System and program

Abstract

To provide a system and a program allowing information processing of designing a second structure on the basis of a first structure to be performed in an industrially advantageous manner.SOLUTION: A system is to design a second structure on the basis of a first structure, and comprises means that designs two or more types of the second structure having different characteristics by using a use environment of and / or an operation condition for the second structure. The characteristics include information indicating physical characteristics. The system further includes means that calculates trade-off information corresponding to the second structure. The trade-off information includes cost information. The system includes evaluation means that, upon receiving information on the first structure and the use environment and / or the operation condition from a user, evaluates the characteristics of the second structure.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a system and a computer program that are useful for designing structures such as motors. [Background technology]

[0002] In recent years, Interior Permanent Magnet Synchronous Motors (IPMSMs), which boast high output, high efficiency, and high reliability, have been widely adopted as motors for driving electric vehicles and industrial robots. The optimal shape design of an IPMSM requires repeated finite element analysis (FEA), which poses a challenge in terms of long calculation times. Surrogate models utilizing machine learning and deep learning have attracted attention as a way to solve this issue, and can achieve optimal design in a short period of time without using finite element analysis.

[0003] Non-Patent Document 1 discloses an automated design system for interior permanent magnet synchronous motors. When automatically designing a structure such as a motor, it is necessary to be able to consider the energy conversion efficiency under various operating conditions. This automated design system uses a deep learning model that predicts the iron loss of the motor, making it possible to evaluate the motor's efficiency map in a shorter time.

[0004] Furthermore, the automatic design system in Non-Patent Document 2 proposes an automatic design system that further varies the magnet temperature and magnet material from Non-Patent Document 1, but in order to achieve an optimal design in a state closer to the actual operating environment, there are still issues to be resolved from the perspective of design freedom.

[0005] Therefore, in order to realize an optimal design in a state closer to the actual operating environment, an automatic design system is required that can freely set any parameters related to the usage environment and operating conditions. [Prior art documents] [Non-patent literature]

[0006] [Non-Patent Document 1] Y. Shimizu, “Automatic Design System with Generative Adversarial Network and Vision Transformer for Efficiency Optimization of Interior Permanent Magnet Synchronous Motor,” IEEE Trans. Ind. Electron., early access. [Non-patent document 2] Yuuki Shimizu, Kan Akatsu, “Automatic Design System for IPMSM with Variable Magnet Characteristics Using Deep Learning”, 2023 Industrial Applications Conference of the Institute of Electrical Engineers of Japan, 2023, 3-50, 2023-08-24 Summary of the Invention [Problem to be solved by the invention]

[0007] An object of the present invention is to provide a system and a program that can industrially advantageously perform information processing for designing a second structure based on a first structure. [Means for solving the problem]

[0008] As a result of intensive research to achieve the above-mentioned object, the inventors discovered that a system for designing a second structure based on a first structure, which system is characterized by having a means for designing two or more types of the second structure using the usage environment and / or operating conditions of the second structure, can freely set any parameters related to the usage environment and operating conditions in order to achieve an optimal design in a state closer to the actual operating environment, and found that such a system can solve the above-mentioned conventional problems in one fell swoop. Furthermore, after obtaining the above findings, the present inventors conducted further studies and completed the present invention.

[0009] That is, the present invention relates to the following inventions. [1] A system for designing a second structure based on a first structure, characterized in that the system includes a means for designing two or more types of the second structure using the usage environment and / or operating conditions of the second structure. [2] The system according to [1], wherein the structure is an electrical device. [3] The system according to [2], wherein the structure is a driver. [4] The system according to [1], wherein the usage environment includes a temperature range, a humidity range, a degree of contamination, or an atmospheric pressure range. [5] The system according to [3], wherein the operating conditions include a maximum current, a maximum voltage, or a maximum speed. [6] The system according to [1], wherein the design means further designs two or more types of the second structure using the required specifications. [7] The system according to [1], wherein the design means designs two or more types of the second structure having different characteristics. [8] The system according to [7], wherein the characteristics include information indicating physical characteristics. [9] The system according to [1], further comprising means for calculating trade-off information corresponding to the second structure.

[10] The system according to [9], wherein the trade-off information includes cost information.

[11] The system described in [1] includes an evaluation means for evaluating the characteristics of the second structure upon receiving the first structure information and the usage environment and / or the operating conditions from a user.

[12] The system described in

[11] learns the relationship between the structure information of the structure, the usage environment and / or the operating conditions, and the characteristics, predicts the characteristics from the structure information of the structure of the user, the usage environment and / or the operating conditions through the learning, and outputs the predicted evaluation value to the user.

[13] A program that causes a system for designing two or more types of second structures based on a first structure to function as a means for evaluating the characteristics of the second structure when it receives information about the first structure and the usage environment and / or the operating conditions.

[14] A program according to

[13] , which learns the relationship between the structure information of the structure, the usage environment and / or the operating conditions and the characteristics, predicts the characteristics from the structure information of the structure of the user, the usage environment and / or the operating conditions through the learning, and outputs the predicted evaluation value to the user. [Effects of the Invention]

[0010] The system and program of the present invention can industrially advantageously perform information processing for designing a second structure based on a first structure. [Brief explanation of the drawings]

[0011] [Figure 1] Figure 1 is a diagram of the system configuration. [Figure 2] FIG. 2 is a perspective view of the motor. [Figure 3] FIG. 3 is a diagram showing the topology of one pole of the rotor. [Figure 4] FIG. 4 is a schematic diagram of a preferred embodiment of the system of the present invention. [Figure 5] FIG. 5 is a diagram showing a preferred exchange of information between the user terminal 211 and the information processing device 212 of FIG. [Figure 6] FIG. 6 is a flowchart showing the processing procedure of the design system. [Figure 7] FIG. 7 shows an example of a user input and an example of a system output. [Figure 8] FIG. 8 shows an example of a user input and an example of a system output. [Figure 9] FIG. 9 is a diagram illustrating an example of trade-off information between cost and loss. [Figure 10] FIG. 10 is a diagram illustrating an evaluator. DETAILED DESCRIPTION OF THE INVENTION

[0012] The present invention is a system for designing a second structure based on a first structure, characterized in that it includes a means for designing two or more types of the second structure using the usage environment and / or operating conditions of the second structure.

[0013] The use environment and / or operating conditions used in the present invention are not particularly limited as long as they do not impede the object of the present invention, and may be known use environments and / or operating conditions. In the present invention, the use environment preferably includes a temperature range, a humidity range, a degree of contamination, or a pressure range. According to such a preferred embodiment, characteristic information of the constituent material of the second structure that depends on various use environments can be effectively utilized in design. In the present invention, the operating conditions preferably include a maximum current, a maximum voltage, or a maximum speed. According to such a preferred embodiment, the operating characteristics of the second structure that depend on various operating conditions can be effectively utilized in design.

[0014] The structure used in the present invention is not particularly limited as long as it does not impede the objectives of the present invention, and may be a known structure. Examples of such structures include motors, piezoelectric actuators, RFID (Radio Frequency Identification), cables, high-frequency preheaters, capacitors, magnetic heads, magnetic shields, magnetic gears, magnets, circuit breakers, sensors, electrical heating devices, electrolytic plating, electromagnetic molding, electromagnetic retarders, electromagnetic relays, transformers / reactors, bus bars, generators, heaters, bearings, magnetic couplings, induction heating devices, induction machines, linear solenoids / linear actuators, and wireless power supply systems. In the present invention, the structure is preferably an electrical device, and also preferably a driving body. According to such a preferred embodiment, the electromagnetic operating characteristics of the electrical device or the driving body can be more effectively utilized in the design.

[0015] In the present invention, it is also preferable that the design means further designs two or more types of the second structure using required specifications. According to such a preferred embodiment, the second structure can be designed to better reflect the designer's intentions. The required specifications may be known required specifications.

[0016] In the present invention, it is also preferable that the design means designs two or more types of the second structure having different characteristics. According to this preferred aspect, a user can more efficiently select a design proposal from a larger number of design candidates. According to this preferred aspect, it is also preferable that the characteristics include information indicating physical characteristics. According to this preferred aspect, a user can more efficiently select a design proposal from a larger number of design candidates having a larger number of physical characteristics. Suitable examples of the physical characteristics include characteristics of a rotor or a stationary rotor. The characteristics may be, for example, electromagnetic characteristics. When the structure is a motor, the characteristics may be motor characteristics. The motor characteristics may include, for example, motor speed-torque characteristics, motor efficiency, torque ripple, output, and any one or combination of iron loss and copper loss.

[0017] In addition, the present invention preferably further comprises means for calculating trade-off information corresponding to the second structure. According to such a preferred embodiment, the user can understand the relationships between various usage environments, operating conditions, and characteristics, and can more efficiently select a design plan.

[0018] In the present invention, it is also preferable that the trade-off information includes cost information. According to such a preferred aspect, the user can understand the relationships between various usage environments, operating conditions, characteristics, and costs, and can more efficiently select design proposals.

[0019] Furthermore, in the present invention, it is preferable that the system further includes an evaluation means for evaluating the characteristics of the second structure upon receiving the first structure information and the usage environment and / or the operating conditions from a user. According to this preferred embodiment, it is possible to evaluate in more detail the nonlinear characteristics of the structure in particular. Examples of the evaluation means include finite element analysis.

[0020] In addition, in the present invention, it is preferable to learn the relationship between the characteristics and the structure information of the structure, the usage environment and / or the operating conditions, and the characteristics of the user based on the structure information of the structure, the usage environment and / or the operating conditions through the learning, and output the predicted evaluation value to the user. According to this preferred embodiment, the characteristics of the structure can be evaluated in a shorter time. Examples of the learning and prediction means include machine learning techniques such as support vector regression, Gaussian process regression, random forest, gradient boosting decision tree, neural network, multilayer perceptron, convolutional neural network, Transformer, Vision Transformer, MLP-Mixer, and graph neural network.

[0021] The present invention will be specifically described below with reference to the drawings, but the present invention is not limited to these specific examples.

[0022] FIG. 1 shows a design system 100 according to a preferred embodiment. The design system 100 is a system that accepts a first structure 30 and design instructions 110 relating to the usage environment and / or operating conditions and / or required specifications of the second structure, and designs two or more types of second structures. The second structure to be designed is, for example, a physical two-dimensional or three-dimensional shape of a tangible structure. The shape may be the shape of a portion of the structure, or the shape of the entire structure.

[0023] The structure may, for example, comprise a magnet, for example an electric machine such as a motor.

[0024] The structure may be, for example, an electric machine. Here, electric machines are a general term for rotating electric machines (rotating machines) such as motors and generators, and stationary electric machines (stationary machines) such as transformers, rectifiers, and switching control devices. The electric machine may be any machine whose electromagnetic properties can be evaluated in design.

[0025] A suitable design system 100 according to the embodiment includes a structure design system 200 and a property evaluator 300. The structure design system 200 generates shape candidates for a second structure. The property evaluator 300 evaluates the properties of the structure based on the shape candidates generated by the structure design system 200.

[0026] The design system 100 may be configured with a single or multiple computers having a processor and a memory. The processor may be a CPU or a GPU. The memory is connected to the processor. The memory includes, for example, a primary storage device and a secondary storage device. The primary storage device is, for example, a RAM. The secondary storage device is, for example, a hard disk drive (HDD) or a solid-state drive (SSD). The memory includes a computer program executed by the processor. The processor reads and executes the computer program stored in the memory. The computer program has program code for causing the computer to operate as the design system 100. In other words, the computer program has program code for causing the computer to operate as the structure design system 200 and the characteristic evaluator 300.

[0027] The design system 100 can output a plurality of optimized second structures by repeatedly generating and evaluating shapes. For example, the design system 100 determines whether the characteristics evaluated (predicted) by the characteristic evaluator 300 satisfy predetermined requirements, and if the requirements are satisfied, outputs a shape having the characteristics as a second structure. If the characteristics evaluated by the characteristic evaluator 300 do not satisfy the predetermined requirements, the design system 100 regenerates and evaluates the shape. The design system 100 automatically outputs a plurality of optimized second structures by repeatedly designing and evaluating various shapes.

[0028] The characteristics evaluated by the characteristic evaluator 300 are characteristics of a structure having a shape designed by the structure design system 200. The characteristics may be, for example, characteristics of a rotor or a stationary machine. The characteristics may be, for example, electromagnetic characteristics. If the structure is a motor, the characteristics may be motor characteristics. The motor characteristics may include, for example, any one or a combination of the speed-torque characteristics of the motor, the efficiency of the motor, torque ripple, and iron loss. Techniques for evaluating motor characteristics from the motor shape are disclosed in, for example, Non-Patent Document 1 and Non-Patent Document 2.

[0029] The use environment, operating environment, and required specifications of the design instructions 110 may be instructions in natural language. An instruction to the use environment is an instruction to the environment in which the structure is used, such as "Please keep the magnet temperature at 100°C." An instruction to the operating environment is an instruction regarding the operating conditions of the structure, such as "Change the current condition from 100A to 80A." An instruction regarding required specifications is, for example, "Make the magnet 1mm thicker" (required specification regarding the magnet shape), "Increase the torque a little more" (required specification regarding characteristics), or "Reduce the cost by 10% while keeping the loss the same" (required specification regarding characteristics and cost). The design instructions 110 may be quantitative instructions for modifying the shape or qualitative instructions.

[0030] Here, when the use environment, operating environment, and required specifications of the design instructions 110 are instructions in natural language, the structure design system 200 is configured, for example, by a pre-trained large-scale language model.

[0031] When the design instructions 110 include instructions for the characteristics of the structure, the design system 200 performs shape modification to achieve the characteristic instructions. The modified shape candidate is input to the characteristic evaluator 300, where the characteristics are evaluated. The evaluated characteristics of the modified shape candidate are compared with the characteristic evaluation results of the first structure 30 before modification, and it is determined to what extent the characteristics should be changed.

[0032] For example, if the maximum torque of the first structure is 180 Nm and the specified maximum torque is 200 Nm, the required specifications are interpreted as an instruction to "increase the maximum torque by 20 Nm compared to the first structure."

[0033] Here, the large-scale language model of the structure design system 200 has previously learned how to change the shape in order to change motor characteristics such as torque. That is, the design system 100 uses a machine-learned model to determine how much the shape should be changed based on the difference between the characteristics of a reference shape and the characteristics specified by a user such as a designer. For example, by machine-learning a shape modification measure for changing characteristics, such as increasing the size of the magnet to increase torque, the design system 100 can derive a shape modification measure from the characteristic change.

[0034] Therefore, if there is a requirement specification for characteristics based on the first structure, such as "increase the maximum torque by 20 Nm compared to the motor of the first structure," the structure design system 200 can generate a strategy showing how to change the shape from the first structure.

[0035] Furthermore, when the design instructions 110 include instructions on the usage environment and / or operating conditions, the design system 100 provides the usage environment and / or operating conditions to the characteristic evaluator 300 as conditions for characteristic evaluation. The characteristic evaluator 300 determines the characteristics of the structure according to the usage environment and / or operating conditions. In this case, the characteristics of the structure in the given usage environment and / or operating conditions are determined. Using these characteristics, the structure design system 200 can design two or more types of second structures according to the usage environment and / or operating conditions, just as when the design instructions 110 include instructions on the characteristics of the structure.

[0036] In the following description, the design system 100 according to the embodiment is used to design a motor, as an example. Motors are used in various products such as electric vehicles, drones, aircraft, and industrial robots. The motor to be designed by the design system 100 is, as an example, an interior permanent magnet synchronous motor (IPMSM).

[0037] As shown in Fig. 2, interior permanent magnet synchronous motor 10 is a type of motor that uses permanent magnets 15. Interior permanent magnet synchronous motor 10 includes stator 11 and rotor 12 provided inside stator 11. Permanent magnets 15 are embedded in rotor 12. Interior permanent magnet synchronous motor 10 shown in Fig. 2 is, as an example, an 8-pole, 48-slot distributed winding IPMSM.

[0038] The stator 11 is made of electromagnetic steel and has multiple slots 16 formed in the circumferential direction. Air exists in the slots 16. Therefore, when designing the stator 11, two types of materials must be taken into consideration: electromagnetic steel and air.

[0039] Rotor 12 is constructed by embedding permanent magnets 15 in a rotor body made of electromagnetic steel. In rotor 12, regions (holes) where air exists are formed in positions adjacent to permanent magnets 15. Therefore, when designing rotor 12, three types of materials must be considered: electromagnetic steel, permanent magnets, and air.

[0040] Here, the object of design is rotor 12, and the structure of stator 11 (stator structure) is assumed to be predetermined. The external shape of rotor 12 is also assumed to be predetermined. Therefore, the object of design here is the shape and arrangement of the magnets and air in rotor 12. Note that the external shapes of stator 11 and rotor 12 may also be subject to design.

[0041] Furthermore, since each pole of the rotor 12 has the same structure, when designing the rotor 12, it is sufficient to design one pole of the rotor 12.

[0042] Fig. 3 shows an example of a two-dimensional topology for one pole of the rotor 12. In each topology shown in Fig. 3, the position, number, shape, etc. of the permanent magnets and holes (air) differ.

[0043] In the design system 100 according to the embodiment, the structure design system 200 generates and outputs, for example, a two-dimensional shape for one pole of the rotor 12 shown in Fig. 3. The characteristic evaluator 300 acquires the structure information output from the structure design system 200 and evaluates the characteristics.

[0044] Fig. 4 is a schematic diagram of a preferred embodiment of the system of the present invention. In the system of Fig. 4, a user terminal 211 and an information processing device 212 are connected via a communication line 210, enabling the exchange of instructions described above. The user terminal 211 may be a known terminal such as a personal computer or tablet used by a user. The information processing device 212 may be a known database, such as a database containing user information, structure information, usage environment, and / or operating conditions.

[0045] FIG. 5 is a diagram showing a preferred exchange of information between the user terminal 211 and the information processing device 212 of FIG. 4. First structure information is transmitted from the user terminal 211 to the information processing device 212 (S101). Upon receiving the first structure information from the user terminal 211, the information processing device 212 evaluates the characteristics of the first structure (S102). After the evaluation, the information processing device 212 transmits characteristic information to the user terminal 211 (S103). Upon receiving the characteristic information from the information processing device 212, the user terminal 211 transmits the usage environment and / or operating conditions of the second structure to the information processing device 212 (S104). Furthermore, if desired, the user terminal 211 transmits required specifications of the second structure to the information processing device 212 (S105). Upon receiving the usage environment and / or operating conditions of the second structure and, if desired, the required specifications of the second structure from the user terminal 211, the information processing device 212 designs two or more types of second structures (S106). After the design, the information processing device 212 further evaluates the characteristics of two or more types of second structures (S107), and transmits the design results to the user terminal 211 (S108).

[0046] 6 shows an example of a procedure for shape modification by the design system 100. Here, LLM stands for large-scale language model. When a design instruction 110 is input to the design system 100, the instruction 110 is determined by the processing decision LLM 410 (step S71). In step S71, the processing decision LLM 410 analyzes the instruction 110 and determines whether there is a modification command (command name) corresponding to the instruction 110. If there is a modification command corresponding to the instruction 110, it can be processed ("Yes" in step S71), and the process proceeds to step S72.

[0047] If there is no modification command corresponding to the instruction 110, processing is not possible ("No" in step S71), and the process proceeds to step S77. In step S77, the interactive LLM 430 creates a response prompting the user to re-input the instruction 110. The response is displayed to the user (step S78).

[0048] In step S72, the JSON creation LLM 420 creates a modification command (modification instruction JSON) from the user's text instruction 110. In step S73, the JSON creation LLM 420 determines whether the information in the user instruction 110 is complete (whether all the necessary information is included). If the information is not complete ("No" in step S73), the process proceeds to step S77. In step S77, the interactive LLM 430 creates a response that prompts the user to enter the necessary information. The response is displayed to the user (step S78).

[0049] If the necessary information is available ("Yes" in step S73), the process proceeds to step S74.

[0050] In step S74, the shape correction process is executed based on the correction command. If an error occurs in the shape correction, a response notifying the error is created and displayed (steps S77 and S78).

[0051] When the execution of the shape correction process is completed normally, the interactive LLM 430 creates a response to the user (step S75), which is displayed together with the corrected shape (step S76).

[0052] The design system 100 stores the above-described interaction history between the user and the system 100 in memory (step S79). The user can also give the system 100 an instruction 110 to further modify the modified shape. In this case, the system 100 executes the process again from step S71.

[0053] 7 and 8 show examples of user instructions 110 (user input) and the output of each LLM 410, 420, 430.

[0054] FIG. 7 shows "Example 1." In Example 1, the user instruction 110 is "Please set the thickness of the front-side permanent magnet to 6.0 mm." In Example 1, the process determination LLM (LLM1) 410 outputs {'command': 'designate'}. This output indicates that the command name selected by the process determination LLM 410 based on the user instruction is "designate."

[0055] In Example 1, the JSON creation LLM 420 outputs the modified command shown in Figure 7 based on the instruction 110. The interactive LLM 430 also generates and outputs the response sentence shown in Figure 7 based on the instruction 110 and the modified command.

[0056] FIG. 8(A) shows "Example 2." Example 2 illustrates a case in which an error occurs due to shape modification. In Example 2, the user instruction 110 is "Please increase the thickness of the permanent magnet by 1.2 times." In Example 2, the processing decision LLM 410 outputs the command name "enlarge," and the JSON creation LLM 420 outputs a modification command, but an error occurs as a result of the shape modification process. In this case, the shape modification system 300 outputs "point idx 1 is out of radial boundary," indicating that the vertex has moved outside the design domain as a result of the shape modification.

[0057] 8(B) shows "Example 3." In Example 3, the user's instruction 110 is "Hello," which is a user input unrelated to shape modification. In this case, the processing determination LLM 410 determines that processing is impossible, and creates and displays a response indicating that processing is impossible or a response prompting re-input of the instruction (steps S71, S77, and S78 in FIG. 6).

[0058] Furthermore, in the present invention, it is preferable to further include a means for calculating trade-off information corresponding to the second structure, and more preferably, the trade-off information includes cost information. An example of such a preferable means is the relationship diagram between loss and cost shown in FIG. 9. Loss and cost have a trade-off relationship, and in the present invention, it is preferable to use such trade-off information. By using such trade-off information, shape candidates with a variety of characteristics can be presented to the designer, enabling more efficient design.

[0059] Fig. 10 shows a variation of the characteristic evaluator 300 shown in Fig. 1. The characteristic evaluator 300 shown in Fig. 10 includes a characteristic evaluation model 301 (trained model) that has been machine-learned to output the characteristics of a structure when structure information is input. The characteristic evaluation model 301 has been machine-learned (deep learning) using the structure information and characteristic data of the structure as training data.

[0060] The present invention is not limited to the above-described embodiment and can be modified in various ways. In the above-described embodiment, a motor is described as one suitable example. However, the present invention can be applied to other applications. For example, the present invention can be applied to piezoelectric actuators, RFID (Radio Frequency Identification), cables, high-frequency preheaters, capacitors, magnetic heads, magnetic shields, magnetic gears, magnets, circuit breakers, sensors, electrical heating devices, electrolytic plating, electromagnetic forming, electromagnetic retarders, electromagnetic relays, transformers and reactors, bus bars, generators, heaters, bearings, magnetic couplings, induction heating devices, induction machines, linear solenoids and linear actuators, and wireless power transfer systems. When the present invention is applied to a motor, it has the advantage of being able to express motor design information using only the minimum necessary information. [Industrial Applicability]

[0061] The system of the present invention is particularly useful in the design of motors and the like. [Explanation of symbols]

[0062] 10: Interior permanent magnet synchronous motor 11: Stator 12: Rotor 15: Permanent magnet 16: Slot 30: First structure 100: Design System 110: Design instructions 200: Structural design system 210: Communication lines 211: User terminal 212: Information processing equipment 300: Characteristic evaluator 301: Trained model 410: Processing Judgment LLM 420 :JSON Creation LLM 430: LLM for Interactive Studies

Claims

1. A system for designing a second structure based on a first structure, characterized in that the system includes a means for designing two or more types of the second structure using the usage environment and / or operating conditions of the second structure.

2. The system of claim 1 , wherein the structure is an electrical device.

3. The system of claim 2 wherein the structure is a driver.

4. The system according to claim 1 , wherein the usage environment includes a temperature range, a humidity range, a degree of contamination, or a pressure range.

5. The system of claim 3 , wherein the operating conditions include a maximum current, a maximum voltage, or a maximum speed.

6. 2. The system according to claim 1, wherein said design means further designs two or more types of said second structure using required specifications.

7. 2. The system according to claim 1, wherein said design means designs two or more types of said second structure having different characteristics.

8. The system of claim 7 , wherein the characteristics include information indicative of physical characteristics.

9. 2. The system of claim 1, further comprising means for calculating trade-off information corresponding to said second structure.

10. The system of claim 9 , wherein the trade-off information includes cost information.

11. 2. The system according to claim 1, further comprising an evaluation means for evaluating characteristics of said second structure when said first structure information and said usage environment and / or said operating conditions are received from a user.

12. The system described in claim 11 learns the relationship between the structure's structural information, the usage environment and / or the operating conditions, and the characteristics, predicts the characteristics from the user's structural information, the usage environment and / or the operating conditions, and outputs the predicted evaluation value to the user.

13. A program that causes a system for designing two or more types of second structures based on a first structure to function as a means for evaluating the characteristics of the second structure when it receives information about the first structure and the usage environment and / or the operating conditions.

14. The program of claim 13, which learns the relationship between the structure information of the structure, the usage environment and / or the operating conditions, and the characteristics, predicts the characteristics from the structure information of the structure of the user, the usage environment and / or the operating conditions through said learning, and outputs the predicted evaluation value to the user.

Images