An optimization method and device for the layout of energy-consuming nodes in a structure

Abstract

The present invention provides a method and device for optimizing the layout of energy-dissipating nodes in a structure, which relates to the technical field of building structure design. The method includes establishing an energy-dissipating node library and a corresponding hysteretic model library, generating multiple structural schemes based on the energy-dissipating node library and a conventional component library, establishing efficient numerical models for multiple structural schemes, simplifying the efficient numerical models into multi-degree-of-freedom elastoplastic analysis models, and calibrating equivalent mechanical parameters using the efficient numerical models; training a graph neural network model; establishing multiple structural schemes to be optimized, calibrating equivalent mechanical parameters using the graph neural network model, and analyzing the seismic performance indexes of the structural schemes to be optimized through the multi-degree-of-freedom elastoplastic analysis models; and screening the optimal scheme from multiple structural schemes to be optimized through an adaptability function. Embodiments of the present invention can significantly improve the energy-dissipating capacity of the structure under seismic action and enhance the seismic performance of the structure by optimizing the layout position and quantity of the energy-dissipating nodes.

Description

Technical Field

[0001] The present invention relates to the technical field of building structure design, and particularly to a method and device for optimizing the layout of energy-dissipating joints in a structure. Background Art

[0002] With the acceleration of the urbanization process, high-rise buildings and super high-rise buildings are increasing day by day. As a natural disaster, earthquakes pose a serious threat to the safety of building structures. Traditional seismic design methods mainly resist seismic actions by enhancing the stiffness and bearing capacity of structural members, but this method often leads to large self-weights of structures, high material consumption, and poor economy.

[0003] An energy-dissipating joint is a new type of structural member with excellent energy-dissipating ability, usually made of high-performance materials such as low-yield-point steel or shape memory alloy. Since the lateral deformation that occurs in the structure under seismic action is mainly concentrated at the joints, the main function of the energy-dissipating joints is to dissipate seismic energy through their own deformation under seismic action, thereby reducing the damage to the main structure. After an earthquake, the energy-dissipating joints are convenient to replace, so as to quickly restore the building function. The energy-dissipating joints have the following advantages: (1) reducing the seismic response of the main structure; (2) improving the ductility and deformation ability of the structure; (3) reducing the structure repair cost and the difficulty of post-earthquake reconstruction.

[0004] Although the energy-dissipating joints have significant advantages in structural seismic design, in the prior art, the layout methods of energy-dissipating joints often ignore the consideration of structural economy and post-earthquake rapid repair ability during the optimization process. Summary of the Invention

[0005] In order to solve the technical problem that in the prior art, the layout methods of energy-dissipating joints often ignore the consideration of structural economy and post-earthquake rapid repair ability during the optimization process, the embodiments of the present invention provide a method and device for optimizing the layout of energy-dissipating joints in a structure. The technical solutions are as follows:

[0006] On the one hand, a method for optimizing the layout of energy-dissipating joints in a structure is provided, including the following steps:

[0007] Step 1: Establish an energy-dissipating joint library and a corresponding hysteretic model library of the energy-dissipating joint library. Based on the energy-dissipating joint library and a conventional member library, randomly combine energy-dissipating joints and conventional structural members to generate multiple structural schemes, establish an efficient numerical model of the multiple structural schemes, simplify the efficient numerical model into a multi-degree-of-freedom elastoplastic analysis model, and use the efficient numerical model to calibrate equivalent mechanical parameters;

[0008] Step 2: Repeatedly execute Step 1 multiple times to generate a large number of structural schemes and the equivalent mechanical parameters corresponding to the large number of structural schemes. Based on the large number of structural schemes and the equivalent mechanical parameters corresponding to the large number of structural schemes, train a graph neural network model;

[0009] Step 3: Establish multiple structural schemes to be optimized according to the design requirements. Randomly arrange energy-dissipating nodes and encode them in the multiple structural schemes to be optimized. Use the graph neural network model to calibrate the equivalent mechanical parameters of each structural scheme to be optimized, and analyze the seismic performance indicators of the structural scheme to be optimized through an elastoplastic analysis model with multiple degrees of freedom according to the equivalent mechanical parameters;

[0010] Step 4: Define an adaptability function. Through the adaptability function, comprehensively evaluate and screen the optimal scheme among the multiple structural schemes to be optimized according to the seismic performance indicators and economic benefits. If the termination condition is not reached, change the types, sizes, material property parameters, and arrangement positions of the energy-dissipating nodes in the multiple structural schemes to be optimized, use the graph neural network model to calibrate the equivalent mechanical parameters of each structural scheme to be optimized, analyze the seismic performance indicators of the structural scheme to be optimized through an elastoplastic analysis model with multiple degrees of freedom according to the equivalent mechanical parameters, and comprehensively evaluate and screen the optimal scheme among the multiple structural schemes to be optimized through the adaptability function according to the seismic performance indicators and economic benefits. If the termination condition is reached, select the optimal scheme as the final scheme;

[0011] The adaptability function is:

[0012] + , where represents the overall weight of the seismic performance, represents the overall weight of the economy, and the sum of the two is 1;

[0013] is the weight of the first seismic performance indicator, is the weight of the second seismic performance indicator, is the weight of the third seismic performance indicator, is the weight of the fourth seismic performance indicator, and the sum of the weights is 1, which is selected according to the project requirements;

[0014] D represents the ductility coefficient, SF represents the safety factor, represents the hysteretic energy dissipation, represents the maximum inter-story drift angle, represents the reference energy dissipation value without adding energy-dissipating nodes;

[0015] C is the total construction cost, is a small positive number used to prevent the denominator from being zero in the division operation.

[0016] Optionally, establishing the hysteretic model library corresponding to the energy-dissipating node library includes:

[0017] For each type of energy-dissipating node and its corresponding size and mechanical properties parameters, establish the corresponding hysteretic model and generate the hysteretic model library.

[0018] Optionally, establishing the efficient numerical models for the multiple structural schemes includes:

[0019] For each structural scheme, integrate the improved beam elements for simulating energy-dissipating nodes, the traditional fiber beam elements for simulating beam-columns, the layered shell elements for simulating shear walls, and the shear fiber beam elements for simulating coupling beams, which are the calculation units of conventional components, to obtain an efficient numerical model for accurately simulating the mechanical response of the structural system with energy-dissipating nodes arranged.

[0020] Optionally, training the graph neural network model based on the large number of structural schemes and the equivalent mechanical parameters corresponding to the large number of structural schemes includes:

[0021] Represent the connection points in the structural scheme as nodes in the structural system graph structure, represent the beams, columns, shear walls, coupling beams, and energy-dissipating nodes as edges between the nodes in the structural system graph structure, represent the connection method as the characteristics of the nodes in the structural system graph structure, and represent the member attributes as the characteristics of the edges in the structural system graph structure to generate the structural system graph structure;

[0022] Using the structural system graph structure as the input and the pre-calibrated equivalent mechanical parameters as the output, train and learn using a graph neural network to obtain a graph neural network model for quickly calibrating the equivalent mechanical parameters.

[0023] Optionally, establishing multiple structural schemes to be optimized according to the design requirements includes:

[0024] According to the design requirements, establish a structural system to be optimized that does not have energy-dissipating nodes and only meets the basic spatial function and force requirements.

[0025] Optionally, after establishing the energy-dissipating node library and the hysteretic model library corresponding to the energy-dissipating node library, it further includes:

[0026] Obtain and store the typical hysteretic curves based on the hysteretic model library.

[0027] Optionally, the termination condition is that the adaptive function values of the multiple structural schemes to be optimized converge, or the iteration reaches the set number of times.

[0028] On the other hand, provided is an optimization device for the arrangement of energy-dissipating nodes in a structure. The optimization device for the arrangement of energy-dissipating nodes in a structure is used to implement the optimization method for the arrangement of energy-dissipating nodes in a structure provided in the embodiments of the present invention. The device includes:

[0029] A building module, which is used to build an energy-consuming node library and a corresponding hysteretic model library for the energy-consuming node library, randomly combine energy-consuming nodes and conventional structural members based on the energy-consuming node library and the conventional member library to generate multiple structural schemes, build an efficient numerical model for the multiple structural schemes, simplify the efficient numerical model into a multi-degree-of-freedom elastoplastic analysis model, and calibrate equivalent mechanical parameters using the efficient numerical model;

[0030] A training module, which is used to generate a large number of structural schemes and the corresponding equivalent mechanical parameters thereof through the building module and the generating module, and train a graph neural network model based on the large number of structural schemes and the corresponding equivalent mechanical parameters thereof;

[0031] A calculation module, which is used to establish multiple structural schemes to be optimized according to design requirements, randomly arrange energy-consuming nodes and encode them in the multiple structural schemes to be optimized, calibrate the equivalent mechanical parameters of each structural scheme to be optimized using the graph neural network model, and analyze the seismic performance indexes of the structural schemes to be optimized through the multi-degree-of-freedom elastoplastic analysis model according to the equivalent mechanical parameters;

[0032] A selection module, which is used to define an adaptability function, comprehensively evaluate and screen the optimal scheme among the multiple structural schemes to be optimized according to the seismic performance indexes and economic benefits through the adaptability function. If the optimal scheme does not meet the termination condition, change the types, sizes, material property parameters and layout positions of the energy-consuming nodes in the multiple structural schemes to be optimized, calibrate the equivalent mechanical parameters of each structural scheme to be optimized using the graph neural network model, analyze the seismic performance indexes of the structural schemes to be optimized through the multi-degree-of-freedom elastoplastic analysis model according to the equivalent mechanical parameters, and comprehensively evaluate and screen the optimal scheme among the multiple structural schemes to be optimized according to the seismic performance indexes and economic benefits through the adaptability function. If the optimal scheme meets the termination condition, select the optimal scheme as the final scheme;

[0033] The adaptability function is:

[0034] + , where represents the overall weight of seismic performance, represents the overall weight of economy, and the sum of the two is 1;

[0035] is the weight of the first seismic performance index, is the weight of the second seismic performance index, is the weight of the third seismic performance index, is the weight of the fourth seismic performance index, and the sum of the weights is 1, which is selected according to project requirements;

[0036] D represents the ductility coefficient, and SF represents the safety factor. represents the hysteretic energy dissipation. represents the maximum inter-story drift angle. represents the reference energy dissipation value without adding energy dissipation nodes;

[0037] C is the total construction cost. is a small positive number used to prevent the denominator from being zero in the division operation.

[0038] Optionally, the device for optimizing the layout of the energy dissipation nodes in the structure includes:

[0039] a processor;

[0040] a memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the method provided by the embodiments of the present invention is implemented.

[0041] On the other hand, a computer-readable storage medium is provided, in which program code is stored, and the program code can be called by a processor to execute the method provided by the embodiments of the present invention.

[0042] The beneficial effects brought by the technical solutions provided by the embodiments of the present invention at least include:

[0043] By optimizing the layout position and quantity of the energy dissipation nodes, the embodiments of the present invention can significantly improve the energy dissipation capacity of the structure under earthquake action, enhance the seismic performance of the structure, improve the energy dissipation efficiency of the nodes, maximize the improvement effect of the energy dissipation nodes on the seismic performance of the overall structure, reduce the material consumption, facilitate post-earthquake repair and function restoration, and reduce the construction and operation and maintenance costs. It promotes the engineering application of the energy dissipation nodes and is beneficial to the construction of resilient cities. Description of the Drawings

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0045] Figure 1 is a flowchart of a method for optimizing the layout of energy dissipation nodes in a structure provided by an embodiment of the present invention;

[0046] Figure 2 is a schematic structural diagram of a device for optimizing the layout of energy dissipation nodes in a structure provided by an embodiment of the present invention;

[0047] Figure 3It is a flowchart of a method for optimizing the layout of energy-dissipating nodes in a structure provided by an embodiment of the present invention;

[0048] Figure 4 It is a schematic diagram of the structure of an energy-dissipating node provided by an embodiment of the present invention;

[0049] Figure 5 It is a schematic diagram of the structure of an efficient numerical model of a structural system with energy-dissipating nodes provided by an embodiment of the present invention;

[0050] Figure 6 It is a schematic diagram of the layout scheme of a structural system with energy-dissipating nodes arranged provided by an embodiment of the present invention;

[0051] Figure 7 It is a schematic diagram of another layout scheme of a structural system with energy-dissipating nodes arranged provided by an embodiment of the present invention;

[0052] Figure 8 It is a schematic diagram of a simplified analysis model of a structure with energy-dissipating nodes arranged provided by an embodiment of the present invention;

[0053] Figure 9 It is a schematic diagram of the structure of an optimization device for the layout of energy-dissipating nodes in a structure provided by an embodiment of the present invention.

[0054] Reference numerals:

[0055] 1 - Web connection plate (ordinary steel); 2 - Flange connection plate (low yield point steel); 3 - High-strength bolt; 4 - Frame column; 5 - Bracket; 6 - Steel beam; 7 - Floor slab. Detailed implementation manners

[0056] The following describes the technical solutions in the present invention with reference to the accompanying drawings.

[0057] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0058] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same.

[0059] In the embodiments of the present invention, sometimes a subscript such as W1 may be expressed in a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0060] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0061] To solve the technical problem that in the optimization process of the existing layout method of energy-dissipating nodes, the consideration of structural economy and post-earthquake rapid repair ability is often ignored, the embodiments of the present invention provide an optimization method and device for the layout of energy-dissipating nodes in a structure. The technical solutions are as follows:

[0062] On the one hand, as Figure 1 shown, an optimization method for the layout of energy-dissipating nodes in a structure is provided, including the following steps:

[0063] S1. Establish an energy-dissipating node library and a corresponding hysteretic model library for the energy-dissipating node library. Based on the energy-dissipating node library and the conventional component library, randomly combine energy-dissipating nodes and conventional structural components to generate multiple structural schemes. Establish an efficient numerical model for the multiple structural schemes, simplify the efficient numerical model into a multi-degree-of-freedom elastoplastic analysis model, and use the efficient numerical model to calibrate the equivalent mechanical parameters;

[0064] S2. Repeat S1 multiple times to generate a large number of structural schemes and the corresponding equivalent mechanical parameters for the large number of structural schemes. Based on the large number of structural schemes and the corresponding equivalent mechanical parameters for the large number of structural schemes, train a graph neural network model;

[0065] S3. Establish multiple structural schemes to be optimized according to the design requirements. In the multiple structural schemes to be optimized, randomly arrange energy-dissipating nodes and encode them. Use the graph neural network model to calibrate the equivalent mechanical parameters of each structural scheme to be optimized, and analyze the seismic performance indicators of the structural scheme to be optimized through the multi-degree-of-freedom elastoplastic analysis model according to the equivalent mechanical parameters;

[0066] S4. Define an adaptability function. According to the adaptability function, comprehensively evaluate and screen the optimal solution among the multiple to-be-optimized structural solutions based on seismic performance indicators and economic benefits. If the optimal solution does not meet the termination condition, change the types, sizes, material property parameters, and layout positions of the energy-dissipating nodes in the multiple to-be-optimized structural solutions, and use the graph neural network model to calibrate the equivalent mechanical parameters of each to-be-optimized structural solution. Analyze the seismic performance indicators of the to-be-optimized structural solutions through the elastoplastic analysis model with multiple degrees of freedom according to the equivalent mechanical parameters, and comprehensively evaluate and screen the optimal solution among the multiple to-be-optimized structural solutions according to the seismic performance indicators and economic benefits through the adaptability function. If the optimal solution meets the termination condition, select the optimal solution as the final solution;

[0067] The adaptability function is as follows:

[0068] + , where represents the overall weight of seismic performance, represents the overall weight of economy, and the sum of the two is 1;

[0069] is the weight of the first seismic performance indicator, is the weight of the second seismic performance indicator, is the weight of the third seismic performance indicator, is the weight of the fourth seismic performance indicator, and the sum of the weights is 1, which is selected according to project requirements;

[0070] D represents the ductility coefficient, SF represents the safety factor, represents the hysteretic energy dissipation, represents the maximum inter-story drift angle, represents the reference energy dissipation value without adding energy-dissipating nodes;

[0071] C is the total construction cost, is a small positive number used to prevent the denominator from being zero in the division operation.

[0072] On the other hand, as Figure 2 shown, provide an optimization device for the layout of energy-dissipating nodes in a structure. The optimization device for the layout of energy-dissipating nodes in a structure is used to implement the optimization method for the layout of energy-dissipating nodes in a structure provided by the embodiments of the present invention. The device includes:

[0073] The establishment module 201 is used to establish an energy-dissipating node library and a corresponding hysteretic model library for the energy-dissipating node library. Based on the energy-dissipating node library and the conventional component library, the energy-dissipating nodes and conventional structural components are randomly combined to generate multiple structural schemes, establish an efficient numerical model for the multiple structural schemes, simplify the efficient numerical model into an elastoplastic analysis model with multiple degrees of freedom, and use the efficient numerical model to calibrate the equivalent mechanical parameters;

[0074] The training module 202 is used to generate a large number of structural schemes and the corresponding equivalent mechanical parameters thereof through the establishment module and the generation module, and train a graph neural network model based on the large number of structural schemes and the corresponding equivalent mechanical parameters thereof;

[0075] The calculation module 203 is used to establish multiple structural schemes to be optimized according to the design requirements. In the multiple structural schemes to be optimized, the energy-dissipating nodes are randomly arranged and encoded, the equivalent mechanical parameters of each structural scheme to be optimized are calibrated by using the graph neural network model, and the seismic performance indexes of the structural schemes to be optimized are analyzed by using the elastoplastic analysis model with multiple degrees of freedom according to the equivalent mechanical parameters;

[0076] The selection module 204 is used to define an adaptability function, and comprehensively evaluate and screen the optimal scheme among the multiple structural schemes to be optimized according to the seismic performance indexes and economic benefits through the adaptability function. If the optimal scheme does not meet the termination condition, the types, sizes, material property parameters and layout positions of the energy-dissipating nodes in the multiple structural schemes to be optimized are changed, the equivalent mechanical parameters of each structural scheme to be optimized are calibrated by using the graph neural network model, the seismic performance indexes of the structural schemes to be optimized are analyzed by using the elastoplastic analysis model with multiple degrees of freedom according to the equivalent mechanical parameters, and the optimal scheme among the multiple structural schemes to be optimized is comprehensively evaluated and screened according to the seismic performance indexes and economic benefits through the adaptability function. If the optimal scheme meets the termination condition, the optimal scheme is selected as the final scheme;

[0077] The adaptability function is:

[0078] + , where represents the overall weight of the seismic performance, represents the overall weight of the economy, and the sum of the two is 1;

[0079] is the weight of the first seismic performance index, is the weight of the second seismic performance index, is the weight of the third seismic performance index, is the weight of the fourth seismic performance index, and the sum of the weights is 1, which is selected according to the project requirements;

[0080] D represents the ductility coefficient, and SF represents the safety factor. represents the hysteretic energy dissipation. represents the maximum inter-story drift ratio. represents the reference energy dissipation value without adding energy dissipation nodes.

[0081] C is the total construction cost. is a small positive number used to prevent the denominator from being zero in the division operation.

[0082] The present invention relates to an optimization method for the layout of energy dissipation nodes in a structure. The physical information neural network method is used to quickly analyze the performance indicators of different schemes as a whole, and the genetic algorithm is used as a framework to optimize the schemes. The overall algorithm process is as shown in the appendix Figure 3 The physical information neural network consists of two parts, namely, a physical simplified analysis model for quickly calculating seismic performance indicators and a graph neural network for quickly calibrating the equivalent mechanical parameters required by the former. The specific implementation steps are divided into two parts: the training stage and the optimization stage:

[0083] 1) Training stage

[0084] Step 1.1: Establish an energy dissipation node and corresponding hysteretic model library.

[0085] In this step, a series of energy dissipation nodes are first defined. Specifically, a certain form of energy dissipation node structure is as shown in the appendix Figure 4 It includes components such as a web connection plate (ordinary steel) 1, a flange connection plate (low yield point steel) 2, and high-strength bolts 3. This node connects the bracket 5 of the frame column 4 and the steel beam 6, and part of the web connection plate is installed on the floor slab 7. These energy dissipation nodes can concentrate damage and absorb energy when the structure is subjected to external loads such as earthquakes, protecting the main structure. For each type of energy dissipation node and its size and material mechanical parameters, a corresponding hysteretic model is established to describe the mechanical behavior of the energy dissipation node under cyclic loading conditions, including its load-displacement relationship. Through experimental tests or finite element analysis, a series of typical hysteretic curves are obtained and stored in a database for subsequent use.

[0086] Step 1.2: Establish an improved beam element for simulating energy dissipation nodes and integrate it with the calculation units of conventional components to form an efficient numerical model of the structural system with energy dissipation nodes arranged.

[0087] Based on the above hysteretic model of the energy dissipation node, an improved beam element that can be embedded in a general finite element calculation program is developed, which can accurately simulate the mechanical behavior of the energy dissipation node under hysteretic loads. The improved beam element for simulating energy dissipation nodes is integrated with the calculation units of conventional components such as traditional fiber beam elements for simulating beam-columns, layered shell elements for simulating shear walls, and shear fiber beam elements for simulating coupling beams to obtain an efficient numerical model that can accurately simulate the mechanical response of the structural system with energy dissipation nodes arranged, as shown in the appendixFigure 5 as shown

[0088] Step 1.3: Randomly combine energy-dissipating nodes and conventional structural members to form multiple structural schemes

[0089] Randomly select components from the established energy-dissipating node library and conventional member libraries such as beams, columns, and shear walls, and assemble them into a complete structural system according to common building structure layout rules, such as symmetry rules, square rules, etc. This can generate various building layouts and design schemes, thereby exploring a wider design space. Different energy-dissipating node layout schemes are shown in the appendix Figure 6 and 7 as shown

[0090] Step 1.4: Establish an efficient numerical model of the structural system with energy-dissipating nodes arranged, conduct seismic performance analysis, and obtain seismic performance indicators

[0091] Establish an efficient numerical model for each of the structural schemes generated in Step 1.3. Through pushover analysis and nonlinear time history analysis, evaluate the performance of each structural system under earthquake action, and calculate key seismic performance indicators, including ductility coefficient, safety factor, hysteretic energy dissipation, maximum inter-story drift angle, etc

[0092] Step 1.5: Simplify the efficient numerical model into a multi-degree-of-freedom elastoplastic analysis model and calibrate the equivalent mechanical parameters of the multi-degree-of-freedom elastoplastic analysis model

[0093] Considering the repeated iterative calculations of the schemes during the optimization process, the computational cost of the efficient numerical model is still relatively high. It is necessary to further simplify the complex efficient numerical model into a multi-degree-of-freedom elastoplastic analysis model, as shown in Figure 8 . The frame structure can be simplified into a shear-type story model, the shear wall structure can be simplified into a flexure-type story model, and the frame-shear wall structure can be simplified into a flexure-shear-type story model. Here, the most complex flexure-shear-type story model is taken as an example for introduction. The simplified elastoplastic analysis model of the structural system with energy-dissipating nodes arranged is shown in the appendix Figure 8 as shown. Each layer is connected in series, and each layer model is formed by parallel connection of flexural springs, shear springs, and damping springs. The flexural stiffness of the i-th layer is denoted as , the shear stiffness is denoted as , the damping coefficient related to mass is denoted as , and the damping coefficient related to stiffness is denoted as . The dynamic equation of the structural system under earthquake action can be expressed as follows

[0094]

[0095] where {u} is the displacement vector of the structural system relative to the ground, is the ground acceleration vector caused by ground motion, [M] is the mass matrix of the structural system, [C] is the damping matrix of the structural system, and [K] is the stiffness matrix of the structural system. The coefficients in these matrices are composed of the flexural stiffness, shear stiffness, and damping coefficients of each floor of the structure.

[0096] By applying pure bending static force, pure shear static force, modified mass and material stiffness to the high-efficiency numerical model and combining with modal analysis, mechanical parameters such as equivalent flexural stiffness, shear stiffness, and damping coefficients can be calculated. The simplified multi-degree-of-freedom elastoplastic analysis model can generate almost the same mechanical response as the high-efficiency numerical model under similar conditions, but the computational amount is greatly reduced, and it can be used to calculate seismic performance indicators.

[0097] Step 1.6: Repeat Steps 1.3 - 1.5 to obtain a large number of different structural system layout schemes with energy-dissipating nodes arranged and their corresponding equivalent mechanical parameters

[0098] Repeat the above process to generate a large number of different structural system layout schemes with energy-dissipating nodes arranged and their corresponding sets of equivalent mechanical parameters. This step is the key to accumulating data, aiming to provide sufficient and diverse training samples for graph neural network machine learning.

[0099] Step 1.7: Based on the spatial topological relationship and design parameters of the structural system, as well as the equivalent mechanical parameters, train a graph neural network for quickly calibrating the equivalent mechanical parameters of the structural system

[0100] Finally, using the established dataset, train a graph neural network (Graph Neural Network, GNN) through supervised learning. Represent the connection points in the structural system as nodes in the graph structure, and represent components such as beams, columns, shear walls, coupling beams, and energy-dissipating nodes as edges between nodes in the graph structure. Represent the connection method and component attributes as the features of nodes and edges in the graph structure respectively. Using the abstracted graph structure of the structural system as the input and the pre-calibrated equivalent mechanical parameters as the output, train and learn using a graph neural network to obtain a graph neural model for quickly calibrating equivalent mechanical parameters. This graph neural network model combined with the simplified multi-degree-of-freedom elastoplastic analysis model is the physical information neural network model, which is used to quickly calculate the seismic performance indicators of each scheme.

[0101] 2) Optimization stage

[0102] Step 2.1: Establish the structural system to be optimized according to the design requirements

[0103] Based on the specific requirements of the project or the already designed preliminary scheme, establish a structural system to be optimized without energy-dissipating nodes that only meets the basic spatial function and force requirements.

[0104] Step 2.2: Randomly arrange energy dissipation nodes, generate multiple different structural schemes and encode them as the initial population

[0105] Number all the possible positions for arranging energy dissipation nodes in the structural system to be optimized. First, number them in an S-shaped pattern along the axis within the same floor plane, and then number them from the lower floor to the upper floor. The numbering starts from 1, and 0 indicates no arrangement. Randomly arrange a certain number of energy dissipation nodes (the total number does not exceed n) to create multiple candidate structural schemes. Each energy dissipation node forms an energy dissipation node code according to the number of its location and its number in the energy dissipation node library. The codes of n energy dissipation nodes form the code of this structural scheme, representing a specific combination of the positions and types of energy dissipation nodes. The codes of multiple structural schemes constitute the initial population of the genetic algorithm.

[0106] Step 2.3: Quickly calibrate the equivalent mechanical parameters for each scheme in the initial population and quickly calculate the seismic performance indicators based on the simplified analysis model

[0107] Using the graph neural network model trained in the previous stage, the equivalent mechanical parameters of each scheme can be calibrated very efficiently, and the seismic performance indicators can be quickly calculated by combining the simplified multi-degree-of-freedom elastoplastic analysis model. This method significantly improves the calculation efficiency and makes large-scale search possible.

[0108] Step 2.4: Define the fitness function and screen the population

[0109] To find the optimal solution of the structural scheme, this method introduces the concept of multi-objective optimization, that is, considering both seismic performance and economic benefits. For this purpose, a comprehensive evaluation function is designed, which includes a weighted consideration of seismic capacity and construction cost.

[0110] + , where and represent the overall weights of seismic performance and economy respectively, and the sum of the two is 1;

[0111] , , , are the specific weights of each seismic performance index, and the sum of the weights is 1, which are selected according to project requirements;

[0112] D, SF, , represent the ductility coefficient, safety factor, hysteretic energy dissipation, and maximum inter-story drift angle respectively, represents the reference energy dissipation value without adding energy dissipation nodes;

[0113] C is the total construction cost is a small positive number used to prevent the denominator from being zero in division operations.

[0114] By adjusting the weight coefficient, the importance ratio of the two can be flexibly adjusted according to the actual situation. Then, the population is sorted and screened according to the value of this adaptability function, and those individuals with the best performance are retained.

[0115] Step 2.5: When the termination condition is not reached, perform crossover and mutation on the screened population, and return to Step 2.3; otherwise, take the optimal solution in the current population as the final solution.

[0116] If the number of iterations or other preset termination conditions have not been met, then the genetic operations will continue to be executed, including crossover and mutation of the encoding, so as to change the types, sizes, material properties, and layout positions of the energy-consuming nodes, in order to explore more potential excellent design solutions. After each iteration, it will return to Step 2.3 to re-evaluate the performance of the newly generated individuals. When all termination conditions are met, select the optimal structural solution in the population at this time as the final optimization result.

[0117] On the other hand, an optimization device for the layout of energy-consuming nodes in a structure is provided. The optimization device for the layout of energy-consuming nodes in a structure includes:

[0118] A processor;

[0119] A memory, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor, the method provided in the embodiment of the present invention is implemented.

[0120] On the other hand, a computer-readable storage medium is provided. Program code is stored in the computer-readable storage medium, and the program code can be called by a processor to execute the method provided in the embodiment of the present invention.

[0121] The beneficial effects brought by the technical solution provided in the embodiment of the present invention at least include:

[0122] By optimizing the layout positions and quantities of the energy-consuming nodes in the embodiment of the present invention, the energy-consuming capacity of the structure under seismic action can be significantly improved, the seismic performance of the structure can be enhanced, the energy-consuming efficiency of the nodes can be increased, the improvement effect of the energy-consuming nodes on the seismic performance of the overall structure can be maximized, the material consumption can be reduced, the post-earthquake repair and function restoration can be facilitated, and the construction and operation and maintenance costs can be reduced. It promotes the engineering application of energy-consuming nodes and is beneficial to the construction of resilient cities.

[0123] Figure 9 is a schematic structural diagram of an optimization device for the layout of energy-consuming nodes in a structure provided in the embodiment of the present invention, as Figure 9As shown, optionally, the device 910 for optimizing the layout of energy-consuming nodes in a structure may include a first processor 2001.

[0124] Optionally, the device 910 for optimizing the layout of energy-consuming nodes in a structure may further include a memory 2002 and a transceiver 2003.

[0125] Among them, the first processor 2001 is connected to the memory 2002 and the transceiver 2003, for example, through a communication bus.

[0126] Next, in combination with Figure 9 Specific introductions will be made to each component of the device 910 for optimizing the layout of energy-consuming nodes in a structure:

[0127] Among them, the first processor 2001 is the control center of the device 910 for optimizing the layout of energy-consuming nodes in a structure. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or it can be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. For example: one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0128] Optionally, the first processor 2001 can execute various functions of the device 910 for optimizing the layout of energy-consuming nodes in a structure by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0129] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 9 the CPU0 and CPU1 shown in

[0130] In a specific implementation, as an embodiment, the device 910 for optimizing the layout of energy-consuming nodes in a structure may also include multiple processors, such as Figure 9 the first processor 2001 and the second processor 2004 shown in

[0131] Among them, the memory 2002 is used to store the software program for implementing the solution of the present invention and is controlled by the first processor 2001 for execution. The specific implementation manner can refer to the above method embodiment and will not be elaborated here.

[0132] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently and is coupled to the first processor 2001 through the interface circuit of the motor control device 910 ( Figure 9 not shown in the figure), and the embodiments of the present invention do not make specific limitations on this.

[0133] The transceiver 2003 is used to communicate with a network device or with a terminal device.

[0134] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 9 not separately shown in the figure). Among them, the receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0135] Optionally, the transceiver 2003 may be integrated with the first processor 2001 or may exist independently and is coupled to the first processor 2001 through the interface circuit of the device 910 for optimizing the layout of the energy-consuming nodes in the structure ( Figure 9 not shown in the figure), and the embodiments of the present invention do not make specific limitations on this.

[0136] It should be noted that Figure 9 the structure of the device 910 for optimizing the layout of the energy-consuming nodes shown in the figure does not constitute a limitation on the router. The actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine some components, or have different component layouts.

[0137] In addition, for the technical effects of the device 910 for optimizing the layout of energy-consuming nodes in the structure, reference can be made to the technical effects of the multi-modal emotion recognition method described in the above method embodiments, which will not be elaborated here.

[0138] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0139] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).

[0140] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, motor driver, or data center to another website, computer, motor driver, or data center by infrared, wireless, microwave, etc. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a motor driver or a data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0141] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0142] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0143] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0144] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0145] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices, apparatuses, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0146] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in electrical, mechanical, or other forms.

[0147] 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 can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0149] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a motor driver, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0150] As described above, the above are only specific implementation manners of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for optimizing the arrangement of energy-consuming nodes in a structure, characterized in that: The following steps are involved: Step 1: Establish an energy-consuming node library and a hysteresis model library corresponding to the energy-consuming node library; based on the energy-consuming node library and the conventional component library, randomly combine energy-consuming nodes and conventional structural components to generate a variety of structural schemes; establish efficient numerical models of the various structural schemes; simplify the efficient numerical models into a multi-degree-of-freedom elastic-plastic analysis model; and use the efficient numerical models to calibrate equivalent mechanical parameters; Step 2, repeatedly executing step 1 multiple times to generate a large number of structural schemes and equivalent mechanical parameters corresponding to the large number of structural schemes, and training a graph neural network model based on the large number of structural schemes and the equivalent mechanical parameters corresponding to the large number of structural schemes; Step 3, establishing multiple structural schemes to be optimized according to design requirements, randomly arranging and encoding energy consumption nodes in the multiple structural schemes to be optimized, calibrating the equivalent mechanical parameters of each structural scheme to be optimized using the graph neural network model, and analyzing the seismic performance index of the structural scheme to be optimized through a multi-degree-of-freedom elastic-plastic analysis model based on the equivalent mechanical parameters; Step 4, define an adaptability function, and use the adaptability function to select the optimal solution among the multiple structural solutions to be optimized according to the seismic performance index and the comprehensive evaluation of economic benefits. If the optimal solution does not meet the termination condition, change the type, size, material parameters and layout position of the energy-consuming nodes in the multiple structural solutions to be optimized, and use the graph neural network model to calibrate the equivalent mechanical parameters of each of the structural solutions to be optimized, analyze the seismic performance index of the structural solution to be optimized through a multi-degree-of-freedom elastic-plastic analysis model according to the equivalent mechanical parameters, and use the adaptability function to select the optimal solution among the multiple structural solutions to be optimized according to the seismic performance index and the comprehensive evaluation of economic benefits. If the optimal solution meets the termination condition, select the optimal solution as the final solution; The fitness function is: + ,in represents the overall weight of seismic performance, Represents the overall weight of economy, the sum of the two is 1; is the weight of the first seismic performance indicator, is the weight of the second seismic performance indicator, is the weight of the third seismic performance indicator, It is the weight of the fourth seismic performance index. The sum of all weights is 1 and is selected according to project requirements. D is the ductility factor, SF is the safety factor, represents hysteresis energy consumption, represents the maximum inter-story displacement angle, Indicates the reference energy consumption value without adding energy consumption nodes; C is the total construction cost, is a small positive number used to prevent the denominator from being zero in division operations.

2. The method according to claim 1, characterized in that The step of establishing a hysteresis model library corresponding to the energy consumption node library comprises: For each type of energy-consuming node and its corresponding size and material mechanical parameters, a corresponding hysteresis model is established to generate a hysteresis model library.

3. The method according to claim 1, characterized in that: The method of establishing an efficient numerical model of the plurality of structural schemes comprises: For each structural scheme, the improved beam elements simulating energy-absorbing nodes, the traditional fiber beam elements simulating beam-columns, the layered shell elements simulating shear walls, and the shear-considering fiber beam elements simulating connecting beams are integrated to obtain an efficient numerical model for accurately simulating the mechanical response of the structural system with energy-absorbing nodes.

4. The method according to claim 1, characterized in that: The training of the graph neural network model based on the large number of structural schemes and the equivalent mechanical parameters corresponding to the large number of structural schemes includes: The connection points in the structural scheme are represented as nodes in the structural system diagram structure, the beams, columns, shear walls, coupling beams and energy dissipation nodes are represented as edges between nodes in the structural system diagram structure, the connection mode is represented as the characteristics of the nodes in the structural system diagram structure, and the component attributes are represented as the characteristics of the edges in the structural system diagram structure, thereby generating a structural system diagram structure; The structural system graph structure is taken as input and the pre-calibrated equivalent mechanical parameters are taken as output. A graph neural network is used for training and learning to obtain a graph neural network model for quickly calibrating equivalent mechanical parameters.

5. The method according to claim 1, characterized in that The method of establishing multiple structural schemes to be optimized according to the design requirements includes: According to the design requirements, a structural system to be optimized is established without energy-consuming nodes but only meeting the basic spatial functions and force requirements.

6. The method according to claim 1, characterized in that After the energy consumption node library and the hysteresis model library corresponding to the energy consumption node library are established, the method further includes: A typical hysteresis curve is obtained and stored based on the hysteresis model library.

7. The method according to claim 1, characterized in that The termination condition is that the adaptability function values ​​of the multiple structures to be optimized converge, or the iterations reach a set number of times.

8. A device for optimizing the arrangement of energy-consuming nodes in a structure, the device for optimizing the arrangement of energy-consuming nodes in a structure being used to implement the method for optimizing the arrangement of energy-consuming nodes in a structure as claimed in any one of claims 1 to 7, characterized in that: The device comprises: Establishing a module, used to establish an energy-consuming node library and a hysteresis model library corresponding to the energy-consuming node library, randomly combining energy-consuming nodes and conventional structural components based on the energy-consuming node library and the conventional component library, generating multiple structural schemes, establishing efficient numerical models of the multiple structural schemes, simplifying the efficient numerical models into multi-degree-of-freedom elastic-plastic analysis models, and using the efficient numerical models to calibrate equivalent mechanical parameters; A training module, used for generating a large number of structural schemes and equivalent mechanical parameters corresponding to the structural schemes by building a module, and training a graph neural network model based on the large number of structural schemes and equivalent mechanical parameters corresponding to the large number of structural schemes; A calculation module, used to establish multiple structural schemes to be optimized according to design requirements, randomly arrange energy consumption nodes in the multiple structural schemes to be optimized and encode them, calibrate the equivalent mechanical parameters of each structural scheme to be optimized using the graph neural network model, and analyze the seismic performance index of the structural scheme to be optimized through a multi-degree-of-freedom elastic-plastic analysis model according to the equivalent mechanical parameters; A selection module is used to define an adaptability function, and the optimal solution among the multiple structural solutions to be optimized is screened through the adaptability function according to the seismic performance index and the comprehensive evaluation of economic benefits. If the optimal solution does not meet the termination condition, the types, sizes, material parameters and layout positions of the energy-consuming nodes in the multiple structural solutions to be optimized are changed, and the equivalent mechanical parameters of each structural solution to be optimized are calibrated using the graph neural network model, and the seismic performance index of the structural solution to be optimized is analyzed through a multi-degree-of-freedom elastic-plastic analysis model according to the equivalent mechanical parameters, and the optimal solution among the multiple structural solutions to be optimized is screened through the adaptability function according to the seismic performance index and the comprehensive evaluation of economic benefits. If the optimal solution meets the termination condition, the optimal solution is selected as the final solution; The fitness function is: + ,in represents the overall weight of seismic performance, Represents the overall weight of economy, the sum of the two is 1; is the weight of the first seismic performance indicator, is the weight of the second seismic performance indicator, is the weight of the third seismic performance indicator, It is the weight of the fourth seismic performance index. The sum of all weights is 1 and is selected according to project requirements. D is the ductility factor, SF is the safety factor, represents hysteresis energy consumption, represents the maximum inter-story displacement angle, Indicates the reference energy consumption value without adding energy consumption nodes; C is the total construction cost, is a small positive number used to prevent the denominator from being zero in division operations.

9. A device for optimizing the arrangement of energy-consuming nodes in a structure, characterized in that: The arrangement optimization device of the energy consumption nodes in the structure includes: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 7.

Images