WO2016038705A1 - 圧延シミュレーション装置 - Google Patents

圧延シミュレーション装置 Download PDF

Info

Publication number
WO2016038705A1
WO2016038705A1 PCT/JP2014/073975 JP2014073975W WO2016038705A1 WO 2016038705 A1 WO2016038705 A1 WO 2016038705A1 JP 2014073975 W JP2014073975 W JP 2014073975W WO 2016038705 A1 WO2016038705 A1 WO 2016038705A1
Authority
WO
WIPO (PCT)
Prior art keywords
rolling
model
simulation
parameter
model formula
Prior art date
Application number
PCT/JP2014/073975
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
美怜 木原
小原　一浩
Original Assignee
東芝三菱電機産業システム株式会社
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 東芝三菱電機産業システム株式会社 filed Critical 東芝三菱電機産業システム株式会社
Priority to JP2016547307A priority Critical patent/JP6292309B2/ja
Priority to KR1020177006332A priority patent/KR101889668B1/ko
Priority to CN201480081164.XA priority patent/CN106660090B/zh
Priority to PCT/JP2014/073975 priority patent/WO2016038705A1/ja
Priority to TW103142558A priority patent/TWI554340B/zh
Publication of WO2016038705A1 publication Critical patent/WO2016038705A1/ja

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
    • B21B—ROLLING OF METAL
    • B21B2261/00—Product parameters

Definitions

  • the present invention simulates a rolling line and a rolling operation for producing a metal product, and changes the dimensions and alloy composition of the metal material, the target value and process of heating, rolling and cooling, the operation stability, the process intermediate material,
  • the present invention relates to a rolling simulation apparatus for predicting product quality.
  • materials such as mechanical properties (strength, formability, toughness, etc.) and electromagnetic properties (permeability, etc.) depend on the alloy composition, heating conditions, processing conditions, and cooling conditions. Change.
  • the alloy composition is adjusted by controlling the addition amount of the component elements, but one lot unit is large at the time of component adjustment, such as using a component adjustment furnace capable of holding molten steel of about 100 tons. For this reason, it is impossible to change the addition amount for each product of about 15 tons. Therefore, in order to manufacture a product of a desired material, it is important to make the material by making heating conditions, processing conditions, and cooling conditions appropriate. Furthermore, these process conditions are important not only for materials but also for product quality such as product dimensions and shapes, and for the realization of stable operations.
  • Process parameters include, for example, target temperatures at each point on the rolling line represented by finish entry temperature, finish delivery temperature, coiling temperature, plate thickness schedule for each pass, and rolling mills. Necessary use of descaler for each pass, use necessity of interstand cooling placed between stands of continuous rolling mill and initial flow rate, amount of lubricant used in finishing mill, cooling pattern used in runout table, etc. There is.
  • Process control by the setting computer is performed so as to achieve the target product quality, that is, to achieve the target values of the various process parameters described above.
  • the setting calculator uses a model formula that expresses the physical phenomenon of each process such as heating, rolling, cooling, and conveyance, and performs setting calculation so as to achieve the target values of the various process parameters.
  • calculation of control target values for various actuators and prediction calculation of the state of the rolled material (metal material) at each stage of the process are repeatedly performed.
  • Model formulas used in setting calculations to calculate physical quantities such as rolling load, deformation resistance, roll gap, temperature, and grain size are expressed as functions with input variables, machine constants, adjustment terms, and learning terms as inputs. .
  • the setting computer compares the model predicted value with actual values such as temperature, shape, sheet thickness, sheet width, and rolling load obtained from sensors provided in the rolling line.
  • a method for automatically learning a learning term of a model formula in advance and improving the accuracy of the model formula and the control accuracy using the model term is disclosed.
  • Patent Document 3 discloses a mechanical property such as a tensile test and a structure observation performed on some product coils, regarding a material prediction model for predicting a change in microstructure of a rolled material and a mechanical property of a final product.
  • a model learning method has been proposed using actual values of mechanical properties obtained from the measurement test results.
  • model parameters mechanical constants, adjustment terms, learning terms
  • model parameters are set using a stratified table divided by factors that are prone to model errors, such as steel grade, target plate thickness, target plate width, target temperature, etc. It is managed in the database belonging to the computer.
  • the process parameters of the rolling operation are determined based on experience over many years for each product specification, and a method of performing temperature control and dimensional control to achieve this has been common.
  • the demand for product specifications has become increasingly sophisticated and diversified, and the method based on experience cannot always determine these target values properly and achieve the final quality of the target such as desired dimensions and mechanical properties.
  • Patent Document 4 An apparatus for simulating a manufacturing process offline has been proposed (for example, Patent Document 4).
  • the simulation device predicts the state of the metal material from time to time, such as dimensions, temperature, and position on the production line, and provides information on the alloy composition of the metal material and information on the processing history and temperature history obtained from the simulation of the production process.
  • the microstructure prediction model predicts changes in the microstructure of the rolled material and the mechanical properties of the final product.
  • the simulation device is also used to find alloy composition and process parameter target values that will achieve the desired quality.
  • the same model as the model used in the actual operation setting calculation, a simplified model, or a highly accurate model in which a part is modeled more faithfully to a physical phenomenon is used.
  • a setting computer used for actual operation and a database for managing the process parameters and model parameters are not used, and a computer and a database dedicated to the simulation are prepared separately.
  • the present invention has been made to solve the above-described problems, and is a rolling simulation capable of accurately simulating the rolling process of a virtual metal material using a rolling line in actual operation on a computer different from the actual operation setting computer.
  • the object is to provide a device.
  • the first invention includes an actuator group that heats, rolls, cools, and conveys a metal material, and a sensor group that detects a control result value of the actuator group and a state result value of the metal material.
  • a rolling simulation apparatus connected to a rolling system and a rolling system including a setting computer for calculating a control target value of the actuator group and a state prediction value of the metal material,
  • the setting calculator is A model formula expressing physical phenomena of each process of heating, rolling, cooling, and conveyance in the rolling line, and having a first model formula expressed by a function having an input variable and a model parameter group as inputs, Using the first model formula, in order to achieve process conditions related to product quality and operating conditions in actual operation, calculate the control target value of the actuator group and the state prediction value of the metal material,
  • the model parameter group of the first model formula is updated as needed based on a comparison value obtained by comparing the control target value and the predicted state value with the actual control value and the actual state value detected by the sensor group.
  • the rolling simulation apparatus is A simulation condition setting unit that sets simulation conditions related to product quality and operation conditions in virtual operation in which the virtual metal material is heated, rolled, cooled, and transported in the rolling line;
  • the second model formula is the same as the first model formula, and the control target value of the actuator group and the predicted state value of the virtual metal material are used to achieve the simulation condition using the second model formula.
  • a virtual rolling line setting calculation unit for calculating A parameter updating unit that updates the model parameter group of the second model formula based on the model parameter group of the first model formula when the model parameter group of the first model formula is updated; It is characterized by providing.
  • the second invention is the first invention, wherein
  • the parameter update unit An update timing designating unit for designating a timing at which calculation is not executed by the setting computer in actual operation; And a parameter copy unit that copies the model parameter group of the first model formula to the model parameter group of the second model formula at the timing.
  • the third invention is the first invention, wherein
  • the model parameter group of the first model formula when the model parameter group of the first model formula is updated, the model parameter group of the second model formula is updated based on the model parameter group of the first model formula.
  • the model parameter of a rolling simulation apparatus can be updated to the newest data in the setting computer of actual operation. For this reason, according to 1st invention, on the computer different from the setting computer of actual operation, the rolling process of the virtual metal material using the rolling line of actual operation can be simulated with high precision.
  • the model parameter of the rolling simulation apparatus can be updated to the latest data in the actual operation setting computer while suppressing an increase in load applied to the calculation in the actual operation setting computer.
  • FIG. 3 is a block diagram showing a configuration of a parameter update unit 33.
  • FIG. It is a figure which shows the update timing suitable for updating the model parameter used with the rolling simulation apparatus 24 in the newest state. It is a figure which shows one specific example of the process which updates the adjustment term and learning term which are required for simulation to the newest state, when a simulation execution command is received. It is a flowchart of the process routine which updates the parameter of each model inherent in the virtual rolling line setting calculation part 32 to the same value as the newest parameter used by actual operation. It is a flowchart which shows one procedure which examines an alloy composition and manufacturing conditions using the rolling simulation apparatus.
  • FIG. 1 is a diagram showing an example of a hot sheet rolling line in Embodiment 1 of the present invention.
  • the object of the subsequent description is a simulator simulating the hot sheet rolling line shown in FIG. This simulator can also be applied to other rolling lines.
  • the rolling line includes a heating device, a rolling mill, a cooling device, a winding device, and a conveyance table that connects them. These devices are driven by actuators such as electric motors and hydraulic devices.
  • the rolling line 1 shown in FIG. 1 includes a heating furnace 11, a rough rolling mill 12, a bar heater 13, a finishing mill entry-side thermometer 14, a finishing mill 15, and a finish in order from the upstream side of the conveyance table 10.
  • a rolling mill outlet side thermometer 16, a runout table 17, a winder inlet side thermometer 18, and a winder 19 are provided.
  • the heating furnace 11 is a furnace for heating the slab.
  • the heating furnace 11 is controlled to obtain a desired slab temperature rising pattern and heating furnace extraction temperature.
  • the rough rolling mill 12 includes a single or a plurality of stands. In the example illustrated in FIG. 1, the rough rolling mill 12 is a reversible rough rolling mill including a single stand.
  • the bar heater 13 is a device that raises the temperature of the rolled product by electromagnetic induction heating or the like in order to control the temperature of the rolled product (including the state in the middle of the product from the slab to the finished product).
  • the finishing mill 15 is composed of one or a plurality of stands, and in the example shown in FIG. 1, is a tandem type finishing mill composed of seven stands.
  • the runout table 17 is a cooling device that cools the rolled product with cooling water in order to control the temperature of the rolled product.
  • the rolling line 1 may be provided with a cooling table, a forced cooling device, etc. as a cooling device.
  • the winder 19 is an apparatus for winding a rolled product into a shape that can be easily conveyed.
  • the conveyance table 10 is an apparatus for conveying the rolled product in each process to the next process. These devices are driven by actuators such as electric motors and hydraulic devices.
  • FIG. 2 is a block diagram showing the rolling system according to Embodiment 1 of the present invention.
  • the rolling system 20 shown in FIG. 2 has a hierarchical structure from level 0 to level 3.
  • Level 0 includes a drive control device that controls an electric motor that drives each device of the rolling line 1 and a hydraulic device that drives each device of the rolling line 1.
  • Level 1 includes a controller 21 for control.
  • Level 2 is composed of a setting computer 23. In addition, it is good also as a structure which replaces with the setting computer 23 and uses a process controller.
  • Level 3 is composed of a host computer 25 for production management.
  • the rolling simulation device 24 does not affect rolling in actual operation, but is connected to the setting computer 23 for parameter update.
  • the target value of the process parameter may be specified from the upper computer 25 of the level 3 that is higher than the setting computer 23 of the level 2.
  • the target value of the process parameter may have a table in a database belonging to the setting computer 23, and may be specified using steel type, plate thickness, plate width, etc. as keys. Further, the target value of the process parameter may be changed during rolling by an operator.
  • the setting computer 23 represents a model formula expressing physical phenomena of each process such as heating, rolling, cooling, and conveyance in the rolling line 1 (hereinafter, the model formula of the setting computer 23 is also referred to as “first model formula”). Have.
  • the setting calculator 23 uses the first model formula to perform setting calculation so as to achieve the target values (process conditions) of the various process parameters described above in actual operation. In the setting calculation, calculation of control target values of various actuators and calculation of the state of the rolled material (state prediction value of the metal material) at each stage of the process are repeatedly performed.
  • Actuator control target values include the roll gap of the rolling mill, the rolling speed, the conveying speed, the flow rate of the descaler and various sprays, the ON / OFF of the valve of the runout table, and the like.
  • the state of the rolled material (predicted value of the state of the metal material) at each stage of the process includes dimensions, shape, temperature, microstructure, and the like.
  • the controller 21 for control receives the setting calculation result from the setting computer 23, and controls various actuators so as to follow the control target value.
  • various sensors are installed throughout the rolling line to monitor and collect actual values of parameters that affect process control, such as temperature, shape, plate thickness, plate width, and rolling load.
  • the model formula (first model formula) that calculates physical quantities such as rolling load, deformation resistance, roll gap, temperature, and grain size used in the setting calculation is input variables, model parameter groups (machine constants, adjustment terms, learning This is expressed as a function with (
  • the input variable is a physical quantity correlated with the model output. For example, when the model output is a rolling load, the deformation resistance, the width of the rolled material, the amount of reduction, and the like are input variables.
  • the mechanical constant is a physical quantity that represents the mechanical characteristics of the actuator, such as the roll diameter, mill curve, and spray flow rate of the rolling roll.
  • the machine constant is updated at any time because it changes due to roll change, equipment repair and adjustment, and aging.
  • the adjustment term and the learning term are terms for improving the prediction accuracy of the model formula.
  • the adjustment term is a coefficient or constant of each term in the model formula, and a factor that is likely to cause a model error, for example, a stratified table divided by steel type, target plate thickness, target plate width, target temperature, etc.
  • Each layer is managed in a database belonging to the setting computer 23.
  • the adjustment term is adjusted not only at the time of starting the operation, but mainly when rolling a new steel type or rolling with a combination of new process parameters.
  • the adjustment term may be adjusted by an engineer based on experience or numerical analysis results, or in recent years may be semi-automatically adjusted using a statistical technique such as a neural network.
  • the learning term is a term that is multiplied and added to the model expression in order to fill an error between the model output and the actual process output.
  • FIG. 3 is a block diagram showing functions of the rolling simulation device 24 according to Embodiment 1 of the present invention.
  • the rolling simulation apparatus 24 simulates each process in the hot sheet rolling line shown in FIG. 1, and the operational stability when the metal material dimensions, alloy composition, heating, rolling, and cooling target values and processes are changed. Predict the state of rolled material and product quality during the process.
  • the rolling simulation device 24 includes a simulation condition setting unit 31, a virtual rolling line setting calculation unit 32, and a parameter update unit 33.
  • the rolling simulation device 24 is a computer including an arithmetic processing device, a storage device, and an input / output device.
  • the storage device stores a program describing the processing contents of the above-described units. Each of the above sections is realized by executing a program loaded from the storage device on the arithmetic processing unit.
  • the simulation condition setting unit 31 sets simulation conditions related to product quality and operation conditions in a virtual operation in which a virtual metal material is heated, rolled, cooled, and conveyed in the rolling line 1. Details will be described below.
  • the simulation condition setting unit 31 sets the parameters of the rolling operation process in the rolling simulation device 24 as simulation conditions.
  • the parameters of the rolling operation process are, for example, the alloy composition and dimensions of the rolled material, the target plate thickness, the target plate width, the slab temperature rising pattern in the heating furnace, the heating furnace discharge, which are given from the host computer 25 in the actual operation. Side temperature, finish delivery target temperature, finish entry target temperature, cooling pattern, winding target temperature, and the like.
  • the parameters of the rolling operation process are set in advance in the setting computer 23 for each steel type and each target sheet thickness category, or are given from the HMI by the operator from the HMI and the distribution of the reduction rate of each pass. , Plate speed and acceleration rate.
  • the operating conditions of the metal material rolled or planned to be rolled in the actual operation stored in the upper computer 25 or the setting computer 23 of the actual operation are copied via a communication LAN or a storage medium. Can be used. In addition, all or some of the conditions can be set manually. Further, it is possible to reuse the simulation conditions used in the past by the rolling simulation apparatus or to change a part of the simulation conditions.
  • FIG. 4 is an input screen for inputting chemical components of a virtual metal product (virtual metal material).
  • the simulation condition setting unit 31 includes, for example, the content (wt%) of each chemical component in each virtual metal product so that the change in product quality when the alloy composition is changed can be easily calculated. Enter to set. It is also possible to call the alloy composition of the metal product rolled in actual operation or the alloy composition used in the past simulation as a reference value, and to simulate by changing a part of it.
  • FIG. 5 is a diagram showing an example of a slab temperature rising pattern in the heating furnace 11.
  • the slab temperature rising pattern in the heating furnace 11 and the heating furnace extraction temperature also affect the product material and quality. For example, when the slab is not heated sufficiently, the solid solution amount of the microalloy cannot be obtained sufficiently, the Solute drag effect due to the solid solution microalloy is reduced, and the amount of precipitation during rolling and cooling after extraction is reduced, There is a concern that the pinning effect due to precipitates is reduced. Furthermore, rolling a low-temperature rolled material causes a hard material to be rolled, and there is a concern that the rolling operation may become unstable due to an increase in the rolling load in the rolling mill and the power consumption of the rolling motor may increase.
  • the simulation condition setting unit 31 sets a slab temperature rising pattern in the heating furnace 11 as shown in FIG. When the temperature pattern does not affect the quality or when a simple calculation is desired, only the target value of the heating furnace extraction temperature is set.
  • target values of process parameters such as finishing target temperature, finishing input target temperature, and winding target temperature are set via the host computer 25 or HMI.
  • the rolling speed, the temperature rising pattern of the heating device in the middle of the rolling line, various sprays, and the cooling pattern on the run-out table 17 are controlled so as to follow the target value given by the operator.
  • the cooling pattern may be specified by the host computer 25.
  • the finish side target temperature and the finish side target temperature are used as simulation conditions so that the effect on product quality and rolling operation when the temperature history during rolling is changed can be confirmed by simulation.
  • the winding target temperature and the cooling pattern on the run-out table 17 are set.
  • the cooling pattern in the run-out table 17 includes three patterns of pre-cooling that preferentially uses the upstream cooling equipment, post-cooling that preferentially uses the downstream cooling equipment, and gentle cooling that uses all the cooling equipment. There is a method of selecting either of them and setting the cooling rate of the zone for water cooling and the time for air cooling as target values. Further, as the cooling pattern in the run-out table 17, a pattern in which water cooling is performed on the upstream side and downstream side of the cooling facility shown in FIG. 7 and air cooling is selected in the middle stream is selected. For example, the water cooling rate on the upstream side and the air cooling time are selected. And a method of setting the temperature at the midpoint of the runout table as a target value.
  • target values of process parameters such as the rolling amount of each pass, the rolling rate distribution, the plate passing speed and the acceleration rate are set in advance for each steel type and target plate.
  • the operator inputs a target value for the process parameter.
  • the simulation condition setting unit 31 changes the product quality and the rolling operation when the rolling amount and rolling rate distribution of each pass, the sheet feeding speed and the acceleration rate are changed. Set simulation conditions so that the impact can be calculated easily.
  • the virtual rolling line setting calculation unit 32 has a model formula similar to the first model formula (referred to as a second model formula) and uses the second model formula to achieve the simulation conditions of the actuator group. A control target value and a predicted state value of the virtual metal material are calculated. Details will be described below.
  • the virtual rolling line setting calculation unit 32 sets the setting values of each process for rolling the virtual metal material on the virtual rolling line so as to follow each target value given by the simulation condition setting unit 31, and the metal every moment. Calculate material dimensions, location, and temperature.
  • FIG. 8 is a diagram illustrating a model group and a model parameter table group included in the virtual rolling line setting calculation unit 32.
  • the virtual rolling line setting calculation unit 32 includes a process model, a transfer model, a temperature model, and a material model as a model group.
  • the process model calculates set values for each rolling process such as a heating device, a rolling device, and a cooling device.
  • the transport model calculates the position of the virtual metal material at each time.
  • the temperature model calculates the temperature of the virtual metal material at each time at each location.
  • the material model predicts the microstructure of the metal material and the final product material at each time at each location on the virtual rolling line based on the alloy composition, processing history, and temperature.
  • the virtual rolling line setting calculation unit 32 includes a storage device such as a database that stores a model parameter table group for storing the parameters of each model described above, and performs simultaneous calculation of each model formula.
  • the process model uses information on the position of the virtual metal material at each time at each location given by the transfer model and the temperature of the virtual metal material at each time at each location given by the temperature model, and a target value given by the simulation condition setting unit 31
  • the cooling setting of the runout table 17 is calculated.
  • the transfer model calculates the position of the virtual metal material at each time at each location using the distance between each process and the path schedule given by the process model.
  • the transport model calculates the transport speed that follows each target temperature using the temperature information of the virtual metal material given by the temperature model.
  • the temperature model includes virtual metal material dimension information in each process, machine specification information, a path schedule given from the simulation condition setting unit 31 and the process model, a roll gap, a rolling speed, a conveying speed, and a heating device in the middle of the rolling line.
  • the temperature of the virtual metal material at each time at each location on the virtual rolling line is calculated from information on the command value such as the temperature rising pattern.
  • the material model predicts the microstructure of the virtual metal material during and after the rolling process, using the processing history of the virtual metal given by the process model and the temperature history information given by the temperature model.
  • the predicted microstructure is, for example, the fraction of each structure such as particle size, dislocation density, austenite, ferrite, pearlite and the like.
  • parameters related to mechanical properties such as yield stress and tensile strength are calculated based on the microstructure prediction results.
  • a variety of microstructure prediction models that formulate metallurgical phenomena have been proposed and consist of a group of mathematical expressions that represent static recovery, static recrystallization, dynamic recovery, dynamic recrystallization, grain growth, etc. Is widely known. An example is given on pages 198 to 229 of the plastic working technology series 7 plate rolling (Corona).
  • the above process model, transfer model, temperature model, and material model are represented by the same function as the model formula (first model formula) inherent in the setting computer 23 used in the actual operation of hot rolling.
  • model formula first model formula
  • the model formula (first model formula) of the setting computer 23 used for the actual operation and the database structure for managing the model parameters can be ported to the rolling simulation device 24. Therefore, the rolling simulation device 24 has a model formula (second model formula) similar to the first model formula.
  • the model formula is a function with input variables, machine constants, and adjustment terms as inputs, and is expressed by the following formula.
  • f Model expression that does not include learning term
  • Y Output of model expression that does not include learning term
  • X i Input variable m i related to model expression
  • f Machine constant
  • a j Adjustment term
  • the input variable is a physical quantity correlated with the model output.
  • the mechanical constant is a physical quantity representing mechanical characteristics such as a roll diameter of a rolling roll, a mill curve, and a spray flow rate.
  • the machine constant changes due to roll change, periodic repair, equipment replacement, aging, and the like. In actual operation, the machine constant is managed by a database table belonging to the setting computer 23 used for actual operation, and is corrected as needed in accordance with the above change.
  • the adjustment term is a term for improving the prediction accuracy of the model formula.
  • the adjustment term is a coefficient or a constant that is provided to reduce the model error and is allowed to be corrected.
  • the adjustment term belongs to the setting computer 23 used for actual operation for each stratification using a stratification table divided by factors that are likely to cause model errors, for example, steel type, target plate thickness, target plate width, target temperature, etc. Managed in the database.
  • the adjustment term is adjusted mainly when a new steel type is rolled or when a new process parameter combination is used, in addition to when the operation is started.
  • An engineer may make adjustments based on experience or numerical analysis results of actual operations, or in recent years, semi-automatic adjustments may also be made using statistical methods such as neural networks.
  • various sensors are installed everywhere on the rolling line 1 to monitor and collect actual values of parameters that affect process control, such as temperature, shape, thickness, width, and rolling load. These actual values are used for process control, accuracy improvement of the model formula (first model formula), and quality control. Compare the model predicted value of the setting calculation with the actual value acquired by various sensors, the actual value and the actual calculated value recalculated from the calculated value, and learn the model formula. A method for improving the used control accuracy is used. The learning term is multiplied or added to the model expression to fill in the error between the model output and the actual process output.
  • Each of the multiplication type and the addition type is expressed as follows.
  • Y L Prediction result of learned model expression
  • Y Output of model expression not including learning term
  • Z p Multiplicative learning term
  • Z A Additive learning term
  • the learning term is updated by obtaining the actual value of the parameter corresponding to the output of the model formula with a sensor or the like.
  • the learning term is updated as follows.
  • Z P ACT Multiplying learning term Y ACT calculated based on the actual value Y ACT : Actual value of parameter according to the model equation output Y: Model equation output not including the learning term Z P NEW : Multiplicative learning term Z P after update OLD : multiplication learning term before update ⁇ : smoothing gain
  • the learning term is automatically updated for each stratification using a stratification table divided by factors that are likely to cause model errors, such as steel grade, target plate thickness, target plate width, target temperature, and the like.
  • the microstructure prediction model for predicting changes in the microstructure of the rolled material and mechanical properties of the final product, the results of mechanical properties measurement tests such as tensile tests and structural observations performed on some product coils
  • the model is learned using the actual values of mechanical properties obtained in step (1).
  • Model parameters of the model formula (first model formula) used in the actual operation setting calculation that is, machine constants, adjustment terms, and learning terms are managed in a database belonging to the actual operation setting computer 23.
  • the model model (second model formula) of the process model, the transfer model, the temperature model, and the material model in which the virtual rolling line setting calculation unit 32 of the rolling simulation apparatus 24 in FIG. 8 is used is used for the actual operation of hot rolling.
  • a function having the same definition as the model formula (first model formula) inherent in the setting computer 23 is used.
  • the model parameter table group in which the parameters of the machine constant, the adjustment term, and the learning term are stored for each layer is managed by a database belonging to the virtual rolling line setting calculation unit 32.
  • the database table belonging to the virtual rolling line setting calculation unit 32 has the same structure as the table storing machine constants, adjustment terms, and learning terms in the database belonging to the setting computer 23 used for actual operation.
  • FIG. 9 is a diagram for explaining processing executed by the parameter update unit 33.
  • the parameter updating unit 33 updates the model parameter group of the second model formula based on the model parameter group of the first model formula when the model parameter group of the first model formula is updated. Details will be described below.
  • the model parameters of the model formula of the virtual rolling line setting calculation unit 32 that is, machine parameters, adjustment terms, and learning terms are parameters of the database belonging to the actual operation setting computer 23. Update based on parameters stored in tables.
  • simulation unlike actual process control of rolling operations, it is impossible to obtain actual values of loads, temperatures, dimensions, and actual values of mechanical properties of product coils obtained by sensors installed in various parts of the process. It is necessary to prevent the calculation by simulation and the load by reading and writing to the database from affecting the setting calculation of actual operation. Therefore, in the simulation, the setting computer 23 and its database used for actual operation are not used, and a computer and database dedicated to the simulation are used.
  • the machine constant, the adjustment term, and the learning term in the second model formula are not updated at the same timing as the first model formula of the setting computer 23 used for actual operation.
  • the parameter updating unit 33 does not affect the actual operation setting calculation, and the second model formula of the virtual rolling line setting calculation unit 32 of the simulation is ensured so as to ensure the same model accuracy as the actual operation setting calculation.
  • Model parameters that is, machine constants, adjustment terms, and learning terms are updated.
  • FIG. 10 is a block diagram showing the configuration of the parameter update unit 33.
  • the parameter update unit 33 includes an update timing designation unit 41, an update parameter selection unit 42, and a parameter copy unit 43.
  • the update timing designation unit 41 automatically designates the timing for updating the simulator parameters. For example, the timing at which the calculation is not executed by the setting computer 23 in the actual operation is designated.
  • the update parameter selection unit 42 selects a parameter to be updated. For example, from the model parameter group of the second model formula, a part of the model parameter group necessary for the model calculation using the simulation condition in the virtual rolling line setting calculation unit 32 is selected.
  • the parameter copy unit 43 stores only a part of the model parameter group selected by the update parameter selection unit 42 at the update timing obtained from the update timing specification unit 41 in the database belonging to the setting computer 23 for actual operation. Copy from the model parameter group of the first model formula.
  • the rolling line stops for example, a roll change period in which the line is stopped for several tens of minutes at a frequency of several hours, or a line is stopped for several hours to several tens of hours at a frequency of several days or weeks.
  • the update timing designating unit 41 inherent in the parameter updating unit 33 of the rolling simulation device 24 selects the roll change, regular repair, and facility update periods in the actual operation as the model parameter update timing of the rolling simulation device 24. For example, it does not affect the setting calculation of actual operation.
  • the model parameters (machine constants, adjustment terms, and learning terms) used in the actual operation setting calculation are updated at different timings. For example, among the mechanical constants, the initial roll diameter of the rolling roll is changed every time the roll is changed every several hours. Even with the machine constant, the mill curve, which is an indicator of the elongation of the rolling mill, is updated over a relatively long span of several months or years.
  • the flow rates of various sprays change over time, but the amount of change is gradual, and it is difficult to measure the flow rate if a flow meter is not installed in advance. Therefore, the flow rates of various sprays are not measured unless there are special circumstances, such as when a malfunction occurs or when equipment is updated.
  • the adjustment term is adjusted not only at the time of starting the operation, but mainly when rolling a new steel type or rolling with a combination of new process parameters. Of these, the learning term has the highest update frequency.
  • the learning term is managed for each rolling by a stratified table divided by factors that are likely to cause model errors, such as steel type, target plate thickness, target plate width, target temperature, etc.
  • the learning terms in the corresponding layer of the model formula are updated. If the model parameters used in the rolling simulation device 24 are updated at a frequency equivalent to the update frequency of the model parameters used in actual operation, the rolling in actual operation can be accurately simulated.
  • FIG. 11 is a diagram showing an update timing suitable for updating the model parameters used in the rolling simulation device 24 to the latest state.
  • the same value as the actual operation parameter is copied to each parameter used in the rolling simulation device 24.
  • the adjustment term and the learning term may be updated at a frequency that is higher than that at the time of regular repair or roll change, or at a different timing.
  • the automatic update of all parameters should be performed at the timing when the rolling operation is stopped.
  • the rolling simulation device 24 a simulation including the dimensions and alloy composition of the rolling material to be simulated given by the simulation condition setting unit 31, target product dimensions and materials, and parameters of the rolling operation process such as rolling reduction distribution and cooling pattern, etc. From the conditions, the model parameters necessary for the simulation to be executed are clear. Therefore, if the adjustment term and the learning term necessary for the simulation are updated to the latest state at the time of executing the simulation, it is possible to accurately simulate the rolling in the actual operation under the conditions.
  • FIG. 12 is a diagram showing one specific example of the process of updating the adjustment term and the learning term necessary for the simulation to the latest state when receiving the simulation execution command.
  • the steel type and the plate thickness classification of the virtual rolled material used for the simulation are identified from the alloy composition, the target plate thickness, etc. among the simulation conditions.
  • the database table group belonging to the actual operation setting computer 23 and the database table group belonging to the rolling simulation device 24 have the same table structure, and data can be copied between the databases.
  • the database includes an adjustment term table group, a learning term table group, and a machine constant table group.
  • the update parameter is notified to the update timing designation unit 41 and the parameter copy unit 43.
  • the update timing specifying unit 41 confirms that the update of the selected parameter does not affect the actual operation setting calculation. When there is no influence, the update timing is designated and notified to the parameter copy unit 43.
  • the parameter copy unit 43 copies the selected update parameter from the database belonging to the actual operation setting computer 23 to the database belonging to the rolling simulation device 24 at the designated update timing.
  • FIG. 13 is a flowchart of a processing routine for updating the parameters of each model inherent in the virtual rolling line setting calculation unit 32 to the same values as the latest parameters used in actual operation. This processing routine is repeatedly executed by the parameter update unit 33.
  • step S131 the parameter update unit 33 determines whether or not the rolling line 1 is under periodic repair. Specifically, the update timing designation unit 41 inquires of the controller 21 for control or the setting computer 23 whether the rolling line 1 is undergoing periodic repair. The update timing designation unit 41 determines whether or not the rolling line 1 is undergoing periodic repair based on the inquiry result. If it is under periodic repair, the process of step S132 is executed. If the regular repair is not in progress, the process of step S133 is executed.
  • step S132 the parameter update unit 33 selects all model parameters as update parameters.
  • the update parameter selection unit 42 selects all parameters at the time of periodic repair.
  • step S133 the parameter update unit 33 determines whether or not a roll change has been performed. Specifically, the update timing designation unit 41 inquires of the controller 21 for control or the setting computer 23 whether or not the operation mode of the rolling line 1 is the roll change mode. The update timing designation unit 41 determines whether or not the roll change mode is set based on the inquiry result. If it is the roll change mode, the process of step S134 is executed. If it is not the roll change mode, the process of step S135 is executed.
  • step S134 the parameter update unit 33 selects machine constants related to the roll and all learning terms as update parameters. Specifically, the update parameter selection unit 42 selects machine constants related to the roll and all learning terms as model parameters to be updated.
  • step S135 the parameter update unit 33 determines whether a simulation execution command has been issued. Specifically, the update timing command unit 41 of the parameter update unit 33 inquires of the simulation condition setting unit 31 whether the simulation condition is input and a simulation execution command is issued. The parameter update unit 33 determines whether or not a simulation execution command has been issued based on the inquiry result. If a simulation execution command is given, the process of step S136 is executed.
  • step S136 the parameter update unit 33 selects a learning term and an adjustment term related to the simulation condition as an update parameter before executing the simulation calculation.
  • the update parameter selection unit 42 selects learning terms and adjustment terms related to simulation conditions as model parameters to be updated.
  • step S137 the update timing specification unit 41 of the parameter update unit 33 determines whether or not the update of the parameter selected by the update parameter selection unit 42 does not affect the actual operation setting calculation. Specifically, the update timing designating unit 41 calculates the load applied to the setting computer 23 when acquiring the parameter selected by the update parameter selecting unit 42 from the setting computer 23 for actual operation. In addition, the update timing designation unit 41 confirms the load status of the setting computer 23. Based on these, the update timing designating unit 41 confirms that even if a load due to parameter acquisition occurs, it does not affect the actual operation setting calculation. If it is determined that the parameter update does not affect the actual operation setting calculation, the process of step S139 is executed. If it is determined that the parameter update affects the actual operation setting calculation, the process of step S138 is executed.
  • step S138 it is determined whether the number of executions of the determination process in step S137 is less than the upper limit number. If the determination condition is satisfied, the process of step S137 is re-executed after the specified time has elapsed. If the determination condition is not satisfied, the process of this routine is terminated.
  • step S139 the parameter copy unit 43 updates the model parameter selected by the update parameter selection unit 42 to the same value as the latest parameter used in the setting computer 23 for actual operation.
  • FIG. 14 is a flowchart showing one procedure for examining the alloy composition and manufacturing conditions using the rolling simulation device 24.
  • step S141 the parameter update unit 33 updates all model parameters at the time of periodic repair.
  • the processing in step S141 is the same as the processing in steps S131 and S132 in FIG.
  • step S142 the parameter update unit 33 updates the machine constant and all learning terms related to the roll.
  • the processing in step S142 is the same as the processing in steps S133 and S134 of FIG. 13 described above.
  • step S143 the user inputs simulation conditions using the input / output device of the rolling simulation device 24.
  • the user can obtain initial slab information (dimensions, alloy composition) of virtual metal used for the simulation, various target values (heating furnace extraction target temperature, finishing input target temperature, finishing output target temperature, winding target temperature). , Rough rolling delivery target plate thickness, rough rolling delivery target plate width, target plate width, target plate thickness, target crown ratio, target flatness, etc.) and more detailed conditions (for example, heating furnace slab temperature rising pattern, Enter the roughing-side target temperature, the rolling amount and rolling rate distribution of each pass, the plate feed speed and acceleration rate, the cooling pattern at the run-out table, various spray settings, finish rolling bender, work roll shift, etc., as necessary. .
  • the input simulation condition is set in the simulation condition setting unit 31.
  • step S144 the parameter updating unit 33 updates the learning terms and adjustment terms related to the simulation conditions before executing the simulation calculation.
  • the update parameter selection unit 42 selects learning terms and adjustment terms related to simulation conditions as model parameters to be updated.
  • the parameter copy unit 43 updates the selected model parameter to the same value as the latest parameter used for actual operation.
  • step S145 the virtual rolling line setting calculation unit 32 sets the set value of each process and the size and position of the metal material at each time when the virtual metal material is rolled on the virtual rolling line based on the set simulation conditions.
  • the temperature is calculated using a process model, a transfer model, and a temperature model.
  • the virtual rolling line setting calculation unit 32 predicts the final product material using the material model as input values of the processing history and temperature history information of the given virtual metal.
  • the metal structure change during virtual rolling of the virtual metal is predicted using the metal structure prediction model.
  • the material such as the mechanical properties such as yield stress and tensile strength is predicted using the finally calculated structure and alloy composition of the virtual metal product as input values.
  • step S146 the user confirms the quality of the virtual metal product based on the calculation result in step S145.
  • step S147 the user confirms the setting value of each process.
  • step S148 the simulation conditions are changed as necessary, and the processes in steps S144 to S147 are repeated.
  • step S149 the user considers application of the simulation result to actual operation.
  • an accurate simulation simulating actual operation rolling can be performed without affecting actual operation rolling.
  • the simulation conditions are changed, the above simulation is repeatedly performed, and the results are analyzed to obtain guidelines for improving the heating, rolling and cooling conditions and slab alloy composition in actual operation.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Mechanical Engineering (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Control Of Metal Rolling (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Feedback Control In General (AREA)
  • Testing And Monitoring For Control Systems (AREA)
PCT/JP2014/073975 2014-09-10 2014-09-10 圧延シミュレーション装置 WO2016038705A1 (ja)

Priority Applications (5)

Application Number Priority Date Filing Date Title
JP2016547307A JP6292309B2 (ja) 2014-09-10 2014-09-10 圧延シミュレーション装置
KR1020177006332A KR101889668B1 (ko) 2014-09-10 2014-09-10 압연 시뮬레이션 장치
CN201480081164.XA CN106660090B (zh) 2014-09-10 2014-09-10 轧制模拟装置
PCT/JP2014/073975 WO2016038705A1 (ja) 2014-09-10 2014-09-10 圧延シミュレーション装置
TW103142558A TWI554340B (zh) 2014-09-10 2014-12-08 壓延模擬裝置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2014/073975 WO2016038705A1 (ja) 2014-09-10 2014-09-10 圧延シミュレーション装置

Publications (1)

Publication Number Publication Date
WO2016038705A1 true WO2016038705A1 (ja) 2016-03-17

Family

ID=55458493

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2014/073975 WO2016038705A1 (ja) 2014-09-10 2014-09-10 圧延シミュレーション装置

Country Status (5)

Country Link
JP (1) JP6292309B2 (zh)
KR (1) KR101889668B1 (zh)
CN (1) CN106660090B (zh)
TW (1) TWI554340B (zh)
WO (1) WO2016038705A1 (zh)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019202934A1 (ja) * 2018-04-20 2019-10-24 オムロン株式会社 情報処理システム、情報処理方法、および情報処理プログラム
JP2020082112A (ja) * 2018-11-20 2020-06-04 東芝三菱電機産業システム株式会社 金属材料の材質制御支援装置
JPWO2020149198A1 (ja) * 2019-01-15 2021-02-18 Ｊｆｅスチール株式会社 解析システム及び解析方法
JPWO2021229727A1 (zh) * 2020-05-13 2021-11-18
JP2021181095A (ja) * 2020-05-18 2021-11-25 Ｊｆｅスチール株式会社 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
CN113780852A (zh) * 2021-09-16 2021-12-10 东北大学 一种板带轧制过程质量缺陷的诊断方法
CN115038965A (zh) * 2020-01-29 2022-09-09 杰富意钢铁株式会社 金相组织的相的分类方法、金相组织的相的分类装置、金相组织的相的学习方法、金相组织的相的学习装置、金属材料的材料特性预测方法和金属材料的材料特性预测装置
EP4006670A4 (en) * 2019-07-22 2022-09-14 JFE Steel Corporation METHOD FOR CREATING QUALITY PREDICTION MODEL, QUALITY PREDICTION MODEL, QUALITY PREDICTION METHOD, METHOD FOR MANUFACTURING METAL MATERIAL, DEVICE FOR CREATING QUALITY PREDICTION MODEL, AND QUALITY PREDICTION DEVICE
TWI808407B (zh) * 2021-01-21 2023-07-11 日商東芝三菱電機產業系統股份有限公司 輥管理裝置
EP4131159A4 (en) * 2020-03-31 2023-11-08 JFE Steel Corporation METHOD FOR DETERMINING METALLOGRAPHIC STRUCTURE IMAGING CONDITION, METALLOGRAPHIC STRUCTURE IMAGING METHOD, METHOD FOR CLASSIFYING METALLOGRAPHIC STRUCTURE PHASES, DEVICE FOR DETERMINING METALLOGRAPHIC STRUCTURE IMAGING CONDITION, METALLOGRAPHIC STRUCTURE IMAGING CONDITION DEVICE METALLOGRAPHIC STRUCTURE, DEVICE FOR CLASSIFYING PHASES OF METALLOGRAPHIC STRUCTURE, METHOD FOR PREDICTING MATERIAL PROPERTIES OF METAL MATERIAL, AND DEVICE FOR PREDICTING MATERIAL PROPERTIES OF METAL MATERIAL

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7052250B2 (ja) * 2017-08-10 2022-04-12 オムロン株式会社 情報処理装置、情報処理方法、および情報処理プログラム
WO2020152750A1 (ja) * 2019-01-21 2020-07-30 Ｊｆｅスチール株式会社 金属材料の設計支援方法、予測モデルの生成方法、金属材料の製造方法、及び設計支援装置
JP2020131248A (ja) * 2019-02-21 2020-08-31 Ｊｆｅスチール株式会社 圧延荷重予測方法、圧延荷重予測装置、及び圧延制御方法
TWI721879B (zh) * 2020-05-04 2021-03-11 和碩聯合科技股份有限公司 決定產能參數的方法及產能參數產生系統
TWI740494B (zh) * 2020-05-12 2021-09-21 中國鋼鐵股份有限公司 軋輥檢驗方法與軋輥檢驗系統
TWI731809B (zh) * 2020-10-21 2021-06-21 中國鋼鐵股份有限公司 改善鋼條捲溫震盪的控制方法
WO2022172524A1 (ja) * 2021-02-15 2022-08-18 Ｊｆｅスチール株式会社 冷間圧延機の圧延条件算出方法、冷間圧延機の圧延条件算出装置、冷間圧延方法、冷間圧延機、及び鋼板の製造方法
TWI792240B (zh) * 2021-03-24 2023-02-11 中國鋼鐵股份有限公司 用於軋延製程的控制參數的調整方法
TWI787940B (zh) * 2021-08-04 2022-12-21 中國鋼鐵股份有限公司 加熱爐的爐溫設定值的優化方法
TWI798047B (zh) * 2022-04-08 2023-04-01 中國鋼鐵股份有限公司 鋼板軋延力預測方法與軋延系統

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008012881A1 (fr) * 2006-07-26 2008-01-31 Toshiba Mitsubishi-Electric Industrial Systems Corporation Appareil de contrôle de matériaux et de prévision de matériaux pour ligne de laminage
JP2010172962A (ja) * 2009-02-02 2010-08-12 Toshiba Mitsubishi-Electric Industrial System Corp 圧延製品の特性予測方法

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05118979A (ja) * 1991-10-25 1993-05-14 Hitachi Metals Ltd 転造シミユレーシヨン試験方法およびその試験装置
JPH06312206A (ja) * 1993-04-28 1994-11-08 Nippon Steel Corp 熱間圧延工場の物流シミュレーション装置
JP2001025805A (ja) 1999-07-13 2001-01-30 Kobe Steel Ltd 圧延シミュレーション装置，及び圧延シミュレーションプログラムを記録したコンピュータ読み取り可能な記録媒体
KR100425601B1 (ko) * 1999-12-28 2004-04-03 주식회사 포스코 압연기의 형상 제어 특성을 실시간으로 시뮬레이션할 수있는 장치
JP4119684B2 (ja) 2002-05-27 2008-07-16 東芝三菱電機産業システム株式会社 圧延機設定計算装置用学習制御装置
JP4402502B2 (ja) 2004-04-13 2010-01-20 東芝三菱電機産業システム株式会社 巻取温度制御装置
KR100841888B1 (ko) * 2007-04-12 2008-06-27 도시바 미쓰비시덴키 산교시스템 가부시키가이샤 압연 라인의 재질 예측 및 재질 제어 장치
JP4890433B2 (ja) * 2007-12-28 2012-03-07 株式会社神戸製鋼所 圧延材の温度予測方法、圧延材の冷却装置の制御方法、及び連続圧延設備
JP2009208115A (ja) * 2008-03-04 2009-09-17 Kobe Steel Ltd 圧延制御パラメータの算出方法及び算出装置、圧延シミュレーション装置
CN103406362B (zh) * 2013-08-08 2015-03-04 东北大学 一种模拟中厚板轧机轧制过程的控制系统及方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008012881A1 (fr) * 2006-07-26 2008-01-31 Toshiba Mitsubishi-Electric Industrial Systems Corporation Appareil de contrôle de matériaux et de prévision de matériaux pour ligne de laminage
JP2010172962A (ja) * 2009-02-02 2010-08-12 Toshiba Mitsubishi-Electric Industrial System Corp 圧延製品の特性予測方法

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019191737A (ja) * 2018-04-20 2019-10-31 オムロン株式会社 情報処理システム、情報処理方法、および情報処理プログラム
WO2019202934A1 (ja) * 2018-04-20 2019-10-24 オムロン株式会社 情報処理システム、情報処理方法、および情報処理プログラム
JP2020082112A (ja) * 2018-11-20 2020-06-04 東芝三菱電機産業システム株式会社 金属材料の材質制御支援装置
JP7020379B2 (ja) 2018-11-20 2022-02-16 東芝三菱電機産業システム株式会社 金属材料の材質制御支援装置
JPWO2020149198A1 (ja) * 2019-01-15 2021-02-18 Ｊｆｅスチール株式会社 解析システム及び解析方法
JP7027536B2 (ja) 2019-01-15 2022-03-01 Ｊｆｅスチール株式会社 解析システム及び解析方法
EP4006670A4 (en) * 2019-07-22 2022-09-14 JFE Steel Corporation METHOD FOR CREATING QUALITY PREDICTION MODEL, QUALITY PREDICTION MODEL, QUALITY PREDICTION METHOD, METHOD FOR MANUFACTURING METAL MATERIAL, DEVICE FOR CREATING QUALITY PREDICTION MODEL, AND QUALITY PREDICTION DEVICE
EP4099012A4 (en) * 2020-01-29 2023-08-23 JFE Steel Corporation METALLIC STRUCTURE PHASE CLASSIFYING METHOD AND DEVICE, METALLIC STRUCTURE PHASE LEARNING METHOD AND DEVICE, MATERIAL PROPERTY PREDICTION METHOD AND DEVICE FOR METALLIC MATERIAL
CN115038965A (zh) * 2020-01-29 2022-09-09 杰富意钢铁株式会社 金相组织的相的分类方法、金相组织的相的分类装置、金相组织的相的学习方法、金相组织的相的学习装置、金属材料的材料特性预测方法和金属材料的材料特性预测装置
EP4131159A4 (en) * 2020-03-31 2023-11-08 JFE Steel Corporation METHOD FOR DETERMINING METALLOGRAPHIC STRUCTURE IMAGING CONDITION, METALLOGRAPHIC STRUCTURE IMAGING METHOD, METHOD FOR CLASSIFYING METALLOGRAPHIC STRUCTURE PHASES, DEVICE FOR DETERMINING METALLOGRAPHIC STRUCTURE IMAGING CONDITION, METALLOGRAPHIC STRUCTURE IMAGING CONDITION DEVICE METALLOGRAPHIC STRUCTURE, DEVICE FOR CLASSIFYING PHASES OF METALLOGRAPHIC STRUCTURE, METHOD FOR PREDICTING MATERIAL PROPERTIES OF METAL MATERIAL, AND DEVICE FOR PREDICTING MATERIAL PROPERTIES OF METAL MATERIAL
JPWO2021229727A1 (zh) * 2020-05-13 2021-11-18
JP7180796B2 (ja) 2020-05-13 2022-11-30 東芝三菱電機産業システム株式会社 物理モデル同定システム
JP7230880B2 (ja) 2020-05-18 2023-03-01 Ｊｆｅスチール株式会社 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
JP2021181095A (ja) * 2020-05-18 2021-11-25 Ｊｆｅスチール株式会社 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
TWI808407B (zh) * 2021-01-21 2023-07-11 日商東芝三菱電機產業系統股份有限公司 輥管理裝置
CN113780852A (zh) * 2021-09-16 2021-12-10 东北大学 一种板带轧制过程质量缺陷的诊断方法
CN113780852B (zh) * 2021-09-16 2024-03-05 东北大学 一种板带轧制过程质量缺陷的诊断方法

Also Published As

Publication number Publication date
CN106660090B (zh) 2019-03-19
KR101889668B1 (ko) 2018-08-17
KR20170039736A (ko) 2017-04-11
TWI554340B (zh) 2016-10-21
JPWO2016038705A1 (ja) 2017-06-15
JP6292309B2 (ja) 2018-03-14
CN106660090A (zh) 2017-05-10
TW201609283A (zh) 2016-03-16

Similar Documents

Publication Publication Date Title
JP6292309B2 (ja) 圧延シミュレーション装置
CN101361085B (zh) 预测公式生成装置及预测公式生成方法
JP5003483B2 (ja) 圧延ラインの材質予測および材質制御装置
CN108311544B (zh) 一种轧制力参数自学习方法及装置
WO2023130666A1 (zh) 一种基于数据驱动和机理模型融合的板带钢凸度预测方法
JP2008112288A (ja) 予測式作成装置、結果予測装置、品質設計装置、予測式作成方法及び製品の製造方法
CN102172641B (zh) 卷绕温度控制装置和控制方法
CN112916624B (zh) 一种ucm轧机板形执行机构调控功效系数获取方法
JP7135962B2 (ja) 鋼板の仕上出側温度制御方法、鋼板の仕上出側温度制御装置、及び鋼板の製造方法
JP2006309709A (ja) 結果予測装置、制御装置及び品質設計装置
JP4047875B2 (ja) 設計パラメータの最適値決定方法とこの方法を用いた圧延パススケジュールの決定方法
JP7020379B2 (ja) 金属材料の材質制御支援装置
JP4696775B2 (ja) 板幅制御方法および装置
CN111132773B (zh) 使用优化器的平整度控制
CN109032097B (zh) 一种冷轧带钢镀锌线过程控制方法
KR102045652B1 (ko) 인공지능 기반 열연 런아웃 테이블 열유속계수 결정 장치
JP6652095B2 (ja) 鋼板の圧延方法及び鋼板の製造方法
JP2012011448A (ja) 圧延材の冷却制御方法、及びこの冷却制御方法が適用された連続圧延機
KR100841888B1 (ko) 압연 라인의 재질 예측 및 재질 제어 장치
JP5007630B2 (ja) 製品品質の制御方法及び制御装置
CN110770357A (zh) 退火炉的运行方法
CN115218603A (zh) 冷却流量控制方法及装置
KR102045651B1 (ko) 인공지능 기반 열연 런아웃 테이블 열유속계수 추정 장치
JP2023527707A (ja) 複数の設備部分から成る生産設備、特に金属の半製品のような工業製品を生産するための生産設備を制御するためのシステム及び方法
JP2755893B2 (ja) 圧延制御方法および装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14901513

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2016547307

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20177006332

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14901513

Country of ref document: EP

Kind code of ref document: A1