Dynamic optimization method and device for steel column connection scheme

Abstract

The present disclosure relates to a dynamic optimization method and device for a steel column connection scheme, and relates to the technical field of big data processing. The method comprises the following steps: determining, based on a preset stress value analysis model, an ear plate stress distribution characteristic of a butt joint connecting ear plate of a steel column according to current real-time construction data, and determining the relevance of a to-be-installed steel column and the butt joint connecting ear plate of the steel column according to the ear plate stress distribution characteristic to obtain a first analysis result; analyzing the stress change law and safety of the butt joint connecting ear plate of the steel column in the construction process according to the ear plate stress distribution characteristic to obtain a second analysis result, and obtaining a target analysis result according to the first analysis result and the second analysis result; dynamically optimizing an original steel column connection scheme of a target steel frame structure according to the target analysis result to obtain a target steel column connection scheme, and connecting the to-be-installed steel column in the target steel frame structure based on the target steel column connection scheme. The present disclosure improves the steel column connection efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of big data processing technology, and more specifically, to a dynamic optimization method and apparatus for steel column connection schemes. Background Technology

[0002] Existing steel column connection schemes can be implemented as follows: First, the steel column is segmented, typically with 2-3 floors per segment; second, connecting lugs are used to temporarily fix the steel column joints around their perimeter, and then the main frame steel beams of the current floor are installed to form a stable frame unit. Based on this, wind loads, construction loads, and hoisting impact loads during installation are considered, and a complete steel column connection scheme is derived based on expert experience. However, this connection scheme does not consider environmental factors during construction or real-time deviations of the steel columns, resulting in a low accuracy rate.

[0003] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this disclosure is to provide a dynamic optimization method and device for steel column connection schemes, thereby overcoming, to at least a certain extent, the problem of low accuracy of connection schemes caused by limitations and defects in related technologies.

[0005] According to one aspect of this disclosure, a dynamic optimization method for a steel column connection scheme is provided, comprising: receiving current real-time construction data corresponding to a target steel frame structure sent by a data acquisition terminal; the current real-time construction data including at least one of the following: first strain data of the steel column butt joint connecting lug of the steel column to be installed, second strain data of the bolt associated with the steel column butt joint connecting lug, steel column inclination angle data and steel column displacement data of the steel column to be installed, and current construction environment data; determining the stress distribution characteristics of the steel column butt joint connecting lug based on a preset stress value analysis model according to the current real-time construction data, and further optimizing the steel column butt joint connecting lug. The correlation between the steel column to be installed and the steel column butt joint connecting lug is analyzed based on the stress distribution characteristics of the lug, resulting in a first analysis result. The stress change law and safety of the steel column butt joint connecting lug during construction are analyzed based on the stress distribution characteristics of the lug, resulting in a second analysis result. A target analysis result is obtained based on the first and second analysis results. The original steel column connection scheme with the target steel frame structure is dynamically optimized based on the target analysis result to obtain a target steel column connection scheme. The steel columns to be installed in the target steel frame structure are then connected based on the target steel column connection scheme.

[0006] In an exemplary embodiment of this disclosure, the first strain data includes strain data of the shear core region between the lug bolt holes corresponding to the lug connecting to the steel column and strain data at the weld toe; the strain data of the shear core region between the lug bolt holes is collected based on a first foil strain gauge disposed in the shear core region between the lug bolt holes, and the strain data at the weld toe is collected based on a second foil strain gauge disposed at the weld toe; the second strain data is collected based on a strain gauge axial force meter disposed on the bolt; the steel column tilt angle data is collected based on a tilt sensor disposed at the top of the steel column to be installed, and the steel column displacement data is collected based on a wire displacement meter disposed at the bottom of the steel column to be installed; the current construction environment data includes current temperature data and current wind force data, the current temperature data is collected based on a temperature sensor, and the current wind force data is collected based on a wind force sensor.

[0007] In an exemplary embodiment of this disclosure, the stress distribution characteristics of the lug plate of the steel column butt connection are determined based on the current real-time construction data according to a preset stress value analysis model. This includes: determining a first stress value based on the elastic modulus of the lug plate and the strain data of the shear core area between the lug plate bolt holes; determining a second stress value based on the elastic modulus of the lug plate and the strain data at the weld toe; determining the actual axial force of the bolt based on the second strain data; and obtaining the original attribute data of the target steel frame structure. The original attribute data includes at least one of the following: the first weight of the steel column to be installed, the second weight of the installed steel beam / secondary component, the third weight of the construction personnel and construction equipment, and the load of the hoisting equipment; constructing an input feature sequence based on the original attribute data, the first stress value, the second stress value, the actual axial force of the bolt, the steel column inclination angle data, the steel column displacement data, the current temperature data, and the current wind force data; and inputting the input feature sequence into the preset stress value analysis model to obtain the stress distribution characteristics of the lug plate of the steel column butt connection.

[0008] In an exemplary embodiment of this disclosure, the input feature sequence is input into a preset stress value analysis model to obtain the stress distribution characteristics of the lug plate of the steel column butt joint connection. This includes: embedding the input feature sequence into a first embedding vector based on a first embedding layer, and encoding the input feature sequence into a first position vector based on a first position encoding module; superimposing the first embedding vector and the first position vector to obtain a first input vector, and encoding the first input vector into a first encoding result based on a first rotation feature encoding module; decoding the first encoding result into a first encoding matrix based on a first feature decoding module, and transforming the first encoding matrix into a first logical matrix based on a first linear transformation layer; and mapping the first logical matrix into the lug plate of the steel column butt joint connection to obtain the stress distribution characteristics of the lug plate. The stress distribution characteristics of the lug plate include a stress concentration region, the actual stress value of each stress monitoring point in the stress concentration region, and the maximum stress value, minimum stress value, average stress value, and stress gradient distribution of the stress concentration region.

[0009] In one exemplary embodiment of this disclosure, encoding a first input vector based on a first rotation feature encoding module to obtain a first encoding result includes: calculating a first attention mechanism for the first input vector based on a first multi-head self-attention module, and performing residual connection and normalization processing on the first attention mechanism based on a first residual connection and normalization module to obtain a first normalization processing result; the first attention mechanism is used to interact with the first stress value and the second stress value, as well as other data in the original attribute data and the current real-time construction data other than the first stress value and the second stress value; linearizing the first normalization processing result based on a first feedforward neural network to obtain a first linearization processing result, and performing residual connection and normalization processing on the first linearization processing result based on a second residual connection and normalization module to obtain the first encoding result.

[0010] In an exemplary embodiment of this disclosure, a first analysis result is obtained by analyzing the correlation between the steel column to be installed and the steel column butt joint connecting lug plate based on the lug plate stress distribution characteristics. This includes: analyzing the correspondence between the steel column deformation of the steel column to be installed and the lug plate stress change of the steel column butt joint connecting lug plate based on the steel column inclination angle data, steel column displacement data, and lug plate stress distribution characteristics to obtain the first analysis result; wherein, the first analysis result is used to evaluate the impact of the structural deformation of the steel column to be installed on the long-term stress safety of the lug plate of the steel column butt joint connecting lug plate.

[0011] In an exemplary embodiment of this disclosure, a second analysis result is obtained by analyzing the safety and stress variation law of the steel column butt joint connecting lug plate during construction based on the stress distribution characteristics of the lug plate. This includes: extracting the stress concentration region from the stress distribution characteristics of the lug plate and the actual stress value of each stress monitoring point within the stress concentration region, and obtaining the expected stress value of the stress monitoring point; calculating a first ratio between the actual stress value and the expected stress value of the stress monitoring point, and obtaining a safety analysis result of the steel column butt joint connecting lug plate during construction based on the first ratio; determining the working condition category of the stress distribution characteristics of the lug plate based on the current construction environment data, and determining the stress characteristics of the steel column butt joint connecting lug plate under different working conditions based on the working condition category and the stress distribution characteristics of the lug plate, to obtain a stress variation law analysis result; generating a second analysis result based on the safety analysis result and the stress variation law analysis result; the second analysis result is used to assess the safety hazards of the steel column butt joint connecting lug plate during construction and the degree of influence of special working conditions on the steel column butt joint connecting lug plate.

[0012] In one exemplary embodiment of this disclosure, the target steel column connection scheme is obtained by dynamically optimizing the original steel column connection scheme with the target steel frame structure based on the target analysis results. This includes: obtaining the first weight of the steel column to be installed associated with the target steel frame structure, the second weight of the installed steel beam / secondary component, the third weight of construction personnel and construction equipment, the load of hoisting equipment, and the maximum wind load; generating the original steel column connection scheme with the target steel frame structure based on the first weight, the second weight, the third weight, the load of hoisting equipment, and the maximum wind load; calling a preset content generation model and inputting the original steel column connection scheme and the target analysis results into the preset content generation model to dynamically optimize the original steel column connection scheme to obtain the target steel column connection scheme.

[0013] In one exemplary embodiment of this disclosure, the original steel column connection scheme and the target analysis result are input into the preset content generation model to dynamically optimize the original steel column connection scheme to obtain the target steel column connection scheme. This includes: generating basic information to be predicted based on the original steel column connection scheme and the target analysis result, and generating context information to be predicted based on preset parameter prompts; performing embedding mapping processing on the basic information to be predicted based on an embedding mapping layer to obtain a first basic feature, performing embedding mapping processing on the context information to be predicted to obtain a context flag sequence, and encoding the first basic feature and the context flag sequence based on an encoding layer to obtain a first target feature; and determining the first model weights of multiple expert neural network models in performing the scheme optimization task in the construction safety dimension and the scheme weights in performing the construction cost dimension based on the context flag sequence using a hybrid expert model. The second model weights for optimizing the task and the third model weights for optimizing the scheme in the dimension of construction efficiency are determined. Based on the first model weights, the second model weights, and the third model weights, the first target neural network model required for optimizing the scheme in the dimension of construction safety, the second target neural network model required for optimizing the scheme in the dimension of construction cost, and the third target neural network model required for optimizing the scheme in the dimension of construction efficiency are determined from multiple expert neural network models. The first target feature is input into the first target neural network model, the second target neural network model, and the third target neural network model respectively to obtain the first prediction result in the dimension of construction safety, the second prediction result in the dimension of construction cost, and the third prediction result in the dimension of construction efficiency. Based on the first prediction result, the second prediction result, and the third prediction result, the target steel column connection scheme is obtained.

[0014] According to one aspect of this disclosure, a dynamic optimization device for steel column connection schemes is provided, comprising: a real-time construction data acquisition module, used to receive real-time construction data corresponding to a target steel frame structure sent by a data acquisition terminal; the real-time construction data includes at least one of the following: first strain data of the steel column butt joint connecting lug plate of the steel column to be installed, second strain data of the bolt associated with the steel column butt joint connecting lug plate, steel column inclination angle data and steel column displacement data of the steel column to be installed, and current construction environment data; and a lug plate stress distribution characteristic determination module, used to determine the lug plate stress distribution characteristics of the steel column butt joint connecting lug plate based on a preset stress value analysis model and the real-time construction data, and The first analysis result is obtained by analyzing the correlation between the steel column to be installed and the steel column butt joint connecting lug plate based on the stress distribution characteristics of the lug plate; the second analysis result is obtained by analyzing the stress change law and safety of the steel column butt joint connecting lug plate during construction based on the stress distribution characteristics of the lug plate, and the target analysis result is obtained based on the first and second analysis results; the third analysis result is obtained by dynamically optimizing the original steel column connection scheme with the target steel frame structure based on the target analysis result, and the target steel column connection scheme is obtained by connecting the steel column to be installed in the target steel frame structure based on the target steel column connection scheme.

[0015] This disclosure provides a dynamic optimization method for steel column connection schemes. On one hand, it receives real-time construction data corresponding to the target steel frame structure from a data acquisition terminal. Based on a preset stress analysis model and the real-time construction data, it determines the stress distribution characteristics of the connecting lugs of the steel columns. Based on these stress distribution characteristics, it analyzes the correlation between the steel column to be installed and the connecting lugs to obtain a first analysis result. Then, based on the stress distribution characteristics, it analyzes the stress change law and safety of the connecting lugs during construction to obtain a second analysis result. Based on the first and second analysis results, it obtains a target analysis result. Finally, based on the target analysis result, it dynamically optimizes the original steel column connection scheme with the target steel frame structure to obtain a target steel column connection scheme. Based on the target steel column connection scheme, it connects the steel columns to be installed in the target steel frame structure. This achieves automatic generation of steel column connection schemes, thus solving the problem of low generation efficiency in existing technologies. On the other hand, since the steel column connection scheme can be dynamically adjusted, it solves the problem of the inability to dynamically adjust in existing technologies, improving the accuracy of the obtained target steel column connection scheme.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0018] Figure 1 The flowchart schematically illustrates a dynamic optimization method for a steel column connection scheme according to an exemplary embodiment of the present disclosure.

[0019] Figure 2 The illustration shows a scenario example diagram of a target steel frame structure including multiple steel columns to be installed according to an exemplary embodiment of the present disclosure.

[0020] Figure 3 The illustration schematically shows an example diagram of a foil strain gauge and a strain gauge axial force gauge associated with a steel column to be installed, according to an example embodiment of the present disclosure.

[0021] Figure 4 The diagram schematically illustrates a specific structural example of a preset stress value analysis model according to an exemplary embodiment of the present disclosure.

[0022] Figure 5 The diagram schematically illustrates a specific structural example of a first rotational feature encoding module in a preset stress value analysis model according to an example embodiment of the present disclosure.

[0023] Figure 6 The illustration schematically depicts a scenario example of an optimized steel column to be installed according to an exemplary embodiment of the present disclosure.

[0024] Figure 7 The diagram schematically illustrates a scenario example of an original steel column connection scheme requiring optimization according to an exemplary embodiment of the present disclosure.

[0025] Figure 8 The illustration shows a scenario example of a target steel column connection scheme obtained by optimizing an original steel column connection scheme according to an example embodiment of the present disclosure.

[0026] Figure 9 The diagram schematically illustrates a structural example of a dynamic optimization device for a steel column connection scheme according to an exemplary embodiment of the present disclosure.

[0027] Figure 10 The diagram schematically illustrates an example structure of an electronic device for implementing a dynamic optimization method for steel column connection schemes according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0029] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0030] This exemplary embodiment first provides a dynamic optimization method for steel column connection schemes. This method can run on terminal devices, servers, server clusters, or cloud servers, etc. Of course, those skilled in the art can also run the method disclosed herein on other platforms as needed, and this exemplary embodiment does not impose any special limitations on this. Specifically, refer to... Figure 1 As shown, the dynamic optimization method for steel column connection schemes may include the following steps: Step S110. Receive the current real-time construction data corresponding to the target steel frame structure sent by the data acquisition terminal; the current real-time construction data includes at least one of the following: the first strain data of the steel column butt joint connecting lug plate to be installed, the second strain data of the bolt associated with the steel column butt joint connecting lug plate, the steel column inclination angle data and steel column displacement data of the steel column to be installed, and the current construction environment data; Step S120. Based on the preset stress value analysis model and the current real-time construction data, determine the stress distribution characteristics of the lug plate of the steel column butt connection, and analyze the correlation between the steel column to be installed and the steel column butt connection lug plate according to the stress distribution characteristics of the lug plate to obtain the first analysis result. Step S130. Analyze the stress change law and safety of the steel column butt joint ear plate during construction based on the stress distribution characteristics of the ear plate to obtain the second analysis result, and obtain the target analysis result based on the first analysis result and the second analysis result; Step S140. Based on the target analysis results, dynamically optimize the original steel column connection scheme with the target steel frame structure to obtain the target steel column connection scheme, and connect the steel columns to be installed in the target steel frame structure based on the target steel column connection scheme.

[0031] In the aforementioned dynamic optimization method for steel column connection schemes, on the one hand, the method receives real-time construction data corresponding to the target steel frame structure from a data acquisition terminal; then, based on a preset stress value analysis model and the real-time construction data, it determines the stress distribution characteristics of the lugs of the steel column butt joint connection plates, and analyzes the correlation between the steel column to be installed and the steel column butt joint connection plates based on the stress distribution characteristics of the lugs to obtain a first analysis result; then, based on the stress distribution characteristics of the lugs, it analyzes the stress change law and safety of the steel column butt joint connection plates during construction to obtain a second analysis result, and obtains a target analysis result based on the first and second analysis results; finally, based on the target analysis result, it dynamically optimizes the original steel column connection scheme with the target steel frame structure to obtain a target steel column connection scheme, and connects the steel columns to be installed in the target steel frame structure based on the target steel column connection scheme; this achieves automatic generation of steel column connection schemes, thereby solving the problem of low generation efficiency of steel column connection schemes in the prior art; on the other hand, since the steel column connection scheme can be dynamically adjusted, it solves the problem of the inability to dynamically adjust in the prior art, and improves the accuracy of the obtained target steel column connection scheme.

[0032] The following will further explain and illustrate the dynamic optimization method for the steel column connection scheme described in the exemplary embodiments of this disclosure, with reference to the accompanying drawings.

[0033] First, the application scenarios and technical implementation principles of the exemplary embodiments of this disclosure will be explained and described. Specifically, the dynamic optimization method for steel column connection schemes described in the exemplary embodiments of this disclosure can be applied to steel column connection scenarios in steel frame structures. During the steel column connection process, steel column butt joint connection lugs are required. Specifically, the steel column butt joint connection lugs described here are auxiliary components used for temporary positioning, hoisting and fixing, and verticality correction during steel structure construction. In practical applications, the steel column butt joint connection lugs are usually welded symmetrically to the flanges or webs of the upper and lower steel column butt joint ends. Simultaneously, through the temporary splicing of the steel column butt joint connection lugs with high-strength bolts, final welding or permanent connection can be performed after ensuring splicing accuracy. It should also be noted that since the steel column butt joint connection lugs do not participate in the structural stress design, they are temporary construction components, mainly used for quick hole alignment, straightening, and fixing of the upper and lower steel columns. In actual operation, the steel column butt joint connection lugs are removed after the permanent weld is completed.

[0034] Secondly, for Figure 1 The dynamic optimization method for the steel column connection scheme shown will be further explained and illustrated. Specifically: In step S110, the current real-time construction data corresponding to the target steel frame structure sent by the data acquisition terminal is received; the current real-time construction data includes at least one of the following: the first strain data of the steel column butt joint connecting lug of the steel column to be installed, the second strain data of the bolt associated with the steel column butt joint connecting lug, the steel column inclination angle data and steel column displacement data of the steel column to be installed, and the current construction environment data.

[0035] Specifically, the first strain data recorded here includes the shear core area strain data between the lug bolt holes corresponding to the lug connecting to the steel column and the strain data at the weld toe; the shear core area strain data between the lug bolt holes recorded here is collected based on the first foil strain gauge installed in the shear core area between the lug bolt holes, and the weld toe strain data is collected based on the second foil strain gauge installed at the weld toe; further, the second strain data recorded here is collected based on the strain gauge installed on the bolt; the steel column inclination angle data is collected based on the inclination sensor installed at the top of the steel column to be installed, and the steel column displacement data is collected based on the wire displacement gauge installed at the bottom of the steel column to be installed; further still, the current construction environment data recorded here includes the current temperature data and the current wind force data, the current temperature data is collected based on the temperature sensor, and the current wind force data is collected based on the wind force sensor.

[0036] The following will further explain and illustrate the specific process for determining the current real-time construction data. Specifically, in practical application, firstly, a first foil strain gauge can be attached to the shear core area between the bolt holes of the connecting ear plate of the steel column to be installed. Simultaneously, a second foil strain gauge is attached to the weld toe of the connecting ear plate of the steel column to be installed. Based on this, strain gauges are installed on the corresponding bolts, and tilt sensors are placed at the top of the steel column to be installed, while wire displacement gauges are installed at the bottom of the column. Furthermore, temperature compensation measuring points (i.e., temperature sensors) and wind sensors are simultaneously set up to eliminate environmental interference. The temperature and wind sensors can be installed in non-stressed areas of the ear plate or in other locations; this example does not impose any special restrictions. It should be noted that a target steel frame structure can include multiple steel columns to be installed (see the specific scenario example diagram). Figure 2 As shown in the diagram, two steel columns to be installed can be temporarily fixed together using steel column butt joint connecting lugs; furthermore, each steel column butt joint connecting lug is equipped with a first foil strain gauge, a second foil strain gauge, and multiple strain gauge axial force gauges (see the specific scenario example diagram for reference). Figure 3 (As shown); the number of axial force gauges can be determined based on the number of bolts, and this example does not impose any special restrictions on this. Meanwhile, the specific number of foil strain gauges required for each different stress concentration area (i.e., the critical area) (i.e., the number of the first foil strain gauge and the number of the second foil strain gauge) can be set according to actual needs, and this example does not impose any special restrictions on this.

[0037] In one example embodiment, during the deployment of various sensors or measuring devices, the key monitoring areas can be clearly identified based on the ear plate structure design drawings: the shear core area between the ear plate bolt holes and the weld toe. Based on this, the strain gauge bonding positions are precisely marked using a marker pen; the temporary bolt installation positions are determined to mark the axial force gauge installation points; the tilt sensor installation point is marked at the center of the top of the steel column, and the corresponding wire displacement meter installation point is marked at the bottom of the steel column. Simultaneously, temperature compensation measuring points and wind force sensors are marked in the non-stressed areas of the ear plate (no stress, no welds, and temperature consistent with the monitoring area) to ensure that the compensation measuring points and monitoring measuring points are under the same environmental conditions, effectively eliminating temperature interference. Furthermore, during the specific deployment process, all marked measuring point surfaces need to be ground, degreased, and derusted until the surface is free of oxide layers, oil stains, and impurities, with the roughness controlled within a suitable range (to ensure the strain gauges are firmly bonded). The surface is then wiped with anhydrous ethanol, and the measuring point positions are remarked after the surface is completely dry to avoid point displacement during the grinding process.

[0038] In one example embodiment, during the acquisition of real-time construction data, a communication connection can first be established between each sensor or measuring device and the wireless strain gauge. This communication connection can be implemented using the Internet of Things (IoT). Based on this, if real-time construction data needs to be collected, corresponding instructions can be sent to the wireless strain gauge, which then forwards these instructions to the sensors or measuring devices. Once the wireless strain gauge receives the data from the sensors or measuring devices, it can feed the obtained real-time construction data back to the terminal device or server. It should be noted that the data acquisition frequency can be set according to actual needs; for example, sampling can be performed every 5 minutes during normal periods, and increased to every 10 seconds during periods of gusts or hoisting. In practical applications, the acquisition frequency can be set according to actual needs; this example does not impose any special restrictions on this.

[0039] In step S120, based on the preset stress value analysis model and the current real-time construction data, the stress distribution characteristics of the lug plate of the steel column butt connection are determined, and the correlation between the steel column to be installed and the steel column butt connection lug plate is analyzed based on the stress distribution characteristics of the lug plate to obtain the first analysis result.

[0040] In this exemplary embodiment, firstly, based on a preset stress value analysis model and the current real-time construction data, the stress distribution characteristics of the lug plate of the steel column butt connection are determined, including: determining a first stress value based on the elastic modulus of the lug plate and the strain data of the shear core area between the lug plate bolt holes, and determining a second stress value based on the elastic modulus of the lug plate and the strain data at the weld toe; determining the actual axial force of the bolt based on the second strain data, and obtaining the original attribute data of the target steel frame structure; the original attribute data includes at least one of the following: the first weight of the steel column to be installed, the second weight of the installed steel beam / secondary component, the third weight of the construction personnel and construction equipment, and the load of the hoisting equipment; constructing an input feature sequence based on the original attribute data, the first stress value, the second stress value, the actual axial force of the bolt, the steel column inclination angle data, the steel column displacement data, the current temperature data, and the current wind force data, and inputting the input feature sequence into the preset stress value analysis model to obtain the stress distribution characteristics of the lug plate of the steel column butt connection.

[0041] In this embodiment of the present disclosure, the specific calculation process of the first stress value can be achieved as follows: the first strain in the strain data of the shear core area between the lug bolt holes. The specific calculation process for the elastic modulus of the ear plate and the second stress value can be achieved as follows: strain data at the weld toe. Elastic modulus of the ear plate.

[0042] In an exemplary embodiment, the input feature sequence is input into a preset stress value analysis model to obtain the stress distribution characteristics of the lug plate of the steel column butt joint connection. This can be achieved as follows: The input feature sequence is embedded using a first embedding layer to obtain a first embedding vector; the input feature sequence is then encoded using a first position encoding module to obtain a first position vector; the first embedding vector and the first position vector are superimposed to obtain a first input vector; the first input vector is then encoded using a first rotation feature encoding module to obtain a first encoding result; the first encoding result is decoded using a first feature decoding module to obtain a first encoding matrix; the first encoding matrix is ​​then transformed using a first linear transformation layer to obtain a first logical matrix; and the first logical matrix is ​​mapped using a first classification layer to obtain the stress distribution characteristics of the lug plate of the steel column butt joint connection. The stress distribution characteristics include a stress concentration region, the actual stress values ​​at each stress monitoring point within the stress concentration region, and the maximum, minimum, average stress values, and stress gradient distribution of the stress concentration region. A specific structural example diagram of the preset stress value analysis model can be found in the following diagram. Figure 4 As shown.

[0043] In an exemplary embodiment, the encoding of the first input vector based on the first rotation feature encoding module to obtain the first encoding result can be achieved as follows: A first attention mechanism is calculated based on the first multi-head self-attention module for the first input vector, and residual connections and normalization are performed on the first attention mechanism based on the first residual connection and normalization module to obtain a first normalization result; the first attention mechanism is used to interact with the first stress value, the second stress value, the original attribute data, and other data in the current real-time construction data besides the first and second stress values; the first normalization result is linearized based on the first feedforward neural network to obtain a first linearization result, and residual connections and normalization are performed on the first linearization result based on the second residual connection and normalization module to obtain the first encoding result; a specific structural example diagram of the first rotation feature encoding module described herein can be found in the following diagram. Figure 5 As shown.

[0044] In one example embodiment, the first attention mechanism based on the first multi-head self-attention module to calculate the first input vector can be implemented as follows: The first input vector is linearly fused to obtain a first query vector, a first key vector, and a first value vector; the relative angles of the first query vector and the first key vector are adjusted based on a preset first rotation matrix to obtain adjusted first query vectors and adjusted first key vectors; the first outer product vector of the adjusted first query vector and the adjusted first key vector is calculated to obtain a first similarity between the adjusted first query vector and the adjusted first key vector; the first similarity is normalized to obtain a first weight matrix; and the second outer product vector of the first weight matrix and the first value vector is calculated to obtain the first attention mechanism.

[0045] It should also be noted that, because the determination of the ear plate stress distribution characteristics considered not only the original construction data (i.e., the original attribute data) but also the current real-time construction data, the accuracy of the obtained ear plate stress distribution characteristics was further improved. Furthermore, the determination of the ear plate stress distribution characteristics involved in-depth interaction between the first and second stress values, as well as other data in the original attribute data and the current real-time construction data (excluding the first and second stress values), further enhancing the accuracy of the obtained ear plate stress distribution characteristics.

[0046] Secondly, based on the stress distribution characteristics of the lugs, the correlation between the steel column to be installed and the lugs connecting the steel column is analyzed to obtain a first analysis result. Specifically, this can be achieved as follows: based on the steel column inclination angle data, steel column displacement data, and lug stress distribution characteristics of the steel column to be installed, the correspondence between the steel column deformation and the change in stress of the lugs connecting the steel column is analyzed to obtain a first analysis result. The first analysis result is used to evaluate the impact of the structural deformation of the steel column to be installed on the long-term stress safety of the lugs connecting the steel column. In other words, in practical applications, based on the stress distribution characteristics of the lugs, the inherent correlation between the deformation of the steel column during installation and the stress of the lugs can be analyzed by combining the tilt angle data of the steel column collected by the tilt sensor and the displacement data of the steel column collected by the wire displacement gauge. For example, it can be determined whether tilting and / or displacement of the steel column during installation will lead to uneven stress on the lugs connecting the steel column, thereby causing local stress concentration. For another example, the correspondence between the deformation of the steel column and the change in stress of the lugs can be quantitatively analyzed to assess the impact of structural deformation on the long-term stress safety of the lugs. In the actual optimization process, if deformation leads to abnormal stress in the lugs, targeted adjustment suggestions should be proposed based on the cause of the deformation.

[0047] In this embodiment of the disclosure, the specific implementation process of correlation analysis can be based on a preset correlation analysis model; specifically, the correlation analysis model described herein can be a model implemented based on a graph convolutional neural network or a model implemented by BERT, and this example does not impose any special restrictions on it.

[0048] In step S130, the stress change law and safety of the steel column butt joint connection ear plate during construction are analyzed according to the stress distribution characteristics of the ear plate to obtain the second analysis result, and the target analysis result is obtained according to the first analysis result and the second analysis result.

[0049] In this exemplary embodiment, firstly, the stress variation law and safety of the steel column butt joint connecting lug plate during construction are analyzed based on the lug plate stress distribution characteristics to obtain a second analysis result. Specifically, this can be achieved as follows: extracting the stress concentration area and the actual stress value of each stress monitoring point in the stress concentration area from the lug plate stress distribution characteristics, and obtaining the expected stress value of the stress monitoring point; calculating the first ratio between the actual stress value and the expected stress value of the stress monitoring point, and obtaining the safety analysis result of the steel column butt joint connecting lug plate during construction based on the first ratio; determining the working condition category of the lug plate stress distribution characteristics based on the current construction environment data, and determining the stress characteristics of the steel column butt joint connecting lug plate under different working conditions based on the working condition category and the lug plate stress distribution characteristics to obtain the stress variation law analysis result; generating the second analysis result based on the safety analysis result and the stress variation law analysis result; the second analysis result is used to evaluate the safety hazards of the steel column butt joint connecting lug plate during construction and the degree of influence of special working conditions on the steel column butt joint connecting lug plate.

[0050] In this embodiment of the disclosure, during the process of determining the safety analysis results, the actual stress values ​​of each stress monitoring point included in the stress concentration area can be compared one by one with the expected stress values ​​specified in the design drawings (which can also be understood as the allowable stress values), and the first ratio of the actual stress to the allowable stress can be calculated. Based on this, it is determined whether the stress of each measuring point is within the allowable range (a ratio ≤ 1 is considered qualified). At the same time, for measuring points that exceed the allowable range, their locations, corresponding working conditions, and stress values ​​are marked to preliminarily determine whether there are any safety hazards in the stress on the area. Meanwhile, the data is checked for abnormalities (such as whether the stress data is distorted due to equipment failure) to ensure the reliability of the comparison results in order to obtain the safety analysis results.

[0051] In this embodiment of the disclosure, in determining the stress variation law analysis results, it is first necessary to determine the corresponding working condition category (e.g., gust working condition or normal working condition); then, determine the stress variation trend of the concentrated stress area under different working conditions; at the same time, in the process of determining the stress variation trend, stress-time variation curves can be plotted, focusing on analyzing the degree of influence of gust working conditions on the stress of the ear plate; for example, under gust working conditions, the correlation between wind speed change and stress peak can be focused on; under normal working conditions, the stress fluctuation of different stages of hoisting operations (lifting, translation, and positioning) can be analyzed; the specific time of stress peak occurrence, corresponding working condition details (such as gust wind speed, hoisting position) and peak position under each working condition can be found, the stress characteristics of the ear plate under different working conditions can be clarified, and it can be determined whether special working conditions will lead to a significant increase in ear plate stress in order to obtain the stress variation law analysis results.

[0052] Secondly, the target analysis results are determined based on the results of the first and second analyses. It should be noted that the obtained target sub-analysis results not only include the correlation between the structural deformation of the steel column to be installed and the stress on the ear plate, but also consider the safety and stress variation patterns of each concentrated stress area. This further improves the comprehensiveness and accuracy of the obtained analysis results, laying a solid foundation for the dynamic optimization of the steel column connection scheme.

[0053] In step S140, the original steel column connection scheme with the target steel frame structure is dynamically optimized according to the target analysis results to obtain the target steel column connection scheme, and the steel columns to be installed in the target steel frame structure are connected based on the target steel column connection scheme.

[0054] In this exemplary embodiment, firstly, the original steel column connection scheme with the target steel frame structure is dynamically optimized based on the target analysis results to obtain the target steel column connection scheme. Specifically, this can be achieved as follows: obtaining the first weight of the steel column to be installed associated with the target steel frame structure, the second weight of the installed steel beam / secondary component, the third weight of construction personnel and equipment, the hoisting equipment load, and the maximum wind load; generating the original steel column connection scheme with the target steel frame structure based on the first weight, second weight, third weight, hoisting equipment load, and maximum wind load; calling a preset content generation model and inputting the original steel column connection scheme and the target analysis results into the preset content generation model to dynamically optimize the original steel column connection scheme to obtain the target steel column connection scheme. Specifically, in practical applications, the generation process of the original steel column connection scheme can rely on a large content generation model. For example, the first weight of the steel column to be installed associated with the target steel frame structure, the second weight of the installed steel beams / secondary components, the third weight of construction personnel and equipment, the load of the hoisting equipment, the maximum wind load, and the project drawings associated with the target steel frame structure can be input into the large content generation model to obtain the corresponding original steel column connection scheme. Specifically, the original steel column connection scheme may include, but is not limited to, the connection schemes required for the steel columns to be installed with different codes. For example, the required number, size, and material of the steel column butt joint connection lugs, as well as the required number, size, and material of the bolts, can also be included. Of course, other parameters may also be included, and this example does not impose any special restrictions on them. Furthermore, in the process of dynamic optimization, it is first necessary to determine the steel column to be installed that needs to be optimized, then locate the corresponding scheme, and then optimize it. For specific scenario examples, please refer to the following diagram. Figure 6 as well as Figure 7 As shown; where, Figure 6 This is an example diagram of a scenario where steel columns to be installed require optimization. Figure 7 This is a scenario example diagram showing the original steel column connection scheme for a steel column to be installed that needs optimization.

[0055] In an exemplary embodiment, the original steel column connection scheme and the target analysis result are input into the preset content generation model to dynamically optimize the original steel column connection scheme to obtain the target steel column connection scheme. This can be achieved as follows: Basic information to be predicted is generated based on the original steel column connection scheme and the target analysis result, and context information to be predicted is generated based on preset parameter prompts; the basic information to be predicted is embedded and mapped using an embedding mapping layer to obtain a first basic feature, and the context information to be predicted is embedded and mapped to obtain a context flag sequence; the first basic feature and the context flag sequence are encoded using an encoding layer to obtain a first target feature; based on the context flag sequence, a hybrid expert model determines the first model weight of multiple expert neural network models for performing the scheme optimization task in the construction safety dimension, and the second model weight of multiple expert neural network models for performing the scheme optimization task in the construction cost dimension. The model weights and the third model weights for optimizing the scheme in the construction efficiency dimension are defined. Based on the first, second, and third model weights, a first target neural network model, a second target neural network model, and a third target neural network model are determined from multiple expert neural network models for optimizing the scheme in the construction safety dimension, the construction cost dimension, and the construction efficiency dimension. The first target features are input into the first, second, and third target neural network models respectively to obtain a first prediction result in the construction safety dimension, a second prediction result in the construction cost dimension, and a third prediction result in the construction efficiency dimension. Based on the first, second, and third prediction results, the target steel column connection scheme is obtained. The obtained target steel column connection scheme can be referenced. Figure 8 As shown.

[0056] It should also be noted that during the dynamic optimization of the steel column connection scheme, it is possible to determine whether to suspend subsequent construction or add temporary supports and other emergency measures as needed. In practical applications, adaptive optimization can be performed according to actual needs, and this example does not impose any special restrictions on this.

[0057] Thus, the dynamic optimization method for steel column connection schemes described in the exemplary embodiments of this disclosure has been fully implemented. The following will further explain and illustrate the dynamic optimization method for steel column connection schemes described in the exemplary embodiments of this disclosure with reference to specific exemplary embodiments.

[0058] Specifically, taking the steel frame structure of a warehouse in a certain project as an example, the building dimensions are 134.4m. 49.4m, building height 18.8m~20.45m, steel frame column spacing (digital axis spacing: 8.2m+11m+12m) 7+11m+8.2m, letter axis spacing: 8.3m+8.2m The steel column (4+8.3m) is divided into two sections for connection (section 1: -1.48m to 1.2m, section 2: 1.2m to 18.8m). The connection work is carried out on-site in two separate workflows. In the first stage, during the steel structure refinement, the most unfavorable temporary stress conditions are calculated for the steel column connection lugs. The design load of the lugs must include the combination of the steel column's self-weight + the self-weight of the installed steel beams / other structures + construction live load (i.e., hoisting equipment + construction personnel) + the maximum gust load. Under this premise, an original steel column connection scheme can be generated; the obtained original steel column connection scheme may include, but is not limited to: ① load adaptability index; specifically, the load combination that the lugs can withstand: column self-weight + steel beam self-weight / other structure self-weight + construction live load + Maximum gust load, under which there is no deformation or cracking; extreme wind load adaptability: can withstand gust loads of 1.1 times the basic wind pressure, with horizontal displacement of the steel column ≤ H / 500; secondly, calculate stability index; the weld connecting the ear plate and the column is free of defects such as cracks and slag inclusions, and the weld flaw detection pass rate is 100% (first-class welds need to pass ultrasonic testing); ② the length, width, thickness, connection form (single plate / double plate) of the installed ear plate, as well as the requirements for the connection weld and the specifications, size, and quantity of the temporary fixing bolts; among which, the geometric parameters of the ear plate The specifications are as follows: Ear plate thickness: ≥10mm (≥12mm for heavy steel columns), thickness deviation ≤±0.5mm; Weld parameters: double-sided fillet weld leg size ≥8mm (≥10mm for heavy steel columns), weld calculated length deviation ≤±5mm, weld reinforcement 0-3mm; Bolt configuration: 3 bolts for each of the upper and lower columns, bolt diameter ≥20mm (≥22mm for heavy steel columns), bolt hole diameter 2-4mm larger than the bolt, hole position deviation ≤±1mm; Material mechanical properties: Ear plate steel strength: Q355B or higher steel, yield strength fy ≥355MPa, tensile strength fu ≥470MPa; Welding material matching: welding electrode strength grade matches the base material (e.g., E50 series), weld tensile strength ≥90% of the base material strength; Temporary bolt performance: 4.8 grade or higher high-strength bolts, shear strength design value fbv ≥310MPa, tightening torque deviation ≤±5%.

[0059] Furthermore, in the actual construction process, firstly, stress monitoring of the connecting lugs is conducted. Specifically, the butt welds of steel columns are key force transmission parts in multi-story steel frame structures. Under the action of superstructure loads (vertical loads, horizontal loads, temperature stress, etc.), the welds are prone to stress concentration, fatigue damage, and other problems. Simultaneously, stress monitoring can monitor the stress distribution and variation patterns of the welds in real time, verifying the safety and reliability of the connection nodes, and providing data support for structural design optimization and construction quality control. Based on this, the steel column connection scheme can be dynamically optimized based on the monitored real-time construction data. Construction is then carried out according to the optimized steel column connecting lugs. After all connecting components within the segmented steel columns are installed to form a stable frame unit, correction and final node connection fixation are performed to verify the efficiency of steel structure installation and the pass rate of high-strength bolt perforation. Furthermore, during the steel column connection process based on the optimized steel column connection scheme, the deviation of the gap between the upper and lower columns after connection is ≤ ±2mm; the offset of the column cross-section centerline is ≤ 3mm; the fit gap between the ear plate and the connecting plate is ≤ 0.5mm (gap-free fit rate ≥ 90%); at the same time, the coaxiality deviation between the ear plate bolt hole and the connecting plate bolt hole is ≤ 1mm; the on-site hole expansion rate is ≤ 0 (ideal state), and the maximum does not exceed 3% (special working conditions).

[0060] Furthermore, based on actual construction results, it can be seen that the dynamic optimization method for the steel column connection scheme described in the exemplary embodiments of this disclosure, with the structural installation within each flow section (area 3000), 2 Comparing the time taken, the optimized steel column connection lug structure installation and alignment time is 10 days (compared to ≤14 days for traditional methods, reducing the construction period by approximately 30%). Simultaneously, the high-strength bolt perforation qualification rate is significantly improved: after the structure is installed and the steel column butt welds are performed, the high-strength bolt perforation qualification rate for the steel beams reaches over 96%. In other words, the dynamic optimization method for steel column connection schemes described in the exemplary embodiments of this disclosure not only greatly improves construction efficiency but also ensures that the resulting target steel frame structure possesses excellent performance.

[0061] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0062] This disclosure also provides an example embodiment of a dynamic optimization device for steel column connection schemes. Specifically, refer to... Figure 9 As shown, the dynamic optimization device for the steel column connection scheme may include a real-time construction data acquisition module 910, an ear plate stress distribution characteristic determination module 920, a target analysis result determination module 930, and a steel column connection scheme dynamic optimization module 940.

[0063] The current real-time construction data acquisition module 910 can be used to receive current real-time construction data corresponding to the target steel frame structure sent by the data acquisition terminal; the current real-time construction data includes at least one of the following: first strain data of the steel column butt joint connection lug plate to be installed, second strain data of the bolts associated with the steel column butt joint connection lug plate, steel column inclination angle data and steel column displacement data of the steel column to be installed, and current construction environment data; the lug plate stress distribution characteristic determination module 920 can be used to determine the lug plate stress distribution characteristics of the steel column butt joint connection lug plate based on the current real-time construction data according to a preset stress value analysis model, and to determine the steel column butt joint connection lug plate stress distribution characteristics of the target steel frame structure according to the lug plate stress distribution characteristics. The first analysis result is obtained by analyzing the correlation between the installed steel column and the steel column butt joint connecting lug. The target analysis result determination module 930 can be used to analyze the stress change law and safety of the steel column butt joint connecting lug during the construction process based on the stress distribution characteristics of the lug, and obtain the second analysis result. The target analysis result is obtained based on the first analysis result and the second analysis result. The steel column connection scheme dynamic optimization module 940 can be used to dynamically optimize the original steel column connection scheme with the target steel frame structure based on the target analysis result, obtain the target steel column connection scheme, and connect the steel columns to be installed in the target steel frame structure based on the target steel column connection scheme.

[0064] In an exemplary embodiment of this disclosure, the first strain data includes strain data of the shear core region between the lug bolt holes corresponding to the lug connecting to the steel column and strain data at the weld toe; the strain data of the shear core region between the lug bolt holes is collected based on a first foil strain gauge disposed in the shear core region between the lug bolt holes, and the strain data at the weld toe is collected based on a second foil strain gauge disposed at the weld toe; the second strain data is collected based on a strain gauge axial force meter disposed on the bolt; the steel column tilt angle data is collected based on a tilt sensor disposed at the top of the steel column to be installed, and the steel column displacement data is collected based on a wire displacement meter disposed at the bottom of the steel column to be installed; the current construction environment data includes current temperature data and current wind force data, the current temperature data is collected based on a temperature sensor, and the current wind force data is collected based on a wind force sensor.

[0065] In an exemplary embodiment of this disclosure, the stress distribution characteristics of the lug plate of the steel column butt connection are determined based on the current real-time construction data according to a preset stress value analysis model. This includes: determining a first stress value based on the elastic modulus of the lug plate and the strain data of the shear core area between the lug plate bolt holes; determining a second stress value based on the elastic modulus of the lug plate and the strain data at the weld toe; determining the actual axial force of the bolt based on the second strain data; and obtaining the original attribute data of the target steel frame structure. The original attribute data includes at least one of the following: the first weight of the steel column to be installed, the second weight of the installed steel beam / secondary component, the third weight of the construction personnel and construction equipment, and the load of the hoisting equipment; constructing an input feature sequence based on the original attribute data, the first stress value, the second stress value, the actual axial force of the bolt, the steel column inclination angle data, the steel column displacement data, the current temperature data, and the current wind force data; and inputting the input feature sequence into the preset stress value analysis model to obtain the stress distribution characteristics of the lug plate of the steel column butt connection.

[0066] In an exemplary embodiment of this disclosure, the input feature sequence is input into a preset stress value analysis model to obtain the stress distribution characteristics of the lug plate of the steel column butt joint connection. This includes: embedding the input feature sequence into a first embedding vector based on a first embedding layer, and encoding the input feature sequence into a first position vector based on a first position encoding module; superimposing the first embedding vector and the first position vector to obtain a first input vector, and encoding the first input vector into a first encoding result based on a first rotation feature encoding module; decoding the first encoding result into a first encoding matrix based on a first feature decoding module, and transforming the first encoding matrix into a first logical matrix based on a first linear transformation layer; and mapping the first logical matrix into the lug plate of the steel column butt joint connection to obtain the stress distribution characteristics of the lug plate. The stress distribution characteristics of the lug plate include a stress concentration region, the actual stress value of each stress monitoring point in the stress concentration region, and the maximum stress value, minimum stress value, average stress value, and stress gradient distribution of the stress concentration region.

[0067] In one exemplary embodiment of this disclosure, encoding a first input vector based on a first rotation feature encoding module to obtain a first encoding result includes: calculating a first attention mechanism for the first input vector based on a first multi-head self-attention module, and performing residual connection and normalization processing on the first attention mechanism based on a first residual connection and normalization module to obtain a first normalization processing result; the first attention mechanism is used to interact with the first stress value and the second stress value, as well as other data in the original attribute data and the current real-time construction data other than the first stress value and the second stress value; linearizing the first normalization processing result based on a first feedforward neural network to obtain a first linearization processing result, and performing residual connection and normalization processing on the first linearization processing result based on a second residual connection and normalization module to obtain the first encoding result.

[0068] In an exemplary embodiment of this disclosure, a first analysis result is obtained by analyzing the correlation between the steel column to be installed and the steel column butt joint connecting lug plate based on the lug plate stress distribution characteristics. This includes: analyzing the correspondence between the steel column deformation of the steel column to be installed and the lug plate stress change of the steel column butt joint connecting lug plate based on the steel column inclination angle data, steel column displacement data, and lug plate stress distribution characteristics to obtain the first analysis result; wherein, the first analysis result is used to evaluate the impact of the structural deformation of the steel column to be installed on the long-term stress safety of the lug plate of the steel column butt joint connecting lug plate.

[0069] In an exemplary embodiment of this disclosure, a second analysis result is obtained by analyzing the safety and stress variation law of the steel column butt joint connecting lug plate during construction based on the stress distribution characteristics of the lug plate. This includes: extracting the stress concentration region from the stress distribution characteristics of the lug plate and the actual stress value of each stress monitoring point within the stress concentration region, and obtaining the expected stress value of the stress monitoring point; calculating a first ratio between the actual stress value and the expected stress value of the stress monitoring point, and obtaining a safety analysis result of the steel column butt joint connecting lug plate during construction based on the first ratio; determining the working condition category of the stress distribution characteristics of the lug plate based on the current construction environment data, and determining the stress characteristics of the steel column butt joint connecting lug plate under different working conditions based on the working condition category and the stress distribution characteristics of the lug plate, to obtain a stress variation law analysis result; generating a second analysis result based on the safety analysis result and the stress variation law analysis result; the second analysis result is used to assess the safety hazards of the steel column butt joint connecting lug plate during construction and the degree of influence of special working conditions on the steel column butt joint connecting lug plate.

[0070] In one exemplary embodiment of this disclosure, the target steel column connection scheme is obtained by dynamically optimizing the original steel column connection scheme with the target steel frame structure based on the target analysis results. This includes: obtaining the first weight of the steel column to be installed associated with the target steel frame structure, the second weight of the installed steel beam / secondary component, the third weight of construction personnel and construction equipment, the load of hoisting equipment, and the maximum wind load; generating the original steel column connection scheme with the target steel frame structure based on the first weight, the second weight, the third weight, the load of hoisting equipment, and the maximum wind load; calling a preset content generation model and inputting the original steel column connection scheme and the target analysis results into the preset content generation model to dynamically optimize the original steel column connection scheme to obtain the target steel column connection scheme.

[0071] In one exemplary embodiment of this disclosure, the original steel column connection scheme and the target analysis result are input into the preset content generation model to dynamically optimize the original steel column connection scheme to obtain the target steel column connection scheme. This includes: generating basic information to be predicted based on the original steel column connection scheme and the target analysis result, and generating context information to be predicted based on preset parameter prompts; performing embedding mapping processing on the basic information to be predicted based on an embedding mapping layer to obtain a first basic feature, performing embedding mapping processing on the context information to be predicted to obtain a context flag sequence, and encoding the first basic feature and the context flag sequence based on an encoding layer to obtain a first target feature; and determining the first model weights of multiple expert neural network models in performing the scheme optimization task in the construction safety dimension and the scheme weights in performing the construction cost dimension based on the context flag sequence using a hybrid expert model. The second model weights for optimizing the task and the third model weights for optimizing the scheme in the dimension of construction efficiency are determined. Based on the first model weights, the second model weights, and the third model weights, the first target neural network model required for optimizing the scheme in the dimension of construction safety, the second target neural network model required for optimizing the scheme in the dimension of construction cost, and the third target neural network model required for optimizing the scheme in the dimension of construction efficiency are determined from multiple expert neural network models. The first target feature is input into the first target neural network model, the second target neural network model, and the third target neural network model respectively to obtain the first prediction result in the dimension of construction safety, the second prediction result in the dimension of construction cost, and the third prediction result in the dimension of construction efficiency. Based on the first prediction result, the second prediction result, and the third prediction result, the target steel column connection scheme is obtained.

[0072] The specific details of each module in the dynamic optimization device for the above-mentioned steel column connection scheme have been described in detail in the corresponding dynamic optimization method for the steel column connection scheme, so they will not be repeated here.

[0073] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0074] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0075] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0076] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0077] The following reference Figure 10 To describe an electronic device 1000 according to such an embodiment of the present disclosure. Figure 10 The electronic device 1000 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0078] like Figure 10 As shown, the electronic device 1000 is manifested in the form of a general-purpose computing device. The components of the electronic device 1000 may include, but are not limited to: at least one processing unit 1010, at least one storage unit 1020, a bus 1030 connecting different system components (including storage unit 1020 and processing unit 1010), and a display unit 1040.

[0079] The storage unit stores program code that can be executed by the processing unit 1010, causing the processing unit 1010 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 1010 can perform actions such as... Figure 1 Step S110: Receive current real-time construction data corresponding to the target steel frame structure sent by the data acquisition terminal; the current real-time construction data includes at least one of the following: first strain data of the steel column butt joint connecting lug plate to be installed, second strain data of the bolt associated with the steel column butt joint connecting lug plate, steel column inclination angle data and steel column displacement data of the steel column to be installed, and current construction environment data; Step S120: Based on a preset stress value analysis model and the current real-time construction data, determine the stress distribution characteristics of the steel column butt joint connecting lug plate, and adjust the stress distribution characteristics of the lug plate according to the current real-time construction data. Step S130: Analyze the correlation between the steel column to be installed and the steel column butt joint connecting lug to obtain the first analysis result; Step S140: Analyze the stress change law and safety of the steel column butt joint connecting lug during construction based on the stress distribution characteristics of the lug to obtain the second analysis result, and obtain the target analysis result based on the first analysis result and the second analysis result; Step S140: Dynamically optimize the original steel column connection scheme with the target steel frame structure based on the target analysis result to obtain the target steel column connection scheme, and connect the steel column to be installed in the target steel frame structure based on the target steel column connection scheme.

[0080] Storage unit 1020 may include readable media in the form of volatile storage units, such as random access memory (RAM) 10201 and / or cache memory 10202, and may further include read-only memory (ROM) 10203.

[0081] Storage unit 1020 may also include a program / utility 10204 having a set (at least one) program module 10205, such program module 10205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0082] Bus 1030 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the multiple bus structures.

[0083] Electronic device 1000 can also communicate with one or more external devices 1100 (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 1000, and / or any device that enables electronic device 1000 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1050. Furthermore, electronic device 1000 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1060. As shown, network adapter 1060 communicates with other modules of electronic device 1000 via bus 1030. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0084] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0085] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above.

[0086] A program product for implementing the above-described method according to embodiments of the present disclosure is described, which may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0087] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0088] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0089] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0090] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0091] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0092] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention described herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not invented by this disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A dynamic optimization method for steel column connection schemes, characterized in that, include: The system receives real-time construction data corresponding to the target steel frame structure sent by the data acquisition terminal. The real-time construction data includes at least one of the following: first strain data of the steel column butt joint connecting lugs to be installed, second strain data of the bolts associated with the steel column butt joint connecting lugs, steel column inclination angle data and steel column displacement data, and current construction environment data. Based on the preset stress value analysis model and the current real-time construction data, the stress distribution characteristics of the lug plate of the steel column butt connection are determined, and the correlation between the steel column to be installed and the steel column butt connection lug plate is analyzed based on the stress distribution characteristics of the lug plate to obtain the first analysis result. The stress distribution characteristics of the ear plate are used to analyze the stress change law and safety of the steel column butt joint ear plate during construction to obtain the second analysis result, and the target analysis result is obtained based on the first analysis result and the second analysis result. Based on the target analysis results, the original steel column connection scheme with the target steel frame structure is dynamically optimized to obtain the target steel column connection scheme, and the steel columns to be installed in the target steel frame structure are connected based on the target steel column connection scheme.

2. The dynamic optimization method for the steel column connection scheme according to claim 1, characterized in that, The first strain data includes the shear core area strain data between the bolt holes of the lugs corresponding to the lugs that connect to the steel column and the strain data at the weld toe of the weld. The strain data of the shear core area between the ear plate bolt holes is collected based on the first foil strain gauge set in the shear core area between the ear plate bolt holes, and the strain data of the weld toe is collected based on the second foil strain gauge set in the weld toe. The second strain data was collected based on a strain gauge installed on the bolt; The steel column tilt angle data is collected based on the tilt angle sensor installed at the top of the steel column to be installed, and the steel column displacement data is collected based on the wire displacement meter installed at the bottom of the steel column to be installed. The current construction environment data includes current temperature data and current wind speed data. The current temperature data is collected based on a temperature sensor, and the current wind speed data is collected based on a wind speed sensor.

3. The dynamic optimization method for the steel column connection scheme according to claim 2, characterized in that, Based on a preset stress value analysis model and the current real-time construction data, the stress distribution characteristics of the lugs in the steel column butt joint connection are determined, including: The first stress value is determined based on the elastic modulus of the lugs of the butt joint connection of the steel column and the strain data of the shear core area between the bolt holes of the lugs, and the second stress value is determined based on the elastic modulus of the lugs and the strain data at the weld toe of the weld. The actual axial force of the bolt is determined based on the second strain data, and the original attribute data of the target steel frame structure is obtained; the original attribute data includes at least one of the following: the first weight of the steel column to be installed, the second weight of the installed steel beam / sub-component, the third weight of the construction personnel and construction equipment, and the load of the hoisting equipment; Based on the original attribute data, the first stress value, the second stress value, the actual axial force of the bolt, the inclination angle data of the steel column, the displacement data of the steel column, the current temperature data, and the current wind force data, an input feature sequence is constructed, and the input feature sequence is input into a preset stress value analysis model to obtain the stress distribution characteristics of the lug plate of the steel column butt joint connection.

4. The dynamic optimization method for the steel column connection scheme according to claim 3, characterized in that, The input feature sequence is input into a preset stress value analysis model to obtain the stress distribution characteristics of the lug plate of the steel column butt joint, including: The first embedding vector is obtained by embedding the input feature sequence based on the first embedding layer, and the first position vector is obtained by encoding the input feature sequence based on the first position encoding module. The first embedding vector and the first position vector are superimposed to obtain the first input vector, and the first input vector is encoded based on the first rotation feature encoding module to obtain the first encoding result; The first encoding matrix is ​​obtained by decoding the first encoding result based on the first feature decoding module, and the first encoding matrix is ​​transformed based on the first linear transformation layer to obtain the first logical matrix. The stress distribution characteristics of the lug plate of the steel column butt joint are obtained by mapping the first logic matrix based on the first classification layer; the stress distribution characteristics of the lug plate include the stress concentration area, the actual stress value of each stress monitoring point in the stress concentration area, and the maximum stress value, minimum stress value, average stress value and stress gradient distribution of the stress concentration area.

5. The dynamic optimization method for the steel column connection scheme according to claim 4, characterized in that, The first encoding result is obtained by encoding the first input vector based on the first rotation feature encoding module, including: The first attention mechanism is calculated based on the first multi-head self-attention module, and the first attention mechanism is subjected to residual connection and normalization processing based on the first residual connection and normalization module to obtain the first normalization processing result; the first attention mechanism is used to interact with the first stress value and the second stress value, as well as the original attribute data and other data in the current real-time construction data other than the first stress value and the second stress value. The first normalization result is linearized based on the first feedforward neural network to obtain the first linearized result. The first linearized result is then subjected to residual connection and normalization based on the second residual connection and normalization module to obtain the first encoding result.

6. The dynamic optimization method for the steel column connection scheme according to claim 1, characterized in that, The correlation between the lugs connecting the steel column to be installed and the steel column is analyzed based on the stress distribution characteristics of the lugs to obtain the first analysis result, including: Based on the column inclination angle data, column displacement data, and ear plate stress distribution characteristics of the steel column to be installed, the first analysis result is obtained by analyzing the correspondence between the column deformation and the ear plate stress change of the steel column butt connection ear plate. The first analysis result is used to evaluate the impact of the structural deformation of the steel column to be installed on the long-term stress safety of the lug plate of the steel column butt joint connection.

7. The dynamic optimization method for the steel column connection scheme according to claim 1, characterized in that, The second analysis result is obtained by analyzing the safety and stress change law of the steel column butt joint ear plate during construction based on the stress distribution characteristics of the ear plate, including: Extract the stress concentration region from the stress distribution characteristics of the ear plate and the actual stress value of each stress monitoring point in the stress concentration region, and obtain the expected stress value of the stress monitoring point; Calculate the first ratio between the actual stress value and the expected stress value at the stress monitoring point, and obtain the safety analysis results of the steel column butt joint lug plate during construction based on the first ratio; Based on the current construction environment data, the working condition category of the stress distribution characteristics of the ear plate is determined, and based on the working condition category and the stress distribution characteristics of the ear plate, the stress characteristics of the steel column butt joint ear plate under different working conditions are determined, so as to obtain the stress change law analysis results. A second analysis result is generated based on the safety analysis results and the stress change law analysis results; the second analysis result is used to evaluate the safety hazards of the steel column butt joint connection lugs during construction and the degree of influence of special working conditions on the steel column butt joint connection lugs.

8. The dynamic optimization method for the steel column connection scheme according to claim 1, characterized in that, Based on the target analysis results, the original steel column connection scheme with the target steel frame structure is dynamically optimized to obtain the target steel column connection scheme, including: Obtain the first weight of the steel column to be installed associated with the target steel frame structure, the second weight of the installed steel beams / sub-components, the third weight of the construction personnel and equipment, the load of the hoisting equipment, and the maximum wind load; Based on the first weight, second weight, third weight, hoisting equipment load, and maximum wind load, an original steel column connection scheme with the target steel frame structure is generated; A preset content generation model is invoked, and the original steel column connection scheme and the target analysis results are input into the preset content generation model to dynamically optimize the original steel column connection scheme to obtain the target steel column connection scheme.

9. The dynamic optimization method for the steel column connection scheme according to claim 8, characterized in that, The original steel column connection scheme and the target analysis results are input into the preset content generation model to dynamically optimize the original steel column connection scheme to obtain the target steel column connection scheme, including: Based on the original steel column connection scheme and the target analysis results, generate basic information to be predicted, and generate context information to be predicted based on preset parameter prompts. The first basic feature is obtained by embedding and mapping the basic information to be predicted based on the embedding and mapping layer, the context information to be predicted is obtained by embedding and mapping the context information to be predicted, and the first target feature is obtained by encoding the first basic feature and the context flag sequence based on the encoding layer. Based on the contextual flag sequence, the first model weights of multiple expert neural network models are determined for the scheme optimization task in the construction safety dimension, the second model weights for the scheme optimization task in the construction cost dimension, and the third model weights for the scheme optimization task in the construction efficiency dimension. Based on the first model weight, the second model weight, and the third model weight, the first objective neural network model required for performing the scheme optimization task in the construction safety dimension, the second objective neural network model required for performing the scheme optimization task in the construction cost dimension, and the third objective neural network model required for performing the scheme optimization task in the construction efficiency dimension are determined from multiple expert neural network models. The first target feature is input into the first target neural network model, the second target neural network model, and the third target neural network model respectively to obtain the first prediction result in the dimension of construction safety, the second prediction result in the dimension of construction cost, and the third prediction result in the dimension of construction efficiency. Based on the first prediction result, the second prediction result, and the third prediction result, the target steel column connection scheme is obtained.

10. A dynamic optimization device for steel column connection schemes, characterized in that, include: The current real-time construction data acquisition module is used to receive the current real-time construction data corresponding to the target steel frame structure sent by the data acquisition terminal; the current real-time construction data includes at least one of the following: the first strain data of the steel column butt joint connecting lug plate to be installed, the second strain data of the bolt associated with the steel column butt joint connecting lug plate, the steel column inclination angle data and steel column displacement data of the steel column to be installed, and the current construction environment data; The ear plate stress distribution characteristic determination module is used to determine the ear plate stress distribution characteristics of the steel column butt connection ear plate based on the current real-time construction data according to the preset stress value analysis model, and to analyze the correlation between the steel column to be installed and the steel column butt connection ear plate according to the ear plate stress distribution characteristics to obtain the first analysis result; The target analysis result determination module is used to analyze the stress change law and safety of the steel column butt joint ear plate during construction based on the stress distribution characteristics of the ear plate to obtain a second analysis result, and to obtain the target analysis result based on the first analysis result and the second analysis result; The steel column connection scheme dynamic optimization module is used to dynamically optimize the original steel column connection scheme with the target steel frame structure according to the target analysis results to obtain the target steel column connection scheme, and connect the steel columns to be installed in the target steel frame structure based on the target steel column connection scheme.

Images