Intelligent optimized arrangement method and equipment for beam-column joint steel bars of stiff structure

Abstract

The invention provides an intelligent optimized arrangement method and equipment for reinforced structure beam-column joint steel bars, and provides a novel intelligent optimized arrangement method for the reinforced structure beam-column joint steel bars in order to solve the problems that the arrangement process of the reinforced structure joint steel bars is tedious, long in consumed time, low in efficiency, excessively dependent on artificial experience and the like. According to the main technical scheme, reinforcing steel bar arrangement parameters of nodes to be optimized are extracted through a node reinforcing steel bar parameter extraction model, the reinforcing steel bar arrangement parameters are input into a reinforcing steel bar arrangement optimization parameter selection module for parameter selection to be optimized, and the node reinforcing steel bar intelligent optimization arrangement model of the stiff structure is obtained according to all the reinforcing steel bar arrangement parameters meeting the conditions output by the node reinforcing steel bar intelligent optimization arrangement model. And the optimization function is used for calculation to obtain optimal steel bar arrangement parameters. According to the method, the optimal arrangement parameters of the beam-column joint steel bars of the stiff structure can be quickly obtained through simple drawing input.

Description

Technical Field

[0001] The invention relates to a method and equipment for intelligently optimizing the arrangement of steel bars at beam-column nodes of a rigid structure. Background Art

[0002] As a high-performance building form, rigid structure is widely used in modern engineering construction. With its superior force-bearing performance, good earthquake resistance and high space utilization, it has been widely used in high-rise buildings, large public facilities, industrial plants, bridges and special-purpose buildings.

[0003] During on-site construction, there are often a series of problems such as difficulty in interlacing steel bars, too dense steel bars, and inconvenient anchor welding. Experienced engineering and technical personnel are needed to optimize the steel bar arrangement in advance, and different types of nodes need to be optimized one by one. The process is cumbersome, time-consuming, and overly dependent on manual experience. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for intelligently optimizing the arrangement of steel bars at beam-column nodes of a rigid structure.

[0005] In order to solve the above problems, the present invention provides a method for intelligent optimization arrangement of steel bars at beam-column nodes of a rigid structure, comprising:

[0006] The first information collection and processing module collects sample steel bar arrangement parameters from the steel bar arrangement drawings of the rigid structure nodes;

[0007] The first model training module is to establish a node reinforcement parameter extraction model based on the reinforcement arrangement drawings and sample reinforcement arrangement parameters of the rigid structure nodes and the use of artificial intelligence methods;

[0008] The second information collection and processing module collects sample steel bar arrangement parameters and optimizes arrangement rules;

[0009] The second model training module trains the intelligent optimization arrangement model of steel bars in the rigid structure nodes based on the sample steel bar arrangement parameters and the optimization arrangement rules;

[0010] The steel bar arrangement optimization parameter selection module sets the steel bar arrangement parameters to be optimized according to the requirements; the steel bar intelligent optimization arrangement model of the rigid structure node optimizes the steel bar arrangement parameters to be optimized according to the optimization arrangement rules to select the steel bar arrangement information parameters that meet the requirements of each rigid structure node, and inputs all the steel bar arrangement information parameter groups that meet the requirements of each rigid structure node into the optimization function to obtain the optimal arrangement plan.

[0011] Furthermore, in the above method, the sample steel bar arrangement parameters include: steel bar type x, steel bar diameter d, steel bar spacing s, steel bar row number m and total number of steel bars n.

[0012] Furthermore, in the above method, the first information collection and processing module collects sample steel bar arrangement parameters from the steel bar arrangement drawings of the rigid structure nodes, including:

[0013] The steel bar arrangement parameters are labeled to facilitate recognition by the first model training module; and the data units of the steel bar arrangement parameters are unified, the units of the steel bar diameter d and the steel bar spacing s are unified as "mm"; the units of the steel bar type x, the number of steel bar rows m and the total number of steel bars n are "dimensionless".

[0014] Furthermore, in the above method, the input of the node reinforcement parameter extraction model is a reinforcement arrangement drawing of the rigid structure node;

[0015] The output of the node reinforcement parameter extraction model is the reinforcement type x, reinforcement diameter d, reinforcement spacing s, reinforcement row number m, and total number of reinforcement n.

[0016] Furthermore, in the above method, the first model training module, based on obtaining the steel bar arrangement drawings and sample steel bar arrangement parameters of the rigid structure nodes and using artificial intelligence methods, establishes a node steel bar parameter extraction model, including:

[0017] The node reinforcement parameter extraction model includes: a DNN, RNN or Transformer model.

[0018] The training process of the node reinforcement parameter extraction model adopts optimization algorithms such as SGD and Adam. The training can be stopped when the target loss function reaches the preset expected value. After the training is completed, the template support system component parameter group model, namely the node reinforcement parameter extraction model, is obtained.

[0019] Furthermore, in the above method, the reinforcement arrangement optimization parameter selection module sets the reinforcement arrangement parameters to be optimized according to the requirements.

[0020] The steel bar arrangement parameters to be optimized include: one or more of the steel bar type x, steel bar diameter d, steel bar spacing s, steel bar row number m and steel bar total number n.

[0021] Furthermore, in the above method, the optimization arrangement rule includes:

[0022] The number of steel bar rows m is less than or equal to 3; the steel bar spacing s is between 25 and 300 mm; the total number of steel bars n is optimized to be between 75% and 125% n 0 , where n 0 is the initial number of steel bars; the optimal range of steel bar diameter is 75% to 125%d 0 , and between 12 and 40 mm, where d 0is the initial steel bar diameter; the steel bar anchoring methods include: direct anchoring, connecting plate welding and steel bar sleeve connection; avoid casting spaces smaller than the preset threshold or complex geometric shapes.

[0023] Furthermore, in the above method, the steel bar arrangement information parameters of each rigid structure node output by the steel bar intelligent optimization arrangement model of the rigid structure node appear in groups. Assuming that there are j groups of steel bar arrangement information parameters of each rigid structure node that meet the requirements, the following matrix is ​​output:

[0024]

[0025] The optimization function is:

[0026] p=p 1 (x)+p 2 (n,d)+p 3 (s)+p 4 (m);

[0027]

[0028] Among them, d p is the target steel bar diameter, set by the designer, n 0 is the initial number of steel bars, w 1 、w 2 、w 3 、w 4 is the weight coefficient, the weight value range is 0 to 1, and the weight values ​​should be determined by the project staff according to the characteristics and requirements of different projects; the type of steel bar is x, the diameter of the steel bar is d, the spacing of the steel bars is s, the number of steel bar rows is m, and the total number of steel bars is n;

[0029] p is the score of a group of steel bar arrangement information parameters of a certain steel bar rigid structure node, and the group of steel bar arrangement information parameters with the highest score output by the optimization function is selected as the result output.

[0030] According to another aspect of the present invention, there is further provided a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: adopt any of the methods described above.

[0031] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0032] Processor; and

[0033] A memory arranged to store computer executable instructions which, when executed, cause the processor to: adopt any of the methods described above.

[0034] Compared with the prior art, the present invention proposes a new intelligent optimization arrangement method for steel bars at beam-column nodes of rigid structures to solve the problems of cumbersome, time-consuming, low efficiency, and over-reliance on manual experience in the arrangement process of steel bars at rigid structure nodes. The main technical components of the present invention are as follows:

[0035] The reinforcement arrangement parameters of the nodes to be optimized in the model are extracted through the node reinforcement parameters, and input into the reinforcement arrangement optimization parameter selection module to select the parameters to be optimized. All qualified reinforcement arrangement parameters output by the intelligent optimization arrangement model of the reinforcement at the rigid structure nodes are calculated by the optimization function to obtain the optimal reinforcement arrangement parameters. This application can quickly obtain the optimal reinforcement arrangement parameters of the rigid structure beam-column nodes through simple drawing input.

[0036] Compared with the current method for arranging steel bars in rigid structure nodes, the beneficial effects of the present invention are mainly as follows:

[0037] (1) High efficiency. The present invention provides a method for intelligent optimization of steel bar arrangement at rigid structure nodes, which automatically recognizes drawings and intelligently optimizes steel bar arrangement, and the speed is much higher than the traditional manual arrangement method;

[0038] (2) The optimization parameters have strong overall integrity. In the existing rigid structure node reinforcement arrangement method, individual parameters are continuously adjusted based on manual experience, and then other parameters are checked in turn to see if they meet the requirements. If one of the parameters does not meet the requirements, the next set of adjustments needs to be made again. This method comprehensively considers various parameters, performs overall optimization scoring based on preset rules, and selects the best solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of a method for intelligently optimizing the arrangement of steel bars at beam-column nodes of a rigid structure according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0041] In this specification, reference to "one embodiment" or "the embodiment" means that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present invention. The phrase "in one embodiment" appearing in various places in this specification does not necessarily all refer to the same embodiment.

[0042] It should be noted that the embodiments of the present invention describe the process steps in a specific order, but this is only for the purpose of illustrating the specific embodiment, rather than limiting the order of the steps. On the contrary, in different embodiments of the present invention, the order of the steps can be adjusted according to the adjustment of the process.

[0043] like Figure 1 As shown, the present invention provides a method for intelligently optimizing the arrangement of steel bars at beam-column nodes of a rigid structure, comprising:

[0044] Step S1, the first information collection and processing module collects sample steel bar arrangement parameters from the steel bar arrangement drawing of the rigid structure node;

[0045] Preferably, the sample steel bar arrangement parameters include: steel bar type x, steel bar diameter d, steel bar spacing s, steel bar row number m and total number of steel bars n;

[0046] Here, the collection work of the first information collection and processing module includes collecting drawings related to the steel bar arrangement of the rigid structure node, and processing the steel bar arrangement information such as the steel bar type x, steel bar diameter d, steel bar spacing s, steel bar row number m and steel bar total number n;

[0047] Preferably, the processing work of the first information collection and processing module further includes labeling the steel bar arrangement parameters to facilitate identification by the first model training module; and unifying the data units of the steel bar arrangement parameters, the units of the steel bar diameter d and the steel bar spacing s are unified as "mm", and the units of the steel bar type x, the number of steel bar rows m, and the total number of steel bars n are "dimensionless";

[0048] Step S2, a first model training module, based on obtaining the reinforcement arrangement drawings and sample reinforcement arrangement parameters of the rigid structure nodes, and using artificial intelligence methods, establishes a node reinforcement parameter extraction model;

[0049] Here, the input of the node reinforcement parameter extraction model is the reinforcement arrangement drawing of the rigid structure node;

[0050] The output of the node reinforcement parameter extraction model is reinforcement type x, reinforcement diameter d, reinforcement spacing s, reinforcement row number m, and total number of reinforcement n;

[0051] Optionally, the node reinforcement parameter extraction model may be in any form, and may include: DNN, RNN, Transformer and other models, which may be used to establish a parameter group model of the formwork support system component;

[0052] Preferably, in order to ensure the training effect, the training set of the node reinforcement parameter extraction model needs to exceed 10,000 sets of data.

[0053] Preferably, the training process of the node reinforcement parameter extraction model can adopt optimization algorithms such as SGD and Adam, and the training can be stopped until the target loss function reaches a preset expected value; after the training is completed, the template support system component parameter group model, i.e., the node reinforcement parameter extraction model, is obtained.

[0054] Step S3, a first information collection and processing module, collecting sample steel bar arrangement parameters and optimizing arrangement rules;

[0055] Step S4, a second model training module, based on the sample steel bar arrangement parameters and the optimization arrangement rules, trains a steel bar intelligent optimization arrangement model for a rigid structure node;

[0056] Step S5, a reinforcement arrangement optimization parameter selection module, setting reinforcement arrangement parameters to be optimized according to requirements;

[0057] Preferably, the reinforcement arrangement parameters to be optimized include: one or more of the reinforcement type x, reinforcement diameter d, reinforcement spacing s, reinforcement row number m, and reinforcement total number n;

[0058] Step S6, the intelligent optimization layout model of steel bars at rigid structure nodes optimizes the steel bar layout parameters to be optimized according to the optimization layout rules to select steel bar layout information parameters that meet each rigid structure node, and inputs all steel bar layout information parameters of each rigid structure node into the optimization function to obtain a layout plan.

[0059] Preferably, the optimized arrangement rules include: the number of steel bar rows m is less than or equal to 3; the steel bar spacing s is between 25 and 300 mm; the total number of steel bars n is optimized to be between 75% and 125% n 0 , where n 0 is the initial number of steel bars; the optimal range of steel bar diameter is 75% to 125%d 0 , and between 12 and 40 mm, where d 0 is the initial steel bar diameter; the steel bar anchoring methods include: direct anchoring, connection plate welding and steel bar sleeve connection; avoid casting spaces smaller than the preset threshold or complex geometric shapes;

[0060] The steel bar arrangement information parameters of each rigid structure node output by the steel bar intelligent optimization arrangement model appear in groups. Assuming that there are j groups of steel bar arrangement information parameters of each rigid structure node that meet the requirements, the following matrix is ​​output:

[0061]

[0062] The optimization function is:

[0063] p=p 1 (x)+p 2 (n,d)+p 3 (s)+p 4 (m);

[0064]

[0065] Among them, d pis the target steel bar diameter, set by the designer, n 0 is the initial number of steel bars, w 1 、w 2 、w 3 、w 4 is the weight coefficient, the weight value range is 0 to 1, and the weight values ​​should be determined by the project staff according to the characteristics and requirements of different projects; the type of steel bar is x, the diameter of the steel bar is d, the spacing of the steel bars is s, the number of steel bar rows is m, and the total number of steel bars is n;

[0066] p is the score of a group of steel bar arrangement information parameters of a certain steel bar rigid structure node, and the group of steel bar arrangement information parameters with the highest score output by the optimization function is selected as the result output.

[0067] According to another aspect of the present invention, there is further provided a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: adopt any of the methods described above.

[0068] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0069] Processor; and

[0070] A memory arranged to store computer executable instructions which, when executed, cause the processor to: adopt any of the methods described above.

[0071] In summary, in order to solve the problems of cumbersome, time-consuming, low-efficiency, and over-reliance on manual experience in the steel bar arrangement process of rigid structure nodes, the present invention proposes a new intelligent optimization arrangement method for steel bars at the beam-column nodes of rigid structures. The main technical components are as follows: extracting the steel bar arrangement parameters to be optimized of the nodes to be optimized through the node steel bar parameter extraction model, selecting the parameters to be optimized through the steel bar arrangement optimization parameter selection module, and calculating the optimal steel bar arrangement parameters by the optimization function according to the output of the steel bar intelligent optimization arrangement model of the rigid structure nodes. The present application can realize the rapid acquisition of the optimal template support system component parameters through simple parameter input.

[0072] Compared with the current method for arranging steel bars in rigid structure nodes, the beneficial effects of the present invention are mainly as follows:

[0073] (1) High efficiency. The present invention provides a method for intelligent optimization of steel bar arrangement at rigid structure nodes, which automatically recognizes drawings and intelligently optimizes steel bar arrangement, and the speed is much higher than the traditional manual arrangement method;

[0074] (2) The optimization parameters have strong overall integrity. In the existing rigid structure node reinforcement arrangement method, individual parameters are continuously adjusted based on manual experience, and then other parameters are checked in turn to see if they meet the requirements. If one of the parameters does not meet the requirements, the next set of adjustments needs to be made again. This method comprehensively considers various parameters, performs overall optimization scoring based on preset rules, and selects the best solution.

[0075] The detailed contents of the device embodiments of the present invention can be found in the corresponding parts of the method embodiments, which will not be described in detail here.

[0076] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0077] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0078] In addition, a part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The program instruction for calling the method of the present invention may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-bearing medium, and / or stored in a working memory of a computer device that runs according to the program instruction. Here, according to an embodiment of the present invention, a device is included, the device including a memory for storing computer program instructions and a processor for executing program instructions, wherein, when the computer program instruction is executed by the processor, the device is triggered to run the method and / or technical solution based on the aforementioned multiple embodiments of the present invention.

[0079] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for intelligent optimization of steel bar arrangement at beam-column nodes of rigid structures, characterized in that: include: The first information collection and processing module collects sample steel bar arrangement parameters from the steel bar arrangement drawings of the rigid structure nodes; The first model training module is to establish a node reinforcement parameter extraction model based on the reinforcement arrangement drawings and sample reinforcement arrangement parameters of the rigid structure nodes and the use of artificial intelligence methods; The second information collection and processing module collects sample steel bar arrangement parameters and optimizes arrangement rules; The second model training module trains the intelligent optimization arrangement model of steel bars in the rigid structure nodes based on the sample steel bar arrangement parameters and the optimization arrangement rules; The reinforcement arrangement optimization parameter selection module sets the reinforcement arrangement parameters to be optimized according to the requirements; The intelligent optimization arrangement model of steel bars at rigid structure nodes optimizes the steel bar arrangement parameters to be optimized according to the optimization arrangement rules to select steel bar arrangement information parameters that meet the requirements of each rigid structure node, and inputs all steel bar arrangement information parameter groups that meet the requirements of each rigid structure node into the optimization function to obtain the optimal arrangement plan.

2. The method for intelligent optimization of steel bar arrangement at beam-column nodes of rigid structures according to claim 1, characterized in that: The sample steel bar arrangement parameters include: steel bar type x, steel bar diameter d, steel bar spacing s, steel bar row number m and total number of steel bars n.

3. The intelligent optimization arrangement method for steel bars at the beam-column nodes of a rigid structure according to claim 1 or 2, characterized in that: The first information collection and processing module collects sample steel bar arrangement parameters from the steel bar arrangement drawings of the rigid structure nodes, including: The steel bar arrangement parameters are labeled to facilitate identification by the first model training module; and the data units of the steel bar arrangement parameters are unified, the units of the steel bar diameter d and the steel bar spacing s are unified as "mm"; the units of the steel bar type x, the number of steel bar rows m and the total number of steel bars n are "dimensionless".

4. The method for intelligent optimization of steel bar arrangement at beam-column nodes of a rigid structure according to claim 1 or 2, characterized in that: The input of the node reinforcement parameter extraction model is the reinforcement arrangement drawing of the rigid structure node; The output of the node reinforcement parameter extraction model is the reinforcement type x, reinforcement diameter d, reinforcement spacing s, reinforcement row number m, and total number of reinforcement n.

5. The method for intelligent optimization of steel bar arrangement at beam-column nodes of rigid structures according to claim 1, characterized in that: The first model training module, based on the steel bar arrangement drawings and sample steel bar arrangement parameters of the rigid structure nodes, uses artificial intelligence methods to establish a node steel bar parameter extraction model, including: The node reinforcement parameter extraction model includes: a DNN, RNN or Transformer model. The training process of the node reinforcement parameter extraction model adopts the SGD and Adam optimization algorithms until the target loss function reaches the preset expected value, and then the training can be stopped. After the training is completed, the template support system component parameter group model, namely the node reinforcement parameter extraction model, is obtained.

6. The method for intelligent optimization of steel bar arrangement at beam-column nodes of a rigid structure according to claim 1 or 2, characterized in that: The reinforcement arrangement optimization parameter selection module sets the reinforcement arrangement parameters to be optimized according to the requirements. The steel bar arrangement parameters to be optimized include: one or more of the steel bar type x, steel bar diameter d, steel bar spacing s, steel bar row number m and steel bar total number n.

7. The method for intelligent optimization of steel bar arrangement at beam-column nodes of a rigid structure according to claim 1 or 2, characterized in that: The optimization arrangement rules include: The number of steel bar rows m is less than or equal to 3; the steel bar spacing s is between 25 and 300 mm; the optimization interval of the total number of steel bars n is 75% to 125% n0, where n0 is the initial number of steel bars; the optimization interval of steel bar diameter is 75% to 125% d0, and is between 12 and 40 mm, where d0 is the initial steel bar diameter; steel bar anchoring methods include: direct anchoring, connecting plate welding and steel bar sleeve connection; avoid casting space smaller than the preset threshold or complex geometric shapes.

8. The method for intelligent optimization of steel bar arrangement at beam-column nodes of a rigid structure according to claim 1 or 2, characterized in that: The steel bar arrangement information parameters of each rigid structure node output by the steel bar intelligent optimization arrangement model appear in groups. Assuming that there are j groups of steel bar arrangement information parameters of each rigid structure node that meet the requirements, the following matrix is ​​output: The optimization function is: p=p1(x)+p2(n,d)+p3(s)+p4(m); Among them, d p is the target steel bar diameter, set by the designer, n0 is the initial number of steel bars, w1, w2, w3, w4 are weight coefficients, the weight value range is 0-1, and the weight values ​​should be determined by the project staff according to the characteristics and requirements of different projects; the type of steel bar is x, the diameter of the steel bar is d, the spacing between the steel bars is s, the number of steel bar rows is m, and the total number of steel bars is n; p is the score of a group of steel bar arrangement information parameters of a certain steel bar rigid structure node, and the group of steel bar arrangement information parameters with the highest score output by the optimization function is selected as the result output.

9. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor is caused to: adopt the method according to any one of claims 1 to 8.

10. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: employ a method as claimed in any one of claims 1 to 8.

Images