Metallic material search method, metallic material search device, metallic material search system and computer program

Abstract

To acquire chemical composition of a metallic material satisfying conditions of material properties and raw material cost.SOLUTION: A metallic material search method includes: acquiring composition pattern information including a plurality of composition patterns related to a chemical composition of a metallic material to be determined; estimating information showing material properties of the metallic material for each composition pattern by using trained model information obtained by performing training processing in advance using training data including condition information including information on the chemical composition of the metallic material and information showing the material properties of the metallic material corresponding to a condition shown by the condition information; recording, as basic condition information, the composition pattern and the material properties in association with each other; calculating raw material cost for each composition pattern included in the basic condition information; recording, as property cost information, the chemical composition, the material properties and the raw material cost in association with one another; and acquires suitable condition information being information on the chemical composition of the metallic material satisfying a condition of desired raw material cost about the metallic material having a prescribed material property on the basis of the property cost information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a method for searching for metal materials, a metal material search device, a metal material search system, and a computer program.

Background Art

[0002] Conventionally, research has been underway to improve the material properties of metal materials. For example, as a document regarding the influence of alloying elements on the material properties of metal materials, there is Patent Document 1 shown below. Specifically, for example, in stainless steel, when alloying elements are contained, mechanical properties, pitting corrosion resistance, crevice corrosion resistance, sulfuric acid corrosion resistance, porosity resistance, solidification crack susceptibility, etc. change.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, simply improving the material properties of metal materials may cause other problems. For example, the alloying elements contained in stainless steel are made from metals refined from various minerals. The price of minerals is at risk of rising due to speculative or political influences. The burden of rising mineral prices will be borne by material manufacturers, distributors, and consumers. Therefore, it is required to produce a metal material that satisfies the conditions regarding raw material prices while ensuring the necessary material properties.

[0005] The present invention has been made in view of the above circumstances, and provides a technology capable of obtaining the chemical composition of a metal material that satisfies the conditions regarding raw material prices while ensuring the necessary material properties.

Means for Solving the Problems

[0006] One aspect of the present invention includes an acquisition step of acquiring composition pattern information including a plurality of composition patterns related to the chemical composition of a metal material to be determined, condition information including information related to the chemical composition of the metal material, and information indicating the material properties of the metal material according to the conditions indicated by the condition information. Using the learned model information obtained by performing learning processing in advance using the teacher data, information indicating the material properties of the metal material is estimated for each composition pattern, and the composition pattern and the material properties are associated and recorded as basic condition information in a basic condition information recording step. For each composition pattern included in the basic condition information, a raw material price is calculated, and the chemical composition, the material properties, and the raw material price are associated and recorded as characteristic price information in a characteristic price information recording step. Based on the characteristic price information, a suitable condition information acquisition step of acquiring, for a metal material having predetermined material properties, information related to the chemical composition of the metal material that satisfies the condition of a desired raw material price, is a metal material search method.

[0007] One aspect of the present invention is the above metal material search method, wherein in the characteristic price information recording step, among the composition patterns included in the basic condition information, composition patterns that satisfy a search condition including predetermined material properties are extracted, the raw material price is calculated for each of the extracted composition patterns, and the extracted composition patterns and the material properties are associated and recorded as basic condition information.

[0008] One aspect of the present invention is the above metal material search method, wherein in the characteristic price information recording step, for all the composition patterns included in the basic condition information, the raw material price is calculated for each composition pattern, and the composition pattern and the material properties are associated and recorded as basic condition information.

[0009] One aspect of the present invention is the above metal material search method, wherein in the basic condition information recording step, a logarithm is taken of the value included in the condition information, and the obtained value is used to estimate information indicating the material properties of the metal material.

[0010] One aspect of the present invention is to obtain composition pattern information including a plurality of composition patterns regarding the chemical composition of a metal material to be determined, and to perform pre-learning processing using teacher data including condition information including information regarding the chemical composition of the metal material and information indicating the material characteristics of the metal material according to the conditions indicated by the condition information. Using the obtained learned model information, information indicating the material characteristics of the metal material is estimated for each of the composition patterns, and the composition pattern and the material characteristics are associated and recorded as basic condition information. The raw material price is calculated for each of the composition patterns included in the basic condition information, and the chemical composition, the material characteristics, and the raw material price are associated and recorded as characteristic price information. Based on the characteristic price information, a control unit that obtains suitable condition information, which is information regarding the chemical composition of a metal material that satisfies the condition of a desired raw material price for a metal material having predetermined material characteristics, is provided. A metal material search device is provided.

[0011] One aspect of the present invention is a metal material search system including a metal material search device, a terminal device, and a storage device. The storage device stores composition pattern information including a plurality of composition patterns regarding the chemical composition of a metal material to be determined. The metal material search device uses teacher data including condition information regarding the chemical composition of a metal material and information indicating the material characteristics of the metal material according to the conditions indicated by the condition information, and performs a learning process in advance to obtain learned model information. Using the learned model information, information indicating the material characteristics of the metal material is estimated for each composition pattern, and a control unit is provided to record the composition pattern and the material characteristics in association with each other as basic condition information. The terminal device includes a communication unit that communicates with other devices, an input unit that receives user operations, an output unit that outputs information to the user, and a control unit that acquires search condition information including predetermined material characteristics according to an operation on the input unit and transmits the search condition information to the metal material search device. The control unit of the metal material search device calculates the raw material price for each composition pattern included in the basic condition information, records the chemical composition, the material characteristics, and the raw material price in association with each other as characteristic price information, and based on the characteristic price information, obtains suitable condition information, which is information regarding the chemical composition of a metal material that satisfies the condition of a desired raw material price, for the metal material having the predetermined material characteristics included in the search condition information, and transmits the suitable condition information to the terminal device. The control unit of the terminal device outputs the suitable condition information from the output unit when receiving the suitable condition information from the metal material search device. This is the metal material search system.

[0012] One aspect of the present invention is the above metal material search system, wherein the control unit extracts a composition pattern that satisfies the search conditions including predetermined material characteristics from among the composition patterns included in the basic condition information, calculates the raw material price for each of the extracted composition patterns, and records the extracted composition pattern and the material characteristics in association with each other as basic condition information.

[0013] One aspect of the present invention is the above-described metal material search system, wherein the control unit calculates the raw material price for each composition pattern for all the composition patterns included in the basic condition information, and associates the composition pattern with the material characteristics and records them as basic condition information.

[0014] One aspect of the present invention is to obtain composition pattern information including a plurality of composition patterns regarding the chemical composition of a metal material to be determined, and to perform learning processing in advance using teacher data including condition information regarding the chemical composition of the metal material and information indicating the material characteristics of the metal material according to the conditions indicated by the condition information. Using the obtained learned model information, information indicating the material characteristics of the metal material is estimated for each composition pattern, the composition pattern is associated with the material characteristics and recorded as basic condition information, and the raw material price is calculated for each composition pattern included in the basic condition information. The chemical composition, the material characteristics, and the raw material price are associated and recorded as characteristic price information, and based on the characteristic price information, for a metal material having predetermined material characteristics, suitable condition information which is information regarding the chemical composition of the metal material satisfying the condition of a desired raw material price is obtained. A computer program for causing a computer to function as a metal material search device including a control unit.

Advantages of the Invention

[0015] According to the present invention, it becomes possible to obtain the chemical composition of a metal material that satisfies the conditions regarding the raw material price while ensuring the necessary material characteristics.

Brief Description of the Drawings

[0016]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

Figure 23

Embodiments for Carrying Out the Invention

[0017] [Overview] Hereinafter, specific configuration examples of the present invention will be described with reference to the drawings. FIG. 1 is a schematic block diagram showing the system configuration of the metal material exploration system 100 of the present invention. First, an overview of the metal material exploration system 100 will be described. The metal material exploration system 100 is used when estimating information (hereinafter referred to as "suitable condition information") indicating conditions necessary to realize a metal material having predetermined material characteristics while suppressing raw material costs. Hereinafter, a person who performs such an operation for estimation is called a user. The user inputs information (hereinafter referred to as "characteristic information") indicating the material characteristics of the metal material to be estimated into the terminal device 10. Specific examples of such characteristic information include pitting corrosion resistance. A specific example of information indicating pitting corrosion resistance is the pitting potential (Vpit). The unit of the value of the pitting potential may be, for example, V (volt) (reference electrode of silver-silver chloride (SSE) standard). Note that the characteristic information does not necessarily have to be limited to pitting corrosion resistance. Other specific examples of the characteristic information include mechanical properties (for example, yield strength, tensile strength, elongation), crevice corrosion resistance, sulfuric acid corrosion resistance, pitting resistance, and solidification cracking susceptibility.

[0018] The terminal device 10 transmits the input characteristic information to the metal material search device 30. The metal material search device 30 estimates the suitable condition information of the metal material according to the conditions indicated by the characteristic information. In the present embodiment, as a specific example of the specified characteristic, pitting corrosion resistance is used. The metal material search device 30 transmits the estimated suitable condition information to the terminal device 10. When the terminal device 10 receives the suitable condition information, it outputs the received suitable condition information. In this way, the user can easily obtain the condition information (for example, chemical composition) required to realize a metal material having the material characteristics to be estimated at a lower raw material price without conducting experiments using metal materials having various actual chemical compositions.

[0019] [Details of the System] Next, the details of the metal material search system 100 will be described. The metal material search system 100 includes a terminal device 10, a learning device 20, and a metal material search device 30. The terminal device 10 and the metal material search device 30 are communicably connected via a network 70. The learning device 20 and the metal material search device 30 may be communicably connected via the network 70. The network 70 may be a network using wireless communication or a network using wired communication. The network 70 may be configured using, for example, the Internet or a local area network (LAN). The network 70 may be configured by combining a plurality of networks.

[0020] FIG. 2 is a schematic block diagram showing a specific example of the functional configuration of the terminal device 10. The terminal device 10 is configured using an information device such as a smartphone, a tablet, a personal computer, or a dedicated device. The terminal device 10 includes a communication unit 11, an operation unit 12, an output unit 13, a storage unit 14, and a control unit 15.

[0021] The communication unit 11 is a communication device. The communication unit 11 may be configured as, for example, a network interface. The communication unit 11 performs data communication with other devices via the network 70 according to the control of the control unit 15. The communication unit 11 may be a device that performs wireless communication or a device that performs wired communication.

[0022] The operation unit 12 is configured using existing input devices such as a keyboard, a pointing device (mouse, tablet, etc.), buttons, and a touch panel. The operation unit 12 is operated by the user when inputting an instruction of the user to the terminal device 10. The operation unit 12 may be an interface for connecting an input device to the terminal device 10. In this case, the operation unit 12 inputs an input signal generated according to the user's input in the input device to the terminal device 10. The operation unit 12 may be configured using a microphone and a voice recognition device. In this case, the operation unit 12 performs voice recognition on the words spoken by the user and inputs the character string information of the recognition result to the terminal device 10. In this case, the operation unit 12 may perform only voice input, and the voice recognition may be executed by the control unit 15. The operation unit 12 may be configured in any manner as long as it can input an instruction of the user to the terminal device 10.

[0023] The output unit 13 outputs information in a form recognizable by the user. The output unit 13 may be, for example, an image display device such as a liquid crystal display or an organic EL (Electro Luminescence) display. The output unit 13 may be an interface for connecting an image display device to the terminal device 10. In this case, the output unit 13 generates a video signal for displaying image data and outputs the video signal to the image display device connected to itself. The output unit 13 may be a device that outputs sound such as a speaker. The output unit 13 may be an interface for connecting a sound output device such as a speaker or headphones to the terminal device 10. In this case, the output unit 13 generates a sound signal for reproducing sound data and outputs the sound signal to the sound output device connected to itself.

[0024] The storage unit 14 is configured using a storage device such as a magnetic hard disk drive or a semiconductor memory device. The storage unit 14 stores data used by the control unit 15. The storage unit 14 stores data necessary when the control unit 15 performs processing.

[0025] The control unit 15 is configured using a processor such as a CPU (Central Processing Unit) and a memory (main storage device). The control unit 15 functions when the processor executes a program. Note that all or part of each function of the control unit 15 may be realized using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The above program may be recorded on a computer-readable recording medium. A computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, a semiconductor memory device (e.g., SSD: Solid State Drive), or a storage device such as a hard disk or a semiconductor memory device built into a computer system. The above program may be transmitted via a telecommunication line.

[0026] The control unit 15 may execute, for example, an application pre-installed in the self-mounted (terminal device 10). As a specific example of such an application, there is an application provided to the terminal device 10 as a dedicated application of the metal material search system 100. As another specific example of such an application, there is an application of a WEB browser. The control unit 15 operates according to the program of the running application.

[0027] The control unit 15 controls the terminal device 10 according to the user's operations and the information received from the metal material detector 30. For example, the control unit 15 transmits the information input by the user operating the operation unit 12 to the metal material detector 30 by using the communication unit 11. For example, when the information transmitted from the metal material detector 30 is received by the communication unit 11 via the network 70, the control unit 15 generates screen data based on the received information and causes the output unit 13 to display the screen data. Such screen data includes images and characters transmitted from the metal material detector 30. For example, when the information transmitted from the metal material detector 30 is received by the communication unit 11 via the network 70, the control unit 15 generates audio data based on the received information and causes the output unit 13 to output the audio data.

[0028] Hereinafter, a specific example of the operation of the control unit 15 will be described. In the following example, an image display device is used as a specific example of the output unit 13. However, as described above, the output unit 13 does not necessarily need to be configured using an image display device, and may be configured using an audio output device, or may be configured using both an image display device and an audio output device.

[0029] The control unit 15 generates, for example, screen data having characters and images instructing the user to input characteristic information. The control unit 15 causes the output unit 13 to display the generated screen data. The control unit 15 may instruct the input of information indicating, for example, pitting corrosion resistance (e.g., pitting potential) as the characteristic information. Also, for example, as the characteristic information, the input of information indicating mechanical properties, crevice corrosion resistance, sulfuric acid corrosion resistance, pitting resistance, solidification cracking susceptibility, etc. may be instructed.

[0030] The user inputs characteristic information into the terminal device 10 by operating the operation unit 12. The control unit 15 transmits the input characteristic information to the metal material search device 30 using the communication unit 11. The control unit 15 receives an estimation result (suitable condition information) corresponding to the characteristic information from the metal material search device 30. The control unit 15 generates screen data indicating information showing the estimation result. The control unit 15 causes the output unit 13 to display the generated screen data.

[0031] Figure 3 is a schematic block diagram showing a specific example of the functional configuration of the learning device 20. The learning device 20 is configured using an information processing device such as a personal computer or a server device, for example. The learning device 20 includes a communication unit 21, a storage unit 22, and a control unit 23.

[0032] The communication unit 21 is a communication device. The communication unit 21 may be configured as a network interface, for example. The communication unit 21 performs data communication with other devices via the network 70 according to the control of the control unit 23. The communication unit 21 may be a device that performs wireless communication or a device that performs wired communication.

[0033] The storage unit 22 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 22 stores data used by the control unit 23. The storage unit 22 may function as, for example, a teacher data storage unit 221, a preprocessed teacher data storage unit 222, and a learned model information storage unit 223.

[0034] The teacher data storage unit 221 stores teacher data used in the supervised learning process executed in the learning device 20. The teacher data stored in the teacher data storage unit 221 is data including condition information (explanatory variable) and characteristic information (objective variable) of the metal material corresponding to the condition information. Hereinafter, the condition information and the characteristic information will be described respectively.

[0035] The conditional information may be, for example, information regarding the chemical composition of a metallic material for estimating pitting corrosion resistance. As specific examples of information regarding the chemical composition of a metallic material, there is information regarding elements contained in the metallic material to be estimated (for example, when the metallic material is ferritic stainless steel, elements such as silicon (Si), manganese (Mn), nickel (Ni), chromium (Cr), molybdenum (Mo), copper (Cu), niobium (Nb), titanium (Ti), aluminum (Al), tin (Sn), etc. contained therein). Among these, information regarding only some of the elements may be used. For example, information regarding the contents of a plurality of elements that affect pitting corrosion resistance contained in the metallic material to be estimated may be used. For example, information regarding the content of each of chromium, nickel, molybdenum, copper, and tin may be used. The unit of the content referred to here is mass percent. Note that the metallic material referred to here is, for example, steel such as stainless steel, but the metallic material is not limited to steel and may be any metal. For example, it may be a nickel alloy or the like. Among such conditional information, the conditional information necessary for realizing a metallic material having predetermined material characteristics while suppressing raw material costs corresponds to the suitable conditional information.

[0036] The characteristic information is information indicating the material characteristics of the metallic material. As specific examples of the characteristic information, there is information indicating pitting corrosion resistance. As a specific example of such information indicating pitting corrosion resistance, there is the pitting potential. Further, as other specific examples of the characteristic information, there are mechanical characteristics. Examples of information indicating mechanical characteristics include, for example, 0.2% proof stress, tensile strength, elongation, etc. Further, as other specific examples of the characteristic information, there are intergranular corrosion resistance, sulfuric acid corrosion resistance, pitting resistance, solidification cracking susceptibility, etc. Examples of information indicating intergranular corrosion resistance include, for example, information regarding the corrosion groove repassivation potential and information regarding the critical temperature for the occurrence of groove corrosion. Examples of information indicating sulfuric acid corrosion resistance include, for example, information regarding the corrosion rate and the repassivation current density in a sulfuric acid solution. Examples of information indicating pitting resistance include, for example, information regarding the maximum pitting depth.

[0037] Teacher data having such condition information and characteristic information may be obtained, for example, by conducting an experiment to actually measure the characteristic information using a metal material according to the condition information. Specifically, it may be obtained by manufacturing a metal material according to the condition information as a test material and conducting an experiment to measure the characteristic information of the manufactured test material, or by cutting out a sample from an actual product material and conducting an experiment to measure the characteristic information instead of or in addition to the test material. Further, it is preferable that the teacher data is data created using the experimental results of a metal material having a chemical composition relatively close to the chemical composition of the metal material for which the characteristic information is to be estimated.

[0038] The preprocessed teacher data storage unit 222 stores preprocessed teacher data obtained by executing preprocessing on the teacher data by the preprocessing control unit 232.

[0039] The learned model information storage unit 223 stores learned model information obtained by executing learning processing by the learning control unit 233.

[0040] The control unit 23 is configured using a processor such as a CPU and a memory. The control unit 23 functions as the information control unit 231, the preprocessing control unit 232, and the learning control unit 233 when the processor executes a program. Note that all or part of each function of the control unit 23 may be realized using hardware such as an ASIC, a PLD, or an FPGA. The above program may be recorded on a computer-readable recording medium. A computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, a semiconductor storage device (e.g., an SSD), or a storage device such as a hard disk or a semiconductor storage device built into a computer system. The above program may be transmitted via a telecommunication line.

[0041] The information control unit 231 controls the input and output of information. For example, the information control unit 231 acquires teacher data from other devices (information processing apparatuses and storage media) and records it in the teacher data storage unit 221. For example, the information control unit 231 transmits the learned model information stored in the learned model information storage unit 223 to other devices (for example, the metal material search device 30).

[0042] The preprocessing control unit 232 generates preprocessed teacher data by performing predetermined preprocessing on the teacher data. The preprocessing control unit 232 may perform, for example, a process of taking the logarithm (logarithmic conversion process) on the numerical values included in the teacher data. More specifically, a process of taking the logarithm may be performed on the values included in the condition information (for example, information indicating the chemical composition of a metal material). Even more specifically, a process of taking the logarithm may be performed on the contents (mass percentages) of a plurality (for example, all) of the elements included in the condition information. Also, a process of taking the logarithm may be performed on the values included in the characteristic information (for example, information indicating pitting corrosion resistance or mechanical characteristics). Even more specifically, for example, when the characteristic information is pitting corrosion resistance, a process of taking the logarithm may be performed on the value of the pitting potential (V) (volts (silver-silver chloride reference electrode (SSE) standard)), which is information indicating pitting corrosion resistance. By performing such preprocessing, for example, even when the contents of each element are greatly different (for example, differ by one digit, several digits, or around ten digits), it becomes possible to perform more accurate estimation processing by bringing the numerical values representing the contents of each element closer together.

[0043] The preprocessing control unit 232 may perform scaling on the explanatory variables included in the teacher data. As a specific example of such scaling, standardization may be performed, or normalization may be performed. As a specific example of such standardization processing, a process of dividing the deviation from the average value of the data by the standard deviation may be performed.

[0044] When the preprocessing is completed, the preprocessing control unit 232 records the teacher data converted by the preprocessing as preprocessed teacher data in the preprocessed teacher data storage unit 222.

[0045] The learning control unit 233 executes supervised learning processing using the preprocessed teacher data stored in the preprocessed teacher data storage unit 222. As a specific example of such learning processing, for example, support vector regression (SVR) may be used, or other learning techniques such as neural networks and deep learning may be used. Support vector regression is a complex model and has low model interpretability. However, it has the advantage that both linear regression and non-linear regression are possible, and high estimation accuracy can be achieved with less teacher data than deep learning. The learning control unit 233 records the learned model information obtained by executing the learning processing in the learned model information storage unit 223. The learned model information obtained by such a learning control unit 233 may be transmitted to the metal material search device 30 and recorded in the learned model information storage unit 321 of the metal material search device 30. Such learned model information can obtain an estimated value of the characteristic information as an output by giving condition information as an input.

[0046] FIG. 4 is a diagram showing information regarding a specific example of teacher data used in the learning device 20. In FIG. 4, the condition information is information regarding the contents of a plurality of elements contained in the metal material to be estimated. In FIG. 4, the characteristic information is information regarding the pitting corrosion resistance of the metal material to be estimated. The information regarding the contents of the plurality of elements is the content (mass percentage) of silicon (Si), manganese (Mn), nickel (Ni), chromium (Cr), molybdenum (Mo), copper (Cu), niobium (Nb), titanium (Ti), aluminum (Al), and tin (Sn), respectively. The information regarding the pitting corrosion resistance is the pitting potential (Vpit), and the unit is V (reference electrode of silver-silver chloride (SSE)).

[0047] The teacher data was created by manufacturing a metal material according to the condition information shown in FIG. 4, specifically, a metal material containing the alloying elements shown in FIG. 4, and measuring the pitting potential of the manufactured metal material. The remainder of the metal material manufactured to obtain the teacher data shown in FIG. 4 is iron (Fe) and impurities. Impurities are components that are mixed in during the industrial manufacture of metal materials due to raw materials such as ores and scraps, and various factors in the manufacturing process. Note that the metal material used to obtain the teacher data may contain trace amounts of elements other than the alloying elements (silicon, manganese, nickel, chromium, molybdenum, copper, niobium, titanium, aluminum, tin) contained in the teacher data, as well as iron (Fe) and impurities. Specifically, a metal material containing trace amounts of alloying elements such as carbon (C) and nitrogen (N) may be used. The measurement conditions for the pitting potential were in accordance with JIS G0577:2014, for example, and a 3.5% NaCl aqueous solution was used as the test solution.

[0048] FIG. 4 shows the minimum value, average value, and maximum value of each value. Each value of the teacher data used in the learning device 20 may be distributed so as to satisfy the statistical values shown in FIG. 4, for example.

[0049] FIG. 5 is a diagram that more specifically shows an example of the teacher data used in the learning device 20 shown in FIG. 4. In FIGS. 4 and 5, information regarding ferritic stainless steel is shown as a specific example of the teacher data. In FIGS. 4 and 5, the information regarding pitting corrosion resistance is the value of the pitting potential (Vpit), and the measurement conditions are as described above. The steel material used was a steel material with a plate thickness of 800 μm.

[0050] FIG. 5(A) shows a specific example of teacher data, indicating the content (mass percentage) of silicon (Si), manganese (Mn), nickel (Ni), chromium (Cr), molybdenum (Mo), copper (Cu), niobium (Nb), titanium (Ti), aluminum (Al), and tin (Sn) respectively. Also, "Vpit" in FIG. 5(A) represents the value of the pitting potential (V) (with reference to a silver-silver chloride reference electrode (SSE)). FIG. 5(B) shows the values of the teacher data after preprocessing. In the preprocessing, for each numerical value included in the teacher data, a logarithmic transformation process (a process of calculating the common logarithm) is performed. In the learning device 20, learning processing may be performed using the teacher data shown in FIG. 5(B) obtained in this way. In this case, it is desirable that a similar preprocessing is also executed in the metal material search device 30.

[0051] FIG. 6 is a flowchart showing a specific example of the processing of the learning device 20. First, the information control unit 231 acquires teacher data (step S101). The teacher data may be input by a user, for example, or acquired through communication from another information device, or acquired from a recording medium connected to the learning device 20. The preprocessing control unit 232 executes a predetermined preprocessing on the teacher data (step S102). The learning control unit 233 executes learning processing using the preprocessed teacher data and records the learned model information in the learned model information storage unit 223 (step S103).

[0052] FIG. 7 is a schematic block diagram showing a specific example of the functional configuration of the metal material search device 30. The metal material search device 30 is configured using an information processing device such as a personal computer or a server device. The metal material search device 30 includes a communication unit 31, a storage unit 32, and a control unit 33.

[0053] The communication unit 31 is a communication device. The communication unit 31 may be configured as a network interface, for example. The communication unit 31 performs data communication with other devices via the network 70 under the control of the control unit 33. The communication unit 31 may be a device that performs wireless communication or a device that performs wired communication.

[0054] The storage unit 32 is configured by using a storage device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 32 stores data used by the control unit 33. The storage unit 32 may function as, for example, a learned model information storage unit 321, a design condition information storage unit 322, a composition pattern information storage unit 323, a basic condition information storage unit 324, a unit price information storage unit 325, and a characteristic price information storage unit 326.

[0055] The learned model information storage unit 321 stores information on a learned model generated in advance by a learning process. The learned model information storage unit 321 is an estimation model for estimating material characteristics to be estimated. For example, when pitting corrosion resistance is the estimation target, the learned model information storage unit 321 stores an estimation model (learned model) for estimating pitting corrosion resistance. The learning process for acquiring such a learned model may be executed by, for example, another device (for example, the learning device 20), or may be executed by the own device (the metal material search device 30).

[0056] The design condition information storage unit 322 stores design condition information. FIG. 8 is a diagram showing a specific example of the design condition information. The design condition information indicates the design conditions of the chemical composition of the metal material that is the search target for the suitable condition information. For example, the values of the minimum content, the maximum content, and the pitch of each alloy element may be defined as the design condition information. The pitch indicates the width of the value when defining candidate values for each content. The unit of the content mentioned here is mass percent. In the example of FIG. 8, for chromium, three values of a minimum value (minimum content: 17%), a maximum value (maximum content: 20%), and a pitch (0.5%) are defined. In this case, the content of chromium is defined as candidate values for each value from 17% to 20% at 0.5% intervals. Also, for nickel, the minimum value (minimum content) is not defined, and two values of a maximum value (maximum content: 0.3%) and a pitch (0.1%) are defined. When the minimum content is not defined, 0% may be used as the minimum content. In this case, the content of nickel is defined as candidate values for each value from 0% to 0.3% at 0.1% intervals.

[0057] The composition pattern information storage unit 323 stores composition pattern information. FIG. 9 is a diagram showing a specific example of the composition pattern information. The composition pattern information shows candidates for the composition pattern (condition information) for each type of metal material (for each steel type) that is the search target of the suitable condition information. Each composition pattern shows candidate values for the content of each alloy element indicated by the design condition information in FIG. 8. For example, the composition pattern information may have all combinations of the candidate values of each alloy element indicated by the design condition information.

[0058] The basic condition information storage unit 324 stores basic condition information. FIG. 10 is a diagram showing a specific example of the basic condition information. For each steel type indicated by the composition pattern (condition information), it has the value of the material property obtained based on the content of each alloy element. In the example of FIG. 10, as the value of the material property, the value of the pitting corrosion resistance (Vpit) is used, and the unit is V (standard of silver-silver chloride reference electrode (SSE)). The basic condition information in FIG. 10 is information obtained by adding the estimated value of the material property (for example, pitting corrosion resistance) for each steel type to the composition pattern information in FIG. 9.

[0059] The value of the material property included in the basic condition information may be obtained by an estimation process using a learned model. A part of the value of the material property included in the basic condition information may be actually obtained by an experiment by producing a metal material of such a component. In the example of FIG. 10, the value of the material property of the metal material is the characteristic information that can be estimated using the learned model stored in the learned model information storage unit 321. The estimation process using the learned model may be executed, for example, by the estimation unit 332 described later.

[0060] The unit price information storage unit 325 stores unit price information. FIG. 11 is a diagram showing a specific example of the unit price information. The unit price information indicates the unit price of each alloy element. The unit of the unit price may be any unit. It may be a different unit depending on the alloy element. In the example of FIG. 11, the price (yen) per ton is shown for all alloy elements. By using the unit price information, the raw material price for each steel type included in the basic condition information can be calculated. For example, the unit price and the content are multiplied for each alloy element, the values are summed up for all alloy elements, and further, the value obtained by multiplying the unit price of iron and the content is added to obtain the raw material price. The iron content is obtained by subtracting the total content of all alloy elements from 100. For example, the raw material price can be calculated using the following formula. Note that the raw material price may be defined as a price that does not include labor costs and manufacturing costs. In the following description, the raw material price is defined as a price that does not include labor costs and manufacturing costs as described above.

[0061] Raw material price (yen / ton) = Chromium unit price (yen / ton) × Chromium content (mass%) + Nickel unit price (yen / ton) × Nickel content (mass%) + ··· + Iron unit price (yen / ton) × Iron content (mass%) Iron content (mass%) = 100 - (Chromium content (mass%) + Nickel content (mass%) + ··· Tin content (mass%))

[0062] The characteristic price information storage unit 326 stores characteristic price information. FIG. 12 is a diagram showing a specific example of the characteristic price information. The characteristic price information includes information regarding the chemical composition (for example, information on the content of each alloy element), information regarding the material characteristics, and information regarding the raw material price. The characteristic price information may be generated, for example, in the following procedure. First, a composition pattern that satisfies the search conditions described later is extracted from the basic condition information shown in FIG. 10. The search conditions may be specified by the user, for example. Next, for each of the extracted composition patterns, the raw material price is calculated, and the calculated raw material price is further associated. In such a procedure, characteristic price information in which information regarding the chemical composition, material characteristics, and raw material price is associated for each composition pattern may be generated. In FIG. 12, an example is shown in which values regarding pitting corrosion resistance, which are information regarding the material characteristics, more specifically, the minimum and maximum values of the pitting potential (Vpit: 0.40 to 0.44 V), are specified as the search conditions.

[0063] FIG. 13 is a diagram showing an example of the relationship between the pitting potential (Vpit) obtained experimentally and the pitting potential (Vpit) estimated using the learned model information obtained by the learning device 20. The horizontal axis of FIG. 13 shows the pitting potential (V) (silver-silver chloride reference electrode (SSE) standard) obtained experimentally. The vertical axis of FIG. 13 shows the pitting potential (V) (silver-silver chloride reference electrode (SSE) standard) obtained by the metal material search device 30. In FIG. 13, the teacher data (146 data) shown in FIGS. 4 and 5 are shown as white circles. The black circles (hatched circles) shown in FIG. 13 are test data different from the teacher data.

[0064] The white circles and black circles shown in FIG. 13 are both distributed substantially linearly. Therefore, FIG. 13 shows that the learned model information obtained by the learning device 20 can be obtained with high accuracy and can output pitting corrosion resistance data indicating a highly reliable pitting potential (Vpit). That is, it can be seen that by using the learned model information obtained by the learning device 20, characteristic information can be accurately obtained from the condition information. Thus, it can be seen from the experimental results shown in FIG. 13 that there is a correlation between the condition information and the characteristic information.

[0065] FIG. 14 is a diagram showing an image of a graph indicating the correspondence between specific characteristic information of a metal material among the information included in the characteristic price information and the raw material price that does not include labor costs and manufacturing costs required to manufacture a predetermined unit amount (for example, 1 ton) of the metal material for which each characteristic information is obtained. In FIG. 14, as in FIG. 12, a value related to pitting corrosion resistance (more specifically, pitting potential (Vpit)) is used as the specific characteristic information of the metal material. In FIG. 14, the raw material price is shown on the horizontal axis and the characteristic information (pitting potential) is shown on the vertical axis. Each circle arranged in the graph is associated with the chemical composition (content of each alloy element) of the metal material corresponding to the raw material price and the specific characteristic information. Regarding the characteristic information on the vertical axis, for example, among the metal materials located at a predetermined interval (for example, an interval of 0.01), the circle corresponding to the metal material with the lowest price is shown as a white circle (preferred condition).

[0066] For example, when a metal material having a pitting potential of 0.40 to 0.44 V is desired, based on the characteristic price information shown in FIG. 12 and the graph shown in FIG. 14 where Vpit: 0.40 to 0.44 V is specified as the search condition described later, it becomes possible to easily know the chemical composition (preferred condition information) for realizing the price reduction for the metal material having the desired characteristic information. For example, in FIG. 14, by selecting the graph value located most to the left among the graph values (each circle) in the range of 0.40 to 0.44 V, it becomes possible to obtain the chemical composition for realizing the metal material having the desired characteristic information at the lowest cost.

[0067] In addition, for a metal material having desired characteristic information, when there is a desired price range, it becomes possible to easily obtain options for the chemical composition of the metal material that satisfy both the requirements of the characteristic information and the price range. FIG. 15 is a diagram for explaining such options. In FIG. 15, the same graph as in FIG. 14 is shown. In FIG. 15, when desiring a metal material having a pitting potential of 0.40 to 0.44 V and within a price range of 70,000 yen / ton to 90,000 yen / ton, by selecting the graph values located inside the region 81 indicating the above characteristic information and price range among the values (each circle) of the graph of 0.40 to 0.44 V, it becomes possible to obtain the chemical composition of the metal material that has the desired characteristic information and can be realized within the desired price range. By obtaining such multiple options in this way, it becomes possible to more flexibly realize the metal material with the desired characteristic information and price range. For example, when it is difficult to obtain a specific element, it becomes possible to realize the metal material with the desired characteristic information and price range while keeping the usage amount of such an element low.

[0068] The control unit 33 is configured using a processor such as a CPU and a memory. The control unit 33 functions as an information control unit 331, an estimation unit 332, a characteristic price information generation unit 333, and a suitable condition information acquisition unit 334 when the processor executes a program. Note that all or part of each function of the control unit 33 may be realized using hardware such as an ASIC, a PLD, or an FPGA. The above program may be recorded on a computer-readable recording medium. A computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, a semiconductor storage device (e.g., SSD), or a storage device such as a hard disk or a semiconductor storage device built into a computer system. The above program may also be transmitted via an electric communication line.

[0069] The information control unit 331 acquires information from other devices such as the terminal device 10. As a specific example of the information to be acquired, there is, for example, the characteristic information input to the terminal device 10. The information control unit 331 records the acquired information in a storage device such as a memory. The information control unit 331 transmits information to other devices such as the terminal device 10. As a specific example of the information to be transmitted, there is, for example, information (suitable condition information) regarding the chemical composition of one or more metal materials selected based on the information stored in the characteristic price information storage unit 326. More specifically, there is information regarding the chemical composition of metal materials that satisfy the search conditions (characteristic information) transmitted from the terminal device 10. This information (suitable condition information) may include information indicating the raw material price or may include characteristic information. For example, as described in the above explanation using FIG. 14, the information control unit 331 may acquire the chemical composition of the cheapest metal material that can be realized among the metal materials having the characteristic information specified in the terminal device 10 and transmit it to the terminal device 10. For example, the information control unit 331 may acquire the chemical compositions of a predetermined number of metal materials in order from those that can be realized at a low price among the metal materials having the characteristic information specified in the terminal device 10 and transmit them to the terminal device 10. For example, as described in the above explanation using FIG. 15, when the characteristic information and the price range are specified in the terminal device 10, the information control unit 331 may acquire the chemical composition of the metal materials that can be realized within the specified price range among the metal materials having the specified characteristic information and transmit it to the terminal device 10. Such information exchange between the information control unit 331 and other devices may be performed, for example, by communication by the communication unit 31.

[0070] Also, the information control unit 331 may acquire the latest information among the information stored in the storage unit 32 and update the information in the storage unit 32. For example, the information control unit 331 may acquire the latest unit price information and update the unit price information stored in the unit price information storage unit 325. By recalculating the raw material prices of each composition pattern using the latest unit price information and updating the characteristic price information, the influence of price increases can be considered. The information control unit 331 may acquire the design condition information according to the operations of other devices or users and record it in the design condition information storage unit 332.

[0071] The estimation unit 332 estimates information on material properties corresponding to the composition pattern (condition information: content of each alloying element) for each steel type included in the composition pattern information stored in the composition pattern information storage unit 323. This estimation process is performed using the learned model information stored in the learned model information storage unit 321. The estimation unit 332 executes an inference process using the learned model information and the composition pattern included in the composition pattern information, thereby estimating the characteristic information of the metal material corresponding to the condition information indicated by the composition pattern.

[0072] The characteristic price information generation unit 333 generates composition pattern information based on the design condition information recorded in the design condition information storage unit 322 and records it in the composition pattern information storage unit 323. The characteristic price information generation unit 333 instructs the estimation unit 332 to estimate the material properties of the metal generated by the composition pattern (condition information) for each composition pattern included in the composition pattern information. The characteristic price information generation unit 333 generates basic condition information using the composition pattern information and the estimation result, and records it in the basic condition information storage unit 324.

[0073] The characteristic price information generation unit 333 receives an input of search conditions from the user. The search conditions are information indicating the conditions of the steel type to be searched. The search conditions include, for example, information (characteristic information) indicating the material properties of the metal material to be searched. For example, in a person (e.g., a customer of a metal manufacturer) who offers a steel type indicated by the suitable condition information, characteristic information suitable for the usage environment (characteristic information corresponding to the specifications required by the customer) may be set as the search conditions. The suitable condition information provided by the metal material search device 30 selects, from among the metal materials of the steel type that satisfy this search condition, those that satisfy the conditions regarding the desired raw material price. The characteristic price information generation unit 333 extracts only the steel types that satisfy the search conditions from the basic condition information stored in the basic condition information storage unit 324. The characteristic price information generation unit 333 calculates the raw material price using the unit price information for each of the extracted steel types. The characteristic price information generation unit 333 generates characteristic price information by adding the value of the raw material price to the record for each of the extracted steel types, and records it in the characteristic price information storage unit 326.

[0074] Based on the characteristic price information, the suitable condition information acquisition unit 334 acquires suitable condition information, which is information regarding the chemical composition of a metal material that satisfies a desired (predetermined) raw material price condition (for example, the condition of being the cheapest) among the metal materials included in the characteristic price information.

[0075] FIG. 16 is a flowchart showing a specific example of the processing of the metal material search device 30. First, the characteristic price information generation unit 333 acquires design condition information from the design condition information storage unit 322 (step S201). The characteristic price information generation unit 333 generates composition pattern information based on the acquired design condition information (step S202). The characteristic price information generation unit 333 instructs the estimation unit 332 to perform an estimation process for the composition patterns (condition information) included in the composition pattern information. The estimation unit 332 performs a predetermined preprocessing on the instructed condition information (step S203). The preprocessing performed by the estimation unit 332 is the same process as the preprocessing performed on the teacher data when the learned model information is acquired. For example, the preprocessing performed by the estimation unit 332 is the same process as the preprocessing performed on the condition information included in the teacher data by the preprocessing control unit 232 of the learning device 20. The estimation unit 332 performs an estimation process using the preprocessed condition information and the learned model information (step S204). The estimation unit 332 acquires characteristic information as an estimation result by executing the estimation process. The characteristic price information generation unit 333 acquires the estimation result (characteristic information) from the estimation unit 332. The estimation unit 332 and the characteristic price information generation unit 333 repeatedly execute the process until the estimation process is completed for all the condition information to be estimated. The characteristic price information generation unit 333 associates the acquired characteristic information with the condition information used in the estimation process and records it in the basic condition information storage unit 324 as basic condition information (step S205).

[0076] FIG. 17 is a flowchart showing a specific example of the processing of the metal material exploration device 30. First, the information control unit 331 acquires information (exploration condition information) regarding the exploration conditions transmitted from the terminal device 10 (step S301). The information regarding the exploration conditions may be acquired via the network 70, for example, information input to the terminal device 10 by the user. The suitable condition information acquisition unit 334 selects a metal material (composition pattern) of a steel type that satisfies the exploration conditions from the basic condition information based on the acquired information regarding the exploration conditions (step S302). The exploration conditions include at least characteristic information. The suitable condition information acquisition unit 334 calculates the raw material price based on the unit price information recorded in the unit price information storage unit 325 for each selected metal material (each composition pattern). The suitable condition information acquisition unit 334 generates and records characteristic price information by associating the raw material price calculated for each selected metal material (step S303). The suitable condition information acquisition unit 334 acquires the chemical composition of the steel type that satisfies the conditions regarding price from the characteristic price information (step S304). The conditions regarding price may be conditions defined by the user of the terminal device 10 (for example, a price range), or may be a condition of the lowest price. The information control unit 331 outputs the acquired information. For example, the information control unit 331 transmits the acquired information on the chemical composition (suitable condition information) to the terminal device 10 (step S305).

[0077] FIG. 18 is a diagram showing an outline of a hardware configuration example of an information processing apparatus 90 to which the present embodiment is applied. The information processing apparatus 90 includes a processor 91, a main storage device 92, a communication interface 93, an auxiliary storage device 94, an input / output interface 95, and an internal bus 96. The processor 91, the main storage device 92, the communication interface 93, the auxiliary storage device 94, and the input / output interface 95 are communicably connected to each other via the internal bus 96. The information processing apparatus 90 may be applied to, for example, the learning apparatus 20 and the metal material search apparatus 30. In this case, for example, the communication unit 21 and the communication unit 31 may be configured using the communication interface 93. For example, the storage unit 22 and the storage unit 32 may be configured using the auxiliary storage device 94. Also, the control unit 23 and the control unit 33 may be configured using the processor 91 and the main storage device 92.

[0078] In the metal material search system 100 of the present embodiment, it is possible to estimate the chemical composition of a metal material according to the price for a metal material having predetermined characteristic information. Therefore, it is possible to reduce the burden caused in determining the chemical composition of the metal material. More specifically, it is possible to reduce some or all of the burden that has hitherto been required for actual experiments. Also, at a desired timing (for example, each time a predetermined frequency or the trading price of each alloy element is changed), by recalculating the raw material price of each composition pattern using the latest unit price information and updating the characteristic price information, while ensuring the necessary material characteristics, and further considering the influence of price hikes, it becomes possible to select the cheapest steel type at that time and determine the chemical composition of the metal material.

[0079] (Modification example) In the description of FIG. 12, characteristic price information was generated only for composition patterns that satisfied search conditions specified by the user or the like. Therefore, for example, only composition patterns that satisfied the search conditions were extracted from the basic condition information shown in FIG. 10, and raw material prices were calculated only for the extracted composition patterns and treated as characteristic price information. On the other hand, characteristic price information may be generated for all composition patterns. For example, raw material prices may be calculated for all composition patterns of the basic condition information shown in FIG. 10, and characteristic price information may be generated. FIG. 19 is a diagram showing a modification example of the characteristic price information configured in this way. In the example of FIG. 19, the characteristic price information is configured as a table associating raw material prices for all steel grades.

[0080] In the above description, an example in which information indicating the material characteristics of the metal material to be searched for (characteristic information) is included as a search condition has been described. The search condition may further include information regarding the content of alloying elements in addition to the characteristic information. For example, in the specific example of the basic condition information shown in FIG. 10, information regarding the content (mass percentage) of some of the 10 alloying elements from Cr to Sn (for example, the minimum content and the maximum content) may be included in the search condition.

[0081] Here, the basic condition information shown in FIG. 10 is obtained by adding an estimated value of the material characteristics to the composition pattern information generated based on the design condition information shown in FIG. 8, and is a specific example mainly assuming ferritic stainless steel. However, as another specific example, for example, it is conceivable to use basic condition information assuming stainless steel including not only ferritic stainless steel but also austenitic stainless steel and duplex stainless steel. In such a case, for example, by a user who desires austenitic stainless steel, the minimum content and the maximum content of nickel and chromium respectively may be specified as search conditions within the range indicating austenitic stainless steel.

[0082] FIG. 20 is a diagram showing an image of a graph indicating the correspondence between specific characteristic information of a metal material and the raw material price among the information included in the characteristic price information shown in FIG. 19. The values represented by the vertical axis and the horizontal axis of the graph shown in FIG. 20 and the values indicated by the white circles and black circles of the graph are the same as those in FIG. 14. Based on the characteristic price information shown in FIG. 19 and the graph shown in FIG. 20, it becomes possible to easily know the chemical composition (preferred condition information) for realizing a metal material having desired characteristic information while suppressing the price. For example, when desiring a metal material having a pitting potential of 0.30 to 0.40 in FIG. 20, as one option, by selecting the value of the graph located most to the left among the values of the graph of 0.30 to 0.40 (each circle), it becomes possible to obtain the chemical composition for realizing the metal material having the desired characteristic information at the lowest cost.

[0083] Also, for a metal material having desired characteristic information, when there is a desired price range, it becomes possible to easily obtain options for the chemical composition of the metal material that satisfies both the requirements of the characteristic information and the price range. FIG. 21 is a diagram for explaining such options. In FIG. 21, the same graph as in FIG. 20 is shown. In FIG. 21, when desiring a metal material having a pitting potential of 0.30 to 0.40 and in the price range of 66,000 yen / ton to 74,000 yen / ton, by selecting the value of the graph located inside the region 81 indicating the above characteristic information and price range among the values of the graph of 0.30 to 0.40 (each circle), it becomes possible to obtain the chemical composition of the metal material that has the desired characteristic information and can be realized within the desired price range. By obtaining a plurality of such options in this way, it becomes possible to more flexibly realize a metal material having the desired characteristic information and price range. For example, when it is difficult to obtain a specific element, it becomes possible to realize a metal material having the desired characteristic information and price range while suppressing the usage amount of such an element to a small amount.

[0084] In this embodiment, the terminal device 10 and the metal material exploration device 30 are configured as different devices, but they may also be configured as an integrated device. FIG. 22 is a diagram showing a modified example of the metal material exploration device 30 configured in this way. The metal material exploration device 30 shown in FIG. 22 includes an operation unit 34 and an output unit 35. The operation unit 34 and the output unit 35 of the metal material exploration device 30 shown in FIG. 22 function in the same manner as the operation unit 12 and the output unit 13 of the terminal device 10, respectively. The control unit 33 operates in response to an operation on the operation unit 34 and outputs information using the output unit 35.

[0085] In this embodiment, the learning device 20 and the metal material exploration device 30 are configured as different devices, but they may also be configured as an integrated device. FIG. 23 is a diagram showing a modified example of the metal material exploration device 30 configured in this way. The storage unit 32 of the metal material exploration device 30 shown in FIG. 23 also functions as a teacher data storage unit 327 and a preprocessed teacher data storage unit 328. The control unit 33 of the metal material exploration device 30 shown in FIG. 23 also functions as a preprocessing control unit 335 and a learning control unit 336. The teacher data storage unit 327 and the preprocessed teacher data storage unit 328 function in the same manner as the teacher data storage unit 221 and the preprocessed teacher data storage unit 222 of the learning device 20, respectively. The preprocessing control unit 336 and the learning control unit 337 function in the same manner as the preprocessing control unit 232 and the learning control unit 233 of the learning device 20, respectively.

[0086] The learning device 20 may be implemented using a plurality of information processing devices. For example, the learning device 20 may be implemented using a device such as a cloud. For example, in the learning device 20, the storage unit 22 and the control unit 23 may be implemented in different information processing devices, respectively. For example, the storage unit 22 of the learning device 20 may be implemented in a distributed manner in a plurality of information processing devices. The metal material exploration device 30 may be implemented using a plurality of information processing devices. For example, the metal material exploration device 30 may be implemented using a device such as a cloud. For example, in the metal material exploration device 30, the storage unit 32 and the control unit 33 may be implemented in different information processing devices, respectively. For example, the storage unit 32 of the metal material exploration device 30 may be implemented in a distributed manner in a plurality of information processing devices.

[0087] As described above, the embodiments of the present invention have been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and designs and the like within the scope not departing from the gist of the present invention are also included.

Explanation of Reference Numerals

[0088] 100…Metal material search system, 10…Terminal device, 11…Communication unit, 12…Operation unit, 13…Output unit, 14…Storage unit, 15…Control unit, 20…Learning device, 21…Communication unit, 22…Storage unit, 221…Teacher data storage unit, 222…Pre-processed teacher data storage unit, 223…Learned model information storage unit, 23…Control unit, 231…Information control unit, 232…Pre-processing control unit, 233…Learning control unit, 30…Metal material search device, 31…Communication unit, 32…Storage unit, 321…Learned model information storage unit, 322…Design condition information storage unit, 323…Composition pattern information storage unit, 324…Basic condition information storage unit, 325…Unit price information storage unit, 326…Characteristic price information storage unit, 33…Control unit, 331…Information control unit, 332…Estimation unit, 333…Characteristic price information generation unit, 334…Suitable condition information acquisition unit

Claims

1. An acquisition step of acquiring composition pattern information including a plurality of composition patterns regarding the chemical composition of a metal material to be determined; Using learned model information obtained by performing learning processing in advance using teacher data including condition information regarding the chemical composition of the metal material and information indicating the material properties of the metal material according to the conditions indicated by the condition information, estimating information indicating the material properties of the metal material for each composition pattern, and recording the composition pattern and the material properties in association with each other as basic condition information in a basic condition information recording step; Calculating a raw material price for each composition pattern included in the basic condition information, and recording the chemical composition, the material properties, and the raw material price in association with each other as characteristic price information in a characteristic price information recording step; A suitable condition information acquisition step of acquiring, based on the characteristic price information, suitable condition information which is information regarding the chemical composition of a metal material that satisfies the condition of a desired raw material price for a metal material having predetermined material properties; A metal material search method having the above.

2. In the characteristic price information recording step, among the composition patterns included in the basic condition information, extracting a composition pattern that satisfies a search condition including predetermined material properties, calculating the raw material price for each extracted composition pattern, and recording the extracted composition pattern and the material properties in association with each other as basic condition information. The metal material search method according to claim 1.

3. In the characteristic price information recording step, for all the composition patterns included in the basic condition information, calculating the raw material price for each composition pattern, and recording the composition pattern and the material properties in association with each other as basic condition information. The metal material search method according to claim 1.

4. In the basic condition information recording step, taking the logarithm of the value included in the condition information and using the obtained value to estimate information indicating the material properties of the metal material. The metal material search method according to claim 1.

5. Obtain composition pattern information including a plurality of composition patterns regarding the chemical composition of the metal material to be determined, and use teacher data including condition information regarding the chemical composition of the metal material and information indicating the material properties of the metal material according to the conditions indicated by the condition information to perform learning processing in advance. Using the obtained learned model information, estimate information indicating the material properties of the metal material for each composition pattern, associate the composition pattern with the material properties, and record them as basic condition information. Calculate the raw material price for each composition pattern included in the basic condition information, associate the chemical composition, the material properties, and the raw material price, and record them as characteristic price information. Based on the characteristic price information, obtain suitable condition information, which is information regarding the chemical composition of the metal material that satisfies the condition of the desired raw material price for the metal material having predetermined material properties, in a control unit. A metal material search device comprising the above.

6. A metal material search system comprising a metal material search device, a terminal device, and a storage device, wherein the storage device stores composition pattern information including a plurality of composition patterns regarding the chemical composition of the metal material to be determined, the metal material search device includes a control unit that estimates information indicating the material properties of the metal material for each composition pattern using learned model information obtained by performing learning processing in advance using teacher data including condition information regarding the chemical composition of the metal material and information indicating the material properties of the metal material according to the conditions indicated by the condition information, and associates the composition pattern with the material properties and records them as basic condition information, the terminal device includes a communication unit that communicates with other devices, an input unit that receives user operations, an output unit that outputs information to the user, and a control unit that obtains search condition information including predetermined material properties according to an operation on the input unit and transmits the search condition information to the metal material search device. The control unit of the metal material search device calculates the raw material price for each composition pattern included in the basic condition information, associates the chemical composition, the material properties, and the raw material price, and records them as characteristic price information. Based on the characteristic price information, obtain suitable condition information, which is information regarding the chemical composition of the metal material that satisfies the condition of the desired raw material price for the metal material having the predetermined material properties included in the search condition information, and transmit the suitable condition information to the terminal device. When the control unit of the terminal device receives the suitable condition information from the metal material search device, it outputs from the output unit. Metal material search system.

7. The control unit extracts a composition pattern that satisfies a search condition including a predetermined material property from the composition patterns included in the basic condition information, calculates the raw material price for each of the extracted composition patterns, and associates the extracted composition pattern with the material property and records it as basic condition information. The metal material search system according to claim 6.

8. The control unit calculates the raw material price for each composition pattern for all the composition patterns included in the basic condition information, associates the composition pattern with the material property, and records it as basic condition information. The metal material search system according to claim 6.

9. A computer program for causing a computer to function as a metal material search device including a control unit that acquires composition pattern information including a plurality of composition patterns related to the chemical composition of a metal material to be determined, performs pre-learning processing using teacher data including condition information related to the chemical composition of the metal material and information indicating the material properties of the metal material according to the conditions indicated by the condition information, estimates information indicating the material properties of the metal material for each of the composition patterns, associates the composition pattern with the material property and records it as basic condition information, calculates the raw material price for each of the composition patterns included in the basic condition information, associates the chemical composition, the material property, and the raw material price and records it as characteristic price information, and based on the characteristic price information, acquires suitable condition information that is information related to the chemical composition of a metal material that satisfies the condition of a desired raw material price for a metal material having a predetermined material property.

Images