Method for supporting material creation, system for supporting material creation, and evaluation apparatus

Abstract

This method for supporting material creation has an evaluation step in which, selected from between the crystal phases and the physical properties of a ceramic material obtained after sintering a ceramic powder obtained by reactive synthesis of a plurality of ceramic raw materials, the physical properties are predicted by evaluating the physical properties of said ceramic powder.

Description

Material creation support method, material creation support system, and evaluation device

[0001] The present invention relates generally to aiding materials creation.

[0002] One process in material creation is the evaluation of a material created as a sample in an experiment. In Non-Patent Document 1, the sample material is a catalyst, and its catalytic activity is evaluated.

[0003] Masanori Kodera and Kazuhiro Sayama, “An automatic robot system for machine learning-assisted high-throughput Screening of composite electrocatalysts”, Digital Discovery, 2023, 2, 1683-1687, published by the Royal Society of Chemistry, on 7 October 2023

[0004] In the creation of ceramic materials, the crystalline phase and physical properties of the ceramic materials are evaluated.

[0005] In this specification, the term "crystalline phase" refers to the arrangement of constituent atoms, symmetry, etc., and does not include the properties of how the material responds to external factors (typically, physical force, heat, electricity, magnetic force, or light). "Crystalline phase" may also be referred to as "material characteristics," and refers to a physical and / or chemical state, and specifically may include, for example, one or more characteristic items (e.g., crystal grain size, grain size distribution, etc.) and values ​​for each of the one or more characteristic items.

[0006] In this specification, "physical properties" refer to the properties of how a substance responds to external factors. "Physical properties" may also be called "material properties," and refer to physical and / or chemical properties exhibited by a substance as a material, and specifically may include, for example, one or more property items (e.g., stiffness, thermal conductivity, electrical conductivity, permittivity, magnetic susceptibility, etc.) and values ​​(typically numerical values) for each of the one or more property items.

[0007] Furthermore, "ceramics" refers to a general term for inorganic materials that are composed of polycrystals, but may also contain metals or organic compounds. Ceramics may be composed of single crystals or may be amorphous, such as glass. In this specification, "ceramics" may be polycrystalline, single crystal, amorphous, or a mixture of these.

[0008] Ceramic materials are classified into structural ceramic materials, which are ceramic materials that are made by mixing and firing commercially available raw materials and do not require the synthesis of raw materials, and functional ceramic materials, which are ceramic materials that require the synthesis of raw materials.

[0009] The physical properties of functional ceramic materials vary depending on the additives used and their ratios. Therefore, the creation of functional ceramic materials (e.g., composite oxides or composite nitrides) requires multiple levels of prototyping. For example, ABO3 is a functional ceramic material. However, in ABO3, it is necessary to synthesize compounds in which various elements are doped at each site in various ratios, resulting in multiple levels of prototyping. To evaluate the physical properties of each sample (each ceramic powder), it is necessary to mold and sinter each of many samples. Furthermore, to perform molding and sintering, a large number of samples must be synthesized. Therefore, creating a ceramic material as a functional ceramic material requires time and effort.

[0010] In Non-Patent Document 1, the material to be created is a catalyst, and the material itself is evaluated. Therefore, even if the technology disclosed in Non-Patent Document 1 is applied to the creation of ceramic materials, molding and firing are required for each sample, and the above-mentioned problem is not solved.

[0011] The material creation support method includes an evaluation step of predicting the crystalline phase and physical properties of a ceramic material after sintering a ceramic powder obtained by reactively synthesizing a plurality of ceramic raw materials by evaluating the physical properties of the ceramic powder.

[0012] This can improve the speed at which ceramic materials can be created.

[0013] 1 shows an example of a system configuration according to an embodiment of the present invention. 2 shows an example of the configuration of an experimental system and a processing flow performed by a materials creation support system. 3 shows a specific example of FIG.

[0014] In the following description, an "interface apparatus" may be one or more interface devices. The one or more interface devices may be at least one of the following: - One or more I / O (Input / Output) interface devices. The I / O (Input / Output) interface device is an interface device for at least one of an I / O device and a remote display computer. The I / O interface device for the display computer may be a communication interface device. The at least one I / O device may be a user interface device, for example, either an input device such as a keyboard and a pointing device, or an output device such as a display device. - One or more communication interface devices. The one or more communication interface devices may be one or more homogeneous communication interface devices (e.g., one or more NICs (Network Interface Cards)) or two or more heterogeneous communication interface devices (e.g., a NIC and an HBA (Host Bus Adapter)).

[0015] In the following description, "memory" refers to one or more memory devices, which are an example of one or more storage devices, and may typically be a primary storage device. At least one memory device in the memory may be a volatile memory device or a non-volatile memory device.

[0016] In the following description, a "persistent storage device" may refer to one or more persistent storage devices, which are an example of one or more storage devices. A persistent storage device may typically be a non-volatile storage device (e.g., an auxiliary storage device), and more specifically, may be, for example, a hard disk drive (HDD), a solid state drive (SSD), a non-volatile memory express (NVME) drive, or a storage class memory (SCM).

[0017] In the following description, the term "storage device" may refer to at least one of memory and persistent storage device.

[0018] In the following description, a "processor" may refer to one or more processor devices. The at least one processor device may typically be a microprocessor device such as a CPU (Central Processing Unit), but may also be another type of processor device such as a GPU (Graphics Processing Unit). The at least one processor device may be a single-core or multi-core. The at least one processor device may also be a processor core. At least one processor device may be a processor device in a broad sense, such as a circuit that is a collection of gate arrays written in a hardware description language that performs some or all of the processing (for example, an FPGA (Field-Programmable Gate Array), a CPLD (Complex Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit)).

[0019] Furthermore, in the following description, functions may be described using the expression "yyy unit." However, the functions may be realized by one or more computer programs executed by a processor, by one or more hardware circuits (e.g., FPGAs or ASICs), or by a combination thereof. When a function is realized by a program executed by a processor, the specified processing is performed using a storage device and / or an interface device, etc., as appropriate, and therefore the function may be considered to be at least a part of the processor. Processing described using a function as the subject may be processing performed by a processor or a device having the processor. A program may be installed from a program source. The program source may be, for example, a program distribution computer or a computer-readable recording medium (e.g., a non-transitory recording medium). The description of each function is an example, and multiple functions may be combined into one function, or one function may be divided into multiple functions.

[0020] In the following description, when elements of the same type are described without distinction, common reference symbols are used, and when elements of the same type are described with distinction, reference symbols are used.

[0021] An embodiment of the present invention will be described below with reference to the drawings. In the following description, "MI" stands for materials informatics, and "DB" stands for database.

[0022] 1 shows an example of a system configuration according to one embodiment of the present invention. Note that the description of this embodiment can be based on at least a portion of the disclosures in the earlier applications PCT / JP2023 / 009174 and PCT / JP2023 / 009175 filed by the same applicant as the present application. A brief description of FIG. 1 will be given below.

[0023] The material creation support system 10 includes an experiment system 110, a data acquisition unit 60, an MI platform system 100, and a researcher terminal 11 A. The MI platform system 100 includes a data presentation unit 50 and a data conversion unit 70.

[0024] The data presentation unit 50 has an AI (Artificial Intelligence) unit 108 and an IF (Interface) unit 109. The AI ​​unit 108 performs training of the machine learning model and inference using the machine learning model. For example, in response to instructions from the IF unit 109, the AI ​​unit 108 outputs to the IF unit 109 the inference results obtained by inputting organized data obtained from the data mart 107 into the machine learning model. The IF unit 109 receives inquiries from the researcher terminal 11A and presents target data to the researcher terminal 11A in response to the inquiries. The researcher terminal 11A is an information processing terminal (e.g., a personal computer or smartphone) of the materials researcher 5A (an example of a user). The researcher terminal 11A is an example of a sender of an inquiry for target data and also an example of a recipient of the target data. When an inquiry is received from the researcher terminal 11A (or periodically), the IF unit 109 presents the object represented by the target data (organized data obtained from the data mart 107 and / or data based on inference results obtained by instructing the AI ​​unit 108). The presented object may be, for example, a manufacturing recipe or material properties. In this embodiment, a "manufacturing recipe" refers to a method for creating a material and may typically include a material composition and / or a synthesis process. A "material composition" may be, for example, a blending composition, and a "synthesis process" may be the type of raw material (e.g., different particle sizes) or process conditions. A manufacturing recipe may also include a material development strategy.

[0025] The materials researcher 5A creates new materials and conducts experiments based on the presented target data. The target data may be presented (transmitted) to a system such as the experiment system 110 instead of or in addition to the researcher terminal 11A.

[0026] An experiment is conducted using the experimental system 110 based on the presented subject. The experimental system 110 may include a fabrication system 111 (e.g., an atmospheric firing furnace), a robot system 187 for the fabrication system 111 and / or the evaluation system 112, and the evaluation system 112 (e.g., an apparatus for evaluating thermal expansion coefficients). Experimental data is output from the experimental devices, such as the fabrication system 111 and the evaluation system 112. The output experimental data is transmitted to and stored in the data server 120. A combinatorial experiment is an example of an experiment, and at least one of a high-throughput experiment, an automated experiment using a robot, and an experiment mainly performed by human labor may be adopted instead of or in addition to a combinatorial experiment. The fabrication system 111 and the robot system 187 may be operated by the MI platform system 100 according to the manufacturing recipe data.

[0027] The data acquisition unit 60 includes a data server 120 and an experiment notebook unit 130. The data server 120 has two databases for storing experimental data from the experiment system 110: a production database 121 for storing experimental data from the production system 111, and an evaluation database 122 for storing experimental data from the evaluation system 112. "Experimental data" may be data related to an experiment, such as a summary, details, results, or evaluation of the experiment. The experiment notebook unit 130 manages the experimental data acquired from the databases managed by the data server 120 as an electronic experiment notebook 131.

[0028] The data conversion unit 70 includes a collection unit 101, a feature calculation unit 103, an image analysis unit 104, a natural language analysis unit 105, and an organization unit 106. The collection unit 101 collects experimental data from the electronic experiment notebook 131 or the database of the data server 120, formats the collected experimental data, and stores the formatted experimental data in the data lake 102. Alternatively, the collection unit 101 collects various data 150 and stores at least a portion of the various data 150 in the data lake 102. The feature calculation unit 103 calculates the feature values ​​of one or more predetermined types of data in the formatted experimental data. For example, the one or more types of data may be image data and text data. The image data is analyzed by the image analysis unit 104, and the feature calculation unit 103 calculates the feature values ​​of the image data based on the results of the analysis. Furthermore, the text data is text-mined by the natural language analysis unit 105, and the feature calculation unit 103 calculates the feature values ​​of the text data based on the results of the text mining. The organizer 106 organizes the data lake 102 into one or more data marts 107 as data sets that meet predetermined conditions.

[0029] The system shown in FIG. 1 is expected to efficiently and quickly execute the cycle of presenting target data → conducting an experiment → collecting experimental data → converting the experimental data into organized data → presenting target data based on the organized data. For example, organized data is prepared based on experimental data collected and formatted in the MI platform system 100, and the target data is presented to the materials researcher 5A by the MI platform system 100 based on the organized data. Data presentation to the materials researcher 5A may also be performed without going through the MI platform system 100. For example, another materials researcher 5B may use the trainee terminal 11B to acquire experimental data from the electronic experiment notebook 131, organize the experimental data, and input it into the AI ​​unit 140. The AI ​​unit 140 may be implemented outside (or within) the trainee terminal 11B.

[0030] The MI platform system 100 provides manufacturing recipe data representing a manufacturing recipe for ceramics as target data, and ceramics (ceramic materials) are produced according to the manufacturing recipe represented by the manufacturing recipe data, and an experiment is carried out.

[0031] The production of ceramics according to a manufacturing recipe may include the synthesis (mixing) of ceramic raw materials. While at least some of the steps in the synthesis of ceramic raw materials may be performed manually (e.g., by a materials researcher 5A), in this embodiment, the MI platform system 100 (an example of a computer system) may automatically perform all or part of the ceramic raw material synthesis process by operating the manufacturing system 111 and the robot system 187 according to the manufacturing recipe data. This allows the ceramic raw material synthesis process to be performed quickly. The synthesis process may include multiple steps, as long as at least one of the multiple steps is performed automatically. Alternatively, instead of generating manufacturing recipe data, the MI platform system 100 may receive manufacturing recipe data from an external system and operate the manufacturing system 111 and the robot system 187 according to the received manufacturing recipe data. In other words, a computer system such as the MI platform system 100 may generate or receive manufacturing recipe data and operate the manufacturing system 111 and the robot system 187 according to the generated or received manufacturing recipe data. For the synthesis process of ceramic raw materials, at least a part of the disclosures in, for example, the earlier applications PCT / JP2023 / 031646 and PCT / JP2024 / 012942 filed by the same applicant as the present application can be cited.

[0032] A ceramic powder (ceramic raw material powder) is obtained by reactively synthesizing multiple ceramic raw materials using a production system 111 (or manually). The evaluation system 112 performs an evaluation process. In the evaluation process, the evaluation system 112 predicts the crystalline phase and physical properties of the sintered ceramic material by evaluating the physical properties of the ceramic powder. In other words, the evaluation system 112 evaluates the physical properties of the ceramic powder to predict the physical properties of the sintered ceramic material. This allows the physical properties of the sintered ceramic material to be predicted without molding and firing the ceramic powder, thereby improving the speed at which ceramic materials are created. Furthermore, since molding and firing of the ceramic powder are not required, fewer raw materials can be synthesized, which is expected to reduce the time required for the synthesis process, thereby also improving the speed at which ceramic materials can be created. For example, in the synthesis process, liquid-phase synthesis may be performed to synthesize multiple ceramic raw materials. For each ceramic raw material, the amount of liquid required in liquid-phase synthesis is smaller than when molding and firing of ceramic powder is required.

[0033] Thus, in this embodiment, the physical properties of the ceramic material as a final sintered body are predicted at the particle stage. Typical physical property items include mechanical properties (mechanical properties), thermal properties, electrical properties, magnetic properties (magnetism), and optical properties (optical properties). Of these, the thermal, electrical, and magnetic properties of the particles are not substantially affected by differences in molding and firing conditions. In light of this, the physical property of the ceramic powder evaluated in the evaluation step according to this embodiment is at least one of the thermal, electrical, and magnetic properties. The physical properties to be evaluated are not limited; for example, mechanical and / or optical properties may be evaluated in addition to at least one of the thermal, electrical, and magnetic properties.

[0034] Furthermore, the evaluation system 112 automatically evaluates the physical properties of a ceramic powder when the ceramic powder is given, which is expected to further improve the speed at which ceramic materials can be created.

[0035] Furthermore, the ceramic material in this embodiment may be a functional ceramic material. Unlike structural ceramic materials, functional ceramic materials are ceramic materials that require the synthesis of raw materials (multiple levels of prototyping). If the ceramic material in this embodiment is a functional ceramic material, the speed at which such multi-level prototyping ceramic materials can be created can be improved.

[0036] This embodiment will be described in detail below.

[0037] 2 shows an example of the configuration of the experiment system 110 and the processing flow performed by the material creation support system. FIG. 3 shows a specific example of FIG.

[0038] The material creation support method may include a synthesis step and / or a composition determination step in addition to the evaluation step. In the material creation support method according to this embodiment, if the physical properties evaluated in the evaluation step do not match the target physical properties, a composition determination step is performed to determine the composition, synthesis is performed according to the determined composition in the synthesis step, and the physical properties of the ceramic powder obtained by the synthesis are evaluated again in the evaluation step. That is, the cycle of evaluation step → composition determination step → synthesis step → evaluation step is repeated until an evaluation that matches the target physical properties is obtained.

[0039] Specifically, the material creation support system 10 performs the following steps (a) to (c) ((a) is performed again using the composition determined in (c) as the designated composition). This makes it possible to quickly find a composition for the ceramic powder 290 having properties that match the target properties, thereby contributing to improving the speed at which ceramic materials are created. (a) A synthesis step is performed, including synthesizing a plurality of ceramic raw materials 211 according to the designated composition. (b) An evaluation step is performed, including evaluating the properties of the ceramic powder 290 obtained by the synthesis step (a). (c) If the predicted properties do not match the target properties, a composition determination step is performed, in which a different composition is determined based on accumulated data, including data resulting from the evaluation in (b).

[0040] Data resulting from the evaluation in (b) is stored in the evaluation DB 122. In (c), the MI platform system 100 determines whether the predicted physical properties represented by the evaluation result data acquired from the evaluation DB 122 match the target physical properties. If the result of this determination is false, the AI ​​unit 108 of the MI platform system 100 uses the data stored in the evaluation DB 122 to update the machine learning model 210, which outputs data representing a composition in response to input data representing physical properties. By inputting data representing the target physical properties into the updated machine learning model 210, the AI ​​unit 108 outputs data representing the composition (at least a part of the manufacturing recipe) of a ceramic material expected to have the target physical properties. Manufacturing recipe data based on this data is output by the IF unit 109, and the synthesis process is performed by the production system 111 according to the composition represented by the output manufacturing recipe data. This improves the speed at which ceramic materials can be created.

[0041] The machine learning model 210 may be any model, such as linear regression, logistic regression, decision tree model, neural network, Bayesian optimization, k-NN, or a combination of any two or more of these models. In this embodiment, the machine learning model 210 is a model in which physical properties are the objective variables and multiple composition-related items are the explanatory variables. The composition-related items may be elements or their ratios. For example, if the ceramic material is ABO3, the composition-related items may be the elements doped in the A site and their ratios, the elements doped in the B site and their ratios, etc. Updating the machine learning model 210 based on the data accumulated in the evaluation DB 122 may include updating the coefficients of the explanatory variables.

[0042] In (b), the evaluation system 112 may evaluate the composition of the ceramic powder in addition to the physical properties of the ceramic powder obtained by the synthesis process. For example, the evaluation system 112 may include an ICP-MS (Inductively Coupled Plasma Mass Spectrometry) and / or an X-ray fluorescence analyzer as an example of an evaluation device 202 for evaluating the composition. Such an evaluation device 202 can identify and quantify the types of constituent ions to evaluate the composition of the ceramic powder. The composition evaluation may include confirming whether the ceramic raw materials were synthesized in the synthesis process according to the specified composition. The data resulting from the evaluation in (b) may include data representing one or more pairs of the evaluated composition and predicted physical properties. The machine learning model 210 may be updated based on data representing one or more pairs of the evaluated composition and predicted physical properties. This will update the machine learning model 210 based on a more accurate relationship between composition and physical properties, which is expected to increase the likelihood of quickly outputting a composition of a ceramic material with the target physical properties.

[0043] In this embodiment, the cycles (a) to (c) described above are performed automatically as follows. The cycle ends when the predicted physical properties match the target physical properties. This can improve the speed at which ceramic materials are created. In (a), the MI platform system 100 controls the production system 111 that synthesizes ceramic raw materials, thereby automatically synthesizing the raw materials according to the composition of the manufacturing recipe. In (b), the MI platform system 100 operates the robot system 187 and the evaluation system 112, thereby automatically feeding the ceramic powder obtained by the synthesis in (a) into the evaluation system 112, automatically evaluating the physical properties of the fed ceramic powder, and automatically removing the ceramic powder whose physical properties have been evaluated from the evaluation system 112. The robot system 187 includes one or more robots, which feed samples into the evaluation system 112, which evaluates the physical properties, and automatically remove the samples from the evaluation system 112. In (c), a determination is made as to whether the predicted physical properties match the target physical properties, and if the predicted physical properties do not match the target physical properties, a different composition is determined, automatically performed by the MI platform system 100. (a) is again automatically performed according to the composition determined in (c).

[0044] The production system 111 performs a synthesis process. In the synthesis process, the production system 111 obtains ceramic powder 290 by synthesizing multiple ceramic raw materials (e.g., raw materials 211A-211C) according to a recipe (an example of a composition) represented by recipe data output from the MI platform system 100 (an example of a computer system). The production system 111 may include multiple devices, and multiple steps (e.g., weighing, raw material mixing, drying, crushing, and separation) that make up the synthesis process may be performed by these multiple devices. The recipe data may be input to the production system 111 from the IF unit 109 of the MI platform system 100, and the synthesis process may be performed according to the composition represented by the recipe data under the control of the MI platform system 100 and the robot system 187.

[0045] The robot system 187 may include one or more robots. The robot in the robot system 187 may be a collaborative robot or other robots (e.g., industrial robots). Furthermore, a robot may be provided in at least one of one or more devices in the manufacturing system 111 and / or at least one of one or more evaluation devices 202 in the evaluation system 112, or one robot may be common to two or more devices in the manufacturing system 111 and / or two or more evaluation devices 202 in the evaluation system 112. The robots in the robot system 187 receive requests directly or indirectly from the MI platform system 100, for example, via a communication network, and operate according to the received requests. In the case where a request is received indirectly, a control device of at least one robot may receive a request from the MI platform system 100 and issue a request based on the request to the at least one robot. In the case where a request is received directly, a request may be received from the MI platform system 100 without passing through such a control device. For ease of explanation, it is assumed below that any robot in the robot system 187 receives a request according to the manufacturing recipe data 200 from the MI platform system 100, regardless of whether the request is received directly or indirectly. It is also assumed that the robot system 187 operates when any of the one or more robots in the robot system 187 operates. The robot may transmit a notification (e.g., a status notification such as completion of the request) to the MI platform system 100 at the start or completion of an operation according to the request.

[0046] As shown in FIG. 2 , the evaluation system 112 includes one or more evaluation devices 202. A sample of ceramic powder 290 is fed into one or more evaluation devices 202 by the robot system 187 (or manually), and each of the one or more evaluation devices 202 evaluates the sample. Evaluation result data, including data as the evaluation result of each evaluation device 202, is stored in the evaluation DB 122. The evaluation result data may be stored in the evaluation DB 122 automatically by the evaluation system 112 via or without the MI platform system 100. The evaluation result data may be data for each sample, and may include data representing the physical properties of the sample (e.g., physical property values ​​obtained for each of multiple physical property items such as thermal expansion coefficient and electrical conductivity). Furthermore, the evaluation result data for each sample may include data representing the evaluated composition of the sample in addition to data representing the physical properties of the sample.

[0047] The MI platform system 100 determines whether the predicted physical properties represented by the data stored in the evaluation DB 122 match the target physical properties. When the target physical properties and the predicted physical properties include multiple items (e.g., thermal expansion coefficient and electrical conductivity), the determination that the predicted physical properties match the target physical properties may require that the values ​​of the predicted physical properties match the target values ​​of the target physical properties for all of the multiple items.

[0048] As shown in FIG. 3, the evaluation system 112 may include, as an example of the evaluation device 202, a high-temperature XRD device 202A and a scanning microwave impedance microscope (sMIM) 202B.

[0049] The high-temperature XRD device 202A evaluates the thermal expansion coefficient (an example of a thermal property) by high-temperature XRD. The high-temperature XRD device 202A may be configured to automatically perform high-temperature XRD measurement under control of the MI platform system 100 and / or the robot system 187 (or without such control). The evaluation process may include, for example, performing high-temperature XRD measurement using the high-temperature XRD device 202A, which automatically performs the following steps: loading a sample into the high-temperature XRD device 202A, heating the loaded sample to a predetermined temperature, performing XRD measurement on the sample once it has reached the predetermined temperature, and removing the sample from the high-temperature XRD device 202A. Specifically, for example, the high-temperature XRD device 202A and a robot in the robot system 187 may cooperate to automatically load a sample into the high-temperature XRD device 202A, heating the loaded sample to a predetermined temperature, performing XRD measurement on the sample once it has reached the predetermined temperature, and removing the sample from the high-temperature XRD device 202A. For example, the high-temperature XRD apparatus 202A may be equipped with an automatic sample changer. The automatic sample changer may be an element included in the robot system 187 or may be an element separate from the robot system 187. A plurality of samples (ceramic powders) of different compositions may be set on the automatic sample changer by, for example, the robot system 187, the thermal expansion coefficients of the plurality of samples may be evaluated, and data representing the evaluated thermal expansion coefficients for each of the plurality of samples may be stored in the evaluation DB 122 as at least a part of the evaluation result data.

[0050] The sMIM 202B evaluates the conductivity. Although not shown, the conductivity may be evaluated by impedance measurement or spectroscopy instead of or in addition to the sMIM 202B. Data representing the evaluated conductivity for each sample may be stored in the evaluation DB 122 as at least a part of the evaluation result data, together with, for example, data on the thermal expansion coefficient of the sample.

[0051] At least one evaluation device 202, for example, the high-temperature XRD device 202A, may have an input unit that automatically inputs ceramic powder, a temperature control unit that automatically heats the input ceramic powder to a predetermined temperature, a measurement unit that automatically performs XRD measurement of the ceramic material that has reached the predetermined temperature, and an output unit that automatically removes the ceramic powder from the high-temperature XRD device 202A. The input unit and the output unit may be realized by a robot such as an auto sample changer. Combining such an evaluation device 202 with the MI platform system 100 can improve the speed at which ceramic materials can be created.

[0052] Although one embodiment has been described above, this is merely an example for explaining the present invention, and the scope of the present invention is not limited to this embodiment. The present invention can be implemented in various other forms.

[0053] 10...Material creation support system 100...MI platform system 112...Evaluation system 187...Robot system

Claims

1. A materials creation support method characterized by evaluating the physical properties of ceramic powder obtained by reactively synthesizing multiple ceramic raw materials, and predicting the physical properties of ceramic materials after sintering using the ceramic powder.

2. The material creation support method according to claim 1, wherein the evaluation of the ceramic powder involves automatically evaluating the physical properties.

3. A materials creation support method according to claim 1, comprising: (a) performing a ceramic powder synthesis process including reactively synthesizing a plurality of ceramic raw materials according to a specified composition; (b) performing an evaluation process including evaluating the physical properties of the ceramic powder obtained by the synthesis process of (a); (c) when the predicted physical properties do not match the target physical properties, determining a different composition based on accumulated data including data resulting from the evaluation in (b); and performing (a) using the composition determined in (c) as the specified composition.

4. In (c), the accumulated data is used to update a machine learning model that outputs data representing a composition in response to input of data representing physical properties, and by inputting data representing the target physical properties into the updated machine learning model, data representing the composition of a ceramic material expected to have the target physical properties is output; the data resulting from the evaluation in (b) includes data representing the predicted physical properties, and the composition represented by the output data is the different composition. A material creation support method as described in claim 3.

5. The material creation support method according to claim 4, wherein in (b), in addition to the physical properties of the ceramic powder obtained by the synthesis step, the composition of the ceramic powder is evaluated, and the data resulting from the evaluation in (b) includes data representing one or more pairs of the evaluated composition and the predicted physical properties.

6. The materials creation support method according to claim 1, wherein the physical property is at least one of a thermal property, an electrical property, and a magnetic property.

7. The materials creation support method according to claim 6, wherein the evaluation step evaluates the thermal expansion coefficient by high-temperature XRD.

8. The materials creation support method according to claim 6, wherein the evaluation step evaluates the conductivity by sMIM, impedance measurement, or spectroscopic measurement.

9. The materials creation support method according to claim 1, wherein the synthesis of the plurality of ceramic raw materials is liquid phase synthesis.

10. The materials creation support method according to claim 5, wherein the evaluation step includes performing high-temperature XRD measurement using a high-temperature XRD device that automatically performs the steps of: loading a sample into the high-temperature XRD device; heating the loaded sample to a predetermined temperature; performing XRD measurement on the sample once the predetermined temperature has been reached; and removing the sample from the high-temperature XRD device.

11. The material creation support method according to claim 3, wherein the cycles of (a) to (c) are performed automatically as follows: in (a), a production system for synthesizing ceramic raw materials is controlled by a computer system to automatically perform synthesis according to the specified composition; in (b), a robot system including one or more robots that input samples into an evaluation system that evaluates physical properties and remove samples from the evaluation system, and the evaluation system are operated by a computer system, thereby automatically inputting the ceramic powder obtained by the synthesis in (a) into the evaluation system, automatically evaluating the physical properties of the input ceramic powder, and automatically removing the ceramic powder whose physical properties have been evaluated from the evaluation system; in (c), the computer system automatically determines whether the predicted physical properties match the target physical properties, and if the predicted physical properties do not match the target physical properties, determines the different composition; (a) is automatically performed using the composition determined in (c) as the specified composition; and the cycle is terminated if the predicted physical properties match the target physical properties.

12. The materials creation support method according to claim 1, wherein the ceramic material is a functional ceramic material.

13. An evaluation device having an input unit that automatically inputs ceramic powder obtained by synthesizing multiple ceramic raw materials, an evaluation unit that automatically evaluates the physical properties of the input ceramic powder in order to predict the physical properties of the ceramic material after sintering the ceramic powder, and an extraction unit that automatically extracts the evaluated ceramic powder.

14. The evaluation device according to claim 13, which is a high-temperature XRD device.

15. A materials creation support system comprising: an evaluation system that evaluates the physical properties of a ceramic powder obtained by reactively synthesizing a plurality of ceramic raw materials according to a specified composition in order to predict the crystalline phase and physical properties of the ceramic material after sintering the ceramic powder; and a computer system that determines whether the predicted physical properties match target physical properties, and if the predicted physical properties do not match the target physical properties, updates a machine learning model that outputs data representing a composition in response to input data representing the physical properties using accumulated data including data resulting from the evaluation by the evaluation system, and inputs the data representing the target physical properties into the updated machine learning model, thereby outputting data representing the composition of a ceramic material that is expected to have the target physical properties, wherein the data resulting from the evaluation includes data representing the predicted physical properties, and the composition represented by the output data is the specified composition.

16. The material creation support system according to claim 15, further comprising a production system that synthesizes a plurality of ceramic raw materials in accordance with a composition represented by data output from said computer system, wherein said evaluation system evaluates the physical properties of the ceramic powder resulting from synthesis by said production system.

Images