Design method and device for buckling-restrained brace for reinforcing concrete frame structure

Abstract

The invention provides a design method and device for a buckling-restrained brace for reinforcing a concrete frame structure, and relates to the technical field of building design. The design method for the buckling-restrained brace for reinforcing the concrete frame structure comprises the steps that a concrete frame structure design drawing of a target building is obtained; according to the concrete frame structure design drawing, the position information of the first buckling-restrained brace capable of being arranged of the target building is obtained through the buckling-restrained brace position prediction model; wherein the anti-buckling support position prediction model is a machine learning model obtained by training a training data set; and according to the position information of the first buckling-restrained brace capable of being arranged, the buckling-restrained brace design of the target building is determined. According to the method, the buckling-restrained brace design for reinforcing the concrete frame structure can be efficiently and reliably completed.

Description

Technical Field

[0001] The present invention relates to the technical field of building design, and in particular to a buckling-resistance brace design method and device for reinforcing a concrete frame structure. Background Art

[0002] With the accelerated pace of urbanization and the continuous extension of the service life of buildings, the safety, stability and seismic performance of existing building structures have become increasingly critical issues that need to be urgently addressed in the engineering field. In the face of possible earthquake disasters, it is particularly important to ensure the seismic resistance of building structures. To this end, my country continues to update the seismic parameter zoning map and proposes more stringent earthquake design standards for different regions. However, this series of measures also reveals a grim reality: many old buildings have been unable to meet the new requirements of current structural stiffness due to technical limitations in design and lagging seismic concepts. Therefore, it is urgent to strengthen and renovate the structure to improve its seismic performance.

[0003] Among the many reinforcement methods, adding anti-buckling braces is highly favored due to its unique advantages. As an efficient seismic component, anti-buckling braces can not only significantly improve the overall stiffness and bearing capacity of the structure, but also have excellent energy dissipation and shock absorption capabilities, which can effectively reduce the impact and response of earthquakes on the structure, thereby ensuring the safety and stability of the building during earthquakes. However, the traditional anti-buckling brace design process is complicated and cumbersome, and often requires engineers to conduct multiple rounds of verification and optimization based on their rich experience, which not only consumes a lot of time and energy, but also seriously affects the design efficiency.

[0004] Therefore, how to efficiently and reliably complete the buckling-resistance brace design for reinforced concrete frame structures is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of the above problems existing in the prior art, the present invention provides a method and device for designing anti-buckling braces for reinforcing a concrete frame structure, so as to efficiently and reliably complete the design of anti-buckling braces for reinforcing a concrete frame structure.

[0006] The invention provides a buckling-resistance brace design method for reinforcing a concrete frame structure, comprising the following steps.

[0007] Acquire a concrete frame structure design drawing of a target building; obtain position information of a first arrangable anti-buckling brace of the target building using a buckling-resistance brace position prediction model based on the concrete frame structure design drawing; wherein the buckling-resistance brace position prediction model is a machine learning model trained using a training data set; determine the buckling-resistance brace design of the target building based on the position information of the first arrangable anti-buckling brace.

[0008] According to a buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention, the method comprises: extracting the position information of a plurality of building components from the concrete frame structure design drawing by using a buckling-resistance brace position prediction model; wherein the position information of each building component is represented by a single-channel feature matrix, each element in the single-channel feature matrix corresponds to a position in the concrete frame structure design drawing, the element in the single-channel feature matrix is ​​a first value, indicating that the building component exists at the position in the concrete frame structure design drawing corresponding to the element, and the element in the single-channel feature matrix is ​​a second value, indicating that the building component does not exist at the position in the concrete frame structure design drawing corresponding to the element; constructing a multi-channel feature matrix according to the position information of the plurality of building components; wherein the multi-channel feature matrix is ​​composed of a plurality of single-channel feature matrices, each of which corresponds to a type of building component; and processing the multi-channel feature matrix by using the buckling-resistance brace position prediction model to obtain the position information of the first buckling-resistance brace that can be arranged.

[0009] According to a buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention, the position information of the plurality of building components includes the position information of beams, and the buckling-resistance brace position prediction model is used to process the multi-channel feature matrix to obtain the position information of the first arrangable buckling-resistance brace, comprising: inputting the multi-channel feature matrix into the buckling-resistance brace position prediction model to obtain the position information of the initial arrangable buckling-resistance brace output by the buckling-resistance brace position prediction model; wherein the position information of the initial arrangable buckling-resistance brace is in the form of a single-channel feature matrix; and using the beam position information as a mask and utilizing a dot multiplication operation to process the position information of the initial arrangable buckling-resistance brace to obtain the position information of the first arrangable buckling-resistance brace.

[0010] According to a buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention, the buckling-resistance brace design of the target building is determined based on the position information of the first arrangeable buckling-resistance brace, comprising: obtaining the position characteristics of the buckling-resistance brace from the position information of the first arrangeable buckling-resistance brace; wherein the position characteristics at least include: the relative coordinates of the support midpoint of the buckling-resistance brace in the x-direction, the relative coordinates of the support midpoint of the buckling-resistance brace in the y-direction, the arrangement direction of the buckling-resistance brace and the number of adjacent components of the buckling-resistance brace; using a preset clustering algorithm, processing the position characteristics of all the buckling-resistance braces to obtain the classification information of the buckling-resistance braces in the position information of the arrangeable buckling-resistance braces; processing the position information of the arrangeable buckling-resistance brace based on the classification information of the buckling-resistance brace to obtain the position information of the second arrangeable buckling-resistance brace; and determining the buckling-resistance brace design of the target building based on the position information of the second arrangeable buckling-resistance brace.

[0011] According to a buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention, the buckling-resistance brace design of the target building is determined according to the position information of the second buckling-resistance brace that can be arranged, including: obtaining a plurality of positions where the buckling-resistance brace can be arranged in the concrete frame structure design drawing according to the position information of the second buckling-resistance brace that can be arranged; taking the plurality of positions where the buckling-resistance brace can be arranged and the side length of the equivalent cross section of the steel core of the buckling-resistance brace corresponding to each position as optimization variables, and establishing an objective function based on a preset optimization target; wherein the optimization target includes mechanical properties or material usage; taking the optimization objective function value as the target, solving the objective function using a preset optimization algorithm, obtaining the position plane layout information of the buckling-resistance brace and the side length of the equivalent cross section of the steel core of each buckling-resistance brace; determining the buckling-resistance brace design of the target building according to the position plane layout information of the buckling-resistance brace and the side length of the equivalent cross section of the steel core of each buckling-resistance brace.

[0012] According to a buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention, the buckling-resistance brace position prediction model is obtained by training in the following manner: constructing a training data set based on a plurality of designed buckling-resistance brace arrangeable position drawings; wherein the training data set includes the concrete frame structure design part of the buckling-resistance brace arrangeable position drawings as sample data, and the buckling-resistance brace design part of the buckling-resistance brace arrangeable position drawings as labels; constructing an adversarial network composed of a generator and a discriminator; wherein the generator is used to generate predicted position information of arrangeable buckling-resistance braces, and the discriminator is used to evaluate the rationality of the predicted position information of arrangeable buckling-resistance braces; using the training data set and based on the adversarial network, adversarially training the generator and the discriminator until the training completion condition is met; and using the trained generator as the buckling-resistance brace position prediction model.

[0013] The present invention also provides a buckling-resistance brace design device for reinforcing a concrete frame structure, comprising the following modules: The first acquisition module is used to acquire the concrete frame structure design drawings of the target building; the second acquisition module is used to obtain the position information of the first arrangable anti-buckling brace of the target building based on the concrete frame structure design drawings and the anti-buckling brace position prediction model; wherein the anti-buckling brace position prediction model is a machine learning model trained using a training data set; the determination module is used to determine the anti-buckling brace design of the target building based on the position information of the first arrangable anti-buckling brace.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the anti-buckling support design method for reinforcing a concrete frame structure as described in any one of the above-mentioned methods is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the anti-buckling brace design method for reinforcing a concrete frame structure as described in any one of the above.

[0016] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for designing anti-buckling braces for reinforcing a concrete frame structure as described in any one of the above is implemented.

[0017] The buckling-resistance brace design method and device for reinforced concrete frame structure provided by the present invention efficiently obtains accurate position information of the target building where the buckling-resistance brace can be arranged based on the concrete frame structure design drawings, using the powerful data processing capability of the buckling-resistance brace position prediction model and the prior knowledge obtained from the training data set. According to the position information of the buckling-resistance brace where the buckling-resistance brace can be arranged, the reasonable design of the buckling-resistance brace of the target building is determined, thereby efficiently and reliably completing the buckling-resistance brace design for reinforced concrete frame structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is one of the flow diagrams of the buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention.

[0020] Figure 2 This is the second flow chart of the buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention.

[0021] Figure 3 This is the third flow chart of the buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention.

[0022] Figure 4 It is a flow chart of the training method of the buckling-resistance brace position prediction model provided by the present invention.

[0023] Figure 5 It is a schematic diagram of the process of training the anti-buckling brace position prediction model based on the generative adversarial network provided by the present invention.

[0024] Figure 6 It is a schematic diagram of the model architecture of the generator and discriminator provided by the present invention.

[0025] Figure 7 It is a schematic diagram of clustering of possible arrangement positions of the buckling-restrained braces provided by the present invention.

[0026] Figure 8 This is the buckling-resistance brace optimization design process provided by the present invention.

[0027] Fig. 9 This is the Online Learning optimization process provided by the present invention.

[0028] Fig.10This is the final arrangement position and size of the optimized anti-buckling brace provided by the present invention.

[0029] Fig.11 It is a comparison of the interlayer displacement angles before and after the optimization provided by the present invention.

[0030] Fig.12 It is a structural schematic diagram of the buckling-resistance brace design device for reinforcing a concrete frame structure provided by the present invention.

[0031] Fig.13 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Combine the following Figure 1-Figure 12 The buckling-restrained brace design method for reinforcing a concrete frame structure of the present invention is described.

[0034] Figure 1 This is one of the flow charts of the buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101: Obtain the concrete frame structure design drawings of the target building.

[0035] The target building is a building whose concrete frame structure is reinforced with buckling-resistance braces designed.

[0036] Step 102: According to the concrete frame structure design drawing, using the buckling restraint brace position prediction model, obtain the position information of the first buckling restraint brace that can be arranged in the target building.

[0037] The anti-buckling brace position prediction model is a machine learning model trained using a training data set.

[0038] In the specific implementation process, the anti-buckling support position prediction model can be constructed based on multiple machine learning models. As an example, the anti-buckling support position prediction model can be a convolutional neural network model including a convolution layer, a pooling layer (downsampling), a residual block and an upsampling layer.

[0039] In the specific implementation process, the input of the buckling restraint brace position prediction model is the spatial characteristics of the building components extracted from the concrete frame structure design drawings, and the output is the position plan layout information of the buckling restraint brace in the concrete frame structure design drawings.

[0040] Extract the location information of multiple building components from the concrete frame structure design drawings. Building components may include but are not limited to: beams, walls, columns, doors and windows, etc. In the specific implementation process, the concrete frame structure design drawings in CAD form can be saved in dxf file format, and the Python open source library ezdxf can be used to extract the location information of building components from the drawings.

[0041] The location information of each building component is represented by a single-channel feature matrix. Each element in the single-channel feature matrix corresponds to a position in the concrete frame structure design drawing. The element is a first value (for example, 1), indicating that a building component exists at the position in the concrete frame structure design drawing corresponding to the element. The element in the single-channel feature matrix is ​​a second value (for example, 0), indicating that no building component exists at the position in the concrete frame structure design drawing corresponding to the element.

[0042] Just as an example, the single-channel characteristic matrix L of a beam is as follows: Among them, the first element of the single-channel feature matrix L is 1, indicating that there is a beam at the position (upper left corner) in the concrete frame structure design drawing corresponding to the element; the last element of the single-channel feature matrix L is 0, indicating that there is no beam at the position (lower right corner) in the concrete frame structure design drawing corresponding to the element.

[0043] According to the position information of multiple building components, a multi-channel feature matrix is ​​constructed. The multi-channel feature matrix is ​​composed of multiple single-channel feature matrices, and each single-channel feature matrix corresponds to a building component.

[0044] In the specific implementation process, the extracted single-channel feature matrices of all building components can be superimposed to form a multi-channel feature matrix. The multi-channel feature matrix includes the spatial features of all building components in the concrete frame structure design drawings.

[0045] The anti-buckling brace position prediction model is used to process the multi-channel feature matrix to obtain the position information of the first arrangable anti-buckling brace.

[0046] In a specific implementation process, the multi-channel feature matrix may be used as an input of a buckling restraint brace position prediction model, and the buckling restraint brace position prediction model outputs position information of a first arrangable buckling restraint brace.

[0047] The first position information where the buckling-restraining brace can be arranged is used to indicate information on the position where the buckling-restraining brace can be arranged in the concrete frame structure design drawing.

[0048] The position information of the first arrangable anti-buckling brace can be in various forms and is not limited by the description of this specification. In some embodiments, the position information of the first arrangable anti-buckling brace is in the form of a single-channel feature matrix, each element in the single-channel feature matrix corresponds to a position in the concrete frame structure design drawing, the element is a first value, indicating that the position in the concrete frame structure design drawing corresponding to the element can be arranged with an anti-buckling brace, and the element in the single-channel feature matrix is ​​a second value, indicating that the position in the concrete frame structure design drawing corresponding to the element cannot be arranged with an anti-buckling brace.

[0049] In the specific implementation process, the multi-channel feature matrix is ​​input into the anti-buckling brace position prediction model to obtain the initial position information of the anti-buckling brace output by the anti-buckling brace position prediction model, and the initial position information of the anti-buckling brace is in the form of a single-channel feature matrix.

[0050] The initial position information of the anti-buckling brace that can be arranged is the position information of the anti-buckling brace that can be arranged output by the anti-buckling brace position prediction model. In some embodiments, in order to obtain a more accurate result, the position information of the beam can be used to optimize the initial position information of the anti-buckling brace that can be arranged. Specifically, the position information of the beam is used as a mask, and the point multiplication operation is used to process the initial position information of the anti-buckling brace that can be arranged to obtain the first position information of the anti-buckling brace that can be arranged. In the first position information of the anti-buckling brace that can be arranged, only the position where the beam exists can be arranged.

[0051] For more information about the training process, see Figure 4 The relevant content in will not be repeated here.

[0052] Step 103: Determine the buckling-restrained brace design of the target building according to the position information of the first arrangeable buckling-restrained brace.

[0053] In some embodiments, the buckling-restrained brace design of the target building may be determined based on the position information of the first arrangable buckling-restrained brace.

[0054] In some embodiments, in order to obtain a more accurate and reasonable buckling-resistance brace design for a target building, the position information of the first arrangeable buckling-resistance brace may be further optimized, and the buckling-resistance brace design for the target building may be determined based on the optimized position information of the first arrangeable buckling-resistance brace.

[0055] For an embodiment of further optimizing the position information of the first arrangable buckling-restrained brace, see Figure 2 and Figure 3 The relevant content in will not be repeated here.

[0056] Figure 2 This is the second flow chart of the buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention. Figure 2 As shown, the method includes the following: Step 201: Acquire a position feature of a buckling-restraint brace from position information of a first arrangable buckling-restraint brace.

[0057] The position features include at least: the relative coordinates of the midpoint of the buckling-resistance brace in the x-direction, the relative coordinates of the midpoint of the buckling-resistance brace in the y-direction, the arrangement direction of the buckling-resistance brace (in the x-direction or the y-direction), and the number of adjacent components of the buckling-resistance brace. The above relative coordinates are obtained with the center of the position information of the first arrangeable buckling-resistance brace as the coordinate origin.

[0058] Step 202: Using a preset clustering algorithm, the position features of all the buckling-resistance braces are processed to obtain classification information of the buckling-resistance braces in the position information where the buckling-resistance braces can be arranged.

[0059] The preset clustering algorithm may include but is not limited to: K-means, hierarchical clustering, etc.

[0060] In a specific implementation process, the optimal number of categories can be selected by evaluating the clustering effects (such as silhouette coefficient, SSE, etc.) under different numbers of categories. The position features of all buckling restraints in the position information of the first arrangable buckling restraint are input into the clustering algorithm, and the clustering algorithm divides the buckling restraints into different categories according to the selected number of categories based on the similarity of the position features.

[0061] Just as an example, Figure 7 As shown, different numbers of cluster categories are set according to the complexity of the concrete frame structure in the concrete frame structure design drawings, the possible locations of the buckling-resistance braces are classified, and the optimization variables are reduced.

[0062] Step 203: Process the position information of the buckling-resistance brace that can be arranged according to the classification information of the buckling-resistance brace to obtain the position information of the second buckling-resistance brace that can be arranged.

[0063] In a specific implementation process, the same category of anti-buckling braces output by the clustering algorithm can be used as a single anti-buckling brace, and the same anti-buckling brace arrangement is adopted at symmetrical positions, thereby effectively simplifying the position information of the first arrangeable anti-buckling brace and obtaining the position information of the second arrangeable anti-buckling brace.

[0064] Step 204: Determine the buckling-resistance brace design of the target building according to the position information of the second arrangable buckling-resistance brace.

[0065] In some embodiments, the buckling-restrained brace design of the target building may be determined based on the position information of the second arrangable buckling-restrained brace.

[0066] In some embodiments, the position information of the second arrangable buckling-resistance brace can be further optimized, and the buckling-resistance brace design of the target building can be determined according to the optimized position information of the second arrangable buckling-resistance brace. For details, see Figure 3 The relevant content in will not be repeated here.

[0067] Figure 3 This is the third flow chart of the buckling-resistance brace design method for reinforcing a concrete frame structure provided by the present invention. Figure 3 As shown, the method includes the following: Step 301: According to the second position information of the buckling-restrained brace that can be arranged, a plurality of positions where the buckling-restrained brace can be arranged in the concrete frame structure design drawing are obtained.

[0068] Step 302: Establish an objective function based on a preset optimization target, taking multiple positions where buckling-restrained braces can be arranged and the side length of the equivalent cross section of the steel core of the buckling-restrained brace corresponding to each position as optimization variables.

[0069] As an example only, considering that the number of buckling restraints that need to be added during structural reinforcement is generally limited and the construction needs to be as convenient as possible, it is assumed that the steel cores of all buckling restraints have the same size and are replaced with equivalent rectangular cross-sections. At the same time, the material strength grade is set to Q235. The value range and step size of the optimization variables set according to this embodiment are shown in Table 2.

[0070] Table 2. Type, value range and step size of optimization variables

[0071] In Table 2, 10 locations of buckling-resistance braces can be arranged as 10 optimization variables, with a total of 2^ 10 feasible solutions, 4 feasible solutions for supporting steel core, totaling 2^ 12 A feasible solution.

[0072] After determining the optimization variables, set the corresponding optimization goals. Since this embodiment mainly aims to strengthen the problem of insufficient structural stiffness, the mechanical performance requirements in the elastic stage are focused on. As an example only, according to the multiple positions where anti-buckling braces can be arranged and the equivalent cross-sectional side length of the steel core of the anti-buckling brace corresponding to each position, the mechanical calculation of the elastic stage under small earthquakes is performed using building structure modeling and analysis software (for example, Yingjianke), and the maximum inter-story displacement angles and the rigidity center and mass center distances of the concrete frame structure after the anti-buckling brace is arranged in the x-direction and y-direction are obtained, and the objective function is constructed using the following method.

[0073] First, the maximum inter-story displacement angular coefficients in the x and y directions are constructed and , the formula is as follows.

[0074] (1) (2) in, is the maximum inter-story displacement angle in the x direction, is the maximum inter-story displacement angle in the y direction, It is the recommended limit value of the inter-story displacement angle. A certain redundancy is given on the basis of the building seismic design code. For reinforced concrete frame structures, the value is 0.9 times of 1 / 550. The parameters 10 and 3 are the relative optimal values ​​obtained through multiple optimization attempts.

[0075] In addition, the setting of anti-buckling braces should ensure that the stiffness of the structure in two directions is close as much as possible, so as to control the difference in inter-story displacement angles in two directions. The inter-story displacement angle difference coefficient is constructed as shown in the following formula.

[0076] (3) The inter-story displacement angle difference coefficient is also a continuous differentiable function, but its weight is slightly smaller than the inter-story displacement angle. In the optimization process, the inter-story displacement angle limit requirement is met first, and the inter-story displacement angle difference requirement is considered second.

[0077] Further, control the distance between the center of mass and the center of rigidity To ensure that the structural torsion is controllable.

[0078] (4) is the distance between the center of mass and the center of rigidity of the structure, It is the maximum length of the structure in one direction.

[0079] Finally, in order to arrange the buckling-resistance brace on the outside of the structure as much as possible, the buckling-resistance brace external wall coefficient is set , as shown in the following formula.

[0080] (5) in, is the number of buckling-resistance braces arranged outside the structure, and is the total number of buckling-resistance braces to be arranged in the structure. The factor 5 is used to reduce the weight of this objective function.

[0081] Based on the above coefficients, the final objective function of the optimization is constructed. , priority is given to ensuring the inter-story displacement angle limit, followed by ensuring the stiffness in the x and y directions, and finally ensuring that the anti-buckling supports are arranged on the exterior wall as much as possible. The formula of the objective function is shown below.

[0082] (6) In some embodiments, the objective function may be established with the material usage as the optimization target. In this embodiment, the objective function calculates the total mass of the buckling restraint braces that can be arranged according to the multiple positions where the buckling restraint braces can be arranged and the side length of the steel core equivalent cross section of the buckling restraint brace corresponding to each position.

[0083] Step 303: With the optimization of the objective function value as the goal, the objective function is solved by using a preset optimization algorithm to obtain the positional planar layout information of the buckling-restrained braces and the side length of the equivalent cross section of the steel core of each buckling-restrained brace.

[0084] The optimization algorithm may include but is not limited to: genetic algorithm, particle swarm algorithm, annealing algorithm, online learning algorithm, etc.

[0085] Just as an example, Figure 8 As shown in the figure, Yingjianke Y-GAMA is used to realize the parametric modeling and optimization of the structure. First, the base layer is determined, and then the base layer is used. Figure 2 The method is used to determine the position information of the second arrangable buckling-resistance support, which is used as the reference layer. The arrangement position and size of the buckling-resistance support in the reference layer are used as optimization variables to achieve parametric modeling. Secondly, the floors are assembled, the vertical assembly of the structure is completed according to the floor information, and the buckling-resistance support is arranged on the remaining floors by the vertical alignment method. After the floor assembly is completed, the design conditions are set and the mechanical calculation is performed, and the optimizer module of Y-GAMA is called to realize the optimal design of the buckling-resistance support in this step.

[0086] Taking a reinforced concrete frame structure as an example, the basic information of the case is as follows: the number of floors is 3, the floor height is 3500mm, the seismic fortification intensity is 9 degrees (0.4g), the site category is Class II, the seismic level is 4, the earthquake group is Group 1, the fortification category is Class C, and the characteristic period is 0.35s.

[0087] First, based on the anti-buckling brace position prediction model, the position information of the first anti-buckling brace that can be arranged is generated, and then the position information of the first anti-buckling brace that can be arranged is optimized by using a clustering algorithm to obtain the position information of the second anti-buckling brace that can be arranged. Finally, the specific position of the anti-buckling brace is arranged by the optimization algorithm in this step.

[0088] The optimization algorithm uses Y-GAMA online learning. The optimization process is as follows: Fig. 9 As shown, the final objective function value is 0.594, and the optimization results are as follows Fig.10 shown.

[0089] The final layout position and dimensions of the anti-buckling brace after optimization are as follows: Fig.10 As shown in the figure, the buckling-resistance brace layout is reasonable and symmetrical, which is consistent with the structural design experience. The structure is analyzed in the elastic stage, and the effects before and after optimization are compared. The inter-story displacement angle is compared. Fig.11 As shown in the figure, after reinforcement with anti-buckling braces, the inter-story displacement angles in both directions meet the limit requirements, and the stiffness is basically close, which meets the mechanical performance requirements. At the same time, other overall indicators and component indicators of the structure are checked, and all indicators meet the requirements of the structural specifications, further verifying the rationality of the reinforcement plan.

[0090] Step 304: Determine the buckling-restrained brace design of the target building based on the positional planar layout information of the buckling-restrained braces and the side length of the steel core equivalent cross section of each buckling-restrained brace.

[0091] In the specific implementation process, the specific dimensions of the inner steel core and outer sleeve of the anti-buckling support can be determined according to the side length of the equivalent cross-section of the steel core of the anti-buckling support. For example, the diameter or side length of the inner steel core is determined according to the side length of the equivalent cross-section of the steel core of the anti-buckling support. In addition, the material properties of the steel core (such as yield strength, tensile strength, etc.) and the requirements of the manufacturing process must also be considered. For another example, the outer sleeve needs to be able to accommodate the inner steel core and provide it with sufficient constraints to prevent buckling when subjected to force. Therefore, the inner diameter of the sleeve should be slightly larger than the outer diameter of the steel core, and the wall thickness of the sleeve must meet the requirements of structural strength and stiffness. The length of the sleeve is determined according to the overall length and node structure of the anti-buckling support.

[0092] After determining the specific dimensions of the inner steel core and outer sleeve of the buckling restraint, the node structure design of the connection is realized. For example, according to the position and function of the buckling restraint in the structure, the appropriate node form can be selected, such as welded node, bolted node, etc., and the node needs to be able to withstand the force and moment transmitted by the buckling restraint and ensure the reliability and durability of the connection; for the selected node form, detailed detail design is carried out, including the size of the weld, the specification and arrangement of the bolts, the size and shape of the connection plate, etc.

[0093] After the node structure design at the connection is completed, the design results of the anti-buckling support are drawn in the concrete frame structure design drawings.

[0094] Figure 4 FIG. 1 is a flow chart of a method for training a buckling-resistance brace position prediction model provided by the present invention. Figure 4 As shown, the method includes the following: Step 401: construct a training data set based on a plurality of drawings of possible locations of designed buckling-resistance braces.

[0095] The training data set includes the concrete frame structure design part of the buckling restraint brace arrangement position drawings as sample data, and the buckling restraint brace design part of the buckling restraint brace arrangement position drawings as labels.

[0096] In the specific implementation process, a large number of designed buckling-resistance brace layout drawings can be collected, which include the designed concrete frame structure design part and the buckling-resistance brace design part. The concrete frame structure design part in the collected buckling-resistance brace layout drawings is used as the sample number, and the buckling-resistance brace design part in the buckling-resistance brace layout drawings is used as the label.

[0097] Step 402: construct an adversarial network consisting of a generator and a discriminator.

[0098] The generator is used to generate the predicted position information of the anti-buckling brace, and the discriminator is used to evaluate the rationality of the predicted position information of the anti-buckling brace.

[0099] In the specific implementation process, the generator can be constructed based on a variety of machine learning models. As an example, the generator can be a convolutional neural network model including a convolution layer, a pooling layer (downsampling), a residual block, and an upsampling layer.

[0100] In a specific process, the discriminator can be constructed based on neural networks of various structures. As an example only, the discriminator can be constructed based on a convolutional neural network.

[0101] Step 403: Using the training data set, based on the adversarial network, conduct adversarial training on the generator and the discriminator until the training completion conditions are met.

[0102] In the specific implementation process, a multi-channel feature matrix is ​​extracted from the sample data of the training data set. For a detailed description of the multi-channel feature matrix, see Figure 1 The relevant content in will not be repeated here.

[0103] Input the multi-channel feature matrix into the generator. Figure 6 As shown, the generator first downsamples the input multi-channel feature matrix to extract features of different scales, then fuses the features through the residual block, and finally generates the arrangable positions of the anti-buckling braces through upsampling.

[0104] The multi-channel feature matrix and the arrangeable positions of the anti-buckling brace generated by the generator are used as the input of the discriminator. The discriminator obtains a result matrix for discrimination through downsampling processing. The result matrix is ​​expressed as a series of numerical values ​​or probability values. These numerical values ​​or probability values ​​reflect the possibility of each position among the arrangeable positions of the anti-buckling brace output by the generator being discriminated as a reasonable anti-buckling brace arrangement position.

[0105] In the specific training process, Figure 5 As shown in the figure, the generator and the discriminator are trained alternately, and the parameters of the generator and the discriminator are adjusted respectively based on the loss function (e.g., cross entropy loss) using a preset optimization algorithm (e.g., gradient descent optimization algorithm). The generator generates fake samples of the positions where the buckling-resistance brace can be arranged based on the multi-channel feature matrix, and mixes these fake samples with the real samples in the data set for the discriminator to learn. Through multiple rounds of optimization training, the generator is able to generate more realistic samples, while the discriminator gradually enhances its ability to distinguish between true and false.

[0106] Through alternating training, the generator can eventually generate arrangable locations of buckling restraint braces that strictly comply with building regulations where buckling restraint braces cannot be arranged in areas such as corridors, foyers, balconies, stairs and entrances.

[0107] The training completion conditions also include the convergence of the loss function and the number of training times reaching the preset training times threshold.

[0108] Step 404: Use the trained generator as a buckling-resistance brace position prediction model.

[0109] In order to evaluate the effect of the anti-buckling brace position prediction model trained by the present invention, three evaluation indicators are used: accuracy , recall rate as well as , are defined as shown in equations (7) – (9): (7) (8) (9) in, It indicates the predicted correct possible locations of buckling-restrained braces. represents the predicted possible locations of buckling-restrained braces, represents the actual arrangable positions of the anti-buckling brace. The precision considers whether the predicted anti-buckling brace is accurate, and the recall rate considers whether all the real arrangable positions of the anti-buckling brace can be found. The precision and recall results are considered comprehensively.

[0110] The buckling restraint brace position prediction model was tested using the test data set. The test results are shown in Table 1 below.

[0111] Table 1. Prediction results of possible locations of buckling-resistance braces

[0112] As shown in Table 1, the buckling-resistance brace position prediction model provided by the present invention can output a prediction result with relatively high accuracy.

[0113] The anti-buckling brace design device for reinforcing a concrete frame structure provided by the present invention is described below. The anti-buckling brace design device for reinforcing a concrete frame structure described below and the anti-buckling brace design method for reinforcing a concrete frame structure described above can be referenced to each other.

[0114] Fig.12 Schematic diagram of the structure of the buckling-resistance brace design device for reinforcing a concrete frame structure provided by the present invention. Fig.12 As shown, the device includes the following modules.

[0115] The first acquisition module 1210 is used to acquire the concrete frame structure design drawings of the target building.

[0116] The second acquisition module 1220 is used to obtain the position information of the first arrangable anti-buckling brace of the target building according to the concrete frame structure design drawings and using the anti-buckling brace position prediction model; wherein the anti-buckling brace position prediction model is a machine learning model trained using a training data set.

[0117] The determination module 1230 is used to determine the buckling-restrained brace design of the target building according to the position information of the first arrangeable buckling-restrained brace.

[0118] Fig.13 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.13 As shown, the electronic device may include: a processor 1310, a communication interface 1320, a memory 1330 and a communication bus 1340, wherein the processor 1310, the communication interface 1320 and the memory 1330 communicate with each other through the communication bus 1340. The processor 1310 may call the logic instructions in the memory 1330 to execute the buckling-resistance brace design method for the reinforcement of the concrete frame structure, the method comprising: obtaining the concrete frame structure design drawing of the target building; obtaining the position information of the first buckling-resistance brace of the target building according to the concrete frame structure design drawing by using the buckling-resistance brace position prediction model; wherein the buckling-resistance brace position prediction model is a machine learning model obtained by training with the training data set; and determining the buckling-resistance brace design of the target building according to the position information of the first buckling-resistance brace.

[0119] In addition, the logic instructions in the above-mentioned memory 1330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0120] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the anti-buckling brace design method for concrete frame structure reinforcement provided by the above-mentioned methods, and the method includes: obtaining a concrete frame structure design drawing of a target building; according to the concrete frame structure design drawing, using an anti-buckling brace position prediction model to obtain the position information of a first arrangable anti-buckling brace of the target building; wherein the anti-buckling brace position prediction model is a machine learning model trained using a training data set; and according to the position information of the first arrangable anti-buckling brace, determining the anti-buckling brace design of the target building.

[0121] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the anti-buckling brace design method for reinforcing a concrete frame structure provided by the above-mentioned methods, the method comprising: obtaining a concrete frame structure design drawing of a target building; obtaining position information of a first arrangable anti-buckling brace of the target building using an anti-buckling brace position prediction model according to the concrete frame structure design drawing; wherein the anti-buckling brace position prediction model is a machine learning model trained using a training data set; and determining the anti-buckling brace design of the target building according to the position information of the first arrangable anti-buckling brace.

[0122] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0123] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A buckling-restrained brace design method for reinforcing a concrete frame structure, characterized in that: include: Obtain the concrete frame structure design drawings of the target building; According to the concrete frame structure design drawing, using the anti-buckling brace position prediction model, the position information of the first arrangable anti-buckling brace of the target building is obtained; wherein the anti-buckling brace position prediction model is a machine learning model trained using a training data set; The buckling-resistance brace design of the target building is determined according to the position information of the first arrangeable buckling-resistance brace.

2. The buckling-resistance brace design method for reinforcing a concrete frame structure according to claim 1, characterized in that: The method of obtaining the position information of the first arrangable buckling-resistance brace of the target building by using the buckling-resistance brace position prediction model according to the concrete frame structure design drawing comprises: Extracting location information of a plurality of building components from the concrete frame structure design drawing; wherein the location information of each building component is represented by a single-channel feature matrix, each element in the single-channel feature matrix corresponds to a position in the concrete frame structure design drawing, the element in the single-channel feature matrix is ​​a first value, indicating that the building component exists at the position in the concrete frame structure design drawing corresponding to the element, and the element in the single-channel feature matrix is ​​a second value, indicating that the building component does not exist at the position in the concrete frame structure design drawing corresponding to the element; Constructing a multi-channel feature matrix according to the position information of the plurality of building components; wherein the multi-channel feature matrix is ​​composed of a plurality of single-channel feature matrices, and each single-channel feature matrix corresponds to one of the building components; The multi-channel feature matrix is ​​processed by using the anti-buckling brace position prediction model to obtain the position information of the first arrangeable anti-buckling brace.

3. The buckling-resistance brace design method for reinforcing a concrete frame structure according to claim 2, characterized in that: The position information of the plurality of building components includes the position information of beams, and the step of using the buckling-restrained brace position prediction model to process the multi-channel feature matrix to obtain the position information of the first arrangable buckling-restrained brace includes: Inputting the multi-channel characteristic matrix into the anti-buckling brace position prediction model to obtain the position information of the initial arrangable anti-buckling brace output by the anti-buckling brace position prediction model; wherein the position information of the initial arrangable anti-buckling brace is in the form of a single-channel characteristic matrix; The position information of the beam is used as a mask and a dot multiplication operation is used to process the position information of the initial arrangable buckling-restrained brace to obtain the position information of the first arrangable buckling-restrained brace.

4. The buckling-restrained brace design method for reinforcing a concrete frame structure according to claim 3, characterized in that: The step of determining the buckling-resistance brace design of the target building according to the position information of the first buckling-resistance brace that can be arranged includes: Acquire the position characteristics of the anti-buckling brace from the position information of the first arrangable anti-buckling brace; wherein the position characteristics at least include: the relative coordinates of the support midpoint of the anti-buckling brace in the x-direction, the relative coordinates of the support midpoint of the anti-buckling brace in the y-direction, the arrangement direction of the anti-buckling brace, and the number of adjacent components of the anti-buckling brace; Using a preset clustering algorithm, the position features of all the anti-buckling braces are processed to obtain classification information of the anti-buckling braces in the position information where the anti-buckling braces can be arranged; Processing the position information of the arrangable buckling-resistance brace according to the classification information of the buckling-resistance brace to obtain the position information of the second arrangable buckling-resistance brace; The buckling-resistance brace design of the target building is determined according to the position information of the second arrangeable buckling-resistance brace.

5. The buckling-resistance brace design method for reinforcing a concrete frame structure according to claim 3, characterized in that: The step of determining the buckling-resistance brace design of the target building according to the position information of the second buckling-resistance brace that can be arranged comprises: According to the second position information where the buckling-restrained brace can be arranged, a plurality of positions where the buckling-restrained brace can be arranged in the concrete frame structure design drawing are obtained; Taking the multiple positions where the buckling-restrained braces can be arranged and the side length of the equivalent cross section of the steel core of the buckling-restrained brace corresponding to each position as optimization variables, an objective function is established based on a preset optimization target; wherein the optimization target includes mechanical properties or material usage; With the optimization of the objective function value as the goal, the objective function is solved by using a preset optimization algorithm to obtain the positional plane layout information of the buckling-restrained brace and the side length of the equivalent cross section of the steel core of each buckling-restrained brace; The buckling-resistance brace design of the target building is determined according to the positional planar layout information of the buckling-resistance braces and the side length of the steel core equivalent cross section of each buckling-resistance brace.

6. The buckling-restrained brace design method for reinforcing a concrete frame structure according to claim 3, characterized in that: The buckling-resistance brace position prediction model is obtained by training in the following manner: A training data set is constructed based on a plurality of designed buckling-resistance brace layout drawings; wherein the training data set includes a concrete frame structure design portion of the buckling-resistance brace layout drawings as sample data, and a buckling-resistance brace design portion of the buckling-resistance brace layout drawings as labels; Constructing an adversarial network consisting of a generator and a discriminator; wherein the generator is used to generate information about predicted locations where anti-buckling braces can be arranged, and the discriminator is used to evaluate the rationality of the information about predicted locations where anti-buckling braces can be arranged; Using the training data set, based on the adversarial network, the generator and the discriminator are subjected to adversarial training until a training completion condition is met; The trained generator is used as the anti-buckling brace position prediction model.

7. A buckling-resistance brace design device for reinforcing a concrete frame structure, characterized in that: include: The first acquisition module is used to acquire the concrete frame structure design drawings of the target building; A second acquisition module is used to obtain the position information of the first arrangable anti-buckling brace of the target building according to the concrete frame structure design drawing and using the anti-buckling brace position prediction model; wherein the anti-buckling brace position prediction model is a machine learning model trained using a training data set; A determination module is used to determine the buckling-restrained brace design of the target building according to the position information of the first arrangable buckling-restrained brace.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the buckling-resistance brace design method for reinforcing a concrete frame structure as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for designing buckling-restrained braces for reinforcing a concrete frame structure as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for designing buckling-restrained braces for reinforcing a concrete frame structure as claimed in any one of claims 1 to 6 is implemented.

Images