WO2024252995A1 - 物性予測装置、物性予測方法、及び物性予測プログラム - Google Patents
物性予測装置、物性予測方法、及び物性予測プログラム Download PDFInfo
- Publication number
- WO2024252995A1 WO2024252995A1 PCT/JP2024/019633 JP2024019633W WO2024252995A1 WO 2024252995 A1 WO2024252995 A1 WO 2024252995A1 JP 2024019633 W JP2024019633 W JP 2024019633W WO 2024252995 A1 WO2024252995 A1 WO 2024252995A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- physical property
- uncertainty
- actual measurement
- virtual data
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
Definitions
- This disclosure relates to a property prediction device, a property prediction method, and a property prediction program.
- materials informatics In recent years, a technical field called materials informatics has been attracting attention, which aims to improve the efficiency of material development by utilizing information science techniques such as machine learning.
- materials informatics in order to manufacture materials with desired physical properties, it is necessary to find appropriate combinations of numerous parameters related to the raw material mixing ratio and process conditions. When there are a large number of parameters, the number of parameter combinations becomes enormous. When the number of parameter combinations becomes enormous, it becomes difficult to comprehensively prototype materials.
- a method is used in which the physical properties of a certain number of prototype materials are measured, and a predictive model of the physical properties is constructed based on the actual measurement data obtained by the measurements. By using a predictive model, it is possible to search for optimal parameters even if the number of prototype materials is limited.
- Supervised machine learning methods are sometimes used to build predictive models. With supervised machine learning methods, it is difficult to build a highly accurate predictive model when the number of measured data is insufficient or the relationship between parameters and physical properties is complex. In order to build a highly accurate predictive model even when the number of measured data is insufficient or the relationship between parameters and physical properties is complex, sequential experimental design methods such as Bayesian optimization are used. In Bayesian optimization, Bayesian estimation is used to build predictive models. Bayesian estimation is based on the idea of Bayesian probability and is a method of inferring the matter to be estimated from observed events in a probabilistic sense. Bayesian probability is a probability interpreted as a rational expectation representing the state of knowledge, or a quantification of personal beliefs.
- Bayesian estimation in addition to the predicted value of the physical property, the uncertainty of the predicted value is calculated. By calculating the uncertainty, it is possible to calculate the probability that the physical property will be a specific value and the expected value of the physical property. With Bayesian estimation, it is possible to find optimal parameters based on limited measured data. In other words, with Bayesian estimation, it is possible to create an experimental plan for the next prototype of a material based on limited measured data. The prediction model is updated by making the next prototype of the material, measuring the properties of the prototype, and adding the measurement results to the actual measurement data. In Bayesian optimization, a series of cycles consisting of prototyping, measuring the properties, and updating the prediction model described above is repeated. By repeating this series of cycles, it is possible to minimize the number of prototypes required to obtain the desired physical property values.
- WO2021/200281A1 discloses a technique for sequentially planning experiments by applying machine learning to actual measurement data.
- WO2020/188971A1 discloses a technique for pre-learning physical property values by determining physical property values corresponding to parameters through simulations such as quantum chemical calculations.
- WO2020/188971A1 can only be implemented in certain fields where simulation methods have been established. In other words, the technology disclosed in WO2020/188971A1 is difficult to implement in many fields where it is difficult to apply simulation.
- This disclosure has been made in consideration of the above points, and aims to provide a property prediction device, a property prediction method, and a property prediction program that can appropriately and efficiently develop materials with desired properties.
- the physical property prediction device comprises: an actual measurement data acquiring unit that acquires actual measurement data including a first manufacturing condition of a sample and an actual measurement value obtained by actually measuring a physical property of the sample manufactured under the first manufacturing condition; a virtual data acquisition unit that acquires virtual data including second manufacturing conditions of the sample and virtual values of physical properties of the sample corresponding to the second manufacturing conditions; a model generation unit that generates a prediction model of the physical property based on the actual measurement data acquired by the actual measurement data acquisition unit and the virtual data acquired by the virtual data acquisition unit, the prediction model having a first uncertainty of the physical property with respect to the actual measurement data and a second uncertainty of the physical property with respect to the virtual data that is greater than the first uncertainty of the physical property; Equipped with.
- the virtual data acquisition unit may acquire, as the virtual value, the physical property value of the sample predicted when the value of at least one of the multiple parameters included in the second manufacturing conditions is extremely small or large.
- the virtual data acquisition unit may acquire, as the virtual values, physical property values of a material whose raw materials or process are similar to those of the sample.
- the first uncertainty of the physical property may be 0.
- the physical property prediction apparatus further includes an input screen generation unit that generates an input screen for inputting the actual measurement data and the virtual data
- the actual measurement data acquisition unit acquires the actual measurement data input to the input screen generated by the input screen generation unit
- the virtual data acquisition unit may acquire the virtual data input to the input screen generated by the input screen generation unit.
- the physical property prediction apparatus further includes a communication unit that transmits the input screen generated by the input screen generation unit to a user's terminal device and receives the actual measurement data and the virtual data input to the input screen from the terminal device,
- the actual measurement data acquisition unit acquires the actual measurement data received by the communication unit
- the virtual data acquisition unit may acquire the virtual data received by the communication unit.
- the physical property prediction device further includes a virtual data complementation unit that complements the virtual data,
- the virtual data acquisition unit may acquire the virtual data complemented by the virtual data complement unit.
- the virtual data complementation unit may complement the second manufacturing conditions of the virtual data by calculating the values of the parameters other than the portion of the plurality of parameters when a portion of the parameters having an extremely small or large value among the plurality of parameters included in the second manufacturing conditions and the virtual value predicted based on the portion of the parameters are input to the input screen.
- the physical property prediction apparatus further includes an uncertainty setting unit that sets a first uncertainty of the physical property and a second uncertainty of the physical property
- the model generation unit may generate the prediction model further based on a first uncertainty of the physical property and a second uncertainty of the physical property set by the uncertainty setting unit.
- the physical property prediction device further includes a setting screen generating unit configured to generate a setting screen for setting a first uncertainty of the physical property and a second uncertainty of the physical property,
- the uncertainty setting unit may set a first uncertainty of the physical property and a second uncertainty of the physical property in response to an input operation on the setting screen generated by the setting screen generating unit.
- the model generation unit may generate the prediction model using Bayesian estimation, the first uncertainty may be a first variance, and the second uncertainty may be a second variance that is greater than the first variance.
- the model generation unit may generate the prediction model according to the following equation.
- the physical property prediction device may further include a manufacturing condition calculation unit that calculates a third manufacturing condition for the sample based on the prediction model generated by the model generation unit.
- the third manufacturing conditions may include at least one of the manufacturing conditions when the uncertainty of the physical property in the prediction model is maximized and the manufacturing conditions when the uncertainty of the physical property in the prediction model is minimized.
- the actual measurement data acquisition unit further acquires second actual measurement data including the third manufacturing conditions calculated by the manufacturing condition calculation unit and second actual measurement values obtained by measuring physical properties of the sample manufactured based on the third manufacturing conditions;
- the model generation unit may update the prediction model based on the second actual measurement data acquired by the actual measurement data acquisition unit.
- the model generation unit does not need to update the prediction model if the second measured value is the set optimal value.
- the physical property prediction method includes: acquiring actual measurement data including first manufacturing conditions for a sample and actual measurement values obtained by measuring physical properties of the sample manufactured based on the first manufacturing conditions; acquiring virtual data including second manufacturing conditions for the sample and virtual values obtained by assuming physical properties of the sample corresponding to the second manufacturing conditions; generating a prediction model of the physical property based on the acquired actual measurement data and virtual data, the prediction model having a first uncertainty of the physical property with respect to the actual measurement data and a second uncertainty of the physical property with respect to the virtual data that is greater than the first uncertainty of the physical property; Equipped with.
- the physical property prediction program is On the computer, acquiring actual measurement data including first manufacturing conditions for a sample and actual measurement values obtained by measuring physical properties of the sample manufactured under the first manufacturing conditions; The method executes the steps of: acquiring virtual data including second manufacturing conditions for the sample and virtual values that are hypothetical values of physical properties of the sample corresponding to the second manufacturing conditions; and generating a prediction model of the physical property based on the acquired actual measurement data and virtual data, the prediction model having a first uncertainty of the physical property with respect to the actual measurement data and a second uncertainty of the physical property with respect to the virtual data that is greater than the first uncertainty of the physical property.
- This disclosure makes it possible to appropriately and efficiently develop materials with desired physical properties.
- FIG. 1 is a schematic diagram showing a property prediction apparatus according to the first embodiment.
- FIG. 2 is a block diagram showing the property prediction apparatus according to the first embodiment.
- FIG. 3 is a flowchart showing an example of the operation of the property prediction apparatus according to the first embodiment.
- FIG. 4 is a diagram showing an example of an input screen in an example of the operation of the property prediction apparatus according to the first embodiment.
- FIG. 5 is a diagram showing an example of a prediction model in an example of the operation of the property prediction apparatus according to the first embodiment.
- FIG. 6 is a diagram showing another example of a prediction model in an example of the operation of the property prediction device according to the first embodiment.
- FIG. 1 is a schematic diagram showing a property prediction apparatus according to the first embodiment.
- FIG. 2 is a block diagram showing the property prediction apparatus according to the first embodiment.
- FIG. 3 is a flowchart showing an example of the operation of the property prediction apparatus according to the first embodiment.
- FIG. 4 is a diagram showing an example of
- FIG. 7 is a diagram showing an example of calculation of the third manufacturing condition based on the prediction model in an example of the operation of the property prediction apparatus according to the first embodiment.
- FIG. 8 is a block diagram showing a property prediction apparatus according to the second embodiment.
- FIG. 9 is a flowchart showing an example of the operation of the property prediction apparatus according to the second embodiment.
- FIG. 10 is a diagram showing an example of an input screen in an example of the operation of the property prediction apparatus according to the second embodiment.
- FIG. 11 is a block diagram showing a property prediction apparatus according to the third embodiment.
- FIG. 12 is a flowchart showing an example of the operation of the property prediction apparatus according to the third embodiment.
- FIG. 13 is a diagram showing an example of an input screen in an example of the operation of the property prediction apparatus according to the third embodiment.
- FIG. 14 is a block diagram showing a property prediction apparatus according to the fourth embodiment.
- Figure 1 is a conceptual diagram showing a property prediction apparatus 1 according to the first embodiment.
- the physical property prediction device 1 generates a prediction model of a sample based on actual measurement data and predicted data.
- the actual measurement data is data including the first manufacturing conditions of the sample and the actual measurement values.
- the sample is, for example, a material manufactured based on a plurality of raw materials.
- the first manufacturing conditions are, for example, the compounding ratio of the raw materials of the material, process conditions such as temperature, etc.
- the actual measurement values are values obtained by actually measuring the physical properties of the sample actually manufactured based on the first manufacturing conditions.
- the physical properties of the sample are, for example, electrical conductivity and dielectric constant.
- the predicted data is data including the second manufacturing conditions of the sample and virtual values.
- the second manufacturing conditions are manufacturing conditions different from the first manufacturing conditions.
- the second manufacturing conditions are not the manufacturing conditions when the sample was actually manufactured, but virtual manufacturing conditions.
- the virtual values are virtual values of the physical properties of the sample corresponding to the second manufacturing conditions.
- the prediction model is information indicating the physical properties of the sample predicted based on the manufacturing conditions of the sample. In other words, the prediction model is information indicating the correspondence between the manufacturing conditions and the physical properties of the sample.
- the physical property prediction device 1 also creates a new experimental plan for the sample based on the generated prediction model.
- a new sample is prototyped according to the created new experimental plan.
- An experiment is conducted on the prototyped new sample to measure the physical properties.
- the actual measurement data obtained by the experiment is added to the physical property prediction device 1.
- the physical property prediction device 1 updates the prediction model based on the actual measurement data updated by the addition and the virtual data.
- the physical property prediction device 1 optimizes the experimental plan by repeatedly generating a prediction model based on actual measurement data and virtual data, creating an experimental plan, and adding actual measurement data.
- FIG. 2 is a block diagram showing a physical property prediction device 1 according to a first embodiment. More specifically, as shown in FIG. 2, the physical property prediction device 1 includes a control unit 2, an input interface 3, a display unit 4, and a storage unit 5. The control unit 2, the input interface 3, the display unit 4, and the storage unit 5 are communicatively connected via a bus 6.
- the input interface 3 accepts various instructions and information input operations from the user.
- the input interface 3 converts the input operations accepted from the user into electrical signals.
- the input interface 3 outputs the input operations converted into electrical signals to the control unit 2.
- the input interface 3 may be, for example, a mouse, a keyboard, a touchpad, a touch panel, a trackball, a switch button, a microphone, etc.
- the display unit 4 displays an image according to the image data transmitted from the control unit 2.
- the display unit 4 may be, for example, a liquid crystal monitor, a CRT (Cathode Ray Tube) monitor, a touch panel, or the like.
- the display unit 4 may also be equipped with a speaker.
- the memory unit 5 is a non-transient storage device that stores various information.
- the memory unit 5 may be, for example, a HDD (Hard Disk Drive), an optical disk, a magnetic disk, a magneto-optical disk, a CD (Compact Disc), a DVD (Digital Versatile Disc), a semiconductor memory, etc.
- the memory unit 5 stores, for example, the property prediction program executed by the property prediction device 1 and various data used in executing the property prediction program.
- the control unit 2 controls the operation of the physical property prediction device 1 in response to input operations by the user using the input interface 3.
- the control unit 2 includes an actual measurement data acquisition unit 21, a virtual data acquisition unit 22, a model generation unit 23, an input screen generation unit 24, and a manufacturing condition calculation unit 25.
- the functions corresponding to each of the components 21 to 25 of the control unit 2 are recorded in the memory unit 5 in the form of a property prediction program executable by a computer.
- the control unit 2 is, for example, a processor.
- the processor constituting the control unit 2 reads out the property prediction program from the memory unit 5 and executes it to execute the functions of the components 21 to 25 corresponding to the read property prediction program.
- the property prediction program may be directly incorporated into the circuit of the processor.
- the processor executes the function corresponding to each of the components 21 to 25 by executing the property prediction program incorporated in the circuit.
- the property prediction program may be a program downloaded by the property prediction device 1 from a server via a network.
- the property prediction program may be a program imported into the property prediction device 1 from a portable storage medium.
- the control unit 2 may be composed of a single processor.
- the control unit 2 may be composed of a combination of multiple processors.
- the processor may be, for example, a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a programmable logic device, etc.
- the programmable logic device may be a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), or a field programmable gate array (FPGA).
- the actual measurement data acquisition unit 21 acquires actual measurement data including the first manufacturing conditions of the sample and actual measurement values of the physical properties of the sample manufactured based on the first manufacturing conditions.
- the virtual data acquisition unit 22 acquires virtual data including second manufacturing conditions for the sample and virtual values that are hypothetical physical properties of the sample that correspond to the second manufacturing conditions.
- the virtual data acquisition unit 22 may acquire, as virtual values, the physical property values of the sample that are predicted when the values of some of the multiple parameters included in the second manufacturing conditions are extremely small or large.
- a parameter value When a parameter value is extremely small, it means that the parameter value is the lower limit of a predetermined search range for the parameter or a value below the lower limit. When a parameter value is extremely large, it means that the parameter value is the upper limit of a predetermined search range for the parameter or a value above the upper limit.
- the virtual data acquisition unit 22 may acquire, as virtual values, the physical property values of a material whose raw materials or process are similar to those of the sample.
- the model generation unit 23 generates a prediction model of the physical property based on the actual measurement data acquired by the actual measurement data acquisition unit 21 and the virtual data acquired by the virtual data acquisition unit 22.
- the prediction model may be a probabilistic prediction model that indicates the predicted physical property by a probability.
- the model generation unit 23 generates a prediction model that has a first uncertainty of the physical property for the actual measurement data and a second uncertainty of the physical property for the virtual data that is greater than the first uncertainty of the physical property.
- the first uncertainty of the physical property is, for example, 0.
- the input screen generation unit 24 generates an input screen for inputting actual data and virtual data.
- the input screen generation unit 24 displays the generated input screen on the display unit 4.
- the actual data acquisition unit 21 acquires the actual data input to the input screen generated by the input screen generation unit 24. More specifically, the actual data acquisition unit 21 acquires the actual data input to the input screen displayed on the display unit 4 using the input interface 3.
- the virtual data acquisition unit 22 acquires the virtual data input to the input screen generated by the input screen generation unit 24. More specifically, the virtual data acquisition unit 22 acquires the virtual data input to the input screen displayed on the display unit 4 using the input interface 3.
- the manufacturing condition calculation unit 25 calculates the third manufacturing conditions for the sample based on the prediction model generated by the model generation unit 23.
- the third manufacturing conditions may include at least one of the manufacturing conditions when the uncertainty of the physical property in the prediction model is maximum and the manufacturing conditions when the uncertainty of the physical property in the prediction model is minimum.
- the actual measurement data acquisition unit 21 further acquires second actual measurement data including the third manufacturing conditions calculated by the manufacturing condition calculation unit 25 and second actual measurement values obtained by measuring the physical properties of the sample manufactured based on the third manufacturing conditions.
- the model generation unit 23 updates the prediction model based on the second actual measurement data acquired by the actual measurement data acquisition unit 21. If the second actual measurement value is the set optimal value, the model generation unit 23 does not update the prediction model.
- the model generation unit 23 may generate a prediction model, i.e., a probabilistic prediction model, using Bayesian estimation.
- the first uncertainty may be a first variance
- the second uncertainty may be a second variance that is greater than the first variance.
- the model generation unit 23 may generate the prediction model according to the following formula:
- the model generating unit 23 sets the variance ⁇ 2 of the likelihood corresponding to the measured data to be small, and sets the variance ⁇ 2 of the likelihood corresponding to the virtual data to be large.
- the model generating unit 23 may set the variance ⁇ 2 of the likelihood corresponding to the measured data to 0.
- FIG. 3 is a flowchart showing an example of the operation of the physical property prediction device 1 according to the first embodiment.
- a user creates virtual data.
- the user may create virtual data by prediction based on experience. For example, when each of a plurality of parameters included in the second manufacturing conditions is an extremely small or large value, the physical property value of the sample may be predicted based on experience.
- the user uses a plurality of parameters having extremely small or large values as the second manufacturing conditions, and uses the predicted physical property value of the sample as a virtual value to create virtual data.
- the user may create virtual data using known physical property values of a material whose raw material or process is similar to that of the sample.
- known physical property values of a material the user uses the process of the material as the second manufacturing conditions, and uses the known physical property value of the material as a virtual value to create virtual data.
- the user also creates actual measurement data. Specifically, the user obtains actual measurement values by measuring the physical properties of a sample manufactured under the first manufacturing conditions. The user then creates the actual measurement data by associating the first manufacturing conditions with the actual measurement values. In creating the actual measurement data, the user may set one to five combinations of values of multiple parameters that make up the first manufacturing conditions. The user may then create the actual measurement data by measuring the physical properties of a prototype sample according to the combinations of parameter values that have been set. When setting combinations of multiple parameter values, the user may randomly set the values of multiple parameters of the first manufacturing conditions within a predetermined range. Alternatively, the user may set the values of multiple parameters of the first manufacturing conditions using a method of uniformly selecting parameter values within a predetermined range, such as Latin square sampling.
- the input screen generation unit 24 After the virtual data and actual measurement data are created, the input screen generation unit 24 generates an input screen in response to an input operation by the user using the input interface 3. Then, the input screen generation unit 24 displays the generated input screen on the display unit 4 (step S1).
- FIG. 4 is a diagram showing an example of an input screen SC in an example of the operation of the physical property prediction device 1 according to the first embodiment.
- the input screen SC has an input field F1 for inputting the first parameter to the fifth parameter, which are an example of the first manufacturing condition.
- the input screen SC also has an input field F2 for inputting the first physical property and the second physical property, which are an example of the actual measured value and the virtual value.
- the input screen SC also has an input field F3 for inputting the type of data, that is, either the virtual data or the actual measured data.
- step S2 After the input screen is displayed on the display unit 4, as shown in FIG. 3, the user inputs virtual data into the input screen displayed on the display unit 4 by performing an input operation using the input interface 3 (step S2).
- the user After inputting the virtual data, the user inputs the actual measurement data into the input screen displayed on the display unit 4 by performing an input operation using the input interface 3 (step S3). Steps S2 and S3 may be reversed.
- the model generation unit 23 After the virtual data and the actual measurement data are input, the model generation unit 23 generates a prediction model based on the input virtual data and the actual measurement data (step S4). In the example shown in Fig. 3, the model generation unit 23 generates a prediction model using Bayesian estimation according to the above-mentioned formulas (1) and (2). When generating a prediction model, the model generation unit 23 sets the variance ⁇ 2 of the likelihood corresponding to the actual measurement data to 0. In addition, the model generation unit 23 sets the variance ⁇ 2 of the likelihood corresponding to the virtual data to a value greater than 0. In addition, the model generation unit 23 sets the prior distribution p(A) to have a high probability density when the value of the physical property ⁇ changes smoothly.
- the model generation unit 23 may display the generated prediction model on the display unit 4.
- FIG. 5 is a diagram showing an example of a prediction model in an example of the operation of the physical property prediction device 1 according to the first embodiment.
- FIG. 6 is a diagram showing another example of a prediction model in an example of the operation of the physical property prediction device 1 according to the first embodiment.
- the model generation unit 23 generates, for example, the prediction models shown in FIG. 5 and FIG. 6.
- the horizontal axis in FIG. 5 and FIG. 6 is a parameter x, which is an example of the first manufacturing condition.
- the vertical axis in FIG. 5 and FIG. 6 is a physical property value ⁇ .
- the solid line graphs in FIG. 5 and FIG. 6 show the average value of the physical property ⁇ corresponding to the parameter x.
- the actual measurement data and the virtual data are located on the solid line graph showing the average value.
- the uncertainty is 0 near the actual measured data.
- the uncertainty is 0 because the model generation unit 23 sets the variance ⁇ 2 of the likelihood corresponding to the actual measured data to 0.
- the uncertainty is large near the virtual data.
- the uncertainty is large because the model generation unit 23 sets the variance ⁇ 2 of the likelihood corresponding to the virtual data to be larger than 0.
- an experimental plan is created as shown in FIG. 3 (step S5).
- the manufacturing condition calculation unit 25 calculates the third manufacturing conditions of the sample based on the prediction model generated by the model generation unit 23.
- FIG. 7 is a diagram showing an example of calculation of the third manufacturing conditions based on the prediction model in an operation example of the physical property prediction device 1 according to the first embodiment.
- the manufacturing condition calculation unit 25 calculates the manufacturing conditions when the uncertainty of the physical property in the prediction model is maximum and the manufacturing conditions when the uncertainty of the physical property in the prediction model is minimum as the third manufacturing conditions.
- the manufacturing condition calculation unit 25 calculates the value x1 of the parameter x when the uncertainty of the physical property ⁇ is maximum and the value x2 of the parameter x when the uncertainty of the physical property ⁇ is minimum as the third manufacturing conditions.
- the uncertainty of the physical property is maximum, there is a low probability but a possibility that very good physical properties can be obtained.
- the uncertainty of the physical property is minimum, there is a high probability that good physical properties can be obtained. Therefore, by setting the value x1 of parameter x when the uncertainty of the physical property ⁇ is maximum and the value x2 of parameter x when the uncertainty is minimum as the third manufacturing condition, the number of sample prototypes required to obtain the desired physical property can be reduced.
- the user creates a specific plan for manufacturing the sample using the calculated third manufacturing condition.
- the user carries out the experiment (step S6).
- the user first manufactures a sample in accordance with the experimental plan, i.e., the third manufacturing conditions.
- the sample is manufactured using a manufacturing device (not shown).
- the user measures the physical properties of the manufactured sample.
- the physical properties of the sample are measured using a measuring device (not shown) that is appropriate for the physical properties.
- Step S7 If the desired physical properties are obtained as a result of the experiment (Step S7: Yes), the process ends. On the other hand, if the desired physical properties are not obtained as a result of the experiment (Step S7: No) but additional experiments are possible (Step S8: Yes), the user inputs the actual measurement data obtained from the experiment into the input screen (Step S3). With the input of the actual measurement data obtained from the experiment, the model generation unit 23 updates the prediction model (Step S4).
- the actual data acquisition unit 21 acquires actual data including first manufacturing conditions of the sample and actual values of the physical properties of the sample manufactured based on the first manufacturing conditions.
- the virtual data acquisition unit 22 acquires virtual data including second manufacturing conditions of the sample and virtual values of the physical properties of the sample corresponding to the second manufacturing conditions.
- the model generation unit 23 generates a prediction model of the physical properties based on the actual data acquired by the actual data acquisition unit 21 and the virtual data acquired by the virtual data acquisition unit 22. Specifically, the model generation unit 23 generates a prediction model that has a first uncertainty of the physical properties for the actual data and a second uncertainty of the physical properties for the virtual data that is greater than the first uncertainty of the physical properties.
- the virtual data acquisition unit 22 may acquire, as virtual values, the physical property values of the sample that are predicted when some of the multiple parameters included in the second manufacturing conditions have extremely small or large values.
- the virtual data acquisition unit 22 may acquire, as virtual values, the physical property values of a material whose raw material or process is similar to that of the sample.
- the first uncertainty of the physical property is 0.
- the physical property prediction device 1 further includes an input screen generation unit 24 that generates an input screen for inputting actual measurement data and virtual data.
- the actual measurement data acquisition unit 21 acquires the actual measurement data input to the input screen generated by the input screen generation unit 24.
- the virtual data acquisition unit 22 acquires the virtual data input to the input screen generated by the input screen generation unit 24.
- the model generation unit 23 generates a prediction model using Bayesian estimation according to formulas (1) and (2). That is, the model generation unit 23 generates a prediction model that has a first variance for the actual measured data and a second variance for the virtual data that is larger than the first variance.
- the manufacturing condition calculation unit 25 calculates the third manufacturing condition for the sample based on the prediction model generated by the model generation unit 23.
- the third manufacturing conditions include at least one of the manufacturing conditions when the uncertainty of the physical property in the prediction model is maximum and the manufacturing conditions when the uncertainty of the physical property in the prediction model is minimum.
- the actual measurement data acquisition unit 21 further acquires second actual measurement data including the third manufacturing conditions calculated by the manufacturing condition calculation unit 25 and second actual measurement values obtained by measuring the physical properties of the sample manufactured based on the third manufacturing conditions. Furthermore, the model generation unit 23 updates the prediction model based on the second actual measurement data acquired by the actual measurement data acquisition unit 21.
- the model generation unit 23 does not update the prediction model.
- Fig. 8 is a block diagram showing a property prediction apparatus 1 according to the second embodiment.
- control unit 2 of the physical property prediction device 1 further includes an uncertainty setting unit 26 and a setting screen generating unit 27 in addition to the configuration of the first embodiment.
- the uncertainty setting unit 26 sets a first uncertainty of the physical property and a second uncertainty of the physical property.
- the model generation unit 23 generates a prediction model based further on the first uncertainty of the physical property and the second uncertainty of the physical property set by the uncertainty setting unit 26.
- the setting screen generating unit 27 generates a setting screen for setting a first uncertainty of the physical property and a second uncertainty of the physical property.
- the setting screen generating unit 27 displays the generated setting screen on the display unit 4.
- the uncertainty setting unit 26 sets the first uncertainty of the physical property and the second uncertainty of the physical property in response to an input operation on the setting screen generated by the setting screen generating unit 27. More specifically, the uncertainty setting unit 26 sets the first uncertainty of the physical property and the second uncertainty of the physical property in response to an input operation using the input interface 3 on the setting screen displayed on the display unit 4.
- the setting screen generating unit 27 may display the setting screen simultaneously with the input screen displayed by the input screen generating unit 24. Alternatively, the setting screen generating unit 27 may display the setting screen at a timing different from that of the input screen displayed by the input screen generating unit 24.
- FIG. 9 is a flowchart showing an example of the operation of the physical property prediction device 1 according to the second embodiment.
- the setting screen generating unit 27 displays the setting screen simultaneously with the input screen displayed by the input screen generating unit 24 (step S11).
- FIG. 10 is a diagram showing an example of an input screen SC in an example of the operation of the physical property prediction device according to the second embodiment.
- the setting screen generating unit 27 displays a setting screen SC2 on the input screen SC.
- the setting screen SC2 has a slider bar S that allows input of the ratio between the weight of the actual measured data and the weight of the virtual data. By sliding the slider bar S to input the ratio between the weight of the actual measured data and the weight of the virtual data, it is possible to set the first uncertainty and the second uncertainty that correspond to the input ratio.
- the uncertainty setting unit 26 sets the first uncertainty and the second uncertainty in response to an input operation on the setting screen (step S9).
- the model generation unit 23 generates a prediction model based on the input virtual data and actual measurement data and the set first uncertainty and second uncertainty (step S4).
- the uncertainty setting unit 26 sets a first uncertainty of the physical property and a second uncertainty of the physical property. Furthermore, the model generation unit 23 generates a prediction model based on the first uncertainty of the physical property and the second uncertainty of the physical property set by the uncertainty setting unit 26.
- the setting screen generating unit 27 generates a setting screen for setting the first uncertainty of the physical property and the second uncertainty of the physical property.
- the uncertainty setting unit 26 sets the first uncertainty of the physical property and the second uncertainty of the physical property in response to an input operation on the setting screen generated by the setting screen generating unit 27.
- the first uncertainty and the second uncertainty can be easily set using the setting screen.
- FIG. 11 is a block diagram showing a property prediction apparatus 1 according to the third embodiment.
- control unit 2 of the physical property prediction device 1 further includes a virtual data complementation unit 28 in addition to the configuration of the first embodiment.
- the virtual data completion unit 28 completes the virtual data.
- the virtual data completion unit 28 completes the virtual data by filling in the missing data.
- the virtual data acquisition unit 22 acquires the virtual data complemented by the virtual data complementation unit 28.
- the virtual data complementing unit 28 may complement the virtual data when some of the multiple parameters included in the second manufacturing conditions have extremely small or large values and a virtual value predicted based on the some parameters are input to the input screen. Specifically, the virtual data complementing unit 28 may complement the second manufacturing conditions of the virtual data by calculating the values of parameters other than the some of the multiple parameters.
- FIG. 12 is a flowchart showing an example of the operation of the physical property prediction device 1 according to the third embodiment.
- FIG. 13 is a diagram showing an example of an input screen in the example of the operation of the physical property prediction device 1 according to the third embodiment.
- the virtual data completion unit 28 completes the virtual data when the virtual data entered on the input screen is not complete (step S10).
- the user's tacit knowledge may predict that the physical property value of the sample is ⁇ * .
- the user inputs x1 * as the value of parameter x1 and ⁇ * as the physical property value in the input screen, and does not input the values of parameters other than x1 .
- an extremely small value of 0 is input as the value of the first parameter in the input screen SC.
- 0.0 is input as the first physical property and the second physical property in the input screen SC.
- the values of parameters other than the first parameter are set to undetermined, that is, ***.
- the virtual data complementing unit 28 complements the virtual data by calculating and adding the values of parameters x2 , ..., xm other than x1 . For example, the virtual data complementing unit 28 divides each search area of the predetermined parameters x2 , ..., xm into k levels. Then, the virtual data complementing unit 28 calculates k m-1 values of parameters x2 , ..., xm by combining values selected from each divided area divided into k levels. Instead of the calculation method using k levels, the virtual data complementing unit 28 may calculate the values of parameters x2 , ..., xm by generating m-1-dimensional uniform random numbers.
- the physical property value of the sample may be predicted by the user's tacit knowledge.
- the user inputs the values of 2 to m-1 parameters in the input screen, inputs the predicted physical property value, and does not input parameters other than the 2 to m-1 parameters.
- an extremely large value of 100 is input as the value of the third parameter in the input screen SC.
- an extremely large value of 100 is input as the value of the fourth parameter in the input screen SC.
- 100.0 is input as the first physical property in the input screen SC.
- 133.3 is input as the second physical property in the input screen SC.
- the values of parameters other than the third and fourth parameters are set to undetermined in the input screen SC.
- the virtual data completion unit 28 divides, for example, the search area of each parameter other than 2 to m-1 parameters into k levels. Then, the virtual data completion unit 28 calculates the value of the parameter by combining values selected from each of the divided areas divided into k levels.
- the user may input the actual measurement data of that substance as virtual data into the input screen.
- the virtual data completion unit 28 does not complete the virtual data.
- the virtual data completion unit 28 completes the virtual data. Furthermore, the virtual data acquisition unit 22 acquires the virtual data completed by the virtual data completion unit 28.
- the virtual data complementation unit 28 complements the second manufacturing conditions of the virtual data by calculating the values of the parameters other than the some parameters among the multiple parameters.
- FIG. 14 is a block diagram showing a property prediction device 1 according to the fourth embodiment.
- FIG. 1 an example has been described in which the input interface 3 and the display unit 4 are provided in the physical property prediction device 1.
- the input interface 3 and the display unit 4 are provided in a user's terminal device 9.
- the physical property prediction device 1 and the terminal device 9 are connected so as to be able to communicate with each other via a network 8.
- the physical property prediction device 1 includes a communication unit 7.
- the communication unit 7 is an interface for communicating with a terminal device 9 via a network 8.
- the communication unit 7 may be a network card, a network adapter, or the like.
- the communication unit 7 transmits an input screen generated by the input screen generation unit 24 to the terminal device 9.
- the communication unit 7 receives the actual measurement data and virtual data input to the input screen from the terminal device 9.
- the actual measurement data acquisition unit 21 acquires the actual measurement data received by the communication unit 7.
- the virtual data acquisition unit 22 acquires the virtual data received by the communication unit 7.
- the model generation unit 23 may transmit the prediction model generated by the model generation unit 23 to the terminal device 9 via the communication unit 7.
- the prediction model transmitted to the terminal device 9 may be displayed on the display unit 4 of the terminal device 9.
- the manufacturing condition calculation unit 25 may transmit the manufacturing conditions calculated by the manufacturing condition calculation unit 25 to the terminal device 9 via the communication unit 7.
- the manufacturing conditions transmitted to the terminal device 9 may be displayed on the display unit 4 of the terminal device 9.
- a user using the terminal device 9 can search for optimal manufacturing conditions through an input screen provided by the property prediction device 1, i.e., the server.
Landscapes
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Analytical Chemistry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
試料の第1の製造条件と、前記第1の製造条件に基づいて製造された前記試料の物性を実測した実測値と、を含む実測データを取得する実測データ取得部と、
前記試料の第2の製造条件と、前記第2の製造条件に対応する前記試料の物性を仮想した仮想値と、を含む仮想データを取得する仮想データ取得部と、
前記実測データ取得部により取得された前記実測データと、前記仮想データ取得部により取得された前記仮想データとに基づいて、前記実測データに対して前記物性の第1の不確かさを有し、前記仮想データに対して前記物性の第1の不確かさよりも大きい前記物性の第2の不確かさを有するような前記物性の予測モデルを生成するモデル生成部と、
を備える。
前記実測データ取得部は、前記入力画面生成部により生成された前記入力画面に入力された前記実測データを取得し、
前記仮想データ取得部は、前記入力画面生成部により生成された前記入力画面に入力された前記仮想データを取得してもよい。
前記実測データ取得部は、前記通信部により受信された前記実測データを取得し、
前記仮想データ取得部は、前記通信部により受信された前記仮想データを取得してもよい。
前記仮想データ取得部は、前記仮想データ補完部により補完された前記仮想データを取得してもよい。
前記モデル生成部は、前記不確かさ設定部により設定された前記物性の第1の不確かさ及び前記物性の第2の不確かさに更に基づいて前記予測モデルを生成してもよい。
前記不確かさ設定部は、前記設定画面生成部により生成された前記設定画面に対する入力操作に応じて、前記物性の第1の不確かさ及び前記物性の第2の不確かさを設定してもよい。
前記モデル生成部は、前記実測データ取得部により取得された前記第2の実測データに基づいて前記予測モデルを更新してもよい。
試料の第1の製造条件と、前記第1の製造条件に基づいて製造された前記試料の物性を実測した実測値と、を含む実測データを取得する工程と、
前記試料の第2の製造条件と、前記第2の製造条件に対応する前記試料の物性を仮想した仮想値と、を含む仮想データを取得する工程と、
前記取得された実測データ及び仮想データに基づいて、前記実測データに対して前記物性の第1の不確かさを有し、前記仮想データに対して前記物性の第1の不確かさよりも大きい前記物性の第2の不確かさを有するような前記物性の予測モデルを生成する工程と、
を備える。
コンピュータに、
試料の第1の製造条件と、前記第1の製造条件に基づいて製造された前記試料の物性を実測した実測値と、を含む実測データを取得する手順、
前記試料の第2の製造条件と、前記第2の製造条件に対応する前記試料の物性を仮想した仮想値と、を含む仮想データを取得する手順、及び
前記取得された実測データ及び仮想データに基づいて、前記実測データに対して前記物性の第1の不確かさを有し、前記仮想データに対して前記物性の第1の不確かさよりも大きい前記物性の第2の不確かさを有するような前記物性の予測モデルを生成する手順
を実行させる。
先ず、図1~図7を参照して、第1の実施形態による物性予測装置について説明する。図1は、第1の実施形態による物性予測装置1を示す概念図である。
次に、以上の構成を有する物性予測装置1の動作例について説明する。図3は、第1の実施形態による物性予測装置1の動作例を示すフローチャートである。先ず、図3の前提として、ユーザは仮想データを作成する。ユーザは、経験に基づく予測によって仮想データを作成してもよい。例えば、第2の製造条件に含まれる複数のパラメータのそれぞれが極端に小さい又は大きい値であるときに、経験に基づいて試料の物性値が予測される場合がある。経験に基づいて試料の物性値が予測される場合、ユーザは、極端に小さい又は大きい値をとる複数のパラメータを第2の製造条件として使用し、予測される試料の物性値を仮想値として使用して、仮想データを作成する。或いは、ユーザは、原材料又はプロセスが試料に類似する物質の既知の物性値を用いて、仮想データを作成してもよい。物質の既知の物性値を用いる場合、ユーザは、当該物質のプロセスを第2の製造条件として使用し、当該物質の既知の物性値を仮想値として使用して、仮想データを作成する。
次に、設定された不確かさに基づいて予測モデルを生成する第2の実施形態について、第1の実施形態との差異を中心に説明する。図8は、第2の実施形態による物性予測装置1を示すブロック図である。
次に、仮想データを補完する第3の実施形態について、第1の実施形態との差異を中心に説明する。図11は、第3の実施形態による物性予測装置1を示すブロック図である。
次に、ユーザの端末装置に入力画面を提供する第4の実施形態について、第1の実施形態との差異を中心に説明する。図14は、第4の実施形態による物性予測装置1を示すブロック図である。
Claims (18)
- 試料の第1の製造条件と、前記第1の製造条件に基づいて製造された前記試料の物性を実測した実測値と、を含む実測データを取得する実測データ取得部と、
前記試料の第2の製造条件と、前記第2の製造条件に対応する前記試料の物性を仮想した仮想値と、を含む仮想データを取得する仮想データ取得部と、
前記実測データ取得部により取得された前記実測データと、前記仮想データ取得部により取得された前記仮想データとに基づいて、前記実測データに対して前記物性の第1の不確かさを有し、前記仮想データに対して前記物性の第1の不確かさよりも大きい前記物性の第2の不確かさを有するような前記物性の予測モデルを生成するモデル生成部と、
を備える物性予測装置。 - 前記仮想データ取得部は、前記第2の製造条件に含まれる複数のパラメータのうちの少なくとも1つのパラメータの値が極端に小さい又は大きい場合に予測される前記試料の物性値を、前記仮想値として取得する、請求項1に記載の物性予測装置。
- 前記仮想データ取得部は、原材料又はプロセスが前記試料に類似する物質の物性値を、前記仮想値として取得する、請求項1に記載の物性予測装置。
- 前記物性の第1の不確かさは0である、請求項1に記載の物性予測装置。
- 前記実測データ及び前記仮想データを入力するための入力画面を生成する入力画面生成部を更に備え、
前記実測データ取得部は、前記入力画面生成部により生成された前記入力画面に入力された前記実測データを取得し、
前記仮想データ取得部は、前記入力画面生成部により生成された前記入力画面に入力された前記仮想データを取得する、請求項1に記載の物性予測装置。 - 前記入力画面生成部により生成された前記入力画面をユーザの端末装置に送信し、前記入力画面に入力された前記実測データ及び前記仮想データを前記端末装置から受信する通信部を更に備え、
前記実測データ取得部は、前記通信部により受信された前記実測データを取得し、
前記仮想データ取得部は、前記通信部により受信された前記仮想データを取得する、請求項5に記載の物性予測装置。 - 前記仮想データを補完する仮想データ補完部を更に備え、
前記仮想データ取得部は、前記仮想データ補完部により補完された前記仮想データを取得する、請求項5に記載の物性予測装置。 - 前記仮想データ補完部は、前記第2の製造条件に含まれる複数のパラメータのうちの極端に小さい又は大きい値を有する一部のパラメータと、前記一部のパラメータに基づいて予測される前記仮想値と、が前記入力画面に入力されたときに、前記複数のパラメータのうちの前記一部のパラメータ以外のパラメータの値を算出することで、前記仮想データの前記第2の製造条件を補完する、請求項7に記載の物性予測装置。
- 前記物性の第1の不確かさ及び前記物性の第2の不確かさを設定する不確かさ設定部を更に備え、
前記モデル生成部は、前記不確かさ設定部により設定された前記物性の第1の不確かさ及び前記物性の第2の不確かさに更に基づいて前記予測モデルを生成する、請求項1に記載の物性予測装置。 - 前記物性の第1の不確かさ及び前記物性の第2の不確かさを設定するための設定画面を生成する設定画面生成部を更に備え、
前記不確かさ設定部は、前記設定画面生成部により生成された前記設定画面に対する入力操作に応じて、前記物性の第1の不確かさ及び前記物性の第2の不確かさを設定する、請求項9に記載の物性予測装置。 - 前記モデル生成部は、ベイズ推定を用いて前記予測モデルを生成し、前記第1の不確かさは、第1の分散であり、前記第2の不確かさは、前記第1の分散よりも大きい第2の分散である、請求項1に記載の物性予測装置。
- 前記モデル生成部は、次式にしたがって前記予測モデルを生成する、請求項11に記載の物性予測装置。
- 前記モデル生成部により生成された前記予測モデルに基づいて前記試料の第3の製造条件を算出する製造条件算出部を更に備える、請求項1乃至12のいずれか1項に記載の物性予測装置。
- 前記第3の製造条件は、前記予測モデル中の前記物性の不確かさが最大になるときの製造条件及び前記予測モデル中の前記物性の不確かさが最小になるときの製造条件の少なくとも1つを含む、請求項13に記載の物性予測装置。
- 前記実測データ取得部は、前記製造条件算出部により算出された前記第3の製造条件と、前記第3の製造条件に基づいて製造された前記試料の物性を実測した第2の実測値と、を含む第2の実測データを更に取得し、
前記モデル生成部は、前記実測データ取得部により取得された前記第2の実測データに基づいて前記予測モデルを更新する、請求項13に記載の物性予測装置。 - 前記モデル生成部は、前記第2の実測値が設定された最適値である場合には、前記予測モデルを更新しない、請求項15に記載の物性予測装置。
- 試料の第1の製造条件と、前記第1の製造条件に基づいて製造された前記試料の物性を実測した実測値と、を含む実測データを取得する工程と、
前記試料の第2の製造条件と、前記第2の製造条件に対応する前記試料の物性を仮想した仮想値と、を含む仮想データを取得する工程と、
前記取得された実測データ及び仮想データに基づいて、前記実測データに対して前記物性の第1の不確かさを有し、前記仮想データに対して前記物性の第1の不確かさよりも大きい前記物性の第2の不確かさを有するような前記物性の予測モデルを生成する工程と、
を備える物性予測方法。 - コンピュータに、
試料の第1の製造条件と、前記第1の製造条件に基づいて製造された前記試料の物性を実測した実測値と、を含む実測データを取得する手順、
前記試料の第2の製造条件と、前記第2の製造条件に対応する前記試料の物性を仮想した仮想値と、を含む仮想データを取得する手順、及び
前記取得された実測データ及び仮想データに基づいて、前記実測データに対して前記物性の第1の不確かさを有し、前記仮想データに対して前記物性の第1の不確かさよりも大きい前記物性の第2の不確かさを有するような前記物性の予測モデルを生成する手順
を実行させるための物性予測プログラム。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202480037082.9A CN121241399A (zh) | 2023-06-06 | 2024-05-29 | 物性预测装置、物性预测方法以及物性预测程序 |
| IL325095A IL325095A (en) | 2023-06-06 | 2024-05-29 | Physical property prediction device, physical property prediction method, and physical property prediction program |
| KR1020257040870A KR20260020108A (ko) | 2023-06-06 | 2024-05-29 | 물성 예측 장치, 물성 예측 방법, 및 물성 예측 프로그램 |
| EP24819226.2A EP4726725A1 (en) | 2023-06-06 | 2024-05-29 | Physical property prediction device, physical property prediction method, and physical property prediction program |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2023093364A JP2024175522A (ja) | 2023-06-06 | 2023-06-06 | 物性予測装置、物性予測方法、及び物性予測プログラム |
| JP2023-093364 | 2023-06-06 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024252995A1 true WO2024252995A1 (ja) | 2024-12-12 |
Family
ID=93795953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2024/019633 Ceased WO2024252995A1 (ja) | 2023-06-06 | 2024-05-29 | 物性予測装置、物性予測方法、及び物性予測プログラム |
Country Status (6)
| Country | Link |
|---|---|
| EP (1) | EP4726725A1 (ja) |
| JP (1) | JP2024175522A (ja) |
| KR (1) | KR20260020108A (ja) |
| CN (1) | CN121241399A (ja) |
| IL (1) | IL325095A (ja) |
| WO (1) | WO2024252995A1 (ja) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7729965B1 (en) * | 2005-04-26 | 2010-06-01 | Fannie Mae | Collateral valuation confidence scoring system |
| WO2020188971A1 (ja) | 2019-03-15 | 2020-09-24 | 富士フイルム株式会社 | 特徴推定方法、特徴推定装置、プログラム及び記録媒体 |
| WO2021200281A1 (ja) | 2020-03-31 | 2021-10-07 | Mi-6株式会社 | 試験評価システム、プログラムおよび試験評価方法 |
| JP2022014618A (ja) * | 2020-07-07 | 2022-01-20 | 株式会社日立製作所 | 予測装置および予測方法 |
| JP2022065466A (ja) * | 2020-10-15 | 2022-04-27 | 株式会社ニコン | 物性予測装置、物性予測方法、及びプログラム |
| JP2022082064A (ja) * | 2020-11-20 | 2022-06-01 | 富士通株式会社 | 混合物物性特定方法、混合物物性特定装置、及び混合物物性特定プログラム |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7205122B2 (ja) * | 2018-09-13 | 2023-01-17 | 住友金属鉱山株式会社 | ペーストの設計方法、ペーストの製造方法 |
-
2023
- 2023-06-06 JP JP2023093364A patent/JP2024175522A/ja active Pending
-
2024
- 2024-05-29 EP EP24819226.2A patent/EP4726725A1/en active Pending
- 2024-05-29 IL IL325095A patent/IL325095A/en unknown
- 2024-05-29 CN CN202480037082.9A patent/CN121241399A/zh active Pending
- 2024-05-29 KR KR1020257040870A patent/KR20260020108A/ko active Pending
- 2024-05-29 WO PCT/JP2024/019633 patent/WO2024252995A1/ja not_active Ceased
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7729965B1 (en) * | 2005-04-26 | 2010-06-01 | Fannie Mae | Collateral valuation confidence scoring system |
| WO2020188971A1 (ja) | 2019-03-15 | 2020-09-24 | 富士フイルム株式会社 | 特徴推定方法、特徴推定装置、プログラム及び記録媒体 |
| WO2021200281A1 (ja) | 2020-03-31 | 2021-10-07 | Mi-6株式会社 | 試験評価システム、プログラムおよび試験評価方法 |
| JP2022014618A (ja) * | 2020-07-07 | 2022-01-20 | 株式会社日立製作所 | 予測装置および予測方法 |
| JP2022065466A (ja) * | 2020-10-15 | 2022-04-27 | 株式会社ニコン | 物性予測装置、物性予測方法、及びプログラム |
| JP2022082064A (ja) * | 2020-11-20 | 2022-06-01 | 富士通株式会社 | 混合物物性特定方法、混合物物性特定装置、及び混合物物性特定プログラム |
Also Published As
| Publication number | Publication date |
|---|---|
| CN121241399A (zh) | 2025-12-30 |
| JP2024175522A (ja) | 2024-12-18 |
| EP4726725A1 (en) | 2026-04-15 |
| IL325095A (en) | 2026-02-01 |
| KR20260020108A (ko) | 2026-02-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Symbolic regression in materials science | |
| JP7199489B2 (ja) | 量子測定ノイズの除去方法、システム、電子機器、及び媒体 | |
| US20220207370A1 (en) | Inferring device, training device, inferring method, and training method | |
| JP6555411B2 (ja) | 情報処理方法および情報処理装置 | |
| CN114037084A (zh) | 量子测量设备校准方法及装置、电子设备和介质 | |
| TWI802294B (zh) | 實驗點推薦裝置、實驗點推薦方法及半導體裝置製造系統 | |
| JP2020187642A (ja) | 最適化装置、最適化システム、最適化方法および最適化プログラム | |
| JP7334298B2 (ja) | 量子測定機器の較正方法および装置、電子機器ならびに媒体 | |
| TW202407483A (zh) | 模型產生方法、電腦程式及資訊處理裝置 | |
| CN118538328B (zh) | 二面角能量预测模型的训练方法和装置 | |
| Comess et al. | A Bayesian framework for incorporating exposure uncertainty into health analyses with application to air pollution and stillbirth | |
| Huang et al. | Direct entanglement detection of quantum systems using machine learning | |
| Tan et al. | Enhanced sampling of robust molecular datasets with uncertainty-based collective variables | |
| WO2023238525A1 (ja) | 試作条件提案システム、試作条件提案方法 | |
| Senapati et al. | Towards redefining the reproducibility in quantum computing: A data analysis approach on nisq devices | |
| CN114897175A (zh) | 量子测量设备的噪声消除方法及装置、电子设备和介质 | |
| JP2003288579A (ja) | 最適フィッティングパラメータ決定方法および装置、並びに最適フィッティングパラメータ決定プログラム | |
| Situ et al. | Automl-driven optimization of variational quantum circuit | |
| WO2024252995A1 (ja) | 物性予測装置、物性予測方法、及び物性予測プログラム | |
| JP7631658B2 (ja) | 量子回路の作成方法と装置及びコンピュータ機器とプログラム | |
| Jin et al. | Extending Equivalent Circuit Models for State of Charge and Lifetime Estimation | |
| JP2005038216A (ja) | パラメータ調整装置 | |
| Pelofske et al. | Inferring the dynamics of the state evolution during quantum annealing | |
| TW202430848A (zh) | 光譜度量衡方法 | |
| US20260100253A1 (en) | Image processing device, image processing method, and non-transitory computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24819226 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 325095 Country of ref document: IL Ref document number: 202517121202 Country of ref document: IN |
|
| WWP | Wipo information: published in national office |
Ref document number: 202517121202 Country of ref document: IN |
|
| WWP | Wipo information: published in national office |
Ref document number: 325095 Country of ref document: IL |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024819226 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2024819226 Country of ref document: EP Effective date: 20260107 |
|
| ENP | Entry into the national phase |
Ref document number: 2024819226 Country of ref document: EP Effective date: 20260107 |
|
| ENP | Entry into the national phase |
Ref document number: 2024819226 Country of ref document: EP Effective date: 20260107 |
|
| ENP | Entry into the national phase |
Ref document number: 2024819226 Country of ref document: EP Effective date: 20260107 |
|
| ENP | Entry into the national phase |
Ref document number: 2024819226 Country of ref document: EP Effective date: 20260107 |
|
| WWP | Wipo information: published in national office |
Ref document number: 2024819226 Country of ref document: EP |