TEST PRODUCTION CONDITION PROPOSAL SYSTEM AND TEST PRODUCTION CONDITION PROPOSAL PROCEDURE

Abstract

A technology is provided that is capable of proposing good test production condition(s) for a material with good accuracy, even when a parameter space to be searched is extensive for the computational resources to be used. A test production condition suggestion system 1 is a system for providing a material developer with test production condition(s) for a material and includes a regression model creation processing unit 112 and a test production condition suggestion processing unit 113. The regression model creation processing unit 112 performs regression model creation processing on measured property data indicating an actual measurement result of properties of the material.The test production condition suggestion processing unit 113 performs optimization processing for searching an optimal test production condition for the material using the created regression model, and performs test production condition suggestion processing based on a result of the optimization processing.

Description

TECHNICAL FIELD

[0001] The present invention relates to a system and a method for proposing test production conditions for (a) material(s) to a material developer(s). STATE OF THE ART

[0002] In the field of materials science for materials research and development, a method called "Materials Informatics (MI)" for efficiently predicting the physical properties, structures, etc. of materials using information technology (informatics) such as statistical analysis and machine learning is now widely used. Regarding materials research and development using this materials informatics, for example, a technology is known from PTL 1. PTL 1 discloses a system for estimating manufacturing conditions for substances with optimal physical properties and structures from a data set including manufacturing conditions for each of a plurality of substances that are samples and substance information indicating physical properties and structures of the respective substances. LITERATURE LISTPATENT LITERATURE

[0003] PTL 1: WO 2021 / 044913 SUMMARY OF THE INVENTION PROBLEMS TO BE SOLVED BY THE INVENTION

[0004] At the materials development site(s) where materials informatics are applied, various types of evaluation tests are typically conducted to actually measure the properties of a material(s) being developed, and data indicating the actual measurement results are obtained (hereinafter referred to as "measured property data"). Subsequently, various types of machine learning models are created by inputting these measured property data into a computer. Then, a condition(s) for test production of the material (hereinafter referred to as "test production condition(s)") is / are estimated using the learned machine learning models.

[0005] Incidentally, the aforementioned measured property data typically contain an extremely large number of explanatory variables. When the number of explanatory variables is extremely large, the number of combinations of the explanatory variables also becomes enormous. Accordingly, in most cases, it is necessary to search a very extensive parameter space if one wants to estimate a good test production condition(s) for the material based on materials informatics. On the other hand, there is usually a limit to the computing resources that can be consumed when a computer performs such processing.Therefore, if a good test production condition(s) for the material is to be estimated with realistic computational resources in realistic computation time, the parameter space to be searched is too large for the computational resources that can be expended, so that there is a risk that the good test production condition(s) cannot be estimated in realistic computation time.

[0006] In addition, the number of each of the above-mentioned measured property data (hereinafter also referred to as "the number of samples") is often small, and there are quite a few distortions in the distribution of the explanatory variables contained in each of the measured property data. Therefore, when a region far from a distribution range of the explanatory variables contained in the measured property data input to the construction of the machine learning models (hereinafter also referred to as "learning data") is searched in the parameter space to estimate the good test production condition(s) for the material, the estimation accuracy decreases compared to the case where the neighborhood of the distribution range of the explanatory variables is searched.Accordingly, the range of parameters to be searched with good accuracy is limited to the vicinity of the distribution range of the explanatory variables contained in the training data. Even if the entire range of the parameter space to be searched is thoroughly searched, there is a risk that the entire range of the parameter space will not be searched uniformly with good accuracy, and the assessment of the good test production condition(s) for the material may fail.

[0007] In view of the problems described above, it is an object of the present invention to provide a technology capable of proposing the good test production condition(s) for the material with good accuracy even when the parameter space to be searched is extensive for the computational resources to be used. MEANS TO SOLVE THE PROBLEMS

[0008] A test production condition suggestion system according to the present invention proposes test production conditions for a material to a material developer and includes a regression model creation processing unit and a test production condition suggestion processing unit. The regression model creation processing unit performs regression model creation processing on measured property data indicating an actual measurement result of properties of the material. The test production condition suggestion processing unit performs optimization processing to find an optimal test production condition for the material using the created regression model and executes the test production condition suggestion processing based on a result of the optimization processing.

[0009] Furthermore, a test production condition suggestion method according to the present invention is a method for suggesting a test production condition for a material to a material developer using a computer. This test production condition suggestion method causes the computer to execute regression model creation processing and test production condition suggestion processing. The regression model creation processing represents processing for creating a regression model for measured property data indicating an actual measurement result of the material's properties.The test production condition suggestion processing represents processing for performing optimization processing for searching an optimal test production condition for the material using the created regression model and for suggesting the test production condition for the material based on a result of the optimization processing.

[0010] Incidentally, the problems and their solutions disclosed in this application are explained in more detail in the DESCRIPTION OF THE EMBODIMENTS section and in the descriptions of the drawings. ADVANTAGES OF THE INVENTION

[0011] The good test production condition(s) for the material with good accuracy can be proposed according to the present invention, even if the parameter space to be searched is extensive for the computational resources to be used. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a schematic diagram illustrating the structure of a test production condition suggestion system according to an embodiment of the present invention; Fig. 2 is a diagram illustrating the functional blocks of the test production condition suggestion system according to an embodiment of the present invention; Fig. 3 is a flowchart illustrating a flow of the entire processing of the test production condition suggestion system according to an embodiment of the present invention; Fig. 4 is a flowchart illustrating the details of preprocessing of measured property data; Fig. Figure 5 is a flowchart showing the details of regression model building processing; Fig. 6 is a flowchart showing the details of test production condition suggestion processing; and Fig. Figure 7 is a figure illustrating the structure of a focused search. DESCRIPTION OF EMBODIMENTS

[0012] This embodiment is described in detail below. Fig. 1 is a schematic diagram showing the structure of a test production condition suggestion system according to an embodiment of the present invention. Fig. The test production condition suggestion system 1 shown in Figure 1 was developed to optimize each of the various test production conditions that must be considered during the test production of a material, such as the material composition and firing conditions, and to propose the results to a materials developer who is a user of this system. This optimization of the test production conditions is performed using various types of machine learning algorithms based on measured property data that indicate the actual measurement results of the properties of the material in question.Furthermore, various types of regression models such as Gaussian process regression (GPR) and linear regression, regression trees (including one case by an ensemble method), regression by a neural network (neural network regression), support vector regression (SVR), logistic regression, LASSO regression (Least Absolute Shrinkage and Selection Operator Regression) are used as prediction models.

[0013] As in Fig. As shown in Figure 1, when the user of the test production condition suggestion system 1 performs test production of a material under the test production condition(s) suggested by the test production condition suggestion system 1 and evaluates the properties of the material that is a product of the test production, measured property data indicating an evaluation value of the properties of that product are newly generated. After causing the test production condition suggestion system 1 to learn these measured property data as new learning data, the test production condition suggestion system 1 proposes more optimized test production condition(s) to the user. Each time the user repeats this workflow, the test production condition suggestion system 1 according to this embodiment can propose the test production condition(s) with a better predicted value of the properties.Incidentally, the test production condition suggestion system 1 may include a function for performing the test production of the material and a function for actually measuring the properties of the material that is the subject of the test production, and may be integrally configured with these functions.

[0014] The test production condition suggestion system 1 according to this embodiment is realized by a general-purpose computer device as shown in Fig. 1. In the following explanation, it is assumed that the test production condition suggestion system 1 is implemented by a general-purpose computer device including one or more processor devices, one or more storage devices, one or more input / output devices, and wired or wireless communication lines connecting these components (both are not shown in the drawing).

[0015] This computer device is installed, for example, as a terminal within a laboratory and is connected via a communication network such as the Internet 400 and leased lines to various other terminals installed inside and outside the laboratory, to various types of terminals such as laptops, tablets, and smartphones owned by each user (hereinafter referred to as "user terminals"), and to other devices such as server devices. Incidentally, the computer device and the Internet 400 are connected by wires via known communication devices (not shown in the drawing), but they may also be connected wirelessly.

[0016] An explanation of the various functions of the Test Production Condition Suggestion System 1 is then provided by Fig. 2 is referred to. Fig. 2 is a diagram illustrating the functional blocks of the test production condition suggestion system 1 according to an embodiment of the present invention. Incidentally, the respective blocks explained below denote functional unit blocks, but not hardware unit components. The test production condition suggestion system 1 according to this embodiment is configured as shown in Fig. 2, includes a control unit 11, a storage unit 12, a user interface unit 13 and a communication unit 14.

[0017] The control unit 11 performs various types of data processing based on the user inputs acquired by the user interface unit 13, the data acquired by the communication unit 14, and the programs and data stored in the storage unit 12. The control unit 11 also serves as an interface for the user interface unit 13, the communication unit 14, and the storage unit 12.

[0018] The control unit 11 includes respective functional blocks of a measured property data preprocessing unit 111, a regression model creation processing unit 112, and a test production condition suggestion processing unit 113. The control unit 11 is configured using, for example, processor devices such as a CPU (Central Processing Unit) and various types of coprocessors (hereinafter also referred to simply as "processors"), and can implement these functional blocks by executing specific programs. Incidentally, the control unit 11 can also be configured using, for example, logic circuits such as an FPGA (Field Programmable Gate Array) instead of the processors. Further, the control unit 11 can be configured using a combination of the processors and the logic circuits.

[0019] The programs to be executed by the control unit 11 can be installed from program source(s). The program source(s) can be, for example, a recording medium or the like that can be read by program distribution computer(s) or computer(s). Furthermore, the programs executed by the control unit 11 can be configured by a device driver, an operating system, various types of application programs located at an upper layer thereof, and a library that provides functions common to these programs. Furthermore, two or more programs can be implemented as one program, and one program can be implemented as two or more programs.

[0020] The measured property data preprocessing unit 111 applies preprocessing to the measured property data in a state of so-called raw data immediately after it is recorded. This processing performed by the measured property data preprocessing unit 111 is hereinafter referred to as "measured property data preprocessing."

[0021] The regression model creation processing unit 112 executes processing to create a regression model(s) with respect to the measured characteristic data to which the preprocessing has been applied. This processing performed by the regression model creation processing unit 112 is referred to as "regression model creation processing."

[0022] The test production condition suggestion processing unit 113 performs optimization processing to search the measured property data to which preprocessing has been applied for an optimal test production condition for the material using the regression model created by the regression model creation processing unit 112, and suggests the test production condition(s) for the material to the user based on the result of the optimization processing. This processing by the test production condition suggestion processing unit 113 is hereinafter referred to as "test production condition suggestion processing."

[0023] The specific content of these processing sequences will be described later.

[0024] The storage unit 12 is configured, for example, using storage devices such as RAM(s) and flash memory(s), and stores programs for providing various types of processing instructions to the control unit 11 and data indicating various types of information to be used for the processing performed by the control unit 11. For example, the measured characteristic data to which preprocessing has been applied by the measured characteristic data preprocessing unit 111 (hereinafter referred to as "preprocessed data"), data indicating regression models designed by the regression model creation processing unit 112, etc. are stored in the storage unit 12.The control unit 11 can implement the respective functional blocks of the aforementioned measured property data preprocessing unit 111, the regression model creation processing unit 112, and the test production condition suggestion processing unit 113 by reading / writing these individual pieces of information from / to the storage unit 12.

[0025] In addition to receiving user inputs, the user interface unit 13 is responsible for processing related to the user interface, such as image display and sound output. The user interface unit 13 has respective functional blocks of an input unit 131 and an output unit 132. The input unit 131 recognizes various types of user operations. The input unit 131 is configured, for example, using a keyboard, a pointing device, a touch panel, etc. The output unit 132 performs, for example, the screen display and sound output for the user. The output unit 132 is configured, for example, using a liquid crystal display and a touchscreen.

[0026] The communication unit 14 is responsible for communication processing performed over the Internet 400 with other devices such as each user's user terminal(s), the server device(s), and so on. The communication unit 14 is configured, for example, using a NIC (Network Interface Card) and an HBA (Host Bus Adapter).

[0027] This embodiment has been explained by describing that the respective functions of the test production condition suggestion system 1 are integrally implemented by one computer device. However, these respective functions may be implemented by a plurality of interconnected computer devices or server devices. The test production condition suggestion system 1 may also be configured by including a general-purpose computer device, such as a laptop, and a web browser installed in this general-purpose computer device, or it may be configured by including a web server and various types of portable devices.

[0028] Furthermore, the explanations of each function are examples, and a plurality of functions can be combined into one function or a function can be divided into a plurality of functions.

[0029] Next, an explanation of an entire flow of the test production condition suggestion system 1 will be given with reference to Fig. 3 provided. Fig. 3 is a flowchart illustrating a flow of the entire processing of the test production condition suggestion system 1 according to an embodiment of the present invention. Incidentally, in the following explanation, there is a case where the processing is explained by referring to each aforementioned function or program as the subject matter; however, the processing explained by referring to the function or program as the subject matter may be processing performed by a processor or a device including that processor.

[0030] In step S310, the control unit 11 causes the measured property data preprocessing unit 111 to perform the preprocessing of measured property data. Accordingly, the preprocessing is applied to the measured property data, which then becomes the preprocessed data, so that it becomes possible to perform any subsequent processing normally. Incidentally, the details of the preprocessing of measured property data performed in step S310 will be explained later with reference to a flowchart in Fig. 4. When the preprocessing of measured property data is completed, the control unit 11 proceeds to step S320.

[0031] In step S320, the control unit 11 causes the regression model creation processing unit 112 to execute the regression model creation processing. Accordingly, a regression model is created with respect to the preprocessed data. Incidentally, the details of the regression model creation processing performed in step S320 will be explained later with reference to a flowchart in Fig. 5. When the regression model creation processing is completed, the control unit 11 proceeds to step S330.

[0032] In step S330, the control unit 11 executes the regression model evaluation processing. This regression model evaluation processing is used to evaluate the generalization performance, which is an index indicating the prediction accuracy of the relevant regression model with respect to each of the plurality of regression models created as a result of the respective processing sequences before and in step S320. This evaluation is performed, for example, through cross-validation with other regression models. The evaluation result is visualized, for example, by a diagram such as a scatter plot or a box-and-whisker plot. As a result, the user can obtain a suggestion for the test production condition(s) based on the regression model with good generalization performance. When the regression model evaluation processing is completed, the control unit 11 proceeds to step S340.

[0033] In step S340, the control unit 11 causes the test production condition suggestion processing unit 113 to execute the test production condition suggestion processing. With this test production condition suggestion system, the user of the test production condition suggestion system 1 can modify the test production condition(s) for the material suggested by the test production condition suggestion system 1 as needed to make them more preferable. The control unit 11 determines a predicted value of the material's properties when the material is to be test-produced under the user-modified test production condition(s) by applying it to the selected regression model and presenting the predicted value to the user. Specifically, the user can perform this work interactively to modify the test production condition(s) while verifying the predicted value.Accordingly, the test production condition suggestion system 1 is designed as a system capable of incorporating the knowledge of the user, who is a developer of the relevant material, into the test production condition(s) for the material to be suggested to the user. Incidentally, the details of the test production condition suggestion processing performed in step S340 will be explained later with reference to a flowchart in FIG. Fig. 6. When the test production condition suggestion processing is completed, the control unit 11 ends the process shown in the flowchart in Fig. 3 processing shown once.

[0034] The test production condition suggestion system 1 according to this embodiment performs each processing in steps S310 to S340 in Fig. 3 and suggests good test production condition(s) to the user. Specifically, in the test production condition suggestion system 1 according to this embodiment, in step S310, the required preprocessing is automatically applied to the measured property data in a raw data state. Thus, each processing in steps S320 to S340 can be performed without the need for complicated manual preprocessing of the measured property data. Furthermore, with the test production condition suggestion system 1 according to this embodiment, the user can select a regression model with good generalization performance. Therefore, the test production condition suggestion system 1 can suggest to the user the test production condition(s) for which the predicted property value is good.

[0035] Furthermore, as already mentioned in relation to Fig. 1, the user of the test production condition suggestion system 1, after performing the test production of the material under the test production conditions suggested by the test production condition suggestion system 1, actually measuring the properties of the product, and causing the test production condition suggestion system 1 to learn data indicating the actual measurement result as new measured property data, can then cause the test production condition suggestion system 1 to execute each processing in steps S310 to S340 in Fig. 3 again. In this case, the test production condition suggestion system 1 may suggest more optimized test production condition(s) to the user. Specifically, the test production condition suggestion system 1 according to this embodiment may, each time it executes steps S310 to S340 in Fig. 3 with respect to the same test production object, suggest test production condition(s) with a better predicted value of the properties.

[0036] Fig. Figure 4 is a flowchart showing the details of preprocessing of measured property data.

[0037] In step S410, the control unit 11 causes the measured property data preprocessing unit 111 to receive an input of the measured property data from the user via the input unit 131 or the communication unit 14. The measured property data input to the test production condition suggestion system 1 may be, for example, category data, continuous data, or discrete data. Further, a specific data format of the measured property data to be input to the test production condition suggestion system 1 may be determined as appropriate. When the processing in step S410 is completed, the control unit 11 proceeds to step S420.

[0038] In step S420, the control unit 11 causes the measured property data preprocessing unit 111 to set a variable type related to the measured property data whose input was received from the user in step S410. Under these circumstances, either an explanatory variable(s) or a target variable(s) are set. The explanatory variable(s) is / are a variable that serves as a basis for determining a predicted value of the properties. In this embodiment, the material composition, firing conditions, etc., which constitute the test production conditions, correspond to the explanatory variables. Furthermore, the target variable(s) is / are a variable that indicates a characteristic value(s) of the material to be test-produced, which becomes a prediction object.As an example of concrete processing in step S420, the explanatory variable may be set as the default, and a setting operation may be accepted by the user who wishes to change it to the target variable. When the processing in step S420 is completed, the control unit 11 proceeds to step S430.

[0039] In step S430, the control unit 11 causes the measured characteristic data preprocessing unit 111 to judge whether or not there is an abnormal value with respect to the measured characteristic data to which either the explanatory variable or the target variable was set in step S420. This processing for judging whether or not there is an abnormal value is performed, for example, by displaying the measured characteristic data as a histogram and judging whether or not there is an outlier outside the range of an average value ±2σ, and then judging whether or not there is a data input error or a failure of an evaluation test device in generating the measured characteristic data, in which the presence of the outlier is determined.On the one hand, if it is determined that the measured characteristic data contains an abnormal value, the control unit 11 deletes this abnormal value and recognizes it as a missing value, and proceeds to step S440. Further, if the type of abnormal value included in the measured characteristic data is one of the variables, that is, a target variable, in which the explanatory variables are completely duplicated and there is a standard with different characteristics, the control unit 11 deletes (a) sample(s) related to this abnormal value and proceeds to step S440. In such a case where all the explanatory variables are duplicated and the standard with different characteristics is treated as an abnormal value, the standard itself must be deleted, unlike the case where part of the explanatory variables is an abnormal value, for example, due to an input error.On the other hand, if it is determined that no abnormal value is included in the measured characteristic data, the control unit 11 proceeds directly to step S440.

[0040] Incidentally, if all explanatory variables are duplicated and there is a standard with different properties, as described above, duplication may be considered reasonable, and it may sometimes be desirable to retain all explanatory variables. In such a case, the test production condition suggestion system 1 according to this embodiment may skip the processing in step S430.

[0041] In step S440, the control unit 11 causes the measured characteristic data preprocessing unit 111 to judge whether or not any missing value(s) are / are missing in the measured characteristic data. This judgment is made because the measured characteristic data sometimes includes the missing value(s) in advance. On the one hand, if it is judged that the missing value(s) are / are included in the measured characteristic data, the control unit 11 supplements the missing value(s) and proceeds to step S450. The missing value supplement processing is performed, for example, using an average value, a median value, a minimum value, a maximum value, etc. of the measured characteristic data, excluding an abnormal value(s), as values ​​to supplement the missing value(s). Further, the missing value(s) may be supplemented using linear interpolation.Incidentally, when the missing value(s) is / are supplemented in step S440, the measured property data preprocessing unit 111 may display the supplemented value, for example, in red font to facilitate identification of the supplemented value. Furthermore, the measured property data preprocessing unit 111 may delete standards itself, for example, without supplementing the corresponding missing value in step S440. Furthermore, in the test production condition suggestion system 1 according to this embodiment, when a large proportion of missing explanatory variables is present, for example, when 50% or more of the data set is missing, the measured property data preprocessing unit 111 may delete the relevant explanatory variables itself. On the other hand, when it is judged that the missing value(s) is / are not included in the measured property data, the control unit 11 proceeds directly to step S450.

[0042] If the explanatory variable is not a continuous value but a category value, in step S450, the control unit 11 causes the measured characteristic data preprocessing unit 111 to perform coding processing on the relevant explanatory variables and convert them into numerical value data. The measured characteristic data preprocessing unit 111 performs this coding processing by, for example, referring to a record in a table indicating the correspondence relationship between the category data and the numerical value data, which is stored in the storage unit 12. When the processing in step S450 is completed, the control unit 11 proceeds to step S460.

[0043] In step S460, the control unit 11 causes the measured characteristic data preprocessing unit 111 to judge whether or not redundant explanatory variables are included in the measured characteristic data. This judgment is made based on whether a combination of explanatory variables with a correlation coefficient equal to or greater than a specific number, for example, 0.8 or more, can be extracted. On the one hand, if it is judged that redundant explanatory variables are included in the relevant measured characteristic data, the control unit 11 deletes one of the redundant explanatory variables and proceeds to step S470.Incidentally, in the test production condition suggestion system 1 according to this embodiment, the combination of explanatory variables whose correlation coefficient is equal to or greater than 0.8 is visualized to the user via the output unit 132, so that the explanatory variable to be deleted can be selected via the input unit 131. On the other hand, if it is judged that no redundant explanatory variable(s) is / are included in the relevant measured characteristic data, the control unit 11 proceeds directly to step S470.

[0044] In step S470, the control unit 11 causes the measured property data preprocessing unit 111 to perform standardization processing of the measured property data, if necessary. The standardization processing is to convert the scale of the measured property data so that an average = 0 and a standard deviation (variance) = 1 are obtained. When the processing in step S470 is completed, the control unit 11 stores the preprocessed data, that is, the measured property data to which the preprocessing in steps S410 to S470 was applied, in Fig. 4 was applied, in the storage unit 12 and terminates the preprocessing of measured property data, as shown in the flowchart in Fig. 4. Furthermore, the control unit 11 may cause the measured characteristic data preprocessing unit 111 to perform normalization processing on the measured characteristic data if necessary. In such a case, any of the subsequent processing may be performed without performing the standardization processing in S470.

[0045] Fig. Figure 5 is a flowchart showing the details of regression model building processing.

[0046] In step S510, the control unit 11 causes the regression model creation processing unit 112 to select (a) condition(s) for implementing cross-validation to evaluate a regression model to be created with respect to the preprocessed data. Incidentally, the test production condition suggestion system 1 according to this embodiment evaluates each regression model using K-fold cross-validation. Furthermore, K=10 is set as the implementation condition as the default. In this case, the test production condition suggestion system 1 evaluates the regression model using 10-fold cross-validation. Incidentally, the test production condition suggestion system 1 according to this embodiment also allows the user to select the cross-validation implementation condition(s).More specifically, the regression model creation processing unit 112 may accept the implementation condition(s) for cross-validation from the user via the input unit 131 or the communication unit 14. When the processing in step S510 is completed, the control unit 11 proceeds to step S520.

[0047] In step S520, the control unit 11 causes the regression model creation processing unit 112 to select a candidate regression model to be used as the prediction model for searching for the test production conditions. When this happens, the regression model creation processing unit 112 selects as candidates the regression model(s) for which it has accepted the user's selection processing via the input unit 131 or the communication unit 14.With the test production condition suggestion system 1 according to this embodiment, the user can select a variety of regression models as candidates from various types of regression models, such as Gaussian process regression, the above-mentioned linear regression, regression trees (including a case by an ensemble method), neural network regression, support vector regression, logistic regression, and LASSO regression. When the processing in step S520 is completed, the control unit 11 proceeds to step S530.

[0048] In step S530, the control unit 11 causes the regression model creation processing unit 112 to execute processing for calculating a weight reference, which is a reference for the weight of the measured property data. The weight reference is calculated based on the difference between the target variable included in the measured property data and a target property indicating a target value of the material's properties, or a statistical amount indicating the rarity of the explanatory variable included in the measured property data. Incidentally, a specific example of the statistical amount indicating the rarity of the explanatory variable may include an occurrence probability of the explanatory variable satisfying a specific condition(s). When the processing in step S530 is completed, the control unit 11 proceeds to step S540.

[0049] In step S540, the control unit 11 causes the regression model creation processing unit 112 to execute processing for weighting the measured property data based on the weight reference calculated in step S530. Furthermore, in the test production condition suggestion system 1 according to this embodiment, the regression model creation processing unit 112 may directly weight the regression model based on the weight reference calculated in step S530.Incidentally, the processing executed in step S540 by the regression model creation processing unit 112 based on the result of step S530 is one of processing for setting a loss function that is a function serving as a learning index, oversampling processing for amplifying rare or highly important measured feature data and adding the amplified data as learning data, or undersampling processing for deleting redundant or less important measured feature data from the learning data. While these processing sequences are being executed, the weight of the above-described learning data is adjusted accordingly, even when the number of individual learning data to be used to create a machine learning model is small or when there is a bias in the distribution of the learning data.This makes it possible to improve the estimation accuracy and propose the test production condition(s) for a good material with good accuracy. When the processing in step S540 is completed, the control unit 11 proceeds to step S550.

[0050] In step S550, the control unit 11 causes the regression model creation processing unit 112 to search for and set an optimal hyperparameter for each method selected as a candidate in step S520. In the test production condition suggestion system 1 according to this embodiment, the regression model creation processing unit 112 automatically searches for all parameters for each regression model and automatically sets a parameter that realizes the best generalization performance of the relevant regression model when the parameter is set as a hyperparameter when creating the regression model. When the processing in step S550 is completed, the control unit 11 proceeds to step S560.

[0051] In step S560, the control unit 11 causes the regression model creation processing unit 112 to perform regression model creation processing for each method for which the optimal hyperparameter has been determined. When the regression model creation processing unit 112 creates the regression model for each method, it performs processing to select a regression model with the highest generalization performance from all created regression models and determine a final regression model. When the processing in step S560 is completed, the control unit 11 ends the process shown in the flowchart in Fig. 5 shows the processing used to create the regression model.

[0052] Fig. Figure 6 is a flowchart showing the details of test production condition suggestion processing.

[0053] In step S610, the control unit 11 causes the test production condition suggestion processing unit 113 to start the processing for searching for the test production conditions based on the result obtained in step S560 in Fig. 8. The test production condition suggestion processing unit 113 performs this processing by means of optimization processing (its details will be described later). Incidentally, the test production condition suggestion system 1 according to this embodiment is configured to be capable of applying various types of optimization methods such as mathematical optimization (MO), Bayesian optimization (BO), genetic algorithm (GA), Newton's method (NM), and simplex method (SM). As a result, when a predicted value of the characteristics, i.e., the target variable, becomes the best, the respective explanatory variables are suggested to the user as preliminary test production condition(s), indicating the results of the relevant search processing.Further, under these circumstances, the test production condition suggestion processing unit 113 performs a sensitivity analysis of the relevant preliminary test production condition(s), evaluates the importance of the respective explanatory variables constituting the relevant preliminary test production condition, and compiles the evaluation results. Furthermore, the test production condition suggestion system 1 according to this embodiment can select the test production condition that maximizes the detection function when the regression model used is Gaussian process regression. When the processing in step S610 is completed, the control unit 11 proceeds to step S620.

[0054] In step S620, the control unit 11 causes the test production condition suggestion processing unit 113 to accept from the user a change(s) to the preliminary test production condition proposed to the user in step S610. After accepting an input operation regarding the change(s) to the values ​​of the respective explanatory variables constituting the preliminary test production condition via the input unit 131 or the communication unit 14, the test production condition suggestion processing unit 113 changes the preliminary test production condition according to the change content. Furthermore, under these circumstances, the control unit 11 causes: determining a predicted value for the properties of the material when the material is test-produced under the modified test production conditions using the regression model; and presenting the calculation result to the user.Furthermore, under these circumstances, the test production condition suggestion processing unit 113 also performs the sensitivity analysis of the modified preliminary test production condition in the same manner as in step S610, evaluates the significance of the explanatory variables constituting the relevant modified test production condition, and presents the evaluation results together. Furthermore, these evaluation results are updated each time the user changes the preliminary test production condition, and the user is always presented with the latest evaluation result. When the processing in step S620 is completed, the control unit 11 proceeds to step S630.

[0055] In step S630, the control unit 11 causes the test production condition suggestion processing unit 113 to judge whether or not the predicted value of the properties of the modified preliminary test production condition obtained in step S620 is insufficient as the property value of the material subject to test production.For example, if the regression model to be used is Gaussian process regression, this assessment is performed for each test production condition by determining an acquisition function that indicates an expected value for an improvement in the properties of the material test-produced under the relevant test production condition, with respect to the modified preliminary test production condition, and assessing whether the difference between the value of the relevant acquisition function and a maximum value of the acquisition function lies within a specific range. Furthermore, the acquisition function is calculated based on the predicted value µ of the material properties and a standard deviation σ that indicates the deviations of the relevant predicted value when the test production of the material is conducted under any test production condition.If it is judged that the predicted property value is insufficient, the processing returns to step S620 and again accepts an instruction to change the test production condition from the user; and if it is judged that the predicted property value is not insufficient, it means that the predicted value of the material's properties is sufficient when performing test production under the relevant modified preliminary test production condition, so the preliminary test production condition is determined to be final, and a suggestion is made to the user that the test production condition is completed. Specifically, this judgment processing is repeated until it is judged that the predicted value of the material's properties is not insufficient with respect to the preliminary test production condition(s).When the processing in step S630 is completed, the control unit 11 ends the processing shown in the flowchart in FIG. Fig. 6 shows the test production condition suggestion processing.

[0056] Incidentally, the test production condition suggestion processing unit 113 either executes the optimization processing by a sampling method or executes the optimization processing continuously in step S610. The sampling method is a method of generating a plurality of test production standard candidates and selecting a test production standard candidate with the best characteristics. With the test production condition suggestion system 1 according to this embodiment, the user can select these two types of execution methods when executing the optimization processing in step S610. Of these methods, the specific content of the processing executed in step S610 when the test production condition suggestion processing unit 113 executes the optimization processing by the sampling method will be described below as steps S611 to S616.

[0057] In step S611, when the control unit 11 receives an input operation from the user via the input unit 131 to specify the number of test production standard candidates to be created, it causes the test production condition suggestion processing unit 113 to perform processing for generating the specified number of test production standard candidates. This processing is referred to as "test production standard candidate generation processing." The test production standard candidate generation processing includes the processing that causes the computer to repeatedly execute each processing from steps S614 to S616, which will be described later, the specified number of times. As a result of the test production standard candidate generation processing, as many test production standard candidates as the number specified by the user are generated. With the test production condition suggestion system 1 according to this embodiment, 10.000 test production standard candidates are generated according to the user's specifications. When the processing in step S611 is completed, the control unit 11 proceeds to step S612.

[0058] In step S612, the control unit 11 causes the test production condition suggestion processing unit 113 to perform processing for calculating predicted values ​​or acquisition functions for all test production standard candidates generated in step S611. This processing is referred to as "calculation processing." As a result of the calculation processing, the predicted values ​​or acquisition functions are calculated for all test production standard candidates generated in step S611. When the processing in step S612 is completed, the control unit 11 proceeds to step S613.

[0059] In step S613, the control unit 11 causes the test production condition suggestion processing unit 113 to perform processing to extract a test production condition with the best predicted value or the best detection function from all the test production standard candidates generated in step S611 based on the predicted values ​​or the detection functions calculated in step S612. This processing is hereinafter referred to as "extraction processing." The test production condition suggestion processing unit 113 executes the extraction processing to be performed in step S613 using the various types of optimization processing methods previously described in connection with step S610.As a result of the extraction processing, the test production standard candidate with the best predicted value or the best detection function as the test production condition is extracted from all the test production standard candidates generated in step S611. When the processing in step S613 is completed, the control unit 11 ends the optimization processing executed in step S610.

[0060] Incidentally, the test production standard candidate generation processing executed in step S611 includes the aforementioned processing that causes the computer to repeatedly execute each of the processings from steps S614 to S616 described below the specified number of times.

[0061] In step S614, the control unit 11 causes the test production condition suggestion processing unit 113 to perform processing for selecting a test production standard as a basis from among the test production standard candidates whose characteristics have been measured. This processing is hereinafter referred to as "selection processing." In the selection processing, the measured characteristic data is used as a test production standard candidate whose characteristics have been measured. More specifically, in the selection processing, the measured characteristic data with good characteristics is extracted from a plurality of pieces of the measured characteristic data. Subsequently, a selection probability is calculated so that the extracted measured characteristic data with good characteristics is intensively selected as the test production conditions.Furthermore, the measured property data are randomly selected according to the calculated selection probability. A combination of raw materials in the selected measured property data is set as the test production standard candidate. Accordingly, in the selection processing, the test production standard to be used as the basis is randomly selected according to the calculated selection probability, so as to intensively select the measured property data with the good properties among the measured property data that are considered as test production standard candidates. Consequently, the test production standard candidates with the good properties can be easily selected as test production conditions. Furthermore, the selection processing may include processing for weighting the selection probability of the test production standard to be used as the basis.In such a case, the test production standard that is preferable as a basis can be more easily selected by performing the weighting as described above. As a result of the selection processing, a combination of raw materials is determined as a candidate test production standard to serve as a basis. When the processing in step S614 is completed, the control unit 11 proceeds to step S615.

[0062] In step S615, the control unit 11 causes the test production condition suggestion processing unit 113 to perform processing to output variations of the test production standard selected in step S614 with a random number within a range suitable for test production of the material. This processing is referred to as "variation processing." In this variation processing, first, a composition ratio of the raw material is set for the relevant test production standard candidate, with the total value not exceeding it. Next, an average particle size and a maximum firing temperature of the relevant test production standard candidate are calculated based on the combination of the raw material determined in step S614 and the raw material composition ratio determined in step S615.Then, other explanatory variables are determined according to the distribution of the relevant explanatory variables contained in each of the measured property data. As a result of the variation processing, the values ​​of various explanatory variables, such as the composition ratio of materials, are determined with respect to the test production standard candidate to serve as a basis. When the processing in step S615 is completed, the control unit 11 proceeds to step S616.

[0063] In step S616, the control unit 11 causes the test production condition suggestion processing unit 113 to perform processing for storing the test production standard candidate(s) to which the variation processing in step S615 was applied. This processing is referred to as "storage processing." As a result of the storage processing, the test production standard candidates are stored by writing them to the storage unit 12. When the processing in step S616 is completed, the control unit 11 returns to step S614 and executes each of the aforementioned processing from step S614 to step S616 again. Each processing in steps S614 to S616 is repeatedly executed a predetermined number of times. In the test production condition suggestion system 1 according to this embodiment, the number becomes 10.000 times is the number of times to repeatedly execute each processing from step S614 to step S616. Thus, each processing from step S614 to step S616 is executed 10,000 times. Consequently, in the test production standard candidate generation processing performed in step S611, necessary and sufficient test production standard candidates are generated to extract the test production condition(s) with good characteristics. After each processing from step S614 to step S616 is repeatedly executed 10,000 times, the control unit 11 ends the test production standard candidate generation processing in step S611 and proceeds to step S612.

[0064] Incidentally, the test production standard candidate generation processing executed in step S611 may further include: judgment processing for judging whether a test production standard to serve as a basis exists; and base generation processing for generating the basis with a random number when the judgment processing judges that the basis does not exist. In such a case, even if the basis does not exist, a test production standard candidate can be generated in the same way as in the case where the basis exists, by generating the basis with the random number.

[0065] On the other hand, when the test production condition suggestion processing unit 113 continuously performs the optimization processing, the concrete content of the processing executed in step S610 will be described below as steps S617 to S619.

[0066] In step S617, the control unit 11 causes the test production condition suggestion processing unit 113 to perform processing for selecting a test production standard that will become an initial value from the test production standard candidates whose characteristics have been measured. This processing is hereinafter referred to as "selection processing." In the selection processing, the measured characteristic data is used as a test production standard candidate whose characteristics have been measured. More specifically, in the selection processing, the measured characteristic data to be used as the initial value of the test production standard is selected from the plurality of items of the measured characteristic data. In the selection processing, the test production standard to be used as the initial value is randomly selected.Therefore, when searching for the test production conditions in step S610, the range within the parameter space to be searched is less likely to be distorted. The selection processing may also include processing for performing weighting of the selection probability for selecting the test production standard that becomes the initial value. In such a case, it becomes easier to select a test production standard that is favorable as the initial value by performing weighting as described above. When the processing in step S617 is completed, the control unit 11 proceeds to step S618.

[0067] In step S618, the control unit 11 causes the test production condition suggestion processing unit 113 to perform processing for setting a penalty in the event of a deviation from a specific restriction condition with respect to the selected test production standard. This processing is referred to as "penalty setting processing." When the penalty is added in step S619 as a penalty setting method, a very large negative number is specified as the evaluation value for the penalty. Even when the initial value is multiplied by the penalty in step S619, zero (0) is specified as the evaluation value for the penalty. In the test production condition suggestion system 1 according to this embodiment, when the selected test production standard deviates from the specific restriction condition, zero (0) is specified as the evaluation value with respect to the penalty as the initial setting in step S618.Subsequently, this test production standard is ignored because the output value is multiplied by zero (0) in step S619. Furthermore, with the test production condition suggestion system 1 according to this embodiment, the constraint condition(s) that "the relevant material can be test-produced" is set in advance, that is, "the range or combination of parameters with which the relevant material can be test-produced is permissible." Consequently, the material science constraint condition(s) are imposed, so that the test production condition suggestion system 1 can only suggest the test production condition that allows the material to actually be test-produced.Further, other specific examples of the constraint conditions may include: "The environment of the existing measured property data that is close to the target physical properties is intensively searched" and "The environment of the test production conditions that are considered effective from a materials science perspective is intensively searched." Incidentally, the number of previously set constraint conditions may be one or more. Specifically, only a single constraint condition or a combination of a plurality of constraint conditions may be set. Furthermore, the test production condition suggestion processing unit 113 may automatically adjust the preset constraint conditions and parameters within the constraint conditions (such as a weight for performing a focused search) so that the obtained predicted value or the acquisition function becomes the best.When the processing in step S618 is completed, the control unit 11 proceeds to step S619.

[0068] In step S619, the control unit 11 causes the test production condition suggestion processing unit 113 to perform processing for optimizing the test production condition so that the predicted value or the detection function to which the penalty set in step S618 is added or multiplied by this penalty becomes the best. The test production condition suggestion processing unit 113 executes this processing in step S619 using the various types of optimization methods previously described in connection with step S610. Furthermore, the test production condition suggestion processing unit 113 executes this processing in step S619 the number of times specified by the user. In the test production condition suggestion system 1 according to this embodiment, the number of 10,000 times is referred to as the number of times to repeatedly execute the processing in S616.Thus, the processing in step S619 is repeatedly executed 10,000 times. When the processing in step S619 is completed, the control unit 11 ends the optimization processing executed in step S610.

[0069] Incidentally, the optimization processing executed in step S610, similar to the sampling method, may further include: judgment processing for judging whether a test production standard to serve as a basis exists; and baseline generation processing for generating the basis with a random number when the judgment processing judges that the basis does not exist. In such a case, even if the basis does not exist, a test production standard candidate can be generated in the same way as in the case where the basis exists, by generating the basis with the random number.

[0070] Accordingly, the optimization processing executed in step S610 is performed by the sampling method or continuously. Of these methods, when the optimization processing is performed by the sampling method, a test production standard candidate with the best characteristics is selected from the plurality of test production standard candidates, so that the test production condition suggestion system 1 can estimate the best test production conditions for the material and propose them as preliminary test production conditions. Furthermore, the test production standard is refined during continuous optimization processing compared to one-time optimization processing, so that the test production condition suggestion system 1 can estimate the best test production conditions for the material and propose them as preliminary test production conditions. Fig. 7 shows how the test production condition proposal processing unit 113 searches for the preliminary test production condition that is a target to be proposed by performing the optimization processing in step S610 in this way. Fig. 7 also shows, as a comparative example, how the preliminary test production condition, which is the objective to be proposed, is sought using a conventional technology. Fig. 7 is a scattergram showing estimated data on a coefficient of thermal expansion (CTE) and flexural strength, which are properties of a ceramic composite material made from a plurality of specific raw materials. In the conventional technology described above, only the entire extensive parameter space is thoroughly searched, so the search in the vicinity of the target area within this parameter space is sparse. On the other hand, the test production condition suggestion system 1 according to this embodiment can perform a focused search in the vicinity of the target area within the parameter space by performing optimization processing via the sampling method as indicated in steps S611 to S616 or by continuously performing optimization processing as indicated in steps S617 to S619.More specifically, the test production condition suggestion system 1 according to this embodiment can efficiently determine many test production conditions capable of satisfying the desired characteristics by increasing the degree of influences as test production standard candidates for the measured characteristic data having the good characteristics and thereby intensively searching for the test production conditions close to the characteristics of the measured characteristic data, as shown in FIG. Fig. 7 is specified.

[0071] Incidentally, the test production condition suggestion system 1 according to this embodiment suggests optimized test production conditions to the user based on the newly input measured property data as described above when the user performs the test production of the material under the test conditions specified in step S630 in Fig. 6 proposed test production condition(s) and the data indicating the actual measurement result of the product's properties are input as new measured property data. In this case, the control unit 11 for the test production condition suggestion system 1 judges whether or not a missing value is included in the newly inputted measured property data. If, on the one hand, it is judged that a missing value is included, the preprocessing for measured property data is applied to the newly inputted measured property data to supplement this missing value by executing the processing from step S440 in Fig. 4 begins. On the other hand, if it is judged that a missing value is not included, it is not necessary to perform the preprocessing of measured property data on the newly inputted measured property data. Therefore, in such a case, the control unit 11 judges whether it is necessary to update the regression model or not. On the one hand, if it is judged that it is necessary to update the regression model, the control unit 11 executes the regression model creation processing on the newly inputted measured property data by executing the processing from step S510 in Fig. 5 to generate a regression model again. On the other hand, if it is judged that it is not necessary to update the regression model, the control unit 11 skips the regression model creation processing and the regression model evaluation processing and performs the test production condition suggestion processing on the newly input measured property data by continuing the processing from step S610 in Fig. 6 using the most recently generated regression model. Incidentally, if it is not necessary to update the regression model even if a missing value is included in the newly input measured property data, the control unit 11 similarly omits the regression model creation processing and the regression model evaluation processing.

[0072] According to the above-described embodiment of the present invention, the following operational advantages can be achieved.

[0073] (1) The test production condition suggestion system 1 is a system for suggesting test production conditions for (a) material(s) to a material developer and includes the regression model creation processing unit 112 and the test production condition suggestion processing unit 113. The regression model creation processing unit 112 performs the regression model creation processing ( Fig. 5) based on the measured property data indicating the actual measurement result of the material's properties (step S320). The test production condition suggestion processing unit 113 performs optimization processing to find an optimal test production condition for the material using the created regression model (step S610) and performs the test production condition suggestion processing ( Fig. 6) based on the result of the optimization processing from (step S610) (step S340). Consequently, the good test production condition(s) for the material can be proposed with good accuracy, even if the parameter space to be searched is extensive for the computational resources to be used.

[0074] (2) The optimization processing (step S610) includes: test production standard candidate generation processing (step S611) for generating a predetermined number of test production standard candidates; calculation processing (step S612) for calculating predicted values ​​or coverage functions for all generated test production standard candidates; and extraction processing (step S613) for extracting a test production condition with a best predicted value or coverage function. Accordingly, a test production standard candidate with the best predicted value or coverage function is extracted as the test production condition from all generated test production standard candidates. Thus, the test production condition suggestion system 1 can estimate the best test production conditions for the material.

[0075] (3) The test production standard candidate generation processing (step S611) includes the processing that causes the computer to repeatedly execute the following processing a predetermined number of times: the selection processing (step S614) for selecting a test production standard to be used as a basis from the test production standard candidates whose properties have been measured; and the variation processing (step S615) for assigning variations of the selected test production standard with a random number within a range suitable for test production of the material; and the storage processing (step S616) for storing the test production standard candidates to which the variation processing (step S615) has been applied.Accordingly, the test production standard candidate generation processing (step S611) generates necessary and sufficient test production standard candidates with good accuracy to extract the test production condition(s) with good properties.

[0076] (4) The test production standard to be used as a basis is randomly selected through selection processing (step S614). Accordingly, the test production standard candidates with good properties can be easily selected as the test production condition(s).

[0077] (5) The selection processing (step S614) may include processing (not shown in the drawing) for performing weighting of the selection probability for selecting the test production standard to serve as the basis. In such a case, it becomes easier to select the test production standard that is preferred as the basis by performing the weighting as described above.

[0078] (6) The test production standard candidate generation processing (step S611) may further include: judgment processing (not shown in the drawing) for judging whether the test production standard to be used as a basis exists; and baseline generation processing (not shown in the drawing) for generating the basis with a random number when the judgment processing (not shown in the drawing) judges that the basis does not exist. In such a case, even if the basis does not exist, the test production standard candidate(s) can be generated in the same way as in the case where the basis exists, by generating the basis with the random number.

[0079] (7) The optimization processing (step S610) includes: selection processing for selecting a test production standard that will become the initial value from the test production standard candidates whose properties have been measured (step S617); penalty setting processing for setting a penalty in case of deviation from a specified constraint condition with respect to the selected test production standard (step S618); and processing for optimizing the test production condition so that a predicted value or detection function to which the set penalty is added or multiplied by the set penalty becomes the best (step S619). Accordingly, the test production standard is refined compared to the case where the optimization processing is performed once. Thus, the test production condition suggestion system 1 can estimate the best test production condition for the material.

[0080] (8) The test production standard to be the initial value is randomly selected through the selection processing (step S617). Accordingly, when searching for the test production condition (step S610), the range within the parameter space to be searched is less likely to be distorted.

[0081] (9) The selection processing (step S617) may include processing for performing weighting of the selection probability for selecting the test production standard as the initial value (not shown in the drawing). In such a case, it becomes easier to select the test production standard that is preferred as the initial value by performing the weighting as described above.

[0082] (10) The optimization processing (step S610) may further include: judgment processing (not shown in the drawing) for judging whether the test production standard to be used as a basis exists or not; and basis generation processing (not shown in the drawing) for generating the basis with a random number when it is judged by the judgment processing (not shown in the drawing) that the basis does not exist. In such a case, even if the basis does not exist, the test production standard candidate(s) can be generated in the same way as in the case where the basis exists by generating the basis with the random number.

[0083] (11) The constraint condition is that the relevant material can be produced on a trial basis. Accordingly, the material science constraint is imposed, so that the trial production condition proposal system 1 can only propose the trial production condition that actually allows the material to be produced on a trial basis.

[0084] Incidentally, the present invention is not limited to the above-described embodiment and can be implemented using any components within the scope that does not deviate from the gist of the invention.

[0085] The embodiments and variations described above are merely examples, and the present invention is not limited to their contents unless the characteristics of the invention are impaired. Furthermore, various embodiments and variations are explained above, but the present invention is not limited to their contents. Other aspects conceivable within the scope of the technical ideas of the present invention are also included within the scope of the present invention. LIST OF REFERENCE SYMBOLS 1 test production condition suggestion system 11 Control unit 12 storage units 13 User interface unit 14 Communication unit 111 Preprocessing unit for measured property data 112 Regression model building processing unit 113 Test production condition suggestion processing unit 131 Input unit 132 Output unit 400 Internet QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] WO 2021 / 044913

[0003]

Claims

[1] Test production condition suggestion system to suggest a test production condition for a material to a material developer, where the test production condition suggestion system comprises: a regression model creation processing unit that performs regression model creation processing on measured property data indicating an actual measurement result of properties of the material; and a test production condition suggestion processing unit that performs optimization processing for searching an optimal test production condition for the material using the created regression model and executes test production condition suggestion processing based on a result of the optimization processing. [2] The test production condition suggestion system according to claim 1, wherein the optimization processing includes: Test production standard candidate generation processing for generating a specified number of test production standard candidates; Calculation processing for calculating predicted values ​​or acquisition functions for all generated test production standard candidates; and Extraction processing to extract a test production condition with a best predicted value or best capture function. [3] The test production condition suggestion system according to claim 2, wherein the test production standard candidate generation processing includes processing that causes the computer to repeatedly execute the following processing a predetermined number of times: Selection processing for selecting a test production standard to serve as a basis from the test production standard candidates whose characteristics have been measured; Variation processing for outputting variations of the selected test production standard with a random number within a range suitable for test production of the material; and Storage processing for storing the test production standard candidates to which variation processing has been applied. [4] The test production condition suggestion system according to claim 3, wherein the test production standard to be used as a basis is randomly selected by the selection processing. [5] The test production condition suggestion system according to claim 4, wherein the selection processing includes processing for performing weighting of the selection probability of selecting the test production standard to be used as a basis. [6] The test production condition suggestion system according to claim 3, wherein the test production standard candidate generation processing further includes: Judgment processing for judging whether the test production standard to serve as a basis exists or not; and Basis generation processing for generating the basis with a random number when it is judged by the judgment processing that the basis does not exist. [7] The test production condition suggestion system according to claim 1, wherein the optimization processing further includes: Selection processing for selecting a test production standard to become the baseline from the test production standard candidates whose properties have been measured; Penalty setting processing for setting a penalty in case of deviation from a specific restriction condition with respect to the selected test production standard; and Processing to optimize the test production condition so that a predicted value or detection function to which the specified penalty is added or multiplied by the specified penalty achieves the best value. [8] The test production condition suggestion system according to claim 7, wherein the test production standard to be the initial value is randomly selected by the selection processing. [9] The test production condition suggestion system according to claim 8, wherein the selection processing includes processing for performing weighting of the selection probability of selecting the test production standard to become the initial value. [10] The test production condition suggestion system according to claim 7, wherein the optimization processing further includes: Judgment processing for judging whether the test production standard to serve as a basis exists or not; and Basis generation processing for generating the basis with a random number when it is judged by the judgment processing that the basis does not exist. [11] The test production condition suggestion system according to claim 7, wherein the constraint condition is that the material can be produced on a test basis. [12] Test production condition proposal method for proposing a test production condition for a material to a material developer using a computer, wherein the computer is caused to perform the following: Regression model creation processing for creating a regression model for measured property data indicating an actual measurement result of the properties of the material; and Test production condition suggestion processing for performing optimization processing for finding an optimal test production condition for the material using the created regression model and proposing a test production condition for the material based on a result of the optimization processing.

Images