Hyperboloid pillar base frame structure-based building optimization method, system, device and medium

Abstract

The application discloses a kind of based on hyperboloid pillar base frame structure's construction optimization method, system, equipment and medium, the application relates to building structure optimization calculation technical field, hyperboloid building and its pillar base frame as environment, first intelligent agent perceives information related with structure dynamic characteristic, model is established using structure dynamics theory analysis, from a variety of candidate pillar type selects the type most suitable for current environmental state;Second intelligent agent then after determining pillar type, perceive the second state of environment, and determine optimal structure parameter, ensure that pillar base frame meets bearing capacity requirement and adapts to construction dynamic change;Two intelligent agents continue to perceive environmental state, through information sharing mechanism, realize the dynamic adjustment of construction optimization, effectively solve the deficiency of existing neural network method in construction dynamic adjustment, improve the efficiency and quality of hyperboloid pillar base frame structure construction, ensure the safety and reliability of building construction.

Description

Technical Field

[0001] This invention relates to the field of building structure optimization calculation technology, specifically to a method, system, equipment, and medium for optimizing the construction of a hyperboloid column frame structure. Background Technology

[0002] In the field of building construction, columns, as the main longitudinal load-bearing structures, play a crucial role in ensuring the safety of the overall building through their structural and supporting performance. Traditional columns are widely used in various types of buildings; however, with the continuous advancement of architectural design concepts and the increasing diversification of building functional requirements, higher demands are being placed on the performance of columns.

[0003] For buildings with large horizontal projection areas, traditional columns often generate high local pressure at the support points when providing support. This not only poses a potential risk of damage to the supported structure but also limits the flexibility of the building in terms of space utilization and functional layout. Furthermore, when aesthetics are a requirement for a building, the shape and appearance of traditional columns are often insufficient to meet the pursuit of overall aesthetics and harmony in modern architectural design.

[0004] Hyperboloid columns have emerged due to their unique advantages. They possess high structural performance, maintaining stability and integrity while withstanding large loads. Their excellent support performance effectively and evenly distributes loads, significantly reducing local pressure at the support points and better protecting the supported structure, thus providing strong support for the diversity and practicality of buildings.

[0005] However, the complex shape of hyperboloid columns requires high-precision machining and measurement techniques for the fabrication and installation of their base frames. In actual construction, it is difficult to guarantee that the dimensions and shape accuracy of the base frames meet design requirements, leading to deviations that cause installation difficulties and affect construction progress and quality. Furthermore, due to the unique geometry of hyperboloid columns, the stress distribution on the base frame is uneven when bearing loads. This can result in excessive local stress on the base frame, causing structural deformation or damage, reducing the load-bearing capacity and stability of the columns, and posing a threat to the overall safety of the building.

[0006] While neural network methods are widely used for calculating structural parameters in determining and optimizing hyperboloid column base structures, existing methods still have some limitations. First, the training process of neural networks requires a large amount of data, and obtaining sufficient high-quality data is often challenging in practical engineering. Second, the generalization ability of neural network models may be limited; when encountering new situations that differ significantly from the training data, the accuracy of the calculation results may decrease. Furthermore, dynamic adjustments are often involved in the construction of hyperboloid column base structures. Currently used neural networks typically calculate and predict column base construction parameters based on fixed structures and parameters, making them unable to adapt to the dynamic adjustments during construction. This causes inconvenience for engineers and increases the difficulty of verifying and evaluating the calculation results.

[0007] Therefore, to address the shortcomings of existing neural network methods in calculating the structural parameters of hyperboloid support frames, developing a more efficient, accurate calculation method with better generalization ability is key to promoting the widespread application of hyperboloid supports in the construction field. Summary of the Invention

[0008] Based on the problems raised in the background technology above, the purpose of this invention is to provide a construction optimization method, system, equipment and medium based on hyperboloid column base structure, which solves the problem that existing neural networks cannot adapt to the dynamic adjustment during the construction process of hyperboloid column base structure.

[0009] This invention is achieved through the following technical solution:

[0010] The first aspect of this invention provides an optimized construction method based on a hyperboloid support frame structure, comprising the following steps:

[0011] The hyperboloid building is set as the environment; wherein the environment includes a support frame;

[0012] Construct the first and second intelligent agents;

[0013] The first intelligent agent perceives the first state of the environment and performs structural dynamic analysis based on the first state, and determines the support type of the support frame through the result of the structural dynamic analysis.

[0014] The second intelligent agent perceives the second state of the environment under the type of support pillar, and performs load-bearing performance analysis based on the second state, and determines the structural parameters of the hyperboloid support pillar frame based on the results of the load-bearing performance analysis.

[0015] In the above technical solution, the hyperboloid building and its supporting column framework are defined as the environment, and both intelligent agents perceive and interact based on this environment. The first intelligent agent mainly focuses on the first state of the environment, that is, information related to the structural dynamic characteristics; the second intelligent agent focuses on perceiving the second state of the environment after the column type is determined, including but not limited to material performance parameters, real-time stress conditions during the specific construction process, and the impact of construction equipment on the structure, which are closely related to load-bearing performance.

[0016] The first intelligent agent uses its perception of the first state of the environment to establish a structural dynamic model using relevant theories and methods of structural dynamics, performs structural dynamic analysis on the support frame, and selects the support type most suitable for the current environmental state from a variety of candidate support types based on the results of the structural dynamic analysis.

[0017] After the first agent determines the support type, the second agent, based on the perceived second state of the environment, conducts a load-bearing performance analysis for the selected support type. A load-bearing performance analysis model is established, comprehensively considering factors such as the mechanical properties and geometric dimensions of the materials, the actual stress conditions during construction, and limitations of construction equipment and processes. Through solving and optimizing the model, the optimal structural parameters of the hyperboloid support frame are determined to ensure that the support frame meets the load-bearing capacity requirements during actual construction and use, and can effectively adapt to dynamic changes during construction.

[0018] Two intelligent agents continuously perceive the environmental state throughout the entire construction process, and establish an effective information sharing mechanism between the agents. The second intelligent agent is used to simulate the construction process of the hyperboloid support frame structure by obtaining the second state of the environment under the support type after the first intelligent agent changes the environment, thereby realizing dynamic adjustment for construction optimization.

[0019] In one optional embodiment, the first intelligent agent perceives a first state of the environment, including:

[0020] Obtain the environment in The first state at any moment ,in, The first state at any moment It is expressed as follows:

[0021] ;

[0022] ;

[0023] ;

[0024] In the above formula, This represents a collection of circular support frames. This represents a set of square support frames. Indicates the height of the square support frame. Indicates the number of square support frame bases. This indicates the location of the square support frame. Indicates the height of the circular support frame. Indicates the number of circular support frame bases. This indicates the location of the circular support frame.

[0025] In one optional embodiment, structural dynamic analysis is performed based on the first state, including:

[0026] Calculate the degrees of freedom of each support frame based on its height and number;

[0027] Obtain the hyperboloid building mass, and distribute the hyperboloid building mass to the degrees of freedom of each support frame to obtain the mass matrix;

[0028] The stiffness matrix of each support frame is calculated based on the mass matrix. The stiffness matrix of each support frame is then transformed to the global coordinate system based on the position of the support frame to obtain the hyperboloid building stiffness matrix.

[0029] A dynamic equation is constructed, and the stiffness matrix of the hyperboloid building is solved using the dynamic equation to obtain the vibration frequency.

[0030] In an optional embodiment, the type of support column in the support frame is determined based on the results of structural dynamic analysis, including:

[0031] Construct the natural frequency distribution curve of the support frame structure based on the vibration frequency;

[0032] Based on the natural frequency distribution curve of the aforementioned support frame structure, the first state is determined using a greedy strategy. Down Moment of action ,action It is expressed as follows:

[0033] ;

[0034] In the above formula, This represents the set of support frame types.

[0035] In an optional embodiment, after determining the support type of the support frame based on the results of structural dynamic analysis, the process includes:

[0036] Perform the action and obtain the execution action. Displacement and stress parameters of the rear support frame;

[0037] Calculate based on the displacement parameters and the stress parameters Momentary Rewards ,in, Momentary Rewards The calculation is as follows:

[0038] ;

[0039] In the above formula, , As weight, express Stress at time, express Stress at time, Indicates the time interval. express Displacement at time t, express Displacement at a given moment.

[0040] In one optional embodiment, the second agent senses a second state of the environment under the pillar type and performs load-bearing performance analysis based on the second state, including:

[0041] Get The second state of the environment under the pillar type at any given time ,in, The first state at any moment It is expressed as follows:

[0042] ;

[0043] In the above formula, Indicates the pillar in the Horizontal position Force conditions in the vertical position, Indicates the horizontal length of the support column. Indicates the vertical length of the support column;

[0044] A mechanical model is constructed and environmental parameters are obtained. The mechanical model is then used to calculate the mechanical effects of the forces under the environmental parameters.

[0045] In one optional embodiment, the structural parameters of the hyperboloid column base frame are determined based on the results of load-bearing performance analysis, including:

[0046] Determined based on the aforementioned mechanical effects Moment of action ;

[0047] implement Moment of action The stability values ​​of the hyperboloid support frame structure are obtained.

[0048] For the second state Mapping is performed to obtain the predicted action. ;

[0049] Perform the prediction action The predicted stability values ​​of the hyperboloid support frame structure were obtained.

[0050] Calculate based on the stability value of the hyperboloid column base structure and the predicted stability value of the hyperboloid column base structure. Momentary Rewards ,in, Momentary Rewards The calculation is as follows:

[0051] ;

[0052] In the above formula, This represents the predicted stability value of the hyperboloid column frame structure. This represents the stability value of the hyperboloid support frame structure. Represents a mapping function;

[0053] The second state ,action ,award as well as The second state at time 1 The experience is integrated and placed into an experience replay pool, and the second agent is trained using the experience in the experience replay pool. The values ​​determine the structural parameters of the hyperboloid support frame.

[0054] A second aspect of the present invention provides an optimized construction system based on a hyperboloid support frame structure, comprising:

[0055] An environment setting module is used to set the hyperboloid building as an environment; wherein, the environment includes a support frame;

[0056] The agent construction module is used to construct the first and second agents.

[0057] The first intelligent agent module is used to perceive the first state of the environment and perform structural dynamic analysis based on the first state, and determine the support type of the support frame through the result of the structural dynamic analysis.

[0058] The second intelligent agent module is used to perceive the second state of the environment under the type of support pillar, and to perform load-bearing performance analysis based on the second state, and to determine the structural parameters of the hyperboloid support pillar frame based on the results of the load-bearing performance analysis.

[0059] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement an optimized construction method based on a hyperboloid support frame structure.

[0060] The fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an optimized construction method based on a hyperboloid support frame structure.

[0061] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0062] Two intelligent agents continuously perceive the environmental state throughout the entire construction process, and establish an effective information sharing mechanism between the agents. The second intelligent agent is used to simulate the construction process of the hyperboloid support frame structure by obtaining the second state of the environment under the support type after the first intelligent agent changes the environment, thereby realizing dynamic adjustment for construction optimization. Attached Figure Description

[0063] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings:

[0064] Figure 1 This is a flowchart illustrating an optimized construction method for a hyperboloid support frame structure according to Embodiment 1 of the present invention.

[0065] Figure 2 This is a schematic diagram of a construction optimization system based on a hyperboloid support frame structure provided in Embodiment 2 of the present invention;

[0066] Figure 3 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of this invention are only for explaining this invention and are not intended to limit this invention.

[0068] Example 1

[0069] Figure 1This is a flowchart illustrating an optimized construction method for a hyperboloid support frame structure according to Embodiment 1 of the present invention, as shown below. Figure 1 As shown, an optimization method for constructing a hyperboloid support frame structure includes the following steps:

[0070] The hyperboloid building is set as the environment; wherein the environment includes a support frame;

[0071] Construct the first and second intelligent agents;

[0072] The first intelligent agent perceives the first state of the environment and performs structural dynamic analysis based on the first state, and determines the support type of the support frame through the result of the structural dynamic analysis.

[0073] The second intelligent agent perceives the second state of the environment under the type of support pillar, and performs load-bearing performance analysis based on the second state, and determines the structural parameters of the hyperboloid support pillar frame based on the results of the load-bearing performance analysis.

[0074] It should be noted that the hyperboloid building and its supporting columns are considered the environment, and both intelligent agents use this environment as the basis for perception and interaction. The first intelligent agent mainly focuses on the first state of the environment, i.e., information related to the structural dynamic characteristics; the second intelligent agent focuses on perceiving the second state of the environment after the column type is determined, including but not limited to material performance parameters, real-time stress conditions during the specific construction process, and the impact of construction equipment on the structure, which are closely related to load-bearing performance.

[0075] The first intelligent agent uses its perception of the first state of the environment to establish a structural dynamic model using relevant theories and methods of structural dynamics, performs structural dynamic analysis on the support frame, and selects the support type most suitable for the current environmental state from a variety of candidate support types based on the results of the structural dynamic analysis.

[0076] After the first agent determines the support type, the second agent, based on the perceived second state of the environment, conducts a load-bearing performance analysis for the selected support type. A load-bearing performance analysis model is established, comprehensively considering factors such as the mechanical properties and geometric dimensions of the materials, the actual stress conditions during construction, and limitations of construction equipment and processes. Through solving and optimizing the model, the optimal structural parameters of the hyperboloid support frame are determined to ensure that the support frame meets the load-bearing capacity requirements during actual construction and use, and can effectively adapt to dynamic changes during construction.

[0077] Two intelligent agents continuously perceive the environmental state throughout the entire construction process, and establish an effective information sharing mechanism between the agents. The second intelligent agent is used to simulate the construction process of the hyperboloid support frame structure by obtaining the second state of the environment under the support type after the first intelligent agent changes the environment, thereby realizing dynamic adjustment for construction optimization.

[0078] In one optional embodiment, the first intelligent agent perceives a first state of the environment, including:

[0079] Obtain the environment in The first state at any moment ,in, The first state at any moment It is expressed as follows:

[0080] ;

[0081] ;

[0082] ;

[0083] In the above formula, This represents a collection of circular support frames. This represents a set of square support frames. Indicates the height of the square support frame. Indicates the number of square support frame bases. This indicates the location of the square support frame. Indicates the height of the circular support frame. Indicates the number of circular support frame bases. This indicates the location of the circular support frame.

[0084] It should be noted that the purpose of the first intelligent agent is to select the type of support pillar based on parameters such as the number, position, and shape of the hyperboloid support pillar frame. In this embodiment, the hyperboloid support pillar frame structure is divided into two types: a circular support pillar frame and a square support pillar frame. The structural dynamics are obtained by calculating the number, position, and height of the two types of support pillar frames. Therefore, in this embodiment, the first intelligent agent obtains the number, position, and height of the hyperboloid support pillar frame as... The first state at any moment Determine through a greedy strategy The first state at any moment The corresponding action.

[0085] In one optional embodiment, structural dynamic analysis is performed based on the first state, including:

[0086] Calculate the degrees of freedom of each support frame based on its height and number;

[0087] Obtain the hyperboloid building mass, and distribute the hyperboloid building mass to the degrees of freedom of each support frame to obtain the mass matrix;

[0088] The stiffness matrix of each support frame is calculated based on the mass matrix. The stiffness matrix of each support frame is then transformed to the global coordinate system based on the position of the support frame to obtain the hyperboloid building stiffness matrix.

[0089] A dynamic equation is constructed, and the stiffness matrix of the hyperboloid building is solved using the dynamic equation to obtain the vibration frequency.

[0090] It should be noted that, firstly, based on the height and quantity parameters in the first state, the degrees of freedom of each support frame are accurately calculated. Then, according to the layout of the support frames and the load they bear, the building mass is rationally distributed to the degrees of freedom of each support frame. This involves determining the proportion of mass borne by each support frame in different degrees of freedom directions based on factors such as the position, height, and connection relationship with other structural elements, thus constructing a complete and accurate mass matrix reflecting the building's mass distribution. Next, the stiffness matrix of each support frame is calculated. The stiffness matrix describes the support frame's ability to resist deformation in different degrees of freedom directions; this is an essential step in selecting hyperboloid supports. The stiffness matrices of all the converted support frames are assembled to form the stiffness matrix of the entire hyperboloid building, representing its overall characteristics. Finally, the vibration frequency is calculated, thus completing the structural dynamic analysis.

[0091] In an optional embodiment, the type of support column in the support frame is determined based on the results of structural dynamic analysis, including:

[0092] Construct the natural frequency distribution curve of the support frame structure based on the vibration frequency;

[0093] Based on the natural frequency distribution curve of the aforementioned support frame structure, the first state is determined using a greedy strategy. Down Moment of action ,action It is expressed as follows:

[0094] ;

[0095] In the above formula, This represents the set of support frame types.

[0096] It should be noted that the set of support frame types includes, but is not limited to, X-type and I-type, wherein the support frame type is determined by the shape of the cross-section of the support frame.

[0097] In an optional embodiment, after determining the support type of the support frame based on the results of structural dynamic analysis, the process includes:

[0098] Perform the action and obtain the execution action. Displacement and stress parameters of the rear support frame;

[0099] Calculate based on the displacement parameters and the stress parameters Momentary Rewards ,in, Momentary Rewards The calculation is as follows:

[0100] ;

[0101] In the above formula, , As weight, express Stress at time, express Stress at time, Indicates the time interval. express Displacement at time t, express Displacement at a given moment.

[0102] It should be noted that the reward function is a crucial component in the training of the agent. In this embodiment, stress and displacement are used as parameters for reward calculation. This is because when selecting the type of support frame, the wind resistance and earthquake resistance of the support frame need to be considered, which are typically reflected in the displacement and stress of the support frame. Therefore, this embodiment uses them as parameters for reward calculation. The larger the stress difference and displacement difference, the worse the stability of the support frame type, and thus the lower its reward value. This reward value is then used to provide feedback to the first agent.

[0103] The experience, consisting of the environment, actions, rewards, and the environment in the next moment, is put into the experience replay pool for training the first agent.

[0104] In one optional embodiment, the second agent senses a second state of the environment under the pillar type and performs load-bearing performance analysis based on the second state, including:

[0105] Get The second state of the environment under the pillar type at any given time ,in, The first state at any moment It is expressed as follows:

[0106] ;

[0107] In the above formula, Indicates the pillar in the Horizontal position Force conditions in the vertical position, Indicates the horizontal length of the support column. Indicates the vertical length of the support column;

[0108] A mechanical model is constructed and environmental parameters are obtained. The mechanical model is then used to calculate the mechanical effects of the forces under the environmental parameters.

[0109] In one optional embodiment, the structural parameters of the hyperboloid column base frame are determined based on the results of load-bearing performance analysis, including:

[0110] Determined based on the aforementioned mechanical effects Moment of action ;

[0111] implement Moment of action The stability values ​​of the hyperboloid support frame structure are obtained.

[0112] For the second state Mapping is performed to obtain the predicted action. ;

[0113] Perform the prediction action The predicted stability values ​​of the hyperboloid support frame structure were obtained.

[0114] Calculate based on the stability value of the hyperboloid column base structure and the predicted stability value of the hyperboloid column base structure. Momentary Rewards ,in, Momentary Rewards The calculation is as follows:

[0115] ;

[0116] In the above formula, This represents the predicted stability value of the hyperboloid column frame structure. This represents the stability value of the hyperboloid support frame structure. Represents a mapping function;

[0117] The second state ,action ,award as well as The second state at time 1 The experience is integrated and placed into an experience replay pool, and the second agent is trained using the experience in the experience replay pool. The values ​​determine the structural parameters of the hyperboloid support frame.

[0118] It should be noted that the purpose of the travel mapping in this embodiment is to obtain the stability value of the hyperboloid support frame structure under standard conditions, i.e., the predicted stability value of the hyperboloid support frame structure. This predicted stability value of the hyperboloid support frame structure can be determined by expert experience and historical best data.

[0119] The difference between the two is used as the reward value. The smaller the difference, the larger the reward value. The purpose is to make the same action when the second agent encounters the same situation as the best historical data, thereby reducing the difference between the action output by the neural network and the behavior shown by the best historical data.

[0120] Example 2

[0121] Figure 2 This is a structural diagram of an optimized construction system based on a hyperboloid support frame structure provided in Embodiment 2 of the present invention, as shown below. Figure 2 As shown, an optimized construction system based on a hyperboloid support frame structure includes:

[0122] An environment setting module is used to set the hyperboloid building as an environment; wherein, the environment includes a support frame;

[0123] The agent construction module is used to construct the first and second agents.

[0124] The first intelligent agent module is used to perceive the first state of the environment and perform structural dynamic analysis based on the first state, and determine the support type of the support frame through the result of the structural dynamic analysis.

[0125] The second intelligent agent module is used to perceive the second state of the environment under the type of support pillar, and to perform load-bearing performance analysis based on the second state, and to determine the structural parameters of the hyperboloid support pillar frame based on the results of the load-bearing performance analysis.

[0126] Example 3

[0127] Figure 3 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention, as shown below. Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23, and an output device 24; the number of processors 21 in the computer device can be one or more. Figure 3Taking a processor 21 as an example; the processor 21, memory 22, input device 23, and output device 24 in an electronic device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0128] The memory 22, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules. The processor 21 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 22, thereby implementing the construction optimization method based on the hyperboloid support frame structure of Embodiment 1.

[0129] The memory 22 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 22 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory, or other non-volatile solid-state storage device. In some instances, the memory 22 may further include memory remotely located relative to the processor 21, which can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0130] Input device 23 can be used to receive user input such as ID and password. Output device 24 is used to output the network configuration page.

[0131] Example 4

[0132] Embodiment 4 of the present invention also provides a computer-readable storage medium, wherein the computer-executable instructions, when executed by a computer processor, are used to implement an optimized construction method for a hyperboloid support frame structure as provided in Embodiment 1.

[0133] The storage medium containing computer-executable instructions provided in the embodiments of the present invention is not limited to the method operation provided in Embodiment 1, but can also execute related operations in the construction optimization method based on hyperboloid support frame structure provided in any embodiment of the present invention.

[0134] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for erection optimization based on a hyperboloid strutting base structure, characterized in that, The method comprises the following steps: setting a double-curved building as an environment; wherein the environment comprises pillar bases; constructing a first agent and a second agent; the first agent perceives a first state of the environment, and performs structural dynamic analysis according to the first state, and determines a pillar type of the pillar base through a result of the structural dynamic analysis; wherein the first agent perceiving the first state of the environment comprises: acquiring a first state of the environment at a time instant acquiring a first state of the environment at a time instant wherein, acquiring a first state of the environment at a time instant is represented as follows: ； ； ; in the above formula, denotes a set of circular pillar bases, denotes a set of square pillar bases, denotes the height of a square pillar base, denotes the number of square pillar bases, denotes the position of a square pillar base, denotes the height of a circular pillar base, denotes the number of circular pillar bases, denotes the position of a circular pillar base; performing structural dynamic analysis according to the first state comprises: calculating degrees of freedom of each pillar base according to heights and quantities of the pillar bases; obtaining a mass of the double-curved building, and distributing the mass of the double-curved building to the degrees of freedom of each pillar base to obtain a mass matrix; calculating a stiffness matrix of each pillar base according to the mass matrix, and converting the stiffness matrix of each pillar base to a global coordinate based on positions of the pillar bases to obtain a stiffness matrix of the double-curved building; constructing a dynamic equation, and solving the stiffness matrix of the double-curved building by using the dynamic equation to obtain a vibration frequency; the second agent perceives a second state of the environment under the pillar type, and performs bearing performance analysis according to the second state, and determines a structure parameter of the double-curved pillar base through a result of the bearing performance analysis.

2. The method of claim 1, wherein, determining the pillar type of the pillar base through the result of the structural dynamic analysis comprises: constructing a self-vibration frequency distribution curve of the pillar base structure based on the vibration frequency; Based on the self-vibration frequency distribution curve of the support frame structure, the first state is determined by a greedy strategy Down the action at the moment , action is represented as follows: ； In the above formulae, represents a set of pillar base types.

3. The method of claim 2, wherein, after determining the pillar type of the pillar base through the result of the structural dynamic analysis, comprising: performing the action and obtaining the action performed displacement and stress parameters of the rear strut pedestal calculating, based on the displacement parameter and the stress parameter a reward at the moment wherein a reward at the moment is calculated as follows: ； In the above formula, , is a weight, denotes the stress at the time point, denotes the stress at the time point, denotes the interval time point, denotes the displacement at the time point, denotes the displacement at the time point.

4. The method of claim 1, wherein, the second agent perceives the second state of the environment under the pillar type, and performs bearing performance analysis according to the second state, comprising: acquiring a second state of the environment at the time under the type of the support wherein, a first state at the time is represented as follows: ； In the above formula, denotes the force on the strut at the horizontal position at the vertical position, and denotes the horizontal length of the strut, denotes the vertical length of the strut; constructing a mechanical model and obtaining environment parameters, and calculating a mechanical effect of the stress condition under the environment parameters by using the mechanical model.

5. The method of claim 4, wherein the hyperboloid support structure is optimized by, determining the structure parameter of the double-curved pillar base through the result of the bearing performance analysis comprises: determining the mechanical effect case action at the moment ; Perform Actions at a time , get hyperboloid pillar base frame structure stability value; for the second state mapping, obtaining a predicted action ; performing the predicted action obtaining a predicted hyperboloid strut base structure stability value; calculating a hyperbolic-parabolic support structure stability value based on the predicted hyperbolic-parabolic support structure stability value Rewards at a time wherein Rewards at a time is calculated as follows: ； In the above formula, denotes a predicted hyperbolic braced racking structure stability value, denotes a hyperbolic braced racking structure stability value, denotes a mapping function; the second state , action , reward and the second state at the moment is integrated into experience and put into an experience replay pool, and the second agent is trained using experience in the experience replay pool, and the hyperbolic paraboloid pillar base structure parameters are determined using the obtained value after training.

6. A hyperbolic braced racking structure based build optimization system, characterized in that, comprising: an environment setting module for setting a double-curved building as an environment; wherein the environment comprises pillar bases; an agent constructing module for constructing a first agent and a second agent; a first agent module for the first agent to perceive a first state of the environment, and perform structural dynamic analysis according to the first state, and determine a pillar type of the pillar base through a result of the structural dynamic analysis; wherein the first agent perceives the first state of the environment comprises: acquiring a first state of the environment at a time instant acquiring a first state of the environment at a time instant wherein, acquiring a first state of the environment at a time instant is represented as follows: ； ； ; in the above formula, denotes a set of circular pillar bases, denotes a set of square pillar bases, denotes the height of a square pillar base, denotes the number of square pillar bases, denotes the position of a square pillar base, denotes the height of a circular pillar base, denotes the number of circular pillar bases, denotes the position of a circular pillar base; performing structural dynamic analysis according to the first state comprises: calculating degrees of freedom of each pillar base according to heights and quantities of the pillar bases; obtaining a mass of the double-curved building, and distributing the mass of the double-curved building to the degrees of freedom of each pillar base to obtain a mass matrix; calculating a stiffness matrix of each pillar base according to the mass matrix, and converting the stiffness matrix of each pillar base to a global coordinate based on positions of the pillar bases to obtain a stiffness matrix of the double-curved building; constructing a dynamic equation, and solving the stiffness matrix of the double-curved building by using the dynamic equation to obtain a vibration frequency; A second intelligent agent module is configured to perceive a second state of the environment under the column type by the second intelligent agent, and perform a bearing capacity analysis according to the second state, and determine the parameters of the double-curved column base frame structure according to the result of the bearing capacity analysis.

7. An electronic device, comprising: The computer program is stored in the memory and executable on the processor, and the processor executes the computer program to implement the construction optimization method based on the double-curved column base frame structure according to any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is stored in the memory and executable on the processor, and the processor executes the computer program to implement the construction optimization method based on the double-curved column base frame structure according to any one of claims 1 to 5.

Images