JP7716966B2 - Design support equipment - Google Patents

Description

The present invention relates to a design support device.

Design support devices are known that support structural design that satisfies specified criteria for the cross sections of building components (see, for example, Patent Document 1). This design support device includes a model generation unit that reads a three-dimensional model of a building showing the layout of building components, including structural members, from a storage device and converts the cross sections of the building components included in the three-dimensional model into a structural analysis model for structural calculations set to a temporary size, and a cross-section calculation unit that performs structural calculations using the structural analysis model and calculates the cross section by repeatedly enlarging the cross sections of the structural members included in the structural analysis model until the specified criteria are met.

Japanese Patent Application Publication No. 2019-168838

The technology described in Patent Document 1 performs structural calculations using a structural analysis model, and calculates cross-sections by repeatedly enlarging the cross-sections of the structural members included in the structural analysis model until predetermined standards are met. However, Patent Document 1 does not describe assigning predefined members to each of the multiple structural members of a building model so as to satisfy, in that order, long-term stress conditions, short-term stress conditions, target values for the story deformation angles of each floor, and required horizontal bearing capacity.

The present invention takes the above into consideration and aims to support the structural design of buildings using appropriate structural components simply by inputting design conditions.

The design support device of the present invention includes an input unit that receives a building model of a building to be designed, the building model including multiple structural members, and design conditions including long-term stress conditions, short-term stress conditions, and target values for inter-story deformation angles for each floor, for the building to be designed; a first assignment unit that assigns predetermined members selected from a member list storing predetermined members whose member information is predetermined to each of the multiple structural members based on the results of a stress analysis of the building model, in which the predetermined members are assigned to each of the multiple structural members so that the long-term stress conditions are met and the cross-section of the predetermined members assigned to each of the multiple structural members is minimized; and a second assignment unit that assigns the predetermined members to each of the multiple structural members. a second assignment unit that changes the predetermined members assigned to each of the plurality of structural members so as to satisfy conditions related to short-term stress based on the results of stress analysis on the building model in which the predetermined members have been assigned to each of the plurality of structural members; a third assignment unit that changes the predetermined members assigned to each of the plurality of structural members so as to satisfy the target value of the inter-story deformation angle for each floor based on the results of stress analysis on the building model in which the predetermined members have been assigned to each of the plurality of structural members; and a fourth assignment unit that calculates the required horizontal bearing capacity from the predetermined members assigned to each of the plurality of structural members, and changes the predetermined members assigned to each of the plurality of structural members so that the results of stress analysis on the building model satisfy the calculated required horizontal bearing capacity.

In the design support device according to the present invention, the input unit receives a building model of the building to be designed, which is a model of a building including multiple structural members, as well as design conditions for the building to be designed, including long-term stress conditions, short-term stress conditions, and target values for the inter-story deformation angles of each floor.

Then, based on the results of stress analysis of the building model in which a default member selected from a component list storing default members whose component information is predetermined is assigned to each of the plurality of structural members by a first assignment unit, the default member is assigned to each of the plurality of structural members so as to satisfy long-term stress conditions and minimize the cross-section of the default member assigned to each of the plurality of structural members. Then, based on the results of stress analysis of the building model in which the default member is assigned to each of the plurality of structural members, the second assignment unit changes the default member assigned to each of the plurality of structural members so as to satisfy short-term stress conditions.

Then, a third assignment unit changes the default members assigned to each of the plurality of structural members so as to satisfy the target value of the inter-story deformation angle for each floor, based on the results of stress analysis of the building model in which the default members have been assigned to each of the plurality of structural members. A fourth assignment unit calculates the required horizontal bearing capacity from the default members assigned to each of the plurality of structural members, and changes the default members assigned to each of the plurality of structural members so that the results of stress analysis of the building model satisfy the calculated required horizontal bearing capacity.

In this way, by assigning predefined structural members to structural elements so that they satisfy the long-term stress conditions for the building being designed, the short-term stress conditions, the target value for the story drift angle for each floor, and the required horizontal bearing capacity, in that order, it is possible to support the structural design of buildings using appropriate structural elements simply by inputting the design conditions.

In the design support device according to the present invention, the first assignment unit can assign a predetermined member to each of the plurality of structural members so that the center of gravity in a top view determined by the arrangement of the plurality of structural members corresponds to the center of rigidity in a top view determined by the cross section of the predetermined member assigned to the plurality of structural members. This makes it possible to support the structural design of a building so that the center of gravity and center of rigidity in a top view correspond to each other.

In the design support device according to the present invention, the design conditions further include a target value for the column-to-beam strength ratio, and the fourth assignment unit can change the default members assigned to each of the plurality of structural members based on the results of a stress analysis of the building model in which the default members are assigned to each of the plurality of structural members so as to satisfy the target value for the column-to-beam strength ratio, and then calculate a required horizontal bearing capacity from the default members assigned to each of the plurality of structural members, and change the default members assigned to each of the plurality of structural members so that the results of the stress analysis of the building model satisfy the calculated required horizontal bearing capacity. This makes it possible to support the structural design of buildings using structural members that satisfy the required horizontal bearing capacity, while minimizing the amount of calculations, simply by inputting the design conditions.

In the design support device according to the present invention, the design conditions further include a range of component ranks, and the component list is a component list prepared for each component rank. When selecting default components to be assigned to the structural components from the component list, default components can be selected from a component list with a component rank that falls within the range of component ranks. This makes it possible to support the structural design of a building that satisfies the range of component ranks.

In the design support device according to the present invention, the design conditions can further include a target value for the contribution ratio of braces or shear walls, a target value for the inspection ratio, a target value for the horizontal bearing capacity margin, the number of iterations, or a specified material strength. This can support the structural design of buildings that meet the target values for the contribution ratio of braces or shear walls, the target value for the inspection ratio, the target value for the horizontal bearing capacity margin, the number of iterations, or the specified material strength.

The design support device according to the present invention can further include a grouping processing unit that performs grouping by classifying the plurality of structural members into a plurality of groups consisting of structural members that should have the same cross section, based on the characteristic quantities of each of the plurality of structural members obtained from the results of stress analysis of the building model in which a predetermined member is assigned to each of the plurality of structural members. This makes it possible to support the structural design of buildings using a more appropriate number of groups of structural members.

As explained above, the design support device of the present invention can assist in the structural design of buildings using appropriate structural members simply by inputting design conditions. This can be achieved by assigning predefined members to structural members so that the long-term stress conditions, short-term stress conditions, target values for story drift angles on each floor, and required horizontal bearing capacity, in that order, are satisfied for the building being designed.

1 is a block diagram showing a learning device and a design support device according to a first embodiment of the present invention; 1 is a functional block diagram showing a design support apparatus according to a first embodiment of the present invention; FIG. 10 is a diagram illustrating an example of a design condition input screen. FIG. 10 is a diagram for explaining a method for generating a component list. FIG. 10 is a diagram for explaining a method for generating a component list. FIG. 10 is a graph showing the frequency of use of each predetermined member. 2 is a functional block diagram showing the configuration of a cross-sectional structure calculation unit of the design support apparatus according to the first embodiment of the present invention; FIG. FIG. 10 is a diagram for explaining member information of a structural member. FIG. 10 is a diagram illustrating an example of a trained model for cross-section calculation. FIG. 2 is a diagram for explaining the center of gravity and center of rigidity of a structural member. FIG. 10 is a diagram showing an example of a table for determining a structural characteristic coefficient. FIG. 10 is a diagram showing an example of a table for determining a structural characteristic coefficient. FIG. 10 is a diagram illustrating an example of a grouping result for a grouping plan. FIG. 10 is a diagram illustrating an example of a grouping result for a grouping plan. FIG. 10 is a diagram illustrating an example of a grouping result for a grouping plan. 1 is a functional block diagram showing a learning device according to a first embodiment of the present invention; 3 is a flowchart showing the contents of a design support processing routine of the design support apparatus according to the first embodiment of the present invention; 10 is a flowchart showing a flow of processing for changing the allocation of default members in the design support apparatus according to the first embodiment of the present invention. 4 is a flowchart showing the flow of grouping processing in the design support apparatus according to the first embodiment of the present invention. FIG. 10 is a diagram illustrating an example of a trained model for grouping.

The following describes in detail an embodiment of the present invention with reference to the drawings.

[First embodiment]
<Configuration of the design support device according to the first embodiment of the present invention>
As shown in FIG. 1, a design support device 100 according to a first embodiment of the present invention includes a CPU 12, a graphics card 13, a GPU 14, a RAM 16, a HDD 18, a communication interface 21, and a bus 23 for interconnecting these components.

The CPU 12 and GPU 14 execute various programs. The RAM 16 is used as a work area when the CPU 12 executes the various programs. The HDD 18, which serves as a recording medium, stores various programs and data, including a program for executing the design support processing routine described below.

The design support device 100 in this embodiment is represented by functional blocks in accordance with the program for executing the design support processing routine, as shown in Figure 2. The design support device 100 includes an input unit 10, a calculation unit 20, and an output unit 50.

The input unit 10, operated by the designer, accepts information on multiple predefined components, which are structural components of a building whose component information has been predetermined.

For example, through operation by a designer, component information including component rank, section modulus, cross-sectional area, and external size is accepted for each of multiple predefined components, which are structural components of a building for which component information has been predetermined.

The input unit 10 also accepts input of a building model, which is a model of the building to be designed and includes multiple structural members (columns, beams, walls, braces, etc.), through operation by the designer, and also accepts design conditions related to the building to be designed.

For example, the designer operates the input screen in Figure 3 to accept design conditions, including the specification of the rank range for column-beam braces, by placing multiple structural members for each type of structural member (columns, beams, walls, braces, etc.) in the building model.

For example, design conditions include long-term stress conditions for the building being designed, short-term stress conditions, and target values for the story drift angle of each floor.

The design conditions also include target values for the brace contribution rate and shear wall contribution rate, target values for the inspection ratio, target values for the horizontal bearing capacity margin, number of iterations, target values for the column-beam strength ratio, designation of the rank range for column-beam braced shear walls, or designation of material strength.

The input screen in Figure 3 shows an example of accepting the target value for the inspection ratio, the target value for the horizontal bearing capacity margin, whether or not to adjust the eccentricity ratio, the target value for the column-beam bearing capacity ratio, the number of stories to group for steel columns, the number of iterations, whether or not to consider RC members, whether or not to consider shear walls, the target value for the τ level during the primary design, and the target value for the column long-term axial force ratio. This input screen also shows an example of accepting the target value for the story drift angle, the specification of the column-beam brace rank range, and the specification of the strength for each floor.

The calculation unit 20 includes a component list generation unit 22, a cross-sectional structure calculation unit 24, and a grouping processing unit 28.

The component list generator 22 generates a component list that stores multiple predefined components for each component rank related to the structural components, based on information about multiple predefined components that are structural components of a building whose component information is predetermined, and that is arranged in ascending order by section modulus, cross-sectional area, or external size.

For example, for each component rank, default components are selected so that the combination of section modulus, cross-sectional area, and external size is sorted in ascending order (Figure 4), and a component list arranged in ascending order is generated (Figure 5).

More specifically, from the multiple predefined components of the component rank, the predefined component with the smallest section modulus, cross-sectional area, and outer size is first selected. Then, predefined components are repeatedly selected so that the section modulus, cross-sectional area, and outer size are the same or larger than the previously selected predefined component. This generates a component list consisting of predefined components sorted in ascending order of section modulus, cross-sectional area, and outer size combinations. Figure 4 shows an example in which circled dots indicate predefined components selected so that the section modulus, cross-sectional area, and outer size are the same or larger than the previously selected predefined component. Figure 5 shows an example in which the predefined components are arranged in the component list in the order in which the selected predefined components are lined up from the top right.

Furthermore, by analyzing the default components that are frequently used by designers and incorporating these into the component list, it is possible to select components that are closer to the designer's preference (Figure 6). Figure 6 shows an example in which the default components are sorted in descending order of frequency of use, and the top N default components are used to generate the component list.

The cross-sectional structure calculation unit 24 changes the default members to be assigned to each of the structural members of the building model so as to satisfy the accepted design conditions. At this time, the default members are assigned to each of the multiple structural members of the building model so as to satisfy the conditions related to long-term stress, the conditions related to short-term stress, the target value of the inter-story deformation angle of each floor, and the required horizontal bearing capacity in this order.
Specifically, as shown in FIG. 7, the cross-sectional structure calculation unit 24 includes a first assigning unit 30, a second assigning unit 32, a third assigning unit 34, and a fourth assigning unit 36.

The first assignment unit 30 inputs values related to the design conditions and component information, including positional information, for each structural component of the building model, and calculates the cross-section of the structural component using a trained model for cross-section calculation trained in advance by the learning device 200 (described below), and displays the calculation results. For example, as a calculation result, the structural component reflecting the calculated cross-section may be visually displayed by superimposing it on the volume of the building, or the calculation results for quantity, weight, and cost using the calculated cross-section of the structural component may be displayed.

The trained model for cross-section calculation takes as input data component information (length L, angle θ in Figure 8, position within the building (height position, position on the plane), floor height, component density (span), bearing area, loading conditions, shear force bearing rate of the associated frame, etc.), and outputs as output data cross-sectional information representing the cross section (component width D, component composition B, component thickness t, material strength, component weight, component performance, etc. in Figure 8) (see Figure 9). For example, as shown in Figure 9, a neural network can be used as an example of a model, and deep learning can be used as an example of a learning algorithm. The trained model for cross-section calculation is trained so that when component information from training data is input, the cross-sectional information from the training data is output.

The first assigning unit 30 then assigns a default component to each of the multiple structural components based on the cross section of the structural component and a component list of a component rank that satisfies the design conditions from a component list that stores multiple default components, which are structural components of a building whose component information has been predetermined and that has been prepared in advance for each component rank.

Specifically, for each of the multiple structural members included in the building model, a default member selected from a list of members within a specified rank range is assigned based on the cross-sectional calculation results. At this time, the default member corresponding to the cross-sectional calculation results is selected from the list of members.

In this case, if the specified rank range includes multiple component ranks, an integrated component list is generated by integrating the component lists for each of the multiple component ranks, and default components are selected from the integrated component list. When integrating component lists, default components are selected from the default components included in the component lists for the multiple component ranks so that the combinations of section modulus, cross-sectional area, and external size are in ascending order, and an integrated component list arranged in ascending order is generated.

Here, the center of gravity G and center of rigidity R in top view are determined by the arrangement of the predetermined members assigned to each of the multiple structural members, as shown in Figure 10. Figure 10 shows an example of the center of gravity G in top view, determined by the arrangement of the structural members indicated by circles, and an example of the center of rigidity R in top view, determined by the cross-section of the predetermined members assigned to the structural members.

The first assignment unit 30 then performs stress analysis on the building model including multiple structural members to which default members have been assigned, and, based on the results of the stress analysis, assigns default members to each of the multiple structural members from the member list or integrated member list so that the long-term stress conditions are met and the cross-section of the default member assigned to each of the multiple structural members is minimized.

In this case, a predetermined member is assigned to each of the multiple structural members so that the center of gravity G in a top view determined by the arrangement of the multiple structural members corresponds to the center of rigidity R in a top view determined by the cross section of the predetermined member assigned to the multiple structural members.

Specifically, the cross section of columns that are subject to a large amount of axial force is increased. Increasing the cross section of a column increases the column's horizontal rigidity, and therefore the horizontal force it bears.

Also, change the default members to be assigned according to the order of the member list or integrated member list. This is repeated until the long-term stress conditions are met.

The second assignment unit 32 then performs stress analysis on the building model including multiple structural members to which default members have been assigned, and, based on the results of the stress analysis, assigns default members from the member list or integrated member list to each of the multiple structural members so as to satisfy the conditions related to short-term stress.

Specifically, only the cross sections of the members that are insufficient for short-term stress are enlarged by the necessary amount. At this time, the default members to be assigned are changed according to the arrangement order in the member list or integrated member list. This is repeated until the conditions for short-term stress are met.

The third assignment unit 34 then performs stress analysis on the building model including multiple structural members to which default members have been assigned, and, based on the results of the stress analysis, assigns default members to each of the multiple structural members from the member list or integrated member list so as to satisfy the target value for the inter-story deformation angle for each floor.

At this point, the planar rigidity balance is already in place, so from this point on, changing the cross section of the components on a layer-by-layer basis will avoid changing the planar rigidity balance.

Also, the default components to be assigned are changed according to the arrangement order in the component list or integrated component list. This is repeated until the target value for the story drift angle for each floor is met.

The fourth assignment unit 36 changes the default members assigned to each of the multiple structural members based on the results of stress analysis of the building model in which default members have been assigned to each of the multiple structural members, so as to satisfy the target value of the column-beam strength ratio.

In this way, after adjusting the planar stiffness balance, the default members are assigned to meet the target column-to-beam strength ratio. This is because if this is done before adjusting the planar stiffness balance, it will conflict with the planar stiffness balance adjustment.

Also, before calculating the horizontal load-carrying capacity, default members are assigned to meet the target column-to-beam load-carrying capacity ratio. This is because if the horizontal load-carrying capacity calculation is performed after the calculation, the collapse pattern may change.

In addition, the assigned default members are changed according to the arrangement order of the member list or integrated member list. This is repeated until the target value of the column-beam strength ratio is met.
The fourth assigning unit 36 then obtains a structural characteristic coefficient from the member rank of the predetermined member assigned to each of the plurality of structural members, and calculates the required horizontal bearing capacity from the structural characteristic coefficient.

When calculating the structural characteristic coefficients, a table (see FIG. 11A) storing structural characteristic coefficients for each combination of the component rank of the column and beam component group, the component rank of the brace component group, and the brace contribution rate β _μ is referenced, and the structural characteristic coefficients for each floor are calculated from the component rank of the predetermined component assigned to each of the multiple structural components and the brace contribution rate obtained from the results of stress analysis on the building model.
Furthermore, by referring to a table (see FIG. 11B) that stores the structural characteristic coefficients for each combination of the member ranks of the column and beam member groups, the member ranks of the shear wall member groups, and the shear wall contribution rate β _μ , the structural characteristic coefficients for each floor are calculated from the member ranks of the predetermined members assigned to each of the multiple structural members and the shear wall contribution rate obtained from the results of stress analysis of the building model. The tables in FIGS. 11A and 11B are based on the Ministry of Land, Infrastructure, Transport and Tourism Notification No. 596 of May 18, 2007.

In addition, when calculating the required horizontal bearing capacity, the required horizontal bearing capacity is calculated using a formula that includes the structural characteristic coefficient.

Specifically, the required horizontal bearing capacity Qun for each floor is calculated using the following formula, based on the structural characteristic coefficients for each floor, the shape coefficients for each floor obtained from the results of stress analysis of the building model, and the seismic force generated during an earthquake.

Qun=Ds×Fes×Qud
= Ds × Fes × [W × Ci]
= Ds × Fes × [(W × (Z × Rt × Ai × Co)]

where Ds is the structural characteristic coefficient for each floor. Fes is the shape coefficient for each floor, and is a value determined by the rigidity coefficient based on the balance of deformation in the height direction and the eccentricity ratio based on the balance of deformation in the horizontal direction (degree of torsion). Qud is the seismic force generated on each floor during a major earthquake, and is given by Qud = W x Ci = W x Z x Rt x Ai x Co. W is the weight of the building supported by each floor, Ci is the story shear force coefficient for each floor, and is given by Ci = Z x Rt x Ai x Co. Z is a value set by the Ministry of Land, Infrastructure, Transport and Tourism based on past earthquake records, and is a value that quantifies the likelihood of an earthquake occurring and is determined by the address. Rt is the vibration characteristic coefficient, and is a value determined by ground information and the natural period of the building. A building's natural period is calculated based on the building height and structural type, and is therefore determined by ground information, building height, and structural type. Ai is the distribution of the earthquake story shear force coefficient in the height direction, and is a value determined by the building's natural period and building weight when Rt is calculated. Co is the standard shear force coefficient, which is 1.0 when calculating the required horizontal bearing capacity.

The fourth assignment unit 36 then repeatedly changes the default members assigned to each of the multiple structural members from the member list or integrated member list and calculates the required horizontal bearing capacity until the results of the stress analysis on the building model satisfy the calculated required horizontal bearing capacity. At this time, the default members to be assigned are changed in accordance with the arrangement order of the member list or integrated member list.

The grouping processing unit 28 performs grouping by classifying multiple structural members into multiple groups consisting of structural members that should have the same cross section, based on the characteristic quantities of each of the multiple structural members obtained from the results of stress analysis of a building model in which predetermined members are assigned to each of the multiple structural members.

Specifically, for each type of structural component, grouping is performed based on the distribution of the features of the structural component groups to be grouped. A clustering method can be used as an example of a grouping algorithm.

For example, a stress analysis is performed on a building model in which a predetermined member is assigned to each of multiple structural members, and the feature quantities of the structural member groups are determined based on the results of the stress analysis. The structural member groups are clustered by type based on the distribution of the feature quantities of the structural member groups, and the assignment of predetermined members to each structural member is changed so as to unify the cross sections of structural members in the same cluster. A stress analysis is then performed on the building model in which the changed predetermined members are assigned to each of multiple structural members, and the results of the stress analysis are output. The feature quantities include long-term axial force, short-term moment, short-term axial force, column length, column coordinates, etc. obtained as a result of the stress analysis.

In addition, multiple parameter sets consisting of grouping-related parameters are determined in advance, and multiple grouping results are obtained by performing grouping using each of the multiple parameter sets (Figures 12A to 12C).

The parameter set includes, for example, the value of K for clustering and a weight vector consisting of weights for each feature.

Figures 12A to 12C show an example of displaying three grouping results for three parameter sets. The lower parts of Figures 12A to 12C show enlarged views of the rectangular framed portion of the grouping results shown at the top.

<Configuration of the learning device according to the first embodiment of the present invention>
As shown in FIG. 1 above, the learning device 200 according to the first embodiment of the present invention, like the design support device 100, comprises a CPU 12, a graphics card 13, a GPU 14, a RAM 16, a HDD 18, a communication interface 21, and a bus 23 for interconnecting these.

The CPU 12 and GPU 14 execute various programs. The RAM 16 is used as a work area when the CPU 12 executes the various programs. The HDD 18 serves as a recording medium and stores various programs, including a program for executing the learning process, and various data.

The learning device 200 in this embodiment is represented by functional blocks in accordance with the program for executing the learning process, as shown in Figure 13. The learning device 200 includes an input unit 110, a calculation unit 120, and an output unit 150.

The input unit 110 accepts as input learning data that includes a combination of component information, including positional information of each structural component (columns, beams, walls, braces, etc.), obtained from the building's performance information, and the cross-section of the structural component.

The calculation unit 120 includes a learning unit 122.

The learning unit 122 obtains a trained model for cross-section calculation for each type of structural member based on multiple pieces of learning data received by the input unit 110.

In this embodiment, a trained model for cross-section calculation is generated for each type of structural member (column, beam, wall, brace, etc.) and output to the design support device 100 by the output unit 150.

<Operation of the learning device>
Next, the operation of the learning device 200 according to the first embodiment of the present invention will be described.

The input unit 110 receives as input learning data that includes a combination of component information, including positional information for each structural component (columns, beams, walls, braces, etc.), obtained from the building's performance information, and the cross-sections of the structural components. The learning unit 122 then obtains a trained model for cross-section calculation based on the multiple pieces of learning data received by the input unit 110.

<Operation of the design support device>
Next, the operation of the design support device 100 according to the first embodiment of the present invention will be described.

First, the input unit 10 receives information on multiple predefined components, which are structural components of a building whose component information has been predetermined, through operation by the designer. The component list generation unit 22 of the design support device 100 then generates a component list that stores multiple predefined components for each component rank related to the structural components, based on the information on the multiple predefined components, which are structural components of the building whose component information has been predetermined, and that is arranged in ascending order of the combination of section modulus, cross-sectional area, and external size.

Then, the input unit 10 receives input of a building model of the building to be designed, which includes multiple structural members (columns, beams, walls, braces, etc.), through operation by the designer. Also, when design conditions related to the building to be designed are received, the design support device 100 executes the design support processing routine shown in FIG. 14.

First, in step S100, the cross-sectional structural calculation unit 24 obtains a building model including the input structural members.

In step S102, the first assignment unit 30 calculates the cross section of each structural member of the building model using the trained model for cross section calculation based on the structural member's member information, and displays the calculation results. Then, for each of the multiple structural members, the first assignment unit 30 assigns a default member to each structural member based on the calculated cross section of the structural member and a member list or integrated member list of member ranks that satisfy the design conditions.

In step S104, the first assignment unit 30 to the fourth assignment unit 36 change the default members to be assigned to each of the structural members of the building model from the member list or integrated member list so as to satisfy the accepted design conditions.

In step S108, the grouping processing unit 28 performs grouping to classify the structural members into multiple groups consisting of structural members that should have the same cross section, based on the feature values of each of the structural members obtained from the results of stress analysis of the building model in which default members are assigned to each of the structural members. This grouping is performed for each grouping parameter set, and multiple grouping proposals are obtained.

In step S110, the grouping results for the multiple grouping proposals are displayed by the output unit 150, and the design support processing routine is terminated.

Step S104 above is implemented by the processing routine shown in Figure 15.

In step S112, the first assignment unit 30 performs stress analysis on the building model including multiple structural members to which default members have been assigned, and, based on the results of the stress analysis, assigns default members to each of the multiple structural members from the member list or integrated member list so that the long-term stress conditions are met and the cross-section of the default member assigned to each of the multiple structural members is minimized.

In step S114, the second assignment unit 32 performs stress analysis on the building model including multiple structural members to which default members have been assigned, and, based on the results of the stress analysis, assigns default members from the member list or integrated member list to each of the multiple structural members so as to satisfy the conditions regarding short-term stress.

In step S116, the third assignment unit 34 performs stress analysis on the building model including multiple structural members to which default members have been assigned, and, based on the results of the stress analysis, assigns default members to each of the multiple structural members from the member list or integrated member list so as to satisfy the target value of the inter-story deformation angle for each floor.

In step S118, the fourth assignment unit 36 changes the default members assigned to each of the multiple structural members based on the results of stress analysis of the building model in which default members have been assigned to each of the multiple structural members, so as to satisfy the target value of the column-to-beam strength ratio.

In step S120, the fourth assignment unit 36 determines a structural characteristic coefficient from the component rank of the default component assigned to each of the multiple structural components, and calculates the required horizontal bearing capacity from the structural characteristic coefficient. The fourth assignment unit 36 then repeatedly changes the default component assigned to each of the multiple structural components from the component list or integrated component list and calculates the required horizontal bearing capacity until the results of the stress analysis of the building model satisfy the calculated required horizontal bearing capacity, and then terminates the processing routine.

Step S108 above is implemented by the processing routine shown in Figure 16. This processing routine is repeatedly executed for each grouping parameter set.

In step S130, the grouping processing unit 28 performs stress analysis on the building model in which the default members have been assigned to each of the multiple structural members.

In step S132, the grouping processing unit 28 acquires the characteristic quantities of the structural member group based on the results of the stress analysis.

In step S134, the grouping processing unit 28 performs clustering of the structural member groups for each type of structural member based on the distribution of the feature quantities of the structural member groups.

In step S136, the grouping processing unit 28 changes the assignment of default members to each structural member so as to unify the cross sections of structural members in the same cluster.

In step S138, the grouping processing unit 28 performs stress analysis on the building model in which the changed default members have been assigned to each of the multiple structural members, outputs the results of the stress analysis, and terminates the processing routine.

As explained above, the design support device according to the first embodiment of the present invention can assist in the structural design of buildings using appropriate structural members simply by inputting design conditions. This can be achieved by assigning predefined members to structural members so that the long-term stress conditions, short-term stress conditions, target values for story deformation angles on each floor, and required horizontal bearing capacity of the building being designed are satisfied in that order.

In addition, by assigning predefined members to structural members based on the calculation results of the structural member's cross section and a member list in which predefined members are arranged in ascending order by section modulus, cross-sectional area, and external size, the system can assist in the structural design of buildings using appropriate structural members simply by inputting design conditions.

Furthermore, by repeatedly changing the default members assigned to each structural member in the order of the member list, in which the default members are arranged in ascending order of section modulus, cross-sectional area, and external size, until the accepted design conditions are met, the system can assist in the structural design of buildings using appropriate structural members simply by inputting the design conditions.

In addition, the system changes the default members assigned to each of multiple structural members to meet the received design conditions, then calculates the required horizontal bearing capacity. By repeating this process of changing the default members assigned to each of multiple structural members and calculating the required horizontal bearing capacity until the required horizontal bearing capacity is met, the system can support the structural design of buildings using structural members that meet the required horizontal bearing capacity, minimizing the number of calculation iterations, by simply inputting the design conditions.

Second Embodiment
Next, a second embodiment of the present invention will be described. Note that the configurations of the design support device and learning device of the second embodiment are similar to those of the first embodiment, so the same reference numerals are used and the description thereof will be omitted.

The second embodiment differs from the first embodiment in that grouping is performed using supervised learning.

<Configuration of the learning device according to the second embodiment of the present invention>
The input unit 110 of the learning device 200 according to the second embodiment of the present invention accepts as input learning data for cross-section calculation, similar to the first embodiment. The input unit 110 also accepts as input learning data including the structural member information of each of the two structural members, and a determination result for each structural member pair consisting of two structural members out of all structural members obtained from the building performance information about the structural members, as to whether or not the two structural members are grouped together based on the structural member information of each of the two structural members.

Specifically, for structural member pairs consisting of two structural members from all structural members, learning data is created from the building's performance information, including the member information of the two structural members (length L, angle θ, position within the building (height position, position on the plane), floor height, member density (span), bearing area, and other information characterizing the members (member width D, member thickness B, member thickness t, etc. in Figure 8 above)) and the results of a determination of whether or not the two structural members are grouped based on the structural member information for each of the two structural members. Then, for each structural member pair, learning data is received that includes a combination of the member information of the two structural members and the results of a determination of whether or not they are grouped.

In this embodiment, this learning data is accepted for each type of structural member (column, beam, wall, brace, etc.).

The learning unit 122 obtains a trained model for cross-section calculation, as in the first embodiment described above.

The learning unit 122 also obtains a trained model for grouping based on the training data.

Specifically, as shown in Figure 17, the trained model for grouping takes the feature quantities of two structural members as input data and the degree to which the two structural members should be grouped as output data. For example, a neural network can be used as an example of the model, and deep learning can be used as an example of the learning algorithm. A trained model for grouping is generated for each type of structural member (column, beam, wall, brace, etc.).

<Configuration of the design support device according to the second embodiment of the present invention>
The grouping processing unit 28 of the design support device 100 of the second embodiment calculates the degree of grouping for each structural member pair consisting of two structural members out of all the generated structural members for each type of structural member (column, beam, wall, brace, etc.) based on the feature values of each of the two structural members and the trained model for grouping, and groups the structural member pairs in descending order of the degree of grouping so as to achieve the specified number of groups.

Specifically, for each type of structural member (column, beam, wall, brace, etc.), the grouping processing unit 28 calculates the degree to which each structural member pair consisting of two structural members from all structural members should be grouped based on the structural member information for each of the two structural members and the trained model for grouping that type of structural member.

For example, for each pair of structural members, the member information of the two structural members (length, angle, position within the building (height position, position on the plane), floor height, member density (span), bearing area, and other information characterizing the members) is input into a trained grouping model to determine the degree to which they should be grouped.

The grouping processing unit 28 then repeatedly groups two structural members of a structural member pair in the same group in descending order of grouping degree, for each type of structural member (column, beam, wall, brace, etc.), until the specified number of groups is reached. This results in grouping results for the specified number of groups. The specified number of groupings is then changed in turn, and structural member pairs are grouped in the same manner. This results in grouping results for multiple grouping proposals.

The other configurations and operations of the design support device 100 and learning device 200 in the second embodiment are the same as those in the first embodiment, so explanations will be omitted.

As explained above, the design support device according to the second embodiment of the present invention assigns a default member to each of the multiple structural members of a building based on the received design conditions and required horizontal bearing capacity, calculates the degree of grouping based on the characteristic quantities of each of the multiple structural members obtained from the results of stress analysis of the building model, and performs grouping to categorize the multiple structural members. This makes it possible to support the structural design of a building using an appropriate number of groups of structural members simply by inputting the design conditions.

The present invention is not limited to the above-described embodiments, and various modifications and applications are possible without departing from the spirit and scope of the invention.

For example, in the above-described embodiment, an example was described in which the learning device and the design support device were configured as separate devices, but this is not limited to this, and the learning device and the design support device may also be configured as a single device.

The program of the present invention may also be provided stored on a storage medium.

10, 110 Input unit 12 CPU
20, 120 Calculation unit 21 Communication interface 22 Member list generation unit 24 Cross-sectional structure calculation unit 28 Grouping processing unit 30 First assignment unit 32 Second assignment unit 34 Third assignment unit 36 Fourth assignment unit 50, 150 Output unit 100 Design support device 122 Learning unit 200 Learning device

Claims (6)

an input unit that receives a building model of a building to be designed, the building including a plurality of structural members, and design conditions for the building to be designed, including long-term stress conditions, short-term stress conditions, and target values of inter-story deformation angles for each floor;
a first assigning unit that assigns predetermined members to each of the plurality of structural members based on a result of a stress analysis of the building model in which predetermined members selected from a member list storing predetermined members whose member information is predetermined are assigned to each of the plurality of structural members so that a condition regarding long-term stress is satisfied and a cross section of the predetermined member assigned to each of the plurality of structural members is minimized;
a second assignment unit that changes the predetermined members to be assigned to each of the plurality of structural members based on a result of a stress analysis of the building model in which the predetermined members are assigned to each of the plurality of structural members so as to satisfy a condition regarding short-term stress;
a third assignment unit that changes the predetermined members to be assigned to each of the plurality of structural members based on a result of a stress analysis of the building model in which the predetermined members are assigned to each of the plurality of structural members so as to satisfy a target value of an inter-story deformation angle of each floor;
a fourth assignment unit that calculates a required horizontal bearing capacity from the predetermined members assigned to each of the plurality of structural members, and changes the predetermined members assigned to each of the plurality of structural members so that a result of stress analysis on the building model satisfies the calculated required horizontal bearing capacity;
Including,
A design support device that executes allocation in the order of the first allocation unit, the second allocation unit, the third allocation unit, and the fourth allocation unit . The design support device according to claim 1, wherein the first assigning unit assigns the predetermined members to each of the plurality of structural members so that the center of gravity in a top view determined by the arrangement of the plurality of structural members corresponds to the center of rigidity in a top view determined by the cross section of the predetermined member assigned to the plurality of structural members. The design conditions further include a target value of a column-to-beam strength ratio,
3. The design support device according to claim 1, wherein the fourth allocation unit changes the predetermined members to be assigned to each of the plurality of structural members so as to satisfy the target value of the column-beam strength ratio based on the results of stress analysis of the building model in which the predetermined members are assigned to each of the plurality of structural members, and then calculates a required horizontal bearing capacity from the predetermined members assigned to each of the plurality of structural members, and changes the predetermined members to be assigned to each of the plurality of structural members so that the results of stress analysis of the building model satisfy the calculated required horizontal bearing capacity. The design conditions further include a range of component ranks,
The component list is a component list prepared for each component rank,
A design support device according to any one of claims 1 to 3, wherein when selecting a default component to be assigned to the structural component from the component list, the default component is selected from a component list of component ranks included in the range of component ranks. A design support device according to any one of claims 1 to 4, wherein the design conditions further include a target value for the contribution ratio of braces or shear walls, a target value for the inspection ratio, a target value for the horizontal bearing capacity margin, the number of iterations, or a specification of material strength. The design support device of any one of claims 1 to 5 further includes a grouping processing unit that performs grouping to classify the plurality of structural members into a plurality of groups consisting of structural members that should have the same cross section, based on the characteristic quantities of each of the plurality of structural members obtained from the results of stress analysis of the building model in which a predetermined member is assigned to each of the plurality of structural members.