JP7807322B2 - Design support device and design support method - Google Patents

Description

This disclosure relates to a design support device and a design support method.

Conventional design support technology for predicting the optimal shape of mechanical structures involves using topology optimization calculations and image processing, a type of machine learning, to predict the optimal shape. Topology optimization, also known as topology optimization, is a structural optimization technique that derives the optimal density distribution of a material for a given structure made of a given material, based on the design variables of that structure.

Patent Document 1 discloses a modeling process including a learning method that enables the generation of physically realistic CAD data that can be directly used in the design and/or manufacturing process, the modeling process including providing a dataset including a functional structure by the learning method (S10) and training a generative autoencoder on the dataset by the learning method (S20), and may further include training a latent space classifier by the learning method (S30), providing one or more latent vectors by the generation method (S100) and generating a functional structure by the generation method (S200), and may further include performing topology optimization of a mechanical assembly of rigid parts represented by the generated functional structure by the generation method (S300).

In addition, there is a method for generating CAD drawings from the results of optimization calculations in a device that generates the drawings according to the model form of the analysis. Here, CAD stands for Computer Aided Design.

Patent Document 2 discloses a design optimization support system used in the design of structures that includes a finite element method model conversion device that converts CAD data into a finite element method model, an optimization device that constructs an optimized finite element method model using an optimization method, and a CAD data conversion device that converts the optimized finite element method model into CAD data. The system also includes a means for selecting a finite element method model creation method that suits the type of CAD data and model form, a means for selecting an optimization method that suits the optimization purpose, and a CAD data conversion means that converts the optimized finite element method model into CAD data according to the model form.

Japanese Patent Application Laid-Open No. 2021-12693 Japanese Patent Application Laid-Open No. 2006-11729

Conventional topology design support technology uses machine learning to learn a tree representing the functional structure of a CAD drawing using a deep neural network (DNN), generates a new CAD drawing from vector data called latent vectors, and performs topology optimization calculations using the generated CAD drawing to predict the optimal shape. In this case, the predicted optimal shape is represented by a density distribution that varies from 0 to 1 across the entire calculation domain. In other words, the optimal shape of a mechanical structure is predicted by assuming that areas with a density of 0 do not contain any structures and areas with a density of 1 contain structures.

The optimal shape predicted in this way also includes density areas other than 0 and 1. In areas with intermediate density values such as 0.3 or 0.7, it is up to the engineer to decide whether or not a structure is included. As a result, interpretations vary depending on the engineer, which can lead to variations in the final CAD drawing, making it difficult to obtain high-quality CAD drawings.

The method described in Patent Document 1 does not sufficiently consider the ability to generate high-quality CAD drawings regardless of the skill of the individual engineer.

In addition, technology that generates CAD drawings from the results of optimization calculations determines the shape of the CAD drawing by smoothly connecting the density distribution of the calculation domain in the predicted optimal shape. Attributes of CAD drawings include characteristic information such as manufacturing cost and efficiency.

In the design optimization support system described in Patent Document 2, the designer is responsible for selecting the optimization objective. Therefore, selecting an appropriate optimization objective from multiple characteristics is left to the designer's skill and experience, and there are cases where the optimization objective needs to be repeatedly reviewed. This increases the amount of effort and time required for design, leaving room for improvement.

The purpose of this disclosure is to generate high-quality drawings in a short time from the density distribution of a structure derived from structural optimization calculations.

The design support device disclosed herein generates proposed drawings from the results of structural optimization calculations that derive an optimized density distribution for a structure. It includes: a clustering condition input unit that accepts input of clustering conditions; a clustering unit that performs clustering according to the clustering conditions; a machine learning control unit that performs machine learning on each of the clusters obtained by clustering; a drawing generation unit that generates new drawings from the results of machine learning; a drawing discrimination unit that compares the new drawings with the base drawings to be compared and determines whether the drawings are the same; an optimization/analysis condition input unit that accepts input of calculation conditions required for structural optimization calculations; an analytical model generation unit that generates an analytical model according to the calculation conditions; a structural optimization calculation unit that performs structural optimization calculations using the analytical model; a drawing generation condition input unit that displays the results of the structural optimization calculations and the clustering results and accepts input of weights for each cluster required for drawing generation; and a display unit that displays information including at least one of the clustering conditions, calculation results, and generated drawings. The drawing generation unit generates proposed drawings using the results of the structural optimization calculations and the weights, and the display unit displays the proposed drawings.

This disclosure makes it possible to generate high-quality drawings in a short amount of time from the density distribution of a structure derived through structural optimization calculations.

1 is a schematic configuration diagram showing a design support device according to an embodiment; 10 is a flowchart showing a process of inputting clustering conditions in Phase 1. 10 is a flowchart showing a clustering process in Phase 1. 1 is a flowchart illustrating the machine learning process in Phase 1. 10 is a flowchart showing a topology optimization calculation process in Phase 2. 10 is a flowchart showing a drawing generation process in Phase 2. FIG. 2B is a diagram showing an example of data acquired in step S101 of FIG. 2A. FIG. 2B is a diagram showing an example of an input screen for clustering conditions used in step S102 of FIG. 2A. FIG. 2C is a diagram showing an example of a screen showing the clustering results displayed in step S204 of FIG. 2B. FIG. 1 is a conceptual diagram illustrating an example of CycleGAN. FIG. 10 is a diagram showing an example of an input screen for topology optimization calculation. FIG. 4B is a diagram showing an example of the result of the topology optimization calculation obtained in step S403 of FIG. 4A. FIG. 4C is a diagram showing an example of an input screen for conditions for generating a new drawing in step S502 of FIG. 4B. FIG. 4C is a diagram showing an example of a screen displayed in step S504 of FIG. 4B.

This disclosure relates to a design support technology that generates specific drawings based on input condition vectors (weights) from the results of topology optimization with varying density obtained through numerical analysis.

The following describes the examples using drawings.

Figure 1 is a schematic diagram showing the design support system of the embodiment.

As shown in this diagram, the design support device includes a clustering condition input unit 101, a clustering unit 102, a clustering result display unit 103, a machine learning control unit 104, a drawing generation unit 105, a drawing discrimination unit 106, an optimization/analysis condition input unit 107, an analysis model generation unit 108, a topology optimization calculation unit 109 (structural optimization calculation unit), a drawing generation condition input unit 110, a drawing display unit 111, a database 112 (storage device), and a computer 113.

In the clustering condition input unit 101, the operator inputs information (clustering conditions) required for clustering, such as CAD drawings, topology optimization calculation results, and characteristic information.

The clustering unit 102 performs clustering using a self-organizing map according to the input clustering conditions. Here, clustering is a type of machine learning, and refers to a technique for grouping data based on the similarity between data. Clustering is also called "cluster analysis" or "data clustering."

The clustering result display unit 103 displays the clustering results using the self-organizing map, along with the average value of the characteristic information for each cluster.

The machine learning control unit 104 controls the drawing generation unit 105 and drawing determination unit 106, and performs machine learning using a method that applies CycleGAN, taking as input the results of topology optimization calculations, CAD drawings, and condition vectors. Here, CycleGAN is an abbreviation for Cycle Generative Adversarial Networks.

The drawing generation unit 105 generates a new drawing using the results of the topology optimization calculation, the CAD drawing, and the condition vector as input information.

The drawing determination unit 106 takes two drawings as input information and determines whether the two drawings are the same.

The optimization/analysis condition input section 107 allows you to input the analysis conditions, objective functions, and volume constraints required for topology optimization calculations.

The analytical model generation unit 108 generates an analytical model based on the analytical conditions, objective function, and volume constraints required for topology optimization calculations.

The topology optimization calculation unit 109 performs topology optimization calculations using the finite element method for the structural analysis portion of the generated analysis model and the density method for the topology optimization portion.

The drawing generation condition input unit 110 displays the results of the topology optimization calculation and the clustering results, and allows you to enter the weights for each cluster required for drawing generation.

The drawing display unit 111 displays the drawing generated by the drawing generation unit 105 and the drawing generation conditions.

Database 112 stores the data obtained from each section.

Next, we will explain the processing procedures in the design support device, i.e., an example of a design support method.

The design support method of this embodiment can be broadly divided into two processes. The first process (Phase 1) is a process of clustering data such as CAD drawings and applying machine learning to that data. The second process (Phase 2) is a process of performing topology optimization calculations and generating drawings from the results.

The following explanation focuses on mechanical structures.

Figure 2A is a flowchart showing the process for inputting clustering conditions in Phase 1.

In steps S101 to S104 shown in this diagram, clustering conditions are entered via the clustering condition input unit 101 and stored in the database 112.

First, in step S101, past CAD drawings, topology optimization calculation results, and characteristic information such as manufacturing cost, efficiency, strength resistance, and heat resistance are obtained from database 112.

Figure 5 shows an example of the data acquired in step S101.

As shown in this diagram, the CAD drawing for "AA001" is associated with the result of the topology optimization calculation, "AA001TOP," and is managed by linking it to characteristic information such as manufacturing cost, efficiency, strength performance, and heat resistance as its attributes. It is assumed that this past data has been stored in database 112 in advance. In this case, this past data is the data that forms the basis for supervised learning. The past CAD drawing may be one obtained as a result of the topology optimization calculation, or it may be a drawing that a designer actually created in the past.

In step S102, the operator inputs the conditions required for clustering using the clustering condition input unit 101.

Figure 6 shows an example of the clustering condition input screen.

As shown in this figure, "Machine Structure 1" has been entered as the learning model name. The data attributes shown in Figure 5 are displayed in a corresponding format as variables to be clustered. Figure 6 displays CAD drawings, topology optimization calculation results, manufacturing cost, efficiency, strength performance, and heat resistance performance, with manufacturing cost, efficiency, strength performance, and heat resistance performance selected as the clustering conditions. It is also possible to enter the number of clusters into which the acquired data will be divided (number of clusters). Here, "10" has been entered as the number of clusters.

In step S103, information such as the learning model name, clustering condition variables, and number of clusters entered in step S102 is obtained.

In step S104, the information obtained in step S103 is registered in database 112.

Figure 2B is a flowchart showing the clustering process in Phase 1.

In steps S201 to S205 shown in this diagram, the clustering unit 102 classifies the data into clusters, and the clustering result display unit 103 displays the clustering results.

In step S201, the clustering unit 102 obtains past CAD drawings, topology optimization calculation results, and characteristic information such as manufacturing cost, efficiency, strength resistance, and heat resistance from the database 112.

In step S202, the clustering unit 102 acquires the information acquired in steps S101 to S104. Here, the learning model name, variables to be clustered, and the number of clusters are acquired.

In step S203, the clustering unit 102 performs clustering. Various clustering methods have been proposed. Here, clustering is performed using a method called a self-organizing map. A self-organizing map is a type of neural network that models the visual area of the cerebral cortex. A self-organizing map randomly arranges weight vectors on a map and prepares one input vector. The similarity between all weight vectors on the map and the input vector is calculated. Euclidean distance is used to determine the similarity. The vector with the smallest distance is found, and the weight vectors in its vicinity are modified using the following formula (1).

In the formula, _Wu is a weight vector, θ is the neighborhood radius, and α is the learning coefficient. U is an input vector containing the variables to be clustered. Furthermore, n represents the number of iterations. In this way, the self-organizing map is used to divide the data into clusters with high similarity. Here, the data is divided into 10 clusters.

In step S204, the clustering result display unit 103 displays the clustering results.

Figure 7 shows an example of a display screen showing the clustering results.

In this diagram, variables to be clustered, such as manufacturing cost, efficiency, strength resistance, and heat resistance, are displayed as clusters with high similarity, ranging from "1" to "10." The table shown in this diagram also displays information such as the average values of variables such as manufacturing cost, efficiency, strength resistance, and heat resistance for each cluster. This allows the operator to grasp the similarity characteristics of each cluster, such as cluster "1" having low manufacturing costs and cluster "3" having high efficiency. If the operator is satisfied with the results, they press the "Decide" button, and if they want to start over, they press the "Redo" button and review the clustering conditions from step S101.

In step S205, the results of the clustering performed in step S203 are registered in database 112. Here, the clustering information divided into 10 groups and information on the average values of each variable are registered.

Figure 3 is a flowchart showing the machine learning process in Phase 1.

The machine learning shown in this diagram is performed by the machine learning control unit 104 controlling the drawing generation unit 105 and drawing determination unit 106. Various machine learning methods have been proposed, but here we apply an image processing technique called CycleGAN to perform machine learning.

Figure 8 is a conceptual diagram showing an example of CycleGAN.

CycleGAN generates new images from images of horses and other objects. For example, using a zebra as a real image, it performs image discrimination to determine whether the newly generated image is the same as an image of a zebra, and then uses machine learning to adjust the image generation parameters so that they are the same. At this time, it generates a new image from a real image of a zebra, and then performs image discrimination to determine whether the newly generated image is the same as an image of a horse, and then uses machine learning to adjust the image generation parameters so that they are the same. This machine learning process is repeated until they are determined to be the same.

As such, CycleGAN is characterized by its ability to generate an image that resembles a zebra from an image of a horse or other object. In this case, by using a condition vector, it is possible to generate an image that resembles a zebra or an image that resembles a deer from an image of a horse. That is, for example, if the real image is a zebra, machine learning is performed by inputting the condition vector [1 0 0 0 0], and if the real image is a deer, machine learning is performed by inputting the condition vector [0 1 0 0 0]. If you want to generate an image that resembles a zebra after machine learning, inputting the image of a horse and the condition vector [1 0 0 0 0] will generate an image that resembles a zebra. Furthermore, by inputting the condition vector [1 1 0 0 0], images that resemble both zebras and deer can also be generated.

A neural network is used to generate images. A neural network is a mathematical model that aims to represent the characteristics of the brain, which consists of a large number of nerve cells, through computer simulation. If each layer of artificial neurons is designated as _Xi , the neural network is given by the recurrence formula shown below in Equation (2).

In the formula, _Ai is a weight parameter, _Bi is a bias parameter, and f is an activation function. _Ai and _Bi are determined through machine learning. In the case of three layers, _X1 is the input layer, _X2 is the hidden layer, and _X3 is the output layer. A neural network with multiple hidden layers is called a deep neural network. Deep neural networks are applied to CycleGAN image processing.

In step S301, the machine learning control unit 104 obtains from the database 112 all past CAD drawings, topology optimization calculation results, clustering conditions obtained in the step shown in Figure 2A, and clustering data obtained in the step shown in Figure 2B.

In step S302, one of the clusters clustered by the machine learning control unit 104 is extracted, and the topology optimization calculation results and condition vectors belonging to this cluster are input to the drawing generation unit 105 to generate a new drawing. In this example, since there are 10 clusters, the topology optimization calculation results and condition vector [1 0 0 0 0 0 0 0 0] belonging to cluster number "1" are input to generate a new drawing.

In step S303, the machine learning control unit 104 inputs the new drawing generated in step S302 and the drawing related to the input topology optimization calculation results into the drawing determination unit 106, which determines whether the new drawing and the drawing related to the input topology optimization calculation results are the same. If it is determined that they are not the same, the parameters of the drawing generation unit 105 are adjusted. Here, the drawing related to the input topology optimization calculation results is used for comparison as the "real drawing" and is also called the "base drawing."

In step S304, the machine learning control unit 104 inputs the original drawing and condition vector used in step S303 into the drawing generation unit 105 to generate a new drawing. Here too, the condition vector [1 0 0 0 0 0 0 0 0 0] is used.

In step S305, the new drawing generated by the machine learning control unit 104 in step S304 and the results of the topology optimization calculation used in step S302 are input to the drawing determination unit 106, which determines whether the new drawing and the calculation results are the same. If it is determined that they are not the same, the parameters of the drawing generation unit 105 are adjusted. Here, the determination of whether they are the same is made using machine learning. Specifically, this is done using a neural network.

In step S306, the machine learning control unit 104 performs machine learning on all topology optimization calculation results and drawings for the data belonging to the cluster, repeating steps S302 to S305 until convergence is achieved. Furthermore, similar machine learning is performed on all remaining data in each cluster until convergence is achieved. Taking the example of machine learning on data with cluster number "3," machine learning is performed using the condition vector [0 0 1 0 0 0 0 0 0 0]. Here, the convergence criteria are typically entered as an acceptable condition by the user. For example, if the user inputs a value of "99%," the calculation is terminated when image discrimination determines that the two images are "same" with a probability of 99% or higher. If the input value of "99%" is too high and convergence is not achieved, the user can force the calculation to terminate and relax the convergence criteria, for example, by re-entering "95%." An input value of 95% is generally considered appropriate.

In step S307, the information resulting from the machine learning performed by the machine learning control unit 104 is registered in the database 112. Here, the machine learning information in which the parameters have been adjusted so that the generated drawing is the same as the drawing to be made authentic is registered in the database.

This concludes Phase 1.

Next, we'll explain Phase 2.

Figure 4A is a flowchart showing the topology optimization calculation process in Phase 2.

In the topology optimization calculation process shown in this diagram, the optimization/analysis condition input unit 107 inputs the conditions necessary for the topology optimization calculation, the analysis model generation unit 108 generates an analysis model according to the conditions input in the optimization/analysis condition input unit 107, and the topology optimization calculation unit 109 performs the topology optimization calculation for the mechanical structure.

In step S401, the optimization and analysis conditions input unit 107 accepts the optimization and analysis conditions entered by the operator.

Figure 9 shows an example of the input screen.

In this diagram, "Hook" has been entered as the analysis model name. An analysis model for topology optimization calculations has been created by the operator. In the rectangular calculation domain, a boundary condition constrained by a wall has been applied to the left side of the diagram, and a load condition of 1000 N has been applied to the center right side of the diagram. "Aluminum" has also been entered as the material condition. The topology optimization calculation conditions entered are those that minimize the average compliance, expressed as the product of load and displacement, and "40% or less" has been entered as the volume constraint condition. In other words, the optimization conditions have been set so that the volume of the rectangular domain is 40% or less and rigidity is maximized at that time.

In step S402, the analytical model generation unit 108 generates an analytical model based on the conditions entered in step S401. The calculation domain is divided into mesh regions called finite elements, and an analytical model containing information on the analytical model, analysis and optimization conditions, etc. is generated.

In step S403, the topology optimization calculation unit 109 inputs the analysis model generated in step S402 and performs a topology optimization calculation. Here, the finite element method is used for the structural analysis portion, and the density method is used for the topology optimization portion. This calculation method assigns a density that varies from 0 to 1 to each finite element as a design variable, and performs optimization by calculating the product of density and Young's modulus as the Young's modulus of the finite element. Therefore, a density of 0 indicates a state where no structure is present, and a density of 1 indicates a state where a structure is present.

Figure 10 shows an example of the results of a topology optimization calculation. In the figure, the shading of the divided calculation areas represents the density. Darker areas represent higher densities.

As shown in this figure, the structure of the mechanical structure is expressed by the shading of the calculation domain.

Figure 4B is a flowchart showing the drawing generation process in Phase 2.

In the drawing generation process shown in this figure, the drawing generation condition input unit 110 inputs conditions for generating a new drawing from the results of the topology optimization calculation, the machine learning control unit 104 inputs the information input in the drawing generation condition input unit 110 to the drawing generation unit 105 to generate a new drawing, and the drawing display unit 111 displays the generated drawing.

In step S501, the machine learning control unit 104 acquires all information input in the steps shown in Figures 2A, 2B, and 3.

In step S502, the operator uses the drawing generation condition input unit 110 to input conditions for generating a new drawing from the results of the topology optimization calculation.

Figure 11 shows an example of the input screen for creating new drawings.

The operator generates a new drawing by entering the analysis model name, learning model name, and drawing generation conditions. In this diagram, "Hook" has been entered as the analysis model name, and "Machine Structure 1" is displayed as the learning model name.

The topology optimization calculation results display area displays the results of the topology optimization calculation shown in Figure 4A.

The display area at the bottom of Figure 11 also displays the clustering results shown in Figure 2B. The operator generates a new drawing by changing the weight of each cluster number between 0 and 1. Cluster number "3" has a weight of "1," cluster number "5" has a weight of "0.5," and cluster number "7" has a weight of "1." The weights of the other clusters are set to "0."

In step S503, the machine learning control unit 104 inputs the information input in step S502 into the drawing generation unit 105 to generate a new drawing. Here, as a result of the topology optimization calculation for the analysis model named "hook", the condition vector [0 0 1 0 0.5 0 1 0 0 0], in which "1", "0.5", and "1" are entered in the elements corresponding to cluster numbers "3", "5", and "7", is input to the drawing generation unit 105 to generate a new drawing. In this way, a new screen is generated in which the properties of cluster numbers "3", "5", and "7" are possessed in a ratio of 1:0.5:1.

In step S504, the drawing generated in step S503 is displayed by the drawing display unit 111.

Figure 12 shows an example of the generated drawing display screen.

In this diagram, the analysis model name "Hook" and the learning model name "Mechanical Structure 1" are displayed. Also displayed are the drawing (proposed drawing) generated in step S503 and the drawing generation conditions entered in step S502.

In step S505, the drawing generated as a result of the topology optimization calculation shown in FIG. 4A is registered in database 112. After the drawing is displayed in step S504, the process may return to step S502, if necessary, and the operator may repeat the input.

In this way, past CAD drawings and the results of topology optimization calculations are divided into clusters with high similarity based on characteristic information such as manufacturing cost and efficiency, and new drawings are generated from the results of topology optimization calculations by machine learning each cluster. This allows for shapes that are not dependent on the engineer's experience, as opposed to shapes that engineers previously predicted based on the density shades obtained from topology optimization calculations based on their experience. Furthermore, it is possible to generate new drawings that take into account characteristics other than the objective function of the optimization calculation, such as manufacturing cost and efficiency. Furthermore, by applying condition vectors, drawings that take into account multiple characteristics such as manufacturing cost and efficiency can be generated in a short amount of time.

As described above, this disclosure makes it possible to obtain high-quality drawings in a short amount of time.

In this disclosure, clustering, machine learning, and topology optimization calculations are described as being performed on the same computer; however, by utilizing a network environment, they can be performed on different computers. In other words, the design support method according to this disclosure can be implemented by configuring a cloud in which multiple servers installed in remote locations link together via the Internet. In this case, the multiple servers can be said to constitute a design support system.

101: Clustering condition input unit, 102: Clustering unit, 103: Clustering result display unit, 104: Machine learning control unit, 105: Drawing generation unit, 106: Drawing discrimination unit, 107: Optimization/analysis condition input unit, 108: Analysis model generation unit, 109: Topology optimization calculation unit, 110: Drawing generation condition input unit, 111: Drawing display unit, 112: Database, 113: Computer.

Claims (14)

A design support device that generates a proposed drawing from a calculation result of structural optimization that derives an optimized density distribution for a structure,
a clustering condition input unit that accepts input of clustering conditions;
a clustering unit that performs clustering according to the clustering conditions;
a machine learning control unit that performs machine learning on each of the clusters obtained by the clustering;
a drawing generation unit that generates a new drawing from the result of the machine learning;
a drawing discrimination unit that compares the basic drawing to be compared with the new drawing and determines whether these drawings are the same;
an optimization/analysis condition input unit that receives input of calculation conditions necessary for the structural optimization calculation;
an analytical model generation unit that generates an analytical model in accordance with the calculation conditions;
a structural optimization calculation unit that performs the calculation for the structural optimization using the analytical model;
a drawing generation condition input unit that displays the calculation results of the structural optimization and the clustering results and receives input of weights for each of the clusters required for drawing generation;
a display unit that displays information including at least one of the clustering conditions, the calculation results, and the generated drawing,
the drawing generation unit generates a proposed drawing using the calculation result of the structural optimization and the weight;
The display unit displays the proposed drawing. The design support system of claim 1, wherein the clustering conditions include at least one of the manufacturing cost and efficiency of the structure. The design support device of claim 1, wherein the display unit displays information including characteristic information for each of the clusters. The design support system of claim 1, wherein the structural optimization calculation uses the finite element method and the density method. The design support device of claim 1, wherein the clustering is performed using a self-organizing map. The design support system of claim 1, wherein the structural optimization is topology optimization. The design support device of claim 6, wherein the drawing generation unit generates the proposed drawing using the machine learning. A design support method for generating a proposed drawing from a calculation result of structural optimization that derives an optimized density distribution for a structure, comprising:
a clustering condition input unit that receives input of clustering conditions;
a clustering unit performing clustering in accordance with the clustering conditions;
a machine learning control unit that performs machine learning on each of the clusters obtained by the clustering;
a drawing generation unit that generates a new drawing from the results of the machine learning;
A drawing determination unit compares the basic drawing to be compared with the new drawing and determines whether these drawings are the same;
an optimization/analysis condition input unit that receives input of calculation conditions necessary for the structural optimization calculation;
an analytical model generation unit generates an analytical model in accordance with the calculation conditions;
a structural optimization calculation unit that performs the calculation for the structural optimization using the analytical model;
a drawing generation condition input unit that displays the calculation results of the structural optimization and the clustering results, and receives input of weights for each of the clusters required for drawing generation;
a display unit displays information including at least one of the clustering conditions, the calculation results, and the generated diagram;
the drawing generation unit generates a proposed drawing using the calculation result of the structural optimization and the weight;
The display unit displays the proposed drawing. The design support method of claim 8, wherein the clustering conditions include at least one of the manufacturing cost and efficiency of the structure. The design support method of claim 8, wherein the display unit displays information including characteristic information for each of the clusters. The design support method of claim 8, wherein the structural optimization calculation uses the finite element method and the density method. The design support method according to claim 8, wherein the clustering is performed using a self-organizing map. The design support method of claim 8, wherein the structural optimization is topology optimization. The design support method of claim 13, wherein the drawing generation unit generates the proposed drawing using the machine learning.