WO2019088185A1 - Design assistance device and design assistance method - Google Patents

Abstract

To cite an example of the present invention, provided is a design assistance device for treating a product or an intermediate product created using two or more ingredients as a subject to be designed and assisting in the design of the subject to be designed. Said device comprises: a management means for at least managing as a subject to be managed ingredient composition information relating to either a composition or a composition ratio of ingredients; an input means for receiving an input of at least characteristic request information being requested as a characteristic of the subject to be designed, and a composition parameter for either the composition or the composition ratio of the subject to be designed, said parameter defining an allowable range of a value allowed as a target value for the composition or the composition ratio; a processing means for processing the ingredient composition information on the basis of the characteristic request information received by the input means, identifying a composition or a composition ratio of the subject to be designed, which satisfies a condition designated in the characteristic request information, and identifying, for the identified composition or composition ratio of the subject to be designed, a combination of the ingredients falling within the allowable range of the condition indicated by the composition parameter; and a display means for displaying information based on an output from the processing means. The processing means identifies a combination of conditions different from the condition used when identifying the combination of the ingredients, and causes the display means to display the identified different condition combination.

Description

Design support apparatus and design support method

The present invention relates to a design support apparatus and a design support method for supporting product design in the manufacture of chemical products, food products and the like.

The manufacture of chemicals, foods and the like requires accurate and rapid design of recipes for the manufacture of products with one or more characteristics required by the manufacturer and its customers. However, when the characteristics of the product are composed of a plurality of raw materials, the combination patterns are enormous, and it takes a lot of time to design.

On the other hand, in recent years, design support has been studied using simulations that make use of first-principles calculations and machine learning. However, it may take a lot of time for calculation if you try to do precise simulation.

In order to address this problem, Patent Document 1 (Japanese Patent Application Laid-Open No. 2016-200903) proposes that “a method of creating an approximate model of a structure includes a structure and a plurality of design variables that define materials constituting the structure; A plurality of characteristic values defining a structure and a material constituting the structure are obtained to obtain a first approximate model having a characteristic value as an objective function, which is created using a non-linear response relation. The first Pareto solution is extracted using the model, at least one of the upper limit value and the lower limit value is extracted in the first Pareto solution, and at least one value of the extracted upper limit value and the lower limit value is fixed and extracted. Set a new value of the design variable by changing the non-design variable, create a second approximate model using the new design variable, perform multi-objective optimization calculation, and extract a second Pareto solution " Bets have been disclosed (see solutions).

JP, 2016-200903, A

However, since the technique described in Patent Document 1 executes the search after inputting the conditions regarding all the objects and constraints in advance, there is also a solution that does not satisfy the desired characteristics if the constraints on the cost and raw materials other than the characteristics are excessive. There may be many output. That is, when searching for a predetermined solution, it is not taken into consideration that the solution may not be obtained if the constraint is not appropriately set.

The object of the present invention is made in view of the above, and it is an object of the present invention to provide a design support apparatus and method which make it easy to input constraints of a manufacturing recipe of a product having a predetermined characteristic.

In order to solve the above problems, one example of the design support apparatus of the present invention is a design support apparatus for designing a product or an intermediate product made using two or more raw materials and supporting the design of the design target. There are also management means for managing at least the raw material composition information on the composition or composition ratio of the raw material, the property request information required as the property of the design object, and the composition or composition ratio of the design object The raw material composition information is processed based on the input means for inputting the composition parameter which defines the allowable range of the allowable value as the value, and the characteristic request information inputted by the input means, and the condition specified by the characteristic request information is Identify the composition or composition ratio of the design object to be satisfied, and for the composition or composition ratio of the identified design object, the item specified in the composition parameter The processing means for specifying the combination of the raw materials belonging to the range, and the display means for displaying the information by the output of the processing means, the processing means being different from the conditions used when specifying the combination of the raw materials And a combination of different conditions specified is displayed on the display means.

According to the present invention, it is possible to provide a design support apparatus and method that make it easy to input constraint conditions of a production recipe of a product having predetermined characteristics.

It is a block diagram which shows the system configuration | structure in this embodiment, and a function structure. It is a figure which shows the hardware constitutions in this embodiment. It is a figure of the experimental recipe data in this embodiment. It is a figure of cost composition data in this embodiment. It is a figure of the experimental physical-property data in this embodiment. It is a figure of the query data in this embodiment. It is a figure of the raw material filter data in this embodiment. It is a figure of a composition discrepancy parameter in this embodiment. It is a figure of the search result physical-property data in this embodiment. It is a figure of the search result composition ratio data in this embodiment. It is a figure of the search result recipe data in this embodiment. It is a figure of the search result discrepancy data in this embodiment. It is a flowchart which shows the processing flow of experimental data registration in this embodiment. It is a flowchart which shows the processing flow of prediction model learning in this embodiment. It is a flowchart which shows the processing flow of the raw material combination search in this embodiment. It is a figure of the query registration screen in this embodiment. It is a figure of the physical-property display screen in this embodiment. It is a figure of the raw material combination display screen in this embodiment. It is an example of the display screen of the composition data corresponding to the raw material kind and quantity in this embodiment.

Hereinafter, representative embodiments for carrying out the present invention will be described with reference to the drawings as appropriate.

The description of the same or similar parts will not be repeated in principle unless particularly required. The same or similar parts will not be described even if the reference numerals described in the predetermined drawings are described in other drawings.

Further, in the following embodiments, when it is necessary for the sake of convenience, it will be described divided into a plurality of sections or embodiments, but unless specifically stated otherwise, they are not unrelated to each other, one is The other part or all of the variations, the details, the supplementary explanation, etc. are in a relation.

Further, in the following embodiments, when referring to the number of elements (including the number, numerical value, quantity, range, etc.), it is particularly pronounced and clearly limited to a specific number in principle. Except for the specific number, it is not limited to the specific number but may be more or less than the specific number.

Further, in the following embodiments, the constituent elements (including element steps and the like) are not necessarily essential except in the case where they are particularly clearly shown and where they are considered to be obviously essential in principle. Needless to say.

In the present embodiment, in order to support the design of a product, a plastic product or the like having desired characteristics in chemical product manufacture, for example, characteristics meeting characteristics required for manufacturing the product (characteristics meeting the required specifications). The outline of the design support device is described. Not only plastic but also chemical products such as rubber, food, medicine or medicine can be implemented. These are collectively called chemicals or just products.

In addition, the product is not limited to the finished product, but it is also possible to design an intermediate product that supports production of the finished product to be used, mixed or combined as part of the finished product.

The present invention is not limited to the above-described embodiment, and when a product having characteristics meeting the requirements implies a finished product as a final product, for example, a finished product is produced from raw material plastic. The present invention can also be applied to intermediate products (intermediate products) such as pellets and compounds obtained in the process.

In this case, a product or an intermediate product is to be designed. It explained as a product including such an intermediate product. In addition, it is possible to add, delete, and replace other configurations for part of the configurations of the embodiment.

The above-mentioned chemical products are food materials such as texture, taste, hardness, texture, shape, baking, etc. if they are foods, and if they are medicines or medicines, the amount of a plurality of raw materials in order to obtain predetermined characteristics Because it is necessary to combine, it requires very complicated calculation.

Therefore, in the conventional method of searching for a solution after inputting conditions on all the objects and constraints in advance, it is selected in view of the constraints on the cost and the raw materials among the recipes and manufacturing methods that can achieve the desired characteristics. There is a problem that the designer can not cope with the process actually performed. In addition, there are also cases where a solution that satisfies the condition can not be found if too many constraints are applied at first.

In the case of actual operation, often when the raw material itself becomes difficult to obtain, or when a new kind of thing is available, there is a problem that it is necessary to recreate the model used so far from scratch. Design support devices and methods considered have not been provided.

The processing of the design support apparatus in the present embodiment is divided into a basic data registration phase, a prediction model construction phase, and a search phase, and is sequentially processed. The flow of a series of processing will be described below for each phase.

In the basic data registration phase, basic data is data obtained when an experiment is performed to combine a raw material and generate a predetermined product (chemical product) in the past, and corresponds to a product having predetermined characteristics (1) Product Various basic data on physical properties of products (chemicals) such as raw materials combination of (chemicals), (2) cost of raw materials (unit cost), composition of raw materials, such as molecular weight, and (3) gloss and fluidity. Register in the database.

Next, in the prediction model construction phase, on the basis of the basic data registered in the database in the basic data registration phase (experimental data registration phase), a prediction model (simulator) for predicting physical properties from the composition ratio of raw materials is constructed.

The composition ratio includes chemical components such as elements and compounds constituting the substance, nutritional components such as vitamins, calcium, proteins and sugars, effects, effects and the like. Moreover, when a chemical reaction occurs due to heat treatment or the like, information before and after the reaction may be included.

In the search phase, first, query data representing physical property information desired by a user who is a designer of a product, and a parameter representing how much the request is allowed to deviate are received. Next, a search for the composition ratio of the product satisfying the physical properties of the product (chemical product) is performed using the prediction model.

Furthermore, a recipe (raw material combination) in which the composition ratio of the product falls within the predetermined discrepancy category and the cost (unit cost) of the product or production decreases is searched. Then, search result data (physical properties, composition ratio, combination of raw materials) is registered in the database. Not limited to the above unit cost, it is possible to search based on the time of product production, availability of raw materials, and the like. In the present specification, a search method using a unit cost will be representatively described.

A product falling within the category of discontinuation refers to a product that does not exactly match a predetermined property but that has similar characteristics to the predetermined property as a product. That is, it has characteristics different from predetermined characteristics but satisfies the characteristics as a product.

That is, the first condition used to specify the combination of materials of the product recipe in which the product satisfies the predetermined characteristics is input, the manufactured product satisfies the characteristics similar to the predetermined characteristics, and the first condition is To identify a second condition different from

At this time, a combination of conditions different from the condition used when specifying the raw material combination is specified, and the specified content is registered in the database. The search result (data registered in the database) is presented to the user (displayed on the display terminal of the user).

The process of the above search phase may actually be repeatedly performed halfway according to the interaction with the user.

<System configuration>
Next, the configuration of the design support apparatus 1 according to the present embodiment will be described with reference to FIG. FIG. 1 is a configuration diagram showing a system configuration and a functional configuration in the present embodiment.
In FIG. 1, the design support apparatus 1 according to the present embodiment includes at least a calculation server 11 that performs data management, prediction of physical properties, and a search for combinations of raw materials, and an operation terminal 12 that a user inputs and outputs data. The calculation server 11 includes a data registration unit 111, a prediction model construction unit 112, a search unit 113, and a data management unit 114.

The operation terminal 12 has an operation unit 121. The components of the design support apparatus 1 are mutually connected by a network 13 such as a LAN (Local Area Network). In the present embodiment, each component is connected by LAN, but may be connected via WWW (World Wide Web). Further, the number of elements of the calculation server 11 and the operation terminal 12 may be two or more.

<Functions and hardware>
Next, functions and hardware will be described with reference to FIGS. 1 and 2. FIG. 2 is a block diagram showing the hardware configuration in the present embodiment.

The data registration unit 111, the prediction model construction unit 112, the search unit 113, and the data management unit 114 included in the calculation server 11 of the design support apparatus 1 are CPU (Central Processing Unit) 1H101, ROM (Read Only Memory) 1H102 or an external storage. The program stored in the device 1H104 is read into a RAM (Read Access Memory) 1H103, and the communication I / F (Interface) 1H105, an external input device 1H106 represented by a mouse or a keyboard, an external output device 1H107 represented by a display or the like Is realized by controlling the

The data management unit 114 functions as a management unit that manages at least the material composition information (the cost composition data 1D2 in FIG. 4) regarding the composition or composition ratio of the material as a management target. The search unit 113 processes the raw material composition information (cost composition data 1D2 in FIG. 4) based on the characteristic request information (query data 1D4 in FIG. 6) input by the operation unit 121 (input unit) of the operation terminal 12 The composition or composition ratio of the design target satisfying the condition specified in the characteristic requirement information (query data 1D4 in FIG. 6) is specified (step 1F303 in FIG. 15), and the composition or composition ratio of the specified design object is It functions as processing means for specifying (step 1F 304 in FIG. 15) the combination of raw materials that falls within the allowable range of the conditions specified by the composition parameter (composition discrepancy parameter 1D6 in FIG. 8).

The operation unit 121 included in the operation terminal 12 of the design support apparatus 1 includes a central processing unit (CPU) 1H101, a program stored in a read only memory (ROM) 1H102 or an external storage device 1H104 in a read access memory (RAM) 1H103. This is realized by reading and controlling the communication I / F (Interface) 1H105, the external input device 1H106 represented by a mouse and a keyboard, and the external output device 1H107 represented by a display and the like.

The operation unit 121 (external input device 1H106) accepts as the target value the characteristic request information (query data 1D4 in FIG. 6) required as the characteristic of the design object (product) and the composition or composition ratio of the design object It functions as an input means for inputting at least a composition parameter (composition discrepancy parameter 1D6 in FIG. 8) which defines an allowable range of the value to be calculated. The operation unit 121 (external output device 1H 107) functions as a display unit that displays information from the output of the processing unit (search unit 113).

<Data structure>
Next, experimental recipe data 1D1 used for construction of a prediction model, which is managed by the data management unit 114, will be described using FIG. FIG. 3 is a block diagram of experimental recipe data in the present embodiment. The experimental recipe data 1D1 is data representing a combination of raw materials for each experiment performed in the past, and includes experimental number 1D101, raw materials “1” to “20” (1D102 to 1D121), and the data management unit 114 Stored.

The experiment number 1D101 is a number uniquely identifying a past experiment. The raw materials “1” to “20” (1D102 to 1D12) represent the amounts of each raw material used in each experiment. In the present embodiment, although the raw materials are 20 types of the raw materials “1” to “20”, they may be increased or decreased according to the embodiment. Further, in the following, the raw material may be simply referred to except the case of specifying any one of the raw materials “1” to “20”.

Next, cost composition data 1D2 managed by the data management unit 114 will be described using FIG. FIG. 4 is a block diagram of cost composition data in the present embodiment.

The cost composition data 1D2 is data representing the cost and composition for each raw material, and includes a raw material name 1D201, a unit cost 1D202, and compositions “1” to “10” (1D203 to 1D222), and the data management unit 114 Stored in The raw material name 1D201 is a name for uniquely identifying the raw material.

The unit cost 1D 202 is a cost per unit amount (1 kg, etc.). Other unit amounts may be used. The composition “1” to the composition “10” (1D203 to 1D222) are one or more characteristic quantities representing the composition of the raw material, such as molecular weight and chemical structure of the raw material.

In the present embodiment, although the composition of the raw material is set to 10 types of composition “1” to composition “10”, this may be increased or decreased according to the embodiment.

Hereinafter, the composition may be simply referred to as a composition except when specifying the composition of any one of the compositions “1” to “10”. In addition, information belonging to the raw material name 1D201 and unit cost 1D202, and compositions “1” to “10” (1D203 to 1D222) includes cost (unit cost) to the raw material and cost composition information on the composition or composition ratio of the raw material. The information that belongs to the material name 1D201 and the compositions “1” to “10” (1D203 to 1D222) constitutes material composition information on the composition or composition ratio of the material.

Thus, according to the concept of unit cost 1D 202, it is possible to provide a recipe of a product in which a combination of raw materials having predetermined characteristics and low manufacturing cost is specified.

Next, experimental physical property data 1D3 managed by the data management unit 114 will be described with reference to FIG. FIG. 5 is a configuration diagram of experimental physical property data corresponding to an experiment in the present embodiment. The experimental physical property data 1D3 is data of physical properties measured by the recipe of the experiment, and includes experimental number 1D301, gloss 1D302, fluidity 1D303, flexural rigidity 1D304, breaking elongation 1D305, and softening temperature 1D306, and the data It is stored in the management unit 114.

The experimental physical property data is information indicating physical properties of a product manufactured in the past or a product manufactured experimentally. The physical properties will be described representatively for the gloss 1D 302, the flowability 1D 303, and the like, but the characteristics of the other products described above can be used.

Physical properties are characteristics obtained by measuring or analyzing manufactured products. Moreover, not only the physical properties of the product actually manufactured in the past, but also the physical properties corresponding to the recipe of the product designed by the design support apparatus can be used.

The experiment number 1D301 corresponds to the above-described experiment number 1D101, and is a number uniquely identifying a past experiment. The gloss 1D 302, flowability 1D 303, flexural rigidity 1D 304, breaking elongation 1D 305, and softening temperature 1D 306 are indices indicating physical properties of a product (chemical product). In the present embodiment, although five types of indicators of physical properties are used, this may be increased or decreased according to the embodiment.

As described above, by displaying the experimental physical property data 1D3, after confirming the past results, it is possible to refer to the product characteristics and the constraint conditions, so the user simplifies the input of the characteristics and the constraint conditions. be able to.

Further, the product is not limited to the finished product, but data of an intermediate product that supports the production of the finished product to be used, mixed or combined as part of the finished product can be registered in the experimental physical property data 1D3. Also in this case, the user can simplify the input of the characteristic and the constraint condition. The data of the intermediate product can be registered or designed not only in the experimental physical data 1D3 but also in other data.

Next, query data 1D4 managed by the data management unit 114 will be described using FIG. FIG. 6 is a block diagram of query data in the present embodiment. The query data 1D4 is data for indicating to the design support device 1 a request as to what kind of physical property or characteristic the user wants to design when designing a new product (a characteristic required as a characteristic of the product to be designed) This is request information), and includes query number 1D 401, physical property name 1D 402, search type 1D 403, and parameters “1” and “2” (1D 404, 1 D 405), which are stored in the data management unit 114.

The query number 1D 401 is a number for uniquely identifying a query. Physical property name 1D402 indicates the required physical property name described in the query, for example, "gloss", "flowability", "bending stiffness", "break elongation", and "softening temperature".

Search type 1D 403 is a label indicating what kind of physical property is desirable, and in the present embodiment, maximization, minimization, or more (a certain value or more), larger than a certain value, or less (not more than a certain value) , Less than a certain value, and within a range (a range of a certain value 1 and a certain value 2).

The parameters “1” and “2” (1D404 and 1D405) have parameters according to the search type 1D403, and in the maximization and minimization, None is set and above (a certain value or more), larger than a certain value, (Less than or equal to a certain value), less than a certain value, a value corresponding to “some value” is set to the parameter “1” (1D 404).

For example, “7.5” is set in the following, “90” is set in the above, “None” is set in the parameter “2” (1D 405), and the range (a certain value 1 and a certain value 2 In the range, for example, “170” is set as the “certain value 1” to the parameter “1” (1D 404), and “220” is set as the “certain value 2” for the parameter “2” (1D405) can do.

In the present embodiment, the seven types of search types 1D 403 are selected, but may be increased or decreased according to the embodiment. If the parameter to be set is increased or decreased according to the increase or decrease, parameters “3”, “4”, etc. may be added, or parameters “1” and “2” (1D404 and 1D405). Semistructured data may be held therein.

Further, search type 1D 403 and parameters “1” and “2” (1D 404 and 1 D 405) are conditions specified (defined) by characteristic request information corresponding to each physical property, and “gloss” and “break elongation” “Maximization” is used as an objective function, and “flowability”, “bending stiffness”, “softening temperature”, “below”, “range”, “above” are used as constraint conditions.

Next, the raw material filter data 1D5 managed by the data management unit 114 described in FIG. 1 will be described using FIG. 7. FIG. 7 is a block diagram of raw material filter data in the present embodiment.

The raw material filter data 1D5 is data for limiting the raw material used for the recipe (raw material combination) output in the search phase (raw material filter information indicating the presence or absence of use of the raw material), and the query number 1D501, the raw material “1” Raw materials “20” (1D 502 to 1 D 521) are stored in the data management unit 114.

The query number 1D501 is a number corresponding to the query number 1D401 of the query data 1D4, and is a number for uniquely identifying a query. The raw materials “1” to “20” (1D 502 to 1 D 521) are values indicating whether the corresponding raw materials are used or not used (not used).

When using it, take "use" and when not using it, take "unused". These values are determined by the user. This makes it possible to specify the product recipe by the raw material designated to be used.

In addition, it is possible to specify a product recipe using a raw material that does not use a raw material designated as “not in use”, that is, uses a raw material different from the raw material not used by the raw material filter. If there is an unused raw material, it will be difficult to identify and enter constraints, but the present invention can identify a recipe of a product having a characteristic similar to a predetermined characteristic, so a recipe satisfying the characteristic as a product Can be provided.

The past experimental data and product information described above can also be used by the user to select a product or parameter having characteristics similar to the desired product.

Next, the composition discrepancy parameter 1D6 managed by the data management unit 114 will be described with reference to FIG.

FIG. 8 is a block diagram of the composition discrepancy parameter in the present embodiment. When the recipe (raw material combination) is searched for the composition ratio of the product at the end of the search phase, whether the composition ratio deviation parameter 1D6 allows for the composition ratio (for example, the target value of the composition and the search If the absolute value of the difference from the result is a specific example of a discrepancy and the value falls within the range practically satisfactory), or if the corresponding recipe can not be found under the specified condition, the condition is automatically set. It is data (composition discrepancy information) indicating whether or not relaxation may be performed, and includes query number 1D 601, composition name 1D 602, automatic relaxation 1 D 603, and allowance discrepancy 1 D 604, and is stored in the data management unit 114.

By performing the automatic relaxation, it is possible to find a recipe close to a desired recipe whose conditions have been relaxed, when no recipe is found. The allowable deviation indicates a range of characteristics different from the predetermined characteristics but satisfying as a product. The allowable deviation is, for example, a value representing the upper limit of the practically satisfactory range. Also called similar specific range.

The query number 1D601 is a number corresponding to the query number 1D401 of the query data 1D4, and is a number for uniquely identifying a query. The composition name 1D 602 indicates a composition name that designates the tolerance of the discrepancy, for example, “composition 1”, “composition 2”. The automatic relaxation 1D 603 is a value indicating whether or not a composition name (for example, query number = “1”, composition name = composition “1”) in a certain query may be relaxed until a feasible solution is found when searching.

If alleviation is acceptable, the value is "OK", otherwise "NG". The allowable discrepancy 1D 604 is a discrepancy in the composition ratio accepted at the time of recipe search. For example, if tolerance deviation 1D604 is 3% and automatic relaxation 1D603 is "NG", it is ensured that the composition ratio when a recipe (viable solution) is found is within plus or minus 3% of the target value Be done.

By this automatic relaxation 1D 603, it is possible to specify a recipe of a product having characteristics satisfying as a product even if there is no exact solution that falls within the target value of the predetermined characteristic. Also, a characteristic that falls within a range that can be relaxed is called a characteristic similar to the target value.

In the present embodiment, it is assumed that the composition name for which nothing is specified is set to a default value of “NG” for the automatic relaxation 1D 603 and “3%” for the allowable discrepancy 1D 604. On the other hand, when "OK" is set, there is a possibility that the range is relaxed.

In the present embodiment, no distinction is made between upward and downward deviations, but they may be distinguished as necessary. In addition, the default value and the designation method of the deviation or mitigation may be appropriately changed according to the application.

Further, the automatic relaxation 1D603 and the allowable deviation 1D604 are the conditions specified (defined) by the composition deviation parameter 1D6 corresponding to the composition name 1D602, and the allowable deviation 1D604 is a target for the composition or composition ratio of the product Although the difference has been described as an example of the difference with the value (the difference between the target value and the allowable limit value), it is a parameter (information) that defines an allowable range having characteristics satisfying the product. The present invention is not limited to the difference, and other examples of the concept of the difference include the square of the difference, the log, the approximation, etc. (the value acceptable as the target value), and can be appropriately selected according to the parameters.

Next, the search result physical property data 1D7 managed by the data management unit 114 will be described with reference to FIG. FIG. 9 is a block diagram of search result physical data in the present embodiment.

Search result physical property data 1D7 is data representing physical property values searched in the early stage of the search phase, and query number 1D701, candidate number 1D702, gloss 1D703, fluidity 1D704, flexural rigidity 1D705, fracture elongation 1D 706 and a softening temperature 1D 707, which are stored in the data management unit 114.

The query number 1D701 is a number corresponding to the query number 1D401 of the query data 1D4, and is a number for uniquely identifying a query. The candidate number 1D 702 is a number for uniquely identifying a candidate obtained as a result of searching for a query with respect to the same query.

Next, the gloss 1D 703, the fluidity 1D 704, the bending rigidity 1D 705, the breaking elongation 1D 706, and the softening temperature 1D 707 are the prediction results (the search results of the search unit 113) regarding the respective physical properties. In the present embodiment, the prediction result is, for example, a pair of data such as [86.4, 1.2] in which the query number 1D 701 corresponds to “1”, and represents an average value (expected value) and a standard deviation, respectively. In addition, the expression method of a prediction result may be made into the parameter of an average value or the probability density function estimated more easily.

Next, the search result composition ratio data 1D8 managed by the data management unit 114 will be described using FIG. FIG. 10 is a configuration diagram of search result composition ratio data in the present embodiment.

The search result composition ratio data 1D8 is data representing a composition value corresponding to the physical property value searched in the early stage of the search phase, and the query number 1D801, candidate number 1D802, composition “1” to composition “10” (1D802 To 1D 812), and is stored in the data management unit 114.

The query number 1D801 is a number corresponding to the query number 1D401 of the query data 1D4, and is a number for uniquely identifying a query. The candidate number 1D 802 is a number for uniquely identifying, for the same query, a candidate obtained as a result of searching for a query corresponding to the candidate number 1D 702.

The compositions “1” to “10” (1D802 to 1D812) are the values of the composition ratio (composition ratio of the product) respectively searched for. Note that a plurality of candidates are usually output for a single.

Next, search result recipe data 1D9 managed by the data management unit 114 will be described using FIG.

FIG. 11 is a block diagram of search result recipe data in the present embodiment. Search result recipe data 1D9 is recipe (raw material combination) data to be output at the end of the search phase, and the query number 1D901, the search number 1D902, the cost 1D 903 and the raw materials “1” to “20” (1D 904) To 1D 923) and stored in the data management unit 114.

The query number 1D901 is a number corresponding to the query number 1D401 of the query data 1D4, and is a number for uniquely identifying a query. The search number 1D 902 is a number given to identify the result when the raw material search for a certain candidate of a certain query results in an executable solution, and regarding the certain query number 1D 901, It is a number that uniquely identifies a search result.

The cost 1D 903 is the cost (raw material cost) per unit of the searched recipe. The raw materials “1” to “20” (1D904 to 1D923) respectively represent the blending amounts of the respective raw materials, and represent the combination of blending in total. In the present embodiment, although the manufacturing cost is not treated as being the same, the manufacturing cost may be variable according to the recipe, if necessary.

Next, search result discrepancy data 1D10 managed by the data management unit 114 will be described using FIG. FIG. 12 is a block diagram of search result discrepancy data in the present embodiment.

Search result recipe data 1D10 is data indicating how much the target composition ratio (target value of the composition ratio) is out of alignment with the recipe (raw material combination) output at the end of the search phase A query number 1D1001, a search number 1D1002, the number of types 1D1003, and compositions "1" to "10" (1D1003 to 1D1013) are stored in the data management unit 114.

The query number 1D1001 is a number corresponding to the query number 1D401 of the query data 1D4, and is a number for uniquely identifying a query. The search number 1D1002 is a number corresponding to the search number 1D902 of the search result recipe data 1D9, and is a number uniquely identifying a search result regarding a certain query number 1D01. The type number 1D1003 is the number of raw materials used.

The compositions “1” to “10” (1D1003 to 1D1013) are pieces of information indicating how relaxed each composition is with respect to the target value. In the case of upswing, it takes a positive value. “0” indicates that the degree of relaxation is 0 and the value of the composition ratio is equal to the target value.

By displaying the cost 1D 903 corresponding to the search number 1D 902 shown in FIG. 11 and the number of types 1D 1003 shown in FIG. 12, the user can know the correspondence between the production cost and the number of types of products of the product recipe. You can choose a recipe. In addition, these can also be displayed together with the number of types 1D103 corresponding to products of similar characteristics within the range of discrepancies, it is possible to compare recipes having characteristics satisfactory as products, and user convenience is improved Do.

<Processing flow>
Next, the processing flow of the basic data registration phase of the design support apparatus 1 in the present embodiment will be described using FIG. FIG. 13 is a flowchart showing the process flow of the basic data registration phase (experimental data registration) in the present embodiment. This process is started by the CPU 1 H 101 activating the data registration unit 111 that functions as a data registration program.

First, the data registration unit 111 registers experimental recipe data 1D1 input by the user via the operation unit 121 of the operation terminal 12 in the data management unit 114 as a database (1F101).

Next, the data registration unit 111 registers the cost composition data 1D2 input from the user via the operation unit 121 of the operation terminal 12 in the data management unit 114 (step 1F102).

Finally, the data registration unit 111 registers the experimental physical property data 1D3 input by the user via the operation unit 121 of the operation terminal 12 in the data management unit 114, and the process ends (step 1F103). At this time, the data management unit 114 functions as a management unit that manages various registered data (information) as a management target.

Next, a processing flow of a prediction model construction phase of the design support apparatus 1 in the present embodiment will be described using FIG. FIG. 14 is a flowchart showing a process flow of prediction model learning in the present embodiment. This process is started by the CPU 1 H 101 activating the prediction model construction unit 112 functioning as a prediction model construction program.

First, the prediction model construction unit 112 calculates the composition ratio (composition ratio of the raw material) in each experiment using the experimental recipe data 1D1 and the cost composition data 1D2 registered in the data management unit 114 in the basic data registration phase. (Step 1F201).

Next, the prediction model construction unit 112 learns a prediction model (simulator) using the composition ratio in each experiment described above and the experimental physical data 1D3 registered in the data management unit 114 in the basic data registration phase (step 1F202) ).

In this embodiment, CGAN (Conditional Generative Adversalial Nets) is used as a prediction model. That is, a generation model of physical properties under a condition of a certain composition ratio is constructed by a neural network. In the search phase to be described later, for example, 100 samples can be generated from CGAN, and their mean and variance can be used.

Although CGAN is used in the present embodiment, other statistical and machine learning models can be used. For example, linear regression models, support vector regressions, decision trees, other neural networks, etc. may be used in combination of one or more as required. In addition, when searching for the composition ratio, it may be effective that the prediction model is lightweight (processing time is fast).

In such a case, a plurality of prediction models may be appropriately used, such as using a linear regression model, etc., except for the final stage of composition ratio search or evaluation of final dispersion (dispersion etc.).

Moreover, although the method of constructing a prediction model from various experimental data is dealt with in this embodiment, when the prediction result can be calculated by the first principle method, the calculation formula is adopted as the prediction model. It is also good.

However, in the present embodiment, it is assumed that a prediction model is constructed by learning from experimental data, and further, a case where only one prediction model is handled is described for simplicity. Further, in the present embodiment, although the manufacturing conditions and the like are not included in the prediction model, they may be input as conditions as needed.

Next, the processing flow of the search phase of the design support apparatus 1 in the present embodiment will be described using FIG. FIG. 15 is a flowchart showing a processing flow of the raw material combination search in the present embodiment. This process is started by the CPU 1 H 101 activating the search unit 113 functioning as a search program.

First, search unit 113 receives query data 1 D 4 (characteristic request information including physical property information) input from the user via operation unit 121 of operation terminal 12 and raw material filter data 1 D 5, and registers them in data management unit 114. (Step 1F301).

Next, the search unit 113 receives the composition discrepancy parameter 1D6 input by the user via the operation unit 121 of the operation terminal 12, and registers it in the data management unit 114 (step 1F302).

Next, the searching unit 113 searches for a composition ratio (composition ratio of the product) that satisfies the physical properties designated by the query data 1D4 (step 1F303). The search uses NSGA-II (Non-dominated Sorting Genetic Algorithm II), which is a standard method of multi-objective optimization.

By adopting the multi-objective optimization method, it is possible to obtain a solution candidate that maintains diversity compared to the case of performing single-objective optimization to specific physical properties or a combined value obtained by weighting two or more physical properties. This is effective in maintaining the versatility of the recipe (raw material combination) in the end.

Further, in the query data 1D4, with regard to the conditions specified by the search type 1D403 below, by the above, by the range, etc., it is coped with by not generating solution candidates that do not match the specified conditions at the time of solution candidate creation.

For example, in a situation where the bending stiffness is restricted to be in the range of 170 to 220, when the bending stiffness of the solution candidate generated by the difference evolution is 230, the solution candidate is not adopted. The solution candidate generation is repeated until a solution candidate satisfying the constraints is found. In the present embodiment, NSGA-II, which is a multi-objective optimization method, is adopted, but other optimization methods may be used.

Further, in the above prediction model, samples of each physical property are obtained, so it is possible to evaluate not only average value (expected value) indicating predicted values but also blurring condition / variation (dispersion etc.) Although only the average value (expected value) is used in the form, it is also possible to apply a penalty if, for example, the degree of fluctuation or fluctuation in the prediction is large, as needed.

Next, the searching unit 113 determines that the composition ratio (composition ratio of the product) falls within the discrepancy (within the allowable range designated by the composition discrepancy parameter 1D6) designated by the composition discrepancy parameter 1D6, and designates by the raw material filter data 1D5. Using only the raw materials (raw materials to be used), a recipe (raw material combination) whose cost is reduced is searched for (step 1F 304). Linear programming is used for the search.

That is, the range of the composition ratio of the product (for example, 12.1-5 <composition “1” <12.1 + 5) is set as a constraint condition, a problem that minimizes the cost is set, and the best solution is searched. “12.1” indicates the composition ratio of the composition “1”, and “5” indicates the allowable discrepancy (%).

Since there are many commercial and non-commercial solvers that can be calculated at high speed in linear programming, it is possible to rapidly find low-cost recipes that satisfy queries by formulating in this way. In addition, with regard to raw materials that have not been used, they are not included in the decision variables. Also, the type of raw material used is generally preferred to be small. Therefore, we will create the results of squeezing the raw materials to be used in the form of two, three or four.

If no feasible solution is found as a result of the search, the constraints on the range of composition ratio of the product are gradually relaxed. For example, when the target value of the composition ratio of composition “1” is 10% and the allowable deviation is 1%, the composition ratio of composition “1” is initially less than 11%, and the composition ratio of composition “1” is 9% In the situation where two restrictions are imposed, which is larger, if the automatic relaxation is OK, the composition ratio of composition “1” is smaller than 11.5%, and the composition ratio of composition “1” is larger than 8.5% And so on, we will ease the constraints by 0.5% each. In the present embodiment, it is assumed that the cost is linear with respect to the amount of each raw material used.

If it is necessary to consider, for example, the case where the cost becomes constant if the amount is less than a certain amount, if manufacturing costs etc. break the assumption, a search method other than linear programming should be used. It can also be used.

Also, the method of relieving constraints by 0.5% each is only an example, and it may be relaxed by another method. That is, when a solution corresponding to a predetermined constraint condition can not be obtained, the condition may be relaxed stepwise.

Next, the search unit 113 sends the search result physical property data 1D7, the search result composition ratio data 1D8, the search result recipe data 1D9, and the search result discrepancy data 1D10, which are the search results obtained in step 1F304, to the data management unit 114. It registers (step 1F305).

In the process of step 1F305, the method of creating the result of squeezing the raw materials to be used in the form of two, three, four etc. is simply to select all the combinations of two types of raw materials, three types of raw materials Set the problem in all combinations and solve the set problem. However, if the calculation load of the recipe search is a problem due to a large total number of raw materials, the combination of raw materials to be used may be searched using an exchange Monte Carlo method or the like.

Finally, the operation unit 121 presents the user with various search results and related past results (experimental recipe data 1D1, cost composition data 1D2, and experimental physical data 1D3 with similar physical properties) to the user, and ends the process (step 1F306). . That is, these pieces of information are displayed on the screen of the operation unit 121.

As described above, a prediction model of physical properties with respect to the composition ratio of raw materials is built, and in the first stage search, an objective function and constraint conditions regarding the physical properties of the product are configured, and the composition ratio of the product is searched as a determination variable Do.

Next, in the second stage search, the objective function and the constraint conditions are configured using the raw material cost (unit cost) and the product composition ratio, and the raw material combination is searched as a decision variable to select the raw material (raw material combination ) Can be obtained.

By searching for the raw material through the two-step search via such composition ratio, it is possible to flexibly set complex objective functions and constraints according to the user's thinking.

It is possible to specify a recipe that is a solution even if the user does not input constraints strictly. By performing a two-step search, it is possible not only to identify a recipe that matches the input product characteristics but also to identify a recipe that is similar to the input product characteristics in consideration of cost and past experimental information. it can. In addition, it is possible to reuse the prediction model.

In addition, if the search space becomes very large, the problem can be divided in stages to obtain an effect of reducing the search space. In general, even if it is difficult to handle complex constraints in multi-objective optimization or it often requires prior knowledge of the problem, only a part (specifically, physical properties) is limited in this embodiment. Implement multi-objective optimization.

After that, regarding the number of types of raw materials, the problem itself is divided into multiple linear programming problems to give constraints and search, and therefore, a search that strictly imposes important constraints of interest while maintaining the diversity of candidates. Results can be obtained efficiently.

Further, the search result of the first stage and the search result of the second stage can be displayed on the screen of the operation unit 121 of the operation terminal 12. At this time, when the operation unit 121 executes an operation of changing or adding any one of the condition (information) defined in the query data 1D4, the raw material filter data 1D5, and the composition discrepancy parameter 1D6. Based on the changed or added conditions, the first stage search and the second stage search can be performed again.

<User interface>
The query registration screen 1G1 for receiving the query data 1D4 and the raw material filter data 1D5 from the user by the operation unit 121 of the operation terminal 12 will be described with reference to FIG. FIG. 16 is a configuration diagram of a query registration screen in the present embodiment.

The query registration screen 1G1 includes a physical property input pane 1G101, a raw material filter input pane 1G102, an OK button 1G103, and a reset button 1G104. At this time, the external output device 1H107 of the operation terminal 12 functions as a display unit (query registration screen display unit) or display means for displaying a query registration screen 1G1 for receiving data from the external input device 1H106. The external output device 1H107 and the external input device 1H106 can be implemented integrally or separately.

The physical property input 1G101 has a function of registering search types and parameters of glossiness, fluidity, flexural rigidity, fracture elongation, and softening temperature corresponding to the query data 1D4. In the initial state, nothing is set. The user sets the physical properties of the request including one or more maximizations or minimizations.

The raw material filter input pane 1G102 has a function of registering the use and non-use of each raw material corresponding to the raw material filter data 1D5. "○" corresponds to use, "×" corresponds to non-use, and all initial values are "○". Each time this symbol part is pressed, it changes to "x" in the case of "o", and changes to "o" in the case of "x".

The user can register various data in the data management unit 114 of the calculation server 11 by inputting the physical property input 1G101 and the input pane 1G102 and pressing the OK button 1G103. When the data registration process is completed, the search process is performed. On the other hand, when it is desired to input new physical properties from the beginning, pressing the reset button 1G104 resets the initial state of various input contents.

The physical property display screen 1G2 for the operation unit 121 of the operation terminal 12 to present the search result of physical properties to the user will be described with reference to FIG. FIG. 17 is a configuration diagram of a physical property display screen in the present embodiment.

The physical property display screen 1G2 includes a physical property display pane 1G201 for displaying the searched physical property, a detailed display pane 1G202 for displaying the detailed physical property and composition ratio of the candidate selected in the physical property display pane 1G201, and a material combination display for displaying the raw material combination. A button 1G203 and a back button 1G204 are provided. At this time, the external output device 1H 107 of the operation terminal 12 functions as a display unit (physical property display unit) that displays the physical properties searched by the search unit 113.

The physical property display pane 1G201 displays a set of candidate (pareto solutions) 1G 201a obtained as a result of executing multi-objective optimization on physical properties for which one or more maximizations or minimizations have been set, and past experimental results 1G 201b. Here, the past experimental results are various data (1D1, 1D2, 1D3) of the experiment.

In the example of FIG. 17, a candidate (Pareto solution) related to gloss and fracture elongation or a solution in the vicinity thereof and a past experiment result having similar characteristics are displayed. In addition, when the user selects a point, the physical property information or the outline thereof regarding the candidate or the past experiment result is displayed in the pop-up 1 G 201 c.

Note that FIG. 17 shows the case where the maximization is specified particularly for two physical properties (“gloss”, “breaking elongation”), so the graph is a two-dimensional plot.

If only one maximization or minimization is specified, the solution near the best candidate is displayed as a one-dimensional graph.

When three or more maximizations or minimizations are specified, three-dimensional display may be performed, or a combination of physical properties for which a two-dimensional graph is specified may be displayed side by side. Further, in the present embodiment, only the physical properties for which the maximization or the minimization is specified are displayed on the graph, but the physical properties for which the larger or smaller range is specified may be displayed on the graph. Good.

As described above, the detailed display pane 1G202 shows detailed physical properties ("Gloss", "Flowability", "Bending stiffness", "Break elongation", "Softening temperature") of the candidates selected by the user on the physical property display pane 1G201. And the predicted value (expected value) and the composition ratio are displayed in the sub-pane (1G202a, 1G202b) based on the search result physical property data 1D7 and the search result composition ratio data 1D8.

At that time, not only the goodness of the candidate as a simple expected value but also the certainty of the prediction can be confirmed by displaying the dispersion of the prediction result of the physical property (the degree of blur indicating the dispersion). Although dispersion is described as a representative example of variation, mean, deviation, correlation or the like may be used.

By pressing the raw material combination display button 1G203, it is possible to transition to a screen (raw material combination display screen 1G3 (described later)) for displaying a recipe (raw material combination) regarding the candidate selected by the user on the physical property display pane 1G201. On the other hand, when the back button 1G 204 is pressed, it is possible to return to the setting of the query (required physical property).

By providing such a user interface, it is possible to compare search results with past experimental results. In addition, since the physical properties corresponding to the search result and the past experimental result, and the predicted values and variations thereof can be displayed, the convenience is enhanced.

Moreover, since the combination of the raw materials corresponding to the displayed search result and the past experimental result can be displayed, it becomes easy to select the characteristic to be emphasized among the characteristics of the product.

The raw material combination display screen 1G3 for the operation part 121 of the operation terminal 12 to present a recipe (raw material combination) to a user is demonstrated using FIG. FIG. 18 is a block diagram of the raw material combination display screen in the present embodiment.

The raw material combination display screen 1G3 is a display screen for displaying the search result of the search unit 113, and includes a cost display pane 1G301, a raw material combination display pane 1G302, a relaxation condition display pane 1G303, a report output button 1G304, and a back button 1G305. At this time, the external output device 1H 107 of the operation terminal 12 in FIG. 2 functions as a display unit (search result display unit) that displays the search results of the search unit 113 shown in FIG.

The degree of relaxation is an automatically relaxed range or value, or a range or value of discrepancy. The degree of relaxation is output or automatically set in the degree-of-relaxation display pane 1G 303, and the range or value thereof is displayed.

The cost display pane 1G301 displays, based on the search result recipe data 1D9, the cost (raw material cost) for each of the used raw material numbers for the candidate selected on the physical property display screen 1G2. For example, the cost display pane 1G 301 displays information on a combination of low cost raw materials (3 types use to 6 types use). In this case, use of six types is the minimum cost.

The raw material combination display pane 1G302 displays, based on the search result recipe data 1D9, a combination of raw materials for the number of used raw materials for the candidate selected on the physical property display screen 1G2. For example, in the case of “use of three types”, the raw material combination display pane 1G 302 displays that the raw material “2” with the mixing amount of the raw material “24” is combined with the other two kinds of raw materials (not shown) become. Moreover, in the case of four types of utilization, it is a recipe which combines the raw material 2 and the raw material 3, and two other raw materials which are not shown in figure.

Under the present circumstances, when the raw material filter data 1D5 which shows the presence or absence of use of the raw material shown in FIG. 7 from the operation part 121 is searched from the operation part 121, the search part 113 shown in FIG. Identify combinations that do not use specified raw materials.

Next, the combination which does not use the identified raw material is excluded from among the combinations of raw materials which fall within the allowable range of the condition specified by the compositional discrepancy parameter 1D6. Among the combinations of raw materials that fall within the allowable range of the conditions specified by the compositional deviation parameter 1D6, the combinations of raw materials from which the combinations not using the raw materials have been excluded are specified. The combination of the identified raw materials is displayed on the raw material combination display pane 1G302.

The relaxation degree display pane 1G303 displays, for the candidates selected on the physical property display screen 1G2, the degree of relaxation of the composition ratio for each number of used materials based on the search result discrepancy data 1D10. For example, in the case of “three types of use”, the relaxation degree display pane 1G 303 displays that the relaxation degree of the composition ratio of “composition 1” is “1.3%”.

By pressing the report output button 1G304, it is possible to output a report for the user to request an experiment. On the other hand, when it is desired to confirm another candidate, it is possible to return to the physical property display screen 1G2 by pressing the back button 1G305.

In the present embodiment, the screen example regarding the case of using three to six types of raw materials is shown, but it can be increased or decreased according to the search result or the request from the user. It is also possible to display a search result based on the input product characteristics or information input by the user in the past, even if the request is not made by the user.

As described above, by displaying the search results for each number of raw materials using the search results, the user can simply compare the number of raw materials that are difficult to convert into expenses.

In addition, in the example of FIG. 18, although the composition ratio for every number of used raw materials is not displayed, you may display together as needed.

Also, the contents of search result physical property data 1D7, search result composition ratio data 1D8, search result recipe data 1D9, and search result discrepancy data 1D10 are displayed on the screen of the operation unit 121 of FIG. You can also It is not necessary to display all the items, and the display items can be changed according to the setting of the user.

User interfaces such as physical property display pane 1G201, detail display pane 1G202, cost display pane 1G301, raw material combination display pane 1G302, and relaxation condition display pane 1G303 described in FIGS. 17 and 18 can be freely combined and displayed. it can. Also, some panes may not be displayed as needed.

As described above, according to the present embodiment, after specifying the composition or composition ratio of the product having the characteristics meeting the requirements, different conditions (for example, the composition and composition discrepancy parameter specified in the cost composition data 1D2) Since the combination of materials is searched in consideration (with consideration) of conditions defined by 1D6 and including conditions that can be changed by reusing conditions etc. defined by query data 1D4, etc. Recipes for products with matching characteristics can be identified.

In addition, it is possible to support product design in consideration of different constraints. Furthermore, even if the type of raw material changes as long as there is no change in the composition or composition ratio of the raw material to be considered, the prediction model for the composition or composition ratio of the raw material can be reused.

As an example of the characteristic meeting the requirement, it is a physical property required as a product, which satisfies the condition defined by the query data 1D4 (characteristic request information) of FIG.

Also, by registering the past experiment results of multiple users, it becomes possible to share the past experiment results among users in terms of the physical properties described in the query data, and design with similar recipes The situation can be avoided.

In addition, since the degree of relaxation indicating the discrepancy between the composition ratio and the target value is evaluated with respect to the recipe, the user can select a recipe with less degree of relaxation. The place where the degree of relaxation is large can be selected to search for new formulation possibilities.

These enter the first constraint corresponding to the product of the present invention that satisfies the desired characteristics, identify the combination of the raw materials corresponding to the first constraint, and have characteristics similar to the identified combination of raw materials. By searching the combination of raw materials specified by the corresponding second constraint, it is possible to realize by the idea of searching a plurality of conditions different from the initially input constraint.

A modification of the cost composition data 1D2 described in FIG. 4 will be described with reference to FIG. Unlike FIG. 4, FIG. 19 is a configuration diagram of composition data corresponding to raw material types and amounts in this embodiment.

Composition data 1D2a corresponding to the type and amount of raw material is data indicating a composition that changes depending on the type and amount of raw material. The type of raw material 1D 201a to be mixed or combined, the amount 1D 202a of the raw material 1, and the amount 1D 203a of the raw material 2 are shown.

When the raw materials are mixed or combined, depending on the composition, the amount of the raw materials may increase non-linearly and not linearly with the increase. An equation showing this non-linear, increasing relationship is shown in the equation 1D 204a etc. of the composition "1". Similarly, Formula 1 D 222 a of composition “2” is represented by Formula 1 D 222 a of a predetermined composition “n”.

By selecting Formula 1D 204a of the composition “1”, the user can display a graph having the raw material “1” and the raw material “2” as parameters, and the user can know the amount of the composition for the combination of predetermined raw materials .

When the composition is nonlinear with respect to the type and amount of raw materials as in this example, the second stage search is not a linear programming problem, and is achieved by using, for example, a genetic algorithm or the like.

Further, in this example, two types of raw materials are used, but three or more types of combinations may be input and displayed as a three-dimensional graph or the like. The display method is not limited to these and may be another expression method.

By showing the composition when mixing or combining a plurality of types of raw materials in this way, the user can know the combination of raw materials having predetermined characteristics, and it is easy to input the necessary constraint conditions in the product recipe It becomes.

To explain an example of the present embodiment, the data management unit 114 in FIG. 1 functions as a management unit that manages at least raw material composition information (cost composition data 1D2) related to the composition or composition ratio of the raw material.

The operation unit 121 (external input device 1H106) shown in FIG. 1 allows the characteristic request information (query data 1D4 shown in FIG. 6) required as the characteristic of the design object and the composition or composition ratio of the design object as the target value. It functions as an input means for inputting at least a composition parameter (composition discrepancy parameter 1D6 in FIG. 8) which defines an allowable range of the value to be calculated.

The search unit 113 in FIG. 1 processes the raw material composition information (cost composition data 1D2 in FIG. 4) based on the characteristic request information (query data 1D4 in FIG. 6) input by the input means, and the characteristic request information (query data) The composition or composition ratio of the design object satisfying the conditions specified in 1D4) is identified (step 1F303 in FIG. 15), and the composition parameter (composition discrepancy parameter in FIG. 8) is obtained for the composition or composition ratio of the identified design object It functions as processing means for specifying (step 1F 304) a combination of raw materials that falls within the allowable range of the conditions specified in 1D6).

The operation unit 121 (external output device 1H 107) in FIG. 1 can function as a display unit that displays information from the output of the processing unit (search unit 113). The processing means (searching unit 113) specifies a combination of conditions (raw material type) different from the conditions used when specifying the combination of raw materials, and displays the combination of the different conditions that were specified as the display means (raw material combination display screen 1G3 Display on). Thereby, it is possible to simplify the input of the constraint conditions of the production recipe of the product having the predetermined characteristics.

In addition, the processing means (searching unit 113) requires that cost composition information (cost composition data 1D2) relating to the cost to the raw material and the composition or composition ratio of the raw material exist as a management target of the management means (data management unit 114). Under the conditions, a combination of low cost raw materials is specified based on the cost composition information, and the specified low cost raw material combination is displayed on the display means (cost display pane 1G301). Since the combination of the low cost raw materials is displayed, the combination of the low cost raw materials can be determined as a product.

When the raw material filter information (raw material filter data 1D5 in FIG. 7) indicating the presence or absence of use of the raw material is input to the input means (operation unit 121), the processing means (searching unit 113) Identify combinations that do not use raw materials designated for nonuse, and exclude combinations that do not use the specified raw materials from among combinations of raw materials that fall within the allowable range of the conditions specified in the composition parameters, Among the combinations of raw materials belonging to the allowable range of the condition specified by the parameter, the combination of the raw materials excluding the combination without using the raw material is specified, and the combination of the specified raw materials is displayed as display means (raw material combination of FIG. 18 Display on display pane 1G 302). Since the combination of raw materials used for the product having the predetermined characteristics is displayed, it is possible to confirm the combination of raw materials used for the product.

The processing means (searching unit 113) is information managed by the managing means (data management unit 114), and is index information on an index indicating the physical properties of the product or intermediate product different from the design target (experimental physical property data of FIG. 3) Based on 1D3), the display device (physical property display pane 1G201 of FIG. 17) displays index information (past experiment result) relating to an index indicating physical properties of a product or an intermediate manufactured in the past than the design target. As past performance is displayed, this information can be used as a reference when entering the manufacturing recipe constraints of the product having the predetermined characteristics.

The processing means (searching unit 113) specifies the predicted value of the physical property of the design object and the variation thereof in the process of specifying the composition or the composition ratio of the design object, and the predicted value of the physical property of the identified design object and the dispersion It is displayed on the display device (sub pane 1G 202a in FIG. 17). The predicted values of physical properties to be designed and their variations can be visualized, and the visualized information can be used as a reference when inputting the constraints of the manufacturing recipe of a product having a predetermined characteristic.

The processing means (searching unit 113) further specifies the number of types of raw materials belonging to the combination of low cost raw materials based on the specified combination of low cost raw materials, and the number of types of specified raw materials (see FIG. The number of types of the 12 search result discrepancies data 1D10 is displayed on the display device. Display and visualize the number of types of raw materials belonging to the combination of low cost raw materials.

When the processing means (searching unit 113) can not specify the combination of the raw materials belonging to the allowable range of the condition specified by the composition difference parameter, it gradually reduces the allowable range of the condition specified by the composition difference parameter. It is possible to suppress the inability to identify the combination of raw materials and to accelerate the processing.

The processing means (searching unit 113) is a relaxation degree indicating a difference between the low cost source material combination and the target value of the composition or composition ratio to be designed based on the specified low cost source material combination. (The composition “1” to the composition “10” of the search result discrepancy data 1D10 of FIG. 12) are further specified, and the identified relaxation condition is displayed on the display device (the relaxation condition display pane 1G303 of FIG. 18). Since the information on the degree of relaxation is displayed and visualized, this information can be used as a reference when inputting constraints of a production recipe of a product having a predetermined characteristic.

When the condition designated by the compositional discrepancy parameter is changed or added by the input unit (the external input device 1H 106), the processing unit (searching unit 113) specifies a combination of raw materials that satisfies the changed or added condition. It is possible to identify a combination of raw materials that satisfy the changed or added conditions in which the conditions for inputting manufacturing recipe constraints are changed or added.

Reference Signs List 1 design support apparatus, 11 calculation server, 12 operation terminals, 111 data registration unit, 112 prediction model construction unit, 113 search unit, 114 data management unit, 121 operation unit

Claims (15)

1. A design support apparatus for designing a product or an intermediate product manufactured using two or more raw materials and supporting the design of the design target,
   Management means for managing at least management target material composition information related to the composition or composition ratio of the raw material;
   Input means for inputting at least property request information required as a property of the design object, and a composition parameter defining an allowable range of values acceptable as target values for the composition or composition ratio of the design object;
   The raw material composition information is processed based on the characteristic request information input by the input means, and the composition or composition ratio of the design object satisfying the condition specified by the characteristic request information is identified, and the identification is performed. A processing means for specifying the combination of the raw materials which fall within the allowable range of the conditions specified by the composition parameter with respect to the composition or composition ratio of the design object;
   Displaying means for displaying information from the output of the processing means;
   The processing means
   A design support apparatus characterized by specifying a combination of conditions different from the condition used when specifying the combination of the raw materials, and displaying the combination of the specified different conditions on the display means.
2. The design support apparatus according to claim 1, wherein
   The processing means
   Identify the combination of low cost materials based on the cost composition information on condition that cost composition information regarding the cost to the material and the composition or composition ratio of the material is present as the management target of the management means And the display supporting means is configured to display the combination of the specified low-cost raw materials on the display means.
3. The design support apparatus according to claim 1, wherein
   The processing means
   When raw material filter information indicating presence or absence of use of the raw material is input to the input unit,
   The combination which does not use the raw material designated as unused by the said raw material filter information among the said raw materials is specified, and the combination which does not use the said specified said raw material is within the tolerance | permissible_range of the conditions designated by the said composition parameter. The combination of the raw materials excluding the combination not using the raw material is specified among the combinations of the raw materials which are excluded from the combinations of the belonging raw materials and which fall within the allowable range of the condition specified by the composition parameter; A design support apparatus characterized by displaying the combination of the specified raw materials on the display means.
4. The design support apparatus according to claim 1, wherein
   The processing means
   Physical properties of a product or an intermediate manufactured in the past than the design target on the basis of index information related to indexes managed by the management means and indicating physical properties of the product or intermediate different from the design target A design support apparatus for displaying index information on an index indicating the index on the display means.
5. The design support apparatus according to claim 1, wherein
   The processing means
   In the process of specifying the composition or composition ratio of the design object, the predicted value of the physical property of the design object and the variation thereof are specified, and the predicted value of the physical property of the design object identified and the variation thereof are displayed on the display means A design support apparatus characterized in that
6. The design support apparatus according to claim 2, wherein
   The processing means
   The number of types of raw materials belonging to the combination of low cost raw materials is further specified based on the combination of the low cost raw materials specified above, and the type number of the specified raw materials is displayed on the display means A design support apparatus characterized in that
7. The design support apparatus according to claim 1, wherein
   The processing means
   A design support apparatus characterized in that the allowable range of the conditions specified by the composition parameter is relaxed stepwise when it is not possible to specify the combination of the raw materials within the allowable range of the conditions specified by the composition parameters.
8. The design support apparatus according to claim 2, wherein
   The processing means
   Based on the combination of the identified low cost raw materials, the degree of relaxation indicating the difference between the low cost raw material combination and the target value of the composition or composition ratio to be designed is further specified, A design support apparatus characterized by displaying the specified degree of relaxation on the display means.
9. The design support apparatus according to claim 1, wherein
   The processing means
   A design support apparatus characterized by specifying a combination of the raw materials satisfying the change or the added condition when the condition specified by the composition parameter is changed or added by the input unit.
10. A design support method for designing a product or an intermediate product made using two or more raw materials and supporting the design of the design target,
    A management step of managing at least management target material composition information related to a composition or composition ratio of the raw material;
    An input step of inputting at least characteristic request information required as a characteristic possessed by the design object, and a composition parameter defining an allowable range of values acceptable as target values for the composition or composition ratio of the design object;
    The raw material composition information is processed based on the characteristic request information input in the input step to specify the composition or composition ratio of the design object that satisfies the condition specified by the characteristic request information, and And a processing step of specifying the combination of the raw materials which fall within the allowable range of the condition specified by the composition parameter with respect to the composition or composition ratio of the design object.
    Displaying information from the output of the processing step;
    In the processing step,
    Identify a combination of conditions different from the conditions used to identify the combination of raw materials,
    In the display step,
    A design support method characterized by displaying a combination of the different conditions specified in the processing step.
11. The design support method according to claim 10, wherein
    In the processing step,
    Identifying a combination of low cost materials based on the cost composition information on the cost of the raw material and the composition or composition ratio of the raw material, which is the management target managed in the management step;
    In the display step,
    A design support method characterized by displaying a combination of the low cost raw materials specified in the processing step.
12. The design support method according to claim 10, wherein
    In the processing step,
    In the input step, when raw material filter information indicating the presence or absence of use of the raw material is input, a combination not using the raw material whose nonuse is designated in the raw material filter information is specified among the raw materials, and the specified The combination which does not use the raw material is excluded from the combination of the raw materials which falls within the allowable range of the condition specified by the composition parameter, and the raw material of which the combination falls within the allowable range of the condition specified by the composition parameter Among the combinations, the combinations of the raw materials from which the combinations not using the raw materials are excluded are identified,
    In the display step,
    A design support method characterized by displaying a combination of the raw materials specified in the processing step.
13. The design support method according to claim 10, wherein
    In the processing step,
    Physical properties of a product or an intermediate manufactured in the past than the design target based on index information related to indexes managed in the management step and indicating physical properties of the product or intermediate different from the design target Identify indicator information on indicators that indicate
    In the display step,
    A design support method characterized by displaying index information related to an index indicating physical properties of a product or an intermediate product manufactured in the past than the design object, which is index information specified in the processing step.
14. The design support method according to claim 10, wherein
    In the processing step,
    In the process of specifying the composition or composition ratio of the design object, the predicted value of the physical property of the design object and the variation thereof are specified;
    In the display step,
    A design support method characterized by displaying predicted values of physical properties of the design object specified in the processing step and variations thereof.
15. The design support method according to claim 11, wherein
    In the processing step,
    Based on the combination of the identified low cost raw materials, the number of types of the raw materials belonging to the low cost raw material combination is further specified;
    In the display step,
    A design support method characterized by displaying the number of types of the raw material specified in the processing step.

Images