later, is well known as described in the prior art, so further explanation will be omitted here.
- the upper limit value and the lower limit value which are the limit values that are the threshold values of the rolling reduction rate, are calculated as follows.
- Setting values or actual values for each rolling stand F1 to F5 are extracted from the database 23 in which past rolling data is stored and used.
- either set values or actual values may be used.
- the calculation may be performed using both the set value and the actual value, and in that case, the amount of data to be handled will be twice as much as when either one is used.
- FIG. 3 is a flowchart for explaining the flow of plate thickness schedule calculation in the first embodiment.
- FIG. 3 shows the flow of calculating the upper and lower limits of the rolling reduction ratio according to the first embodiment.
- step S1 When the routine shown in FIG. 3 is started, past rolling data stored in the database 23 is extracted as target data (step S1). There are two types of target data extracted in step S1:
- the first target data is rolling data that was rolled without causing any rolling trouble. This makes it possible to reduce the probability of rolling troubles and enable stable operations.
- the presence or absence of rolling troubles is determined only when winding of the rolled material 10 into a coil shape using the winding machine 6 has been completed and actual data can be measured.
- the second target data is rolling data in which there is little deviation between set values and actual values. Thereby, it becomes possible to calculate the upper limit value and lower limit value with high accuracy.
- "Small deviation” means that the deviation (error ratio) between the set calculated value and the actual value is small, and is expressed by the following formula (1).
- the target data is classified for each product specification including steel type classification AAA and plate thickness classification bb (hereinafter, this hierarchical classification will be referred to as "classification (AAA, bb)").
- the target data may be further subdivided by adding a classification, such as a hierarchical classification (AAA, bb, cc) in which the plate width classification cc is added.
- step S2 calculation is performed for each rolling stand using the following statistical analysis or machine learning.
- Percentile values can be used for statistical analysis.
- the percentile value at N pct,i 50 ⁇ N pct,i ⁇ 100% is calculated as the upper limit
- (100-N pct,i )% is calculated as the lower limit.
- N pct,i 95
- the upper limit value is the 95th percentile value
- the lower limit value is the 5th percentile value.
- N pct,i may be a common value regardless of the rolling stand.
- Quartiles can be used for statistical analysis.
- the first quartile, second quartile, and interquartile range are calculated from the target data (number of data n) of the target classification (AAA, bb).
- Rolling instructions including the steel type, target dimensions, chemical composition, etc. of the slab, actual data on the surface temperature of the rolled material 10 in front of the finishing rolling mill 4, and each Setting calculation data such as material speed, rolling load, rolling reduction rate, material temperature, etc. at rolling stands F1 to F5, as well as material speed, rolling load, rolling reduction rate, and material temperature at each rolling stand F1 to F5, and data on the exit side of the finishing mill.
- Rolling performance data such as plate thickness, plate thickness deviation, and material temperature are used as input data, and a rolling reduction calculation model is generated using machine learning using the input data and using the rolling reduction rates of each rolling stand F1 to F5 as output data.
- a known machine learning method such as random forest may be used.
- Other methods include decision tree learning, neural networks, support vector regression, and the like.
- the data of the latest set values and actual values may be used as input to update as appropriate.
- At least one of the upper and lower limits of the rolling reduction calculated in step S2 above is set as a limit value (limit range) that is a threshold for limit checking in plate thickness schedule calculation (step S3).
- FIG. 4 is a flowchart for explaining the flow of plate thickness schedule calculation in the second embodiment.
- FIG. 4 shows the flow of calculating the upper and lower limits of the rolling reduction ratio according to the second embodiment.
- Example 1 data without rolling troubles or data in which the deviation between the set value and the actual value was smaller than the standard value was extracted as target data, whereas in Example 2, rolling The difference is that rolling data at the time of trouble is also taken into account.
- step S11 rolling of the stratified classification (TTT, bd) (number of data N) in which rolling trouble has occurred (relatively many rolling troubles) among the past rolling data stored in the database 23 is executed.
- the data is extracted as target data (step S11).
- the target data extracted in step S11 is divided into data that was rolled without any rolling troubles (number of data NOK ) and data that had rolling troubles (number of data NNG ), and it is determined which data it is (step S12).
- step S13 the average value of the rolling reduction in the setting calculation of each rolling stand is calculated using the following formula (13) for the NO OK pieces of data that were rolled without any rolling troubles.
- an upper limit value and a lower limit value are calculated based on numerical values close to the average value of the rolling reduction ratio (step S15).
- At least one of the upper and lower limits of the rolling reduction calculated in step S15 is set as a limit value (limit range) that is a threshold for limit checking in plate thickness schedule calculation (step S16).
- FIG. 5 is a flowchart for explaining the flow of plate thickness schedule calculation in the third embodiment.
- FIG. 5 shows the flow of calculating the upper and lower limits of the rolling reduction ratio according to the third embodiment.
- the routine shown in FIG. 5 is activated when the upper and lower limits of the rolling reduction ratio are calculated in the first and second embodiments.
- the calculated upper limit or lower limit of the rolling reduction of a certain rolling stand is larger than the upper limit of the rolling reduction of an upstream rolling stand, a reversal of the rolling reduction occurs and the rolling balance in the finishing mill 4 is disrupted. , which may cause rolling troubles.
- processing is defined in the case where the calculated upper limit value of the rolling reduction is larger than that of the upstream rolling stand.
- the rolling reduction ratio of the downstream rolling stand be smaller than that of the upstream rolling stand, so the process shown in FIG. 5 is executed.
- step S17 it is determined whether the upper limit of the rolling reduction calculated at a certain rolling stand i is larger than the upper limit of the rolling reduction calculated at the rolling stand i-1 one upstream. It is determined whether the following formula (16) holds true (step S17).
- the new upper limit value of the rolling reduction rate replaced by the above formula (17) or calculated by the above formula (18) is set as the limit value (limit range) that is the threshold value for limit check in plate thickness schedule calculation. .
- FIG. 6 is a flowchart for explaining the flow of plate thickness schedule calculation in the fourth embodiment.
- FIG. 6 shows the flow of calculating the upper and lower limits of the rolling reduction ratio according to the fourth embodiment.
- the method for calculating the upper and lower limits of the rolling reduction ratio is switched in stages according to the number N of past rolling data stored in the database 23.
- step S21 it is determined whether the number N of rolling data accumulated in the database 23 is less than the threshold value Nb1 (step S21). If the rolling data number N is less than the threshold value Nb1, the upper and lower limits of the rolling reduction rate calculated in advance as in the conventional method are set as limit values (step S22).
- step S23 it is determined whether the number N of rolling data is less than the threshold Nb2 (>Nb1) (step S23).
- the threshold value Nb2 that is, when the number N of accumulated rolling data is small, the statistical analysis explained in Example 1 ⁇ Calculation of upper limit value and lower limit value (any one of Part 1 to Part 3) 1)>
- the upper and lower limits of the rolling reduction ratio are calculated (step S24).
- the accumulated rolling data number N increases and reaches the threshold value Nb2 or more
- rolling The upper limit value and lower limit value of the rate are calculated (step S25). Thereafter, at least one of the upper limit and lower limit of the rolling reduction calculated in step S24 or step S25 is set as a limit value (limit range) (step S26).
- At least one of the upper limit and lower limit of the rolling reduction rate calculated by stepwise calculation according to the number of rolling data stored in the database 23 can be used as the limit value.
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Control Of Metal Rolling (AREA)
Abstract
Description
図1は、実施の形態による圧延プラント1の構成を示す模式図である。圧延プラント1は、鉄鋼又はその他の金属材を被圧延材10とし、被圧延材10を熱間で板状に圧延するものである。被圧延材10は、圧延プラント1で圧延される素材である。なお、圧延プラント1は、被圧延材10を冷間で板状に圧延するように構成されていてもよい。
仕上圧延機4での圧延工程前には、プロセス計算機21にて、仕上圧延機4で実行される板厚スケジュールを計算する。板厚スケジュールは、数式モデルで算定される。板厚スケジュールは、各圧延スタンドF1~F5の出側板厚を含んでいる。この数式モデルは、各圧延スタンドF1~F5の温度、圧延荷重、及び、圧延トルクなどを予測するための数式群である。荷重比配分法に基づく板厚スケジュール計算では、荷重比γiが用いられる。荷重比γiは、各圧延スタンドF1~F5における荷重Piの配分比率である。
上述した板厚スケジュールの計算において、圧下率、圧延荷重や圧延トルクなどの各種パラメータに対して公知のリミットチェックが行われる。
図3は、実施例1における板厚スケジュール計算の流れを説明するためのフローチャートである。図3は、実施例1による圧下率の上限値及び下限値の計算の流れを表している。
1つ目の対象データは、圧延トラブルを起こさず、圧延した圧延データである。これにより、圧延トラブルになる確率を小さくすることができ、安定した操業が可能になる。圧延トラブルの有無は、巻取機6で被圧延材10をコイル状に巻取るところまで完了したもので、実績データを測定できたものに限る。
2つ目の対象データは、設定値と実績値の乖離の少ない圧延データである。これにより、精度の高い上限値及び下限値を算出することが可能となる。「乖離の少ない」とは、実績値に対して設定計算値との偏差(誤差比率)が小さいことであり、下式(1)で表される。
統計解析としてパーセンタイル値を用いることができる。この場合、対象区分(AAA,bb)の対象データ(データ数n)のうち、Npct,i(50<Npct,i<100)%におけるパーセンタイル値を上限値として算出し、(100-Npct,i)%におけるパーセンタイル値を下限値として算出する。例えば、Npct,i=95の場合、上限値は95パーセンタイル値、下限値は5パーセンタイル値となる。Npct,iは、圧延スタンドに依らず共通の値としてもよい。
統計解析として四分位数を用いることができる。この場合、対象区分(AAA,bb)の対象データ(データ数n)から第1四分位数及び第2四分位数、四分位範囲を算出する。
過去の圧延データが格納されたデータベース23から読み出した、スラブの鋼種や目標寸法、化学成分等を含んだ圧延命令、仕上圧延機4前の被圧延材10の表面温度の実績データ、及び、各圧延スタンドF1~F5での材料速度や圧延荷重、圧下率、材料温度等の設定計算データ、及び、各圧延スタンドF1~F5での材料速度や圧延荷重、圧下率、仕上圧延機出側での板厚及び板厚偏差、材料温度等の圧延実績データを入力データとし、その入力データを用いて各圧延スタンドF1~F5の圧下率を出力データとした機械学習による圧下率演算モデルを生成する。
図4は、実施例2における板厚スケジュール計算の流れを説明するためのフローチャートである。図4は、実施例2による圧下率の上限値及び下限値の計算の流れを表している。上記実施例1では、圧延トラブルのないデータ、もしくは、設定値と実績値の乖離が基準値よりも小さいデータを対象データとして抽出したのに対し、本実施例2では、先端部通板における圧延トラブルが発生したときの圧延データも考慮する点で相違する。
図5は、実施例3における板厚スケジュール計算の流れを説明するためのフローチャートである。図5は、実施例3による圧下率の上限値及び下限値の計算の流れを表している。
図6は、実施例4における板厚スケジュール計算の流れを説明するためのフローチャートである。図6は、実施例4による圧下率の上限値及び下限値の計算の流れを表している。
Claims (9)
- 複数の圧延スタンドによって連続で圧延されるタンデム圧延機の板厚スケジュール計算方法において、
先進率モデル及び圧延荷重モデルを含む圧延モデル式を用い、圧延荷重もしくはモーターパワーを基にして板厚スケジュールを計算する計算工程を含み、
前記計算工程は、過去の圧延データを基に、各圧延スタンドにおける圧下率の上限値及び下限値の少なくとも一方を、圧延する鋼種区分及び板厚区分を含む製品仕様毎に算出する算出工程と、前記算出工程で算出した前記上限値及び前記下限値の少なくとも一方を前記圧下率に対するリミットチェックのリミット値として設定する設定工程を有する板厚スケジュール計算方法。 - 前記算出工程は、前記過去の圧延データのうち、圧延トラブルを起こさずに圧延することができたときの圧延データを抽出する工程を有し、抽出した圧延データの圧下率の設定計算値及び実績値の少なくとも一方から統計解析によって前記上限値及び前記下限値の少なくとも一方を算出する請求項1に記載の板厚スケジュール計算方法。
- 前記算出工程は、前記過去の圧延データのうち、圧下率の設定計算値と実績値との乖離が基準値よりも小さいときの圧延データを抽出する工程を有し、抽出した圧延データの圧下率の設定計算値及び実績値の少なくとも一方から統計解析によって前記上限値及び前記下限値の少なくとも一方を算出する請求項1に記載の板厚スケジュール計算方法。
- 前記算出工程において、前記過去の圧延データのうち、圧延トラブルを起こさずに圧延することができたときの過去の設定計算値及び実績値の少なくとも一方を入力とし、圧下率を出力とする機械学習を用いて逐次的に算出し、算出した圧下率に一定の数値を加算または減算することで前記上限値及び前記下限値の少なくとも一方を算出する請求項1に記載の板厚スケジュール計算方法。
- 前記算出工程において、前記過去の圧延データのうち、圧下率の設定計算値と実績値との乖離が基準値よりも小さいときの過去の設定計算値及び実績値の少なくとも一方を入力とし、圧下率を出力とする機械学習を用いて逐次的に算出し、算出した圧下率に一定の数値を加算または減算することで前記上限値及び前記下限値の少なくとも一方を算出する請求項1に記載の板厚スケジュール計算方法。
- 前記算出工程において、前記過去の圧延データのうち、圧延トラブルが発生した区分の圧延データを抽出し、圧延トラブルなく圧延できたときの圧延データを対象として、設定計算の圧下率の平均値を算出すると共に、圧延トラブルがあったときの圧延データを対象として、設定計算の圧下率からパーセンタイル値を算出し、算出した前記平均値及び前記パーセンタイル値から一定の数値を加算または減算することで前記上限値及び前記下限値の少なくとも一方を算出する請求項1に記載の板厚スケジュール計算方法。
- 下流側の前記圧延スタンドにおいて算出した前記上限値及び前記下限値の少なくとも一方が、一つ上流側の前記圧延スタンドの上限値より大きい場合に、下流側の前記圧延スタンドの上限値を一つ上流側の前記圧延スタンドの前記上限値に置き換える、または、下流側の前記圧延スタンドの上限値を一つ上流側のスタンドの上限値から一定の数値を引いた値に置き換える請求項1に記載の板厚スケジュール計算方法。
- 前記過去の圧延データの数が第1の閾値未満であるときには、予め算出された圧下率を前記リミット値として設定し、
前記過去の圧延データの数が前記第1の閾値以上で第2の閾値未満であるときには、統計解析によって算出した圧延データの圧下率の設定計算値及び実績値の少なくとも一方から統計解析によって算出した前記上限値及び前記下限値の少なくとも一方を前記リミット値として設定し、
前記過去の圧延データの数が前記第2の閾値以上であるときには、機械学習を用いて算出した圧下率に一定の数値を加算または減算することで算出した前記上限値及び前記下限値の少なくとも一方を前記リミット値として設定する請求項1に記載の板厚スケジュール計算方法。 - 複数の圧延スタンドと、前記複数の圧延スタンドの各圧延スタンドに設けられた圧下装置と、前記各圧延スタンドが持つロールを回転させる電動機と、前記圧下装置の圧延荷重比と前記電動機のモーターパワー比とのうち一方の値に基づいて前記各圧延スタンドの板厚スケジュールを計算するように構築されたプロセス計算機と、過去の圧延データを蓄積するデータベースを備え、
前記プロセス計算機は、
前記各圧延スタンドの圧下率に対するリミットチェックを実施する処理と、
前記データベースに蓄積された前記過去の圧延データを基に、前記各圧延スタンドにおける圧下率の上限値及び下限値の少なくとも一方を、圧延する鋼種区分及び板厚区分を含む製品仕様毎に算出する処理と、
算出した前記上限値及び前記下限値の少なくとも一方を前記圧下率に対する前記リミットチェックのリミット値として設定する処理と、
を実行するように構築される圧延プラント。
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2024536577A JP7750417B2 (ja) | 2022-07-26 | 2022-07-26 | タンデム圧延機の板厚スケジュール計算方法及び圧延プラント |
| PCT/JP2022/028727 WO2024023910A1 (ja) | 2022-07-26 | 2022-07-26 | タンデム圧延機の板厚スケジュール計算方法及び圧延プラント |
| CN202280057989.2A CN117881492A (zh) | 2022-07-26 | 2022-07-26 | 串列式轧制机的板厚一览表计算方法以及轧制成套设备 |
| KR1020247006170A KR20240039161A (ko) | 2022-07-26 | 2022-07-26 | 탠덤 압연기의 판두께 스케줄 계산 방법 및 압연 플랜트 |
| JP2025114405A JP7848923B2 (ja) | 2022-07-26 | 2025-07-07 | タンデム圧延機の板厚スケジュール計算方法 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2022/028727 WO2024023910A1 (ja) | 2022-07-26 | 2022-07-26 | タンデム圧延機の板厚スケジュール計算方法及び圧延プラント |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024023910A1 true WO2024023910A1 (ja) | 2024-02-01 |
Family
ID=89705776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2022/028727 Ceased WO2024023910A1 (ja) | 2022-07-26 | 2022-07-26 | タンデム圧延機の板厚スケジュール計算方法及び圧延プラント |
Country Status (4)
| Country | Link |
|---|---|
| JP (2) | JP7750417B2 (ja) |
| KR (1) | KR20240039161A (ja) |
| CN (1) | CN117881492A (ja) |
| WO (1) | WO2024023910A1 (ja) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7713204B1 (ja) * | 2024-07-26 | 2025-07-25 | ちょいぷらす株式会社 | メッシュ入りウィッグ型エクステンション及びその製造方法 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119426360B (zh) * | 2024-11-29 | 2025-10-03 | 鞍钢集团北京研究院有限公司 | 一种基于人工标签的智能热轧工艺优化方法 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1157825A (ja) * | 1997-08-12 | 1999-03-02 | Furukawa Electric Co Ltd:The | 圧延機のパススケジュール作成支援システム |
| WO2021084636A1 (ja) * | 2019-10-30 | 2021-05-06 | 東芝三菱電機産業システム株式会社 | タンデム圧延機の板厚スケジュール計算方法および圧延プラント |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000167612A (ja) | 1998-12-04 | 2000-06-20 | Toshiba Corp | 圧延機の最適パススケジュール決定方法及び装置 |
-
2022
- 2022-07-26 CN CN202280057989.2A patent/CN117881492A/zh active Pending
- 2022-07-26 WO PCT/JP2022/028727 patent/WO2024023910A1/ja not_active Ceased
- 2022-07-26 JP JP2024536577A patent/JP7750417B2/ja active Active
- 2022-07-26 KR KR1020247006170A patent/KR20240039161A/ko active Pending
-
2025
- 2025-07-07 JP JP2025114405A patent/JP7848923B2/ja active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1157825A (ja) * | 1997-08-12 | 1999-03-02 | Furukawa Electric Co Ltd:The | 圧延機のパススケジュール作成支援システム |
| WO2021084636A1 (ja) * | 2019-10-30 | 2021-05-06 | 東芝三菱電機産業システム株式会社 | タンデム圧延機の板厚スケジュール計算方法および圧延プラント |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7713204B1 (ja) * | 2024-07-26 | 2025-07-25 | ちょいぷらす株式会社 | メッシュ入りウィッグ型エクステンション及びその製造方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2025129388A (ja) | 2025-09-04 |
| JPWO2024023910A1 (ja) | 2024-02-01 |
| KR20240039161A (ko) | 2024-03-26 |
| CN117881492A (zh) | 2024-04-12 |
| JP7750417B2 (ja) | 2025-10-07 |
| JP7848923B2 (ja) | 2026-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7848923B2 (ja) | タンデム圧延機の板厚スケジュール計算方法 | |
| CN103962391B (zh) | 一种热连轧机精轧机组的轧制负荷优化方法 | |
| JP5647917B2 (ja) | 制御装置及び制御方法 | |
| JP5759206B2 (ja) | 学習係数制御装置 | |
| JPWO2009113719A1 (ja) | 熱間での板圧延における圧延負荷予測の学習方法 | |
| US20230118015A1 (en) | Method Of Controlling Flatness Of Strip Of Rolled Material, Control System And Production Line | |
| TWI749517B (zh) | 直列式壓延機的板厚規格計算方法及壓延設備 | |
| US12140939B2 (en) | Physical model identification system | |
| KR20250093609A (ko) | 마무리 압연재의 폭 예측 방법, 마무리 압연재의 폭 제어 방법, 열연 강판의 제조 방법, 및 마무리 압연재의 폭 예측 모델의 생성 방법 | |
| JP7211386B2 (ja) | モデル学習方法、走間板厚変更方法、鋼板の製造方法、モデル学習装置、走間板厚変更装置および鋼板の製造装置 | |
| JP7230880B2 (ja) | 圧延荷重予測方法、圧延方法、熱延鋼板の製造方法、及び圧延荷重予測モデルの生成方法 | |
| JP7776013B2 (ja) | 圧延機の板厚制御装置 | |
| JP2002336906A (ja) | 圧延機の制御方法および装置 | |
| JP4696775B2 (ja) | 板幅制御方法および装置 | |
| JP5786844B2 (ja) | タンデム圧延機の制御方法及び制御装置 | |
| JP2023177918A (ja) | 熱間圧延におけるレベリング制御方法、レベリング制御装置、熱間圧延設備、及び熱間圧延鋼帯の製造方法 | |
| JP2018122339A (ja) | 板厚制御方法、板厚制御装置、冷間圧延設備および鋼板の製造方法 | |
| JP7841618B2 (ja) | 圧延制御装置 | |
| JP5293403B2 (ja) | ダルワークロールを用いた冷間圧延方法 | |
| JPH0413413A (ja) | 熱間連続圧延機における通板時の板厚制御方法 | |
| JP2006051512A (ja) | 熱間圧延における被圧延材幅の制御方法及び熱延金属板の製造方法 | |
| JP2015147249A (ja) | 圧延機の制御方法、圧延機の制御装置、及び圧延材の製造方法 | |
| JP7736017B2 (ja) | 被圧延材の蛇行量予測装置、蛇行量制御装置、蛇行量予測方法、蛇行量制御方法、及び金属帯の製造方法 | |
| EP4516419A1 (en) | Method for setting rolling condition for cold rolling mill, cold rolling method, method for manufacturing steel sheet, device for setting rolling condition for cold rolling mill, and cold rolling mill | |
| WO2019102790A1 (ja) | 演算装置、情報処理プログラム、および記録媒体 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| ENP | Entry into the national phase |
Ref document number: 20247006170 Country of ref document: KR Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 1020247006170 Country of ref document: KR |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202280057989.2 Country of ref document: CN |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22953008 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024536577 Country of ref document: JP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 22953008 Country of ref document: EP Kind code of ref document: A1 |


















