A mechanical response analysis method for long-span UHPC-steel box composite beams

Abstract

The present invention discloses a method for mechanical response analysis of large-span UHPC-steel box composite beams, comprising: obtaining the height ratio, UHPC prestress ratio, and slip coefficient of the composite beam to be analyzed; constructing a first finite element model based on the composite beam to be analyzed, and setting a slip unit between the upper steel box beam and the lower UHPC beam; assigning slip damping to the slip unit in each direction according to the slip coefficient, and assigning values ​​to the corresponding units in the first finite element model according to the material properties of the upper steel box beam and the lower UHPC beam; and performing a mechanical response analysis of the large-span UHPC-steel box composite beam by applying a uniformly distributed load to the top of the assigned first finite element model. The present invention simplifies the relatively complex load redistribution process into a set of slip coefficients, thereby facilitating a rapid and effective mechanical response analysis of the composite beam to be analyzed through simulation, thereby clarifying the stress characteristics of the structural system under normal use and ultimate bearing capacity conditions.

Description

Technical Field

[0001] The present invention relates to intelligent design analysis technology, and in particular to a mechanical response analysis method for a long-span UHPC-steel box composite beam. Background Art

[0002] For super-large main bridges with main spans exceeding 300m, in order to optimize the stress on the main beam and give full play to the material properties, a composite cross-section of a uniform-height steel box girder plus a variable-height UHPC was proposed based on the mechanical properties of the main beam. The remaining beam sections are uniform-height steel box girders. The main feature of this structural system is the upper steel box girder and the lower UHPC. The structure has reasonable stress, a novel system type, outstanding innovation, and broad application prospects.

[0003] Currently, research on this structural form is lacking. Because the steel-concrete components are joined after forming, the load-bearing mechanism differs from that of traditional structures. Consequently, the uniform-height steel box girder + variable-height UHPC laminated beam bridge structure exhibits unique characteristics, most notably complex variations in the bending and shear capacity distribution under varying prestressing and structural conditions. Therefore, a technical solution is needed to rapidly analyze the mechanical response of this structure. Summary of the Invention

[0004] In order to at least overcome the above-mentioned deficiencies in the prior art, the purpose of the present application is to provide a mechanical response analysis method for a long-span UHPC-steel box composite beam.

[0005] The present application provides a method for analyzing the mechanical response of a long-span UHPC-steel box composite beam, including:

[0006] Obtaining a height ratio and a UHPC prestress ratio of the composite beam to be analyzed, and converting the shear capacity of the shear connection member between the steel box girder and the UHPC girder in the composite beam to be analyzed into a slip coefficient based on the height ratio and the UHPC prestress ratio; the height ratio is the ratio of the height of the upper steel box girder and the lower UHPC girder of the composite beam to be analyzed; and the UHPC prestress ratio is the ratio between the prestress used in the lower UHPC girder and the maximum allowable prestress;

[0007] Constructing a first finite element model based on the composite beam to be analyzed, and setting a sliding unit between the upper steel box beam and the lower UHPC beam;

[0008] Assigning sliding damping in each direction to the sliding unit according to the sliding coefficient, and assigning values ​​to corresponding units in the first finite element model according to the material properties of the upper steel box girder and the lower UHPC beam;

[0009] The mechanical response analysis of the long-span UHPC-steel box composite beam was performed by applying a uniformly distributed load to the top of the first finite element model after assignment.

[0010] When implementing the embodiments of the present application, in order to facilitate the analysis of the composite beam to be analyzed, it is necessary to select appropriate analysis data. Among them, the height ratio and UHPC prestress ratio are parameters that have a greater impact on load redistribution. For shear connectors, since there are many optional structures and parameters for shear connectors, and the impact of load redistribution on different shear connectors under such structures is complex, in order to facilitate analysis, it is necessary to convert the shear capacity of the shear connector into a slip coefficient through the height ratio and UHPC prestress ratio. It should be understood that the slip coefficient in this application is an array containing damping in the three directions of x, y, and z, where x is the damping of the shear connector as a whole in the horizontal direction, y is the damping of the shear connector as a whole in the horizontal direction, and z is the vertical damping of the shear connector as a whole. The height ratio and UHPC prestress ratio are proposed to dedimensionalize the analysis and facilitate the corresponding analysis.

[0011] In an embodiment of the present application, after obtaining the slip coefficient, the mechanical response analysis can be performed by means of finite element simulation, wherein the shear connection member is simplified into at least one layer of sliding units in the constructed first finite element model. Since the relevant sliding properties of the shear connector have been simplified into three-way sliding damping through the above analysis process, it is only necessary to assign values ​​to the corresponding units to perform the mechanical response analysis. When performing the mechanical response analysis, the required uniformly distributed load can be applied to the top of the finite element model to obtain the corresponding stress, strain, displacement and other data, which belongs to the prior art and is not limited in the embodiment of the present application. Through the above technical solution, the embodiment of the present application simplifies the more complex load redistribution process into a set of slip coefficients, thereby facilitating the rapid and effective mechanical response analysis of the composite beam to be analyzed by simulation, thereby clarifying the stress characteristics of the structural system under normal use and ultimate bearing capacity.

[0012] In a possible implementation, converting the shear capacity of the shear connection member between the steel box girder and the UHPC girder in the composite beam to be analyzed into a slip coefficient according to the height ratio and the UHPC prestress ratio includes:

[0013] Obtaining shear parameters of the shear connection member; the shear parameters include a shear ratio and a depth of embedded parts; the shear ratio is the ratio of the shear stiffness of the steel structure to the shear stiffness of the concrete structure in the longitudinal section of the shear connection member; the embedded part depth is the maximum depth of the steel structure into the concrete structure in the shear connection member;

[0014] The height ratio, the UHPC prestress ratio, and the shear resistance parameter are input into a preset analysis model, and the slip coefficient output by the analysis model is obtained.

[0015] In a possible implementation, generating the analysis model includes:

[0016] constructing a scaled model specimen comprising a sample steel box girder and a sample UHPC beam, wherein the sample steel box girder is located above the sample UHPC beam, and the sample steel box girder is connected to the sample UHPC beam via a sample connecting member;

[0017] Obtaining a sample height ratio, a sample prestress ratio, a sample shear ratio, and a sample embedment depth of the scaled model specimen; the sample height ratio being the ratio of the heights of the sample steel box girder and the sample UHPC beam of the scaled model specimen; the sample prestress ratio being the ratio of the prestress used in the sample UHPC beam of the scaled model specimen to the maximum allowable prestress; the sample shear ratio being the ratio of the shear stiffness of the steel structure to the shear stiffness of the concrete structure in the longitudinal section of the sample connection member; and the sample embedment depth being the maximum depth of the steel structure into the concrete structure in the sample connection member;

[0018] Applying a uniformly distributed load to the top of the scaled model specimen, and recording a deflection change curve of the bottom of the scaled model specimen and a horizontal slip curve of the sample connecting member;

[0019] Constructing a second finite element model corresponding to the scaled model specimen, and setting a sample sliding unit between the sample steel box girder and the sample UHPC beam;

[0020] Assigning initial sliding damping in three orthogonal directions to the sample sliding element, and assigning values ​​to the corresponding elements in the second finite element model according to the material properties of the sample steel box girder and the sample UHPC beam;

[0021] Applying the same uniformly distributed load as that in the model test to the top of the second finite element model, and obtaining a sample deflection change curve and a sample horizontal slip curve of a sample slip unit at the bottom of the second finite element model;

[0022] When at least one of the first similarity and the second similarity does not meet the preset requirements, adjusting the sliding damping of the sample sliding unit and performing the calculation again until both the first similarity and the second similarity meet the preset requirements; the first similarity is the similarity between the sample deflection change curve and the deflection change curve; the second similarity is the similarity between the sample horizontal slip curve and the horizontal slip curve;

[0023] Recording the sliding damping of the sample sliding unit in three orthogonal directions when both the first similarity and the second similarity meet the preset requirements as the sample sliding coefficient;

[0024] Conduct multiple sets of scaled model specimen tests and finite element model calculations to obtain multiple sets of sample slip coefficients, sample height ratios, sample prestress ratios, sample shear ratios, and sample burial depths;

[0025] The sample height ratio, sample prestress ratio, sample shear ratio and sample burial depth are used as data input, and the sample slip coefficient is used as data output to train a neural network model to form the analysis model.

[0026] In a possible implementation, adjusting the sliding damping of the sample sliding unit includes:

[0027] Setting adjustment ranges centered on the initial slip damping for the slip damping in three orthogonal directions;

[0028] During adjustment, the slip damping is randomly selected within the corresponding adjustment range. The closer the value is to the initial slip damping, the higher the random weight.

[0029] In a possible implementation, the adjustment interval is a normally distributed interval centered on the initial slip damping.

[0030] In a possible implementation, calculating the first similarity and the second similarity includes:

[0031] calculating the cosine similarity between the sample deflection change curve and the deflection change curve as the first similarity;

[0032] The cosine similarity between the sample horizontal slip curve and the horizontal slip curve is calculated as the second similarity.

[0033] In one possible implementation, training a neural network model to form the analysis model includes:

[0034] Constructing a neural network model, wherein the input layer of the neural network model includes four input neuron nodes, one output neuron node and multiple hidden neuron nodes;

[0035] Construct the weights from the input neuron node to the hidden neuron node and the weights from the hidden neuron node to the output neuron node;

[0036] Inputting the sample height ratio, sample prestress ratio, sample shear ratio and sample burial depth as data input into four input neuron nodes respectively, and recording output data of the output neuron node;

[0037] The loss function is used to calculate the difference between the output data and the sample slip coefficient and the weights are adjusted until the difference meets the expected requirements to complete the training.

[0038] In a possible implementation, performing a mechanical response analysis on the long-span UHPC-steel box composite beam by applying a uniformly distributed load to the top of the assigned first finite element model includes:

[0039] The mechanical response analysis is completed by calculating the deformation, stress, strain and deflection of each part under uniformly distributed load through the first finite element model.

[0040] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0041] The present invention provides a mechanical response analysis method for long-span UHPC-steel box composite beams. Through the above technical solution, the relatively complex load redistribution process is simplified to a set of slip coefficients, thereby facilitating rapid and effective mechanical response analysis of the composite beam to be analyzed through simulation, thereby clarifying the stress characteristics of the structural system under normal use and ultimate bearing capacity conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0043] Figure 1 This is a schematic diagram of the method steps of an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0045] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0046] Please refer to Figure 1 , which is a flow chart of a mechanical response analysis method for a large-span UHPC-steel box composite beam provided in an embodiment of the present invention. Furthermore, the mechanical response analysis method for a large-span UHPC-steel box composite beam may specifically include the contents described in the following steps S1 to S4.

[0047] S1: Obtaining a height ratio and a UHPC prestress ratio of the composite beam to be analyzed, and converting the shear capacity of the shear connection member between the steel box girder and the UHPC girder in the composite beam to be analyzed into a slip coefficient based on the height ratio and the UHPC prestress ratio; the height ratio is the ratio of the height of the upper steel box girder and the lower UHPC girder of the composite beam to be analyzed; and the UHPC prestress ratio is the ratio between the prestress used in the lower UHPC girder and the maximum allowable prestress;

[0048] S2: constructing a first finite element model based on the composite beam to be analyzed, and setting a sliding unit between the upper steel box beam and the lower UHPC beam;

[0049] S3: assigning sliding damping in each direction to the sliding element according to the sliding coefficient, and assigning values ​​to corresponding elements in the first finite element model according to the material properties of the upper steel box girder and the lower UHPC beam;

[0050] S4: Perform mechanical response analysis on the long-span UHPC-steel box composite beam by applying a uniformly distributed load to the top of the first finite element model after the assignment.

[0051] When implementing the embodiments of the present application, in order to facilitate the analysis of the composite beam to be analyzed, it is necessary to select appropriate analysis data. Among them, the height ratio and UHPC prestress ratio are parameters that have a greater impact on load redistribution. For shear connectors, since there are many optional structures and parameters for shear connectors, and the impact of load redistribution on different shear connectors under such structures is complex, in order to facilitate analysis, it is necessary to convert the shear capacity of the shear connector into a slip coefficient through the height ratio and UHPC prestress ratio. It should be understood that the slip coefficient in this application is an array containing damping in the three directions of x, y, and z, where x is the damping of the shear connector as a whole in the horizontal direction, y is the damping of the shear connector as a whole in the horizontal direction, and z is the vertical damping of the shear connector as a whole. The height ratio and UHPC prestress ratio are proposed to dedimensionalize the analysis and facilitate the corresponding analysis.

[0052] In an embodiment of the present application, after obtaining the slip coefficient, the mechanical response analysis can be performed by means of finite element simulation, wherein the shear connection member is simplified into at least one layer of sliding units in the constructed first finite element model. Since the relevant sliding properties of the shear connector have been simplified into three-way sliding damping through the above analysis process, it is only necessary to assign values ​​to the corresponding units to perform the mechanical response analysis. When performing the mechanical response analysis, the required uniformly distributed load can be applied to the top of the finite element model to obtain the corresponding stress, strain, displacement and other data, which belongs to the prior art and is not limited in the embodiment of the present application. Through the above technical solution, the embodiment of the present application simplifies the more complex load redistribution process into a set of slip coefficients, thereby facilitating the rapid and effective mechanical response analysis of the composite beam to be analyzed by simulation, thereby clarifying the stress characteristics of the structural system under normal use and ultimate bearing capacity.

[0053] In a possible implementation, converting the shear capacity of the shear connection member between the steel box girder and the UHPC girder in the composite beam to be analyzed into a slip coefficient according to the height ratio and the UHPC prestress ratio includes:

[0054] Obtaining shear parameters of the shear connection member; the shear parameters include a shear ratio and a depth of embedded parts; the shear ratio is the ratio of the shear stiffness of the steel structure to the shear stiffness of the concrete structure in the longitudinal section of the shear connection member; the embedded part depth is the maximum depth of the steel structure into the concrete structure in the shear connection member;

[0055] The height ratio, the UHPC prestress ratio, and the shear resistance parameter are input into a preset analysis model, and the slip coefficient output by the analysis model is obtained.

[0056] When implementing the embodiment of the present application, in order to achieve a simplified description of the corresponding slip of the shear connection member, in addition to the height ratio and the UHPC prestress ratio, it is necessary to obtain the shear parameters of the shear connection member itself. In the embodiment of the present application, the shear parameters used are the shear ratio and the embedded parts burial depth. Since the shear ratio will affect the overall shear redistribution state and the embedded parts burial depth will affect the overall shear capacity in the process of the shear connection member resisting shear slip, these two points are selected as shear parameters. For the shear ratio, in a longitudinal section of the shear connection member, the shear stiffness of the steel structure is obtained by multiplying the area of ​​the steel structure by the shear elastic modulus, and the shear stiffness of the steel structure is obtained by multiplying the area of ​​the concrete structure by the shear elastic modulus, and the ratio is calculated; and the embedded parts burial depth is calculated by the maximum depth of the steel structure into the concrete structure. In order to reduce the analytical impact of various complex factors, the embodiment of the present application uses a preset analytical model to perform a black box comprehensive analysis of these parameters to obtain the slip coefficient.

[0057] In a possible implementation, generating the analysis model includes:

[0058] constructing a scaled model specimen comprising a sample steel box girder and a sample UHPC beam, wherein the sample steel box girder is located above the sample UHPC beam, and the sample steel box girder is connected to the sample UHPC beam via a sample connecting member;

[0059] Obtaining a sample height ratio, a sample prestress ratio, a sample shear ratio, and a sample embedment depth of the scaled model specimen; the sample height ratio being the ratio of the heights of the sample steel box girder and the sample UHPC beam of the scaled model specimen; the sample prestress ratio being the ratio of the prestress used in the sample UHPC beam of the scaled model specimen to the maximum allowable prestress; the sample shear ratio being the ratio of the shear stiffness of the steel structure to the shear stiffness of the concrete structure in the longitudinal section of the sample connection member; and the sample embedment depth being the maximum depth of the steel structure into the concrete structure in the sample connection member;

[0060] Applying a uniformly distributed load to the top of the scaled model specimen, and recording a deflection change curve of the bottom of the scaled model specimen and a horizontal slip curve of the sample connecting member;

[0061] Constructing a second finite element model corresponding to the scaled model specimen, and setting a sample sliding unit between the sample steel box girder and the sample UHPC beam;

[0062] Assigning initial sliding damping in three orthogonal directions to the sample sliding element, and assigning values ​​to the corresponding elements in the second finite element model according to the material properties of the sample steel box girder and the sample UHPC beam;

[0063] Applying the same uniformly distributed load as that in the model test to the top of the second finite element model, and obtaining a sample deflection change curve and a sample horizontal slip curve of a sample slip unit at the bottom of the second finite element model;

[0064] When at least one of the first similarity and the second similarity does not meet the preset requirements, adjusting the sliding damping of the sample sliding unit and performing the calculation again until both the first similarity and the second similarity meet the preset requirements; the first similarity is the similarity between the sample deflection change curve and the deflection change curve; the second similarity is the similarity between the sample horizontal slip curve and the horizontal slip curve;

[0065] Recording the sliding damping of the sample sliding unit in three orthogonal directions when both the first similarity and the second similarity meet the preset requirements as the sample sliding coefficient;

[0066] Conduct multiple sets of scaled model specimen tests and finite element model calculations to obtain multiple sets of sample slip coefficients, sample height ratios, sample prestress ratios, sample shear ratios, and sample burial depths;

[0067] The sample height ratio, sample prestress ratio, sample shear ratio and sample burial depth are used as data input, and the sample slip coefficient is used as data output to train a neural network model to form the analysis model.

[0068] When implementing the embodiment of the present application, the samples required for analysis model training are obtained by scaled model testing and finite element simulation. Among them, the subsequent multiple groups of scaled model specimen tests need to be configured with scaled model specimens with different parameters such as different connectors, prestressing, height, etc. to increase the richness of the samples, which can reduce the specimen preparation and specimen testing time. The preferred scale ratio is 1:20. The deflection change curve and the horizontal slip curve can be obtained by loading the scaled model specimen. In general, the deflection is measured by a dial indicator, and the horizontal slip is measured by a micrometer.

[0069] In this embodiment, to obtain the slip parameters corresponding to the current scaled model test, a second finite element model is constructed and subjected to the same uniformly distributed load. The slip damping is then adjusted until the final calculated results match the test results. The slip damping at this point is the sample slip coefficient corresponding to the various parameters of the current scaled model test. Multiple rounds of testing and data sampling yield a large number of sample pairs, which can then be trained through a neural network model to form an analytical model.

[0070] In a possible implementation, adjusting the sliding damping of the sample sliding unit includes:

[0071] Setting adjustment ranges centered on the initial slip damping for the slip damping in three orthogonal directions;

[0072] During adjustment, the slip damping is randomly selected within the corresponding adjustment range. The closer the value is to the initial slip damping, the higher the random weight.

[0073] In a possible implementation, the adjustment interval is a normally distributed interval centered on the initial slip damping.

[0074] When implementing the embodiment of the present application, in order to realize the automated process of adjusting the slip damping, it is necessary to construct an adjustment interval, wherein the adjustment interval is a data interval that satisfies the normal distribution, and the center of the interval is the initial slip damping. Randomly taking values ​​in the data interval of the normal distribution can ensure that the data offset is not too large.

[0075] In a possible implementation, calculating the first similarity and the second similarity includes:

[0076] calculating the cosine similarity between the sample deflection change curve and the deflection change curve as the first similarity;

[0077] The cosine similarity between the sample horizontal slip curve and the horizontal slip curve is calculated as the second similarity.

[0078] In one possible implementation, training a neural network model to form the analysis model includes:

[0079] Constructing a neural network model, wherein the input layer of the neural network model includes four input neuron nodes, one output neuron node and multiple hidden neuron nodes;

[0080] Construct the weights from the input neuron node to the hidden neuron node and the weights from the hidden neuron node to the output neuron node;

[0081] Inputting the sample height ratio, sample prestress ratio, sample shear ratio and sample burial depth as data input into four input neuron nodes respectively, and recording output data of the output neuron node;

[0082] The loss function is used to calculate the difference between the output data and the sample slip coefficient and the weights are adjusted until the difference meets the expected requirements to complete the training.

[0083] In a possible implementation, performing a mechanical response analysis on the long-span UHPC-steel box composite beam by applying a uniformly distributed load to the top of the assigned first finite element model includes:

[0084] The mechanical response analysis is completed by calculating the deformation, stress, strain and deflection of each part under uniformly distributed load through the first finite element model.

[0085] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0087] The units described as separate components may or may not be physically separated. As units, it is obvious that a person of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0088] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or grid device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0090] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A mechanical response analysis method for long-span UHPC-steel box composite beams, characterized in that: include: Obtaining a height ratio and a UHPC prestress ratio of the composite beam to be analyzed, and converting the shear capacity of the shear connection member between the steel box girder and the UHPC girder in the composite beam to be analyzed into a slip coefficient based on the height ratio and the UHPC prestress ratio; the height ratio is the ratio of the height of the upper steel box girder and the lower UHPC girder of the composite beam to be analyzed; and the UHPC prestress ratio is the ratio between the prestress used in the lower UHPC girder and the maximum allowable prestress; Constructing a first finite element model based on the composite beam to be analyzed, and setting a sliding unit between the upper steel box beam and the lower UHPC beam; Assigning sliding damping in each direction to the sliding unit according to the sliding coefficient, and assigning values ​​to corresponding units in the first finite element model according to the material properties of the upper steel box girder and the lower UHPC beam; Performing a mechanical response analysis on the long-span UHPC-steel box composite beam by applying a uniformly distributed load to the top of the first finite element model after the assignment; Converting the shear capacity of the shear connection member between the steel box girder and the UHPC girder in the composite beam to be analyzed into a slip coefficient according to the height ratio and the UHPC prestress ratio includes: Obtaining shear parameters of the shear connection member; the shear parameters include a shear ratio and a depth of embedded parts; the shear ratio is the ratio of the shear stiffness of the steel structure to the shear stiffness of the concrete structure in the longitudinal section of the shear connection member; the embedded part depth is the maximum depth of the steel structure into the concrete structure in the shear connection member; Inputting the height ratio, the UHPC prestress ratio, and the shear resistance parameter into a preset analysis model, and obtaining the slip coefficient output by the analysis model; The generation of the analysis model includes: Obtain samples required for analytical model training through scaled model testing and finite element simulation; After multiple rounds of experiments and data sampling, a large number of sample pairs are obtained and then an analysis model is formed through neural network model training.

2. The mechanical response analysis method of a long-span UHPC-steel box composite beam according to claim 1 is characterized in that: The generation of the analysis model includes: constructing a scaled model specimen comprising a sample steel box girder and a sample UHPC beam, wherein the sample steel box girder is located above the sample UHPC beam, and the sample steel box girder is connected to the sample UHPC beam via a sample connecting member; Obtaining a sample height ratio, a sample prestress ratio, a sample shear ratio, and a sample embedment depth of the scaled model specimen; the sample height ratio being the ratio of the heights of the sample steel box girder and the sample UHPC beam of the scaled model specimen; the sample prestress ratio being the ratio of the prestress used in the sample UHPC beam of the scaled model specimen to the maximum allowable prestress; the sample shear ratio being the ratio of the shear stiffness of the steel structure to the shear stiffness of the concrete structure in the longitudinal section of the sample connection member; and the sample embedment depth being the maximum depth of the steel structure into the concrete structure in the sample connection member; Applying a uniformly distributed load to the top of the scaled model specimen, and recording a deflection change curve of the bottom of the scaled model specimen and a horizontal slip curve of the sample connecting member; Constructing a second finite element model corresponding to the scaled model specimen, and setting a sample sliding unit between the sample steel box girder and the sample UHPC beam; Assigning initial sliding damping in three orthogonal directions to the sample sliding element, and assigning values ​​to the corresponding elements in the second finite element model according to the material properties of the sample steel box girder and the sample UHPC beam; Applying the same uniformly distributed load as that in the model test to the top of the second finite element model, and recording the sample deflection change curve and the sample horizontal slip curve of the sample slip unit at the bottom of the second finite element model; When at least one of the first similarity and the second similarity does not meet the preset requirements, adjusting the sliding damping of the sample sliding unit and performing the calculation again until both the first similarity and the second similarity meet the preset requirements; the first similarity is the similarity between the sample deflection change curve and the deflection change curve of the bottom of the scaled model specimen; the second similarity is the similarity between the sample horizontal slip curve and the horizontal slip curve of the sample connecting member; Recording the sliding damping of the sample sliding unit in three orthogonal directions when both the first similarity and the second similarity meet the preset requirements as the sample sliding coefficient; Conduct multiple sets of scaled model specimen tests and finite element model calculations to obtain multiple sets of sample slip coefficients, sample height ratios, sample prestress ratios, sample shear ratios, and sample burial depths; The sample height ratio, sample prestress ratio, sample shear ratio and sample burial depth are used as data input, and the sample slip coefficient is used as data output to train a neural network model to form the analysis model.

3. The mechanical response analysis method of a long-span UHPC-steel box composite beam according to claim 2 is characterized in that: Adjusting the sliding damping of the sample sliding unit includes: Setting adjustment ranges centered on the initial slip damping for the slip damping in three orthogonal directions; During adjustment, the slip damping is randomly selected within the corresponding adjustment range. The closer the value is to the initial slip damping, the higher the random weight.

4. The mechanical response analysis method of a long-span UHPC-steel box composite beam according to claim 3 is characterized in that: The adjustment interval is a normally distributed interval centered on the initial slip damping.

5. The mechanical response analysis method of a long-span UHPC-steel box composite beam according to claim 2, characterized in that: The calculation of the first similarity and the second similarity includes: Calculating the cosine similarity between the sample deflection change curve and the deflection change curve at the bottom of the scaled model specimen as the first similarity; The cosine similarity between the sample horizontal slip curve and the horizontal slip curve of the sample connecting member is calculated as the second similarity.

6. The method for mechanical response analysis of a long-span UHPC-steel box composite beam according to claim 2, characterized in that: Training the neural network model to form the analysis model includes: Constructing a neural network model, wherein the input layer of the neural network model includes four input neuron nodes, one output neuron node and multiple hidden neuron nodes; Construct the weights from the input neuron node to the hidden neuron node and the weights from the hidden neuron node to the output neuron node; Inputting the sample height ratio, sample prestress ratio, sample shear ratio and sample burial depth as data input into four input neuron nodes respectively, and recording output data of the output neuron node; The loss function is used to calculate the difference between the output data and the sample slip coefficient and the weights are adjusted until the difference meets the expected requirements to complete the training.

7. The method for mechanical response analysis of a long-span UHPC-steel box composite beam according to claim 1, characterized in that: The mechanical response analysis of the long-span UHPC-steel box composite beam is performed by applying a uniformly distributed load to the top of the first finite element model after the assignment, including: The mechanical response analysis is completed by calculating the deformation, stress, strain and deflection of each part under uniformly distributed load through the first finite element model.

Images