Steel evaluation method, program, and model generation method

Abstract

To provide a steel evaluation method by which a more-detailed evaluation can be carried out regarding steel satisfying a composition-related standard.SOLUTION: In a steel evaluation method, a steel composition is analyzed, and if composition data obtained from the analysis satisfies a prescribed standard, the composition data is input to a model 56 that has been trained through machine learning so as to output data that is the same as input data. A loss error between output data output from the model 56 and the composition data is then calculated, and it is determined whether the loss error is greater than a prescribed reference value.SELECTED DRAWING: Figure 14

Description

[Technical field]

[0001] The present invention relates to a method, a program, and a method for generating a model for evaluating steel. [Background technology]

[0002] Steel is an alloy of iron with small amounts of additives such as carbon, silicon, manganese, and phosphorus. The properties of steel vary greatly depending on the ratio of each component, i.e., the composition, so various types of steel, such as carbon steel, tool steel, and spring steel, are manufactured and used. Standards regarding the composition are established for each type of steel (Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2006-152356 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the above mentioned standards, the ratio of each component is set within a range. When manufacturing steel, the content of each component is adjusted so that it falls within the set range, i.e., to satisfy the component standards. The manufactured steel undergoes various pre-shipment inspections, including compositional analysis, to confirm that the compositional standards are actually being met. Steel that passes the pre-shipment inspections is shipped.

[0005] However, it is known from experience that when multiple lots of steel manufactured to meet the same chemical composition standards are compared, some lots of steel exhibit superior properties compared to other lots of steel. By detecting the occurrence of such superior steel properties and reflecting this in the management of the manufacturing process, it is expected that the quality of steel will be improved.

[0006] In one aspect, an object of the present invention is to provide a method for evaluating steel that can evaluate in more detail steel that satisfies standards regarding its composition. [Means for solving the problem]

[0007] The method for evaluating steel involves analyzing the composition of the steel, and if the composition data obtained by the analysis meets a predetermined standard, inputting the composition data into a machine-learned model that outputs data identical to the input data, calculating the error loss between the output data output from the model and the composition data, and determining whether the error loss exceeds a predetermined reference value. Effect of the Invention

[0008] In one aspect, it is possible to provide a steel evaluation method that can evaluate steel that satisfies a standard regarding its composition in more detail. [Brief description of the drawings]

[0009] [Figure 1] FIG. 2 is an explanatory diagram for explaining the process of determining and using a steel evaluation method. [Diagram 2] FIG. 2 is an explanatory diagram illustrating the stages of use of the steel evaluation method. [Diagram 3] 1 is a table showing the compositions of samples used in the preliminary study stage. [Figure 4] 1 is a graph showing the heat treatment dimensional change rates of steels having different molybdenum contents. [Diagram 5] 1 is a graph showing the heat treatment dimensional change rates of steels having different chromium contents. [Figure 6] 1 is a graph showing the heat treatment dimensional change rates of steels with different vanadium contents. [Figure 7] 1 is a graph showing the heat treatment dimensional change rates of steels having different silicon contents. [Figure 8] 1 is a graph showing the heat treatment dimensional change rates of steels with different manganese contents. [Figure 9] FIG. 2 is an explanatory diagram illustrating a configuration of an information processing device used to generate a model. [Figure 10] FIG. 1 is an explanatory diagram for explaining a model. [Figure 11] FIG. 11 is an explanatory diagram illustrating a processing flow of a program for generating a model. [Figure 12] 1 is a graph showing the variation of mean absolute error loss depending on the manufacturing time. [Figure 13] FIG. 1 is an explanatory diagram illustrating a configuration of a steel evaluation system. [Figure 14] FIG. 11 is an explanatory diagram illustrating a flow of program processing in the utilization stage. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] [Embodiment 1] Fig. 1 is an explanatory diagram for explaining the process of determining and using an evaluation method for steel. In this embodiment, an example will be described in which the composition of a steel that has already been mass-produced is fine-tuned so as to stably reproduce excellent properties, and an evaluation method for stably manufacturing the fine-tuned steel is determined. An overview of the process of determining an evaluation method for steel will be described using Fig. 1.

[0011] First, a preliminary study is carried out, in which samples of steels with slightly different compositions are prepared, including steels with standard properties among mass-produced steels, as well as steels with intentionally high or low contents of each element.

[0012] A compositional analysis is performed for each sample. Furthermore, properties are evaluated for each sample. Based on the compositional analysis results and the property evaluation results, a target composition is established for stably producing steel with desired properties.

[0013] Here, the target composition is determined so that the ratio of a specific component is larger or smaller within a range of the content of each component defined in the standard of the mass-produced steel. In other words, the target composition does not deviate from the standard of the mass-produced steel. Details of the preliminary study stage will be described later.

[0014] Next, a data collection stage is carried out. In the data collection stage, a plurality of lots of steel are produced under the production conditions modified based on the target composition established in the preliminary study stage. Note that the composition of the steel actually produced varies between lots.

[0015] A composition analysis is performed on each lot of steel. A training DB (Database) 51 is created in which multiple sets of composition analysis data are recorded. A model 56 is generated using the training DB 51. The model 56 is, for example, an autoencoder, and is trained by machine learning so as to restore and output data identical to the input composition analysis data. Details of the model 56 will be described later.

[0016] Next, a verification stage is performed. In the verification stage, compositional analysis data measured on multiple lots of steel produced before the preliminary study stage and compositional analysis data measured on multiple lots of steel produced in the data collection stage are used. Each compositional analysis data is input to a model 56, and output data is output from the model 56. An error loss between the compositional analysis data, which is the input data, and the output data is calculated.

[0017] In this embodiment, the error loss is defined by the mean absolute error loss (Loss MAE). When the composition of the input data is similar to the training data used to generate the model 56, the error loss is small. Conversely, when the composition of the input data is significantly different from the training data, the error loss is large.

[0018] Therefore, the error loss calculated for the steel produced before the data collection stage tends to be larger than the error loss calculated for the steel produced in the data collection stage. A reference value for the error loss is established at a level that can distinguish the variation range of the steel of the production lot after the data collection stage from the variation range of the steel of the production lot before the data collection stage. Details of the verification stage will be described later.

[0019] Finally, an overview of the utilization stage will be given. For each steel production lot, the error loss is calculated in the same way as in the verification stage. Based on the established reference values, the manufactured steel is evaluated. Details of the utilization stage will be described later.

[0020] The significance of establishing a standard value for error loss is explained below. Steel with a composition similar to the target composition established in the preliminary study stage is expected to have good properties. However, because the content of each component changes due to manufacturing variations, it is difficult for manufacturing engineers to judge the similarity of properties between the measured composition and the target composition when they look at the composition data.

[0021] By using the reference value of the error loss established in the verification phase, it is possible to easily determine whether the composition is similar to the target composition. That is, if the calculated error loss is equal to or less than the reference value, it can be determined that the composition of the produced steel is similar to the steel produced in the data collection phase and has the desired properties. If the calculated error loss exceeds the reference value, it can be determined that the composition of the produced steel, even if it meets the specified specifications, is different from the steel produced in the data collection phase and does not have particularly desirable properties.

[0022] FIG. 2 is an explanatory diagram that explains the stages of use of the steel evaluation method. Various quality inspections, including composition analysis, are carried out on newly manufactured steel. Based on the quality inspection results, a conformity judgment is made as to whether the steel meets the established standards. Steel that is judged to be non-conforming is not shipped as it is a non-conforming product, and is used as raw material for the manufacture of new steel. Conformity judgments for steel quality inspections have been carried out for some time, so a detailed explanation will be omitted.

[0023] For steels that are determined to be suitable (suitable products), the compositional analysis data is input to a model 56. The error loss between the output data of the model 56 and the compositional analysis data is calculated. If the error loss is equal to or less than a reference value, the steel is determined to be a superior product having desirable properties. The superior product is then delivered to, for example, a customer that requires particularly high reliability.

[0024] If the error loss exceeds the standard value, the steel is determined to be conforming to the specified standards, but not a quality product. In the following explanation, products that conform but are not a quality product will be referred to as semi-quality products. Semi-quality products are subjected to additional inspections, for example, taking into account the intended use at the delivery destination. Based on the results of the additional inspections, semi-quality steel is sorted into normal conforming products and products conforming for specific uses, and shipped to the appropriate customers.

[0025] As explained above, steel that has been determined to be in compliance through conventional quality inspections can be sorted into good and second-rate products based on the standard values, and the second-rate products can be sorted according to customer uses through additional inspections, allowing each type of steel to be shipped to the appropriate customer according to its characteristics.

[0026] [Preliminary consideration stage] Figure 3 is a table showing the composition of the samples used in the preliminary study stage. Eight types of samples were used. Each sample is identified by the sample symbol shown on the left side of Figure 3. For each sample, each component is shown in mass percent.

[0027] "Std" indicates steel with standard properties among mass-produced steels. "MoL" indicates steel with a lower molybdenum (Mo) content than "Std". "MoH" indicates steel with a higher molybdenum content than "Std". "CrL" indicates steel with a lower chromium (Cr) content than "Std". "CrH" indicates steel with a higher chromium content than "Std". "VH" indicates steel with a higher vanadium (V) content than "Std". "SiL" indicates steel with a lower silicon (Si) content than "Std". "MnH" indicates steel with a higher manganese (Mn) content than "Std".

[0028] Six rectangular specimens were prepared for each sample shown in Figure 3. Each specimen was cut out from a single piece of steel so that the direction in which the steel expands due to hot working is the length direction, the direction in which the steel is compressed is the thickness direction, and the direction perpendicular to both the length direction and the thickness direction is the width direction. In the graphs used in the following explanation, the length direction is indicated by the symbol L, the width direction by the symbol W, and the thickness direction by the symbol T.

[0029] The dimensional change rate after heat treatment was measured for each sample before and after heat treatment. The dimensional change rate after heat treatment is the dimensional change amount due to heat treatment divided by the dimension before heat treatment. The measurement of the dimensional change rate after heat treatment is an example of a characteristic evaluation method in the preliminary study stage described using Figure 1.

[0030] The heat treatment consisted of quenching and tempering. The quenching conditions were all the same. Quenching was performed by semi-cooling from 1020°C for 10 minutes. The semi-cooling number indicates the time required to cool to half the temperature of 1020°C (510°C). Tempering was performed under five different conditions, with tempering temperatures of 485°C, 500°C, 515°C, 530°C, and 545°C. Tempering was performed twice at each temperature.

[0031] Figure 4 is a graph showing the heat treatment dimensional change rates of steels with different molybdenum contents. In Figure 4, three graphs are arranged horizontally with a common vertical axis. (a) on the far left shows the heat treatment dimensional change rate of "MoL", (b) in the middle shows the heat treatment dimensional change rate of "Std", and (c) on the far right shows the heat treatment dimensional change rate of "MoH".

[0032] The horizontal axis of the graph indicates the tempering temperature, and the vertical axis of the graph indicates the dimensional change rate due to heat treatment. The dimensional change rate due to heat treatment on the vertical axis is a value calculated by measuring the sample dimensions before and after heat treatment, and then dividing the amount of dimensional change before and after heat treatment by the dimensions before heat treatment. Positive values ​​on the vertical axis indicate expansion due to heat treatment, and negative values ​​on the vertical axis indicate contraction due to heat treatment. "As(Q)" on the horizontal axis indicates samples that were only hardened.

[0033] The black circles on the graph indicate the heat treatment dimensional change rate in the length direction (L). The black diamonds indicate the heat treatment dimensional change rate in the width direction (W). The black triangles indicate the heat treatment dimensional change rate in the thickness direction (T). For each temperature, the average value ave of the three heat treatment dimensional change rates in the length direction, width direction, and thickness direction, and the sample standard deviation s were calculated, and the range of ave ± 3s is shown in gray.

[0034] Figure 5 is a graph showing the heat treatment dimensional change rates of steels with different chromium contents. In Figure 5, three graphs with a common vertical axis are arranged horizontally. (a) on the left side shows the heat treatment dimensional change rate of "CrL", (b) in the middle shows the heat treatment dimensional change rate of "Std", and (c) on the right side shows the heat treatment dimensional change rate of "CrH". The vertical and horizontal axes and plot symbols are the same as in Figure 4, so explanations will be omitted. (b) of Figure 4 and (b) of Figure 5 are the same graph.

[0035] Figure 6 is a graph showing the heat treatment dimensional change rates of steels with different vanadium contents side by side. In Figure 6, two graphs with a common vertical axis are arranged side by side. (a) on the left side shows the heat treatment dimensional change rate of "Std", and (b) on the right side shows the heat treatment dimensional change rate of "VH". The vertical and horizontal axes and plot symbols are the same as in Figure 4, so explanations will be omitted. (b) of Figure 4 and (a) of Figure 6 are the same graph.

[0036] Figure 7 is a graph showing the heat treatment dimensional change rates of steels with different silicon contents. In Figure 7, two graphs with a common vertical axis are arranged side by side. (a) on the left side shows the heat treatment dimensional change rate of "SiL", and (b) on the right side shows the heat treatment dimensional change rate of "Std". The vertical and horizontal axes and plot symbols are the same as in Figure 4, so explanations will be omitted. (b) of Figure 4 and (b) of Figure 7 are the same graph.

[0037] Figure 8 is a graph showing the heat treatment dimensional change rates of steels with different manganese contents side by side. In Figure 8, two graphs with a common vertical axis are arranged horizontally. (a) on the left side shows the heat treatment dimensional change rate of "Std", and (b) on the right side shows the heat treatment dimensional change rate of "MnH". The vertical and horizontal axes and plot symbols are the same as in Figure 4, so explanations will be omitted. (b) of Figure 4 and (a) of Figure 8 are the same graph.

[0038] When processing steel with large anisotropy in the rate of dimensional change due to heat treatment, differences in shape occur due to dimensional change caused by heat treatment after machining, so machining to correct the shape requires a large machining cost or increases the number of processing steps. Therefore, it is desirable for the steel material to have small anisotropy in the rate of dimensional change due to heat treatment, that is, a narrow range of ave ±3s shown in gray in the graphs of Figures 4 to 8.

[0039] Furthermore, it is difficult to consider dimensional changes caused by heat treatment because the temperature for heat treatment such as tempering must be appropriately selected depending on the equipment used and the mechanical properties of the machine parts to be manufactured. Therefore, it is desirable for the steel material to have little difference in the rate of dimensional changes caused by heat treatment due to the tempering temperature, that is, little change in the vertical axis direction in the graphs of Figures 4 to 8.

[0040] Considering the above criteria, it can be seen that the steel with a relatively high chromium content shown in Fig. 5(c) and the steel with a relatively high vanadium content shown in Fig. 6(b) have good properties with little variation in heat treatment dimensional change rate depending on the direction and temperature. Therefore, in the preliminary study stage, a target composition was established with relatively high chromium and vanadium contents.

[0041] [Data collection stage] Based on the target composition, 18 lots of steel with higher chromium and vanadium contents within the standard range were manufactured (after the target composition was established). Composition analysis was performed on each lot of steel, and a training DB51 was created that recorded the composition analysis data (Fig. 9, described below). The record layout of the training DB51 is similar to the table showing the composition of the samples explained using Fig. 3, and the content of each component is recorded for each lot. An illustration of the record layout of the training DB51 is omitted.

[0042] 9 is an explanatory diagram illustrating the configuration of the information processing device 10 used to generate the model 56. The information processing device 10 includes a control unit 11, a main storage device 12, an auxiliary storage device 13, a communication unit 14, an output unit 15, an input unit 16, a reading unit 19, and a bus.

[0043] The control unit 11 is an arithmetic and control device that executes the program of this embodiment. The control unit 11 uses one or more central processing units (CPUs), graphics processing units (GPUs), tensor processing units (TPUs), multi-core CPUs, etc. The control unit 11 is connected to each hardware unit constituting the information processing device 10 via a bus.

[0044] The main memory device 12 is a storage device such as an SRAM (Static Random Access Memory), a DRAM (Dynamic Random Access Memory), a flash memory, etc. The main memory device 12 temporarily stores information required during processing performed by the control unit 11 and programs being executed by the control unit 11.

[0045] The auxiliary storage device 13 is a storage device such as an SRAM, a flash memory, a hard disk, or a magnetic tape. The auxiliary storage device 13 stores a training DB 51, a model 56 being generated, a program to be executed by the control unit 11, and various data required for executing the program. The training DB 51 may be stored in an external large-capacity storage device connected to the information processing device 10. The communication unit 14 is an interface that performs communication between the information processing device 10 and a network.

[0046] The output unit 15 is, for example, a liquid crystal display device or an organic EL (Electro Luminescence) display device. The input unit 16 is, for example, an input device such as a keyboard, a mouse, a trackball, or a microphone. The output unit 15 and the input unit 16 may be integrally laminated to form a touch panel.

[0047] The portable recording medium 96 is, for example, a Universal Serial Bus (USB) memory, a Compact Disc Read only memory (CD-ROM), a magneto-optical disk medium, other optical disk medium, an SD memory card, etc. The portable recording medium 96 stores a program 97, which will be described later.

[0048] The reading unit 19 is an interface capable of reading a portable recording medium 96, such as a USB connector, a CD-ROM drive, or an SD memory reader. The semiconductor memory 98 stores a program 97 and is a memory that can be attached inside the information processing device 10.

[0049] The information processing device 10 is a general-purpose personal computer, a tablet, a mainframe computer, a virtual machine running on a mainframe computer, or a quantum computer. The information processing device 10 may be configured with hardware such as a plurality of personal computers or a mainframe computer that perform distributed processing. The information processing device 10 may be configured with a cloud computing system. The information processing device 10 may be configured with hardware such as a plurality of personal computers or a mainframe computer that operate in cooperation with each other.

[0050] The program 97 is recorded in a portable recording medium 96. The control unit 11 reads the program 97 via the reading unit 19 and stores it in the auxiliary storage device 13. The control unit 11 may also read out the program 97 stored in a semiconductor memory 98. Furthermore, the control unit 11 may download the program 97 from another server computer (not shown) connected via the communication unit 14 and a network (not shown) and store it in the auxiliary storage device 13.

[0051] The program 97 is installed as a control program for the information processing device 10, and is executed by being loaded into the main storage device 12. The program 97 of the present embodiment is an example of a program product.

[0052] The program 97 may be constructed and used on an open software platform, which allows the program 97 to be easily ported to various hardware.

[0053] FIG. 10 is an explanatory diagram for explaining the model 56. As described above, the model 56 is a machine learning model trained to output the same data as the input composition analysis data. Note that the composition analysis data is a one-dimensional matrix in which numerical values ​​indicating the content rate of each component are arranged, as described using FIG. 3. That is, the model 56 accepts an input of a one-dimensional matrix and outputs a one-dimensional matrix of the same size.

[0054] The model 56 has a structure of an autoencoder that combines an encoder and a decoder, for example. The model 56 may be generated using an algorithm such as Transformers or LSTM (Long Short-term Memory).

[0055] Fig. 11 is an explanatory diagram illustrating the flow of processing of a program for generating a model 56. Prior to execution of the program of Fig. 11, for example, an untrained autoencoder model is prepared. The parameters of the untrained model are adjusted by the program of Fig. 11, and the model 56 described using Fig. 10 is generated.

[0056] The control unit 11 acquires a training record from the training DB 51 (step S601). The control unit 11 inputs the composition analysis data included in the acquired training record to the model in training 56, and acquires an output one-dimensional matrix (step S602). In the following description, the matrix output from the model in training 56 is referred to as in-training output data.

[0057] The control unit 11 adjusts the parameters of the model 56 using a method such as backpropagation so that the difference between the composition analysis data input to the model 56 and the training output data output from the model 56 becomes small (step S603).

[0058] The control unit 11 determines whether or not to end the parameter adjustment (step S604). For example, when learning using all the training data recorded in the training DB 51 is completed, the control unit 11 determines to end the parameter adjustment. When the number of training data recorded in the training DB 51 is sufficiently large, the control unit 11 may determine to end the process when learning is repeated a predetermined number of times defined by the hyperparameters.

[0059] If it is determined that the process should not be terminated (NO in step S604), the control unit 11 returns to step S601. If it is determined that the process should be terminated (YES in step S604), the control unit 11 records the model 56 including the adjusted parameters in the auxiliary storage device 13 (step S605). Thereafter, the control unit 11 terminates the process. This completes the generation of the model 56.

[0060] [Verification stage] FIG. 12 is a graph showing the variation of the mean absolute error loss depending on the manufacturing time. The horizontal axis shows the manufacturing time of the steel. The vertical axis shows the mean absolute error loss calculated from the composition analysis data of the steel and the output data output from the model 56 after the composition analysis data is input into the model 56. The mean absolute error loss is defined by formula (1). Based on the target composition described in the [Data collection stage], 18 lots of steel with higher chromium and vanadium contents within the standard range were manufactured (18 black circles, after the target composition was established).

[0061]

number

[0062] FIG. 12 is a graph plotting the mean absolute error loss calculated by inputting the composition analysis data of each lot of steel into the completed model 56. The horizontal axis indicates the production date of the steel. The scale on the horizontal axis indicates the number of years since the start of production of the steel related to this embodiment. The scale lines indicate January 1 of each year. The vertical axis indicates the mean absolute error loss. Each black circle indicates data related to one lot of steel.

[0063] As shown in the graph of FIG. 12, the steel used in this embodiment has been manufactured since the end of the first year, and the production frequency increased from the first half of the sixth year. From the end of the first year to the middle of the eighth year, the steel has been manufactured based on the same specifications. In the second half of the eighth year, a preliminary study stage was carried out, and a target composition was established. The samples in the preliminary study stage are not plotted in the graph of FIG. 12.

[0064] From the beginning of the ninth year, the data collection phase began, and production was carried out under modified production conditions based on the target composition. The samples from the data collection phase are plotted in the graph of Figure 12. The composition analysis data of the steels produced according to the target specifications from the beginning of the ninth year to around the autumn of the tenth year were recorded in the training DB51 and used to generate the model 56.

[0065] When comparing lots of steel produced before the target composition was established with lots of steel produced after the target composition was established, it can be seen that the mean absolute error loss is significantly lower for the lots of steel produced after the target composition was established.

[0066] The dashed line indicates the standard value of the mean absolute error loss determined by experts such as manufacturing engineers based on the data plotted in Figure 12. In Figure 12, the standard value is set to a value slightly larger than the maximum value of the mean absolute error loss after the target composition is determined. In other words, the standard value is set to a value smaller than the maximum value of the mean absolute error loss before the target loss is determined.

[0067] [Use stage] 13 is an explanatory diagram illustrating the configuration of a steel evaluation system 40. The steel evaluation system 40 includes an information processing device 20 and an analysis device 30. The analysis device 30 is, for example, an ICP-OES (Inductively Coupled Plasma Optical Emission Spectrometer), and is used for analyzing the composition of steel.

[0068] The information processing device 20 includes a control unit 21, a main memory device 22, an auxiliary memory device 23, a communication unit 24, an output unit 25, an input unit 26, a reading unit 29, and a bus.

[0069] The control unit 21 is an arithmetic and control device that executes the program of this embodiment. The control unit 21 uses one or more CPUs, GPUs, multi-core CPUs, etc. The control unit 21 is connected to each hardware unit constituting the information processing device 20 via a bus.

[0070] The main memory device 22 is a storage device such as an SRAM, a DRAM, a flash memory, etc. The main memory device 22 temporarily stores information required during processing performed by the control unit 21 and programs being executed by the control unit 21.

[0071] The auxiliary storage device 23 is a storage device such as an SRAM, a flash memory, a hard disk, or a magnetic tape. The auxiliary storage device 23 stores the model 56, the programs to be executed by the control unit 21, and various data required for executing the programs. The communication unit 24 is an interface that communicates between the information processing device 20 and a network.

[0072] The output unit 25 is, for example, a liquid crystal display device or an organic EL display device. The input unit 26 is, for example, an input device such as a keyboard, a mouse, a trackball, or a microphone. The output unit 25 and the input unit 26 may be integrally laminated to form a touch panel.

[0073] The portable recording medium 91 is, for example, a USB memory, a CD-ROM, a magneto-optical disk medium, other optical disk medium, an SD memory card, etc. The portable recording medium 91 stores a program 92, which will be described later.

[0074] The reading unit 29 is an interface capable of reading a portable recording medium 91, such as a USB connector, a CD-ROM drive, or an SD memory reader. The semiconductor memory 93 stores a program 92, and is a memory that can be attached inside the information processing device 20.

[0075] The information processing device 20 is a general-purpose personal computer, a tablet, a mainframe computer, a virtual machine running on a mainframe computer, or a quantum computer. The information processing device 20 may be configured with hardware such as a plurality of personal computers or a mainframe computer that perform distributed processing. The information processing device 20 may be configured with a cloud computing system. The information processing device 20 may be configured with hardware such as a plurality of personal computers or a mainframe computer that operate in cooperation with each other.

[0076] The information processing device 20 is configured integrally with the analysis device 30, and may also function as a control device for the analysis device 30. The analysis device 30 may be configured to automatically transmit the composition analysis data to the information processing device 20. A user may cause the information processing device 20 to read the composition analysis data recorded in the analysis device 30, for example, via a network drive or any recording medium.

[0077] The program 92 is recorded in a portable recording medium 91. The control unit 21 reads the program 92 via the reading unit 29 and stores it in the auxiliary storage device 23. The control unit 21 may also read out the program 92 stored in a semiconductor memory 93. Furthermore, the control unit 21 may download the program 92 from another server computer (not shown) connected via the communication unit 24 and a network (not shown), and store it in the auxiliary storage device 23.

[0078] The program 92 is installed as a control program for the information processing device 20, and is executed by being loaded into the main storage device 22. The program 92 of the present embodiment is an example of a program product.

[0079] 14 is an explanatory diagram illustrating the flow of the program processing in the utilization stage. The control unit 21 acquires composition analysis data from the analysis device 30 or a network drive (step S501). The control unit 21 determines whether the content of each component is within the range defined by the standard (step S502).

[0080] When it is determined that there is a component that is not within the range defined by the standard (NO in step S502), the control unit 21 notifies the user that the steel related to the composition analysis data acquired in step S501 is a non-conforming product (step S511). The notification is sent to, for example, an automated machine, which marks the steel as unshippable. The notification may be sent to a manufacturing technology engineer.

[0081] When it is determined that all components are within the ranges defined by the standards (YES in step S502), the control unit 21 inputs the composition analysis data acquired in step S501 to the model 56, and acquires output data output from the model 56 (step S503). The control unit 21 calculates the error loss between the composition analysis data and the output data based on, for example, equation (1) (step S504).

[0082] The control unit 21 judges whether the calculated error loss is equal to or less than a reference value (step S505). If it is judged to be equal to or less than the reference value (YES in step S505), the control unit 21 notifies that the steel related to the composition analysis data acquired in step S501 is a superior product (step S512). The notification is sent to, for example, an automatic machine, which marks the target steel as a superior product. The notification may be sent to a manufacturing technology engineer.

[0083] If it is determined that the value is greater than the reference value (NO in step S505), the control unit 21 notifies the user that the steel related to the composition analysis data acquired in step S501 is neither a good product nor a non-conforming product, but a second-rate product (step S513). The notification is sent, for example, to a manufacturing engineer. The manufacturing engineer performs various additional inspections described with reference to FIG. 2.

[0084] After step S511, step S512, or step S513 ends, the control unit 21 ends the process.

[0085] According to the present embodiment, a method for evaluating steel that can evaluate in more detail steel that is judged to be compliant by existing inspection methods can be provided. Since it is easy to distinguish between high-quality steel that has particularly good properties and other second-quality steel among compliant steel that meets the standards, it is possible to preferentially deliver high-quality steel to customers who require particularly high reliability, for example.

[0086] According to this embodiment, by setting a target composition, it is possible to increase the frequency of producing high-quality products, thereby raising the standard of steel quality.

[0087] According to this embodiment, by utilizing compositional analysis data of steel produced before the target composition is determined in determining the reference value, it is not necessary to manufacture and test samples for comparison after the data collection stage is completed, and the reference value can be determined quickly.

[0088] According to this embodiment, by using the reference value, deviations in composition during the manufacturing process can be quickly detected, and steel of stable quality can be manufactured.

[0089] For the error loss, a loss mean squared error (LOSS MSE) may be used. The loss mean squared error loss is defined by equation (2).

[0090]

number

[0091] Even when the error loss is defined as the mean squared error loss, the error loss will be small if the composition of the input data is similar to the training data used to generate model 56. Conversely, the error loss will be large if the composition of the input data is significantly different from the training data.

[0092] Other loss functions that may be used for generating and evaluating machine learning models include the above-mentioned square root of mean squared error loss, loss mean squared logarithmic error loss (LOSS MSLE), square root of mean squared logarithmic error loss, Huber loss, Poisson loss, hinge loss, or Kullback-Leibler Divergence (KLD), among others.

[0093] The loss function used when adjusting the parameters of the model 56 by machine learning using the training DB 51 (step S603 in FIG. 11) and the error loss used when formulating the reference value in the verification stage may be the same function or different functions. The same function is used for the error loss used when formulating the reference value and the error loss calculated in the utilization stage (step S504 in FIG. 14).

[0094] A computer program can be deployed to be executed on a single computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

[0095] The technical features (constitutive elements) described in each embodiment can be combined with each other, and by combining them, new technical features can be formed. The embodiments disclosed herein are illustrative in all respects and should not be considered as limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the scope and meaning equivalent to the claims.

[0096] Independent claims and dependent claims described in the claims may be combined with each other in any combination, regardless of the reference format. Furthermore, the claims may be written in a format in which a claim references two or more other claims (multiple claim format), but this is not limited to this format. The claims may also be written in a format in which a multiple claim references at least one other claim (multiple multiple claim format). [Explanation of symbols]

[0097] 10. Information processing device 11 Control section 12 Main storage 13 Auxiliary storage device 14 Communications Department 15 Output section 16 Input section 19 Reading section 20 Information processing device 21 Control section 22 Main storage 23 Auxiliary storage device 24 Communications Department 25 Output section 26 Input section 29 Reading unit 30 Analyzer 40 Steel Evaluation System 51 Training DB 56 Models 91 Portable recording media 92 Programs 93 Semiconductor Memory 96 Portable recording media 97 Program 98 Semiconductor Memory

Claims

1. Analyzing the composition of steel, If the composition data obtained by the analysis meets a predetermined standard, the composition data is input to a machine-learned model that outputs the same data as the input data, and the error loss between the output data output from the model and the composition data is calculated; Determine whether the error loss exceeds a predetermined reference value. How steel is evaluated.

2. If it is determined that the error loss exceeds a predetermined reference value, additional testing is performed on the steel. A method for evaluating a steel according to claim 1.

3. The model is an autoencoder model that includes an encoder and a decoder. A method for evaluating a steel according to claim 1.

4. The model is machine-trained using composition data of steel manufactured after changing the manufacturing process as training data, The reference value is set to a value that is greater than a maximum value of an error loss between composition data included in the training data and output data output from the model after machine learning is completed, and is smaller than a maximum value of an error loss between composition data and output data output from the model after machine learning is completed, and is set to a value that is greater than a maximum value of an error loss between composition data and output data output from the model after machine learning is completed, and is smaller than a maximum value of an error loss between composition data and output data output from the model after machine learning is completed. A method for evaluating a steel according to any one of claims 1 to 3.

5. Obtaining steel composition data, If the composition data satisfies a predetermined standard, the composition data is input to a machine-learned model that outputs the same data as the input data, and an error loss between the output data output from the model and the composition data is calculated; Determine whether the error loss exceeds a predetermined reference value. A program that causes a computer to carry out processing.

6. Obtain training data that contains many sets of composition data showing the content of each component of steel, Based on the acquired training data, a model is generated through machine learning that outputs the same data as the input composition data when the composition data is input. How to generate the model.

Images