A system for quickly building a 3D model for welding construction of large-span and wide steel box girders

Abstract

The present invention relates to a system for rapidly constructing a three-dimensional model of welding construction of a large-span wide steel box girder, and relates to the technical field of data processing and modeling, including: constructing a specification three-dimensional model and a material three-dimensional model of a large-span wide steel box girder, obtaining a basic construction three-dimensional model, processing and obtaining a specification deviation distribution and a material deviation distribution, gridding multiple welding areas, and obtaining multiple welding grid area sets; obtaining a preset welding process parameter set, combining specification deviation information and material deviation information in multiple welding grid area sets, respectively performing welding stress rapid analysis, obtaining multiple grid welding stress information sets, combining specification deviation distribution and material deviation distribution, generating multiple welding grid identification information sets of multiple welding grid area sets, identifying the basic construction three-dimensional model, and completing rapid construction. The present invention achieves the technical effect of improving the construction efficiency and precision of the three-dimensional model of welding construction of a large-span wide steel box girder.

Description

Technical Field

[0001] The invention relates to the technical field of data processing modeling, and in particular to a system for quickly building a three-dimensional model of a large-span and wide steel box girder welding construction. Background Art

[0002] In the welding construction process of large-span and wide steel box girders, accurate understanding of the specification and characteristic information of the steel box girders is of great significance to improving the welding quality. Welding workers often need to rely on the three-dimensional model of the steel box girder to assist in welding adjustments to ensure the accuracy and consistency of welding. However, the currently widely used three-dimensional model construction method has some shortcomings, especially in the representation of the characteristics of different positions of large-span and wide steel box girders, which is relatively rough and cannot effectively distinguish subtle differences. In addition, if detailed marking is performed, model construction often takes a lot of time, which affects construction efficiency. In complex large-span steel structure construction scenarios, traditional three-dimensional model construction methods are difficult to quickly respond to the actual needs of the construction site, and cannot be flexibly adjusted according to the welding requirements of different positions, which has an adverse effect on welding accuracy and quality. Summary of the invention

[0003] The invention aims to solve the technical problems in the prior art that the construction of a three-dimensional model for welding construction of a large-span wide steel box girder is not precise and has low construction efficiency.

[0004] In a first aspect, the present invention provides a system for quickly constructing a three-dimensional model of welding construction of a large-span wide steel box girder, the system comprising: a basic model construction module, for collecting steel box girder specification parameters of the large-span wide steel box girder, constructing a specification three-dimensional model, and performing material detection on multiple steel box girder parts of the large-span wide steel box girder to obtain material feature information, construct a material three-dimensional model, and construct a basic construction three-dimensional model in combination with the specification three-dimensional model;

[0005] A deviation distribution processing module is used to obtain a standard specification three-dimensional model and a standard material three-dimensional model, compare the specification three-dimensional model and the material three-dimensional model, and obtain a specification deviation distribution and a material deviation distribution;

[0006] A welding grid division module, used for performing grid division on a plurality of welding areas according to the specification deviation distribution and the material deviation distribution to obtain a plurality of welding grid area sets, wherein the size of the welding grid area and the size of the specification deviation information and the size of the material deviation information are negatively correlated;

[0007] A stress rapid analysis module is used to obtain a preset welding process parameter set of the large-span wide steel box girder, and to perform rapid welding stress analysis respectively in combination with the specification deviation information and material deviation information in the plurality of welding grid area sets, to obtain a plurality of grid welding stress information sets, wherein rapid analysis is performed according to the size of each welding grid area;

[0008] The model identification module is used to generate multiple welding grid identification information sets of the multiple welding grid area sets according to the multiple grid welding stress information sets, specification deviation distribution and material deviation distribution, identify the basic construction three-dimensional model, complete rapid construction, and obtain the construction three-dimensional model.

[0009] In a second aspect, the present invention provides an electronic device comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby realizing the system for rapidly constructing a three-dimensional model of welding construction of a large-span and wide-width steel box girder of the first aspect.

[0010] In a third aspect, the present invention provides a computer-readable storage medium having a computer software program stored therein. When the computer software program is executed by a processor, the system for rapidly constructing a three-dimensional model of large-span and wide-width steel box girder welding construction of the first aspect is implemented.

[0011] The present invention realizes the rapid construction of a three-dimensional model of a large-span wide steel box girder through one or more of the above-mentioned technical solutions, and ensures the accuracy of the construction information identification in the three-dimensional model. Among them, the basic model construction module can combine the design parameters and material feature information to generate an accurate basic construction three-dimensional model, which improves the understanding of the characteristic parameters of different positions of the steel box girder. The deviation distribution processing module quickly identifies the deviation distribution of specifications and materials by comparing the actual and standard models, providing a basis for the subsequent welding grid division. The welding grid division module dynamically adjusts the size of the welding grid area according to the deviation information, realizes the refined welding area division, and improves the subsequent analysis efficiency and model construction efficiency. The stress rapid analysis module combines the preset welding process parameters to perform rapid stress analysis on the specification deviation and material deviation of each grid area, provides the welding stress state of each area, provides an important basis for the optimization of the welding process, and improves the analysis efficiency and model construction efficiency through rapid stress analysis. Finally, the model identification module completes the identification and construction of the three-dimensional model by generating welding grid identification information, significantly improves the model construction efficiency, provides more accurate and efficient construction guidance for welding operations, and improves the welding construction quality and efficiency as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of the structure of a system for rapidly constructing a three-dimensional model for welding construction of a large-span and wide steel box girder provided in an embodiment of the present invention;

[0013] Figure 2 A functional block diagram of an electronic device provided by an embodiment of the present invention;

[0014] Figure 3A principle block diagram of the computer-readable storage medium provided by the present invention.

[0015] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0016] Basic model building module 11, deviation distribution processing module 12, welding grid division module 13, stress rapid analysis module 14, model identification module 15, electronic device 100, memory 110, processor 120, computer program 111, computer readable storage medium 200, computer program 211. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0018] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0019] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0020] Example 1

[0021] like Figure 1 As shown, an embodiment of the present invention provides a system for quickly building a three-dimensional model of large-span and wide-width steel box girder welding construction, including: a basic model building module 11, a deviation distribution processing module 12, a welding grid division module 13, a stress rapid analysis module 14 and a model identification module 15.

[0022] In an embodiment of the present application, the basic model construction module 11 is used to collect the specification parameters of the large-span and wide-width steel box girder, construct a specification three-dimensional model, and perform material detection on multiple steel box girder parts of the large-span and wide-width steel box girder to obtain material characteristic information, construct a material three-dimensional model, and combine the specification three-dimensional model to construct a basic construction three-dimensional model.

[0023] In the embodiment of the present application, the basic model construction module 11 first collects the specification parameters of the large-span wide steel box girder, which include the structural dimensions, cross-sectional shape, beam length, thickness and other information of the large-span wide steel box girder. The specification parameters of the steel box girder are constructed by testing the structural dimensions, cross-sectional shape, beam length, thickness and other data of the steel box girder to be welded, which are used as the basic data for constructing the specification three-dimensional model. For example, the specification data of multiple parts of the large-span wide steel box girder to be welded can be tested by digital measuring tools, such as digital measuring rulers. By obtaining the specification parameters of the steel box girder, a specification three-dimensional model can be constructed, which accurately presents the overall geometric shape of the steel box girder in three dimensions.

[0024] Furthermore, material testing is performed on different parts of the steel box girder. Material testing refers to the collection of material characteristics of different areas of the steel box girder through sensors or testing equipment, such as the thickness of the steel plate, and may also include important material information such as tensile strength, hardness, density, etc. Due to the inevitable errors in steel plate processing, the material characteristics of the steel box girder in different areas are different from the standard material characteristics. Through these test data, the material performance differences of various parts of the steel box girder can be reflected, helping construction personnel identify possible material problems.

[0025] Based on the material detection results, a material three-dimensional model is constructed. The material three-dimensional model is based on the specification three-dimensional model, and further associates the material information of each position of the steel box girder with the geometric structure to more comprehensively reflect the overall state of the steel box girder. For example, the material three-dimensional model is constructed according to the material information of different positions of the steel box girder combined with its corresponding spatial position coordinates. The specification three-dimensional model is combined with the material three-dimensional model to generate a basic construction three-dimensional model, which not only shows the shape and size of the steel box girder, but also includes the material characteristics of each part. Exemplarily, based on the coordinates of different positions of the steel box girder in the specification three-dimensional model, the material information of the corresponding positions can be indexed for identification to construct a basic construction three-dimensional model.

[0026] The foundation construction 3D model can provide construction workers with basic structure and material references, help them optimize welding, installation and other construction links, and improve construction quality and efficiency.

[0027] In the embodiment of the present application, the deviation distribution processing module 12 is used to obtain a standard specification three-dimensional model and a standard material three-dimensional model, compare the specification three-dimensional model and the material three-dimensional model, and obtain the specification deviation distribution and the material deviation distribution.

[0028] In the embodiment of the present application, a standard specification three-dimensional model and a standard material three-dimensional model are obtained. The standard specification three-dimensional model is an ideal geometric model constructed based on design drawings or project requirements, and includes various standard geometric parameters of the steel box girder, such as multiple structural lengths, widths, heights, thicknesses, etc. The standard material three-dimensional model is a material model constructed based on the standard material property standards in large-span and wide-width steel box girders, such as the standard steel plate thickness at different positions of the steel box girder, or the standard tensile strength, hardness and density, etc., which reflects the material parameters that the steel box girder should have under ideal conditions.

[0029] The specification 3D model and the material 3D model are compared to obtain the distribution of the specification parameters and material parameters with deviations, and obtain the specification deviation distribution and the material deviation distribution.

[0030] The deviation distribution processing module 12 in the embodiment of the present application is also used for:

[0031] Obtain the standard specification 3D model and standard material 3D model of large-span wide steel box girders;

[0032] Based on the standard specification three-dimensional model and the standard material three-dimensional model, the specification three-dimensional model and the material three-dimensional model are compared to obtain specification deviation distribution and material deviation distribution.

[0033] In the embodiment of the present application, a standard specification 3D model and a standard material 3D model are first obtained. The standard specification 3D model is an ideal 3D model constructed according to the design drawings of the wide span steel box girder and the structural requirements of the project. It accurately reflects the standard geometric dimensions and spatial structure information of the steel box girder, such as length, width, height and thickness distribution of each part.

[0034] The standard material 3D model is constructed based on the material standards and process requirements of large-span and wide steel box girders. It includes the standard material characteristic requirements of steel box girders, such as the steel plate thickness at multiple locations of the steel box girder, tensile strength, hardness, density and other key parameters. The standard material 3D model can help understand the standard material characteristic requirements of steel in different parts.

[0035] Furthermore, the standard specification 3D model and the standard material 3D model are compared with the actual specification 3D model and the actual material 3D model in the actual construction process. The comparison process uses actual data obtained by digital measurement tools or sensors, such as traversing the model data of all positions in the standard specification 3D model and the standard material 3D model, the specification 3D model and the material 3D model, comparing the difference in data at each position in the 3D model, such as size difference and material feature difference, obtaining specification difference data of the standard specification 3D model and the specification 3D model and model position data of the specification difference data, such as model coordinate data, and material difference data of the standard material 3D model and the material 3D model, and model position data of the material difference data.

[0036] Based on the model position data of the specification difference data and the model position data of the material difference data, the specification deviation distribution and the material deviation distribution are constructed. The specification deviation distribution is used to show the difference between the geometric dimensions of the steel box girder in different areas and the standard design, reflecting which parts may have size deviations; while the material deviation distribution reveals the difference between the actual performance and the design performance of each part of the steel. These deviation distributions not only provide important references for subsequent welding and construction adjustments, but also help construction personnel optimize the welding process, reduce deviations, and ensure the safety and quality of the overall structure.

[0037] In an embodiment of the present application, the welding grid division module 13 is used to grid-divide multiple welding areas according to the specification deviation distribution and the material deviation distribution to obtain multiple welding grid area sets, wherein the size of the welding grid area and the specification deviation information are negatively correlated with the size of the material deviation information.

[0038] In the embodiment of the present application, multiple welding areas of the steel box girder are accurately grid-divided based on the specification deviation distribution and the material deviation distribution. Grid division refers to dividing multiple welding areas in a large-span wide steel box girder into small unit grids according to specific rules, so as to facilitate more detailed welding analysis and process adjustment for each area.

[0039] In the grid division process, the size of the welding grid area and the specification deviation information are negatively correlated with the size of the material deviation information, that is, the larger the specification deviation information and the larger the material deviation information of the welding area, the smaller the size of the divided welding grid area. In this way, a more detailed welding performance analysis and identification can be performed on the areas with large specification and material deviations to improve the model construction accuracy and welding quality, while a rough welding performance analysis and identification can be performed on the areas with small specification and material deviations to improve the model construction efficiency. Among them, the areas with large specification and material deviations have a greater probability of welding deformation and other problems during welding. Therefore, a more detailed welding performance analysis and identification is conducive to improving the construction function of the three-dimensional model of welding construction and improving welding quality.

[0040] In the embodiment of the present application, the welding grid division module 13 is also used for:

[0041] Acquire multiple welding areas of the large-span wide steel box girder;

[0042] According to the specification deviation distribution and the material deviation distribution, divide and calculate to obtain the average specification deviation information and the average material deviation information in the plurality of welding areas;

[0043] According to the plurality of average specification deviation information and the plurality of average material deviation information, a plurality of specification grid size information and a plurality of material grid size information are obtained by classification, and a plurality of grid size information is obtained by calculation;

[0044] The plurality of welding areas are grid-divided according to the plurality of grid size information to obtain a plurality of welding grid area sets.

[0045] In the embodiment of the present application, during the welding process of a large-span wide steel box girder, multiple welding areas are obtained, and these welding areas are divided according to the structural characteristics and design requirements of the steel box girder. Each welding area represents a local welding position, which is usually divided according to the length, width and height of the beam body. Exemplarily, the welding area includes the welding area of ​​the upper flange plate and the lower flange plate of the steel box girder, the web welding area, etc. The welding area is specifically the area where welding is directly performed during the welding process and the area where welding may be affected, such as the area where welding deformation has occurred in historical events.

[0046] Further, according to the above-mentioned specification deviation distribution and material deviation distribution, according to the position coordinate information of multiple welding areas in the steel box girder, the specification deviation data and material deviation data in multiple welding areas can be obtained. And the mean of the specification deviation data and material deviation data in each welding area is calculated to obtain the average specification deviation information and the average material deviation information. For example, the average specification deviation information in a certain welding area is a length deviation of -3mm, and the average material deviation information is a steel plate thickness deviation of 0.5mm.

[0047] Furthermore, based on multiple average specification deviation information and multiple average material deviation information, multiple specification grid size information and multiple material grid size information are classified and obtained. The specification grid size information is determined based on the classification of the average specification deviation information. Areas with larger average specification deviation information correspond to smaller grid units, so as to more finely handle welding operations; the material grid size information is determined based on the material deviation information. Areas with larger average material deviation information also require smaller grid units for fine welding control.

[0048] In the embodiment of the present application, according to the multiple average specification deviation information and the multiple average material deviation information, multiple specification grid size information and multiple material grid size information are obtained by classification, including:

[0049] Obtain a sample average specification deviation information set and a sample average material deviation information set, and annotate a sample grid size information set according to the minimum welding deformation area size under different sample average specification deviation information and sample average material deviation information;

[0050] The sample average specification deviation information set and the sample average material deviation information set are respectively used, combined with the sample grid size information set, to construct a specification grid size classifier and a material grid size classifier;

[0051] The multiple average specification deviation information and the multiple average material deviation information are respectively input into the specification grid size classifier and the material grid size classifier, and classified to obtain multiple specification grid size information and multiple material grid size information.

[0052] In the embodiment of the present application, based on the historical welding record data of the previous large-span and wide-width steel box girders, the sample average specification deviation information set and the sample average material deviation information set are processed and collected based on the same steps as in the aforementioned content.

[0053] Furthermore, based on the historical welding record data, the minimum welding deformation area size under different sample average specification deviation information and sample average material deviation information is obtained, that is, the minimum welding deformation area that occurs when welding is performed when different sample average specification deviation information and sample average material deviation information appear within the historical time is used as the sample grid size information, and a sample grid size information set is obtained.

[0054] Optionally, the corresponding sample grid size information may be set according to the size of the sample average specification deviation information set and the sample average material deviation information set, and the size of the sample average specification deviation information and the sample average material deviation information is inversely proportional to the size of the sample grid size information. For example, a preset grid size information such as 10 square centimeters is set, and then the sample grid size information set is obtained by multiplying the preset grid size information by the inverse of the ratio of the mean of each sample average specification deviation information and each sample average material deviation information and the sample average specification deviation information set and the sample average material deviation information set.

[0055] Furthermore, the sample average specification deviation information set and the sample average material deviation information set are respectively used in combination with the generated sample grid size information set to construct a specification grid size classifier and a material grid size classifier. For example, the sample average specification deviation information is used as the classification input, and the sample grid size information corresponding to the sample average specification deviation information is used as the input to construct a mapping relationship between the sample average specification deviation information and the sample grid size information as a specification grid size classifier. Based on the same method, the sample average material deviation information set is combined with the sample grid size information set to construct a material grid size classifier.

[0056] Based on the constructed specification grid size classifier and material grid size classifier, the current multiple average specification deviation information and multiple average material deviation information are respectively input into the specification grid size classifier and the material grid size classifier, and mapping index classification is performed to obtain multiple specification grid size information and multiple material grid size information to complete the classification of grid size information.

[0057] Furthermore, according to the multiple specification grid size information and the multiple material grid size information, the specification grid size information and the material grid size information of a welding area are respectively combined, and the average is calculated to obtain multiple grid size information.

[0058] Finally, according to the grid size information, each welding area is divided into welding grid areas to generate multiple welding grid area sets of multiple welding grid areas. If the welding area cannot be completely divided according to the grid size information, the remaining welding area area is retained as the welding grid area to obtain multiple welding grid area sets.

[0059] In an embodiment of the present application, the stress rapid analysis module 14 is used to obtain a preset welding process parameter set for the large-span and wide-width steel box girder, and to perform rapid welding stress analysis respectively in combination with the specification deviation information and material deviation information in the multiple welding grid area sets to obtain multiple grid welding stress information sets, wherein rapid analysis is performed based on the size of each welding grid area.

[0060] In an embodiment of the present application, after dividing multiple welding grid area sets into multiple welding areas, a rapid analysis of welding stress is performed on each welding grid area to obtain the stress that may be generated in each welding grid area during welding, which is then used as a basis for adjusting welding process parameters (for example, adjusting welding temperature or speed) to avoid welding deformation, etc., thereby improving model building efficiency through rapid analysis.

[0061] First, the preset welding process parameters of multiple welding areas of the large-span wide steel box girder are obtained as the preset welding process parameter set, each of which contains key process parameters related to welding, such as welding current, voltage, welding speed, heat input, etc. The preset welding process parameter set is a welding process parameter set in advance based on engineering experience and design requirements.

[0062] Next, combining the multiple welding grid area sets generated previously, each welding grid area is analyzed, and welding stress is quickly analyzed based on the specification deviation information and material deviation information in the specification deviation distribution and material deviation distribution corresponding to each welding grid area.

[0063] When performing a quick analysis of welding stress, the stress that may be generated during the welding process is calculated based on the size of each welding grid area, combined with the specification deviation information and material deviation information. When the deviation information is large, the welding stress that may be generated is large. Welding stress refers to the internal stress generated by temperature changes and material deformation during the welding process, which may cause problems such as weld cracking and structural deformation. By quickly analyzing the stress in each grid area, potential stress concentration areas can be predicted in advance, and the three-dimensional model can be marked to provide a basis for subsequent welding process adjustments.

[0064] The fast analysis includes performing a fast analysis according to the size of each welding grid area, for example, performing different accuracy levels of analysis on welding grid areas of different sizes to reduce the overall analysis time while ensuring the accuracy of stress analysis of key welding grid areas. For example, a relatively accurate analysis is performed on a smaller welding grid area, and a relatively simple analysis is performed on a larger welding grid area. In this way, multiple grid welding stress information sets are obtained.

[0065] Through rapid stress analysis, welding grid areas that may have stress concentration or deformation risks can be identified before construction. By marking these areas in the 3D model, the efficiency of building the 3D model for welding construction can be improved. At the same time, the construction and identification accuracy of the 3D model for welding construction can be guaranteed, and the reference significance of the 3D model construction for construction can be enhanced. Process optimization can be carried out in advance, effectively improving welding quality and reducing subsequent structural problems.

[0066] In the embodiment of the present application, a preset welding process parameter set of the large-span wide steel box girder is obtained, and the specification deviation information and material deviation information in the multiple welding grid area sets are combined to perform rapid welding stress analysis respectively, and obtain multiple grid welding stress information sets, including:

[0067] Acquire welding process parameters of the plurality of welding areas in the large-span wide steel box girder as a preset welding process parameter set;

[0068] Training a weld stress analyzer including multiple weld stress analysis branches;

[0069] According to the sizes of the plurality of welding grid area sets and in combination with the number of the plurality of welding stress analysis branches, the rapid analysis quantity of each welding grid area is calculated to obtain a plurality of grid rapid analysis quantity sets;

[0070] According to the specification deviation distribution and the material deviation distribution, a plurality of grid specification deviation information sets and a plurality of grid material deviation information sets in the plurality of welding grid region sets are screened and obtained;

[0071] According to the multiple grid specification deviation information sets and the multiple grid material deviation information sets, combined with the preset welding process parameter set, they are respectively input into the welding stress analysis branches of the multiple grid quick analysis quantity sets to perform welding stress quick analysis, and the average is taken to obtain multiple grid welding stress information sets.

[0072] In the embodiment of the present application, welding process parameters of multiple welding areas are obtained and used as a preset welding process parameter set. These parameters include key factors such as welding current, voltage, welding speed, and heat input. Welding process parameters affect the heat conduction and deformation characteristics during welding and are basic data for stress analysis.

[0073] Furthermore, a welding stress analyzer including a plurality of welding stress analysis branches is trained according to welding record data in a historical period.

[0074] In an embodiment of the present application, training a welding stress analyzer including multiple welding stress analysis branches includes:

[0075] Collecting a sample grid specification deviation information set, a sample grid material deviation information set and a sample welding process parameter set, and obtaining welding stress test data after welding, and marking the obtained sample grid welding stress information set;

[0076] Combining the sample grid specification deviation information set, the sample grid material deviation information set, the sample welding process parameter set and the sample grid welding stress information set as a stress analysis training data set;

[0077] A preset proportion of training data is randomly selected multiple times from the stress analysis training data set to train multiple welding stress analysis branches and obtain a welding stress analyzer.

[0078] In an embodiment of the present application, according to the previous historical welding data of large-span and wide-width steel box girders, based on the steps in the aforementioned content, the grid specification deviation information, grid material deviation information and welding process parameters of the welding grid area in the previous welding are processed and extracted to obtain a sample grid specification deviation information set, a sample grid material deviation information set and a sample welding process parameter set.

[0079] Furthermore, welding stress tests are performed on the welded parts of each sample large-span wide steel box girder after welding, and the actual stress data of the weld and the surrounding area are obtained through the stress testing equipment to form welding stress test data. By matching these test data with the corresponding grid deviation information, material information and process parameters, the grid welding stress information of each sample welding grid area can be annotated and obtained. In this way, the sample grid welding stress information set is obtained by annotation, that is, the actual stress magnitude of these welding grid areas after welding is completed. Annotation can be performed through manual annotation and other annotation methods.

[0080] The sample grid specification deviation information set, the sample grid material deviation information set, the sample welding process parameter set and the sample grid welding stress information set are combined to form a comprehensive data set as a stress analysis training data set for training a welding stress analyzer.

[0081] Furthermore, in order to improve the accuracy of the welding stress analyzer, the stress analysis training data set is randomly sampled multiple times, and part of the training data is selected for training according to a preset ratio. The preset ratio can be set by yourself, for example, 60%. Through random sampling, different subsets of training data can be created to ensure the generalization ability of multiple welding stress analysis branches during training, and multiple welding stress analysis branches with different performances are obtained through training. Based on the training data randomly selected multiple times, multiple welding stress analysis branches are trained, and each branch is trained through a different subset of training data to enhance the diversity and prediction ability of the final overall welding stress analyzer.

[0082] Exemplarily, using BP (back propagation) neural network to train multiple welding stress analysis branches can achieve efficient stress prediction. The training process first needs to process the collected training data, and use the sample grid specification deviation information set, the sample grid material deviation information set and the sample welding process parameter set as the input features of the BP neural network, and the sample grid welding stress information set as the output target.

[0083] Among them, a network structure of multiple welding stress analysis branches is constructed, including an input layer, a hidden layer and an output layer, and then multiple sets of training data are used for training. In each training iteration, the input layer inputs the specification deviation, material deviation and welding process parameters into the network, and transmits them to the hidden layer through the weight matrix. The output of the hidden layer is then transmitted to the output layer, and finally the predicted welding stress value is generated. The welding stress value predicted by the welding stress analysis branch is compared with the real sample grid welding stress information to calculate the prediction error. The commonly used error function is the mean square error (MSE), which measures the performance of the welding stress analysis branch by summing the squares of the difference between the predicted value and the true value and taking the average value. According to the error size, the gradient descent algorithm is used to adjust the weights and biases in the network through back propagation. The back propagation process calculates the gradient of each neuron layer by layer, and updates the weights according to the learning rate to minimize the error. Further multiple iterations of training are performed until the error converges to a preset threshold, such as an error less than 5%, or the maximum number of iterations is reached. In order to improve the generalization ability, the training process can be evaluated using a cross-validation method.

[0084] Finally, after multiple training and optimization, multiple trained welding stress analysis branches are obtained, and the multiple welding stress analysis branches are combined to obtain an overall welding stress analyzer. The analyzer can accurately predict the welding stress of the welding grid area after welding based on the input specification deviation information, material deviation information and welding process parameters, thereby providing a reference for stress distribution for actual welding operations, helping to optimize welding processes, reduce stress concentration phenomena and improve welding quality.

[0085] In the embodiment of the present application, according to the size of multiple welding grid area sets and the number of multiple welding stress analysis branches, the number of rapid analyses using welding stress analysis branches for rapid stress analysis in each welding grid area is calculated, that is, the number of welding stress analysis branches is used to obtain multiple grid rapid analysis number sets. Among them, for smaller welding grid areas, the number of rapid analyses set by calculation is larger, and a more accurate welding stress analysis is performed, while for larger welding grid areas, the number of rapid analyses set by calculation is smaller, and fewer welding stress analysis branches are used for welding stress analysis, and a faster welding stress analysis is performed, thereby improving the speed of building a three-dimensional model.

[0086] In the embodiment of the present application, according to the sizes of the plurality of welding grid area sets and in combination with the number of the plurality of welding stress analysis branches, the number of rapid analysis of each welding grid area is calculated, including:

[0087] Acquire minimum grid size information of the plurality of welding grid area sets;

[0088] According to the grid size information of each welding grid area and the minimum grid size information, combined with the number of the multiple welding stress analysis branches, the grid fast analysis quantity is calculated to obtain multiple grid fast analysis quantity sets.

[0089] In the embodiment of the present application, the quick analysis quantity of each welding grid area is calculated based on the minimum grid size information as a benchmark.

[0090] The minimum grid size information of the plurality of welding grid area sets is obtained by filtering and obtaining the minimum grid size information according to the plurality of grid size information in the aforementioned content.

[0091] Further, the number of quick analyses corresponding to the minimum grid size information is set to the maximum number of multiple welding stress analysis branches, that is, the welding grid area of ​​the minimum grid size information adopts all welding stress analysis branches for stress analysis. Then, optionally, the ratio of the minimum grid size information to the grid size information of other welding grid areas is calculated, multiplied by the number of the multiple welding stress analysis branches, and then the integer is taken as the number of grid quick analyses to obtain multiple grid quick analysis number sets. In this way, the larger the grid size information of the welding area grid, the smaller the corresponding grid quick analysis number.

[0092] In this way, an efficient welding stress analysis process is achieved. This method not only improves the speed of welding stress analysis, but also ensures the accuracy of welding quality.

[0093] Furthermore, based on the specification deviation distribution and material deviation distribution of the aforementioned content, combined with the position of each welding grid area in multiple welding grid area sets, the specification deviation information set and grid material deviation information in each welding grid area set are screened to obtain multiple grid specification deviation information sets and multiple grid material deviation information sets.

[0094] Then, according to multiple grid specification deviation information sets and multiple grid material deviation information sets, combined with a preset welding process parameter set, the grid specification deviation information and grid material deviation information in each welding grid area, combined with the preset welding process parameters of the welding area to which it belongs, are respectively input into the welding stress analysis branch of the corresponding grid rapid analysis quantity, and the welding stress rapid analysis is performed, so that the grid welding stress information of the grid rapid analysis quantity can be obtained, and then the mean is calculated as the grid welding stress information of the welding grid area obtained by the final analysis. Since the analysis results of the welding stress analysis branches of the grid rapid analysis quantity are integrated, the grid welding stress information is more accurate. Among them, the corresponding number of welding stress analysis branches can be randomly selected from the multiple welding stress analysis branches according to the grid rapid analysis quantity for welding stress analysis.

[0095] In this way, the grid welding stress information of each welding grid area can be analyzed and obtained, and then multiple grid welding stress information sets of multiple welding grid area sets can be obtained. Through the above steps, the welding stress of each welding grid area in the welding process can be predicted efficiently and accurately, helping welding engineers to identify potential stress concentration areas and risk points in advance, optimize welding processes, and improve the safety and stability of the overall structure, thereby achieving the auxiliary value of enhancing the construction of the three-dimensional model of welding construction.

[0096] In an embodiment of the present application, the model identification module 15 is used to generate multiple welding grid identification information sets of the multiple welding grid area sets based on the multiple grid welding stress information sets, specification deviation distribution and material deviation distribution, identify the basic construction three-dimensional model, complete rapid construction, and obtain the construction three-dimensional model.

[0097] In an embodiment of the present application, a welding grid identification information set is generated for each welding grid area based on multiple grid welding stress information, specification deviation distribution and material deviation distribution, and it is applied to the basic construction three-dimensional model for identification, completing the final construction three-dimensional model construction and obtaining the construction three-dimensional model.

[0098] Among them, the welding grid identification information of each welding grid area includes the grid welding stress information that may be generated by welding in the welding grid area obtained through analysis, as well as the corresponding specification deviation information and material deviation information. By marking, it helps operators understand the geometric and material property deviations of different welding areas of large-span and wide-width steel box girders, as well as the welding stress generated, which can help optimize welding parameters and ensure welding quality.

[0099] In the embodiment of the present application, a welding grid identification information set is generated for each welding grid area according to a plurality of grid welding stress information, specification deviation distribution and material deviation distribution, and is applied to the basic construction three-dimensional model for identification, and the final construction three-dimensional model is constructed to obtain the construction three-dimensional model, including:

[0100] According to the specification deviation distribution and the material deviation distribution, a plurality of grid specification deviation information sets and a plurality of grid material deviation information sets of the plurality of welding grid area sets are obtained by screening;

[0101] The multiple grid specification deviation information sets and multiple grid material deviation information sets are used in combination with the multiple grid welding stress information sets to generate multiple welding grid identification information sets of the multiple welding grid area sets to identify the foundation construction three-dimensional model.

[0102] In an embodiment of the present application, during the identification process of the welding grid area, it is first necessary to screen the data based on the specification deviation distribution and the material deviation distribution. Specifically, based on the coordinate position of each welding grid area in the multiple welding grid area sets in the basic construction three-dimensional model, the specification deviation information and material deviation information of the corresponding position are indexed. In this way, the grid specification deviation information and grid material deviation information of each welding grid area are obtained, and multiple grid specification deviation information sets and multiple grid material deviation information sets are obtained.

[0103] Further, the multiple grid specification deviation information sets and multiple grid material deviation information sets obtained by screening are combined with the welding stress information of each welding grid area to generate multiple welding grid identification information sets of multiple welding grid area sets, and the basic construction three-dimensional model is identified. By combining the specification deviation, material deviation and welding stress information together, the characteristics of each welding grid area can be comprehensively evaluated and the key factors affecting the welding quality can be identified. Exemplarily, the grid specification deviation information, grid material deviation information and welding stress information of each grid area are directly used as welding grid identification information and identified in the basic construction three-dimensional model. For example, the welding grid identification information of a certain welding grid area is (length -3mm, thickness 0.5mm, welding stress 180Mpa), and it can also be combined with the welding grid area ID numbered for multiple welding grid area sets for identification. In this way, the rapid construction and identification of the construction three-dimensional model is completed, and the final construction three-dimensional model is obtained.

[0104] The embodiments of the present application achieve the following technical effects through the above specific implementation methods:

[0105] The present invention realizes the rapid three-dimensional model construction of large-span wide steel box girders through the above-mentioned technical scheme, and ensures the accuracy of the construction information identification in the three-dimensional model. Among them, the basic model construction module can combine the design parameters and material feature information to generate an accurate basic construction three-dimensional model, which improves the understanding of the characteristic parameters of different positions of the steel box girder. The deviation distribution processing module quickly identifies the deviation distribution of specifications and materials by comparing the actual and standard models, providing a basis for the subsequent welding grid division. The welding grid division module dynamically adjusts the size of the welding grid area according to the deviation information, realizes the refined welding area division, and improves the subsequent analysis efficiency and model construction efficiency. The stress rapid analysis module combines the preset welding process parameters to perform rapid stress analysis on the specification deviation and material deviation of each grid area, provides the welding stress state of each area, provides an important basis for the optimization of the welding process, and improves the analysis efficiency and model construction efficiency through rapid stress analysis. Finally, the model identification module completes the identification and construction of the three-dimensional model by generating welding grid identification information, significantly improves the model construction efficiency, provides more accurate and efficient construction guidance for welding operations, and improves the welding construction quality and efficiency as a whole.

[0106] See also Figure 2 , Figure 2 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides an electronic device 100, including a memory 110, a processor 120, and a computer program 111 stored in the memory 110 and executable on the processor 120. When the processor 120 executes the computer program 111, the system in Example 1 is implemented.

[0107] See also Figure 3 , Figure 3 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 3 As shown, this embodiment provides a computer-readable storage medium 200 on which a computer program 211 is stored. When the computer program 211 is executed by a processor, the system in Embodiment 1 is implemented.

[0108] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0109] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0110] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0114] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A system for rapidly constructing a three-dimensional model for welding construction of a large-span and wide steel box girder, characterized in that: The system comprises: A basic model building module is used to collect steel box girder specification parameters of the large-span wide steel box girder, build a specification three-dimensional model, and perform material detection on multiple steel box girder parts of the large-span wide steel box girder to obtain material feature information and build a material three-dimensional model. Combined with the specification three-dimensional model, a basic construction three-dimensional model is built; A deviation distribution processing module is used to obtain a standard specification three-dimensional model and a standard material three-dimensional model, compare the specification three-dimensional model and the material three-dimensional model, and obtain a specification deviation distribution and a material deviation distribution; A welding grid division module, used for performing grid division on a plurality of welding areas according to the specification deviation distribution and the material deviation distribution to obtain a plurality of welding grid area sets, wherein the size of the welding grid area and the size of the specification deviation information and the size of the material deviation information are negatively correlated; A stress rapid analysis module is used to obtain a preset welding process parameter set of the large-span wide steel box girder, and to perform rapid welding stress analysis respectively in combination with the specification deviation information and material deviation information in the plurality of welding grid area sets, to obtain a plurality of grid welding stress information sets, wherein rapid analysis is performed according to the size of each welding grid area; A model identification module is used to generate a plurality of welding grid identification information sets of the plurality of welding grid area sets according to the plurality of grid welding stress information sets, specification deviation distribution and material deviation distribution, identify the foundation construction three-dimensional model, complete rapid construction, and obtain a construction three-dimensional model; According to the specification deviation distribution and the material deviation distribution, multiple welding areas are grid-divided to obtain multiple welding grid area sets, including: Acquire multiple welding areas of the large-span wide steel box girder; According to the specification deviation distribution and the material deviation distribution, divide and calculate to obtain the average specification deviation information and the average material deviation information in the plurality of welding areas; According to the plurality of average specification deviation information and the plurality of average material deviation information, a plurality of specification grid size information and a plurality of material grid size information are obtained by classification, and a plurality of grid size information is obtained by calculation; According to the plurality of grid size information, the plurality of welding areas are grid-divided to obtain a plurality of welding grid area sets; According to the plurality of average specification deviation information and the plurality of average material deviation information, a plurality of specification grid size information and a plurality of material grid size information are obtained by classification, including: Obtain a sample average specification deviation information set and a sample average material deviation information set, and annotate a sample grid size information set according to the minimum welding deformation area size under different sample average specification deviation information and sample average material deviation information; The sample average specification deviation information set and the sample average material deviation information set are respectively used, combined with the sample grid size information set, to construct a specification grid size classifier and a material grid size classifier; The multiple average specification deviation information and the multiple average material deviation information are respectively input into the specification grid size classifier and the material grid size classifier, and classified to obtain multiple specification grid size information and multiple material grid size information.

2. The system for rapidly constructing a three-dimensional model for welding construction of a large-span and wide steel box girder according to claim 1 is characterized in that: Obtaining a standard specification 3D model and a standard material 3D model, and comparing the specification 3D model and the material 3D model, including: Obtain the standard specification 3D model and standard material 3D model of large-span wide steel box girders; Based on the standard specification three-dimensional model and the standard material three-dimensional model, the specification three-dimensional model and the material three-dimensional model are compared to obtain specification deviation distribution and material deviation distribution.

3. The system for rapidly constructing a three-dimensional model for welding construction of a large-span and wide steel box girder according to claim 1 is characterized in that: Obtaining a preset welding process parameter set of the large-span wide steel box girder, combining the specification deviation information and the material deviation information in the multiple welding grid area sets, and performing a rapid welding stress analysis respectively, including: Acquire welding process parameters of the plurality of welding areas in the large-span wide steel box girder as a preset welding process parameter set; Training a weld stress analyzer including multiple weld stress analysis branches; According to the sizes of the plurality of welding grid area sets and in combination with the number of the plurality of welding stress analysis branches, the rapid analysis quantity of each welding grid area is calculated to obtain a plurality of grid rapid analysis quantity sets; According to the specification deviation distribution and the material deviation distribution, a plurality of grid specification deviation information sets and a plurality of grid material deviation information sets in the plurality of welding grid region sets are screened and obtained; According to the multiple grid specification deviation information sets and the multiple grid material deviation information sets, combined with the preset welding process parameter set, they are respectively input into the welding stress analysis branches of the multiple grid quick analysis quantity sets to perform welding stress quick analysis, and the average is taken to obtain multiple grid welding stress information sets.

4. The system for rapidly constructing a three-dimensional model for welding construction of a large-span and wide steel box girder according to claim 3 is characterized in that: Training of the Weld Stress Analyzer includes several branches of weld stress analysis, including: Collecting a sample grid specification deviation information set, a sample grid material deviation information set and a sample welding process parameter set, and obtaining welding stress test data after welding, and marking the obtained sample grid welding stress information set; Combining the sample grid specification deviation information set, the sample grid material deviation information set, the sample welding process parameter set and the sample grid welding stress information set as a stress analysis training data set; A preset proportion of training data is randomly selected multiple times from the stress analysis training data set to train multiple welding stress analysis branches and obtain a welding stress analyzer.

5. The system for rapidly constructing a three-dimensional model for welding construction of a large-span and wide steel box girder according to claim 3 is characterized in that: According to the sizes of the plurality of welding grid area sets and in combination with the number of the plurality of welding stress analysis branches, the number of quick analyses of each welding grid area is calculated, including: Obtaining minimum grid size information of the plurality of welding grid area sets; According to the grid size information of each welding grid area and the minimum grid size information, combined with the number of the multiple welding stress analysis branches, the grid fast analysis quantity is calculated to obtain multiple grid fast analysis quantity sets.

6. The system for rapidly constructing a three-dimensional model for welding construction of a large-span and wide steel box girder according to claim 1 is characterized in that: According to the plurality of grid welding stress information sets, specification deviation distributions and material deviation distributions, a plurality of welding grid identification information sets of the plurality of welding grid area sets are generated, and the foundation construction three-dimensional model is identified, including: According to the specification deviation distribution and the material deviation distribution, a plurality of grid specification deviation information sets and a plurality of grid material deviation information sets of the plurality of welding grid area sets are obtained by screening; The multiple grid specification deviation information sets and multiple grid material deviation information sets are used in combination with the multiple grid welding stress information sets to generate multiple welding grid identification information sets of the multiple welding grid area sets to identify the foundation construction three-dimensional model.

7. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby realizing the system for quickly building a three-dimensional model of large-span and wide-width steel box girder welding construction as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements a system for rapidly constructing a three-dimensional model for welding construction of a large-span and wide-width steel box girder as described in any one of claims 1 to 6.

Images