WO2023167107A1 - 情報処理装置、情報処理システム、プログラム、及び材料組成探索方法 - Google Patents

情報処理装置、情報処理システム、プログラム、及び材料組成探索方法 Download PDF

Info

Publication number
WO2023167107A1
WO2023167107A1 PCT/JP2023/006789 JP2023006789W WO2023167107A1 WO 2023167107 A1 WO2023167107 A1 WO 2023167107A1 JP 2023006789 W JP2023006789 W JP 2023006789W WO 2023167107 A1 WO2023167107 A1 WO 2023167107A1
Authority
WO
WIPO (PCT)
Prior art keywords
explanatory variables
information processing
physical properties
mixed material
ising model
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
Application number
PCT/JP2023/006789
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
俊 坂口
皓亮 角田
好成 奥野
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Resonac Corp
Original Assignee
Resonac Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Resonac Corp filed Critical Resonac Corp
Priority to JP2024504664A priority Critical patent/JP7601279B2/ja
Priority to EP23763366.4A priority patent/EP4489013A4/en
Priority to CN202380023904.3A priority patent/CN118765418A/zh
Priority to US18/841,022 priority patent/US20250191704A1/en
Publication of WO2023167107A1 publication Critical patent/WO2023167107A1/ja
Anticipated expiration legal-status Critical
Priority to JP2024204074A priority patent/JP2025028938A/ja
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • 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
    • 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

Definitions

  • the present disclosure relates to an information processing device, an information processing system, a program, and a material composition search method.
  • combinatorial optimization problem that selects the optimal combination from various combinations of elements, such as searching for a material composition with optimal physical properties.
  • the number of combinations increases exponentially as the number of elements increases, so it may not be possible to solve it within a realistic amount of time. For example, when 100 kinds of materials are combined in increments of 1% to generate a mixed material, the number of combinations is 5 ⁇ 10 58 .
  • An annealing machine using the Ising model has been proposed as an architecture specialized for solving such combinatorial optimization problems.
  • the annealing machine can efficiently solve combinatorial optimization problems converted to Ising models.
  • Non-Patent Document 1 there is known a technique for optimizing the thermophysical properties of mixed refrigerants using a computer architecture specialized for combinatorial optimization problems (see, for example, Non-Patent Document 1).
  • a user who wants to solve a combinatorial optimization problem of material compositions that asymptotically (approximately) a target physical property value with an annealing machine needs to prepare a function to convert to an Ising model.
  • the function to be converted to the Ising model must be described so as to include explanatory variables, and must satisfy the constraint that the variable group at the minimum value is the optimization result (optimal mixed material composition).
  • the function to be converted into the Ising model includes arbitrary constants such as target values of explanatory variables and weighting coefficients, and these constants need to be adjusted.
  • the present disclosure provides an information processing device, an information processing system, a program, and a material composition search that can reduce the labor of creating an Ising model for having an annealing-type computing device solve a combinatorial optimization problem of material compositions that asymptotically approach a target physical property.
  • the purpose is to provide a method.
  • the present disclosure has the configuration shown below.
  • An information processing device that supports creation of an Ising model for solving a combination optimization problem of material compositions that asymptotically approach a target physical property by an annealing-type computing device, The one or more explanatory variables and the physical properties of the mixed material by a trained machine learning model for predicting the physical properties of the mixed material described using one or more explanatory variables of the function converted to the Ising model.
  • a calculation unit that calculates the relationship between a determination unit that determines an optimum value and an allowable variation range of the one or more explanatory variables for the target physical properties based on the relationship between the one or more explanatory variables and the physical properties of the mixed material; outputting the determined optimum values of the one or more explanatory variables as target values of the one or more explanatory variables in the function, and in the function based on the determined allowable variation range of the one or more explanatory variables an output unit that outputs weighting coefficients of the one or more explanatory variables;
  • the output unit outputs a smaller weighting factor for the explanatory variable with a larger allowable change range, and a larger weighting factor for the explanatory variable with a smaller allowable change range.
  • [1] or [ 2] The information processing apparatus described above.
  • the machine learning model is characterized in that the relationship between the properties of the mixed material that can be described by a weighted average of the ratio of the material composition and the physical properties of the mixed material has been learned from experimental data [ The information processing apparatus according to any one of [1] to [4].
  • a conversion unit that converts the function obtained by substituting the target values of the one or more explanatory variables and the weighting coefficients of the one or more explanatory variables output by the output unit into the Ising model;
  • An annealing-type computing device that uses an Ising model, and an information processing device that assists creation of an Ising model for causing the computing device to solve a combinatorial optimization problem of material compositions that asymptotically approach a target physical property.
  • An information processing system The one or more explanatory variables and the physical properties of the mixed material by a trained machine learning model for predicting the physical properties of the mixed material described using one or more explanatory variables of the function converted to the Ising model.
  • a calculation unit that calculates the relationship between a determination unit that determines an optimum value and an allowable variation range of the one or more explanatory variables for the target physical properties based on the relationship between the one or more explanatory variables and the physical properties of the mixed material; outputting the determined optimum values of the one or more explanatory variables as target values of the one or more explanatory variables in the function, and in the function based on the determined allowable variation range of the one or more explanatory variables an output unit that outputs weighting coefficients of the one or more explanatory variables; a transforming unit that transforms the function obtained by substituting the target values of the one or more predictor variables and the weighting factors of the one or more predictor variables output by the output unit into the Ising model; an optimum solution calculation unit that calculates an optimum solution for the material composition that asymptotically approaches the target value using the Ising model; a display unit that displays the optimum solution of the material composition that asymptotically approaches the target value;
  • An information processing device that supports creation of an Ising model for solving a combinatorial optimization problem of material composition that asymptotically approaches a target physical property by an annealing-type computing device, The one or more explanatory variables and the physical properties of the mixed material by a trained machine learning model for predicting the physical properties of the mixed material described using one or more explanatory variables of the function converted to the Ising model.
  • a calculation unit that calculates the relationship between A determination unit that determines an optimum value and an allowable change range of the one or more explanatory variables for the target physical properties based on the relationship between the one or more explanatory variables and the physical properties of the mixed material; outputting the determined optimum values of the one or more explanatory variables as target values of the one or more explanatory variables in the function, and in the function based on the determined allowable variation range of the one or more explanatory variables an output unit that outputs weighting coefficients of the one or more explanatory variables;
  • An annealing-type computing device that uses an Ising model, and an information processing device that assists creation of an Ising model for causing the computing device to solve a combinatorial optimization problem of material compositions that asymptotically approach a target physical property.
  • a material composition search method for an information processing system The one or more explanatory variables and the physical properties of the mixed material by a trained machine learning model for predicting the physical properties of the mixed material described using one or more explanatory variables of the function converted to the Ising model.
  • an information processing device an information processing system, a program, and a material that can reduce the effort of creating an Ising model for having an annealing-type computing device solve a combinatorial optimization problem of material compositions that asymptotically approach a target physical property Compositional search methods can be provided.
  • FIG. 1 is a configuration diagram of an example of an information processing system according to an embodiment
  • FIG. 1 is a hardware configuration diagram of an example of a computer according to the embodiment
  • FIG. 1 is a configuration diagram of an example of an information processing system according to an embodiment
  • FIG. It is the flowchart which showed an example of the processing procedure of the material composition search method using the information processing system which concerns on this embodiment.
  • FIG. 4 is an explanatory diagram of an example of a function for conversion into an Ising model
  • FIG. 4 is an explanatory diagram of an example of a problem to be solved as a combinatorial optimization problem
  • FIG. 4 is an explanatory diagram of an example of a problem to be solved as a combinatorial optimization problem
  • FIG. 4 is an explanatory diagram of an example of a problem to be solved as a combinatorial optimization problem
  • FIG. 4 is an explanatory diagram of an example of a problem to be solved as a combinatorial optimization problem
  • FIG. 4 is an explanatory diagram of an
  • FIG. 4 is an explanatory diagram of an example of a problem to be solved as a combinatorial optimization problem; It is a figure explaining cooperation with combinatorial optimization and machine learning.
  • 4 is a configuration diagram of an example of material information
  • FIG. FIG. 4 is a configuration diagram of an example of experimental data
  • FIG. 10 is a diagram showing an example of the relationship between the calculated explanatory variable X i and the variable Z
  • FIG. 11 is a diagram illustrating an example of an optimum value and allowable change width of an explanatory variable X i
  • FIG. 4 is an explanatory diagram of an example of a process of determining a weighting factor A i of an explanatory variable X i
  • FIG. 10 is a diagram illustrating an example of the relationship between the threshold value C for allowable deviation from the minimum variable Z and the shape of the explanatory variable region of the mixed material that asymptotically approaches the target physical properties;
  • FIG. 1 is a configuration diagram of an example of an information processing system according to this embodiment.
  • the information processing system 1 shown in FIG. 1 has a configuration including an annealing-type computing device 10 and an information processing device 12 .
  • the annealing-type computing device 10 and the information processing device 12 are connected for data communication via a communication network 18 such as a local area network (LAN) or the Internet.
  • LAN local area network
  • the annealing computing device 10 is an example of a device that solves combinatorial optimization problems using the Ising model.
  • the annealing-type computing device 10 is, for example, an annealing machine using an Ising model.
  • the annealing-type computing device 10 may be realized by a quantum computer, or may be realized by Digital Annealer (registered trademark), which is a computer architecture in which the annealing method is realized by a digital circuit.
  • the annealing machine solves the combinatorial optimization problem reduced to the Ising model by the convergence behavior of the Ising model.
  • An Ising model is a statistical mechanics model that represents the behavior of a magnetic material.
  • the Ising model has the property that the spin state is updated so that the energy (Hamiltonian) is minimized by the interaction between the spins of the magnetic material, and finally the energy is minimized.
  • An annealing machine reduces a combinatorial optimization problem to an Ising model and finds the state with the minimum energy, thereby obtaining that state as the optimal solution of the combinatorial optimization problem.
  • the information processing device 12 is a device operated by a user, such as a PC, tablet terminal, or smartphone.
  • the information processing device 12 receives input from the user of information necessary for causing the annealing-type computing device 10 to solve the combinatorial optimization problem reduced to the Ising model, and causes the annealing-type computing device 10 to solve the Ising model.
  • the information necessary for the annealing computing device 10 to solve the combinatorial optimization problem reduced to the Ising model includes information on the function to be converted into the Ising model.
  • the information processing apparatus 12 assists the user in creating the Ising model by assisting the user in creating a function to be converted into the Ising model as described later.
  • the information processing device 12 also receives the optimal solution of the combinatorial optimization problem solved by the annealing-type computing device 10, and outputs the optimal solution so that the user can check it, such as by displaying it on a display device.
  • the information processing system 1 of FIG. 1 is an example, and a user accesses and uses the information processing device 12 from a user terminal (not shown) connected to the information processing device 12 via the communication network 18.
  • a user terminal not shown
  • the communication network 18 may be in the form
  • annealing-type computing device 10 may be implemented as a cloud computing service.
  • annealing-based computing device 10 may be enabled by calling an API (application programming interface) over communication network 18 .
  • the annealing-type computing device 10 is not limited to being implemented as a cloud computing service, and may be implemented on-premise or operated by another company.
  • the annealing-type computing device 10 may be implemented by a plurality of computers.
  • the information processing device 12 may be realized as a cloud computing service, may be realized on-premises, or may be operated by another company. It may be implemented by a plurality of computers. Needless to say, the information processing system 1 of FIG. 1 has various system configuration examples depending on the application and purpose.
  • the information processing apparatus 12 of FIG. 1 is realized by, for example, a computer 500 having a hardware configuration shown in FIG.
  • FIG. 2 is a hardware configuration diagram of an example of a computer according to this embodiment.
  • a computer 500 in FIG. 2 includes an input device 501, a display device 502, an external I/F 503, a RAM 504, a ROM 505, a CPU 506, a communication I/F 507, an HDD 508, and the like, which are interconnected via a bus B. .
  • the input device 501 and the display device 502 may be connected and used.
  • the input device 501 is a touch panel, operation keys, buttons, keyboard, mouse, etc. used by the user to input various signals.
  • the display device 502 includes a display such as liquid crystal or organic EL for displaying a screen, a speaker for outputting sound data such as voice or sound, and the like.
  • a communication I/F 507 is an interface for the computer 500 to perform data communication.
  • the HDD 508 is an example of a non-volatile storage device that stores programs and data.
  • the stored programs and data include an OS, which is basic software that controls the entire computer 500, and applications that provide various functions on the OS.
  • the computer 500 may use a drive device (for example, solid state drive: SSD, etc.) using flash memory as a storage medium instead of the HDD 508 .
  • the external I/F 503 is an interface with an external device.
  • the external device includes a recording medium 503a and the like. Thereby, the computer 500 can read and/or write the recording medium 503a via the external I/F 503.
  • the recording medium 503a includes a flexible disk, CD, DVD, SD memory card, USB memory, and the like.
  • the ROM 505 is an example of a non-volatile semiconductor memory (storage device) that can retain programs and data even when the power is turned off.
  • the ROM 505 stores programs and data such as the BIOS, OS settings, and network settings that are executed when the computer 500 is started.
  • a RAM 504 is an example of a volatile semiconductor memory (storage device) that temporarily holds programs and data.
  • the CPU 506 is an arithmetic unit that implements the overall control and functions of the computer 500 by reading programs and data from storage devices such as the ROM 505 and HDD 508 onto the RAM 504 and executing processing.
  • the information processing apparatus 12 according to this embodiment can realize various functions as described later. A description of the hardware configuration of the annealing-type computing device 10 will be omitted.
  • FIG. 3 is a configuration diagram of an example of an information processing system according to this embodiment. It should be noted that the configuration diagram of FIG. 3 omits parts that are not necessary for the explanation of the present embodiment as appropriate.
  • the information processing device 12 also includes an input reception unit 30, a calculation unit 32, a determination unit 34, an output unit 36, a conversion unit 38, a cooperation unit 40, a display unit 42, an experimental data storage unit 50, a formula storage unit 52, and a material It has an information storage unit 54 .
  • the input reception unit 30 is an input interface that receives input of information from the user necessary for the annealing computing device 10 to solve the combinatorial optimization problem reduced to the Ising model.
  • the information necessary for causing the annealing-type computing device 10 to solve the combinatorial optimization problem reduced to the Ising model includes the information of the function for conversion to the Ising model. Note that the function to be converted into the Ising model is described so as to include one or more explanatory variables (explanatory variable group).
  • the calculation unit 32 calculates the relationship between one or more explanatory variables and the physical properties of the mixed material using a learned machine learning model described using one or more explanatory variables of the function to be converted into the Ising model. Further, it is preferable that the explanatory variable used for describing the machine learning model is the characteristic of the mixed material that can be described by the weighted average of the ratio of the material composition. It is assumed that the machine learning model has learned from experimental data the relationship between the characteristics of the mixed material that can be described by the weighted average of the ratio of the material composition and the physical properties of the mixed material.
  • the determining unit 34 determines the optimum value and allowable change range of the one or more explanatory variables for the target physical properties, as will be described later. to decide.
  • the output unit 36 outputs the optimum values of one or more explanatory variables determined by the determination unit 34 as target values of one or more explanatory variables of the function to be converted into the Ising model. Also, the output unit 36 outputs weighting coefficients of one or more explanatory variables of the function to be converted into the Ising model based on the allowable change range of the one or more explanatory variables determined by the determination unit 34, as described later.
  • the conversion unit 38 converts the function obtained by substituting the target values of the one or more explanatory variables and the weighting coefficients of the one or more explanatory variables output by the output unit 36 into an Ising Convert to model.
  • the cooperation unit 40 transmits the Ising model converted by the conversion unit 38 to the annealing-type computing device 10 . Also, the linking unit 40 receives the optimum solution calculated by the annealing-type computing device 10 .
  • the display unit 42 displays the optimum solution received by the cooperation unit 40 on the display device 502 for confirmation by the user.
  • the optimum solution displayed on the display device 502 is displayed as, for example, a mixing ratio of mixed materials that is easy for the user to understand.
  • the experimental data storage unit 50 stores experimental data used for learning the machine learning model.
  • the formula storage unit 52 stores a function to be converted into an Ising model and a machine learning model.
  • the material information storage unit 54 stores material information such as material properties.
  • the call reception unit 20 receives a call from the information processing device 12 and receives from the information processing device 12 the Ising model converted into a usable data format.
  • the optimum solution calculation unit 22 searches for the optimum solution of the mixture ratio of the mixed material in which the physical properties asymptotically approach the target value by obtaining the state in which the energy (Hamiltonian) of the Ising model received by the call reception unit 20 is minimized.
  • the call reception unit 20 transmits the searched optimum solution to the information processing device 12 .
  • FIG. 3 is an example. Various configurations can be considered for the information processing system 1 according to the present embodiment.
  • FIG. 4 is a flow chart showing an example of the processing procedure of the material composition searching method using the information processing system according to the present embodiment.
  • step S100 the user creates a function for conversion to an Ising model.
  • a function for conversion to an Ising model has a configuration as shown in FIG. 5, for example.
  • FIG. 5 is an explanatory diagram of an example of a function for conversion into an Ising model.
  • Xibest is the target value of the explanatory variable Xi .
  • the explanatory variable X i is a property of the mixed material, such as the HSP value or molecular weight, which describes the weighted average of the proportions of the material composition.
  • the terms other than the last term become smaller as the respective explanatory variables X i approach the target value X ibest .
  • the mixing ratio constraint term is a term that becomes "0" when the sum of the mixing ratios of the materials is "100%”.
  • a i is a weighting factor of the explanatory variable X i .
  • B is the weighting factor of the mixture ratio constraint term.
  • the annealing-type calculation device 10 obtains, for example, a state in which the function in FIG . %” is calculated as the optimum solution for the material composition.
  • the present embodiment supports creation of a function for conversion into an Ising model by causing the information processing device 12 to output the target value X ibest and the weighting factor A i adjusted by the user.
  • FIG. 6A shows that the purpose is to mix a plurality of solvents (solvent group) with known molecular weights to create a mixed solvent whose average molecular weight asymptotically (approximates) to M0 .
  • the average molecular weight M of the mixed solvent obtained by mixing the solvent groups can be calculated by the formula shown in FIG. 6B. Also, a function that becomes a smaller value as the average molecular weight M of the mixed solvent in which the solvent groups are mixed approaches M0 asymptotically can be described, for example, as shown in FIG. 6C.
  • the average molecular weights M and M0 are an example of mixed solvent properties that can be described by a weighted average of the mixing ratios of the mixed solvent groups.
  • step S102 the user creates a machine learning model for predicting the physical property Y of the mixed material described using the explanatory variables X i included in the function to be converted into the Ising model.
  • the processing of step S102 will be described with reference to FIG.
  • FIG. 7 is a diagram explaining the linkage between combinatorial optimization and machine learning.
  • FIG. 7 shows an example of solving a combinatorial optimization problem for the optimum mixture ratio of monomer species for producing a polymer with physical property Y.
  • FIG. 7 shows an example of solving a combinatorial optimization problem for the optimum mixture ratio of monomer species for producing a polymer with physical property Y.
  • the function for converting to the Ising model for solving the combinatorial optimization problem in FIG. 7 includes an explanatory variable group X that can be described by the weighted average of the mixing ratio of the monomer species, as described using FIG. there is Therefore, the relationship between the explanatory variable group X of the polymer and the physical property Y of the polymer can be obtained by creating a machine learning model for predicting the physical properties of the polymer described using the explanatory variable group X of the polymer and learning the experimental data. can be obtained with
  • the region of the explanatory variable group in the explanatory variable space for obtaining the polymer with the target physical property is obtained by a machine learning model that has already learned the relationship between the explanatory variable group X i of the polymer and the physical property Y of the polymer. can be obtained as described below.
  • step S104 the user causes the machine learning model created in step S102 to learn using experimental data.
  • machine learning model there are no restrictions on the type of machine learning model, and LASSO, random forest, or the like can be used.
  • material information as shown in FIG. 8 and experimental data as shown in FIG. 9 are used.
  • FIG. 8 is a configuration diagram of an example of material information. In the material information of FIG. 8, characteristic values are set for each material.
  • FIG. 9 is a configuration diagram of an example of experimental data. In the experimental data of FIG. 9, the compounding ratio of the mixed material and the physical property values of the mixed material compounded at that compounding ratio are set. The explanatory variable i can be calculated based on the material information in FIG. 8 and the compounding ratio of the mixed material shown in FIG.
  • step S106 the user uses the machine learning model learned in step S104 to create a variable Z that outputs a smaller value as the mixed material asymptotically approaches the target physical properties.
  • the calculation unit 32 of the information processing device 12 determines grid points to perform exhaustive calculation on the explanatory variable space, performs exhaustive calculation of the variable Z, and calculates the explanatory variable Xi and the variable Z as shown in FIG. Calculate the relationship between
  • FIG. 10 is a diagram showing an example of the relationship between the calculated explanatory variable X i and the variable Z.
  • the explanatory variable X i corresponding to the variable Z with the smallest value shown in FIG. 10 is the optimum value of the explanatory variable X i .
  • the threshold for allowing a deviation from the minimum value of the variable Z You can choose multiple values for the variable Z in .
  • step S108 the determination unit 34 determines the value of the explanatory variable X i when the variable Z is the minimum as the optimum value of the explanatory variable X i .
  • the output unit 36 outputs the determined optimal value of the explanatory variable X i as the target value X ibest of the explanatory variable X i .
  • step S110 the determination unit 34 selects a plurality of values of the variable Z within a threshold value for allowing a deviation from the minimum value of the variable Z, and uses the values of the explanatory variables Xi of the selected variables Z to perform the explanation. Determine the allowable range of variation for the variable X i .
  • FIG. 11 is a diagram illustrating an example of the optimal value and allowable change width of the explanatory variable Xi .
  • FIG. 11 is an example in which the explanatory variable X i is two-dimensional.
  • the optimum value of explanatory variable X1 is the value of X1best .
  • the optimum value of the explanatory variable X2 is the value of X2best .
  • the elliptical region shown in FIG. 11 can be drawn using the values of the explanatory variable X1 and the explanatory variable X2 of a plurality of variables Z within the allowable deviation threshold from the minimum variable Z value.
  • the elliptical region shown in FIG. 11 is the explanatory variable region of the mixed material that asymptotically approaches the target physical properties.
  • FIG. 11 shows an example in which the predictor variable region of the mixed material that asymptotically approaches the target physical properties is an ellipse, it is not limited to an ellipse.
  • the determining unit 34 determines the allowable change range for each explanatory variable X1 and explanatory variable X2 from the elliptical area shown in FIG.
  • the allowable change width of the explanatory variable X1 is the distance of the short axis of the ellipse shown in FIG.
  • the allowable change width of the explanatory variable X2 is the distance of the major axis of the ellipse shown in FIG.
  • step S112 the output unit 36 determines and outputs the weighting factor A i of the explanatory variable X i from the determined allowable change range for each explanatory variable X i by, for example, the method shown in FIG. .
  • FIG. 12 is an explanatory diagram of an example of the process of determining the weighting factor A i of the explanatory variable X i .
  • the weighting factor A i of the explanatory variable X i can be calculated by 1/ r i , where r i is the axial distance of the elliptical region.
  • the weighting factor A1 of the explanatory variable X1 is 1/ r1 .
  • the weighting factor A2 of the explanatory variable X2 is 1/ r2 .
  • explanatory variable X 1 >explanatory variable X 2
  • weighting factor A 1 >weighting factor A 2 is output.
  • the explanatory variable Xi with a larger allowable change range has a smaller weighting factor Ai
  • the explanatory variable Xi with a smaller allowable range of change smaller variance
  • FIG. 13 is a diagram illustrating an example of the relationship between the allowable deviation threshold value C from the minimum variable Z and the shape of the explanatory variable region of the mixed material that asymptotically approaches the target physical properties.
  • the allowable deviation threshold C from the minimum variable Z is too large, for example, as shown in the graph on the left side of FIG. There is a possibility that the sensitivity of the explanatory variable X1 and the explanatory variable X2 cannot be determined effectively. Also, if the threshold value C for allowing a deviation from the minimum variable Z is too small, as shown in the graph on the right side of FIG. There is a possibility that the sensitivity of the explanatory variable X1 and the explanatory variable X2 to .
  • the threshold C for allowable deviation from the minimum variable Z may be adjusted by the user with reference to the shape of the explanatory variable region of the mixed material that asymptotically approaches the target physical properties. If it is determined that it is not, it may be adjusted.
  • step S114 the conversion unit 38 converts the target value X ibest of the explanatory variable X i output in step S108 and the weighting factor A i of the explanatory variable X i output in step S112 into an Ising model. Assign to a function that In step S116, the conversion unit 38 converts the function obtained by substituting the target value X ibest of the explanatory variable X i and the weighting factor A i of the explanatory variable X i into the Ising model (calculates the matrix elements of the formula of the Ising model).
  • the technology for converting the function into the quadratic unconstrained binary optimization (QUBO) format of the evaluation function or converting it into the Ising model in a data format that can be used by the annealing-type computing device 10 is provided as a Web API or the like. It is an existing technology.
  • the conversion unit 38 develops a function obtained by substituting the target value X ibest of the explanatory variable X i and the weighting factor A i of the explanatory variable X i to calculate the matrix element Q i,j of the Ising model, and the cooperation unit 40
  • the matrix element Qi ,j calculated by the transforming unit 38 is transmitted to the annealing-type computing device 10 as a parameter of the Ising model.
  • step S118 the optimum solution calculation unit 22 of the annealing-type calculation device 10 that has received the parameters of the Ising model searches for the optimum solution of the mixture ratio of the mixed material that minimizes the function in FIG. 5, for example.
  • the call reception unit 20 transmits information representing the searched optimum solution to the information processing device 12 .
  • step S120 the display unit 42 converts the information (bit information of the annealing-type computing device 10) received by the cooperation unit 40 as the optimum solution into information such as the mixing ratio of the mixed material that is easy for the user to understand, and outputs the information.
  • the display unit 42 displays the name of the material contained in the mixed solvent of the optimum solution and the compounding ratio of the material.
  • the mixed material is generated by specifying the material to be mixed and its mixing ratio. For example, it can be used to control a mixed material generator. Further, the physical properties of the mixed material generated by the mixed material generating apparatus can be evaluated by an evaluation apparatus.
  • the information of the mixed material searched for as the optimum solution can be compared with the physical properties of the mixed material generated by the mixed material generator by specifying the information of the mixed material, and the result of the comparison can be fed back.
  • the accuracy of searching for the optimum solution can be improved.
  • the information processing system 1 it is possible to reduce the trouble of creating an Ising model for causing the annealing-type computing device 10 to solve the combination optimization problem of material compositions that asymptotically approach the target physical properties.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Mathematical Physics (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Health & Medical Sciences (AREA)
  • Geometry (AREA)
  • Computational Linguistics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Feedback Control In General (AREA)
PCT/JP2023/006789 2022-03-01 2023-02-24 情報処理装置、情報処理システム、プログラム、及び材料組成探索方法 Ceased WO2023167107A1 (ja)

Priority Applications (5)

Application Number Priority Date Filing Date Title
JP2024504664A JP7601279B2 (ja) 2022-03-01 2023-02-24 情報処理装置、情報処理システム、プログラム、及び材料組成探索方法
EP23763366.4A EP4489013A4 (en) 2022-03-01 2023-02-24 INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING SYSTEM, PROGRAM AND MATERIAL COMPOSITION SEARCH METHOD
CN202380023904.3A CN118765418A (zh) 2022-03-01 2023-02-24 信息处理装置、信息处理系统、程序及材料组成搜索方法
US18/841,022 US20250191704A1 (en) 2022-03-01 2023-02-24 Information processing device, information processing system, program, and material composition searching method
JP2024204074A JP2025028938A (ja) 2022-03-01 2024-11-22 材料組成探索方法を用いる混合材料の生成方法

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2022031084 2022-03-01
JP2022-031084 2022-03-01

Publications (1)

Publication Number Publication Date
WO2023167107A1 true WO2023167107A1 (ja) 2023-09-07

Family

ID=87883723

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/006789 Ceased WO2023167107A1 (ja) 2022-03-01 2023-02-24 情報処理装置、情報処理システム、プログラム、及び材料組成探索方法

Country Status (5)

Country Link
US (1) US20250191704A1 (https=)
EP (1) EP4489013A4 (https=)
JP (2) JP7601279B2 (https=)
CN (1) CN118765418A (https=)
WO (1) WO2023167107A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025142956A1 (ja) * 2023-12-28 2025-07-03 株式会社レゾナック 情報処理装置、情報処理システム、プログラム、及びイジングモデル作成支援方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119626419B (zh) * 2025-02-17 2025-06-24 陕西金骏特钢制造有限公司 基于退火酸洗的镍卷带材力学性能评估方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019086817A (ja) * 2017-11-01 2019-06-06 株式会社日立製作所 設計支援装置及び設計支援方法
JP2021127418A (ja) * 2020-02-17 2021-09-02 富士通株式会社 混合物性能最適化装置、混合物性能最適化プログラム、混合物性能最適化方法、及び混合冷媒
WO2022003943A1 (ja) * 2020-07-03 2022-01-06 日本電気株式会社 解精度保証アニーリング計算装置、方法及びプログラム
JP2022031084A (ja) 2020-08-07 2022-02-18 エスジーエム・カンパニー・リミテッド プレー情報を提供する仮想ゴルフ装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019086817A (ja) * 2017-11-01 2019-06-06 株式会社日立製作所 設計支援装置及び設計支援方法
JP2021127418A (ja) * 2020-02-17 2021-09-02 富士通株式会社 混合物性能最適化装置、混合物性能最適化プログラム、混合物性能最適化方法、及び混合冷媒
WO2022003943A1 (ja) * 2020-07-03 2022-01-06 日本電気株式会社 解精度保証アニーリング計算装置、方法及びプログラム
JP2022031084A (ja) 2020-08-07 2022-02-18 エスジーエム・カンパニー・リミテッド プレー情報を提供する仮想ゴルフ装置

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
ASAHARA. AKINORI: "Analytics and IT Platform to Support Materials Informatics", THE JOURNAL OF INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS, vol. 105, no. 1, 1 January 2022 (2022-01-01), pages 52 - 57, XP009548625 *
See also references of EP4489013A4
TAKESHI SHIOGA ET AL.: "Proceedings of the Thermal Engineering Conference 2019", 12 October 2019, JAPAN SOCIETY OF MECHANICAL ENGINEERS, article "Optimization of Thermosphysical Properties for Mixed Refrigerants with Digital Annealer"
TAMURA. RYO: "Application of Quantum Annealing in Materials Informatics", LECTURE PROCEEDINGS OF THE IEICE ENGINEERING SCIENCES SOCIETY/ NOLTA SOCIETY CONFERENCE 2019, 27 August 2019 (2019-08-27), XP009542075 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025142956A1 (ja) * 2023-12-28 2025-07-03 株式会社レゾナック 情報処理装置、情報処理システム、プログラム、及びイジングモデル作成支援方法
JPWO2025142956A1 (https=) * 2023-12-28 2025-07-03
JP7845593B2 (ja) 2023-12-28 2026-04-14 株式会社レゾナック 情報処理装置、情報処理システム、プログラム、及びイジングモデル作成支援方法

Also Published As

Publication number Publication date
JP2025028938A (ja) 2025-03-05
US20250191704A1 (en) 2025-06-12
JPWO2023167107A1 (https=) 2023-09-07
EP4489013A1 (en) 2025-01-08
JP7601279B2 (ja) 2024-12-17
EP4489013A4 (en) 2026-03-04
CN118765418A (zh) 2024-10-11

Similar Documents

Publication Publication Date Title
JP2025028938A (ja) 材料組成探索方法を用いる混合材料の生成方法
CN107077497B (zh) 复合分区函数
JP7726280B2 (ja) 特性予測装置、特性予測方法、及びプログラム
JP2022529178A (ja) 人工知能推奨モデルの特徴処理方法、装置、電子機器、及びコンピュータプログラム
CN104750731B (zh) 一种获取完整用户画像的方法及装置
JP7414194B1 (ja) 情報処理装置、情報処理システム、プログラム、及びイジングモデル作成支援方法
JP7424544B2 (ja) 情報処理システム、材料組成探索方法、材料組成探索装置、及びプログラム
JP7525083B2 (ja) 材料設計装置、材料設計方法及びプログラム
WO2024062837A1 (ja) 設計支援装置、設計支援方法、プログラム及び情報処理システム
WO2022260030A1 (ja) 情報処理システム、材料組成探索方法、材料組成探索装置、及びプログラム
WO2022004883A1 (ja) 推定装置、訓練装置、推定方法、訓練方法及び反応生成物を得る方法
JP7468812B1 (ja) 情報処理装置、情報処理システム、プログラム、及びイジングモデル作成支援方法
CN114861742A (zh) 基于图神经网络的图分类方法和系统
JP7077746B2 (ja) 学習装置、学習方法及び学習プログラム
EP4362031A1 (en) Physical property prediction device, physical property prediction method, and program
JP7845593B2 (ja) 情報処理装置、情報処理システム、プログラム、及びイジングモデル作成支援方法
JP7464151B2 (ja) 位置制御装置、方法およびプログラム
Pedersen et al. Experiences with industrial application of wave-based architectural acoustics simulations
WO2025018394A1 (ja) シミュレーション装置、シミュレーション方法及びプログラム
US20200220990A1 (en) Information processing terminal and information processing system
CN117492757A (zh) 数字孪生系统生成方法、装置、介质及电子设备

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: 23763366

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2024504664

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 18841022

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 202380023904.3

Country of ref document: CN

WWE Wipo information: entry into national phase

Ref document number: 2023763366

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: 2023763366

Country of ref document: EP

Effective date: 20241001

WWP Wipo information: published in national office

Ref document number: 18841022

Country of ref document: US