Material search and compounding design device and compounding design method
The material search and blending design system addresses the inefficiencies in selecting candidate materials by using a systematic approach to select alternative materials and additives, effectively reducing costs and ensuring high specification compliance.
Patent Information
- Application Number
- PCT/JP2024/040449
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-12-13
- Filing Date
- 2024-11-14
- Publication Date
- 2025-06-19
AI Technical Summary
The current methods for selecting candidate materials for products, especially those using recycled materials for exterior components, are inefficient due to insufficient data and time-consuming trial production processes, leading to high costs and potential inability to meet required specifications.
A material search and blending design system that selects alternative materials and additives by calculating addition rate ranges based on physical property change characteristics, overlapping ranges for multiple physical properties, and using machine learning to determine appropriate additives and their addition rates.
This system efficiently searches for alternative materials and additives, reducing the time and cost associated with material selection and enabling the production of recycled materials that meet high specifications for exterior components.
Smart Images

Figure JP2024040449_19062025_PF_FP_ABST
Abstract
Description
Material search and mix design device and mix design method
[0001] The present invention relates to a material search and mix design device and mix design method.
[0002] While demand for plastics has been increasing in recent years, production of new plastics derived from petroleum, a dwindling resource, is expected to decline in the future. As a result, the proportion of recycled plastics is expected to increase significantly.
[0003] Recently, there has also been an increase in the number of products released that use recycled materials in exterior parts, etc. As a result, the use of recycled materials is becoming a new competitive axis.
[0004] Patent Document 1 describes a similar material search system, test device, and computer program (see abstract) in which "a processor acquires input design parameters, reads out SS data representing at least two stress-strain curves from a storage device, determines, for each SS data, feature quantities including at least one shape parameter that characterizes the shape of the SS curve, assigns the at least two SS data to one of k (k is an integer of 2 or more) similar groups based on the feature quantities, searches for a target material having material property parameters that satisfy a design range defined by the input design parameters from the at least two SS data assigned to each of the k similar groups, and searches for a material corresponding to the SS data assigned to the similar group selected by the user from l (l is an integer equal to or less than k) similar groups for which target SS data could be found"
[0005] Japanese Patent Application Laid-Open No. 2020-190863
[0006] In response to the rapidly increasing demand for recycled materials, there are currently insufficient methods and data for selecting candidate materials. Furthermore, materials with the desired properties do not necessarily exist, and manufacturers must repeatedly conduct prototyping to search for and adopt suitable candidate materials. This requires a great deal of time and expense, which is an issue.
[0007] As the use of recycled materials becomes more active, it is expected that the proportion of recycled materials used in exterior parts of products will increase in the future. However, when recycled materials are used in exterior parts, the required specifications for dimensions and molding quality precision are higher than when they are used in internal parts. Therefore, if the appropriate recycled material cannot be selected according to the required specifications, it may not be possible to meet them by adjusting them at the injection molding stage.
[0008] The similar material search system described in Patent Document 1 determines the optimal material based on feature quantities, including at least one shape parameter, that characterize the shape of the SS curve. The technology described in Patent Document 1 is effective when registered materials have properties that fully satisfy the specifications. However, the technology does not consider suggesting appropriate candidate materials when registered materials do not have properties that fully satisfy the specifications. Therefore, the technology described in Patent Document 1 has difficulty comprehensively resolving the above-mentioned problem of supplying recycled materials with high required specifications.
[0009] The present invention has been made in view of the above background, and an object of the present invention is to efficiently search for alternative materials and additives to be added to the alternative materials.
[0010] In order to solve the above-mentioned problems, the present invention comprises a blending design unit that selects additives to be added to an alternative material, which is a candidate material for replacing a reference material, which is a material currently used in a product or a material expected to be used, and an output processing unit that outputs a combination of the alternative material selected by the blending design unit and the additive, wherein the blending design unit calculates an addition rate range that is a range of addition rates corresponding to the physical property change characteristics of the additive based on the range of physical property change rates due to the additive that meets the additive conditions, and if the calculated addition rate ranges for multiple physical properties have an overlapping range, selects the overlapping range as the additive addition rate, and the output processing unit outputs the addition rate corresponding to the overlapping range in addition to the combination of the alternative material and the additive. Other solutions will be described as appropriate in the embodiments.
[0011] According to the present invention, it is possible to efficiently search for alternative materials and additives to be added to the alternative materials.
[0012] 1 is a diagram showing an example of the overall configuration of a material search and mix design system. FIG. 2 is a diagram showing an example of the configuration of a material search and mix design device. FIG. 3 is a diagram showing an example of material information. FIG. 4 is a diagram showing an example of additive information. FIG. 5 is a flowchart showing an example of a material search process. FIG. 6 is a diagram (part 1) showing the relationship between two physical property values. FIG. 7 is a diagram (part 2) showing the relationship between two physical property values. FIG. 8 is a flowchart showing an example of a mix design process. FIG. 9 is an enlarged view of the vicinity of a frame. FIG. 10 is a diagram (part 1) showing the relationship between the additive addition rate and the rate of change in the physical property value of a material due to the addition of the additive. FIG. 11 is a diagram (part 2) showing the relationship between the additive addition rate and the rate of change in the physical property value of a material due to the addition of the additive. FIG. 12 is a diagram (part 2) showing an example of a result display screen. FIG. 13 is a diagram (part 2) showing an example of a result display screen. FIG. 14 is a flowchart showing an example of a mix design process according to the second embodiment. FIG. 15 is a diagram showing an example of a ranking display screen displayed in the second embodiment.
[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
[0014] Here, the terms used in this embodiment will be explained. A material is a resin or the like. A reference material is a material currently used in a product or a material that is expected to be used. A recycled material is different from the reference material and has similar properties to the reference material. An alternative material is a material that is a candidate to replace the reference material, such as a resin. An additive is something that is added to an alternative material to produce a recycled material. In other words, a recycled material is produced by adding an additive to an alternative material. In other words, in this embodiment, a recycled material is an alternative material to which an additive has been added.
[0015] [First Embodiment] <Overall Configuration of Material Search and Mix Design System Z> Figure 1 is a diagram showing an example of the overall configuration of the material search and mix design system Z. As shown in Figure 1, the material search and mix design device 1 stores material information 120a (see Figure 3) provided by, for example, a material manufacturer or a recycler as a database (material DB 120 (see Figure 2)). In addition, the material search and mix design device 1 accepts a search request for materials to generate recycled materials from an external device 2, such as a manufacturer's computer. The material search and mix design device 1 calculates a recommended ranking of alternative materials based on their similarity to a reference material by using predetermined information (e.g., physical property information 126 (see Figure 3)).
[0016] Furthermore, the material search and mix design system 1 sequentially sets alternative materials based on the recommendation ranking obtained in the material search. Then, the material search and mix design system 1 determines the appropriate type and addition rate of additives that satisfy the additive conditions based on a regression model derived by machine learning or the like. The addition rate represents the ratio of additive to the total weight when the resin material (material) and additive are mixed. The additive conditions are conditions used when selecting additives. The additive conditions will be described later. Furthermore, the material search and mix design system 1 outputs the results of alternative materials, additive types, addition rates, etc. to an external device 2 or a user interface 13 (see Figure 2).
[0017] In this way, the material search and mix design system 1 searches for alternative materials that are candidates for replacing the reference material, and additives to be added to the alternative materials.
[0018] The material is, for example, polypropylene or ABS resin, and the additive is, for example, an elastomer.
[0019] Such a material search and mix design system Z has a material search and mix design device 1 and an external device 2, and is a system that provides combinations of alternative materials, additive types, and addition rates that have desired properties. Note that the material search and mix design system Z can search for various types of materials, but in this embodiment, materials used in injection molding (for example, recycled materials such as resin materials and plastic materials, and bioplastics) will be described as an example.
[0020] The material search and blending design system Z is used when selecting suitable substitute materials, types of additives, addition rates, etc. that can be used in the manufacture of a target product. For example, the material search and blending design system Z is used when a manufacturer attempts to create another material (i.e., recycled material) from a material (reference material) that is currently being used.
[0021] Examples of using the Material Search and Mix Design System Z include the following: When an alternative material and an additive at a specified addition rate are mixed in an injection molding machine, or when an alternative material and an additive at a specified addition rate are mixed at a compound manufacturer and pelletized for supply.
[0022] Specifically, the material search and mix design system 1 accepts input of information on materials currently used in the manufacture of a product and materials (reference materials) that are expected to be used, for example. After narrowing down the alternative materials based on the characteristic values of physical properties (hereinafter referred to as physical property values) that user P (see FIG. 2) values, the system ranks the alternative materials in order of their proximity to the reference material and outputs the results as search results.
[0023] The material search and mix design system 1 also sequentially sets substitute materials based on the ranking obtained from the material search results.The material search and mix design system 1 then determines the appropriate type of additive that satisfies the additive conditions and the addition rate based on a regression model derived by machine learning or the like, and outputs the results of the substitute material, type of additive, addition rate, etc.
[0024] Such a material search and compounding design system Z can present manufacturers with combinations of alternative materials, additive types, and additive rates that have similar physical properties to the materials used in current products.
[0025] <Schematic Configuration of the Material Search and Mix Design Device 1> Figure 2 is a diagram showing an example of the configuration of the material search and mix design device 1. As shown in Figure 2, the material search and mix design device 1 is connected to an external device 2 via a communication cable or a predetermined communication network N, for example, by a network interface (NI: Network Interface Device) 12, so as to be able to communicate with each other. The communication network N is, for example, the Internet, a LAN (Local Area Network), or a WAN (Wide Area Network).
[0026] <<External Device 2>> The external device 2 is a device that sends search requests to the material search and mix design device 1 and displays the results of the search and mix design, such as substitute materials, types of additives, and addition rates. In this case, the external device 2 corresponds to a computer of a business operator, such as a manufacturer, that uses the search service provided by the material search and mix design device 1, for example.
[0027] <<Details of the Material Search and Mix Design Device 1>> The material search and mix design device 1 executes various processes by having the processor 11 read the program 110 and various information stored in the memory resource 10. Specifically, the material search and mix design device 1 executes a material search process that searches for alternative materials similar to the reference material. Furthermore, the material search and mix design device 1 executes a mix design process that determines combinations of alternative materials, additive types, and addition rates. Details of these processes will be described later.
[0028] The material search and blend design device 1 is, for example, a server computer, a cloud server, or a personal computer, and is a system including at least one of these computers.
[0029] The material search and mix design system 1 has a processor 11, a memory resource 10, and a network interface 12. The material search and mix design system 1 also has a user interface (UI: User Interface Device) 13.
[0030] The processor 11 is an arithmetic device that reads the program 110 stored in the memory resource 10 and executes processing corresponding to the program 110. Examples of the processor 11 include a microprocessor, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field Programmable Gate Array), or other semiconductor devices capable of performing calculations.
[0031] The memory resource 10 is a storage device that stores various types of information. Specifically, the memory resource 10 is configured with a non-volatile or volatile storage medium such as a random access memory (RAM) or a read-only memory (ROM). Note that the memory resource 10 may also be configured with a rewritable storage medium such as a flash memory, a hard disk, or a solid state drive (SSD), a universal serial bus (USB) memory, a memory card, a hard disk, or the like.
[0032] The network interface 12 is a communication device that communicates information with the external device 2. The network interface 12 communicates information with the external device 2 via a predetermined communication network N, such as a LAN or the Internet. Unless otherwise specified below, it is assumed that information communication between the material search and blend design system 1 and the external device 2 is performed via the network interface 12.
[0033] The user interface 13 includes an input device for inputting instructions from the user P to the material search and mix design system 1, and an output device for outputting information generated by the material search and mix design system 1. Possible input devices include, for example, a pointing device such as a mouse, a voice input device such as a microphone, a keyboard, a touch panel, etc.
[0034] In addition, examples of output devices include a display, a printer, a voice synthesizer, etc. Unless otherwise specified below, it is assumed that the operations of the user P on the material search and blend design system 1 (for example, inputting and outputting information, issuing instructions to execute processing, etc.) are performed via the user interface 13.
[0035] Furthermore, some or all of the components, functions, processing means, etc. of the material search and mix design system 1 may be realized in hardware, for example, by designing them as integrated circuits. Furthermore, some or all of the functions of the material search and mix design system 1 can be realized by software, or by a combination of software and hardware. Furthermore, the material search and mix design system 1 may use hardware with fixed circuits, or may use hardware with at least some of the circuits that are changeable.
[0036] In addition, the material search and blend design device 1 can also realize a system by having a user P (operator) execute some of the functions and processes realized by each program 110.
[0037] The program 110 executed by the material search and mix design system 1 may be stored in a non-volatile storage medium that can be read by the material search and mix design system 1. The program 110 stored in such a non-volatile storage medium may be directly read by the material search and mix design system 1, or a processor system for program distribution may read the program 110 from the medium. Then, the program 110 may be transmitted (distributed) from the processor system for program distribution to the material search and mix design system 1. Examples of non-volatile storage media include non-volatile memories described as memory resources 10, but other optical disk media may also be used.
[0038] The programs 110 stored in the memory resource 10 include a material search program 111 and a mix design program 112. The material search program 111 is a program 110 that determines whether or not there is an alternative material that satisfies predetermined search conditions for a reference material. The mix design program 112 is a program 110 that searches for possible alternative materials and additives when there is no alternative material that satisfies the search conditions for the reference material.
[0039] Furthermore, the memory resource 10 stores a material DB 120, an additive DB 130, and a recipe DB 140.
[0040] <<<Material DB 120>>> The material DB 120 is a database that stores material information 120a (see FIG. 3). The material information 120a stores information about various materials (including reference materials and alternative materials) used in the manufacture of products.
[0041] <<<Additive DB 130>>> The additive DB 130 is a database that stores additive information 130a (see FIG. 4). The additive information 130a includes information 134 (see FIG. 4) on the rate of change in physical properties due to each additive, etc.
[0042] <<<<Recipe DB 140>>> The recipe DB 140 stores the search results of the material search and blend design system 1. Specifically, the recipe DB 140 stores identification information 121 of alternative materials (see FIG. 3), identification information 131 of additives (see FIG. 4), addition rates, etc., derived by the program 110.
[0043] <<Details of Material Information 120a>> FIG. 3 is a diagram showing an example of the material information 120a.
[0044] As shown in FIG. 3, the material information 120a includes identification information 121, material name and type 122, model number 123, manufacturer name 124, lot number 125, physical property information 126, environmental load information 127, and cost information 128, all of which are registered in association with each other.
[0045] The identification information 121 is information for uniquely identifying a material registered in each record of the material information 120a.
[0046] The name and type 122 is information indicating the name and type of material (for example, type of resin material or plastic material).
[0047] The model number 123, manufacturer name 124, and lot number 125 are information indicating the model number of the material, the name of the manufacturer of the material, and the lot number of the material, respectively.
[0048] The physical property information 126 is information about the characteristic values (physical property values) of the physical properties of each material, and physical properties such as mechanical properties and thermal properties and their values (physical property values) are registered. Here, mechanical properties include, for example, elastic modulus, tensile strength, and impact properties. Thermal properties include, for example, crystallization temperature, melting temperature, and heat distortion temperature. Note that these physical property information 126 are just examples, and in addition to the above examples, various types of physical properties and their values are registered in the physical property information 126.
[0049] The environmental load information 127 is information about the load on the environment when processing the material. An example of the environmental load information 127 is the CO2 required to heat the material. 2 The amount of CO 2 There are emissions, etc.
[0050] The cost information 128 may be, for example, 3 Price per unit (unit price), etc.
[0051] Note that even if the materials are of the same type, different model numbers 123 and grades are assigned depending on the material manufacturer, and the physical properties and other values are also different. Therefore, in the material information 120a, materials of the same type but with different model numbers 123 and grades are registered as different types of materials.
[0052] <<Details of Additive Information 130a>> FIG. 4 is a diagram showing an example of the additive information 130a.
[0053] As shown in FIG. 4, the additive information 130a includes identification information 131, additive name and type 132, manufacturer name 133, property change rate information 134, prediction model information 135, and cost information 136, all of which are registered in association with each other.
[0054] The identification information 131 is information that uniquely identifies the additive.
[0055] The name and type 132 and the manufacturer name 133 are information indicating the name and type of the additive and the manufacturer of the additive, respectively.
[0056] The physical property change rate information 134 is numerical information relating to the rate of change of the physical property value of the material when an additive is added to the material. Specifically, the physical property change rate information 134 is the rate of change (unit: %) of the physical property value relative to the additive rate (unit: %). Examples of the physical property change rate include the modulus of elasticity, tensile strength, and bending strength.
[0057] The prediction model information 135 is information on a prediction formula that indicates the relationship between the additive rate determined by machine learning or the like and the rate of change in the physical properties of the material, and the function of the prediction formula and each coefficient are registered. The prediction model information 135 is calculated in advance by experiments or the like. The machine learning is, for example, linear regression. Such prediction model information 135 is the physical property change characteristics of the additive.
[0058] The cost information 136 may be, for example, 3 Price per unit (unit price), etc.
[0059] <<Flowchart>> Figure 5 is a flowchart showing an example of material search processing. When the material search and mix design system 1 receives a request from the external device 2, the processor 11 loads the material search program 111. The processor 11 then executes the loaded material search program 111, thereby performing the processing shown in Figure 5. As a result, the processor 11 operates as a material search unit. Figures 2 and 3 will be referenced as appropriate.
[0060] 5 starts, the processor 11 receives input of reference material information from the external device 2 (S101). Specifically, the processor 11 receives input of, for example, the name and type of the reference material from the external device 2 as the reference material information. The reference material information is input by the user P operating the external device 2. In step S101, the processor 11 may also receive identification information of the reference material. Note that the input in step S101 may be received via the user interface 18.
[0061] Next, the processor 11 acquires the physical property value information 126 and the like of the reference material that has been input (S102). Specifically, the processor 11 acquires a record of the material information 120a that corresponds to the reference material from the material information 120a based on the name and type of the input reference material. Furthermore, the processor 11 acquires the corresponding physical property value information 126 from the material information 120a based on the identification information 121 in the record of the material information 120a of the acquired reference material.
[0062] Next, the processor 11 accepts the selection of a physical property evaluation item and the input of an evaluation physical property value (S103). The physical property evaluation item is, for example, a mechanical property such as elastic modulus or a thermal property such as crystallization temperature in the material information 120a. In step S103, the processor 11 accepts the selection of a physical property evaluation item that the user P considers important from among the plurality of physical property evaluation items corresponding to the physical property value information 126 of the reference material. For example, if the physical property value information 126 of the reference material includes the elastic modulus, tensile strength, impact strength, melting temperature, etc., the processor 11 accepts the selection of a physical property evaluation item that the user P considers important from among these (e.g., elastic modulus and impact strength).
[0063] In step S103, the processor 11 receives an input of an evaluation property value for the selected evaluation item. For example, if the elastic modulus and impact strength are selected as the evaluation items, the processor 11 receives the numerical range of the elastic modulus and impact strength desired (accepted) by the user P as the evaluation property value.
[0064] That is, in step S103, it is set which physical property evaluation items and what numerical ranges are to be used to search for substitute materials.
[0065] Next, the processor 11 sets search conditions for the alternative material (S104). Specifically, the processor 11 sets the physical property evaluation items and evaluation physical property values input in step S103 as search conditions for the alternative material. Note that the search conditions may also include the type of reference material. By including the type of reference material in the search conditions, the processor 11 can further narrow down the search range, thereby reducing the processing load on the processor 11.
[0066] Next, the processor 11 executes a search for an alternative material and determines whether or not there is an alternative material (material) that satisfies the search conditions (S105). At this time, the processor 11 searches the material information 120a based on the search conditions.
[0067] If there is an alternative material that satisfies the search criteria (S105 → Yes), the processor 11 outputs the search results (S106). Note that if there are multiple alternative materials that satisfy the search criteria, the processor 11 outputs all of the searched alternative materials. The alternative materials that satisfy the search criteria are appropriately referred to as candidate materials.
[0068] If there is no alternative material (candidate material) that satisfies the search criteria in step S105 (S105→No), the processor 11 executes the mix design process (S200). The mix design process will be described later with reference to Figures 7 to 9B.
[0069] Step S105 in FIG. 5 will be described with reference to FIGS. 6A and 6B.
[0070] 6A and 6B are diagrams showing the relationship between two physical property values (physical property value "A" and physical property value "B" in the example shown in FIGS. 6A and 6B). As shown in FIGS. 6A and 6B, coordinates in which each coordinate axis is configured as a different physical property value are referred to as a physical property coordinate space 300. In the example shown in FIGS. 6A and 6B, the physical property coordinate space 300 is configured with two coordinate axes (i.e., a two-dimensional coordinate space), but it may also be configured with one coordinate axis or three or more coordinate axes.
[0071] 6A and 6B, reference numeral 301 indicates the physical property information of the reference material, and reference numeral 302 indicates the physical property information of the alternative material. Furthermore, a box C indicates the search conditions. The reference material (reference numeral 301) is located at the center of the box C indicating the search conditions. Each of the reference numerals 302 corresponds to a material stored in the material information 120a.
[0072] When the reference material is stored in the material information 120a, the code 301 indicating the reference material is plotted according to the physical property value information 126 corresponding to the reference material. When the reference material is not stored in the material information 120a, the code 301 indicating the reference material is plotted by manual input by the user P, or plotted according to the physical property values of the reference material that are manually input.
[0073] 6A shows a case where there are alternative materials (candidate materials) that satisfy the search criteria. In FIG. 6A, there are multiple candidate materials in the box C that indicates the search criteria (reference numeral 302a). In this case, the processor 11 determines "Yes" in step S105.
[0074] Figure 6B shows a case where no candidate material satisfies the search criteria. In Figure 6B, no candidate material (reference numeral 302) exists within box C, which indicates the search criteria. In such a case, processor 11 determines "No" in step S105. In other words, depending on the search criteria, the result may be that a candidate material exists, as shown in Figure 6A, or that no candidate material exists, as shown in Figure 6B. Note that, since changing the properties of the candidate material also changes the properties of the recycled material generated, the search criteria cannot, in principle, be changed.
[0075] Through the process shown in FIG. 5, the processor 11 searches for materials that satisfy predetermined search conditions with respect to the reference material.
[0076] <<Mixture Design Processing>> Figure 7 is a flowchart showing an example of the mix design processing, which is a mix design method. In the processing shown in Figure 6, when the material search and mix design system 1 receives a request, the processor 11 reads the mix design program 112. Then, the processor 11 executes the mix design program 112, thereby performing the processing shown in Figure 7. As a result, the processor 11 operates as a mix design unit and an output processing unit. Note that Figures 2 to 4 will be referred to as appropriate.
[0077] It should be noted that steps S201 to S207 and S211 in FIG. 7 correspond to the mix design step, and steps S212 to S213 correspond to the output processing step.
[0078] First, processor 11 selects an alternative material based on the degree of similarity between the physical properties of the reference material and the alternative material (S201). The alternative material selected in step S201 is referred to as the base material. Specifically, processor 11 calculates the degree of similarity between the physical properties of the reference material and the alternative material, and sorts the identification numbers of the alternative materials in descending order of similarity. Processor 11 then selects the alternative material with the highest degree of similarity (most similar) to the reference material as the base material for mix design. Here, the degree of similarity is, for example, the Euclidean distance 311 ( FIG. 8 ) between the reference material and the alternative material for the physical properties specified in the search criteria. The Euclidean distance 311 will be described later.
[0079] Step S201 in FIG. 7 will be described with reference to FIG.
[0080] FIG. 8 is an enlarged view of the vicinity of the frame C shown in FIG. 6B.
[0081] As described above, the similarity is defined by the Euclidean distance 311. Here, the Euclidean distance 311 is a distance defined in the physical property coordinate space 300.
[0082] 8, in step S201, the processor 11 selects the alternative material having the shortest Euclidean distance 311 to the physical property information (reference numeral 301) of the reference material. In the example shown in FIG. 8, the alternative material indicated by reference numeral 302b is selected as the base material. Reference numeral 302c will be described later.
[0083] In other words, if there is no material that satisfies the search conditions (S105→No in FIG. 5), the processor 11 selects an alternative material for the reference material based on the similarity indicating the degree of similarity to the reference material. Specifically, the processor 11 selects an alternative material that is similar to the reference material based on the Euclidean distance 311 between the physical property information of the alternative material (reference symbol 302) and the physical property information of the reference material (reference symbol 301) in the physical property coordinate space 300.
[0084] In this embodiment, the Euclidean distance 311 in the physical coordinate space 300 is used as the similarity between two materials, but this is not limiting. For example, Manhattan distance or Chebyshev distance may be used as the similarity. Alternatively, any method that can measure the similarity between two materials is not limited to distance.
[0085] Returning to the explanation of Fig. 7, the processor 11 next calculates the target value range (S202). In step S202, the processor 11 calculates the upper and lower limit values of the search conditions set in step S104 of Fig. 5 and the property change rate of the base material, thereby expressing the target value range of the mix design process as the property change rate. Through this process, the processor 11 calculates the range of the property change rate due to the additive that satisfies the additive conditions.
[0086] Next, the processor 11 selects an additive from the additive information 130a (S203). The additive is selected, for example, in ascending order of identification number. Alternatively, frequently combined combinations of alternative materials and additives may be learned by machine learning, and the selection in step S203 may be performed based on the learning results. In this way, additive selection can be performed efficiently.
[0087] Next, the processor 11 refers to the record of the additive information 130a having the identification number selected in step S203, and reads the numerical value of the property change rate information 134 and the prediction model information 135 from the additive information 130a (S204).
[0088] Next, the processor 11 calculates the ranges of the additive rates 431 and 432 (see FIGS. 9A and 9B) that correspond to the property change characteristics of the additive (S205: additive rate range calculation step). The additive rate ranges 431 and 432 will be described later.
[0089] Next, the processor 11 determines whether the additive condition for the selected additive is satisfied (S206). The additive condition is the target value range calculated in step S202.
[0090] The process of step S206 will be described with reference to FIGS. 9A and 9B.
[0091] 9A and 9B are diagrams showing the relationship between the addition rate of an additive and the rate of change in the physical property value of a material due to the addition of the additive (rate of change in physical property).
[0092] In the examples shown in Figures 9A and 9B, the vertical axis represents the rate of change in the physical property value (physical property change rate), and the horizontal axis represents the addition rate. The physical property is the physical property of the alternative material (base material) selected in step S201 of Figure 7. The examples shown in Figures 9A and 9B are based on the numerical values of the physical property change rate information 134 in the additive information 130a and the information of the prediction model information 135. Note that Figure 9A shows the relationship between the addition rate and the physical property change rate for the physical property "A," and Figure 9B shows the relationship between the addition rate and the physical property change rate for the physical property "B." Note that the physical property "A" is the physical property corresponding to the physical property value "A" in Figures 6A and 6B. Similarly, the physical property "B" is the physical property corresponding to the physical property value "B" in Figures 6A and 6B.
[0093] For example, property "A" is the mechanical property described above, and property "B" is the thermal property described above.
[0094] 9A and 9B, plot 401 indicates, for example, experimental values. A straight line 402, which is a property change characteristic, indicates a regression line (a result of machine learning) for the experimental values (plot 401), and indicates the property change characteristic of the material. The straight line 402 is indicated by the prediction model information 135 shown in FIG. 4. In this way, the property change characteristic of the additive is generated by machine learning based on the addition rate of the additive and the property change rate.
[0095] 9A and 9B, additive condition ranges 421 and 422 indicate target value ranges of the property change rates calculated in step 202. The additive condition ranges 421 and 422 are ranges of the property change rates due to additives that satisfy the additive conditions, and are calculated in step S205 in FIG.
[0096] For example, if the additive is an elastomer, the additive tends to improve impact strength, but conversely, tends to decrease elastic modulus. In other words, as shown in Figures 9A and 9B, the rate of change in physical properties relative to the additive rate may have a mutually contradictory relationship depending on the physical property (although there may be no mutually contradictory relationship). Therefore, when multiple physical properties are selected, the processor 11 must search for an additive and additive rate that satisfies the additive conditions, taking into account the mutually contradictory relationships between the respective physical properties.
[0097] As described above, in step S206, the processor 11 determines whether or not there is an additive and an additive rate that satisfies the additive conditions. Specifically, in this process, the processor 11 determines whether or not there is an additive rate that satisfies the target value range of the property change rate (additive condition ranges 421, 422) shown in FIGS. 9A and 9B . More specifically, the processor 11 determines whether or not there is an additive rate range that overlaps the additive rate range 431 shown in FIG. 9A and the additive rate range 432 shown in FIG. 9B . The additive rate range 431 shown in FIG. 9A and the additive rate range 432 shown in FIG. 9B are additive rate ranges that satisfy the target value range of the property change rate (additive condition ranges 421, 422) determined in step 202. The additive rate ranges 431 and 432 are the ranges of the property change rate due to the additive that satisfy the additive conditions and the ranges of additive rates that correspond to the additive property change characteristics.
[0098] That is, in step S206, the processor 11 calculates the addition rate ranges 431 and 432.
[0099] Returning to the explanation of Fig. 7 , if the additive condition is satisfied in step S206 (205 → Yes), the processor 11 selects an additive rate that satisfies the additive rate ranges 431, 432 shown in Fig. 9A and 9B (S211: additive rate selection step). That is, in step S211, if the calculated additive rate ranges 431, 432 for multiple physical properties have overlapping ranges, the processor 11 selects the overlapping range as the additive additive rate.
[0100] Then, the processor 11 stores information about the base material and the additives in the recipe DB 140 (S212). Specifically, the processor 11 stores the base material identification information 121 (see FIG. 3), the additive identification information 131 (see FIG. 4), the addition rate selected in step S211, and the like in the recipe DB 140. The base material identification information 121 to be stored is the identification information 121 of the material selected in step S201. The additive identification information 131 to be stored is the identification information 131 of the additive selected in step S203. The addition rate to be stored is the range of addition rates that overlaps between the addition rate range 431 in FIG. 9A and the addition rate range 432 in FIG. 9B.
[0101] Note that, instead of the base material identification information 121 and the additive identification information 131, the names of the base material and the additives may be stored in the recipe DB 140.
[0102] Next, the processor 11 outputs the search results (S213). Specifically, if an alternative material (candidate material) that satisfies the search conditions exists, the processor 11 outputs (transmits) information about the candidate material and information about additives that satisfy the additive conditions to the external device 2 operated by the user P. If no candidate material exists, the processor 11 outputs (transmits) an error message and the material name, additive name, and additive rate of the base material stored in the additive information 130a to the external device 2 operated by the user P. The output may be to the user interface 18. In this case, the processor 11 may output materials whose Euclidean distance 311 (see FIG. 8) to the reference material (reference numeral 301 in FIGS. 6A and 6B), defined in the physical property coordinate space 300 shown in FIG. 6A or 6B, is equal to or less than a predetermined value.
[0103] If the additive conditions are not satisfied in step S206 (S206→No), the processor 11 determines whether there are any uncalculated additives from the identification numbers (S207).
[0104] If there is an uncalculated additive in step S207 (S207→Yes), the processor 11 returns the process to step S203. Then, the processor 11 reads the next identification number from the additive information 130a and repeats the process from step S204 onwards.
[0105] If there are no uncalculated additives in step S207 (S207→No), the processor 11 returns to step S201. Then, the processor 11 selects the alternative material with the next highest similarity as the base material, and repeats the processes from step S202 onwards. The alternative material with the next highest similarity is the alternative material indicated by reference numeral 302c in FIG. 8, which has the next shortest Euclidean distance 311 from the reference material (reference numeral 301) after reference numeral 302b.
[0106] Similarly, the base materials are selected in descending order of similarity to the reference material (in ascending order of Euclidean distance 311). Note that the base material whose Euclidean distance 311 to the reference material is equal to or less than a predetermined distance may be selected. In other words, a material whose Euclidean distance 311 to the reference material is greater than a predetermined distance may not be selected as the base material.
[0107] After outputting the search results in step S213, the processor 11 ends the processing of the flowchart shown in FIG.
[0108] 7, processor 11 selects an additive to be added to the alternative material. In addition, in steps S212 and S213, processor 11 outputs the combination of the alternative material and the additive, as well as the addition rate that falls within the range where addition rate ranges 431 and 432 overlap.
[0109] <<Results Display Screen 500A>> Fig. 10A is a diagram showing an example of a results display screen 500A output in step S213. The results display screen 500A shown in Fig. 10A is a screen displayed for, for example, a material manufacturer.
[0110] The result display screen 500A includes a reference material input field 501a, a search condition input field 501b, a base material display area 502, and an additive display area 503.
[0111] The reference material input field 501a is a field where reference material information (such as the name and type of the reference material) received in step S101 of FIG. 5 is input.
[0112] The search condition input field 501b is a field for inputting the physical property evaluation items and evaluation physical property values input in step S103 of Fig. 5. As in the example shown in Fig. 10A, information on multiple physical properties is input into the search condition input field 501b. Note that in the example shown in Fig. 10A, "physical property A" and "physical property B" correspond to the physical property evaluation items, and "***" indicating the value of each physical property corresponds to the evaluation physical property value.
[0113] The base material display area 502 and the additive display area 503 display the names, addition rates, etc. of the base material and additives searched for by the processes shown in Figures 5 and 7. The addition rates correspond to the overlapping ranges of the addition rate range 431 according to the example shown in Figure 9A and the addition rate range 432 according to the example shown in Figure 9B.
[0114] 10A, the result display screen 500A displays an environmental load information display area 504, such as costs and greenhouse gas reduction effects, and a cost display area 505. Information regarding the environmental load of the selected alternative material and additive is output in the environmental load information display area 504. Information regarding the cost of the selected alternative material and additive is output in the cost display area 505.
[0115] The environmental impact information display area 504 and the cost display area 505 are based on the environmental impact information 127, cost information 128, etc., of the material information 120a. This allows user P to select a material configuration that incorporates suitable materials and additives by considering a combination of base materials, additive types, additive rates, etc., with physical properties similar to those of the material (reference material) used in the current product, as well as cost and environmental impact. The cost refers to the cost incurred in producing a recycled material from the reference material using the base material and additives. The cost may be calculated as a cost per unit amount. The cost is calculated based on the cost information 128 in FIG. 3 and the cost information 136 in FIG. 4. <<Result Display Screen 500B>> FIG. 10B is a diagram illustrating an example of the result display screen 500B output in step S213. The result display screen 500B shown in FIG. 10B is a screen displayed, for example, to a product manufacturer.
[0116] In the example of the result display screen 500B shown in Fig. 10B, the environmental load information display area 504 and the cost display area 505 displayed in Fig. 10A are omitted. The other configurations are the same as those of the result display screen 500A shown in Fig. 10A.
[0117] 10A and 10B, a result display screen 500A is displayed for the material manufacturer, and a result display screen 500B is displayed for the manufacturing manufacturer. In this way, necessary and appropriate information can be displayed for each manufacturer.
[0118] The material search process and mix design process have been described above.
[0119] The material search and mix design system Z shown in this embodiment can present a user P (see FIG. 2) (such as a manufacturer or material manufacturer) with combinations of base materials, additive types, and additive rates that have similar physical properties to the materials used in the current product (reference material). In other words, this embodiment can select recycled materials with similar material properties to the reference material based on the results of the material search, and provide a material configuration with desired properties by blending appropriate additives. As a result, this embodiment can efficiently search for alternative materials and additives to be added to the alternative materials.
[0120] In this embodiment, the alternative material (base material) can be quantitatively selected by selecting the alternative material based on the similarity with the input reference material. In particular, by using the Euclidean distance 311 as shown in FIG. 8 as the similarity, the alternative material can be quantitatively selected.
[0121] 9A and 9B , in this embodiment, a base material is selected in which there is an overlapping region between the additive rate ranges 431 and 432. This makes it possible to select a combination of base material, additive, and additive rate even when the physical property change characteristics of the additive in the alternative material are contradictory, as shown in FIGS.
[0122] In this embodiment, the additive property change characteristics are generated by a regression line (line 402), that is, machine learning, as shown in Figures 9A and 9B. In this way, the actual additive property change characteristics can be taken into consideration.
[0123] Furthermore, as shown in FIG. 10A, an environmental impact information display area 504 and a cost display area 505 are displayed for the searched base material and additives, allowing user P to easily conduct research, including information on cost and environmental impact.
[0124] 9A and 9B, it is also possible to consider in advance the opposing effects of additives on each physical property. That is, the processor 11 may add the tendency of each physical property and the prediction model (straight line 402) of the additive information 130a to the search conditions as factors for narrowing down the alternative materials.
[0125] Second Embodiment Next, a second embodiment of the present invention will be described with reference to Figures 11 and 12. In the second embodiment, a plurality of combinations of base materials and additives are displayed in a ranking format.
[0126] <<Mixture Design Processing>> Figure 11 is a flowchart showing an example of the mix design processing according to the second embodiment. In Figure 11, the same processes as in Figure 7 are assigned the same step numbers and their explanations will be omitted. Figure 2 will be referenced as appropriate.
[0127] First, the processor 11 selects multiple alternative materials based on the similarity between the physical property values of the reference material and the physical property values of the alternative materials (S201a). In step S201a, the processor 11 selects all alternative materials whose Euclidean distance 311 (see FIG. 8) is equal to or less than a predetermined value. The predetermined value is set in advance by the user P. Each of the multiple alternative materials selected in step S201a is referred to as a base material.
[0128] Then, when "No" is determined in step S207 or step S211 is performed, the processor 11 determines whether the processing of steps S202 to S207 and S211 has been completed for all base materials selected in step S201a (S221).
[0129] If the processing of steps S202 to S207 and S211 has not been completed for all base materials (S221→No), the processor 11 returns the processing to step S202.
[0130] If the processing of steps S202 to S207 and S211 has been completed for all base materials (S221→Yes), the processor 11 proceeds to step S212.
[0131] <<Ranking Display Screen 600>> FIG. 12 is a diagram showing an example of a ranking display screen 600 displayed in the second embodiment.
[0132] The ranking display screen 600 is composed of a ranking condition display area 601, a pull-down menu 602, and a ranking display area 611. The ranking display screen 600 is output (displayed) on the external device 2 or the user interface 13.
[0133] User P (see FIG. 2 ) can switch the ranking conditions using a pull-down menu 602. The ranking conditions can be selected from "cost" and "environmental load information." In the example shown in FIG. 12 , "cost" is selected as the ranking condition. The ranking condition selected using the pull-down menu 602 is displayed in a ranking condition display area 601.
[0134] The ranking display area 611 displays the selected combinations of alternative materials and additives in a predetermined ranking format. This display allows the user P (especially the manufacturer) to consider which combination of base material and additive is best in terms of cost and environmental impact. Incidentally, the number "1" in the ranking display area 611 indicates the highest ranking, and is the most favorable combination among the three displayed combinations.
[0135] User P can select a combination of base material and additive displayed in the ranking display area 611. Then, result display screens 500A and 500B (see FIGS. 10A and 10B) corresponding to the selected combination of base material and additive are displayed. In this way, user P can recognize detailed information about the combination of base material and additive displayed in the ranking.
[0136] 11, there may be a case where a combination of base material and additive that satisfies step S206 is not found among the base materials selected in step S201a. In such a case, a message is displayed in the ranking display area 611 indicating that there is no combination of base material and additive that satisfies the search conditions or additive conditions. When such a message is displayed, user P considers changing the search conditions or the predetermined values used in step S201a.
[0137] Furthermore, this embodiment is not limited to the above, and various modifications are possible. For example, in the above-described embodiment, it is assumed that the material DB 120 and the additive DB 130 are stored in advance in the memory resource 10. However, these databases may be stored in another computer (e.g., a cloud server). In other words, in this case, the material search and blending design system Z includes a computer (cloud server) that stores the database. Alternatively, the material search and blending design system Z may be configured to have a function of searching and collecting, in advance or as needed, all or part of the information and data required for information processing in this embodiment from various information and data scattered on the Internet.
[0138] In this case, the material search / mixing design device 1 searches for and acquires the target material information 120a (see Figure 3) and additive information 130a (see Figure 4) from the database of the computer (cloud server) when executing the material search and mix design process.
[0139] By using the material search and blending design system Z with such a configuration, it is possible to select a material configuration with more appropriate materials and additives added.
[0140] Furthermore, the present invention is not limited to the above-described embodiments and modifications, and includes various other embodiments and modifications. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.
[0141] For example, in this embodiment, resins such as plastics are searched for, but aluminum or iron may also be used as the material.
[0142] In addition, in the above explanation, the control lines and information lines are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it can be considered that almost all components are interconnected.
[0143] 1 Material search and mix design device 2 External device 10 Memory resource 11 Processor (material search section, mix design section, output processing section) 13 User interface 110 Program 111 Material search program 112 Mix design program 120 Material DB 120a Material information 121 Identification information 122 Name and type 126 Physical property value information 127 Environmental load information 128 Cost information 130 Additive DB (stores information about additives) 130a Additive information (stores information about additives) 131 Identification information 132 Name and type 134 Physical property change rate information 135 Prediction model information (physical property change characteristics) 136 Cost information 140 Recipe DB 300 Physical property coordinate space 301 Sign (physical property information of reference material) 302 Sign (physical property information of alternative material) 302a to 302c Symbols 311 Euclidean distance (similarity) 402 Straight line (physical property change characteristics) 421 Additive condition range 422 Additive condition range 431 Addition rate range 432 Addition rate range 500A, 500B Result display screen 501a Reference material input field 501b Search condition input field 502 Base material display area 503 Additive display area 504 Environmental load information display area 505 Cost display area 600 Ranking display screen 601 Ranking condition display area 602 Pull-down menu 611 Ranking display area C Frame P User Z Material search and mix design system S201 Select alternative material based on similarity (mix design step) S202 Calculate target value range (mix design step) S203 Select additive (mix design step) S204 Reading of numerical values of property change rate information and prediction model information (mixing design step) S205 Calculation of addition rate range (mixing design step, addition rate range calculation step) S206 Determination of whether additive conditions are met (mixing design step) S207 Determination of whether there are any uncalculated additives (mixing design step) S211 Selection of addition rate (mixing design step, addition rate selection step) S212 Save information on base material and additives in recipe DB (output processing step) S213 Output of search results (output processing step)
Claims
1. A material search and mix design device comprising: a mix design unit that selects additives to be added to alternative materials, which are candidate materials for replacing a reference material, which is a current material used in a product or a material expected to be used, and an output processing unit that outputs a combination of the alternative materials selected by the mix design unit and the additives, wherein the mix design unit calculates an addition rate range, which is a range of addition rates corresponding to the property change characteristics of the additive, based on the range of property change rates due to the additive that satisfies the additive conditions, and when the calculated addition rate ranges for a plurality of physical properties have an overlapping range, selects the overlapping range as the addition rate of the additive, and the output processing unit outputs the addition rate that falls within the overlapping range of the addition rate ranges in addition to the combination of the alternative material and the additive.
2. The material search and blend design device according to claim 1, characterized in that the property change characteristics of the additive are generated by machine learning based on the additive rate and the property change rate of the additive.
3. The material search / mix design device of claim 1, further comprising a material search unit which searches for materials that satisfy specified search conditions for the reference material, and wherein if the material that satisfies the search conditions is not present in the material search unit, the mix design unit selects an alternative material for the reference material based on a similarity indicating the degree of similarity to the reference material.
4. The material search and mix design device described in claim 3, characterized in that the mix design unit selects the alternative material that is similar to the reference material based on the Euclidean distance between the physical property information of the alternative material and the physical property information of the reference material in the physical property coordinate space.
5. The material search and blend design device according to claim 1, characterized in that the output processing unit outputs information regarding the environmental impact of the selected alternative material and the additive.
6. The material search and blend design device according to claim 1, characterized in that the output processing unit outputs information relating to the costs of the selected alternative material and the additive.
7. The material search and blend design device according to claim 1, characterized in that the output processing unit outputs the selected combinations of the alternative materials and additives in a predetermined ranking format.
8. A material search / mix design device that searches for alternative materials that are candidate substitutes for a reference material that is a current material used in a product or a material expected to be used, and additives to be added to the alternative materials, executes: a mix design step of selecting the additives for the alternative materials; and an output processing step of outputting a combination of the alternative materials selected by the mix design step and the additives, wherein the material search / mix design device executes: in the mix design step: an addition rate range calculation step of calculating an addition rate range that is an addition rate range corresponding to the property change characteristics of the additive, based on the range of property change rates due to the additive that satisfies the additive conditions; and an addition rate selection step of selecting the overlapping range as the addition rate of the additive, when the calculated addition rate ranges for a plurality of physical properties have an overlapping range, and outputs the addition rate that falls within the overlapping range of the addition rate ranges in addition to the combination of the alternative materials and the additives, in the output processing step.
Citation Information
Patent Citations
Resin material ordering-delivery support system and ordering service
JP2003203172A
Design support apparatus and design support method
JP2019086817A
Analysis system, analysis device, and analysis method
JP2022101852A