A method and system for active regulation of tower welding deformation

Abstract

The application provides a bridge tower welding deformation active regulation method and system, relates to the technical field of bridge tower welding, and comprises the following steps: based on a full-scale model of a bridge tower segment constructed in advance, finite element simulation is carried out on the welding process of the bridge tower segment under actual welding conditions, and a welding deformation simulation value of the bridge tower segment is obtained; the welding deformation simulation value is compared with a welding deformation measured value, and the full-scale model meeting the first preset accuracy requirement is determined according to the comparison result; based on the full-scale model meeting the first preset accuracy requirement, a welding deformation database under different welding conditions is established; and based on the welding deformation database under different welding conditions, the welding deformation under all the welding conditions is predicted. According to the application, deformation can be prevented before welding is completed, the welding efficiency is improved, and the regulation problem of the bridge tower segment welding deformation is effectively solved.

Description

Technical Field

[0001] This invention relates to the field of bridge tower welding technology, and more specifically, to a method and system for actively controlling welding deformation of bridge towers. Background Technology

[0002] In the construction of large-scale bridge structures (such as steel bridges), welding is one of the common methods for connecting various components. As an efficient and robust connection method, welding plays a crucial role in the safety and durability of bridge engineering. However, the extremely high local temperatures generated during welding can cause thermal expansion and cooling contraction of materials, resulting in residual stress and deformation in and around the welding area. If not controlled, this deformation may seriously affect the geometric accuracy of the structure and even the overall structural performance.

[0003] Existing methods for controlling welding deformation are mostly passive, such as using flame straightening and mechanical straightening after welding to reduce or correct the deformation caused by welding. Although these methods can improve the welding deformation problem to some extent, they are usually implemented after welding, which often requires expensive and time-consuming rework, so they are inefficient and cannot prevent the occurrence of deformation in advance. Summary of the Invention

[0004] The present invention aims to solve the problem that existing welding deformation control methods are inefficient and cannot prevent deformation in advance.

[0005] To address the above problems, in a first aspect, the present invention provides a method for actively controlling welding deformation of bridge towers, comprising:

[0006] Based on a pre-constructed full-scale model of a bridge tower segment, the welding process of the bridge tower segment is simulated using finite element methods under actual welding conditions to obtain the simulated welding deformation value of the bridge tower segment.

[0007] The simulated welding deformation value is compared with the measured welding deformation value, and the full-scale model that meets the first preset accuracy requirement is determined based on the comparison result.

[0008] Based on the full-scale model that meets the first preset accuracy requirements, a welding deformation database is established for different welding conditions.

[0009] Based on the welding deformation database under different welding conditions, the welding deformation amount under all welding conditions is predicted;

[0010] The welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement are selected, wherein the selected welding condition is used to guide the welding process of the bridge tower segment.

[0011] Optionally, comparing the simulated welding deformation value with the measured welding deformation value, and determining the full-scale model that meets the first preset accuracy requirement based on the comparison result includes:

[0012] Select multiple preset parts from the full-scale model;

[0013] Determine whether the difference between the simulated welding deformation value and the measured welding deformation value of each of the multiple preset parts is within the first deformation range, and obtain the determination result;

[0014] Based on the judgment result, the full-scale model that meets the first preset accuracy requirement is determined.

[0015] Optionally, determining the full-scale model that meets the first preset accuracy requirement based on the judgment result includes:

[0016] If the difference between the simulated welding deformation value and the measured welding deformation value of each of the multiple preset parts is within the first deformation range, then the full-scale model corresponding to the difference being within the first deformation range is taken as the full-scale model that meets the first preset accuracy requirement.

[0017] If the difference between the simulated welding deformation value and the measured welding deformation value of at least one of the multiple preset parts is not within the first deformation range, then the full-scale model is adjusted, and finite element simulation is performed again based on the actual welding conditions until the difference between the simulated welding deformation value and the measured welding deformation value of each of the multiple preset parts is within the first deformation range, and the adjusted full-scale model is taken as the full-scale model that meets the first preset accuracy requirement.

[0018] Optionally, establishing a welding deformation database under different welding conditions based on the full-scale model that meets the first preset accuracy requirement includes:

[0019] Establish multiple sets of the aforementioned welding conditions;

[0020] A preset number of welding conditions are randomly selected from multiple sets of welding conditions. Based on the selected multiple sets of welding conditions, the welding process of the full-scale model that meets the first preset accuracy requirement is simulated by finite element method to obtain the welding deformation data under multiple sets of welding conditions.

[0021] A welding deformation database is constructed based on the welding deformation data under multiple welding conditions.

[0022] Optionally, establishing multiple sets of welding conditions includes:

[0023] The welding conditions are freely arranged and combined according to different compositions to obtain multiple sets of welding conditions. The composition includes a starting point, welding sequence, and constraint conditions. The starting point includes welding from one end to the other, welding from both ends to the middle, and welding from the middle to both sides. The welding sequence includes welding one by one, welding simultaneously, partially simultaneous welding, and partially sequential welding. The constraint types include setting a code plate at the middle position of the middle transverse diaphragm of the bridge tower segment, setting the code plate at the middle position of the top transverse diaphragm and the bottom transverse diaphragm, and setting a process partition at the end of the bridge tower segment.

[0024] Optionally, before obtaining the simulated welding deformation value of the bridge tower segment by performing finite element simulation on the welding process of the bridge tower segment under actual welding conditions based on a pre-constructed full-scale model of the bridge tower segment, the method further includes:

[0025] Obtain point cloud data of the welded bridge tower segment, and determine the measured value of the welding deformation of the bridge tower segment based on the point cloud data.

[0026] Optionally, based on a pre-constructed full-scale model of a bridge tower segment, the welding process of the bridge tower segment is simulated using finite element methods under actual welding conditions to obtain simulated values ​​of the welding deformation of the bridge tower segment, including:

[0027] Obtain the full-scale model of the bridge tower segment;

[0028] Determine the material data of the bridge tower segment in the full-scale model, the material data including material type and material properties;

[0029] Under the actual welding conditions, a full-scale model of the selected material data was subjected to finite element simulation to obtain the simulated welding deformation value.

[0030] Optionally, predicting the welding deformation amount for all welding conditions based on a database of welding deformation under different welding conditions includes:

[0031] The data in the welding deformation database is used as initial data input into the deep learning model, which outputs the welding deformation amount under all the welding conditions.

[0032] Optionally, the screening of the welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement includes:

[0033] The welding deformation under all the welding conditions is judged in turn to determine whether the total deformation under each welding condition and the first deformation in the three coordinate axes of the full-scale model are both less than the corresponding preset deformation.

[0034] If not, then discard the welding condition and welding deformation corresponding to at least one of the total deformation and the first deformation in the three coordinate axis directions that is not less than the corresponding preset deformation.

[0035] If so, then the welding condition and welding deformation are retained if the total deformation and the first deformation in the three coordinate axes are both less than the corresponding preset deformation.

[0036] Among the selected welding conditions, the welding condition with the smallest second deformation in the vertical direction of the wall panel of the bridge tower segment is selected, and the selected welding condition and the welding deformation under that welding condition are output.

[0037] This invention utilizes a pre-constructed full-scale model of a bridge tower segment to perform finite element simulation of the welding process under actual welding conditions. The simulated welding deformation values ​​of the bridge tower segment are obtained, and these simulated values ​​are compared with measured welding deformation values. Based on the comparison results, a full-scale model meeting a first preset accuracy requirement is determined. This verifies the accuracy of the full-scale model and the reliability of the simulation process, providing an accurate three-dimensional model for subsequent simulations of different welding conditions. Furthermore, based on the full-scale model meeting the first preset accuracy requirement, a welding deformation database for different welding conditions is established, providing comprehensive data for predicting welding deformation under all welding conditions. The system provides data support; based on a database of welding deformation under different welding conditions, it predicts the welding deformation amount under all welding conditions, and filters out the welding deformation amount and corresponding welding conditions that meet the second preset accuracy requirements. The welding conditions corresponding to the welding deformation amount that meet the second preset accuracy requirements can be regarded as the better (or optimal) welding conditions that conform to the actual structure of the bridge tower segment. This can be used to guide the welding manufacturing process in the subsequent actual welding process of the bridge tower structure, ensuring optimal control of the welding process during welding. It eliminates the need for adjustment and rework after welding, thus improving welding efficiency and preventing deformation before welding is completed, effectively solving the problem of controlling welding deformation of bridge tower segments.

[0038] Secondly, the present invention also provides an active control system for welding deformation of bridge towers, comprising:

[0039] The simulation module is used to perform finite element simulation of the welding process of the bridge tower segment under actual welding conditions based on a pre-built full-scale model of the bridge tower segment, and obtain the simulated value of the welding deformation of the bridge tower segment.

[0040] The comparison and determination module is used to compare the simulated welding deformation value with the measured welding deformation value, and determine the full-scale model that meets the first preset accuracy requirement based on the comparison result.

[0041] The deformation database establishment module is used to establish a welding deformation database under different welding conditions based on the full-scale model that meets the first preset accuracy requirements.

[0042] The prediction module is used to predict the amount of welding deformation under all the welding conditions based on a database of welding deformation under different welding conditions.

[0043] The filtering module is used to filter the welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement.

[0044] Thirdly, the present invention provides an electronic device, including a memory and a processor;

[0045] The memory is used to store computer programs;

[0046] The processor is configured to implement the optical splitter integration test method as described in the first aspect when executing the computer program.

[0047] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the active control method for bridge tower welding deformation as described in the first aspect.

[0048] The bridge tower welding deformation active control system, electronic equipment, and computer-readable storage medium provided by this invention have the same beneficial effects as the bridge tower welding deformation active control method compared to the prior art, and will not be repeated here. Attached Figure Description

[0049] Figure 1 A flowchart illustrating an active control method for welding deformation of bridge towers according to an embodiment of the present invention is shown.

[0050] Figure 2 A schematic diagram illustrating the use of a 3D scanner to measure a rigid bridge tower segment in an embodiment of the present invention is shown;

[0051] Figure 3 This diagram illustrates the point cloud data processing procedure for bridge tower segments in an embodiment of the present invention.

[0052] Figure 4 A schematic diagram illustrating the establishment of a full-scale model of a bridge tower segment is shown in an embodiment of the present invention;

[0053] Figure 5 A schematic diagram of the welding condition at the weld start position in an embodiment of the present invention is shown;

[0054] Figure 6A schematic diagram of the welding process for the welding sequence of the weld seam in an embodiment of the present invention is shown;

[0055] Figure 7 A schematic diagram of the welding condition for weld constraint in an embodiment of the present invention is shown;

[0056] Figure 8 A schematic diagram showing the arrangement and combination of welding conditions in an embodiment of the present invention is shown;

[0057] Figure 9 A schematic diagram of the active control system for bridge tower welding deformation in an embodiment of the present invention is shown;

[0058] Figure 10 A schematic diagram of the structure of an electronic device according to an embodiment of the present invention is shown. Detailed Implementation

[0059] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0060] It should be noted that relational terms such as "first" and "second" in this invention are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0061] In the description of this specification, references to terms such as "embodiment," "one embodiment," and "one implementation" indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or implementation is included in at least one embodiment or illustrative implementation of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or implementation. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or implementations.

[0062] Reference Figure 1 As shown in the figure, this invention proposes an active control method for bridge tower welding deformation, which can be applied to bridge tower segments. Bridge tower segments are the constituent units of the bridge's main structure; through the assembly of bridge tower structures, the bridge's main structure can be formed, such as... Figure 4 , Figure 5 and Figure 7 All of them are bridge tower structures.

[0063] The active control method for welding deformation of bridge towers includes:

[0064] S100: Based on a pre-built full-scale model of a bridge tower segment, the welding process of the bridge tower segment is simulated using finite element methods under actual welding conditions to obtain the simulated welding deformation value of the bridge tower segment.

[0065] Specifically, the full-scale model is a 3D model of the bridge tower segment before welding. The full-scale model is a 3D model with a 1:1 scale to the solid structure. The actual welding conditions are the actual welding conditions during the welding process. Different welding conditions require different welding processes, such as the constraint of the welding plate applied to maintain the welding state, and the actual welding sequence from the middle to both sides. These are all manifestations of the welding conditions to ensure the quality and reliability of the welding. That is, the selection of welding process should be determined according to the specific welding conditions. Referring to the actual welding conditions in the bridge tower welding process, the welding process corresponding to the actual welding conditions is applied to the full-scale model to complete the finite element simulation. After the simulation is completed, the welding deformation simulation value of the bridge tower segment can be obtained through the measurement tool in the finite element simulation tool, or the welding deformation simulation value of the bridge tower segment can be directly generated.

[0066] S200: Compare the simulated welding deformation value with the measured welding deformation value, and determine the full-scale model that meets the first preset accuracy requirement based on the comparison result.

[0067] Specifically, the measured value of welding deformation can also be determined. The measured value of welding deformation is the data reflecting the structural deformation of the solid structure corresponding to the full-scale model after welding according to the actual welding conditions. The two are compared, and the full-scale model that meets the first preset accuracy requirement is determined. This involves the improvement of the setting position of the bridge tower structure. For example, the deformation of some set edges is extracted for comparative analysis. If the deformation is small, the model and simulation process are considered accurate. Otherwise, the model needs to be adjusted (such as adjusting the set edges) until it is accurate. The above can verify the accuracy of the full-scale model and the reliability of the simulation process (if the deviation is too large and obviously does not match the reality, it means that there is a problem with the simulation). It provides an accurate three-dimensional model for the simulation of different welding conditions in the future.

[0068] S300: Based on the full-scale model that meets the first preset accuracy requirements, establish a welding deformation database for different welding conditions.

[0069] Specifically, based on a validated and reliable full-scale model, a database of welding deformation of bridge tower segments under different welding conditions is established. The welding deformation database consists of welding deformation amounts under multiple welding conditions (not all welding conditions need to be listed), which can provide comprehensive data support for the prediction of welding deformation amounts under all the aforementioned welding conditions.

[0070] S400: Based on the welding deformation database under different welding conditions, predict the welding deformation amount under all welding conditions.

[0071] Specifically, the welding deformation database can be used as input data for the optimization algorithm. The optimization algorithm (such as deep learning algorithm) can be used for optimization learning to actively calculate the welding deformation amount under unlisted welding conditions. In this way, the welding deformation amount under all the welding conditions can be obtained. As mentioned above, welding conditions from the middle to both ends and welding with one constraint and in a certain order are listed. However, welding conditions from the middle to both ends and welding with at least two constraints and in a certain order are not listed. This step can actively calculate the welding deformation amount under the unlisted welding conditions.

[0072] S500: Select the welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement, wherein the selected welding condition is used to guide the welding process of the bridge tower segment.

[0073] Specifically, the welding deformation under all the aforementioned welding conditions is judged by setting a limit. Based on the limit of the deformation, the welding conditions with welding deformation within the specified range and their corresponding welding deformation are output. Based on this, the welding process of subsequent steel tower segments is further guided.

[0074] In practical application, this embodiment uses a pre-constructed full-scale model of a bridge tower segment to perform finite element simulation of the welding process under actual welding conditions. The simulated welding deformation values ​​of the bridge tower segment are obtained, and these simulated values ​​are compared with the measured welding deformation values. Based on the comparison results, a full-scale model meeting the first preset accuracy requirement is determined. This verifies the accuracy of the full-scale model and the reliability of the simulation process, providing an accurate three-dimensional model for subsequent simulations of different welding conditions. Furthermore, based on the full-scale model meeting the first preset accuracy requirement, welding models under different welding conditions are established. By connecting to the deformation database, comprehensive data support can be provided for predicting the welding deformation under all the aforementioned welding conditions. Based on the welding deformation database under different welding conditions, the welding deformation under all the aforementioned welding conditions is predicted, and the welding deformation and corresponding welding conditions that meet the second preset accuracy requirements are selected. The welding conditions corresponding to the welding deformation that meet the second preset accuracy requirements can be regarded as the better (or optimal) welding conditions that conform to the actual structure of the bridge tower segment. They can be used to guide the welding manufacturing process in the subsequent actual welding process of the bridge tower structure, and ensure the optimal control of the welding process during the welding process.

[0075] In summary, by selecting a superior (or optimal) welding condition, this invention effectively solves the problem of controlling welding deformation in bridge tower segments. It eliminates or reduces the need for post-weld flame straightening and mechanical straightening to correct welding deformation, thereby reducing the overall bridge tower manufacturing cost and shortening the manufacturing cycle. It also significantly improves the manufacturing efficiency and precision of bridge towers. In other words, this invention provides a more efficient solution for bridge tower welding, improving welding quality while also enhancing the economy and efficiency of the entire bridge tower manufacturing process.

[0076] like Figure 2 and Figure 3 As shown, in an optional embodiment of the present invention, before performing finite element simulation of the welding process of the bridge tower segment under actual welding conditions based on a pre-constructed full-scale model of the bridge tower segment to obtain the simulated value of the welding deformation of the bridge tower segment, the method further includes:

[0077] Obtain point cloud data of the welded bridge tower segment, and determine the measured value of the welding deformation of the bridge tower segment based on the point cloud data.

[0078] Point cloud data is a digital 3D representation of a physical object or space. It consists of millions of individual measurement points, and each measurement point in the point cloud data has an x, y, and z coordinate. Point clouds can be captured using two tools: laser scanners and photogrammetry. The following explanation uses a laser scanner as an example.

[0079] Specifically, based on the size information of the target object and its environment, a highly adaptable and precise 3D laser scanner is selected, and scanning stations are planned to fully cover the surface of the bridge tower segment. Simultaneously, reference markers or marker points are placed in the scanning area to facilitate data alignment and stitching later. The scanner settings are adjusted before scanning begins. After acquiring the segment's scan data, the point cloud data from each station is stitched together according to the marker points to obtain a point cloud data model of the bridge tower segment. This point cloud data is then further processed using point cloud software to obtain the actual spatial 3D model of the bridge tower segment.

[0080] Furthermore, based on the actual three-dimensional model in space, the end section of the three-dimensional model is compared with the end section of the theoretical model. At the same time, the overlap analysis of the three-dimensional model obtained by scanning and the theoretical three-dimensional model is performed to obtain the spatial measured value of the welding deformation of the bridge tower segment, that is, the measured value of welding deformation. This measured value generally includes the deformation component of each deformation position on the three-dimensional coordinate axis, as well as the total deformation, which is the vector sum of the deformation components.

[0081] As an optional embodiment of the present invention, the step of comparing the simulated welding deformation value with the measured welding deformation value, and determining the full-scale model that meets the first preset accuracy requirement based on the comparison result includes:

[0082] Select multiple preset parts from the full-scale model;

[0083] The preset location includes the area where the marked edges or corners are located.

[0084] Determine whether the difference between the simulated welding deformation value and the measured welding deformation value of each of the multiple preset parts is within the first deformation range, and obtain the determination result;

[0085] The simulated welding deformation value is compared with the measured welding deformation value, and the deformation amount of some edges is extracted for coincidence analysis. For example, if the difference between the two deformation amounts is within ±3mm, the model and simulation process are considered accurate; otherwise, the full-scale model needs to be adjusted until it is accurate.

[0086] Based on the judgment result, the full-scale model that meets the first preset accuracy requirement is determined. Optionally, determining the full-scale model that meets the first preset accuracy requirement based on the judgment result includes:

[0087] If the difference between the simulated welding deformation value and the measured welding deformation value of each of the multiple preset parts is within the first deformation range, then the full-scale model corresponding to the difference being within the first deformation range is taken as the full-scale model that meets the first preset accuracy requirement.

[0088] If the difference between the simulated welding deformation value and the measured welding deformation value of at least one of the multiple preset parts is not within the first deformation range, then the full-scale model is adjusted, and finite element simulation is performed again based on the actual welding conditions until the difference between the simulated welding deformation value and the measured welding deformation value of each of the multiple preset parts is within the first deformation range, and the adjusted full-scale model is taken as the full-scale model that meets the first preset accuracy requirement.

[0089] Specifically, identify the locations where the simulated welding deformation values ​​differ from the measured values. For locations with significant differences, analyze the reasons for the discrepancies in depth. Possible causes include edge conditions and welding parameters. Here, the main adjustment involves modifying the construction of edges or corners in the full-scale model. Due to the complexity of bridge tower structures, which involve assembly, transitions, and chamfering, adjustments to edges or corners in the preset locations can be considered to make the simulated welding deformation values ​​closer to the measured values. This may involve changing edge conditions, adjusting joint dimensions, and changing welding angles. After adjusting the edges or corners, perform finite element simulation again.

[0090] The above ensures that the full-scale model is closer to the actual situation, whether it is the original model or the adjusted model. Therefore, based on the full-scale model that meets the first preset accuracy requirement, it can provide an accurate model basis for finite element simulation under various welding conditions.

[0091] like Figure 4 As shown, in an optional embodiment of the present invention, the welding process of the bridge tower segment is simulated using finite element analysis based on a pre-constructed full-scale model of the bridge tower segment under actual welding conditions, and the simulated welding deformation values ​​of the bridge tower segment are obtained, including:

[0092] Obtain the full-scale model of the bridge tower segment;

[0093] For example, a full-scale model of the bridge tower segment can be created in finite element simulation software (such as the commercial finite element simulation software Abaqus), or an existing three-dimensional model of the bridge tower segment can be imported into the finite element simulation software. In other words, the present invention can be implemented by accessing the extended interface of the finite element simulation software.

[0094] The material data of the bridge tower segment in the full-scale model is determined, and the material data includes the material type and material properties.

[0095] Based on the type of material used in the bridge tower segment, such as steel, input the corresponding material properties, including elastic modulus, Poisson's ratio, shear modulus, tensile strength, yield strength, coefficient of thermal expansion, specific heat, and thermal conductivity.

[0096] Under the actual welding conditions, a full-scale model of the selected material data was subjected to finite element simulation to obtain the simulated welding deformation value.

[0097] Numerical simulations of the welding process are performed based on the actual welding start position, welding sequence, and constraint conditions to obtain simulated values ​​of welding deformation under the aforementioned determined working conditions.

[0098] For example, when the starting position is at the edge of the weldment, it may cause uneven distribution of welding heat, resulting in deformation in a specific direction; different welding sequences may cause welding deformation in different areas to affect each other and superimpose; and constraints may limit the deformation of the weldment in some directions, resulting in more significant deformation in other directions.

[0099] In summary, when implementing the above steps in practice, it is crucial to clarify the specific information of the actual welding conditions, including the materials used in welding, the geometry and dimensions of the weldment, the starting position of welding, the welding sequence, and various constraints present during the welding process. This information forms the basis for subsequent finite element simulation and numerical simulation. The determined actual welding conditions are applied to the constructed full-scale model, and the entire welding process is simulated using finite element analysis software. During the simulation, the weldment is discretized into many small elements, and the changes in parameters such as stress and strain of each element are calculated based on material properties and welding conditions. After a series of complex calculations and iterations, the simulated value of welding deformation is finally obtained. Finally, based on detailed information such as the starting position, welding sequence, and constraints of the actual welding, a more accurate numerical simulation of the welding process is performed. In this process, the influence of the starting position on the welding heat and stress distribution, the effect of the welding sequence on the accumulation of welding deformation, and the limitations of constraints on the direction and extent of weldment deformation must be considered. Through detailed numerical calculations and model analysis, simulated values ​​of welding deformation under the determined specific conditions are obtained.

[0100] The above simulations can reproduce the generation and development of welding deformation in the actual welding process as realistically as possible, providing a reliable basis for subsequent analysis and optimization.

[0101] Referring to the above embodiments, the present invention provides another embodiment for obtaining welding deformation data based on multiple working conditions.

[0102] like Figure 5 , Figure 6 and Figure 7 As shown, in an optional embodiment of the present invention, establishing a welding deformation database under different welding conditions based on the full-scale model that meets the first preset accuracy requirement includes:

[0103] Establish multiple sets of the aforementioned welding conditions;

[0104] A preset number of welding conditions are randomly selected from multiple sets of welding conditions. Based on the selected multiple sets of welding conditions, the welding process of the full-scale model that meets the first preset accuracy requirement is simulated by finite element method to obtain the welding deformation data under multiple sets of welding conditions.

[0105] Optionally, establishing multiple sets of welding conditions includes:

[0106] The welding conditions are freely arranged and combined according to different compositions to obtain multiple sets of welding conditions. The composition includes a starting point, welding sequence, and constraint conditions. The starting point includes welding from one end to the other, welding from both ends to the middle, and welding from the middle to both sides. The welding sequence includes welding one by one, welding simultaneously, partially simultaneous welding, and partially sequential welding. The constraint types include setting a code plate at the middle position of the middle transverse diaphragm of the bridge tower segment, setting the code plate at the middle position of the top transverse diaphragm and the bottom transverse diaphragm, and setting a process partition at the end of the bridge tower segment.

[0107] For example, for bridge tower segments, there are three types of starting points for welding: welding from one end of the weld to the other, welding from both ends to the middle, and welding from the middle to both sides. There are also eight types of welding sequences, namely... Figure 7 The numbers 1-8 in the diagram indicate the location of a vertical weld. A number inside the diagram indicates an inner weld, and a number outside indicates an outer weld. The numerical order indicates the welding sequence; if the numbers are the same, the welds are welded simultaneously. The constraint types include setting a code plate at the middle position of the middle transverse diaphragm of the bridge tower segment, setting the code plate at the middle position of the top and bottom transverse diaphragms, and setting a process partition plate at the end of the bridge tower segment.

[0108] like Figure 8 As shown, by arranging and combining the starting position (3 types), constraint conditions (5 types), and welding sequence (7 types), 3*5*7=105 welding conditions are obtained. Each group will be numbered from 1 to 105, representing the 105 combinations of constitutive conditions. Following a random number pattern, 15 combinations will be randomly selected to obtain 15 welding conditions.

[0109] When the distance between the transverse diaphragms of the bridge tower segments is large, that is, when the distance between the sections without diaphragms is long, the rigidity of the box plate and the rigidity of the bridge tower after assembly are small. In order to ensure the dimensional and positional accuracy requirements of the four plates of the box column during assembly and welding, process diaphragms need to be added. By providing a stable support surface, the mounting plate can effectively fix and position the welding workpiece, prevent it from deforming, displacing or twisting during the welding process, and help ensure the accuracy and consistency of the welded joint.

[0110] The process of obtaining the welding deformation amount based on each welding condition has been described in the previous embodiment and will not be repeated here. Finite element simulation is performed under multiple welding conditions to obtain the welding deformation amount of each welding condition, that is, to obtain multiple sets of welding deformation data under the aforementioned welding conditions, which constitute the input data for subsequent prediction of the entire welding condition. Since multiple sets of welding deformation data are based on the welding process of the full-scale model that meets the first preset accuracy requirements, the multiple sets of welding deformation data are more accurate and have good reference value.

[0111] As an optional embodiment of the present invention, the prediction of welding deformation under all welding conditions based on a welding deformation database of different welding conditions includes:

[0112] The data in the welding deformation database is used as initial data input into the deep learning model, which outputs the welding deformation amount under all the welding conditions.

[0113] Specifically, welding deformation data under all known welding conditions are integrated into a single dataset, including welding parameters and corresponding deformation data for different conditions, such as welding initiation location, welding sequence, and constraints. Data augmentation can be used to expand the existing dataset, generating more data samples under different conditions to increase the model's generalization ability and accuracy. Appropriate machine learning or deep learning models, such as linear regression, support vector machines, decision trees, and neural networks, are selected for training and predicting welding deformation. Feature engineering is then performed on the dataset, including feature selection, feature scaling, and feature transformation, to extract... Key features and noise reduction are achieved; the integrated dataset is divided into training and test sets, the model is trained on the training set, and the model performance is verified on the test set. The model parameters are adjusted to improve prediction accuracy; the generalization ability and stability of the model are verified through methods such as cross-validation to ensure that the model can accurately predict the welding deformation under unlisted working conditions. The trained and verified model can be used to predict the welding deformation under all possible welding working conditions (the welding deformation under unlisted working conditions and the welding deformation under different welding working conditions calculated above are combined to form the welding deformation under all possible welding working conditions).

[0114] As an optional embodiment of the present invention, the screening of the welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement includes:

[0115] The welding deformation under all the welding conditions is judged in turn to determine whether the total deformation under each welding condition and the first deformation in the three coordinate axes of the full-scale model are both less than the corresponding preset deformation.

[0116] If not, then discard the welding condition and welding deformation amount corresponding to at least one of the total deformation amount and the first deformation amount in the three coordinate axis directions that is not less than the corresponding preset deformation amount.

[0117] If so, then the welding condition and welding deformation corresponding to the overall deformation and the first deformation in the three coordinate axes are both less than the corresponding preset deformation.

[0118] Specifically, the overall deformation and the first deformation in each of the three coordinate axes are judged separately. The corresponding preset deformation can be set according to actual needs. For example, the preset deformation corresponding to the overall deformation is 2mm, and the preset deformation in the X, Y and Z directions is 2mm, 2.5mm and 2mm respectively.

[0119] After judging the welding deformation amount under each welding condition, it is determined whether the total deformation amount and the deformation amount in the three directions are all within the preset deformation amount. If so, the data set (the welding deformation amount under the welding condition) is deemed to meet the requirements, and the welding condition and the welding deformation amount under the welding condition are retained. Otherwise, the data set is deemed not to meet the requirements, and the data set is not retained. Regardless of whether it meets the requirements or not, the next set of data is judged until the deformation amount of all welding conditions is judged.

[0120] Among the selected welding conditions, the welding condition with the smallest second deformation in the vertical direction of the wall panel of the bridge tower segment is selected, and the selected welding condition and the welding deformation under that welding condition are output.

[0121] Specifically, the welding conditions that meet the requirements are compared, and the welding condition with the smallest deformation in the direction perpendicular to the wall panel (i.e., the second deformation) is selected. This condition and its welding deformation are output. In subsequent welding operations, this provides a reference for the actual welding construction of large-size bridge tower segments. Selecting the welding condition with the smallest deformation in the direction perpendicular to the wall panel can ensure the accuracy of the bridge tower segments when splicing them together with the wall panels after the bridge tower segments are welded.

[0122] like Figure 9 As shown, the present invention also provides a bridge tower welding deformation active control system 200, comprising:

[0123] The simulation module 210 is used to perform finite element simulation of the welding process of the bridge tower segment under actual welding conditions based on a pre-built full-scale model of the bridge tower segment, and obtain the simulated value of the welding deformation of the bridge tower segment.

[0124] The comparison and determination module 220 is used to compare the simulated welding deformation value with the measured welding deformation value, and determine the full-scale model that meets the first preset accuracy requirement based on the comparison result.

[0125] The deformation database establishment module 230 is used to establish a welding deformation database under different welding conditions based on the full-scale model that meets the first preset accuracy requirements.

[0126] Prediction module 240 is used to predict the amount of welding deformation under all the welding conditions based on a welding deformation database under different welding conditions.

[0127] The screening module 250 is used to screen the welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement.

[0128] The specific implementation method of this embodiment can be referred to the corresponding implementation method described above, and will not be described again here.

[0129] like Figure 10 As shown, an electronic device 300 provided in this embodiment of the invention includes a memory 310 and a processor 320; the memory 310 is used to store a computer program; the processor 320 is used to implement the above-described method for actively controlling the welding deformation of bridge towers when the computer program is executed.

[0130] Alternatively, an electronic device 300 includes a memory 310 and a processor 320 connected to the memory 310; the memory 310 is configured to store a computer program; and the processor 320 is configured to perform the following operations when the computer program is executed:

[0131] Based on a pre-constructed full-scale model of a bridge tower segment, the welding process of the bridge tower segment is simulated using finite element methods under actual welding conditions to obtain the simulated welding deformation value of the bridge tower segment.

[0132] The simulated welding deformation value is compared with the measured welding deformation value, and the full-scale model that meets the first preset accuracy requirement is determined based on the comparison result.

[0133] Based on the full-scale model that meets the first preset accuracy requirements, a welding deformation database is established for different welding conditions.

[0134] Based on the welding deformation database under different welding conditions, the welding deformation amount under all welding conditions is predicted;

[0135] The welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement are selected.

[0136] This invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the active control method for welding deformation of bridge towers as described above.

[0137] Alternatively, a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the following operations:

[0138] Based on a pre-constructed full-scale model of a bridge tower segment, the welding process of the bridge tower segment is simulated using finite element methods under actual welding conditions to obtain the simulated welding deformation value of the bridge tower segment.

[0139] The simulated welding deformation value is compared with the measured welding deformation value, and the full-scale model that meets the first preset accuracy requirement is determined based on the comparison result.

[0140] Based on the full-scale model that meets the first preset accuracy requirements, a welding deformation database is established for different welding conditions.

[0141] Based on the welding deformation database under different welding conditions, the welding deformation amount under all welding conditions is predicted;

[0142] The welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement are selected.

[0143] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0144] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

[0145] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A method for actively controlling welding deformation of bridge towers, characterized in that, include: Based on a pre-constructed full-scale model of a bridge tower segment, the welding process of the bridge tower segment is simulated using finite element methods under actual welding conditions to obtain the simulated welding deformation value of the bridge tower segment. The simulated welding deformation value is compared with the measured welding deformation value, and the full-scale model that meets the first preset accuracy requirement is determined based on the comparison result. Based on the full-scale model that meets the first preset accuracy requirements, a welding deformation database is established for different welding conditions. Based on the welding deformation database under different welding conditions, the welding deformation amount under all welding conditions is predicted; The process of selecting the welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement includes: The welding deformation under all the welding conditions is judged in turn to determine whether the total deformation under each welding condition and the first deformation in the three coordinate axes of the full-scale model are both less than the corresponding preset deformation. If not, then discard the welding condition and welding deformation corresponding to at least one of the total deformation and the first deformation in the three coordinate axis directions that is not less than the corresponding preset deformation. If so, then the welding condition and welding deformation are retained if the total deformation and the first deformation in the three coordinate axes are both less than the corresponding preset deformation. Among the selected welding conditions, the welding condition with the smallest second deformation in the vertical direction of the wall panel of the bridge tower segment is selected, and the selected welding condition and the welding deformation under that welding condition are output. The selected welding conditions are used to guide the welding process of the bridge tower segments.

2. The method for actively controlling welding deformation of bridge towers according to claim 1, characterized in that, The step of comparing the simulated welding deformation value with the measured welding deformation value, and determining the full-scale model that meets the first preset accuracy requirement based on the comparison result, includes: Select multiple preset parts from the full-scale model; Determine whether the difference between the simulated welding deformation value and the measured welding deformation value of each of the multiple preset parts is within the first deformation range, and obtain the determination result; Based on the judgment result, the full-scale model that meets the first preset accuracy requirement is determined.

3. The method for actively controlling welding deformation of bridge towers according to claim 2, characterized in that, The step of determining the full-scale model that meets the first preset accuracy requirement based on the judgment result includes: If the difference between the simulated welding deformation value and the measured welding deformation value of each of the multiple preset parts is within the first deformation range, then the full-scale model corresponding to the difference being within the first deformation range is taken as the full-scale model that meets the first preset accuracy requirement. If the difference between the simulated welding deformation value and the measured welding deformation value of at least one of the multiple preset parts is not within the first deformation range, then the full-scale model is adjusted, and finite element simulation is performed again based on the actual welding conditions until the difference between the simulated welding deformation value and the measured welding deformation value of each of the multiple preset parts is within the first deformation range, and the adjusted full-scale model is taken as the full-scale model that meets the first preset accuracy requirement.

4. The method for actively controlling welding deformation of bridge towers according to any one of claims 1-3, characterized in that, The establishment of a welding deformation database under different welding conditions based on the full-scale model that meets the first preset accuracy requirement includes: Establish multiple sets of the aforementioned welding conditions; A preset number of welding conditions are selected from multiple sets of welding conditions. Based on the selected multiple sets of welding conditions, the welding process of the full-scale model that meets the first preset accuracy requirement is simulated by finite element method to obtain the welding deformation data under multiple sets of welding conditions. The welding deformation database is constructed based on the welding deformation data under multiple sets of welding conditions.

5. The active control method for bridge tower welding deformation according to claim 4, characterized in that, The establishment of multiple sets of welding conditions includes: The welding conditions are freely arranged and combined according to different compositions to obtain multiple sets of welding conditions. The composition includes a starting point, welding sequence, and constraint conditions. The starting point includes welding from one end to the other, welding from both ends to the middle, and welding from the middle to both sides. The welding sequence includes welding one by one, welding simultaneously, partially simultaneous welding, and partially sequential welding. The constraint conditions include setting a code plate at the middle position of the middle transverse diaphragm of the bridge tower segment, setting the code plate at the middle position of the top transverse diaphragm and the bottom transverse diaphragm, and setting a process partition at the end of the bridge tower segment.

6. The method for actively controlling bridge tower welding deformation according to claim 1 or 2, characterized in that, Before obtaining the simulated welding deformation values ​​of the bridge tower segment by performing finite element simulation on the welding process of the bridge tower segment under actual welding conditions based on a pre-constructed full-scale model of the segment, the method further includes: Obtain point cloud data of the welded bridge tower segment, and determine the measured value of the welding deformation of the bridge tower segment based on the point cloud data.

7. The method for actively controlling bridge tower welding deformation according to claim 1, characterized in that, The full-scale model of the bridge tower segment, based on a pre-constructed model, is used to perform finite element simulation of the welding process of the bridge tower segment under actual welding conditions. The simulated welding deformation values ​​of the bridge tower segment are obtained as follows: Obtain the full-scale model of the bridge tower segment; Determine the material data of the bridge tower segment in the full-scale model, the material data including material type and material properties; Under the actual welding conditions, a full-scale model of the selected material data was subjected to finite element simulation to obtain the simulated welding deformation value.

8. The method for actively controlling welding deformation of bridge towers according to claim 1, characterized in that, The welding deformation database based on different welding conditions predicts the welding deformation amount for all welding conditions, including: The data in the welding deformation database is used as initial data input into the deep learning model, which outputs the welding deformation amount under all the welding conditions.

9. A bridge tower welding deformation active control system, characterized in that, The method for actively controlling bridge tower welding deformation as described in any one of claims 1-8 includes: The simulation module is used to perform finite element simulation of the welding process of the bridge tower segment under actual welding conditions based on a pre-built full-scale model of the bridge tower segment, and obtain the simulated value of the welding deformation of the bridge tower segment. The comparison and determination module is used to compare the simulated welding deformation value with the measured welding deformation value, and determine the full-scale model that meets the first preset accuracy requirement based on the comparison result. The deformation database establishment module is used to establish a welding deformation database under different welding conditions based on the full-scale model that meets the first preset accuracy requirements. The prediction module is used to predict the amount of welding deformation under all the welding conditions based on a database of welding deformation under different welding conditions. The screening module is used to screen the welding deformation amount and the corresponding welding condition that meet the second preset accuracy requirement, wherein the screened welding condition is used to guide the welding process of the bridge tower segment.

Images