Metal material quality prediction model generation method, metal material quality prediction method, metal material quality influencing factor inference method, metal material manufacturing method, quality prediction model generation method, metal material quality prediction model generation device, metal material quality prediction device, and metal material quality influencing factor inference device

Abstract

This metal material quality prediction model generation method includes: a first collection step; a second collection step; a saving step in which, using the width of a prescribed range in one specific process among processes as a reference, manufacturing conditions and quality in the other processes are edited and the manufacturing conditions and quality are repeatedly saved in association with each of unified prescribed ranges that are prescribed ranges in which coarse or fine differences in the manufacturing conditions and the quality in the processes are compensated for and that correspond in number to the number of processes; a model generation step; and a model selection step.

Description

METHOD FOR GENERATING A QUALITY PREDICTION MODEL FOR METALLIC MATERIALS, METHOD FOR PREDICTION OF QUALITY OF METALLIC MATERIALS, METHOD FOR ESTIMATING FACTORS AFFECTING QUALITY OF METALLIC MATERIALS, METHOD FOR MANUFACTURING METALLIC MATERIALS, METHOD FOR GENERATING A QUALITY PREDICTION MODEL FOR METALLIC MATERIALS, DEVICE ... PREDICTION OF QUALITY PREDICTION MODELS FOR METALLIC MATERIALS, AND DEVICE FOR ESTIMATING FACTORS AFFECTING QUALITY OF METALLIC MATERIALS

[0001] The present invention relates to a method for generating a quality prediction model for a metallic material, a method for predicting the quality of a metallic material, a method for estimating factors influencing the quality of a metallic material, a manufacturing method for a metallic material, a method for generating a quality prediction model, an apparatus for generating a quality prediction model for a metallic material, an apparatus for predicting the quality of a metallic material, and an apparatus for estimating factors influencing the quality of a metallic material.

[0002] Patent Document 1 discloses a method for predicting the quality of a material using a model that has been trained with data that links manufacturing condition data during the manufacturing of the material with quality data in the final process, taking into account the quality judgment position in the longitudinal direction of the material.

[0003] Patent No. 7207547

[0004] The quality of materials can vary depending on one or more manufacturing conditions, and the manifestation of quality defects also varies depending on the manufacturing conditions that cause them. Therefore, in order to accurately predict quality defects or estimate the causes of quality defects with high accuracy, it is necessary to appropriately utilize information on manufacturing conditions that correspond to the causes of the quality defects, depending on the type of quality defect.

[0005] However, in the conventional technology, manufacturing condition data and quality data associated with a uniform granularity were used, and therefore the information was not fully and appropriately utilized. Specifically, the conventional technology was premised on aligning the granularity (unit of length of the metal material) of the quality data and manufacturing condition data in each process of manufacturing metal materials to the final process where quality is evaluated. As a result, the utilization of manufacturing condition data in intermediate processes, which could be a major cause of quality defects, according to the granularity of the data was not fully and appropriately considered.

[0006] For example, if each process is a rolling process, the length of the metal material increases mainly in the longitudinal direction as it passes through each process. If the length unit of the metal material in the final process is adjusted, the length of the metal material in the corresponding intermediate process may become shorter than the measurement period of the actual manufacturing condition data of the intermediate process as the process is traced back.

[0007] For this reason, the manufacturing condition data for the intermediate process is converted into data in units of length for the metal material in the final process by performing interpolation (e.g., linear interpolation) to align it with the length unit for the metal material in the final process for evaluating quality. Then, a data set is generated in which the converted manufacturing condition data for the intermediate process is associated with the quality data and manufacturing condition data for the final process.

[0008] However, if the measurement period for the actual manufacturing condition data of intermediate processes is shorter than the measurement period, even if data interpolation is performed, there is a possibility that fluctuations in the actual manufacturing conditions will not be accurately reflected. In particular, when manufacturing conditions change rapidly or fluctuate nonlinearly, linear interpolation may not be able to capture the fluctuations, which poses a risk of reducing the prediction accuracy of the quality prediction model. Furthermore, if the number of data points for each process increases due to interpolation, the quality prediction model may overfit, causing a decrease in generalization performance.

[0009] For this reason, the manufacturing condition data for intermediate processes, which could be the main cause of quality defects, is converted by interpolation, and the accuracy of a model (quality prediction model for metal materials) trained on a data set associated with quality defect data for the final process may not be sufficiently improved. Therefore, with the conventional technology, there are limitations to improving the accuracy of prediction of the quality of metal materials and improving the reliability of estimating the causes of quality defects.

[0010] The present invention has been made in consideration of the above, and aims to provide a quality prediction model generation method for metallic materials, a quality prediction method for metallic materials, a quality prediction factor estimation method for metallic materials, a manufacturing method for metallic materials, a quality prediction model generation method, a quality prediction model generation device for metallic materials, a quality prediction device for metallic materials, and a quality prediction factor estimation device for metallic materials, which determine the coarseness (granularity) of data that aligns and associates manufacturing condition data and quality data for each manufacturing process based on specific indices including an index that indicates the predictive accuracy of the quality prediction model and an importance index that indicates the impact on the prediction of the quality of the final process, and by appropriately utilizing the granularity of the manufacturing conditions for each process, it is possible to predict the quality of a material for any manufacturing condition with high accuracy and estimate the causes of quality defects with high accuracy.

[0011] In order to solve the above-mentioned problems and achieve the object, the method for generating a quality prediction model for metallic materials according to the present invention includes a first collection step of collecting manufacturing conditions for metallic materials in each process for each predetermined range of the metallic material that is set for each process, a second collection step of evaluating and collecting the quality of the metallic material in the final process of each of the processes for each predetermined range that is set for the final process, and a second collection step of evaluating and collecting the manufacturing conditions for the metallic material in each process for each predetermined range that is set for the final process, the manufacturing conditions for the metallic material collected in the first collection step and the quality of the metallic material in the final process collected in the second collection step, based on the width of the predetermined range for a specific process among the processes, and the manufacturing conditions and the quality in other processes. and repeatedly associating and saving the manufacturing conditions and the quality for each unified predetermined range that corresponds to the number of processes and that is a predetermined range that complements the differences in the manufacturing conditions and the quality in each process; a model generation step of generating, for each unified predetermined range, one or more quality prediction models that predict the quality for each unified predetermined range from the manufacturing conditions for each unified predetermined range saved in the saving step; and a model selection step of selecting, when a plurality of quality prediction models have been generated in the model generation step, from the plurality of quality prediction models, the quality prediction model to be used for predicting the quality of the metallic material based on an evaluation of a specific index.

[0012] In the method for generating a quality prediction model for metal materials according to the present invention, in the above invention, the saving step targets all of the processes, individually selects one specific process, sets a predetermined range for the selected specific process as the unified predetermined range, and repeatedly associates and saves the manufacturing conditions and the quality for one or more of the unified predetermined ranges.

[0013] In the method for generating a quality prediction model for a metallic material according to the present invention, in the above invention, the model selection step selects the quality prediction model to be used for predicting the quality of the metallic material from among a plurality of quality prediction models based on an index indicating the predictive accuracy of the quality prediction model as the specific index.

[0014] In the method for generating a quality prediction model for a metal material according to the present invention, in the above invention, the model selection step selects a quality prediction model to be used for predicting the quality of the metal material from among a plurality of quality prediction models based on an importance index that indicates the influence that the manufacturing conditions that are input to each quality prediction model have on the prediction of the quality that is output.

[0015] In the method for generating a quality prediction model for a metallic material according to the present invention, in the above invention, the model selection step generates a quality prediction model from actual data associated with a predetermined range of the final process as the unified predetermined range, calculates an importance index for each manufacturing condition for the generated quality prediction model, extracts the manufacturing condition for which the importance index is maximum, and selects the quality prediction model generated from actual data associated with a predetermined range of the process to which the extracted manufacturing condition belongs as the unified predetermined range as the quality prediction model to be used for predicting the quality of the metallic material.

[0016] In the method for generating a quality prediction model for a metallic material according to the present invention, in the above invention, the model selection step generates a first quality prediction model from associated performance data, with a predetermined range of the final process being the unified predetermined range; calculates a first importance index for each manufacturing condition for the first quality prediction model, and extracts the manufacturing condition for which the first importance index is maximized; generates a second quality prediction model from associated performance data, with a predetermined range of the process to which the extracted manufacturing condition belongs being the unified predetermined range; calculates a second importance index for each manufacturing condition for the second quality prediction model, and extracts the manufacturing condition for which the second importance index is maximized; and selects the second quality prediction model when the manufacturing condition for which the second importance index is maximized matches the manufacturing condition for which the first importance index is maximized, as the quality prediction model to be used for predicting the quality of the metallic material.

[0017] The method for generating a quality prediction model for a metallic material according to the present invention is the same as the above invention, in which the model generation step generates the quality prediction model using a statistical analysis method and a machine learning method, 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.

[0018] In order to solve the above-mentioned problems and achieve the objectives, the quality prediction method for metallic materials of the present invention includes a quality prediction step of predicting the quality of metallic materials manufactured under any manufacturing conditions for each specified range using a quality prediction model generated by the above-mentioned method for generating a quality prediction model for metallic materials.

[0019] In order to solve the above-mentioned problems and achieve the objectives, the method for estimating quality influence factors of metal materials according to the present invention includes an influence factor estimation step of estimating manufacturing conditions that are factors that affect the quality of the metal material using a quality prediction model generated by the above-mentioned method for generating a quality prediction model for metal materials.

[0020] In the method for estimating quality influence factors of a metallic material according to the present invention, in the above invention, the influence factor estimation step calculates an importance index of the quality prediction model for each manufacturing condition, and estimates the manufacturing condition with a high importance index as the manufacturing condition that is a factor that influences the quality of the metallic material.

[0021] In order to solve the above-mentioned problems and achieve the objectives, the method for manufacturing a metallic material according to the present invention includes a quality prediction step for predicting the output quality using a quality prediction model whose input includes manufacturing conditions that are factors that affect the quality of the metallic material, estimated by the above-mentioned method for estimating factors affecting the quality of the metallic material; a manufacturing condition determination step for determining manufacturing conditions that are factors that affect the quality of the metallic material so that the predicted quality falls within a predetermined range; and a metallic material manufacturing step for manufacturing the metallic material in accordance with the determined manufacturing conditions.

[0022] In order to solve the above-mentioned problems and achieve the object, the quality prediction model generation method according to the present invention includes a first collection step of collecting manufacturing conditions for materials in each process for each predetermined range of the material that is determined for each process, a second collection step of evaluating and collecting the quality of the material in the final process of each of the processes for each predetermined range that is determined for the final process, and editing the manufacturing conditions and the quality of the material in the other processes based on the width of the predetermined range for a specific process among the processes, for the manufacturing conditions for 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, The method includes a storage step of repeatedly associating and storing the manufacturing conditions and the quality for each unified predetermined range corresponding to the number of processes, the unified predetermined range being a predetermined range that complements the differences in the manufacturing conditions and the quality in each process; a model generation step of generating one or more quality prediction models for each unified predetermined range from the manufacturing conditions for each unified predetermined range stored in the storage step, the quality prediction model predicting the quality for each unified predetermined range; and a model selection step of selecting, when a plurality of quality prediction models are generated in the model generation step, the quality prediction model to be used for predicting the quality of the material from among the plurality of quality prediction models based on an evaluation of a specific index.

[0023] In order to solve the above-mentioned problems and achieve the object, the quality prediction model generation device for metallic materials according to the present invention includes a first collection unit that collects manufacturing conditions for metallic materials in each process for each predetermined range of the metallic material that is set for each process, a second collection unit that evaluates and collects the quality of the metallic material in the final process of each of the processes for each predetermined range that is set for the final process, and a second collection unit that evaluates and collects the manufacturing conditions for the metallic material in each process collected by the first collection unit and the quality of the metallic material in the final process collected by the second collection unit based on the width of the predetermined range for a specific process among the processes, and a storage unit that compiles the quality and repeatedly associates and stores the manufacturing conditions and the quality for each unified predetermined range that corresponds to the number of processes and that is a predetermined range that complements the differences in the manufacturing conditions and the quality in each process; a model generation unit that generates one or more quality prediction models for each unified predetermined range from the manufacturing conditions for each unified predetermined range stored in the storage unit, the quality prediction model predicting the quality for each unified predetermined range; and a model selection unit that, when the model generation unit generates multiple quality prediction models, selects the quality prediction model to be used for predicting the quality of the metal material from the multiple quality prediction models based on an evaluation of a specific index.

[0024] In order to solve the above-mentioned problems and achieve the objectives, the quality prediction device for metal materials according to the present invention includes a quality prediction unit that predicts the quality of metal materials manufactured under any manufacturing conditions for each specified range using a quality prediction model generated by the above-mentioned metal material quality prediction model generation device.

[0025] In order to solve the above-mentioned problems and achieve the objectives, the metal material quality influence factor estimation device of the present invention includes an influence factor estimation unit that uses the quality prediction model generated by the above-mentioned metal material quality prediction model generation device to estimate manufacturing conditions that are factors that affect the quality of the metal material.

[0026] The metallic material quality prediction model generation method, metallic material quality prediction method, metallic material quality influencing factor estimation method, metallic material manufacturing method, quality prediction model generation method, metallic material quality prediction model generation device, metallic material quality prediction device, and metallic material quality influencing factor estimation device according to the present invention make it possible to reflect the maximum information related to the target quality in the generated quality prediction model by appropriately utilizing the granularity of manufacturing condition data for each process in manufacturing the metallic material.As a result, quality can be predicted with high accuracy, and the causes of quality defects can be estimated with high accuracy.

[0027] FIG. 1 is a block diagram showing an example of the configuration of an information processing device functioning as a quality prediction model generation device, a quality prediction device, and a quality influencing factor estimation device for metallic materials according to an embodiment of the present invention. FIG. 2 is a flowchart showing the flow of the quality prediction model generation method and the quality prediction method for metallic materials according to an embodiment of the present invention. FIG. 3 is a diagram showing an example of manufacturing condition data for each predetermined range in the longitudinal direction of a metallic material collected by a manufacturing condition data collection unit in the quality prediction model generation device, quality prediction device, and quality influencing factor estimation device for metallic materials according to an embodiment of the present invention. FIG. 4 is a diagram showing an example of the case where the integrated process data editing unit edits manufacturing condition data and quality data for predetermined ranges of processes 2 and 3, using the width of the predetermined range of process 1 as a reference (uniform predetermined range), in the quality prediction model generation device, quality prediction device, and quality influencing factor estimation device for metallic materials according to an embodiment of the present invention. FIG. 5 is a diagram showing an example of the case where the integrated process data editing unit edits manufacturing condition data and quality data for predetermined ranges of processes 1 and 3, using the width of the predetermined range of process 2 as a reference (uniform predetermined range), in the quality prediction model generation device, quality prediction device, and quality influencing factor estimation device for metallic materials according to an embodiment of the present invention. Fig. 6 is a diagram showing an example of a case where the integrated process data editing unit in the quality prediction model generation device, quality prediction device, and quality influencing factor estimation device for metallic materials according to an embodiment of the present invention edits manufacturing condition data and quality data for the predetermined ranges of processes 1 and 2, using the width of the predetermined range of process 3 as a reference (uniform predetermined range). Fig. 7 is a diagram showing an example of performance data in the quality prediction model generation device, quality prediction device, and quality influencing factor estimation device for metallic materials according to an embodiment of the present invention, where the integrated process data editing unit combines manufacturing condition data and quality data for the predetermined ranges of all processes, using the width of the predetermined range of process 1 as a reference (uniform predetermined range). Fig. 8 is a diagram showing an example of performance data in the quality prediction model generation device, quality prediction device, and quality influencing factor estimation device for metallic materials according to an embodiment of the present invention, where the integrated process data editing unit combines manufacturing condition data and quality data for the predetermined ranges of all processes, using the width of the predetermined range of process 2 as a reference (uniform predetermined range).9 is a diagram showing an example of performance data when the integrated process data editing unit combines manufacturing condition data and quality data for predetermined ranges of all processes, using the width of the predetermined range of process 3 as a standard (unified predetermined range), in the quality prediction model generation device, quality prediction device, and quality influencing factor estimation device for metallic materials according to an embodiment of the present invention. Fig. 10 is a flowchart showing the flow of the method for estimating quality influencing factors of metallic materials according to an embodiment of the present invention.

[0028] A method for generating a quality prediction model for metal materials, a method for predicting quality of metal materials, a method for estimating quality influence factors, a device for generating a quality prediction model for metal materials, a device for predicting quality of metal materials, and a device for estimating quality influence factors according to embodiments of the present invention will be described with reference to the drawings.

[0029] (Device Configuration) The configurations of a quality prediction model generation device, a quality prediction device, and a quality influencing factor estimation device for metallic materials 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 metallic materials manufactured through one or more processes. The quality prediction device is a device for predicting the quality of metallic materials manufactured through one or more processes using the quality prediction model. The quality influencing factor estimation device is a device for estimating manufacturing conditions, which are factors that affect the quality of metallic materials, using the quality prediction model. Note that metallic materials in this embodiment include, for example, steel products, such as semi-finished products such as slabs, and products such as steel plates manufactured by rolling these slabs.

[0030] In the following, we will explain the quality prediction model generation device, quality prediction device, and quality influence factor estimation device for metal materials. However, the devices can also be applied to materials other than metal materials, such as materials manufactured through multiple processes on a continuous production line, and other manufactured products.

[0031] The quality prediction model generation device, the quality prediction device, and the quality influence factor estimation device can be realized by, for example, an information processing device 1 as shown in Fig. 1. Specifically, the information processing device 1 is configured by a personal computer, a workstation, etc. The main components of the information processing device 1 include a processor such as a CPU (Central Processing Unit), and a memory (main storage unit) such as a RAM (Random Access Memory) and a ROM (Read Only Memory).

[0032] The information processing device 1 includes a manufacturing condition data collection unit 11, a quality data collection unit 12, an integrated process data editing unit 13, an integrated process database 14, a model generation unit 15, a model selection unit 16, a quality prediction unit 17, and an influencing factor estimation unit 18. The quality prediction model generation device for metallic materials according to the embodiment is composed of the elements of the information processing device 1 excluding the quality prediction unit 17 and the influencing factor estimation unit 18. The quality prediction device for metallic materials according to the embodiment is composed of the elements of the information processing device 1 excluding the influencing factor estimation unit 18. The quality influencing factor estimation device according to the embodiment is composed of all the elements of the information processing device 1.

[0033] A sensor (not shown) is connected to the manufacturing condition data collection unit 11. The manufacturing condition data collection unit 11 uses this sensor to collect data on the manufacturing conditions of each process (hereinafter referred to as "manufacturing condition data") and outputs the data to the integrated process data editing unit 13. Examples of the "manufacturing conditions of metal material" include 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 thickness of the metal material before and after rolling, and the threading speed of the metal material.

[0034] The manufacturing condition data for each process collected by the manufacturing condition data collection unit 11 includes not only actual values ​​of the manufacturing conditions measured by sensors but also preset values ​​of the manufacturing conditions. That is, since there are cases where sensors are not installed in some processes, in such cases, the set values ​​are collected as manufacturing condition data instead of actual values.

[0035] The manufacturing condition data collection unit 11 collects manufacturing condition data for metal materials in each process for each predetermined range of the metal material that is determined for each process. The "predetermined range" refers to a certain range (position) in the longitudinal direction of the metal material that is predetermined for each process, for example, when the metal material is a slab or steel plate. The predetermined range for each process may be different or the same for each process. The predetermined range in the longitudinal direction of the metal material is determined, for example, based on the moving distance of the metal material in the conveying direction in each process.

[0036] 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 manufactured through each process (hereinafter referred to as "quality data") using this sensor or data input terminal, and outputs the data to the integrated process data editing unit 13. Examples of the "quality of the metal material" include the tensile strength of the metal material in the final process, the defect contamination rate (the number of defects appearing per unit area) of the metal material in the final process, etc.

[0037] The quality data of metal materials collected by the quality data collection unit 12 includes not only actual quality values ​​measured by sensors, but also quality judgment values ​​entered from a data input terminal, where pass / fail is evaluated based on certain standards based on the actual measurement values ​​or by visual inspection by an inspector, etc.

[0038] The quality data collection unit 12 evaluates and collects the quality of the metal material in the final step of each process for each predetermined range determined for the final step. Note that the predetermined range here is synonymous with the "predetermined range" in the manufacturing condition data collection unit 11.

[0039] The integrated process data editing unit 13 edits the performance data input from the manufacturing condition data collecting unit 11 and the quality data collecting unit 12. The integrated process data editing unit 13 associates the manufacturing condition data for each process collected by the manufacturing condition data collecting unit 11 with the quality data of the metal material collected by the quality data collecting unit 12 for each predetermined range in a specific process of each process, and stores the data in the integrated process database 14.

[0040] The integrated process data editing unit 13 edits the manufacturing condition data and quality data for the other processes, using the width of a predetermined range for a specific one of the processes as a standard, for the manufacturing condition data for the metal material in each process and the quality data for the metal material in the final process among the processes.In doing so, the integrated process data editing unit 13 repeatedly associates the manufacturing condition data and quality data for each unified predetermined range corresponding to the number of processes, which is a predetermined range that compensates for differences in density of the manufacturing condition data and quality data in each process, and stores the data in the integrated process database 14.

[0041] In addition, the integrated process data editing unit 13 selects one specific process individually from all of the processes, sets a specified range in the selected specific process as a unified specified range, and repeatedly associates the manufacturing condition data and quality data for one or more unified specified ranges and stores them in the integrated process database 14.

[0042] As will be described later, when there is one process for manufacturing a metal material, only one unified predetermined range is set. In this case, the integrated process data editing unit 13 creates only one set of data set (e.g., a learning data set) in which the manufacturing condition data and quality data have been edited, and stores this in the integrated process database 14. On the other hand, when there are multiple processes for manufacturing a metal material, multiple unified predetermined ranges are set. In this case, the integrated process data editing unit 13 creates multiple sets of data set (e.g., a learning data set) in which the manufacturing condition data and quality data have been edited, and stores these in the integrated process database 14. Details of the processing by the integrated process data editing unit 13 will be described later (see Figures 4 to 9).

[0043] The model generation unit 15 generates one or more quality prediction models for each unified specified range, based on the manufacturing condition data and quality data for each unified specified range stored in the integrated process database 14, to predict the quality of the metal material for each unified specified range.

[0044] As will be described later, when there is one process for manufacturing a metal material, only one unified predetermined range is set. In this case, the model generation unit 15 generates only one quality prediction model. On the other hand, when there are multiple processes for manufacturing a metal material, multiple unified predetermined ranges are set. In this case, the model generation unit 15 generates multiple quality prediction models.

[0045] The model generation unit 15 uses, for example, a gradient boosting tree as a statistical analysis method and a machine learning method when generating a quality prediction model. Note that, in addition to the above, various other statistical analysis methods and machine learning methods can be used, 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.

[0046] The model selection unit 16 selects one quality prediction model from among multiple quality prediction models when multiple quality prediction models are generated by the model generation unit 15. "When multiple quality prediction models are generated" refers to the case where there are multiple processes for manufacturing a metal material and multiple unified predetermined ranges are set, as described above.

[0047] The model selection unit 16 selects a quality prediction model to be used for predicting the quality of the metallic material (processing in the quality prediction unit 17) from among a plurality of quality prediction models, based on, for example, an evaluation of a specific index. In this case, the model selection unit 16 selects a quality prediction model to be used for predicting the quality of the metallic material from among the plurality of quality prediction models, based on, for example, an index indicating the prediction accuracy of the quality prediction model as the specific index.

[0048] Furthermore, the model selection unit 16 may select a quality prediction model to be used for predicting the quality of the metallic material from among a plurality of quality prediction models based on an importance index that indicates the influence that the manufacturing conditions that are input to each quality prediction model have on the prediction of the quality that is output. Details of the processing by the model selection unit 16 will be described later.

[0049] The quality prediction unit 17 uses the quality prediction model generated by the model generation unit 15 and selected by the model selection unit 16 as necessary to predict the quality of metal materials manufactured under any manufacturing conditions for each specified range.

[0050] The influencing factor estimation unit 18 estimates manufacturing conditions that are factors that affect the quality of the metal material, using the quality prediction model generated by the model generation unit 15 and selected as needed by the model selection unit 16. Details of the processing by the influencing factor estimation unit 18 will be described later.

[0051] (Quality Prediction Method) A quality prediction method and a quality prediction model generation method according to this embodiment will be described with reference to Figures 2 to 9. The quality prediction method according to this embodiment performs the processes of steps S11 to S17 shown in Figure 2. Furthermore, the quality prediction model generation method according to this embodiment performs the processes of steps S11 to S16 shown in Figure 2, excluding step S17.

[0052] 2, step S11 corresponds to the first collection step, step S12 corresponds to the second collection step, step S13 corresponds to the storage step, step S14 corresponds to the model generation step, and steps S15 and S16 correspond to the model selection step, and step S17 corresponds to the prediction step.

[0053] First, the manufacturing condition data collection unit 11 collects manufacturing condition data for each process for each predetermined range of metal material that is predefined for each process (step S11). The manufacturing condition data collected by the manufacturing condition data collection unit 11 is data in which actual values ​​or set values ​​of multiple manufacturing conditions are listed for each predetermined range of metal material that is predefined for each process, as shown in Fig. 3, for example.

[0054] The manufacturing condition data shown in FIG. １ , l ２ , ... and a plurality of manufacturing conditions x measured by the sensor at the position １ １ , x １ ２ , ..., x ２ １ , x２ ２ , .... The manufacturing condition data shown in FIG. 3 indicates, for example, manufacturing condition data collected in one process. Therefore, for example, if there are three manufacturing processes for a metal material, three pieces of manufacturing condition data shown in FIG. 3 are also collected in accordance with the number of processes. In this case, the manufacturing condition data collected in each process includes the longitudinal position l １ , l ２ , ... (=predetermined range) may be different or may be the same.

[0055] Next, the quality data collection unit 12 evaluates and collects quality data of the metal material manufactured through each process for each predetermined range (step S12). The quality data collected by the quality data collection unit 12 is collected at the final process of multiple processes, and is data containing quality evaluation results corresponding to the position from the leading end to the trailing end of the metal material in the longitudinal direction in each process.

[0056] Next, the integrated process data editing unit 13 associates and saves the manufacturing condition data for each process with the quality data for the metal material manufactured under those manufacturing conditions (step S13). Based on the manufacturing condition data and quality data for the longitudinal position of the metal material collected in steps S11 and S12, the integrated process data editing unit 13 edits the manufacturing condition data and quality data for other processes using the width of a predetermined range for a specific process among the processes as a reference. The integrated process data editing unit 13 then aligns and associates the manufacturing condition data and quality data for each process into a unified predetermined range that interpolates and compensates for differences in the density of the granularity of the predetermined range.

[0057] The "granularity of the specified range" refers to, for example, the length of the acquisition (collection) period of manufacturing condition data and quality data. If the acquisition period of manufacturing condition data and quality data is short, the granularity of the specified range will be fine. On the other hand, if the acquisition period of manufacturing condition data and quality data is long, the granularity of the specified range will be coarse. Furthermore, the "uniform specified range" refers to the width of the specified range in a specific process among the processes.

[0058] In this way, the integrated process data editing unit 13 associates the manufacturing condition data for each process with the quality data for the metal material manufactured under those manufacturing conditions for each uniform predetermined range in the longitudinal direction of the metal material and stores them. An example of processing by the integrated process data editing unit 13 will be described below with reference to Figures 4 to 9.

[0059] For example, as shown in Figures 4 to 6, consider the case where a metal material (material) is manufactured through steps 1, 2, and 3. In Figures 4 to 6, the longitudinal position of the metal material is shown aligned relative to the leading and trailing ends of the metal material, and steps 1, 2, and 3 each have a different predetermined range. In step 1, the manufacturing condition x ａ In step 2, the manufacturing condition data is represented by the manufacturing condition x ｂ In step 3, the manufacturing condition data is represented by the manufacturing condition x ｃ The manufacturing condition data and quality data (not shown) that fall within a predetermined range are collected.

[0060] In addition, in processes 1, 2, and 3, multiple pieces of manufacturing condition data may be collected within each process, as shown in Fig. 3, but the data acquisition period is basically the same for each process. Therefore, there is only one type of predetermined range for each of processes 1, 2, and 3. In other words, one predetermined range is defined for each process.

[0061] 4, the integrated process data editing unit 13 edits the manufacturing condition data and quality data in the predetermined ranges of processes 2 and 3, using the width of the predetermined range of process 1 as a standard (unified predetermined range), as a first sub-step in the saving step. In this way, the difference in density of the granularity of the predetermined ranges of processes 2 and 3 is compensated for by interpolation with respect to the granularity of the predetermined range of process 1.

[0062] Specifically, the integrated process data editing unit 13 compiles manufacturing condition data for two predetermined ranges in process 2, which correspond to the width of the predetermined range in process 1, and associates the data with each predetermined range in process 1 as representative data for the two predetermined ranges in process 2. Similarly, the integrated process data editing unit 13 compiles manufacturing condition data and quality data for four predetermined ranges in process 3, which correspond to the width of the predetermined range in process 1, and creates a data set associated with each predetermined range in process 1 as representative data for the four predetermined ranges in process 3.

[0063] 5, the integrated process data editing unit 13 edits the manufacturing condition data and quality data in the predetermined ranges of processes 1 and 3, using the width of the predetermined range of process 2 as a standard (unified predetermined range), as a second sub-step in the saving step. As a result, the difference in density of the granularity of the predetermined ranges of processes 1 and 3 is compensated for by interpolation with respect to the granularity of the predetermined range of process 2.

[0064] Specifically, the integrated process data editing unit 13 associates the manufacturing condition data of a predetermined range of process 1, which corresponds to the width of the predetermined range of process 2, as representative data for each predetermined range of process 2. At this time, the representative data of process 1 becomes the same data in two adjacent predetermined ranges of process 2. Furthermore, the integrated process data editing unit 13 aggregates the manufacturing condition data and quality data of two predetermined ranges of process 3, which correspond to the width of the predetermined range of process 2, and creates a data set associated with each predetermined range of process 2 as representative data for the two predetermined ranges of process 3.

[0065] 6, the integrated process data editing unit 13 edits the manufacturing condition data in the predetermined ranges of processes 1 and 2, using the width of the predetermined range of process 3 as a standard (unified predetermined range), thereby interpolating and compensating for the difference in density of the granularity of the predetermined ranges of processes 1 and 2 relative to the granularity of the predetermined range of process 3.

[0066] Specifically, the integrated process data editing unit 13 creates a data set in which the manufacturing condition data for a predetermined range of process 1, which corresponds to the width of the predetermined range of process 3, is used as representative data and associated with each predetermined range of process 3. At this time, the representative data for process 1 will be the same data in the four adjacent predetermined ranges of process 3. Furthermore, the integrated process data editing unit 13 associates the actual data of the manufacturing conditions for a predetermined range of process 2, which corresponds to the width of the predetermined range of process 3, as representative data for each predetermined range of process 3. At this time, the representative data for process 2 will be the same data in the two adjacent predetermined ranges of process 3.

[0067] Note that each sub-step is actually repeated K times, corresponding to the number K of processes. That is, the integrated process data editing unit 13 creates K data sets corresponding to the number K of processes. When compiling performance data performed by the integrated process data editing unit 13, commonly known statistics such as average values, maximum values, and minimum values ​​may be used to determine representative data by aggregation. Alternatively, performance data selected based on arbitrary conditions from performance data within a plurality of predetermined ranges may be used. Returning to FIG. 2, the explanation will be continued below.

[0068] The model generation unit 15 generates one or more quality prediction models that predict the quality of each specified range of the metallic material from the manufacturing condition data (data set) for each unified specified range in each process, depending on the granularity of the unified specified range in which the manufacturing condition data and the quality data are associated (step S14). If there is one process for manufacturing the metallic material and only one unified specified range is set, the model generation unit 15 generates only one quality prediction model. On the other hand, if there are multiple processes for manufacturing the metallic material and multiple unified specified ranges are set, the model generation unit 15 generates multiple quality prediction models for the number of created data sets.

[0069] Next, the model selection unit 16 determines whether multiple quality prediction models have been generated in the model generation step (step S15). If multiple quality prediction models have been generated in the model generation step (Yes in step S15), the process proceeds to step S16. On the other hand, if multiple quality prediction models have not been generated in the model generation step (No in step S15), the process proceeds to step S17.

[0070] Next, the model selection unit 16 selects a quality prediction model to be used from the multiple quality prediction models based on an evaluation of an index indicating the prediction accuracy of the quality prediction model (step S16). The model selection unit 16 evaluates the index indicating the prediction accuracy of the quality prediction model, for example, by holdout validation or cross validation, and selects a quality prediction model based on the granularity of a unified predetermined range in which the index indicates the smallest or largest value, depending on the index to be used.

[0071] When the quality prediction model is a regression model, the index may be, for example, a mean squared error (MSE), a root mean squared error (RMSE), a mean absolute error (MAE), a coefficient of determination (R2), etc. When the quality prediction model is a classification model, the index may be, for example, an accuracy rate (Accuracy), a precision rate (Precision), a recall rate (Recall), an F-measure, etc.

[0072] Next, the quality prediction unit 17 predicts the quality of the metal material manufactured under any manufacturing conditions for each specified range using the quality prediction model generated by the model generation unit 15 and selected by the model selection unit 16 as necessary (step S17).

[0073] In this embodiment, quality prediction is performed in step S17 after selecting a quality prediction model in step S16, but it is not essential to perform all steps up to step S16 every time step S17 is performed. For example, steps S11 to S16 may be performed in advance to select a quality prediction model, and then only steps S11, S13, and S17 may be performed every time step S17 is performed using the selected quality prediction model.

[0074] (Quality Influencing Factor Estimation Method) The quality influencing factor estimation method according to this embodiment will be described with reference to Fig. 10. Note that the processing of steps S21 to S25 shown in Fig. 10 is the same as the processing of steps S11 to S15 shown in Fig. 2, and therefore description thereof will be omitted below.

[0075] 10, step S21 corresponds to the first collection step, step S22 corresponds to the second collection step, step S23 corresponds to the storage step, step S24 corresponds to the model generation step, and steps S25 and S26 correspond to the model selection step, and step S27 corresponds to the quality influence factor estimation step.

[0076] The model selection unit 16 selects a quality prediction model to be used from among the multiple quality prediction models based on an evaluation of an index indicating the prediction accuracy of the quality prediction model (step S26). The model selection unit 16 selects a quality prediction model to be used to predict the quality of the metallic material based on an importance index indicating the influence that manufacturing condition data, which is input to the multiple quality prediction models generated by the model generation unit 15, has on the prediction of output quality data. There are broadly two methods for model selection by the model selection unit 16, which will be described below.

[0077] First, the model selection unit 16 calculates an importance index (variable importance) for each manufacturing condition for a quality prediction model generated from performance data associated with a predetermined range for the final process in which quality data is collected, as a unified predetermined range, among the processes. Then, the model selection unit 16 extracts the manufacturing condition with the maximum importance index.

[0078] The importance index is calculated as an index corresponding to the influence of each factor on the entire prediction model. For example, an algorithm that calculates an importance index specific to the algorithm that created the model, such as the importance based on Gini impurity in decision tree algorithms such as random forest, may be used. Alternatively, a known method that calculates an importance index generically regardless of the model creation algorithm, such as "Permutation Importance," may be used.

[0079] Next, the model selection unit 16 selects, as the quality prediction model to be used for predicting quality, a quality prediction model generated from actual data associated with a predetermined range of the process to which the manufacturing conditions with the largest importance index belong, as a unified predetermined range.

[0080] For example, as shown in Figures 4 to 6, consider the case where a metal material (material) is manufactured through processes 1, 2, and 3, i.e., where three quality prediction models are generated from three pieces of actual data. In this case, the importance index is calculated for each manufacturing condition for the quality prediction model generated from the associated actual data (see Figure 6) with the predetermined range of process 3, which is the final process, as the unified predetermined range. Then, for example, for manufacturing condition x ａ When the importance index of the manufacturing condition x is the largest, ａ The quality prediction model generated from the performance data (see FIG. 4) associated with the predetermined range of process 1 to which the above belongs as the unified predetermined range is selected as the quality prediction model to be used for predicting quality.

[0081] <Second Model Selection Method> First, the model selection unit 16 calculates a first importance index (variable importance) for each manufacturing condition for a first quality prediction model generated from performance data associated with a predetermined range for the final process in which quality data is collected among the processes as a unified predetermined range. Then, the model selection unit 16 extracts the manufacturing condition with the largest first importance index.

[0082] As in the first model selection method, the importance index is calculated as an index corresponding to the influence of each factor on the entire predictive model. For example, an algorithm that calculates an importance index specific to the algorithm that created the model, such as the importance based on Gini impurity in decision tree algorithms such as random forest, may be used. Alternatively, a known method that calculates an importance index generically regardless of the model creation algorithm, such as "Permutation Importance," may be used.

[0083] Next, the model selection unit 16 calculates a second importance index for each manufacturing condition for a second quality prediction model generated from associated performance data, with a predetermined range of processes to which the manufacturing condition with the largest first importance index belongs being defined as a unified predetermined range, and then extracts the manufacturing condition with the largest second importance index.

[0084] In this case, if the process to which the manufacturing conditions for which the second importance index is the maximum value belong coincides with the process to which the manufacturing conditions for which the first importance index is the maximum belong, the model selection unit 16 selects the second quality prediction model as the model to be used.

[0085] On the other hand, if the process to which the manufacturing condition with the largest second importance index belongs does not match the process to which the manufacturing condition with the largest first importance index belongs, the model selection unit 16 extracts a third importance index for each manufacturing condition for the third quality prediction model generated from the associated performance data using the predetermined range of the process to which the manufacturing condition with the largest second importance index belongs as the unified predetermined range. Then, the model selection unit 16 extracts the manufacturing condition with the largest third importance index.

[0086] Thereafter, the model selection unit 16 extracts the kth importance index for each manufacturing condition for the kth quality prediction model (k≧1), and repeats the above process until the process to which the manufacturing condition with the largest kth importance index belongs matches the process to which the manufacturing condition with the largest k−1th importance index belongs, and when the process to which the manufacturing condition belongs matches the Nth time the process is repeated, the Nth quality prediction model is selected as the model to be used. Note that an arbitrary upper limit may be set for the number of times the process is repeated.

[0087] For example, as shown in Figures 4 to 6, consider the case where a metal material (material) is manufactured through processes 1, 2, and 3, i.e., where three quality prediction models are generated from three pieces of actual data. In this case, a first importance index is calculated for each manufacturing condition for a first quality prediction model generated from associated actual data (see Figure 6) with the predetermined range of process 3, which is the final process, as the unified predetermined range. Then, for example, for manufacturing condition x ａ When the importance index of the manufacturing condition x is the largest, ａ The second importance index is calculated for each manufacturing condition for the second quality prediction model generated from the performance data (see FIG. 4) associated with the predetermined range of the process 1 to which the manufacturing condition x belongs, as the unified predetermined range. ｂ When the importance index of the manufacturing condition x is the largest, ｂ The third importance index is calculated for each manufacturing condition for the third quality prediction model generated from the performance data (see FIG. 5) associated with the predetermined range of the process 2 to which the manufacturing condition x belongs, as the unified predetermined range. ｂ When the importance index of the third quality prediction model is the largest, the process to which the manufacturing condition for which the third importance index is the largest belongs coincides with the process to which the manufacturing condition for which the second importance index is the largest, and therefore the third quality prediction model is selected as the quality prediction model to be used for predicting quality.

[0088] Next, the influencing factor estimation unit 18 estimates manufacturing conditions that are factors that affect the quality of the metal material using the quality prediction model selected by the model selection unit 16 (step S27). For example, the influencing factor estimation unit 18 calculates the variable importance of the quality prediction model for each manufacturing condition, and extracts any number of manufacturing conditions in descending order of the variable importance. The influencing factor estimation unit 18 then presents the extracted manufacturing conditions as a list of item names of manufacturing conditions estimated to be influencing factors, or as an illustration, such as a bar graph in descending order.

[0089] (Method for Manufacturing Metallic Material) The method for manufacturing a metallic material according to this embodiment includes a quality prediction step, a manufacturing condition determination step, and a metallic material manufacturing step.

[0090] In the quality prediction step, the influencing factor estimation unit 18 predicts the output quality using a quality prediction model selected by the model selection unit 16, which includes as input factors that affect the quality of the metal material and estimated manufacturing conditions.

[0091] In the manufacturing condition determination step, the influencing factor estimation unit 18 may determine a control range of the manufacturing conditions estimated as factors that affect the quality of the metallic material so that the predicted quality falls within a predetermined range. The control range of the manufacturing conditions can be obtained by a mathematical programming method such as a branch and bound method.

[0092] In the metal material manufacturing step, the metal material is manufactured based on manufacturing conditions that are adjusted so that the manufacturing conditions estimated to be factors that affect the quality of the metal material are within the determined control range.

[0093] The information processing device 1 may further include an output unit that outputs, as an output signal, the control range of the manufacturing conditions that are estimated as factors that affect the quality of the metal material, as determined by the influencing factor estimation unit 18. If the output signal is output to a control device of the equipment, the output signal may be a control signal of the equipment that sets the manufacturing conditions. Furthermore, if the output signal is output to an operation terminal of an operator, the output signal may be operator guidance information that is displayed on the screen as guidance.

[0094] Example An example of the method for predicting quality of a metallic material according to the embodiment will be described. In this example, the method for predicting quality of a metallic material according to the embodiment was applied to predicting the number of surface defects in a surface-treated steel sheet (hot-dip galvanized steel sheet).

[0095] The predetermined grain size ranges in the casting process, hot rolling / rough rolling process, hot rolling / finish rolling process, cold rolling process, and surface treatment process were 0.2 m pitch, 0.2 m pitch, 0.5 m pitch, 1 m pitch, and 1 m pitch, respectively.

[0096] In the example of the invention, a quality prediction model was created that outputs the number of surface defects for each unified range from a data set of performance data for each process, which is related to a predetermined range (1 m pitch) in the surface treatment process, the final process. Next, an importance index (variable importance) for each manufacturing condition was calculated for the created quality prediction model.

[0097] Next, the casting speed in the casting process was extracted as the manufacturing condition with the highest importance index. Next, a predetermined range (0.2 m pitch) of the casting process to which the relevant manufacturing condition (casting speed) belongs was defined as the unified predetermined range, and a quality prediction model generated from a dataset of manufacturing condition data for each associated process was selected. If the coil length of the hot-dip galvanized steel sheet is 2000 m and the slab length after the casting process is 8 m, the coil length of the corresponding hot-dip galvanized steel sheet would be 50 m if the predetermined range (0.2 m pitch) of the casting process was defined as the unified predetermined range.

[0098] In the comparative example, a quality prediction model was selected that outputs the number of surface defects for each unified specified range from a data set of performance data for each process associated with a specified range (1 m pitch) of the final process, the surface treatment process, as the unified specified range.

[0099] The comparison results of the reproducibility of defects and defects are shown in Table 1. As shown in Table 1, the reproducibility of defects in the example of the present invention is slightly lower than that in the comparative example, but the reproducibility of defects is significantly improved.

[0100]

[0101] According to the above-described embodiments of the method for generating a quality prediction model for metallic materials, the method for predicting quality of metallic materials, the method for estimating quality influencing factors for metallic materials, the method for manufacturing a metallic material, the quality prediction model generation method, the device for generating a quality prediction model for metallic materials, the device for predicting quality of metallic materials, and the device for estimating quality influencing factors for metallic materials, the granularity of the manufacturing condition data for each process in manufacturing a metallic material can be appropriately utilized to reflect the maximum information related to the target quality in the generated quality prediction model. As a result, quality can be predicted with high accuracy, and the causes of quality defects can be estimated with high accuracy.

[0102] Furthermore, according to the metallic material quality prediction model generation method, metallic material quality prediction method, metallic material quality influencing factor estimation method, metallic material manufacturing method, quality prediction model generation method, metallic material quality prediction model generation device, metallic material quality prediction device, and metallic material quality influencing factor estimation device, one or more quality prediction models are generated that associate the manufacturing conditions of each process with the quality of the metallic material manufactured under those manufacturing conditions for a predetermined range of each process, and the quality prediction model to be used is selected based on a specific index. This makes it possible to predict the quality of the metallic material for any manufacturing conditions with higher accuracy than before, and to estimate the manufacturing conditions that are factors that affect the quality of the metallic material with high accuracy.

[0103] The method for generating a quality prediction model for metallic materials, the method for predicting quality of metallic materials, the method for estimating quality influencing factors for metallic materials, the method for manufacturing metallic materials, the quality prediction model generating method, the device for generating a quality prediction model for metallic materials, the device for predicting quality of metallic materials, and the device for estimating quality influencing factors for metallic materials according to the present invention have been specifically described above using preferred embodiments and examples for carrying out the invention, but the scope of the present invention is not limited to these descriptions and should be broadly interpreted based on the claims. Needless to say, various changes and modifications based on these descriptions are also included in the scope of the present invention.

[0104] REFERENCE SIGNS LIST 1 Information processing device 11 Manufacturing condition data collection unit 12 Quality data collection unit 13 Integrated process data editing unit 14 Integrated process database 15 Model generation unit 16 Model selection unit 17 Quality prediction unit 18 Influence factor estimation unit

Claims

1. A first collection step of collecting manufacturing conditions for metal materials in each process for each predetermined range of the metal material defined for each process; A second collection step of evaluating and collecting the quality of the metal material in the final process of each of the processes for each predetermined range defined for the final process; A storage step of compiling the manufacturing conditions and quality of the metal material in other processes using the width of the predetermined range for a specific one of the processes as a standard for the manufacturing conditions for 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, and repeatedly associating and storing the manufacturing conditions and quality for each unified predetermined range corresponding to the number of processes, which is a predetermined range that complements the differences in the manufacturing conditions and quality in each process; A model generation step of generating one or more quality prediction models for each unified predetermined range from the manufacturing conditions for each unified predetermined range saved in the storage step, to predict the quality for each unified predetermined range. a model selection step of selecting, when a plurality of quality prediction models are generated in the model generation step, the quality prediction model to be used for predicting the quality of the metallic material from among the plurality of quality prediction models based on an evaluation of a specific index.

2. A method for generating a quality prediction model for metallic materials as described in claim 1, wherein the saving step targets all of the processes, individually selects one specific process, sets a specified range for the selected specific process as the unified specified range, and repeatedly associates and saves the manufacturing conditions and the quality for one or more of the unified specified ranges.

3. A method for generating a quality prediction model for a metallic material as described in claim 1, wherein the model selection step selects the quality prediction model to be used for predicting the quality of the metallic material from among a plurality of quality prediction models based on an index indicating the predictive accuracy of the quality prediction model as the specific index.

4. A method for generating a quality prediction model for a metallic material as described in claim 1, wherein the model selection step selects the quality prediction model to be used for predicting the quality of the metallic material from among a plurality of quality prediction models based on an importance index indicating the influence that the manufacturing conditions that are input to each quality prediction model have on the prediction of the output quality.

5. The method for generating a quality prediction model for a metallic material according to claim 4, wherein the model selection step generates a quality prediction model from actual data associated with a predetermined range of the final process as the unified predetermined range, calculates an importance index for each manufacturing condition for the generated quality prediction model, and extracts the manufacturing condition for which the importance index is maximum, and selects the quality prediction model generated from actual data associated with a predetermined range of the process to which the extracted manufacturing condition belongs as the unified predetermined range, as the quality prediction model to be used for predicting the quality of the metallic material.

6. The method for generating a quality prediction model for a metallic material according to claim 4, wherein the model selection step: generates a first quality prediction model from actual data associated with a predetermined range of the final process as the unified predetermined range; calculates a first importance index for each manufacturing condition for the first quality prediction model, and extracts the manufacturing condition for which the first importance index is maximum; generates a second quality prediction model from actual data associated with a predetermined range of the process to which the extracted manufacturing conditions belong as the unified predetermined range; calculates a second importance index for each manufacturing condition for the second quality prediction model, and extracts the manufacturing condition for which the second importance index is maximum; and selects the second quality prediction model when the manufacturing condition for which the second importance index is maximum coincides with the manufacturing condition for which the first importance index is maximum as the quality prediction model to be used for predicting the quality of the metallic material.

7. A method for generating a quality prediction model for a metallic material according to any one of claims 1 to 6, wherein the model generation step generates the quality prediction model using a statistical analysis method and a machine learning method, 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.

8. A method for predicting the quality of a metallic material, comprising a quality prediction step of predicting the quality of a metallic material manufactured under any manufacturing conditions for each specified range using a quality prediction model generated by the method for generating a quality prediction model for a metallic material described in any one of claims 1 to 7.

9. A method for estimating quality influence factors of metallic materials, comprising an influence factor estimation step of estimating manufacturing conditions that are factors that affect the quality of metallic materials, using a quality prediction model generated by the method for generating a quality prediction model for metallic materials described in any one of claims 1 to 7.

10. A method for estimating factors affecting the quality of metal materials as described in claim 9, wherein the influencing factor estimation step calculates an importance index for the quality prediction model for each manufacturing condition, and estimates manufacturing conditions with high importance indexes as manufacturing conditions that are factors that affect the quality of the metal material.

11. A method for manufacturing a metallic material, comprising: a quality prediction step for predicting output quality using a quality prediction model including, as input, manufacturing conditions that are factors that affect the quality of the metallic material, estimated by the method for estimating factors that affect the quality of a metallic material as described in claim 9; a manufacturing condition determination step for determining manufacturing conditions that are factors that affect the quality of the metallic material so that the predicted quality falls within a predetermined range; and a metallic material manufacturing step for manufacturing the metallic material in accordance with the determined manufacturing conditions.

12. A first collection step of collecting manufacturing conditions for materials in each process for each predetermined range of the material defined for each process; a second collection step of evaluating and collecting the quality of the material in the final process of each of the processes for each predetermined range defined for the final process; a storage step of compiling the manufacturing conditions and quality of the material in other processes based on the width of the predetermined range for a specific one of the processes, for the manufacturing conditions for 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, and repeatedly associating and storing the manufacturing conditions and quality for each unified predetermined range corresponding to the number of processes, which is a predetermined range that complements the differences in the manufacturing conditions and quality in each process; a model generation step of generating one or more quality prediction models for each unified predetermined range, which predict the quality for each unified predetermined range, from the manufacturing conditions for each unified predetermined range saved in the storage step. and a model selection step of selecting, when a plurality of quality prediction models are generated in the model generation step, the quality prediction model to be used for predicting the quality of the material from among the plurality of quality prediction models based on an evaluation of a specific index.

13. A first collection unit that collects manufacturing conditions for metal materials in each process for each predetermined range of the metal material defined for each process; a second collection unit that evaluates and collects the quality of the metal material in the final process of each of the processes for each predetermined range defined for the final process; a storage unit that edits the manufacturing conditions for 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 based on the width of the predetermined range for a specific one of the processes, and repeatedly associates and stores the manufacturing conditions and quality for each unified predetermined range corresponding to the number of processes, which is a predetermined range that complements the differences in the manufacturing conditions and quality for each of the processes; a model generation unit that generates one or more quality prediction models for each unified predetermined range from the manufacturing conditions for each unified predetermined range stored in the storage unit, to predict the quality for each unified predetermined range. a model selection unit that, when the model generation unit generates a plurality of quality prediction models, selects the quality prediction model to be used for predicting the quality of the metal material from the plurality of quality prediction models based on an evaluation of a specific index.

14. A quality prediction device for metallic materials, comprising a quality prediction unit that predicts the quality of metallic materials manufactured under any manufacturing conditions within a specified range using a quality prediction model generated by the metallic material quality prediction model generation device described in claim 13.

15. A quality influence factor estimation device for metal materials, comprising an influence factor estimation unit that estimates manufacturing conditions that are factors that affect the quality of metal materials using a quality prediction model generated by the quality prediction model generation device for metal materials described in claim 13.

Images