Method for generating quality prediction model of metal material, method for predicting quality of metal material, method for manufacturing metal material, method for generating quality prediction model, data processing method, apparatus for generating quality prediction model of metal material, apparatus for predicting quality of metal material, and data processing apparatus

Abstract

The method for generating a quality prediction model of a metal material includes a first collection step, a second collection step, a third collection step, a storage step, and a model generation step. The storage step identifies a predetermined range for each process corresponding to a predetermined range of the final process based on at least one of the cutting positions in the longitudinal and width directions of the metal material collected in the third collection step and the dimensions in the longitudinal and width directions of the metal material that change in each process, and stores the manufacturing conditions of the metal material in the identified predetermined range for each process and the quality of the metal material in the final process in association with each other for each predetermined range of the final process.

Description

Technical Field

[0001] The present invention relates to a method for generating a quality prediction model for a metal material, a method for predicting the quality of a metal material, a method for manufacturing a metal material, a method for generating a quality prediction model, a data processing method, a device for generating a quality prediction model for a metal material, a device for predicting the quality of a metal material, and a data processing device.

Background Art

[0002] Patent Document 1 discloses a method for predicting the quality of a material by using a model obtained by learning data in which manufacturing condition data at the time of manufacturing the material and quality data in the final process are associated in consideration of the quality determination position in the longitudinal direction of the material.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is known that the quality of a material, particularly mechanical properties such as the tensile strength and yield point stress of a metal material, is greatly affected by the temperature of the metal material and its temporal change. This is because the state of the metal structure varies depending on the temperature of the metal material and has a close relationship with the mechanical properties of the metal material. Therefore, in order to accurately predict the quality of a metal material, manufacturing condition data including the temperature of the metal material at the position (part) of the metal material for which the quality is to be predicted and the quality data of the metal material need to be precisely associated.

[0005] However, in the prior art, although the manufacturing condition data finely collected in the longitudinal direction, which is the processing direction of the metal material, is utilized, the manufacturing condition data finely collected in the width direction, which is perpendicular to the longitudinal direction, has not been effectively utilized.

[0006] In the prior art, specifically, in each process of manufacturing a metal material, trimming of the end portion in the width direction of the metal material and division of the metal material with an arbitrarily determined width position as a boundary were not considered. Further, in the prior art, changes in the spread of the length in the width direction due to plastic deformation generated during rolling of the metal material and changes in the narrowing of the length in the width direction due to plastic deformation caused by the longitudinal tension applied to the metal material in each process were not considered. Therefore, in the prior art, there was a limit to improving the prediction accuracy of the quality of the metal material.

[0007] The present invention has been made in view of the above, and an object thereof is to provide a method for generating a quality prediction model for a metal material, a method for predicting the quality of a metal material, a method for manufacturing a metal material, a method for generating a quality prediction model, a data processing method, a device for generating a quality prediction model for a metal material, a device for predicting the quality of a metal material, and a data processing device that can accurately predict the quality of a material under arbitrary manufacturing conditions.

Means for Solving the Problems

[0008] In order to solve the above-mentioned problems and achieve the object, a method for generating a quality prediction model of a metal material according to the present invention includes: a first collection step of collecting the manufacturing conditions of the metal material in each process within a predetermined range in the longitudinal direction and the width direction of the metal material, and collecting for each predetermined range of each process; a second collection step of evaluating and collecting the quality of the metal material in the final process of each process for each predetermined range of the final process; a third collection step of collecting at least one of the cutting positions in the longitudinal direction and the width direction of the metal material in each process and the dimensions in the longitudinal direction and the width direction of the metal material that change in each process; a storage step of associating and storing the manufacturing conditions of the metal material in each process collected in the first collection step and the quality of the metal material in the final process collected in the second collection step for each predetermined range of the final process; and a model generation step of generating a quality prediction model for predicting the quality for each predetermined range of the final process from the manufacturing conditions for each predetermined range of the final process stored in the storage step. The storage step specifies the predetermined ranges of the respective processes corresponding to the predetermined range of the final process based on at least one of the cutting positions in the longitudinal direction and the width direction of the metal material and the dimensions in the longitudinal direction and the width direction of the metal material that change in each process collected in the third collection step, and associates and stores the manufacturing conditions of the metal material in the specified predetermined ranges of the respective processes and the quality of the metal material in the final process for each predetermined range of the final process.

[0009] Further, in the method for generating a quality prediction model of a metal material according to the present invention, in the above invention, among the predetermined ranges of each process, the predetermined range in the longitudinal direction of the metal material is determined based on the moving distance of the metal material according to the conveyance direction in each process, and among the predetermined ranges of each process, the predetermined range in the width direction of the metal material is determined based on a predetermined range division distance determined in each process.

[0010] In addition, in the method for generating a quality prediction model for a metal material according to the present invention, in the above invention, in the third collection step, as the cutting position in the width direction of the metal material in each process, rounding off the ends in the width direction of the metal material in each process and dividing the metal material with a predetermined width position as a boundary are included to collect the cutting position.

[0011] In addition, in the method for generating a quality prediction model for a metal material according to the present invention, in the above invention, in the third collection step, as the dimension in the width direction of the metal material in each process, the change in the spread of the length in the width direction due to plastic deformation generated by rolling the metal material in each process and the change in the narrowing of the length in the width direction due to plastic deformation caused by the longitudinal tension applied to the metal material in each process are included to collect the dimension.

[0012] In addition, in the method for generating a quality prediction model for a metal material according to the present invention, in the above invention, in the first collection step, as the manufacturing conditions of the metal material in each process, at least one or more of the temperature of the metal material, the plate thickness before and after rolling of the metal material, the tension applied to the metal material, and the elongation rate of the metal material are collected for each predetermined range of each process.

[0013] In addition, in the method for generating a quality prediction model for a metal material according to the present invention, in the above invention, in the model generation step, the quality prediction model is generated using statistical analysis methods and machine learning methods including linear regression, local regression, principal component regression, PLS regression, logistic regression, support vector machine, decision tree, regression tree, random forest, gradient boosting tree, and neural network.

[0014] Further, in the method for generating a quality prediction model for a metal material according to the present invention, in the above invention, the manufacturing conditions of the metal material in each of the steps collected in the first collection step and the quality of the metal material in the final step collected in the second collection step are re-stored in association with each other for each predetermined range; and a model regeneration step of regenerating a quality prediction model for predicting the quality for each predetermined range from the manufacturing conditions for each predetermined range re-stored in the re-storing step. Among the predetermined ranges, the predetermined range in the longitudinal direction of the metal material is the predetermined range in the longitudinal direction of the metal material in the process to which the process belongs, where the importance index for the quality output for each manufacturing condition serving as the input of the quality prediction model generated in the model generation step is the maximum. Among the predetermined ranges, the predetermined range in the width direction of the metal material is determined based on a predetermined range division distance determined in the final step.

[0015] In order to solve the above-described problems and achieve the object, a method for predicting the quality of a metal material according to the present invention includes a quality prediction step of predicting the quality of a metal material manufactured under arbitrary manufacturing conditions for each predetermined range in the final step, using the quality prediction model generated by the above-described method for generating a quality prediction model for a metal material.

[0016] In order to solve the above-described problems and achieve the object, a method for predicting the quality of a metal material according to the present invention includes a quality prediction step of predicting the quality of a metal material manufactured under arbitrary manufacturing conditions for each predetermined range, using the quality prediction model generated by the above-described method for generating a quality prediction model for a metal material.

[0017] In order to solve the above-described problems and achieve the object, a method for manufacturing a metal material according to the present invention includes an importance index calculation step of calculating an importance index indicating an influence on the prediction of the quality as an output for each manufacturing condition that is an input to the quality prediction model, using the quality prediction model generated by the above-described quality prediction model generation method for the metal material; a manufacturing condition estimation step of estimating the manufacturing condition with a high importance index as a manufacturing condition that is a factor affecting the quality of the metal material; a quality prediction step of predicting the quality as an output using the quality prediction model including as an input the manufacturing condition estimated to be a factor affecting the quality of the metal material; a manufacturing condition determination step of determining the manufacturing condition that is a factor affecting the quality of the metal material so that the predicted quality falls within a preset range; and a metal material manufacturing step of manufacturing the metal material based on the determined manufacturing condition.

[0018] In order to solve the above problems and achieve the object, a method for generating a quality prediction model according to the present invention includes: a first collection step of collecting the manufacturing conditions of the material in each process within a predetermined range in the longitudinal direction and the width direction of the material, and collecting for each predetermined range of each process; a second collection step of evaluating and collecting the quality of the material in the final process of each process for each predetermined range of the final process; a third collection step of collecting at least one of the cutting positions in the longitudinal direction and the width direction of the material in each process and the dimensions in the longitudinal direction and the width direction of the material that change in each process; a storage step of associating and storing the manufacturing conditions of the material in each process collected in the first collection step and the quality of the material in the final process collected in the second collection step for each predetermined range of the final process; and a model generation step of generating a quality prediction model for predicting the quality for each predetermined range of the final process from the manufacturing conditions for each predetermined range of the final process stored in the storage step. The storage step specifies the predetermined range of each process corresponding to the predetermined range of the final process based on at least one of the cutting positions in the longitudinal direction and the width direction of the material and the dimensions in the longitudinal direction and the width direction of the material that change in each process, which are collected in the third collection step, and associates and stores the manufacturing conditions of the material in the specified predetermined range of each process and the quality of the material in the final process for each predetermined range of the final process.

[0019] In order to solve the above-described problems and achieve the object, a data processing method according to the present invention includes: a first collection step of collecting manufacturing conditions of a metal material in each process within a predetermined range in the longitudinal direction and the width direction of the metal material, and collecting for each predetermined range of each process; a second collection step of evaluating and collecting the quality of the metal material in the final process of each process for each predetermined range of the final process; a third collection step of collecting at least one of a cutting position in the longitudinal direction and the width direction of the metal material in each process and dimensions in the longitudinal direction and the width direction of the metal material that change in each process; and a storage step of associating and storing the manufacturing conditions of the metal material in each process collected in the first collection step and the quality of the metal material in the final process collected in the second collection step for each predetermined range of the final process. The storage step specifies a predetermined range of each process corresponding to the predetermined range of the final process based on at least one of the cutting position in the longitudinal direction and the width direction of the metal material and the dimensions in the longitudinal direction and the width direction of the metal material that change in each process, which are collected in the third collection step, and associates and stores the manufacturing conditions of the metal material in the specified predetermined range of each process and the quality of the metal material in the final process for each predetermined range of the final process.

[0020] In order to solve the above-described problems and achieve the object, a device for generating a quality prediction model for a metal material according to the present invention includes: a first collection unit that collects manufacturing conditions of the metal material in each process within a predetermined range in the longitudinal direction and the width direction of the metal material, and collects them for each predetermined range of each process; a second collection unit that evaluates and collects the quality of the metal material in the final process of each process for each predetermined range of the final process; a third collection unit that collects at least one of a cutting position in the longitudinal direction and the width direction of the metal material in each process and dimensions in the longitudinal direction and the width direction of the metal material that change in each process; a storage unit that associates and stores the manufacturing conditions of the metal material in each process collected by the first collection unit and the quality of the metal material in the final process collected by the second collection unit for each predetermined range of the final process; and a model generation unit that generates a quality prediction model for predicting the quality for each predetermined range of the final process from the manufacturing conditions for each predetermined range of the final process stored in the storage unit. The storage unit specifies the predetermined range of each process corresponding to the predetermined range of the final process based on at least one of the cutting position in the longitudinal direction and the width direction of the metal material collected by the third collection unit and the dimensions in the longitudinal direction and the width direction of the metal material that change in each process, and associates and stores the manufacturing conditions of the metal material in the specified predetermined range of each process and the quality of the metal material in the final process for each predetermined range of the final process.

[0021] In addition, in the metal material quality prediction model generation device according to the present invention, in the above invention, the storage unit re-associates and re-stores the manufacturing conditions of the metal material in each of the above steps collected by the first collection unit and the quality of the metal material in the final step collected by the second collection unit for each predetermined range. The model generation unit regenerates a quality prediction model for predicting the quality for each predetermined range from the manufacturing conditions for each predetermined range that have been re-stored. Among the predetermined ranges, the predetermined range in the longitudinal direction of the metal material is the one in the process to which the manufacturing condition belongs where the importance index for the quality output for each manufacturing condition that serves as the input of the quality prediction model generated in the model generation unit is the maximum. The predetermined range in the longitudinal direction of the metal material is used as the predetermined range in the longitudinal direction of the metal material. Among the predetermined ranges, the predetermined range in the width direction of the metal material is determined based on a predetermined range division distance determined in the final step.

[0022] In order to solve the above-described problems and achieve the object, a metal material quality prediction device according to the present invention includes a quality prediction unit that predicts the quality of a metal material manufactured under arbitrary manufacturing conditions for each predetermined range in the final step using the quality prediction model generated by the above-described metal material quality prediction model generation device.

[0023] In order to solve the above-described problems and achieve the object, a metal material quality prediction device according to the present invention includes a quality prediction unit that predicts the quality of a metal material manufactured under arbitrary manufacturing conditions for each predetermined range using the quality prediction model generated by the above-described metal material quality prediction model generation device.

[0024] In order to solve the above-described problems and achieve the object, a data processing apparatus according to the present invention includes: a first collection unit that collects manufacturing conditions of a metal material in each process within a predetermined range in the longitudinal direction and the width direction of the metal material, and collects for each predetermined range of each process; a second collection unit that evaluates and collects the quality of the metal material in the final process of each process for each predetermined range of the final process; a third collection unit that collects at least one of a cutting position in the longitudinal direction and the width direction of the metal material in each process and dimensions in the longitudinal direction and the width direction of the metal material that change in each process; and a storage unit that associates and stores the manufacturing conditions of the metal material in each process collected by the first collection unit and the quality of the metal material in the final process collected by the second collection unit for each predetermined range of the final process. The storage unit specifies a predetermined range of each process corresponding to the predetermined range of the final process based on at least one of the cutting position in the longitudinal direction and the width direction of the metal material and the dimensions in the longitudinal direction and the width direction of the metal material that change in each process collected by the third collection unit, and associates and stores the manufacturing conditions of the metal material in the specified predetermined range of each process and the quality of the metal material in the final process for each predetermined range of the final process.

Effect of the Invention

[0025] According to the present invention, in addition to the longitudinal direction of the metal material, by dividing a predetermined range in the width direction, it is possible to create learning data in consideration of fluctuations in manufacturing conditions across the width direction of the metal material. As a result, even at the same position in the longitudinal direction, differences in manufacturing conditions in the width direction of the metal material can be appropriately reflected in the quality prediction model, so that a high-precision quality prediction model can be generated.

Brief Description of the Drawings

[0026]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the Invention

[0027] A method for generating a quality prediction model for a metal material, a quality prediction method for a metal material, a quality prediction model generation method, a data processing method, a quality prediction model generation apparatus for a metal material, a quality prediction apparatus for a metal material, and a data processing apparatus according to embodiments of the present invention will be described with reference to the drawings.

[0028] (Device Configuration) The configurations of the metal material quality prediction model generation device, quality prediction device, and data processing device according to this embodiment will be described with reference to FIG. 1. The quality prediction model generation device is a device for generating a quality prediction model for predicting the quality of a metal material manufactured through one or more processes. The quality prediction device is a device for predicting the quality of a metal material manufactured through one or more processes using the quality prediction model. The data processing device is a device for creating learning data when generating the quality prediction model. Note that the metal materials in this embodiment include, for example, steel products, such as semi-finished products like slabs and products like steel plates manufactured by rolling the slabs.

[0029] In the following, the quality prediction model generation device, quality prediction device, and data processing device for metal materials will be described. However, in addition to metal materials, for example, in a continuous manufacturing line, it is naturally applicable to materials manufactured through multiple processes and other manufactured products.

[0030] The quality prediction model generation device, quality prediction device, and data processing device can be realized by, for example, an information processing device 1 as shown in FIG. 1. Specifically, the information processing device 1 is composed of a personal computer, a workstation, or the like. The information processing device 1 mainly includes components such as a processor composed of, for example, a CPU (Central Processing Unit) and a memory (main storage unit) composed of a RAM (Random Access Memory), a ROM (Read Only Memory), etc.

[0031] The information processing apparatus 1 includes a manufacturing condition data collection unit 11, a quality data collection unit 12, a cutting result data collection unit 13, a dimension result data collection unit 14, an integrated process data editing unit 15, an integrated process database 16, a model generation unit 17, a quality prediction unit 18, and an influencing factor estimation unit 19. Note that the quality prediction model generation apparatus for metal materials according to the embodiment is configured by elements excluding the quality prediction unit 18 and the influencing factor estimation unit 19 in the information processing apparatus 1. Further, the quality prediction apparatus for metal materials according to the embodiment is configured by elements excluding the influencing factor estimation unit 19 in the information processing apparatus 1. Further, the data processing apparatus according to the embodiment is configured by elements excluding the model generation unit 17, the quality prediction unit 18, and the influencing factor estimation unit 19 in the information processing apparatus 1.

[0032] A sensor (not shown) is connected to the manufacturing condition data collection unit 11. The manufacturing condition data collection unit 11 collects data on the manufacturing conditions of each process (hereinafter referred to as "manufacturing condition data") by this sensor and outputs it to the integrated process data editing unit 15. Examples of the "manufacturing conditions of metal materials" include, for example, the components of the metal material in each process, the temperature of the metal material, the pressure applied to the metal material, the tension applied to the metal material, the plate thickness before and after rolling of the metal material, the passing speed of the metal material, and the like.

[0033] The manufacturing condition data of each process collected by the manufacturing condition data collection unit 11 includes not only the measured values of the manufacturing conditions measured by the sensor but also the set values of the preset manufacturing conditions. That is, since there may be cases where no sensor is installed in some processes, in such cases, the set value is collected as the manufacturing condition data instead of the actual value.

[0034] The manufacturing condition data collection unit 11 collects the manufacturing condition data of the metal material in each process within a predetermined range in the longitudinal and width directions of the metal material, and collects it for each predetermined range of each process. The "predetermined range of each process" indicates, for example, a certain range (position) in the longitudinal and width directions of the metal material in each process when the metal material is a slab or a steel plate. Also, the predetermined range of each process may be different for each process or the same.

[0035] Among the predetermined ranges of each process, the predetermined range in the longitudinal direction of the metal material is determined based on, for example, the moving distance of the metal material according to the conveyance direction in each process. Also, among the predetermined ranges of each process, the predetermined range in the width direction of the metal material is determined based on, for example, the range division distance predetermined in each process. The predetermined range in the width direction of the metal material is determined as, for example, the highest (finest data granularity) resolution among the resolutions of the respective sensors that comprehensively collect the manufacturing condition data in the width direction of the metal material, as the range division distance, that is, the predetermined range in the width direction. For example, if 10 mm is the minimum among the resolutions of the respective sensors, this 10 mm is set as the predetermined range in the width direction.

[0036] Here, in the configuration shown in FIG. 1, only one manufacturing condition data collection unit 11 is provided, and it is assumed that the manufacturing condition data of each process is collected by this one manufacturing condition data collection unit 11. Note that, different from the configuration shown in FIG. 1, for example, a plurality of manufacturing condition data collection units 11 may be provided according to the number of each process, and the manufacturing condition data of each process may be collected by separate manufacturing condition data collection units 11 respectively.

[0037] A sensor (not shown) or a data input terminal (not shown) is connected to the quality data collection unit 12. The quality data collection unit 12 collects data on the quality of the metal material (hereinafter referred to as "quality data") manufactured through each process by this sensor or data input terminal, and outputs it to the integrated process data editing unit 15. Examples of the above-mentioned "quality of the metal material" include, for example, the tensile strength of the metal material in the final process, the defect mixing rate (the number of defects appearing per unit area) of the metal material in the final process, and the like.

[0038] The quality data of the metal material collected by the quality data collection unit 12 includes not only the actually measured values of the quality measured by the sensor, but also the pass / fail and the like evaluated based on certain criteria or visual inspection by an inspector based on the actually measured values, and also includes the determination values of the quality input from the data input terminal.

[0039] The quality data collection unit 12 evaluates and collects the quality data of the metal material in the final process of each process for each predetermined range of the final process. The "predetermined range of the final process" refers to, for example, in the case of a metal material being a slab or a steel plate, a certain range (position) in the longitudinal direction and the width direction of the metal material in the final process.

[0040] Among the predetermined ranges of the final process, the predetermined range in the longitudinal direction of the metal material is determined based on, for example, the moving distance of the metal material according to the conveying direction in the final process. Also, among the predetermined ranges of the final process, the predetermined range in the width direction of the metal material is determined based on, for example, a predetermined range division distance in the final process. The predetermined range in the width direction of the metal material is determined as, for example, the highest (finest data granularity) resolution among the resolutions of each sensor that comprehensively collects the manufacturing condition data in the width direction of the metal material as the range division distance, that is, the predetermined range in the width direction. For example, if 10 mm is the minimum among the resolutions of each sensor, this 10 mm is set as the predetermined range in the width direction.

[0041] The cutting performance data collection unit 13 collects the cutting positions in the longitudinal direction and the width direction of the metal material in each process. A cutting machine (not shown) for cutting the tip end, the tail end, and an arbitrary position in the longitudinal direction determined in advance of the metal material in each process is connected to the cutting performance data collection unit 13. Also, a cutting machine (not shown) for cutting the end in the width direction of the metal material and an arbitrary cutting position in the width direction determined in advance is connected to the cutting performance data collection unit 13.

[0042] The cutting performance data collection unit 13 collects, for each metal material, the cutting position and the number of cuts (hereinafter referred to as "cutting position, etc.") in the width direction of the metal material in each process through these cutting machines. The "cutting position of the metal material" refers to the distance from the tip of the metal material at the time of longitudinal cutting and the distance from the end of the metal material at the time of widthwise cutting. Also, the "cutting position of the metal material" includes, for example, the rounding off of the end in the width direction of the metal material in each process and the division of the metal material with a predetermined width position as the boundary.

[0043] The cutting result data collection unit 13 outputs the result data regarding the cutting position etc. of the metal material to the integrated process data editing unit. Note that, similar to the manufacturing condition data collection unit 11 described above, the cutting result data collection unit 13 may be provided only one, or may be provided in plurality according to the number of each process.

[0044] The dimension result data collection unit 14 collects the dimensions in the longitudinal direction and width direction of the metal material that change in each process. Connected to the dimension result data collection unit 14 are a sensor (not shown) for collecting the dimension in the longitudinal direction of the shape that changes due to the processing of the metal material in each process, and a sensor (not shown) for collecting the dimension in the width direction of the shape that changes due to the processing of the metal material.

[0045] The dimension result data collection unit 14 collects, for each metal material, the dimension in the width direction of the metal material in each process through these sensors. The "dimension in the width direction of the metal material" includes, for example, the change in the spread of the length in the width direction due to plastic deformation caused by rolling of the metal material in each process, and the change in the narrowing of the length in the width direction due to plastic deformation caused by the longitudinal tension applied to the metal material in each process.

[0046] The dimension result data collection unit 14 outputs the result data regarding the dimension of the metal material to the integrated process data editing unit 15. Note that, similar to the manufacturing condition data collection unit 11 described above, the dimension result data collection unit 14 may be provided only one, or may be provided in plurality according to the number of each process.

[0047] The integrated process data editing unit 15 edits the result data input from the manufacturing condition data collection unit 11, the quality data collection unit 12, the cutting result data collection unit 13, and the dimension result data collection unit 14. Specifically, the integrated process data editing unit 15 associates the manufacturing condition data of each process collected by the manufacturing condition data collection unit 11 with the quality data of the metal material collected by the quality data collection unit 12 for each predetermined range of the final process, and stores them in the integrated process database 16.

[0048] First, based on at least one or more of the cutting positions in the longitudinal and width directions of the metal material, and the dimensions in the longitudinal and width directions of the metal material that change in each process, the integrated process data editing unit 15 identifies the predetermined ranges of each process corresponding to the predetermined range of the final process. Note that the "cutting positions in the longitudinal and width directions of the metal material, etc." are those collected by the cutting result data collection unit 13. Also, the "dimensions in the longitudinal and width directions of the metal material" are those collected by the dimension result data collection unit 14. Further, the "predetermined ranges of each process corresponding to the predetermined range of the final process" indicates the predetermined ranges of each process corresponding to the same position as the predetermined range of the final process.

[0049] Here, in the manufacture of the metal material, for example, as shown in FIG. 6 described later, the dimensions in the longitudinal and width directions of the metal material change through each process. Therefore, the integrated process data editing unit 15 traces and identifies the predetermined ranges of each process corresponding to the predetermined range of the final process while going back to the processes before the final process. Then, the integrated process data editing unit 15 associates the manufacturing condition data of the metal material in the identified predetermined ranges of each process with the quality data of the metal material in the final process for each predetermined range of the final process and stores them in the integrated process database 16. At that time, the integrated process data editing unit 15 stores the manufacturing condition data and quality data of the metal material in the integrated process database 16 in a form that can distinguish the cutting position data and dimension data of the metal material in each process.

[0050] The model generation unit 17 generates a quality prediction model for predicting the quality of the metal material for each predetermined range of the final process from the manufacturing condition data and quality data for each predetermined range of the final process stored in the integrated process database 16. When generating the quality prediction model, the model generation unit 17 uses, for example, a gradient boosting tree as the statistical analysis method and machine learning method. Note that as the statistical analysis method and machine learning method, in addition to the above, various methods such as linear regression, local regression, principal component regression, PLS regression, logistic regression, support vector machine, decision tree, regression tree, random forest, and neural network can be used.

[0051] The quality prediction unit 18 uses the quality prediction model generated by the model generation unit 17 to predict the quality of the metal material manufactured under any manufacturing conditions for each predetermined range in the final process. For example, when the metal material to be predicted is a slab, the conventional method predicted the quality for each predetermined range in the longitudinal direction of the slab, but in this embodiment, the quality for each predetermined range in the longitudinal and width directions of the slab can be predicted.

[0052] The influence factor estimation unit 19 uses the quality prediction model generated by the model generation unit 17 to calculate the variable importance (importance index) of the quality prediction model for each manufacturing condition, and estimates the manufacturing conditions with high variable importance as the manufacturing conditions that are factors affecting the quality of the metal material. Further, the influence factor estimation unit 19 may predict the output quality using the quality prediction model generated by the model generation unit 17, including the manufacturing conditions estimated as factors affecting the quality of the metal material as an input. Then, the influence factor estimation unit 19 may determine the management range of the manufacturing conditions estimated as factors affecting the quality of the metal material so that the predicted quality falls within a preset range. The management range of the manufacturing conditions can be obtained, for example, by a mathematical programming method such as the branch and bound method.

[0053] The information processing device 1 may further include an output unit that outputs, as an output signal, the management range of the manufacturing conditions estimated as factors affecting the quality of the metal material determined by the influence factor estimation unit 19. When the output destination of the output signal is the control device of the facility, the output signal may be a control signal for setting the manufacturing conditions for the facility. Also, when the output destination of the output signal is the operator's operation terminal, the output signal may be operator guidance information to be displayed as guidance on the screen. Then, the manufacturing conditions are adjusted and the metal material is manufactured so that the manufacturing conditions estimated as factors affecting the quality of the metal material are within the determined management range.

[0054] <First Embodiment> (Quality Prediction Method) The quality prediction method, quality prediction model generation method, and data processing method according to the first embodiment will be described with reference to FIGS. 2 to 7. The quality prediction method according to this embodiment performs the processes of steps S1 to S6 shown in FIG. 2. Further, the quality prediction model generation method according to this embodiment performs the processes of steps S1 to S5 shown in FIG. 2 excluding step S6. Further, the data processing method according to this embodiment performs the processes of steps S1 to S4 shown in FIG. 2 excluding steps S5 and S6.

[0055] Also, in FIG. 2, step S1 corresponds to the first collection step, step S2 corresponds to the second collection step, step S3 corresponds to the third collection step and the fourth collection step, and step S4 corresponds to the storage step. Also, in FIG. 2, step S5 corresponds to the model generation step, and step S6 corresponds to the prediction step.

[0056] First, the manufacturing condition data collection unit 11 collects data on the manufacturing conditions of each process (step S1). In step S1, the manufacturing condition data collection unit 11 collects the manufacturing condition data for each metal material and for each process. The manufacturing condition data collected by the manufacturing condition data collection unit 11 is, for example, as shown in FIG. 3, data in which actual values or set values of a plurality of manufacturing conditions are arranged for each position from the tip to the tail end in the longitudinal direction of the metal material and for each position from one end to the other end in the width direction in each process.

[0057] The manufacturing condition data shown in FIG. 3 is the longitudinal position l in each process 1 , l 2 , …, and the widthwise position w in each process 1 , w 2 , …, and a plurality of manufacturing conditions x1 measured by sensors at the positions 11 , x1 12 , …, x2 21 , x2 22 , …, and has items consisting of.

[0058] Subsequently, the quality data collection unit 12 collects quality data of the metal material manufactured through each process (step S2). The quality data collected by the quality data collection unit 12 is data in which the measured values or judgment values of quality are arranged for each position from the tip to the tail end in the longitudinal direction of the metal material manufactured through each process and for each position from one end to the other end in the width direction, as shown in FIG. 4 for example.

[0059] The performance data shown in FIG. 4 has items consisting of the longitudinal position l 1 , l 2 , …, the width position w 1 , w 2 , …, and a plurality of qualities y 11 , y 12 , … at the position.

[0060] Subsequently, the cutting performance data collection unit 13 and the dimensional performance data collection unit 14 collect performance data regarding the cutting position and the like and the dimensions of the metal material in each process (step S3). Subsequently, the integrated process data editing unit 15 aligns and combines the performance data of all processes in units of the longitudinal position and the width position of the metal material (step S4).

[0061] Based on the performance data regarding the longitudinal position, width position, cutting position, etc. and the dimensions of the metal material, the integrated process data editing unit 15 aligns and combines the performance data of the manufacturing conditions and quality of the metal material in all processes for each predetermined range in the final process. Note that "for each predetermined range in the final process" indicates the units of the longitudinal and width positions of the metal material on the output side of the final process.

[0062] In this way, the integrated process data editing unit 15 associates the manufacturing condition data of each process with the quality data of the metal material manufactured under this manufacturing condition for each predetermined range in the longitudinal and width directions of the metal material, and stores it in the integrated process database 16. Hereinafter, an example of the processing by the integrated process data editing unit 15 will be described with reference to FIGS. 5 to 7.

[0063] For example, as shown in FIG. 5, consider the case of manufacturing a metal material (material) through Process 1, Process 2, and Process 3. Process 1, Process 2, and Process 3 are, for example, rolling processes. Each time rolling is performed, the length in the longitudinal direction increases due to plastic deformation of the material, and the length in the width direction also expands. Further, when tension is applied in the longitudinal direction of the material, the length in the width direction decreases due to the plastic deformation caused by the tension. Also, as shown in FIG. 5, when moving from Process 1 to Process 2, Material A is divided into Material A1 and Material A2 in the longitudinal direction, and when moving from Process 2 to Process 3, Material A1 is divided into Material A11 and Material A12 in the width direction. Note that Process 3 is, for example, the final process.

[0064] FIG. 6 shows an image of the material in each process and is a view focusing on part B of FIG. 5. For example, for Material A in Process 1, the manufacturing condition data collection unit 11 collects performance data of M1 items, such as X1 1 ~X1 M1 at intervals of 50 mm from the tip to the tail in the longitudinal direction and at intervals of 20 mm from one end to the other end in the width direction.

[0065] Also, for Material A, the cutting performance data collection unit 13 collects performance data indicating that the tip portion in the longitudinal direction from 0 mm (tip) to 250 mm is discarded and Material A1 is taken in the longitudinal direction from 250 mm to 3300 mm. Also, for Material A, the cutting performance data collection unit 13 collects performance data indicating that Material A2 is taken in the longitudinal direction from 3300 mm to 4950 mm and the tail portion in the longitudinal direction from 4950 mm to 5300 mm (tail) is discarded.

[0066] Also, for Material A, the dimensional performance data collection unit 14 collects performance data of the longitudinal dimension of 5300 mm and the width dimension of 920 mm of Material A before cutting, the longitudinal dimension of 3050 mm and the width dimension of 920 mm of Material A1 after cutting of Material A, and the longitudinal dimension of 1650 mm and the width dimension of 920 mm of Material A2 after cutting of Material A.

[0067] Subsequently, for the material A1 in Process 2, for every 100 mm from the tip to the tail end in the longitudinal direction and for every 10 mm from one end to the other end in the width direction, for example, X2 1 ~X2 M2 The performance data of M2 items are collected.

[0068] Also, for the material A1, the cutting performance data collection unit 13 collects the performance data where one end portion in the width direction from 0 mm (one end) to 20 mm is discarded and the material A11 is taken in the width direction from 20 mm to 500 mm. Also, for the material A1, the cutting performance data collection unit 13 collects the performance data where the material A12 is taken in the width direction from 500 mm to 940 mm and the other end portion in the width direction from 940 mm to 960 mm (the other end) is discarded.

[0069] Also, for the material A1, the dimensional performance data collection unit 14 collects the performance data of the longitudinal dimension of 68000 mm and the width dimension of 960 mm before cutting, which are changed by the rolling of the material A1. Also, for the material A1, the dimensional performance data collection unit 14 collects the performance data of the longitudinal dimension of 68000 mm and the width dimension of 480 mm of the material A11 after cutting the material A1. Also, for the material A1, the dimensional performance data collection unit 14 collects the performance data of the longitudinal dimension of 68000 mm and the width dimension of 440 mm of the material A12 after cutting the material A1.

[0070] Subsequently, for the material A11 in Process 3, for every 500 mm from the tip to the tail end in the longitudinal direction and for every 50 mm from one end to the other end in the width direction, for example, X3 1 ~X3 M3 The performance data of M3 items are collected.

[0071] Also, for the material A11, the dimensional performance data collection unit 14 collects the performance data of the longitudinal dimension of 136000 mm and the width dimension of 500 mm before cutting, which are changed by the rolling of the material A11.

[0072] The integrated process data editing unit 15 combines the performance data of a plurality of manufacturing conditions of all processes that are finely collected in the longitudinal and width directions by a sensor (not shown), while taking into account the actual cutting positions and dimensions of the metal material in each process, for each predetermined range in the final process. That is, the integrated process data editing unit 15 combines the performance data of a plurality of manufacturing conditions of the process in units of the longitudinal position and width position of the metal material in the final process.

[0073] Thereby, as shown by the broken line in FIG. 6, the lengths in the longitudinal direction and width direction of the materials in processes 1 and 2 are scaled according to the lengths in the longitudinal direction and width direction of the material in process 3, which is the final process. Then, the integrated process data editing unit 15 identifies the positions where each metal material is taken while taking into account the cutting positions and dimensions of the metal material in each process. Thereby, the integrated process data editing unit 15 identifies the predetermined ranges of each process corresponding to the predetermined range of the final process in the metal material. Subsequently, the integrated process data editing unit 15 associates the performance data of a plurality of manufacturing conditions and quality of all processes for each predetermined range of the final process of the metal material and stores them in the integrated process database 16.

[0074] For example, in FIG. 6, the process of identifying the galvanized portion where material A11 is taken in process 3, which is the final process, retroactively to material A1 in process 2 and material A in process 1 is repeatedly performed for all metal materials. Thereby, as shown in FIG. 7, the integrated process data editing unit 15 creates performance data in which the performance data of a plurality of manufacturing conditions and quality of the metal material in all processes are aligned and combined in units of the longitudinal position and width position of the metal material. Hereinafter, the description will continue with reference back to FIG. 2.

[0075] The model generation unit 17 generates a quality prediction model for predicting the quality of each predetermined range of the final process of the metal material from the manufacturing condition data and quality data for each predetermined range of the final process (step S5). Subsequently, the quality prediction unit 18 uses the quality prediction model generated by the model generation unit 17 to predict the quality of the metal material manufactured under arbitrary manufacturing conditions for each predetermined range of the final process (step S6).

[0076] In this embodiment, quality prediction is performed in step S6 after generating the quality prediction model in step S5. However, it is not essential to perform all of steps S1 to S5 every time step S6 is executed. For example, steps S1 to S5 may be performed in advance to generate a quality prediction model, and thereafter, every time step S6 is executed using the generated quality prediction model, only steps S1, S3, S4, and S6 may be performed.

[0077] According to the method for generating a quality prediction model for a metallic material, the method for predicting the quality of a metallic material, the method for generating a quality prediction model, the data processing method, the apparatus for generating a quality prediction model for a metallic material, the apparatus for predicting the quality of a metallic material, and the data processing apparatus according to the embodiments described above, in addition to the longitudinal direction of the metallic material, by dividing a predetermined range in the width direction, learning data considering variations in manufacturing conditions across the width direction of the metallic material can be created. Thereby, even at the same position in the longitudinal direction, differences in manufacturing conditions in the width direction of the metallic material can be appropriately reflected in the quality prediction model, and thus a high-precision quality prediction model can be generated.

[0078] Also, according to the method for generating a quality prediction model for a metallic material, the method for predicting the quality of a metallic material, the method for generating a quality prediction model, the data processing method, the apparatus for generating a quality prediction model for a metallic material, the apparatus for predicting the quality of a metallic material, and the data processing apparatus according to the embodiments, by generating a quality prediction model in which the manufacturing conditions of each process are associated with the quality of the metallic material manufactured under these manufacturing conditions for each predetermined range in the final process, the quality of the metallic material for any manufacturing conditions can be predicted with higher precision than before.

[0079] That is, in the method for generating a quality prediction model for a metal material, the method for predicting the quality of a metal material, the method for generating a quality prediction model, the data processing method, the apparatus for generating a quality prediction model for a metal material, the apparatus for predicting the quality of a metal material, and the data processing apparatus according to the embodiment, the performance data of the plurality of manufacturing conditions and quality of all processes are aligned and combined in the longitudinal position unit and the width position unit of the metal material on the outlet side of the final process, taking into account the cutting position and the like and dimensions of the metal material in each process. Therefore, in order to effectively utilize the performance data of the plurality of manufacturing conditions of all processes finely collected in the longitudinal and width directions of the metal material by the sensor to predict the quality, the quality can be predicted with higher accuracy than in the past.

[0080] <Second Embodiment> A method for generating a quality prediction model for a metal material, a method for predicting the quality of a metal material, and a method for manufacturing a metal material according to a second embodiment of the present invention will be described with reference to the drawings.

[0081] The first embodiment was premised on aligning the manufacturing condition data in each process during the manufacture of the metal material and the quality data in the final process in the unit of the length of the metal material of the quality data and the manufacturing condition data in the final process for evaluating the quality. Note that the "unit of the length of the metal material of the quality data and the manufacturing condition data in the final process" indicates a predetermined range in the longitudinal direction of the metal material within a predetermined range of the final process. On the other hand, in the second embodiment, based on the importance index (variable importance) indicating the influence on the prediction of the quality of the final process, the coarseness (unit of the length of the metal material) of the data for aligning and associating the manufacturing condition data and the quality data of each process including the final process is determined.

[0082] When each process is a rolling process, the length of the metal material mainly in the longitudinal direction increases as it passes through each process. When aligned in the length unit of the metal material in the final process, the length of the metal material in the corresponding intermediate process becomes shorter as the process is traced back. If it becomes shorter than the measurement period of the actual manufacturing condition data in the intermediate process, even if data interpolation (for example, linear interpolation) is performed, there is a possibility that the fluctuations in the actual manufacturing conditions are not accurately reflected.

[0083] Especially when the manufacturing conditions change rapidly or vary non-linearly, linear interpolation may not be able to capture such variations, and there is a risk that the prediction accuracy of the quality prediction model will decrease. Also, when the data points of each process increase due to interpolation, the quality prediction model may overfit, leading to a decrease in generalization performance.

[0084] Therefore, in the second embodiment, the manufacturing condition data in the intermediate process that can be the main cause of quality defects is aligned with the roughness in the longitudinal direction of the metal material, and the manufacturing conditions of other processes and the quality of the final process are associated. As a result, it becomes possible to reflect the maximum amount of information regarding the target quality in the generated quality prediction model. Consequently, the quality for any manufacturing conditions of the material can be predicted with higher accuracy.

[0085] (Quality Prediction Method) The quality prediction method and the quality prediction model generation method according to this embodiment will be described with reference to FIG. 8. The quality prediction model generation method according to this embodiment performs the processes of steps S11 to S18 shown in FIG. 8. Also, the quality prediction method according to this embodiment performs the processes of steps S11 to S19 shown in FIG. 8. Further, in FIG. 8, since steps S11 to S15 perform the same processes as steps S1 to S5 in FIG. 2, the description thereof is omitted, and the following will describe steps S16 to S19.

[0086] First, the influence factor estimation unit 19 uses the quality prediction model generated by the model generation unit 17 to calculate, for each manufacturing condition, an importance index (variable importance) indicating the influence of the manufacturing condition that is an input to each quality prediction model on the prediction of the output quality. Then, the influence factor estimation unit 19 estimates the manufacturing condition with the maximum importance index among the calculated manufacturing conditions (step S16).

[0087] The influence factor estimation unit 19 calculates an index corresponding to the influence degree of each factor in the entire quality prediction model as an importance index. As a method for calculating the importance index, for example, an algorithm for calculating an importance index specific to the algorithm that created the quality prediction model, such as the importance based on Gini impurity in decision tree algorithms including random forest, may be used. Alternatively, as a method for calculating the importance index, a known method for generally calculating the importance index regardless of the model creation algorithm, such as "Permutation Importance", may be used.

[0088] Subsequently, the integrated process data editing unit 15 associates the manufacturing condition data of each process collected by the manufacturing condition data collection unit 11 and the quality data of the metal material collected by the quality data collection unit 12 for each predetermined range based on the importance index of the manufacturing conditions calculated by the influence factor estimation unit 19, and re-saves them in the integrated process database 16 (step S17).

[0089] Specifically, the integrated process data editing unit 15 determines the predetermined range in the longitudinal direction of the metal material among the predetermined ranges for aligning and combining the performance data of all processes as follows. That is, the predetermined range in the longitudinal direction of the metal material is the predetermined range in the longitudinal direction of the metal material in the process to which the manufacturing condition with the maximum importance index (variable importance) for the quality output for each manufacturing condition that is an input to the quality prediction model generated in step S15 belongs.

[0090] Also, the integrated process data editing unit 15 determines the predetermined range in the width direction of the metal material among the predetermined ranges for aligning and combining the performance data of all processes based on the predetermined range division distance determined in advance in the final process. Then, the integrated process data editing unit 15 aligns and recombines the performance data of all processes in units of the position in the longitudinal direction and the position in the width direction of the metal material.

[0091] Subsequently, the model generation unit 17 regenerates a quality prediction model that predicts the quality for each predetermined range based on the importance index of manufacturing conditions for the quality of the metal material, from the manufacturing condition data and quality data for each predetermined range based on the importance index of the metal material that have been re-saved (step S18). Subsequently, the quality prediction unit 18 uses the quality prediction model generated by the model generation unit 17 in step S18 to predict the quality of the metal material manufactured under arbitrary manufacturing conditions for each predetermined range based on the importance index of manufacturing conditions for the quality of the metal material (step S19).

[0092] According to the method for generating a quality prediction model for a metal material and the method for predicting the quality of a metal material according to the second embodiment described above, by aligning the manufacturing condition data in the intermediate process, which can be a main cause of quality defects, with the roughness in the longitudinal direction of the metal material, and associating the manufacturing conditions of each other process and the quality of the final process, it becomes possible to reflect the maximum amount of information regarding the target quality in the generated quality prediction model. Therefore, the quality for arbitrary manufacturing conditions of the material can be predicted with higher accuracy.

[0093] (Method for manufacturing a metal material) The method for manufacturing a metal material according to the present embodiment performs an importance index calculation step, a manufacturing condition estimation step, a quality prediction step, a manufacturing condition determination step, and a metal material manufacturing step.

[0094] In the importance index calculation step, the influence factor estimation unit 19 calculates an importance index (variable importance) indicating the influence on the prediction of the output quality for each manufacturing condition that is an input to the quality prediction model, using the quality prediction model generated by the model generation unit 17.

[0095] In the manufacturing condition estimation step, the influence factor estimation unit 19 estimates the manufacturing conditions with high importance indexes as the manufacturing conditions that are factors affecting the quality of the metal material.

[0096] In the quality prediction step, the influence factor estimation unit 19 predicts the quality as the output using the quality prediction model generated by the model generation unit 17, which includes, as an input, the manufacturing conditions that are factors affecting the quality of the estimated metal material.

[0097] In the manufacturing condition determination step, the influence factor estimation unit 19 determines the manufacturing conditions that are factors affecting the quality of the metal material so that the predicted quality falls within a preset range. That is, the influence factor estimation unit 19 determines the control range of the manufacturing conditions estimated to be factors affecting the quality of the metal material so that the predicted quality falls within a preset range. The control range of the manufacturing conditions can be obtained, for example, by a mathematical programming method such as the branch and bound method.

[0098] The influence factor estimation unit 19 may output, as an output signal, the control range of the manufacturing conditions estimated to be factors affecting the quality of the metal material via the output unit of the information processing device 1. When the output destination of the output signal is the control device of the facility, the output signal may be a control signal for setting the manufacturing conditions for the facility. Further, when the output destination of the output signal is the operator's operation terminal, the output signal may be operator guidance information for displaying guidance on the screen.

[0099] In the metal material manufacturing step, the metal material is manufactured based on the manufacturing conditions adjusted so that the manufacturing conditions estimated to be factors affecting the quality of the metal material are within the determined control range.

[0100] As described above, the method for generating a quality prediction model for a metal material, the method for predicting the quality of a metal material, the method for manufacturing a metal material, the method for generating a quality prediction model, the data processing method, the device for generating a quality prediction model for a metal material, the device for predicting the quality of a metal material, and the data processing device according to the present invention have been specifically described by the embodiments and examples for carrying out the invention. However, the gist of the present invention is not limited to these descriptions and should be broadly interpreted based on the descriptions in the claims. Needless to say, various changes and modifications based on these descriptions are also included in the gist of the present invention.

Description of Reference Numerals

[0101] 1 Information processing apparatus 11 Manufacturing condition data collection unit 12 Quality data collection unit 13 Cutting result data collection unit 14 Dimension result data collection unit 15 Integrated process data editing unit 16 Integrated process database 17 Model generation unit 18 Quality prediction unit 19 Influence factor estimation unit

Claims

1. A first collection step of collecting the manufacturing conditions of the metal material in each process within a predetermined range in the longitudinal direction and the width direction of the metal material, and collecting for each predetermined range of each process; A second collection step of evaluating and collecting the quality of the metal material in the final process of each process for each predetermined range of the final process; A third collection step of collecting at least one of the cutting positions in the longitudinal direction and the width direction of the metal material in each process and the dimensions in the longitudinal direction and the width direction of the metal material that change in each process; A storage step of associating and storing the manufacturing conditions of the metal material in each process collected in the first collection step and the quality of the metal material in the final process collected in the second collection step for each predetermined range of the final process; A model generation step of generating a quality prediction model for predicting the quality for each predetermined range of the final process from the manufacturing conditions for each predetermined range of the final process stored in the storage step; comprising The storage step is Based on at least one of the cutting positions in the longitudinal direction and the width direction of the metal material collected in the third collection step and the dimensions in the longitudinal direction and the width direction of the metal material that change in each process, identify the predetermined ranges of each process corresponding to the predetermined range of the final process, Associate and store the manufacturing conditions of the metal material in the identified predetermined ranges of each process and the quality of the metal material in the final process for each predetermined range of the final process. A method for generating a quality prediction model of a metal material.

2. Among the predetermined ranges of each process, the predetermined range in the longitudinal direction of the metal material is determined based on the moving distance of the metal material according to the conveying direction in each process, Among the predetermined ranges of each process, the predetermined range in the width direction of the metal material is determined based on a predetermined range division distance in each process. The method for generating a quality prediction model of a metal material according to Claim 1.

3. The third collection step collects cutting positions including rounding off the ends in the width direction of the metal material in each process and dividing the metal material with a predetermined width position as a boundary as the cutting positions in the width direction of the metal material in each process. The method for generating a quality prediction model of a metal material according to Claim 1 or Claim 2.

4. The third collection step collects dimensions including, as the dimensions in the width direction of the metal material in each of the steps, a change in the length in the width direction due to plastic deformation caused by rolling of the metal material in each of the steps and a change in the narrowing of the length in the width direction due to plastic deformation caused by the longitudinal tension applied to the metal material in each of the steps, for the method for generating a quality prediction model of a metal material according to claim 1 or claim 2.

5. The first collection step collects manufacturing conditions including at least one or more of the temperature of the metal material, the plate thickness before and after rolling of the metal material, the tension applied to the metal material, and the elongation rate of the metal material, as the manufacturing conditions of the metal material in each of the steps, for each predetermined range of each of the steps, for the method for generating a quality prediction model of a metal material according to claim 1 or claim 2.

6. The model generation step generates the quality prediction model using statistical analysis methods and machine learning methods including linear regression, local regression, principal component regression, PLS regression, logistic regression, support vector machine, decision tree, regression tree, random forest, gradient boosting tree, and neural network, for the method for generating a quality prediction model of a metal material according to claim 1 or claim 2.

7. A re-saving step of re-saving by associating, for each predetermined range, the manufacturing conditions of the metal material in each of the steps collected in the first collection step and the quality of the metal material in the final step collected in the second collection step; A model regeneration step of regenerating a quality prediction model for predicting the quality for each predetermined range from the manufacturing conditions for each predetermined range re-saved in the re-saving step; including Among the predetermined ranges, the predetermined range in the longitudinal direction of the metal material is the predetermined range in the longitudinal direction of the metal material in the step to which the manufacturing condition belongs where the importance index for the quality output for each manufacturing condition that is an input to the quality prediction model generated in the model generation step is the maximum; Among the predetermined ranges, the predetermined range in the width direction of the metal material is determined based on a predetermined range division distance determined in advance in the final step; The method for generating a quality prediction model of a metal material according to claim 1 or claim 2.

8. A quality prediction method for a metal material, comprising a quality prediction step of predicting the quality of a metal material manufactured under any manufacturing conditions for each predetermined range in a final process, using the quality prediction model generated by the method for generating a quality prediction model of the metal material according to claim 1 or claim 2.

9. A quality prediction method for a metal material, comprising a quality prediction step of predicting the quality of a metal material manufactured under any manufacturing conditions for each predetermined range, using the quality prediction model generated by the method for generating a quality prediction model of the metal material according to claim 7.

10. Using the quality prediction model generated by the method for generating a quality prediction model of the metal material according to claim 1 or claim 2, for each manufacturing condition that is an input to the quality prediction model, an importance index calculation step of calculating an importance index indicating the influence on the prediction of the output quality; A manufacturing condition estimation step of estimating the manufacturing condition with a high importance index as a manufacturing condition that is a factor affecting the quality of the metal material; A quality prediction step of predicting the output quality using the quality prediction model including, as an input, the manufacturing condition estimated to be a factor affecting the quality of the metal material; A manufacturing condition determination step of determining the manufacturing condition that is a factor affecting the quality of the metal material so that the predicted quality falls within a preset range; A metal material manufacturing step of manufacturing a metal material based on the determined manufacturing conditions; A manufacturing method for a metal material, comprising:

11. A first collection step of collecting the manufacturing conditions of the material in each process within a predetermined range in the longitudinal and width directions of the material, for each predetermined range of each process; A second collection step of evaluating and collecting the quality of the material in the final process of each process for each predetermined range of the final process; A third collection step of collecting at least one of the cutting positions in the longitudinal and width directions of the material in each process and the dimensions in the longitudinal and width directions of the material that change in each process; A storage step of associating and storing the manufacturing conditions of the material in each process collected in the first collection step and the quality of the material in the final process collected in the second collection step for each predetermined range of the final process; A model generation step of generating a quality prediction model for predicting the quality for each predetermined range of the final process from the manufacturing conditions for each predetermined range of the final process stored in the storage step; Including The storage step is based on at least one of the cutting positions in the longitudinal and width directions of the material collected in the third collection step and the dimensions in the longitudinal and width directions of the material that change in each process, to specify the predetermined ranges of each process corresponding to the predetermined range of the final process, and store, for each predetermined range of the final process, the manufacturing conditions of the material in the specified predetermined ranges of each process in association with the quality of the material in the final process. Quality prediction model generation method.

12. A first collection step of collecting the manufacturing conditions of the metal material in each process within a predetermined range in the longitudinal and width directions of the metal material, for each predetermined range of each process; A second collection step of evaluating and collecting the quality of the metal material in the final process of each process, for each predetermined range of the final process; A third collection step of collecting at least one of the cutting positions in the longitudinal and width directions of the metal material in each process and the dimensions in the longitudinal and width directions of the metal material that change in each process; A storage step of storing, for each predetermined range of the final process, the manufacturing conditions of the metal material in each process collected in the first collection step in association with the quality of the metal material in the final process collected in the second collection step; comprising the storage step is based on at least one of the cutting positions in the longitudinal and width directions of the metal material collected in the third collection step and the dimensions in the longitudinal and width directions of the metal material that change in each process, to specify the predetermined ranges of each process corresponding to the predetermined range of the final process, and store, for each predetermined range of the final process, the manufacturing conditions of the metal material in the specified predetermined ranges of each process in association with the quality of the metal material in the final process. Data processing method.

13. A first collection unit that collects the manufacturing conditions of the metal material in each process within a predetermined range in the longitudinal and width directions of the metal material, for each predetermined range of each process; A second collection unit that evaluates and collects the quality of the metal material in the final process of each process, for each predetermined range of the final process; A third collection unit that collects at least one of the cutting positions in the longitudinal and width directions of the metal material in each process and the dimensions in the longitudinal and width directions of the metal material that change in each process; A storage unit that associates and stores the manufacturing conditions of the metal material in each of the steps collected by the first collection unit and the quality of the metal material in the final step collected by the second collection unit for each predetermined range of the final step; A model generation unit that generates a quality prediction model for predicting the quality for each predetermined range of the final step from the manufacturing conditions for each predetermined range of the final step stored in the storage unit; comprising; The storage unit specifies the predetermined range of each step corresponding to the predetermined range of the final step based on at least one or more of the cutting positions in the longitudinal and width directions of the metal material collected by the third collection unit and the dimensions in the longitudinal and width directions of the metal material that change in each step; stores the manufacturing conditions of the metal material in the specified predetermined range of each step and the quality of the metal material in the final step in association with each other for each predetermined range of the final step; A quality prediction model generation device for metal materials.

14. The storage unit re-associates and re-stores the manufacturing conditions of the metal material in each of the steps collected by the first collection unit and the quality of the metal material in the final step collected by the second collection unit for each predetermined range; The model generation unit regenerates a quality prediction model for predicting the quality for each predetermined range from the manufacturing conditions for each predetermined range that have been re-stored; Among the predetermined ranges, the predetermined range in the longitudinal direction of the metal material is the predetermined range in the longitudinal direction of the metal material in the step to which the manufacturing condition belongs, where the importance index for the quality output for each manufacturing condition that becomes the input of the quality prediction model generated in the model generation unit is the maximum; Among the predetermined ranges, the predetermined range in the width direction of the metal material is determined based on a predetermined range division distance determined in advance in the final step; The quality prediction model generation device for metal materials according to claim 13.

15. A quality prediction device for metal materials, comprising a quality prediction unit that predicts the quality of a metal material manufactured under any manufacturing condition for each predetermined range of the final step using the quality prediction model generated by the quality prediction model generation device for metal materials according to claim 13.

16. A quality prediction device for metal materials, comprising a quality prediction unit that predicts the quality of a metal material manufactured under any manufacturing condition for each predetermined range using the quality prediction model generated by the quality prediction model generation device for metal materials according to claim 14.

17. A first collection unit that collects the manufacturing conditions of the metal material in each process within a predetermined range in the longitudinal direction and the width direction of the metal material, and for each predetermined range of each process; A second collection unit that evaluates and collects the quality of the metal material in the final process of each process for each predetermined range of the final process; A third collection unit that collects at least one of the cutting positions in the longitudinal direction and the width direction of the metal material in each process and the dimensions in the longitudinal direction and the width direction of the metal material that change in each process; A storage unit that associates and stores the manufacturing conditions of the metal material in each process collected by the first collection unit and the quality of the metal material in the final process collected by the second collection unit for each predetermined range of the final process; Comprising; The storage unit; Based on at least one of the cutting positions in the longitudinal direction and the width direction of the metal material collected by the third collection unit and the dimensions in the longitudinal direction and the width direction of the metal material that change in each process, identifies the predetermined ranges of the respective processes corresponding to the predetermined range of the final process; Associates and stores the manufacturing conditions of the metal material in the identified predetermined ranges of the respective processes and the quality of the metal material in the final process for each predetermined range of the final process; A data processing device.

Images