WO2022230736A1 - 設計支援装置、設計支援方法及び設計支援プログラム - Google Patents
設計支援装置、設計支援方法及び設計支援プログラム Download PDFInfo
- Publication number
- WO2022230736A1 WO2022230736A1 PCT/JP2022/018312 JP2022018312W WO2022230736A1 WO 2022230736 A1 WO2022230736 A1 WO 2022230736A1 JP 2022018312 W JP2022018312 W JP 2022018312W WO 2022230736 A1 WO2022230736 A1 WO 2022230736A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- design
- parameter group
- design parameter
- objective variable
- evaluation value
- Prior art date
Links
- 238000013461 design Methods 0.000 title claims abstract description 306
- 238000000034 method Methods 0.000 title claims description 54
- 238000011156 evaluation Methods 0.000 claims abstract description 135
- 238000009826 distribution Methods 0.000 claims abstract description 75
- 238000005070 sampling Methods 0.000 claims abstract description 69
- 239000013598 vector Substances 0.000 claims abstract description 17
- 230000006870 function Effects 0.000 claims description 95
- 239000000047 product Substances 0.000 claims description 43
- 239000011265 semifinished product Substances 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 22
- -1 work-in-progress Substances 0.000 claims description 20
- 238000004519 manufacturing process Methods 0.000 claims description 17
- 230000006872 improvement Effects 0.000 claims description 15
- 238000010801 machine learning Methods 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 13
- 238000013145 classification model Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 23
- 239000000463 material Substances 0.000 description 40
- 238000003860 storage Methods 0.000 description 29
- 230000008569 process Effects 0.000 description 17
- 238000002474 experimental method Methods 0.000 description 16
- 238000012545 processing Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 238000002360 preparation method Methods 0.000 description 6
- 239000002994 raw material Substances 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000002156 mixing Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 239000000654 additive Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013329 compounding Methods 0.000 description 2
- 238000012938 design process Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 229920000642 polymer Polymers 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 238000013531 bayesian neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013400 design of experiment Methods 0.000 description 1
- 239000012850 fabricated material Substances 0.000 description 1
- 230000009477 glass transition Effects 0.000 description 1
- 239000008204 material by function Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010238 partial least squares regression Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
Definitions
- One aspect of the present disclosure relates to a design support device, a design support method, and a design support program.
- the present invention has been made in view of the above problems, and optimizes product characteristics and design variables that constitute objective variables in the manufacturing process of products, work-in-progress, semi-finished products, parts, or prototypes.
- the purpose is to make it possible with a low load by reducing the number of experiments.
- a design support device determines and determines design parameters in the design of products, work-in-progress, semi-finished products, parts, or prototypes manufactured based on a design parameter group consisting of a plurality of design parameters.
- Products, work-in-progress, semi-finished products, parts, or prototypes based on the design parameters obtained from the product, work-in-progress, semi-finished products, parts, or prototypes in order to apply the method to optimize design parameters by repeating
- a design support device that obtains a plurality of design parameters that improve a plurality of characteristic items indicating characteristics, and is a design parameter group and a plurality of A data acquisition unit that acquires a plurality of performance data consisting of each observed value of a characteristic item, and a prediction that predicts the observed value of the characteristic item as a target variable as a probability distribution, its approximation, or an alternative index based on the design parameter group.
- a model building section that builds a model based on actual data, and multiple target variable groups sampled from the multidimensional probability distribution of observed values obtained from each prediction model are used as one sampling point, and the target variable group is sampled at a predetermined number of points. and a vector whose dimensions are the number of objective variables contained in the objective variable group and whose elements are the values of each objective variable. and an acquisition function evaluation unit that inputs a group of design parameters based on the distribution of evaluation values at each sampling point and outputs an acquisition function evaluation value related to the improvement of the evaluation value using a predetermined acquisition function.
- a design parameter group acquisition unit that acquires at least one design parameter group by optimizing the acquisition function evaluation value, and an output unit that outputs the design parameter group acquired by the design parameter group acquisition unit.
- a design support method determines and determines design parameters in the design of products, work-in-progress, semi-finished products, parts, or prototypes manufactured based on a design parameter group consisting of a plurality of design parameters.
- Products, work-in-progress, semi-finished products, parts, or prototypes based on the design parameters obtained from the product, work-in-progress, semi-finished products, parts, or prototypes in order to apply the method to optimize design parameters by repeating
- a design support method in a design support device that obtains a plurality of design parameters that improve a plurality of characteristic items indicating characteristics, wherein the design parameters are related to manufactured products, work-in-process products, semi-finished products, parts, or prototypes.
- a model building step that builds a prediction model that predicts as based on actual data, and multiple target variables sampled from the multidimensional probability distribution of observed values obtained from each prediction model as one sampling point. and a vector whose dimensions are the number of objective variables included in the objective variable group, and whose elements are the values of the objective variables.
- An evaluation value calculation step for calculating the evaluation value of the group, and an acquisition for inputting the design parameter group based on the distribution of the evaluation values at each sampling point and outputting an acquisition function evaluation value related to the improvement of the evaluation value by a predetermined acquisition function.
- a function evaluation step for evaluating the evaluation value of the group, and an acquisition for inputting the design parameter group based on the distribution of the evaluation values at each sampling point and outputting an acquisition function evaluation value related to the improvement of the evaluation value by a predetermined acquisition function.
- a function evaluation step for calculating the evaluation value of the group, and an acquisition for inputting the design parameter group based on the distribution of the evaluation values at each sampling point and outputting an acquisition function evaluation value related to the improvement of the evaluation value by a predetermined acquisition function.
- a design support program causes a computer to determine a design parameter in designing a product, a work-in-progress, a semi-finished product, a part, or a prototype manufactured based on a design parameter group consisting of a plurality of design parameters.
- a design support program for functioning as a design support device that obtains a plurality of design parameters such that a plurality of property items indicating the properties of a prototype are improved, wherein a computer stores a manufactured product, a work-in-progress product, and a semi-finished product.
- a data acquisition function that acquires a plurality of performance data consisting of a set of design parameters and observed values for each of a plurality of characteristic items regarding parts or prototypes, and observation of characteristic items as objective variables based on the set of design parameters.
- a model building function that builds a prediction model that predicts values as a probability distribution, its approximation, or an alternative index based on actual data, and multiple objective variable groups sampled from the multidimensional probability distribution of observed values obtained from each prediction model. is one sampling point, a sampling function that samples the objective variable group at a predetermined number of points, and a vector whose dimension is the number of objective variables contained in the objective variable group and the value of each objective variable is scalarized by a predetermined operation.
- an evaluation value calculation function that calculates the evaluation value of the objective variable group at each sampling point, and based on the distribution of the evaluation value at each sampling point, the design parameter group is input, and the acquisition function evaluation related to the improvement of the evaluation value is performed.
- Acquisition function evaluation function for outputting a value using a predetermined acquisition function;
- Design parameter group acquisition function for acquiring at least one design parameter group by optimizing the acquisition function evaluation value;
- a prediction model is constructed that predicts the observed values of the characteristic items based on the actual data. Since this prediction model predicts the observed value as the objective variable as a probability distribution, its approximation, or an alternative index, the objective variable with an arbitrary score is obtained based on the multidimensional distribution of the observed value obtained from the prediction model for each characteristic item. Groups can be sampled. An evaluation value for each sampling point represented by a scalar value can be obtained by performing a predetermined operation on a vector whose elements are the objective variable groups at each sampling point. Then, based on the distribution of the evaluation values at each sampling point, a design parameter group suitable for the next experiment or the like can be obtained by optimizing the output acquisition function evaluation values using a predetermined acquisition function. Therefore, it is possible to obtain a more accurate machine learning model than the usual method of directly learning the evaluation value and constructing the acquisition function. The improvement in the number of experiments makes it possible to reduce the number of experiments.
- the evaluation value calculation unit may calculate the evaluation value including the weighted sum of the objective variables included in the objective variable group.
- the evaluation value calculation unit may calculate an arbitrary scalar value calculated by a predetermined process as an evaluation value using the objective variable as an input.
- the evaluation value calculation unit determines the difference from the target value among the plurality of objective variables included in the objective variable group.
- An evaluation value may be calculated that further includes the difference of the largest objective variable from the target value.
- the evaluation value calculation unit selects the objective variable with the highest numerical value with respect to the target value among a plurality of objective variables included in the objective variable group. An evaluation value that further includes a difference from the target value may be calculated. Further, when the optimization problem is a maximization problem, the evaluation value calculation unit calculates the difference between the target value and the objective variable with the lowest numerical value with respect to the target value among the multiple objective variables included in the objective variable group. Furthermore, it is good also as calculating the evaluation value to include. By optimizing the acquisition function evaluation value obtained based on the evaluation value calculated in this way, an effective design parameter for bringing the objective variable, which is farthest from the target value, closer to the target value in one process of optimization You can get a group.
- the acquisition function evaluation unit selects one of LCB (Lower Confidence Bound), UCB (Upper Confidence Bound), EI (Expected Improvement), and PI (Probability of Improvement). may be used to output the acquisition function evaluation value.
- LCB Lower Confidence Bound
- UCB Upper Confidence Bound
- EI Extended Improvement
- PI Probability of Improvement
- an acquisition function evaluation value suitable for evaluating a design parameter group suitable for improving the evaluation value is output.
- the design parameter group acquisition unit may acquire one design parameter group that optimizes the acquisition function evaluation value.
- the design parameter group acquisition unit may acquire a plurality of design parameter groups using a predetermined algorithm.
- the predictive model is a regression model or a classification model that inputs a group of design parameters and outputs a probability distribution of observed values
- the model construction unit performs machine learning using actual data
- a prediction model may be constructed by
- the prediction model is constructed as a predetermined regression model or classification model, it is possible to obtain a prediction model that can acquire the probability distribution of the observed values of the characteristic item, its approximation, or an alternative index.
- the prediction model includes a posterior distribution of predicted values based on Bayesian theory, a distribution of predicted values of predictors that constitute an ensemble, a theoretical expression of prediction intervals and confidence intervals of a regression model, and a Monte Carlo drop It may be a machine learning model that predicts the probability distribution of observed values or its approximation or alternative index using any one of the prediction distributions of multiple predictors constructed under different conditions. .
- a prediction model capable of predicting the probability distribution of the observed values of the characteristic items based on the design parameter group or its approximation or alternative index is constructed.
- optimization of characteristics and design variables of products and the like that constitute objective variables in the manufacturing process of products, work-in-progress, semi-finished products, parts, or prototypes can be performed with a low load by a smaller number of experiments. make it possible.
- FIG. 10 is a diagram showing an example of design parameter groups related to materials that have already been fabricated;
- FIG. 10 is a diagram showing an example of observed values for fabricated materials;
- 2 is a flow chart showing a process of optimizing property items and design parameters in material design;
- 5 is a flow chart showing an example of contents of a design support method in the design support device according to the embodiment;
- It is a figure which shows the structure of a design support program.
- FIG. 1 is a diagram showing an outline of a material design process, which is an example of a design process for products, work-in-progress, semi-finished products, parts, or prototypes to which the design support device according to the embodiment is applied.
- products, work-in-progress, semi-finished products, parts, or prototypes are referred to as "products, etc.”
- the design support device 10 of the present embodiment can be applied to a process of designing any product or the like that requires a plurality of property items indicating the property of the product or the like and optimization of each property item.
- the design support device 10 is a method of optimizing the design parameters and objective variables of products, etc.
- the design support device 10 can be applied not only to the development and design of materials, but also to the design of products such as automobiles and drugs, and the optimization of the molecular structure of drugs.
- the design support processing by the design support apparatus 10 will be described using an example of material design as an example of product design.
- the design support processing by the design support device 10 is applied to material fabrication and experiments in the plant, laboratory A, and the like. That is, materials are produced in the plant, the laboratory A, etc., according to the set design parameter group x, and the observed values y of a plurality of property items indicating the properties of the materials are obtained based on the produced materials. Note that the material preparation and experiments in the plant and laboratory A may be simulations. In this case, the design support device 10 provides the design parameter group x for executing the next simulation.
- the design support device 10 optimizes a plurality of characteristic items and design parameters based on performance data consisting of a design parameter group x and an observed value y of a plurality of characteristic items of a material manufactured based on the design parameter group x. conduct. Specifically, based on the design parameter group x and the observed value y regarding the material that has already been manufactured, the design support apparatus 10 uses design parameters that may provide more suitable characteristics for the next manufacturing and experiment. Output the group x.
- the design support device 10 of this embodiment is applied for the purpose of tuning a plurality of design variables and improving a plurality of characteristics in the design of material products.
- the design support device 10 uses a group of design parameters such as the compounding amounts of each polymer and additive as design variables, Using the observed values of elastic modulus and coefficient of thermal expansion as objective variables, it is used to tune a group of design parameters to improve one evaluation value set for multiple characteristics.
- FIG. 2 is a block diagram showing an example of the functional configuration of the design support device according to the embodiment.
- the design support device 10 improves one evaluation value set for a plurality of characteristics indicating the characteristics of the material in the design of the material manufactured based on the design parameter group consisting of a plurality of design parameters. It is a device for obtaining a plurality of design parameters.
- the design support device 10 can include functional units configured in a processor 101 , a design parameter storage unit 21 and an observed value storage unit 22 . Each functional unit will be described later.
- FIG. 3 is a diagram showing an example of the hardware configuration of the computer 100 that constitutes the design support device 10 according to the embodiment. Note that the computer 100 can constitute the design support apparatus 10 .
- the computer 100 includes a processor 101, a main storage device 102, an auxiliary storage device 103, and a communication control device 104 as hardware components.
- the computer 100 constituting the design support apparatus 10 may further include an input device 105 such as a keyboard, touch panel, or mouse, and an output device 106 such as a display.
- the processor 101 is a computing device that executes an operating system and application programs. Examples of processors include CPUs (Central Processing Units) and GPUs (Graphics Processing Units), but the type of processor 101 is not limited to these.
- processor 101 may be a combination of sensors and dedicated circuitry.
- the dedicated circuit may be a programmable circuit such as an FPGA (Field-Programmable Gate Array), or other types of circuits.
- the main storage device 102 is a device that stores programs for realizing the design support device 10 and the like, calculation results output from the processor 101, and the like.
- the main storage device 102 is composed of, for example, at least one of ROM (Read Only Memory) and RAM (Random Access Memory).
- the auxiliary storage device 103 is generally a device capable of storing a larger amount of data than the main storage device 102.
- the auxiliary storage device 103 is composed of a non-volatile storage medium such as a hard disk or flash memory.
- the auxiliary storage device 103 stores a design support program P1 for causing the computer 100 to function as the design support device 10 and various data.
- the communication control device 104 is a device that executes data communication with other computers via a communication network.
- the communication control device 104 is composed of, for example, a network card or a wireless communication module.
- Each functional element of the design support device 10 is realized by loading the corresponding program P1 onto the processor 101 or the main storage device 102 and causing the processor 101 to execute the program.
- Program P1 includes code for implementing each functional element of the corresponding server.
- the processor 101 operates the communication control device 104 according to the program P1 to read and write data in the main storage device 102 or the auxiliary storage device 103 .
- Each functional element of the corresponding server is implemented by such processing.
- the program P1 may be provided after being fixedly recorded on a tangible recording medium such as a CD-ROM, DVD-ROM, or semiconductor memory. Alternatively, at least one of these programs may be provided via a communication network as a data signal superimposed on a carrier wave.
- the design support device 10 includes a data acquisition unit 11, a model construction unit 12, a sampling unit 13, an evaluation value calculation unit 14, an acquisition function evaluation unit 15, a design parameter group acquisition unit 16, and an output unit 17.
- the design parameter storage unit 21 and the observed value storage unit 22 may be configured in the design support device 10 as shown in FIG. 2, or may be configured as other devices accessible from the design support device 10. .
- the data acquisition unit 11 acquires a plurality of performance data regarding materials that have already been manufactured. Actual data consists of pairs of design parameter groups and observed values of each of a plurality of characteristic items.
- the design parameter storage unit 21 is storage means for storing a group of design parameters in actual performance data, and may be configured in the main storage device 102 and the auxiliary storage device 103, for example.
- the observed value storage unit 22 is storage means for storing observed values in performance data.
- FIG. 4 is a diagram showing an example of a design parameter group stored in the design parameter storage unit 21.
- the design parameter group x may include, for example, the blending amount of the raw material A, the blending amount of the raw material B, the design parameter D, and the like, and may form vector data with the number of dimensions corresponding to the number D of the design parameters.
- the design parameters may be, for example, non-vector data such as molecular structures and images. Further, when dealing with the problem of selecting the optimum molecule from a plurality of types of molecules, the design parameters may be data indicating options among the plurality of molecules.
- FIG. 5 is a diagram showing an example of observed values y stored in the observed value storage unit 22.
- Characteristic item k may include glass transition temperature, adhesive strength, and characteristic item K, as an example.
- a pair of the design parameter group x t and the observed value y k, t constitutes actual data.
- the model construction unit 12 constructs a prediction model based on actual performance data.
- the prediction model is a model that predicts the observed value yk of the characteristic item k as the objective variable as a probability distribution or its approximation or alternative index based on the design parameter group x.
- a model that constitutes the prediction model may be a model capable of making predictions using the observed value yk as a probability distribution, an approximation thereof, or an alternative index, and the type thereof is not limited.
- the predictive model may be a regression model whose input is the design parameter x and whose output is the probability distribution of observed values yk .
- the prediction model may be configured by any one of regression models such as linear regression, PLS regression, Gaussian process regression, random forest, and neural network.
- the model construction unit 12 may construct a prediction model by a well-known machine learning method using performance data.
- the model building unit 12 may build the prediction model by applying the performance data to the prediction model and updating the parameters of the prediction model by a machine learning technique.
- the prediction model constructed as Gaussian process regression, by inputting the design parameter group x in the performance data that constitutes the explanatory variables of the teacher data, the observed value y that constitutes the objective variable, and the design parameter x to be predicted into the model, A probability distribution of observations is predicted.
- the prediction model includes the posterior distribution of the predicted value based on Bayesian theory, the distribution of the predicted value of the predictor that constitutes the ensemble, the theoretical formula of the prediction interval and confidence interval of the regression model, the distribution obtained by Monte Carlo dropout, and It may be a machine learning model that predicts the probability distribution of observed values or its approximation or alternative index using any one of the prediction distributions of a plurality of predictors constructed under different conditions.
- the probability distribution of observed values or predictions of their alternative indicators can be obtained by model-specific methods.
- the probability distribution of observed values or its approximation or proxy is based on the posterior distribution of predicted values in the case of Gaussian process regression and Bayesian neural networks, or on the distribution of predictions of the predictors that make up the ensemble in the case of random forests. can be obtained based on prediction and confidence intervals for linear regression and on Monte Carlo dropout for neural networks.
- the method of calculating the distribution of observed values for each machine learning model or its alternative index is not limited to the above method.
- Any model may also be extended to a model that can predict the probability distribution of observed values or its alternative indicators.
- a model that uses the distribution of predicted values obtained by constructing multiple datasets using the bootstrap method, etc., and constructing a prediction model for each model as an alternative index for the probability distribution of observed values. is an example.
- the method of extending the machine learning model to a model capable of predicting the probability distribution of observed values or its alternative index is not limited to the above method.
- model construction unit 12 may tune the hyperparameters of the prediction model using a well-known hyperparameter tuning method. That is, the model construction unit 12 may update the hyperparameters of the prediction model by maximum likelihood estimation using a vector representing the design parameter group x, which is the explanatory variable in the performance data, and the observed value y, which is the objective variable. .
- the prediction model may be constructed by a classification model.
- the model building unit 12 can build the prediction model by a machine learning method that can evaluate a well-known probability distribution using performance data.
- the model construction unit 12 constructs a prediction model using a predetermined regression model or classification model, making it possible to acquire the probability distribution of observed values of characteristic items based on an arbitrary design parameter group x.
- the prediction model is a single task model that predicts the observed value of one characteristic item as a probability distribution, its approximation, or an alternative index, or predicts the observed values of multiple characteristic items as a probability distribution, its approximation, or an alternative index. It may be a multitasking model. In this way, by constructing a prediction model using a multi-task model or a single-task model appropriately configured according to the properties of the characteristic items, it is possible to improve the accuracy of prediction of observed values by the prediction model.
- the sampling unit 13 performs sampling of a predetermined number of objective variable groups, with a plurality of objective variable groups sampled from the multi-dimensional probability distribution of observed values obtained from each prediction model as one sampling point.
- the objective variable group y n of the n-th sampling point forms a vector whose dimensions are the number of objective variables included in the objective variable group and whose elements are the values of the objective variables, as described below.
- y n [y 1,n ,y 2,n , . . , y k,n , . . , y K,n ]
- the sampling unit 13 acquires an objective variable group set Y corresponding to N sampling points, which is a predetermined number of points.
- Y [y 1 , y 2 , . . , y n , . . , y N ]
- Objective variables y 1 , y 2 , . . , y n , . . , y N each constitute a vector.
- the observed value yk as the objective variable follows a normal distribution and is unrelated to each other, but there may be a correlation, and it is not limited to being a normal distribution. , may follow other probability distributions.
- the sampling by the sampling unit 13 has been described with an example of sampling for each objective variable, but the sampling unit 13 is not limited to such an example.
- the objective variable group may be collectively sampled based on the multidimensional normal distribution of .
- the sampling unit 13 may collectively perform sampling of N points, or collectively perform sampling corresponding to each of a plurality of design parameter groups x.
- the evaluation value calculation unit 14 calculates the evaluation value of the objective variable group corresponding to one design parameter group x and one sampling point. Specifically, as described above, the objective variable group at one sampling point forms a vector whose dimension is the number of objective variables included in the objective variable group, and whose elements are the values of the objective variables.
- the value calculator 14 calculates the evaluation value of each sampling point by scalarizing the vector representing the objective variable group by a predetermined operation. More generally, the evaluation value of each sampling point may be an arbitrary scalar value calculated by predetermined processing with the objective variable as input.
- the evaluation value calculation unit 14 calculates the evaluation value v n by a scalarizing function (SF) as shown in the following equation (1).
- vn SF( yn ) (1)
- the evaluation value vn constitutes a scalar value.
- the scalarization function SF may include a term for calculating the weighted sum of the objective variables included in the objective variable group y n .
- the scalarization function SF is based on the target value among the plurality of objective variables included in the objective variable group. may further include a term containing the difference of the target variable with the largest numerical value as .
- the scalarization function SF calculates the difference of the objective variable with the smallest numerical value with respect to the target value among the plurality of objective variables included in the objective variable group. You may further include the containing term.
- the evaluation value calculation unit 14 may calculate the evaluation value vn using the following equation (2).
- the first term is a term for calculating the weighted sum of the objective variables included in the objective variable group y n
- w k is a positive weight for the objective variable y k
- the difference between the objective variables It is for adjusting the scale difference
- ⁇ is an arbitrary constant for adjusting the balance between the first term and the second term.
- the second term in equation (2) is a term that includes the difference from the target value of the objective variable with the largest difference from the target value among the plurality of objective variables included in the objective variable group y n .
- g k is the target value of the objective variable y k .
- the evaluation value v n calculated in this way is used by including the weighted sum of the objective variables included in the objective variable group y n .
- each objective variable can be promoted to approach a Pareto solution.
- the objective variable having the largest difference from the target value among the plurality of objective variables whose evaluation value v n is included in the objective variable group y n By including a term that includes the difference from the target value, in the process of Bayesian optimization, the target variable can be encouraged to approach the target value.
- the evaluation value calculation unit 14 calculates an evaluation value v n for each objective variable group y n of the first to N- th sampling points, thereby obtaining an evaluation value set V can be obtained.
- V [v 1 , v 2 , . . , v n , . . , v N ]
- the evaluation values v 1 , v 2 , . . , v n , . . , v N each constitute a scalar value.
- the evaluation value calculator 14 calculates evaluation values v 1 , v 2 , . . , v n , . . , v N may be calculated collectively.
- the acquisition function evaluation unit 15 receives the design parameter group based on the distribution of the evaluation values at each sampling point, and outputs the acquisition function evaluation value related to the improvement of the evaluation value using a predetermined acquisition function.
- the acquisition function evaluation unit 15 may output an acquisition function evaluation value using a known acquisition function such as LCB (Lower Confidence Bound), for example.
- LCB is used to minimize the output of a function, and by minimizing the value of LCB, a suitable design parameter group x can be obtained.
- the acquisition function evaluation unit 15 When constructing the acquisition function by LCB, the acquisition function evaluation unit 15 defines and constructs the acquisition function evaluation value A(x) as shown in Equation (3) below.
- A(x) mv(x)-a ⁇ v(x) (3)
- Acquisition function evaluation unit 15 evaluates and acquires mean mv(x) and standard deviation ⁇ v (x) based on the distribution of evaluation values vn included in evaluation value set V, and obtains Output the acquisition function evaluation value by the function.
- a in Equation (3) is an arbitrary parameter.
- Equation (3) of the above acquisition function represents the lower limit of the confidence interval when it is assumed that the observed values of v n in the next experiment follow a normal distribution when the design parameter group x is used as a parameter.
- the acquisition function evaluation unit 15 may output the acquisition function evaluation value A(x) using well-known functions such as UCB (Upper Confidence Bound), EI (Expected Improvement), and PI (Probability of Improvement).
- UCB Upper Confidence Bound
- EI Exected Improvement
- PI Probability of Improvement
- the design parameter group acquisition unit 16 acquires at least one design parameter group by optimizing the acquisition function evaluation value A(x) output by the acquisition function evaluation unit 15 .
- the design parameter group acquisition unit 16 may acquire at least one design parameter group x that optimizes the output of the acquisition function. Specifically, the design parameter group acquisition unit 16 performs optimization using the acquisition function evaluation value A(x) output by the acquisition function evaluation unit 15 as the objective variable, and acquires the design parameter group x as the optimum solution. do.
- the design parameter group acquisition unit 16 may acquire a plurality of design parameter groups using a predetermined algorithm. Specifically, the design parameter group acquisition unit 16 may acquire a plurality of design parameter groups by applying a batch Bayesian optimization method to the acquisition function.
- the method of batch Bayesian optimization may be, for example, a method such as Local Penalization, but the method is not limited.
- the output unit 17 outputs the following as the design parameter group for N times of material preparation after the (T-1)th time. Output the acquired design parameter group.
- a set of design parameters for multiple rounds of material preparation may be subjected to simultaneous experimentation and material preparation.
- the output unit 17 outputs design parameter group candidates by, for example, displaying them on a predetermined display device or storing them in a predetermined storage means.
- Fig. 6 is a flow chart showing the process of optimizing property items and design parameter groups in material design.
- a design parameter group is obtained.
- the design parameter group acquired here is for the initial material preparation (experiment), and may be an arbitrarily set design parameter group, or may be set based on an experiment that has already been performed. It may be a set of design parameters.
- step S2 material preparation is performed.
- step S3 observed values of property items of the fabricated material are obtained.
- a pair of the design parameter group as the manufacturing conditions in step S2 and the observed value of each characteristic item acquired in step S3 constitutes performance data.
- step S4 it is determined whether or not a predetermined termination condition has been satisfied.
- the predetermined end condition is a condition for optimizing the observed values of the design parameter group and the characteristic items and may be set arbitrarily.
- the end condition for optimization may be, for example, reaching a predetermined number of times of production (experiment) and acquisition of observed values, reaching a target value of observed values, convergence of optimization, and the like.
- the optimization process is terminated if it is determined that a predetermined termination condition is satisfied. If it is determined that the predetermined termination condition has not been met, the process proceeds to step S5.
- step S5 design support processing by the design support device 10 is performed.
- the design support process is a process of outputting a design parameter group for fabricating the next material. The process then returns to step S1 again.
- step S5 the design parameter group output in step S5 is acquired.
- FIG. 7 is a flow chart showing an example of the content of the design support method in the design support device 10 according to the embodiment, and shows the process of step S5 in FIG.
- the design support method is executed by reading the design support program P1 into the processor 101 and executing the program to realize the functional units 11 to 17.
- FIG. 7 is a flow chart showing an example of the content of the design support method in the design support device 10 according to the embodiment, and shows the process of step S5 in FIG.
- the design support method is executed by reading the design support program P1 into the processor 101 and executing the program to realize the functional units 11 to 17.
- FIG. 7 is a flow chart showing an example of the content of the design support method in the design support device 10 according to the embodiment, and shows the process of step S5 in FIG.
- the design support method is executed by reading the design support program P1 into the processor 101 and executing the program to realize the functional units 11 to 17.
- FIG. 7 is a flow chart showing an example of the content of the design support method in the design support device 10 according
- step S11 the data acquisition unit 11 acquires a plurality of performance data regarding materials that have already been produced.
- the actual data consists of pairs of design parameters and observed values for each characteristic item.
- step S12 the model construction unit 12 constructs a prediction model based on the performance data.
- step S13 based on the prediction model, the sampling unit 13 selects a plurality of target variable groups sampled from the multidimensional probability distribution of the observed values obtained from each prediction model based on one design parameter group x at one sampling point. , sampling of the target variable group with a predetermined number of points is performed.
- step S14 the evaluation value calculation unit 14 calculates the evaluation value of each sampling point by scalarizing a vector whose elements are the values of each objective variable of the objective variable group by a predetermined operation.
- step S15 the acquisition function evaluation unit 15 outputs a predetermined acquisition function evaluation value based on the distribution of evaluation values at each sampling point.
- step S16 the design parameter group acquisition unit 16 acquires at least one design parameter group by optimizing the acquisition function evaluation value obtained by the acquisition function evaluation unit 15 in step S15.
- step S17 the output unit 17 outputs the design parameter group acquired by the design parameter group acquisition unit 16 in step S16 as a design parameter group for the next material production (step S1).
- FIG. 8 is a diagram showing the configuration of the design support program.
- the design support program P1 includes a main module m10 for overall control of design support processing in the design support apparatus 10, a data acquisition module m11, a model construction module m12, a sampling module m13, an evaluation value calculation module m14, an acquisition function evaluation module m15, It comprises a design parameter group acquisition module m16 and an output module m17.
- Functions for the data acquisition unit 11, the model construction unit 12, the sampling unit 13, the evaluation value calculation unit 14, the acquisition function evaluation unit 15, the design parameter group acquisition unit 16, and the output unit 17 are provided by the modules m11 to m17. is realized.
- the design support program P1 may be transmitted via a transmission medium such as a communication line, or may be stored in a recording medium M1 as shown in FIG.
- a prediction model for predicting the observed value of the characteristic item is constructed based on the performance data. Since this prediction model predicts the observed value as the objective variable as a probability distribution, its approximation, or an alternative index, the objective variable with an arbitrary score is obtained based on the multidimensional distribution of the observed value obtained from the prediction model for each characteristic item. Groups can be sampled. An evaluation value for each sampling point represented by a scalar value can be obtained by performing a predetermined operation on a vector whose elements are the objective variable groups at each sampling point.
- a design parameter group suitable for the next experiment or the like can be obtained by optimizing the output acquisition function evaluation values using a predetermined acquisition function. Therefore, it is possible to obtain a more accurate machine learning model than the usual method of directly learning the evaluation value and constructing the acquisition function.
- the improvement in the number of experiments makes it possible to reduce the number of experiments.
- P1... Design support program m10... Main module, m11... Data acquisition module, m12... Model construction module, m13... Sampling module, m14... Evaluation value calculation module, m15... Acquisition function evaluation module, m16... Design parameter group acquisition module, m17... Output module, 10... Design support device, 11... Data acquisition unit, 12... Model construction unit, 13... Sampling unit, 14... Evaluation value calculation unit, 15... Acquisition function evaluation unit, 16... Design parameter group acquisition unit, 17... Output unit, 21... Design parameter storage unit, 22... Observation value storage unit.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Computer Hardware Design (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
yk~N(mk(x),σk(x)2)
このような場合において、サンプリング部13は、1つの設計パラメータ群xに基づいて、目的変数ykの確率分布から、複数のyk(k=1~K)をサンプリングする。
yn=[y1,n,y2,n,..,yk,n,..,yK,n]
Y=[y1,y2,..,yn,..,yN]
目的変数群y1,y2,..,yn,..,yNは、各々がベクトルを構成する。
yk,n=y_stdk,n*σk(x)+mk(x)
vn=SF(yn) ・・・(1)
評価値vnは、スカラー値を構成する。スカラー化関数SFは、目的変数群ynに含まれる目的変数の重み付け和を算出する項を含んでもよい。また、各目的変数に目標値が設定されている場合において、最適化を最小化問題とする場合には、スカラー化関数SFは、目的変数群に含まれる複数の目的変数のうち目標値を基準として最も数値が大きい目的変数の該目標値に対する差を含む項を更に含んでもよい。また、最適化を最大化問題とする場合には、スカラー化関数SFは、目的変数群に含まれる複数の目的変数のうち目標値を基準として最も数値が小さい目的変数の該目標値に対する差を含む項を更に含んでもよい。
V=[v1,v2,..,vn,..,vN]
上述のとおり、評価値v1,v2,..,vn,..,vNは、それぞれスカラー値を構成する。
A(x)=mv(x)-aσv(x) ・・・(3)
獲得関数評価部15は、評価値集合Vに含まれる評価値vnの分布に基づいて、平均mv(x)及び標準偏差σv(x)を評価及び取得し、式(3)に示される獲得関数により獲得関数評価値を出力する。式(3)におけるaは、任意のパラメータである。上記獲得関数の式(3)は、設計パラメータ群xをパラメータとしたときの、次の実験におけるvnの観測値が正規分布に従うと仮定した場合の信頼区間下限を表す。
Claims (10)
- 複数の設計パラメータからなる設計パラメータ群に基づいて作製される製品、仕掛品、半製品、部品又は試作品の設計において、設計パラメータの決定と決定された設計パラメータに基づく製品、仕掛品、半製品、部品又は試作品の作製との繰り返しにより設計パラメータの最適化を図る手法に適用するために、製品、仕掛品、半製品、部品又は試作品の特性を示す複数の特性項目が向上するような、前記複数の設計パラメータを求める設計支援装置であって、
作製済みの前記製品、前記仕掛品、前記半製品、前記部品又は前記試作品に関しての、前記設計パラメータ群と前記複数の特性項目のそれぞれの観測値とからなる実績データを複数取得するデータ取得部と、
前記設計パラメータ群に基づいて、目的変数としての前記特性項目の観測値を確率分布若しくはその近似又は代替指標として予測する予測モデルを、前記実績データに基づいて構築するモデル構築部と、
各予測モデルから得られる観測値の多次元確率分布からサンプリングした複数の目的変数群を一のサンプリング点として、前記目的変数群を所定点数サンプリングするサンプリング部と、
前記目的変数群に含まれる目的変数の数を次元数とし各目的変数の値を要素とするベクトルを所定の演算によりスカラー化することにより、各サンプリング点の目的変数群の評価値を算出する評価値算出部と、
各サンプリング点の前記評価値の分布に基づいて、前記設計パラメータ群を入力とし、前記評価値の向上に関する獲得関数評価値を所定の獲得関数により出力する獲得関数評価部と、
前記獲得関数評価値の最適化により少なくとも一つの設計パラメータ群を取得する設計パラメータ群取得部と、
前記設計パラメータ群取得部により取得された前記設計パラメータ群を出力する出力部と、
を備える設計支援装置。 - 前記評価値算出部は、前記目的変数群に含まれる目的変数の重み付け和を含む前記評価値を算出する、
請求項1に記載の設計支援装置。 - 前記評価値算出部は、各目的変数に目標値が設定されている場合には、前記目的変数群に含まれる複数の目的変数のうち、目標値との差が最も大きい目的変数の該目標値に対する差を更に含む前記評価値を算出する、
請求項2に記載の設計支援装置。 - 前記獲得関数評価部は、LCB(Lower Confidence Bound)、UCB(Upper Confidence Bound)、EI(Expected Improvement)及びPI(Probability of Improvement)のうちのいずれかの獲得関数により前記獲得関数評価値を出力する、
請求項1~3のいずれか一項に記載の設計支援装置。 - 前記設計パラメータ群取得部は、前記獲得関数評価値を最適化する一つの設計パラメータ群を取得する、
請求項1~4のいずれか一項に記載の設計支援装置。 - 前記設計パラメータ群取得部は、複数の前記設計パラメータ群を所定のアルゴリズムにより取得する、
請求項1~4のいずれか一項に記載の設計支援装置。 - 前記予測モデルは、前記設計パラメータ群を入力とし、前記観測値の確率分布を出力とする回帰モデルまたは分類モデルであり、
前記モデル構築部は、前記実績データを用いた機械学習により、前記予測モデルを構築する、
請求項1~6のいずれか一項に記載の設計支援装置。 - 前記予測モデルは、ベイズ理論に基づく予測値の事後分布、アンサンブルを構成する予測器の予測値の分布、回帰モデルの予測区間及び信頼区間の理論式、モンテカルロドロップアウト、及び、異なる条件で複数個構築した予測器の予測の分布のうちのいずれか一つを用いて観測値の確率分布若しくはその近似又は代替指標を予測する機械学習モデルである、
請求項7に記載の設計支援装置。 - 複数の設計パラメータからなる設計パラメータ群に基づいて作製される製品、仕掛品、半製品、部品又は試作品の設計において、設計パラメータの決定と決定された設計パラメータに基づく製品、仕掛品、半製品、部品又は試作品の作製との繰り返しにより設計パラメータの最適化を図る手法に適用するために、製品、仕掛品、半製品、部品又は試作品の特性を示す複数の特性項目が向上するような、前記複数の設計パラメータを求める設計支援装置における設計支援方法であって、
作製済みの前記製品、前記仕掛品、前記半製品、前記部品又は前記試作品に関しての、前記設計パラメータ群と前記複数の特性項目のそれぞれの観測値とからなる実績データを複数取得するデータ取得ステップと、
前記設計パラメータ群に基づいて、目的変数としての前記特性項目の観測値を確率分布若しくはその近似又は代替指標として予測する予測モデルを、前記実績データに基づいて構築するモデル構築ステップと、
各予測モデルから得られる観測値の多次元確率分布からサンプリングした複数の目的変数群を1のサンプリング点として、前記目的変数群を所定点数サンプリングするサンプリングステップと、
前記目的変数群に含まれる目的変数の数を次元数とし各目的変数の値を要素とするベクトルを所定の演算によりスカラー化することにより、各サンプリング点の目的変数群の評価値を算出する評価値算出ステップと、
各サンプリング点の前記評価値の分布に基づいて、前記設計パラメータ群を入力とし、前記評価値の向上に関する獲得関数評価値を所定の獲得関数により出力する獲得関数評価ステップと、
前記獲得関数評価値の最適化により少なくとも一つの設計パラメータ群を取得する設計パラメータ群取得ステップと、
前記設計パラメータ群取得ステップにより取得された前記設計パラメータ群を出力する出力ステップと、
を有する設計支援方法。 - コンピュータを、複数の設計パラメータからなる設計パラメータ群に基づいて作製される製品、仕掛品、半製品、部品又は試作品の設計において、設計パラメータの決定と決定された設計パラメータに基づく製品、仕掛品、半製品、部品又は試作品の作製との繰り返しにより設計パラメータの最適化を図る手法に適用するために、製品、仕掛品、半製品、部品又は試作品の特性を示す複数の特性項目が向上するような、前記複数の設計パラメータを求める設計支援装置として機能させるための設計支援プログラムであって、
前記コンピュータに、
作製済みの前記製品、前記仕掛品、前記半製品、前記部品又は前記試作品に関しての、前記設計パラメータ群と前記複数の特性項目のそれぞれの観測値とからなる実績データを複数取得するデータ取得機能と、
前記設計パラメータ群に基づいて、目的変数としての前記特性項目の観測値を確率分布若しくはその近似又は代替指標として予測する予測モデルを、前記実績データに基づいて構築するモデル構築機能と、
各予測モデルから得られる観測値の多次元確率分布からサンプリングした複数の目的変数群を1のサンプリング点として、前記目的変数群を所定点数サンプリングするサンプリング機能と、
前記目的変数群に含まれる目的変数の数を次元数とし各目的変数の値を要素とするベクトルを所定の演算によりスカラー化することにより、各サンプリング点の目的変数群の評価値を算出する評価値算出機能と、
各サンプリング点の前記評価値の分布に基づいて、前記設計パラメータ群を入力とし、前記評価値の向上に関する獲得関数評価値を所定の獲得関数により出力する獲得関数評価機能と、
前記獲得関数評価値の最適化により少なくとも一つの設計パラメータ群を取得する設計パラメータ群取得機能と、
前記設計パラメータ群取得機能により取得された前記設計パラメータ群を出力する出力機能と、
を実現させる設計支援プログラム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020237038032A KR20240001159A (ko) | 2021-04-27 | 2022-04-20 | 설계 지원 장치, 설계 지원 방법 및 설계 지원 프로그램 |
EP22795649.7A EP4318337A1 (en) | 2021-04-27 | 2022-04-20 | Design aid device, design aid method, and design aid program |
CN202280030719.2A CN117242450A (zh) | 2021-04-27 | 2022-04-20 | 设计支援装置、设计支援方法及设计支援程序 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021075151A JP2022169242A (ja) | 2021-04-27 | 2021-04-27 | 設計支援装置、設計支援方法及び設計支援プログラム |
JP2021-075151 | 2021-04-27 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022230736A1 true WO2022230736A1 (ja) | 2022-11-03 |
Family
ID=83847306
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/018312 WO2022230736A1 (ja) | 2021-04-27 | 2022-04-20 | 設計支援装置、設計支援方法及び設計支援プログラム |
Country Status (5)
Country | Link |
---|---|
EP (1) | EP4318337A1 (ja) |
JP (1) | JP2022169242A (ja) |
KR (1) | KR20240001159A (ja) |
CN (1) | CN117242450A (ja) |
WO (1) | WO2022230736A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116522068A (zh) * | 2023-07-03 | 2023-08-01 | 西安羚控电子科技有限公司 | 一种试验参数生成方法和系统 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020030683A (ja) * | 2018-08-23 | 2020-02-27 | 横浜ゴム株式会社 | ゴム材料設計方法、ゴム材料設計装置、及びプログラム |
JP2020052737A (ja) | 2018-09-27 | 2020-04-02 | 株式会社神戸製鋼所 | 製品設計装置および該方法 |
JP2020071827A (ja) * | 2018-11-02 | 2020-05-07 | 昭和電工株式会社 | ポリマー設計装置、プログラム、および方法 |
JP2020144799A (ja) * | 2019-03-08 | 2020-09-10 | 富士通株式会社 | データ処理プログラム及びデータ処理方法 |
JP2021038344A (ja) * | 2019-09-05 | 2021-03-11 | 国立研究開発法人物質・材料研究機構 | 硬化性組成物の探索方法、及び、硬化性組成物の探索装置 |
-
2021
- 2021-04-27 JP JP2021075151A patent/JP2022169242A/ja active Pending
-
2022
- 2022-04-20 EP EP22795649.7A patent/EP4318337A1/en active Pending
- 2022-04-20 WO PCT/JP2022/018312 patent/WO2022230736A1/ja active Application Filing
- 2022-04-20 KR KR1020237038032A patent/KR20240001159A/ko unknown
- 2022-04-20 CN CN202280030719.2A patent/CN117242450A/zh active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020030683A (ja) * | 2018-08-23 | 2020-02-27 | 横浜ゴム株式会社 | ゴム材料設計方法、ゴム材料設計装置、及びプログラム |
JP2020052737A (ja) | 2018-09-27 | 2020-04-02 | 株式会社神戸製鋼所 | 製品設計装置および該方法 |
JP2020071827A (ja) * | 2018-11-02 | 2020-05-07 | 昭和電工株式会社 | ポリマー設計装置、プログラム、および方法 |
JP2020144799A (ja) * | 2019-03-08 | 2020-09-10 | 富士通株式会社 | データ処理プログラム及びデータ処理方法 |
JP2021038344A (ja) * | 2019-09-05 | 2021-03-11 | 国立研究開発法人物質・材料研究機構 | 硬化性組成物の探索方法、及び、硬化性組成物の探索装置 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116522068A (zh) * | 2023-07-03 | 2023-08-01 | 西安羚控电子科技有限公司 | 一种试验参数生成方法和系统 |
CN116522068B (zh) * | 2023-07-03 | 2023-09-15 | 西安羚控电子科技有限公司 | 一种试验参数生成方法和系统 |
Also Published As
Publication number | Publication date |
---|---|
EP4318337A1 (en) | 2024-02-07 |
KR20240001159A (ko) | 2024-01-03 |
JP2022169242A (ja) | 2022-11-09 |
CN117242450A (zh) | 2023-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Guimaraes et al. | An innovative adaptive sparse response surface method for structural reliability analysis | |
Bernardo et al. | Particle learning for sequential Bayesian computation | |
WO2022124077A1 (ja) | 設計支援装置、設計支援方法及び設計支援プログラム | |
WO2022124075A1 (ja) | 設計支援装置、設計支援方法及び設計支援プログラム | |
WO2022230736A1 (ja) | 設計支援装置、設計支援方法及び設計支援プログラム | |
Cavalcanti et al. | Production system efficiency optimization using sensor data, machine learning-based simulation and genetic algorithms | |
Moustapha et al. | Multi-objective robust optimization using adaptive surrogate models for problems with mixed continuous-categorical parameters | |
Battaglia et al. | Parsimonious periodic autoregressive models for time series with evolving trend and seasonality | |
Shi et al. | A robust prediction method based on Kriging method and fuzzy c-means algorithm with application to a combine harvester | |
Grzegorczyk et al. | Overview and evaluation of recent methods for statistical inference of gene regulatory networks from time series data | |
WO2023080179A1 (ja) | 設計支援装置、設計支援方法及び設計支援プログラム | |
WO2023178118A1 (en) | Directed evolution of molecules by iterative experimentation and machine learning | |
US20240211663A1 (en) | Design aid device, design aid method, and design aid program | |
US20230214668A1 (en) | Hyperparameter adjustment device, non-transitory recording medium in which hyperparameter adjustment program is recorded, and hyperparameter adjustment program | |
WO2024024957A1 (ja) | 設計支援装置、設計支援方法及び設計支援プログラム | |
US9183503B2 (en) | Sparse higher-order Markov random field | |
Blanchet-Scalliet et al. | Four algorithms to construct a sparse kriging kernel for dimensionality reduction | |
Ferrari et al. | Response improvement in complex experiments by co-information composite likelihood optimization | |
Kvisgaard | Predicting the future past. How useful is machine learning in economic short-term forecasting? | |
Wang et al. | Error-guided method combining adaptive learning kriging model and parallel-tempering-based importance sampling for system reliability analysis | |
Sinha et al. | Forecasting Short Time Series using Rolling Grey Bayesian Framework | |
Bayrak et al. | A critical evaluation of asymptotic sampling method for highly safe structures | |
US20240169377A1 (en) | Demand prediction device and demand prediction method | |
Krupkin et al. | Prediction Error Estimation in Random Forests | |
Li et al. | Two improved algorithms for sparse generalized canonical correlation analysis |
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: 22795649 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18556900 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280030719.2 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022795649 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2022795649 Country of ref document: EP Effective date: 20231031 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1020237038032 Country of ref document: KR |
|
NENP | Non-entry into the national phase |
Ref country code: DE |