JP7215017B2 - RUBBER MATERIAL DESIGN METHOD, RUBBER MATERIAL DESIGN DEVICE, AND PROGRAM - Google Patents

Description

The present invention relates to a rubber material design method, a rubber material design device, and a program that cause a computer to calculate a combination of raw materials for a vulcanized rubber composition in order to realize a target value of a feature amount that characterizes the vulcanized rubber composition.

2. Description of the Related Art In recent years, techniques for predicting various feature amounts from input data by causing computers to perform machine learning have been actively proposed. For a vulcanized rubber composition produced by blending a plurality of rubber materials, fillers, oils, etc. as raw materials, it is conceivable to apply the prediction of the physical property data to the above technique.
BACKGROUND ART Conventionally, a vulcanized rubber composition has been experimentally prepared by blending a plurality of rubber materials, fillers, oils, and the like by trial and error, and physical property data has been measured. For this reason, a large amount of data linking the compounding information and physical property data of the vulcanized rubber composition is accumulated. Utilizing this accumulated data, it is possible to make a computer perform machine learning and predict physical property data.

For example, there is a technology related to an optimization analysis device and a design method for a multicomponent material that facilitates material design of a material composed of multiple components and can preset the design range of the composition ratio of the material and the desired range of mechanical behavior. It is known (Patent Document 1).

In the above technology, learning is performed so as to convert the composition ratio of the multicomponent material composed of multiple components into the mechanical behavior of the multicomponent material, and the composition ratio of the multicomponent material composed of multiple components is converted. A transformation system using a neural network with nonlinear correspondences is defined, with the input as the input and the mechanical behavior of the multi-component material as the output. After that, an objective function representing the mechanical behavior is defined, and a constraint condition that restricts the permissible range of at least one of the mechanical behavior and the composition ratio of the multi-component material is defined. Furthermore, using the determined conversion system, optimization is performed to give the optimum value of the objective function based on the objective function and constraints, and the composition ratio of the multi-component material is obtained, and based on the composition ratio of the multi-component material Design rubber materials.

Japanese Patent No. 4393586

In the above technology, since the constraint conditions that restrict the permissible range of at least one of the mechanical behavior and the composition ratio of the multi-component material are defined, the material design of the material composed of multiple components is facilitated, and the composition ratio of the material is designed. It is said that the range or desired range of mechanical behavior can be preset. A constraint on the composition ratio of materials is, for example, the mass of at least one constituent material of the multicomponent material.
However, multi-component materials are generally selected from an extremely large number of raw materials such as dozens of rubber materials, dozens of fillers including filler materials, dozens of additives including oils, etc. Therefore, even if the above constraint conditions are imposed, it is extremely difficult to extract and obtain the composition ratio of the multi-component material that gives the optimum value of the target mechanical behavior from an extremely large number of raw materials. Moreover, in a transformation system using a neural network, depending on the learning data used for machine learning, there are parts where the accuracy of the output of mechanical behavior is poor, so high-precision optimization that corresponds to actual mechanical behavior is often not possible.

Therefore, when searching for a combination of raw materials for a vulcanized rubber composition that realizes the target value of the characteristic amount that characterizes the vulcanized rubber composition, the present invention efficiently and accurately selects from an extremely large number of raw materials. To provide a rubber material designing method, a rubber material designing device, and a program capable of extracting a compounding combination of raw materials having a high

In one aspect of the present invention, the combination of raw materials in the unvulcanized rubber composition is calculated by a computer in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition. It is a rubber material design method to calculate. The unvulcanized rubber composition is obtained by combining raw materials selected from a plurality of preset groups of raw materials.
The rubber material design method is
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A step of causing a prediction module in a computer to machine-learn the feature amount for the combination of the ingredients, using learning data that uses the combination of ingredients as input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization step in which the optimization module of the computer extracts formulation combinations;
In the optimization step, the optimization module imposes a constraint condition that limits the number of the raw materials used as the design variables, creates a combination of the raw materials used as the design variables, and By inputting to the prediction module, the output value of the feature amount for the design variable is calculated, and the combination of the combination of the raw materials input as the design variable to the prediction module and the output value of the feature amount for the design variable is used to extract the formulation combination that achieves the target value.

The optimization module is set as the constraint according to the maximum number of raw materials used in each of the combinations of raw materials used as the input data for learning. It is preferable to limit the number of the raw materials used as the design variables with the number as the upper limit.

Another aspect of the present invention also provides a combination of raw materials in the unvulcanized rubber composition, in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition, This is a rubber material design method that is calculated by a computer. The unvulcanized rubber composition is obtained by combining raw materials selected from a plurality of preset groups of raw materials.
The rubber material design method is
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A step of causing a prediction module in a computer to machine-learn the feature amount for the combination of the ingredients, using learning data that uses the combination of ingredients as input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization step in which the optimization module of the computer extracts formulation combinations;
In the optimization step, the optimization module sets a constraint that does not create a combination of the two raw materials set in the group, or the two raw materials set in the group are always set. By imposing a constraint condition to create a combination as follows, creating a combination of the raw material composition as the design variable and inputting it to the prediction module, the output value of the feature amount for the design variable is calculated. Then, by using the combinations of the raw material mixtures input as the design variables to the prediction module and the output values of the feature amounts for the design variables, the mixture combinations that realize the target values are extracted.

In the constraint condition not to create a combination of the two raw materials, two raw materials that do not have a combination among the combination of the raw materials used as the input data for learning are not to be combined. is preferred.

In the constraint condition for creating a combination so that the two raw materials always form a set, a combination is created for the two raw materials that always form a set in the combination of the ingredients used as the input data for learning. It is preferable that the set is set to:

The group of raw materials includes at least a group of rubber raw materials, a group of fillers, and a group of vulcanizing aids,
Preferably, said constraint is imposed within said group.

The raw materials include at least a group of rubber raw materials, a group of fillers, and a group of vulcanizing aids;
Preferably, said constraint is imposed between said groups.

Preferably, said optimization step uses an evolutionary algorithm to extract said formulation combinations that achieve said target value.

Preferably, said optimization step uses a genetic algorithm to extract said formulation combinations that achieve said target values.

A plurality of objective functions are set,
The optimization module further comprises the step of visualizing and displaying on a screen the relationship between the combination of the formulations adopted as the design variables obtained by the optimization step and the plurality of objective functions. is preferred.

Another aspect of the present invention is, in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition, the combination of raw materials in the unvulcanized rubber composition, It is a program that makes a computer calculate. The unvulcanized rubber composition is obtained by combining raw materials selected from a plurality of preset groups of raw materials.
The program is
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material a step of causing a prediction module formed in the computer by starting the program to perform machine learning of the feature amount for the combination of the raw materials using learning data that uses the combination of the ingredients as input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization procedure in which an optimization module formed in the computer upon activation of the program extracts the combination of formulations;
In the optimization procedure, the optimization module imposes a constraint condition that limits the number of the raw materials used as the design variables, creates a combination of the raw materials used as the design variables, and makes the prediction By inputting to the module, the output value of the feature amount for the design variable is calculated, and the combination of the raw material composition input as the design variable to the prediction module and the output value of the feature amount for the design variable are calculated. is used to extract the formulation combination that achieves the target value.

Another aspect of the present invention is, in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition, the combination of raw materials in the unvulcanized rubber composition, It is a program that makes a computer calculate. The unvulcanized rubber composition is obtained by combining raw materials selected from a plurality of preset groups of raw materials.
The program is
A feature quantity that characterizes a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition that combines a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw materials a step of causing a prediction module formed in the computer to machine-learn the feature amount for the combination of the ingredients by starting the program, using learning data in which the combination of ingredients is input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization procedure in which an optimization module formed in the computer extracts the combination of formulations by activating the program;
In the optimization procedure, the optimization module has a constraint condition that does not create a combination of the two set raw materials in the group, or the two set raw materials in the group are always set By imposing a constraint condition to create a combination so that is calculated, and the combination of ingredients that achieves the target value is extracted by using the combination of ingredients input as the design variables to the prediction module and the output value of the feature amount for the design variables.

Another aspect of the present invention is to calculate the combination of raw materials in the unvulcanized rubber composition in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition. It is a rubber material design device that The unvulcanized rubber composition is obtained by combining raw materials selected from a plurality of preset groups of raw materials.
The rubber material design device is
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A prediction unit that machine-learns the feature amount for the combination of the raw materials using learning data that uses the combination of the ingredients as input data for learning;
Using the machine-learned prediction unit, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization unit that extracts a combination of formulations,
The optimization unit imposes a constraint condition that limits the number of the raw materials used as the design variables, creates a combination of the raw materials used as the design variables, and inputs it to the prediction unit, calculating the output value of the feature amount for the design variable, and calculating the target value using the combination of the composition of the raw materials input as the design variable to the prediction unit and the output value of the feature amount for the design variable; Extract the combination of formulations that will be realized.

Another aspect of the present invention is to calculate the combination of raw materials in the unvulcanized rubber composition in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition. It is a rubber material design device that The unvulcanized rubber composition is obtained by combining raw materials selected from a plurality of preset groups of raw materials.
The rubber material design device is
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A prediction unit that machine- learns the feature amount for the combination of the raw materials using learning data that uses the combination of the ingredients as input data for learning;
Using the machine-learned prediction unit, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization unit that extracts a combination of formulations,
The optimization unit is a constraint condition that does not create a combination of two raw materials set in the group, or a constraint that creates a combination so that two raw materials set in the group are always set. By imposing a condition to create a combination of the raw material mixtures as the design variables and inputting them to the prediction unit, the output values of the feature amounts for the design variables are calculated, and the prediction unit sends the Using the combination of raw material mixtures input as design variables and the output values of the feature amounts for the design variables, the combination of mixtures that achieves the target value is extracted.

According to the rubber material design method, the rubber material design device, and the program described above, a combination of raw materials that realizes the target value of the feature amount that characterizes the vulcanized rubber composition can be efficiently selected from among an extremely large number of raw materials. It can be extracted with high accuracy.

It is a figure which shows the example of the flow of the rubber material design method of one Embodiment. It is a figure showing an example of composition of a rubber material design device which carries out a rubber material design method of one embodiment. FIG. 4 is a diagram showing an example of a detailed configuration of an optimization module of the rubber material design device of one embodiment; (a) is a diagram for explaining raw materials divided into groups of rubber materials, fillers, resin materials, and vulcanizing auxiliaries, and (b) is input data for learning in the raw materials shown in FIG. is a diagram for explaining the minimum number and maximum number of combinations used for each group, and (c) explains an example of correcting the combination of raw material mixtures used for optimum calculation by constraint conditions It is a diagram. FIG. 10 is a diagram showing an example of the flow of optimization using a genetic algorithm; (a) to (c) are diagrams showing examples of self-organizing maps of feature values that are objective functions; FIG. 4 is a diagram showing an example of a map;

A rubber material designing method, a rubber material designing device, and a program according to one embodiment will be described in detail below.

(Overview of rubber material design method)
FIG. 1 is a diagram showing an example of the flow of a rubber material design method according to one embodiment. In the example shown in FIG. 1, the compounding combination of raw materials before vulcanization set by trial and error in the past in order to obtain new physical properties, and the physical property data of the vulcanized rubber composition after vulcanization. Several 100 to several 1000 sets of accumulated data are prepared, which are sets of characteristic amounts of the rubber composition. Feature amounts in accumulated data are not limited to physical property data. For example, raw material cost data may be used.
Using this accumulated data as learning data, a prediction module formed in a computer is subjected to machine learning of feature amounts for combinations of ingredients.
Next, using a machine-learning prediction module, multiple combinations are created using the combination of raw material mixtures as design variables so that the feature value will be the target value, and the feature value at that time will be the target value. , to explore combinations of raw material formulations.
At this time, constraint conditions are imposed on the combination of raw material mixtures created as design variables. This constraint is a condition that limits the number of raw materials to be adopted as a design variable, and does not create a combination of two raw materials set in the raw material group, or sets out of the raw material group This is a condition for creating a combination so that two raw materials always form a set.

As shown in FIG. 1, characteristic amounts for each of a plurality of vulcanized rubber compositions produced by processing unvulcanized rubber compositions, and blending of raw materials in the corresponding unvulcanized rubber compositions at this time and are prepared as learning data (step S10). The unvulcanized rubber composition is a combination of multiple ingredients used in the vulcanized rubber composition.
Next, using the feature amount as output data for learning and the corresponding combination of raw material mixtures as input data for learning, the feature amount for the combination of raw material mixtures is machine-learned by the prediction module in the computer (step S12).

Next, using a machine-learned prediction module, in order to extract a combination of raw materials that achieves the target value of the feature amount (perform an optimization operation), the computer causes the prediction module to predict the feature amount. Various combinations of raw material formulations are created as design variables, but constraints are imposed on the creation of combinations of various raw material formulations that will be design variables at this time. For this purpose, constraints are created prior to the optimization operation by the optimization module (step S14).
The optimization module then creates various combinations of raw material formulations according to the above constraints (step S16). For example, after randomly creating combinations of raw materials without imposing the above constraints, combinations that do not satisfy the constraints when the above constraints are imposed are excluded, or combinations that do not satisfy the constraints are corrected. to create a combination of a predetermined number of ingredients. Design of experiments and Latin hypercube methods can also be used, depending on the method of optimization calculations, to create combinations of raw material formulations.
The optimization module acquires the predicted value (output value) of the feature amount by the prediction module by causing the prediction module to predict the feature amount using the created combination of raw materials (step S18).

Next, the optimization module performs an optimization operation using the combinations of raw material mixtures created as design variables and the predicted values of the corresponding feature amounts (step S20). The optimization operation preferably utilizes an evolutionary algorithm. Evolutionary algorithms include Genetic Algorithm, Differential Evolution, Particle Swarm Optimization, Ant Colony Optimization and others.
It is also preferable to use the experimental design method or the Latin hypercube method in combination with the combination of raw material formulations and the optimization calculation. In this case, since the combination of raw materials is determined using the response surface method, it is preferable to create the combination so as to exhaustively cover the space of the design variables.
Next, the optimization module extracts the optimum combination of raw materials that achieves the target value of the feature quantity (step S22).

According to one embodiment, the constraint conditions created in step S14 and imposed on the combination of mixtures in step S16 are constraint conditions that limit the number of raw materials employed as design variables. In this case, a number set according to the maximum number of raw materials used in each combination of raw materials used as input data for learning, for example, the maximum number is multiplied by a count of 0.8 to 1.2 It is preferable to limit the number of raw materials used as design variables, with the number set as the upper limit. In particular, it is preferable to set the upper limit to the above maximum number. Furthermore, the constraint conditions include a number set according to the minimum number of raw materials used in each combination of raw materials used as input data for learning, for example, 0.8 to 1.2 for the minimum number It is preferable to make the lower limit the number obtained by

According to one embodiment, the constraint is a constraint that does not create a combination of the two set raw materials, or a constraint that creates a combination so that the two set raw materials are always a set. . For example, in some cases, it is practically difficult to combine two raw materials because the raw materials cannot be mixed together. Constraints are provided so that such combinations that cannot be realistically realized are excluded from the combination of formulations used as design variables. Two raw materials that do not create such a combination can be set in advance by an instruction from the operator. Further, according to one embodiment, it is also preferable to set two raw materials for which there is no combination among the combination of raw materials used as input data for learning, for which no combination is to be created. It is also possible to find and set two uncombined raw materials from a huge amount of accumulated data used as learning data. Raw materials that are not combined in the vast amount of accumulated data are often not combined for some reason. For this reason, a constraint condition is set on the assumption that raw materials that are not combined in the vast amount of accumulated data should not be combined.

In addition, there are cases where it is preferable to always use two raw materials in combination, such as using two raw materials together being advantageous in terms of processing. In consideration of such a case, a constraint condition is provided to create a combination of mixtures so that the set two raw materials always form a set. Such two raw materials that are always to be combined can be set in advance by an instruction from the operator. In addition, according to one embodiment, two raw materials that are always combined as a set in the combination of raw material mixtures used as input data for learning are regarded as objects that are always set. It is also preferable to Two raw materials that are always combined as a set can be found and set from a huge amount of accumulated data used as learning data. Raw materials that are always combined as a set in the vast amount of accumulated data are often combined for a reason. For this reason, raw materials that are always combined as a set in the vast amount of accumulated data are preferably subject to combination, and a constraint condition is provided. Therefore, under the constraint condition that a combination is created so that two raw materials always form a set, the set for creating a combination is always a set among the combinations of raw material mixtures used as input data for learning. Target what exists.

Under these constraints, a combination of raw materials that serve as design variables is created. However, it can be extracted efficiently and accurately.

(Specific description of rubber material design method and rubber material design device)
FIG. 2 is a diagram showing an example of the configuration of a rubber material designing device that implements the rubber material designing method of one embodiment.
The rubber material design device 10 shown in FIG. 2 is a computer having a CPU 12, a ROM (Read Only Memory) 14, a RAM (Random Access Memory) 16, and an input/output unit 18. The input/output unit 18 is connected to an input operation system 30 including a mouse and keyboard and a display 32 .
The prediction module 20 and the optimization module 22 are formed by calling the program stored in the ROM 14 and activating the computer, which is the rubber material designing device 10 . The prediction module 20 and the optimization module 22 correspond to the prediction unit and the optimization unit in the rubber material design device 10, respectively.

The CPU 12 calls up a huge amount of accumulated data, which is a set of the combination of raw material mixtures recorded in the RAM 16 and the feature values related to the actual vulcanized rubber composition in the corresponding combination, and uses them as learning input data and learning data, respectively. prepared to be supplied to the prediction module 20 as output data for use.
The prediction module 20 is configured to machine-learn the feature amount for the combination of raw material mixtures using the prepared input data for learning and output data for learning. The prediction module 20 performs machine learning using a preset prediction model. Prediction models include models using neural networks represented by well-known deep learning, models using the well-known random forest method for “classification” or “regression” using multiple decision trees, and LASSO regression. Includes models using A nonlinear function using a polynomial, kriging, or RBF (Radial Base Function) can also be used as a prediction model.

FIG. 3 is a diagram showing an example of the detailed configuration of the optimization module 22. As shown in FIG. The optimization module 22 has a constraint condition setting unit 22a, a compound combination creation/feature quantity acquisition unit 22b, and an optimization calculation unit 22c.
The constraint condition setting unit 22a is configured to set conditions that constrain raw materials to be combined in order to create a plurality of combination combinations of raw materials to be created for optimization calculation. The raw materials are all the raw materials used in the learning input data. FIG. 4(a) is a diagram illustrating raw materials classified into groups of rubber materials, fillers, resin materials, and vulcanizing aids. As shown in FIG. 4(a), the rubber material includes rubber materials 1 to N1. Here, the rubber materials 1 to N1 refer to those distinguished by the brand name of the rubber material supplied from the rubber material maker that is actually used. In other words, raw materials can be identified like product B manufactured by A company. Such rubber material products are blended with a plurality of types of rubber compositions. Similarly, fillers, resin materials, and vulcanizing auxiliaries, like rubber materials, are distinguished by the trade names of the raw materials supplied by the manufacturers of the materials actually used. The filler includes fillers 1 to N2, the resin material includes resin materials 1 to N3, and the vulcanizing aid includes vulcanizing aids 1 to N4. In addition, although not shown, oil, anti-aging agents, etc. are also included. Therefore, the total number of raw materials such as rubber materials, fillers, resin materials, and vulcanizing aids is extremely large.

FIG. 4(b) is a diagram for explaining the minimum number and maximum number of combinations used as learning input data for each group in the raw material shown in FIG. 4(a). In the rubber material group, n1min is the minimum number of rubber material elements and n1max is the maximum number of rubber material elements used in combination of compounds used in input data for learning. Similarly, the minimum number of filler elements is n2min, the maximum number is n2max, the minimum number of resin elements is n3min, the maximum number is n3max, the minimum number of vulcanization aid elements is n4min, and the maximum number is The number is n4max.

In such feedstocks, one of the constraints is the requirement to limit the number of feedstock quantities used for the formulation combination used as a design variable. The number of raw materials in this constraint can be set by an operator's input from the input operation system 30, or can be set automatically from learning data used for machine learning in the prediction module.

When automatically set from the learning data, the constraint setting unit 22a determines the upper limit of the number of raw material elements used for the combination of ingredients according to the maximum number of raw material elements in each group used in the learning input data. . For example, in the case of rubber material groups, the upper limit is a value obtained by multiplying the maximum number n1max by a predetermined constant (for example, 0.8 to 1.2 times). For example, the upper limit of the number of rubber materials used in combination is set to the maximum number n1max. By setting the upper limit of the number of rubber materials used in the combination according to the maximum number for the optimization calculation in this way, in the optimized combination of raw materials, the maximum number n1max is extremely large, and the actual number Therefore, it is possible to prevent the optimum combination of rubber raw materials, which are difficult to combine practically, from being determined. It is also preferable to set the lower limit of the number of rubber materials used in combination to the minimum number n1min.

The upper limit of the number of fillers, the upper limit of the number of resin materials, and the upper limit of the number of vulcanizing aids used in the combination are set to the maximum number n2max, the maximum number n3max, and the maximum number n4max, similarly to the upper limit of the rubber material. can be set accordingly. In this case, the respective upper limits may be the maximum number n2max, the maximum number n3max, and the maximum number n4max.

Also, the constraint is a constraint that does not create a combination of two raw materials, or a constraint that creates a combination so that two raw materials set in the group always form a set. The specification of raw materials in these constraints can be set by an operator's input from the input operation system 30, or the constraint setting unit 22a automatically sets from learning data used for machine learning in the prediction module. be able to.
According to one embodiment, the constraint setting unit 22a sets two raw materials for which there is no combination among the combination of ingredients of the input data for learning used for machine learning of the prediction module as the target of the constraint. automatically set as As a result, when a combination of raw materials is created by the combination combination creation/feature acquisition unit 22b, a combination of two raw materials is not created.
In addition, according to one embodiment, the constraint condition setting unit 22a selects two or more raw materials that are always combined as a set among the combination of raw materials of the input data for learning used for machine learning of the prediction module. , two raw materials are automatically set as objects to be always set.
As a result, when a combination of raw materials is created by the combination combination creation/feature value acquisition unit 22b, the combination is created so that the set two raw materials are always a set.

The mixture combination creation/feature amount acquisition unit 22b uses the constraint conditions set by the constraint condition setting unit 22a to create a plurality of combinations of raw material mixtures used for the optimum calculation, and supplies these combinations to the prediction module. , to predict the features. As a result, the combination combination creation/feature quantity acquisition unit 22b acquires the feature quantity predicted by the prediction module.

FIG. 4(c) is a diagram for explaining an example of correction by the combination combination creation/feature amount acquisition unit 22b according to constraint conditions when creating a combination of raw material combinations used for optimum calculation.
For example, when the raw materials subject to the constraint condition for creating a combination so as to always be a set are rubber material 1, rubber material 2, and rubber raw material 3, the raw material blending created by the creation/feature amount acquisition unit 22b includes the rubber material 1, the rubber material 2 and the rubber material 3 are forcibly added to the rubber material 1 as raw materials used in the compounding combination.
In addition, if the raw materials subject to the constraint condition that does not create a combination of two raw materials are the rubber material 1 and the filler 2, in the combination of the raw materials used for the optimum calculation, the rubber material 1 and the filler 2 is included, the filler 2 is changed to filler 1 or filler 3 or filler 4. In this case, instead of changing the filler 2, the rubber material 1 can be changed to the rubber materials 2, 3 and the like.

In the combination of ingredients used for optimum calculation, which is created by the ingredient combination creation/feature amount acquisition unit 22b, the amount of ingredients is set corresponding to the set ingredients. The blending amount is preferably set within the range of the maximum and minimum values of the blending amount of the same raw material used in the input data for learning. The method of setting the compounding amount differs depending on the method of optimization calculation. In the design of experiments method and the Latin hypercube method, a preset blending amount level is prepared and the blending amount is given. In the case of Genetic Algorithm, the blending amount is given randomly. Note that in the case of the Genetic Algorithm, prediction is repeatedly performed by the prediction module each time the generation changes, such as the first generation, the second generation, the third generation, and so on.

The optimum calculation unit 22c uses the combination of raw material mixtures created by the mixture combination creation/feature amount acquisition unit 22b and the predicted value of the feature amount to obtain a combination of raw material mixtures that achieves the target value of the feature amount. Specifically, the compounding amount of each raw material is extracted.
For example, when using the design of experiments method or the Latin hypercube method, the number of combinations of raw material mixtures is increased, the data of the mixture combinations are comprehensively distributed in the space of the design variables, and the response surface function is created, and the data closest to the target value of the feature quantity is extracted by interpolation or the like, thereby extracting the optimum blending amount.

FIG. 5 is a diagram showing an example of a flow when the optimum calculation unit 22c performs optimization using a genetic algorithm.
First, before the optimization calculation by the optimum calculation unit 22c, the mixture combination creation/feature amount acquisition unit 22b creates a mixture combination of raw materials (step S100). In the creation of combinations of raw material formulations, combinations of formulations are created at random, or combinations are created by the Latin hypercube method.

Next, the mixture combination creation/feature amount acquisition unit 22b determines whether or not the created combination of raw material mixtures satisfies the constraint conditions set by the constraint condition setting unit 22a. By correcting the combination of raw material mixtures, a preset number of combinations of raw material mixtures that satisfy the constraint conditions are created (step S102). A combination of raw materials that satisfies the constraint conditions obtained in step S102 is a first-generation combination.

Next, the mixture combination creation/feature amount acquisition unit 22b provides the combination of raw material mixtures that satisfy the constraint conditions to the prediction module 20, and causes the prediction module 20 to calculate the predicted value of the feature amount. As a result, the mixture combination creation/feature amount acquisition unit 22b acquires the predicted value of the feature amount corresponding to the combination of raw material mixtures (step S104).

The optimization calculation unit 22c determines whether or not there is a combination of mixtures such that the obtained predicted value of the feature quantity realizes the target value of the feature quantity, and determines whether or not the optimization calculation ends. is determined (step S106). In this determination, if it is determined that there is a mixture combination that achieves the target value of the feature amount, and it is determined that the optimization operation may be terminated, the optimization operation is terminated and the target value of the feature amount is determined. The combination of raw materials to be realized is displayed on the display 32 as the optimum combination.

In the above determination, if there is no mixture combination that realizes the target value of the feature amount and it is determined to continue the optimization calculation, the optimization calculation unit 22c determines the Pareto rank of the created mixture combination of raw materials. Calculate (step S108). In the illustrated example, there are a plurality of feature amounts. The Pareto rank is a ranking of how close predicted values corresponding to a plurality of objective functions are to target values of a plurality of feature quantities, which are objective functions. Even in the case of the same rank, it is possible to determine superiority or inferiority according to the size of the distance in space between the target value and the predicted value. Instead of the Pareto rank, a plurality of feature amounts, which are objective functions, may be weighted and summed to form a single feature amount, and the combined objective function of the feature amount may be used to rank combinations of ingredients. In addition, when there is one feature amount, ranking can be performed according to the magnitude of the difference between the predicted value of the feature amount and the target value of the feature amount for each combination of ingredients.

Next, the optimization calculation unit 22c divides the combination into, for example, a higher rank (closer to the target value) or a lower rank (farther from the target value) according to the Pareto rank, and out of the combination of raw materials positioned at the higher rank, Select two combinations, exchange information on the combination of the two formulations (exchange part of the information) to create at least one new combination for the two selected combinations Create (step S110).

Next, the optimization calculation unit 22c determines whether or not to mutate the new compound combination obtained by crossing (step S112). Mutations are, for example, randomly generated. If mutation is not to be performed, the new combination obtained by crossing is maintained (step S114), and the process proceeds to step S118. On the other hand, in the case of mutation, part of the compounding amount of the new compounding combination obtained by crossing is changed. Which raw material is to be changed in the blending amount can be determined at random. As a result, the optimization calculation unit 22c corrects the new compounding combination obtained by the crossing (step S116).

Furthermore, the optimization calculation unit 22c determines whether the combination of mixtures maintained in step S114 or the combination of mixtures corrected in step S116 satisfies the above-described constraint conditions. The modified compound combination is further modified to satisfy the constraint (step S118).
Thus, a second generation formulation combination is established. The number of second generation formula combinations remains the same as the first generation formula combinations.

In this way, in step S106, a blending combination is found in which the predicted value of the feature amount in each generation realizes the target value of the feature amount. S118 is repeated.

Finally, the optimization calculation unit 22c preferably visualizes and displays on the display 32 the relationship between the combinations of formulations adopted as the design variables and the feature amounts that are the plurality of objective functions. FIGS. 6(a) to 6(c) are diagrams showing examples of self-organizing maps of feature quantities, which are objective functions, and FIGS. FIG. 3 is a diagram showing an example of a self-organizing map for . FIGS. 6A to 6C are color-coded according to the magnitude of each feature value. 6(d) to (g) are color-coded according to the amount of each raw material. By focusing on the same position within each rectangular area, it is possible to know the value of each feature amount and the compounding amount that realizes this feature amount. In this way, it is possible to know the relationship between the value of the feature value, which is the objective function, and the blending amount of the raw material, which is the design variable.
The example shown in FIG. 6 is a self-organizing map, but instead of the self-organizing map, a scatter diagram is used to compare combinations of mixtures adopted as design variables and feature values, which are multiple objective functions. It is also preferable to visualize the relationships.

Thus, in the optimization module 22, when creating combinations of raw materials to be used for optimization, constraint conditions are imposed to create combinations of raw materials. At this time, the constraint is a constraint that limits the number of raw materials used as a design variable, a constraint that does not create a combination of the two set raw materials, or a constraint that the two set raw materials are always set. Contains constraints that create combinations such that . Therefore, it is possible to limit the combination of raw materials as compared with the conventional method. Therefore, it is possible to efficiently and accurately extract a combination of raw materials that achieves the target value of the feature amount that characterizes the vulcanized rubber composition, even from a large number of raw materials.

The optimization module 22 uses, as a constraint, a number set according to the maximum number of raw materials used in each of the raw material combinations used as learning input data as the upper limit. , it is preferable to limit the number of said raw materials used as design variables.
In addition, in the constraint condition that the combination of two raw materials is not created, it is preferable that the two raw materials that do not have a combination among the combination of raw materials used as input data for learning are not to be combined. . In addition, in the constraint condition that a combination is created so that two raw materials always form a set, two raw materials that always form a set in the combination of ingredients used as input data for learning are combined to create a combination. A set is also preferable. In stored data used as input data for learning, combinations of raw materials are often restricted because it is not preferable to use raw materials as a set or it is preferable to use raw materials as a set. Creating a combination of raw materials without considering such circumstances is not preferable in terms of designing a realistic rubber material.

The group of raw materials includes at least a group of rubber raw materials, a group of fillers, and a group of vulcanizing aids. Constraints, according to one embodiment, can extract combinations of raw materials more efficiently and more accurately by imposing restrictions within groups.
Further, according to one embodiment, it is also preferable that the constraint conditions are imposed between the groups in consideration of compatibility between the rubber material and the filler. That is, the above constraint may be imposed on raw materials belonging to different groups.

As described above, when the rubber material design method is executed by a computer, it is executed by calling and starting a program. In this case, run the following program.
In order to achieve the target value of the feature quantity that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition that is blended by combining raw materials from a group of preset raw materials, the program It is a program that allows a computer to calculate the combination of raw materials.
This program
The feature amount of each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw material blends used in the vulcanized rubber composition is used as output data for learning, and the blend of raw materials is used. A procedure for causing the prediction module 20 formed in the computer to machine-learn the feature amount by activating the program using learning data that uses a combination of as input data for learning,
Using the machine learning prediction module 20, the feature amount of the vulcanized rubber composition is used as the objective function, the combination of raw material blends is used as the design variable, and the combination of formulations that realizes the target value set for the objective function is programmed. and an optimization procedure extracted by an optimization module 22 configured in the computer upon activation.
In the optimization procedure, the optimization module 22 imposes constraints, creates combinations of raw material mixtures that serve as design variables, and inputs them to the prediction module 20 to obtain output values of feature quantities for the design variables. is calculated, and a combination of mixtures that achieves the target value is extracted using the combination of raw material mixtures input as design variables to the prediction module 20 and the output values of the feature amounts for the design variables.
Constraints are constraints that limit the number of raw materials used as design variables. The constraint is a constraint that does not create a combination of the two set raw materials, or a constraint that creates a combination so that the two set raw materials are always a set.

As described above, the rubber material designing method, the rubber material designing device, and the program of the present invention are not limited to the above embodiments, and various improvements and modifications may be made without departing from the gist of the present invention. be.

10 rubber material design device 12 CPU
14 ROM (Read Only Memory)
16 RAM (Random Access Memory)
18 Input/Output Unit 20 Prediction Module 22 Optimization Module 22a Constraint Condition Setting Unit 22b Mixture Combination Creation/Feature Amount Acquisition Unit 22c Optimization Operation Unit 30 Input Operation System 32 Display

Claims (15)

A rubber material design method that allows a computer to calculate the combination of raw materials in the unvulcanized rubber composition in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition. There is
The unvulcanized rubber composition is a combination of raw materials selected from a plurality of preset groups of raw materials,
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A step of causing a prediction module in a computer to machine-learn the feature amount for the combination of the ingredients, using learning data that uses the combination of ingredients as input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization step in which the optimization module of the computer extracts formulation combinations;
In the optimization step, the optimization module imposes a constraint condition that limits the number of the raw materials used as the design variables, creates a combination of the raw materials used as the design variables, and By inputting to the prediction module, the output value of the feature amount for the design variable is calculated, and the combination of the combination of the raw materials input as the design variable to the prediction module and the output value of the feature amount for the design variable to extract the combination of formulations that achieves the target value ,
The optimization module is set as the constraint according to the maximum number of raw materials used in each of the combinations of raw materials used as the input data for learning. A method of designing a rubber material , wherein the number of raw materials used as the design variable is limited with a number as an upper limit . A rubber material design method that allows a computer to calculate the combination of raw materials in the unvulcanized rubber composition in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition. There is
The unvulcanized rubber composition is a combination of raw materials selected from a plurality of preset groups of raw materials,
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A step of causing a prediction module in a computer to machine-learn the feature amount for the combination of the ingredients, using learning data that uses the combination of ingredients as input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization step in which the optimization module of the computer extracts formulation combinations;
In the optimization step, the optimization module sets a constraint that does not create a combination of the two raw materials set in the group, or the two raw materials set in the group are always set. By imposing a constraint condition to create a combination as follows, creating a combination of the raw material composition as the design variable and inputting it to the prediction module, the output value of the feature amount for the design variable is calculated. and extracting the composition combination that achieves the target value by using the composition combination of the raw materials input as the design variables to the prediction module and the output value of the feature amount for the design variable. A rubber material design method characterized by: In the constraint condition that the combination of the two raw materials is not created, the combination of two raw materials that does not exist in the combination of the raw materials used as the input data for learning is not created. Item 2. The rubber material design method according to item 2. In the constraint condition for creating a combination so that the two raw materials always form a set, a combination is created for the two raw materials that always form a set in the combination of the ingredients used as the input data for learning. 3. The method of designing a rubber material according to claim 2 , wherein the set is set to be the same. The group of raw materials includes at least a group of rubber raw materials, a group of fillers, and a group of vulcanizing aids,
The rubber material design method according to any one of claims 1 to 4 , wherein said constraint is imposed within said group. The raw materials include at least a group of rubber raw materials, a group of fillers, and a group of vulcanizing aids;
The rubber material design method according to any one of claims 1 to 5 , wherein said constraint is imposed between said groups. The rubber material design method according to any one of claims 1 to 6 , wherein said optimization step uses an evolutionary algorithm to extract said compounding combination that achieves said target value. 8. The method of designing a rubber material according to claim 7 , wherein said optimization step uses a genetic algorithm to extract said compounding combination that achieves said target value. A plurality of objective functions are set,
The optimization module further comprises the step of visualizing and displaying on a screen the relationship between the combination of the formulations adopted as the design variables obtained by the optimization step and the plurality of objective functions. Item 9. The rubber material design method according to any one of Items 1 to 8 . A rubber material design method that allows a computer to calculate the combination of raw materials in the unvulcanized rubber composition in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition. There is
The unvulcanized rubber composition is a combination of raw materials selected from a plurality of preset groups of raw materials,
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A step of causing a prediction module in a computer to machine-learn the feature amount for the combination of the ingredients, using learning data that uses the combination of ingredients as input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization step in which the optimization module of the computer extracts formulation combinations;
In the optimization step, the optimization module imposes a constraint condition that limits the number of the raw materials used as the design variables, creates a combination of the raw materials used as the design variables, and By inputting to the prediction module, the output value of the feature amount for the design variable is calculated, and the combination of the combination of the raw materials input as the design variable to the prediction module and the output value of the feature amount for the design variable to extract the combination of formulations that achieves the target value,
The group of raw materials includes at least a group of rubber raw materials, a group of fillers, and a group of vulcanizing aids,
The rubber material design method, wherein the constraint is imposed within the group. A rubber material design method that allows a computer to calculate the combination of raw materials in the unvulcanized rubber composition in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition. There is
The unvulcanized rubber composition is a combination of raw materials selected from a plurality of preset groups of raw materials,
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A step of causing a prediction module in a computer to machine-learn the feature amount for the combination of the ingredients, using learning data that uses the combination of ingredients as input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization step in which the optimization module of the computer extracts formulation combinations;
In the optimization step, the optimization module imposes a constraint condition that limits the number of the raw materials used as the design variables, creates a combination of the raw materials used as the design variables, and By inputting to the prediction module, the output value of the feature amount for the design variable is calculated, and the combination of the combination of the raw materials input as the design variable to the prediction module and the output value of the feature amount for the design variable to extract the combination of formulations that achieves the target value,
The raw materials include at least a group of rubber raw materials, a group of fillers, and a group of vulcanizing aids;
The rubber material design method, wherein the constraint is imposed between the groups. A program that causes a computer to calculate a combination of raw materials in the unvulcanized rubber composition in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition,
The unvulcanized rubber composition is a combination of raw materials selected from a plurality of preset groups of raw materials,
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material a step of causing a prediction module formed in the computer by starting the program to perform machine learning of the feature amount for the combination of the raw materials using learning data that uses the combination of the ingredients as input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization procedure in which an optimization module formed in the computer upon activation of the program extracts the combination of formulations;
In the optimization procedure, the optimization module imposes a constraint condition that limits the number of the raw materials used as the design variables, creates a combination of the raw materials used as the design variables, and makes the prediction By inputting to the module, the output value of the feature amount for the design variable is calculated, and the combination of the raw material composition input as the design variable to the prediction module and the output value of the feature amount for the design variable are calculated. to extract the combination of formulations that achieves the target value ,
The optimization module is set as the constraint according to the maximum number of raw materials used in each of the combinations of raw materials used as the input data for learning. A program characterized by limiting the number of said raw materials used as said design variables with a number as an upper limit . A program that causes a computer to calculate a combination of raw materials in the unvulcanized rubber composition in order to achieve the target value of the feature amount that characterizes the vulcanized rubber composition produced from the unvulcanized rubber composition,
The unvulcanized rubber composition is a combination of raw materials selected from a plurality of preset groups of raw materials,
A feature quantity that characterizes a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition that combines a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw materials a step of causing a prediction module formed in the computer to machine-learn the feature amount for the combination of the ingredients by starting the program, using learning data in which the combination of ingredients is input data for learning;
Using the machine learning prediction module, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization procedure in which an optimization module formed in the computer extracts the combination of formulations by activating the program;
In the optimization procedure, the optimization module is a constraint condition that does not create a combination of the two raw materials set in the group, or the two raw materials set in the group are always set. By imposing a constraint condition to create a combination as follows, creating a combination of the raw material composition as the design variable and inputting it to the prediction module, the output value of the feature amount for the design variable is calculated. and extracting the composition combination that achieves the target value by using the composition combination of the raw materials input as the design variables to the prediction module and the output value of the feature amount for the design variable. Program characterized. A rubber material design device for calculating a combination of raw materials in the unvulcanized rubber composition in order to realize a target value of a feature amount that characterizes a vulcanized rubber composition produced from the unvulcanized rubber composition,
The unvulcanized rubber composition is a combination of raw materials selected from a plurality of preset groups of raw materials,
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A prediction unit that machine-learns the feature amount for the combination of the raw materials using learning data that uses the combination of the ingredients as input data for learning;
Using the machine-learned prediction unit, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization unit that extracts a combination of formulations,
The optimization unit imposes a constraint condition that limits the number of the raw materials used as the design variables, creates a combination of the raw materials used as the design variables, and inputs it to the prediction unit, calculating the output value of the feature amount for the design variable, and calculating the target value using the combination of the composition of the raw materials input as the design variable to the prediction unit and the output value of the feature amount for the design variable; Extracting the combination of the formulations to be realized ,
The optimization module is set as the constraint according to the maximum number of raw materials used in each of the combinations of raw materials used as the input data for learning. A rubber material designing apparatus characterized by limiting the number of said raw materials used as said design variables with a number as an upper limit . A rubber material design device for calculating a combination of raw materials in the unvulcanized rubber composition in order to realize a target value of a feature amount that characterizes a vulcanized rubber composition produced from the unvulcanized rubber composition,
The unvulcanized rubber composition is a combination of raw materials selected from a plurality of preset groups of raw materials,
The feature amount for each of a plurality of vulcanized rubber compositions produced by processing an unvulcanized rubber composition obtained by combining a plurality of raw materials used in the vulcanized rubber composition is used as learning output data, and the raw material A prediction unit that machine- learns the feature amount for the combination of the raw materials using learning data that uses the combination of the ingredients as input data for learning;
Using the machine-learned prediction unit, the feature amount of the vulcanized rubber composition is used as an objective function, and the combination of the raw material blends is used as a design variable to achieve the set target value of the objective function. an optimization unit that extracts a combination of formulations,
The optimization unit is a constraint condition that does not create a combination of two raw materials set in the group, or a constraint that creates a combination so that two raw materials set in the group are always set. By imposing a condition to create a combination of the raw material mixtures as the design variables and inputting them to the prediction unit, the output values of the feature amounts for the design variables are calculated, and the prediction unit sends the A rubber material designing device, characterized in that, by using a combination of raw material mixtures input as design variables and an output value of the feature amount for the design variables, a combination of the mixtures that realizes the target value is extracted. .

Images