Intelligent design method and system for equivalent single beam of cable bearing bridge
By generating design parameters for an equivalent single beam of a cable-stayed bridge using a BP neural network model, the problems of difficulty in determining design parameters and long comparison time were solved, achieving efficient generation and comparison of design parameters and improving design efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA RAILWAY MAJOR BRIDGE RECONNAISSANCE & DESIGN INSTITUTE CO LTD
- Filing Date
- 2026-01-16
- Publication Date
- 2026-05-19
AI Technical Summary
Determining the equivalent single beam design parameters for cable-stayed bridges is difficult, the selection of alternatives takes a long time, and the design efficiency is low.
A BP neural network model is used to generate design parameters for an equivalent single beam based on basic design indices, and a finite element model is established to reduce reliance on the experience of designers.
Rapidly generate reasonable and accurate equivalent single beam design parameters, significantly improve the efficiency of scheme comparison and selection, reduce the difficulty of determining design parameters, and provide a reference for main beam design decisions.
Smart Images
Figure CN122065384A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of bridge design technology, specifically to an intelligent design method and system for an equivalent single beam of a cable-stayed bridge. Background Technology
[0002] In the preliminary design stage of cable-stayed bridges, designers first need to complete a preliminary design, followed by a comparison of different schemes. This process consumes a significant amount of manpower. The design of the main girder is the most complex. To improve design efficiency, the specific structure of the main girder can be disregarded in the preliminary design; instead, it can be designed as an equivalent single girder. However, determining the design parameters of this equivalent single girder often relies on the designer's experience, making it difficult to determine. Furthermore, when comparing multiple schemes, different equivalent single girder design parameters need to be calculated and compared, resulting in lengthy comparison times and low design efficiency. Summary of the Invention
[0003] This application provides an intelligent design method and system for the equivalent single beam of a cable-stayed bridge, which solves the technical problems of difficulty in determining the design parameters of the equivalent single beam and long time for scheme comparison in related technologies.
[0004] This application provides an intelligent design method for an equivalent single beam of a cable-stayed bridge, which includes the following steps: The basic design parameters for cable-stayed bridges are set, including the number of railway lanes, the number of highway lanes, the reference wind speed at the bridge site, the main girder form, the main girder material, the bridge type, and the main girder segment length. Based on the BP neural network model, the basic design indicators are used to generate the equivalent single beam design parameters of the cable-stayed bridge. The design parameters include cross-sectional properties, dead load intensity, and equivalent torsional mass. A finite element model of the equivalent single beam is established based on the design parameters of the equivalent single beam.
[0005] In one implementation, the process of establishing the BP neural network model includes: A dataset was established based on the design schemes of multiple cable-stayed bridges, the dataset including the design schemes of each of the cable-stayed bridges. x Tags and y The label, the x The labels are the basic design parameters for each of the cable-stayed bridges. y The labels represent the design parameters of the equivalent single beam for each of the cable-bearing bridges described above. The dataset is used for training to obtain a BP neural network model for predicting the design parameters.
[0006] In one embodiment, the x Labels and descriptions yThe constant load intensity in the label is extracted from the design scheme of the cable-stayed bridge.
[0007] In one embodiment, the y The cross-sectional properties and equivalent torsional mass in the label are calculated based on the unit load method: A finite element model of the main beam is established based on the design scheme of the cable-stayed bridge. Equal and opposite cross-sectional forces are applied to both ends of the finite element model to obtain the cross-sectional properties of the equivalent single beam. The equivalent torsional mass is calculated based on the cross-sectional properties of the equivalent single beam.
[0008] In one embodiment, applying equal and opposite cross-sectional forces at both ends of the finite element model to obtain the cross-sectional properties of the equivalent single beam includes: Equal and opposite axial tensile forces are applied to both ends of the finite element model, and the relative axial displacement between the two ends of the finite element model is calculated to obtain the equivalent cross-sectional area of the equivalent single beam. Equal and opposite vertical bending moments are applied to both ends of the finite element model, and the relative vertical displacements at both ends of the finite element model are calculated to obtain the equivalent vertical bending moment of inertia of the equivalent single beam. Equal and opposite transverse bending moments are applied to both ends of the finite element model, and the relative transverse displacements at both ends of the finite element model are calculated to obtain the equivalent transverse bending moment of inertia of the equivalent single beam. Equal and opposite torques are applied to both ends of the finite element model, and the relative torsional angles between the two ends of the finite element model are calculated to obtain the equivalent torsional moment of inertia of the equivalent single beam.
[0009] In one embodiment, the formula for calculating the equivalent cross-sectional area is: ; The formula for calculating the equivalent vertical bending moment of inertia is as follows: ; The formula for calculating the equivalent lateral bending moment of inertia is as follows: ; The formula for calculating the equivalent torsional moment of inertia is as follows: ; in, These are the axial tensile force, vertical bending moment, lateral bending moment, and torque applied to the finite element model, respectively. l The total length of the main beam; These are the elastic modulus and Poisson's ratio of the main beam material, respectively. for N Axial displacement of one end of the main beam relative to the other end under load; for Vertical displacement of one end of the main beam relative to the other end under action; for Lateral displacement of one end of the main beam relative to the other end under action; for T The torsional angle of one end of the main beam relative to the other end under action.
[0010] In one embodiment, calculating the equivalent torsional mass based on the cross-sectional properties of the equivalent single beam includes: The calculation formula is: ; in, These are the density of the main beam material and the spacing between main beam sections, respectively.
[0011] In one implementation, training the BP neural network model based on the dataset to predict the design parameters includes: Based on the above x The system is trained using the number of railway lanes, number of highway lanes, reference wind speed at the bridge site, main girder type, main girder material, and bridge type listed in the labels to obtain a model for predicting the bridge. y The first BP neural network model for the cross-sectional characteristics of the label; Based on the above x The system is trained using the number of railway lanes, number of highway lanes, reference wind speed at the bridge site, main girder type, main girder material, and bridge type listed in the labels to obtain a model for predicting the bridge. y The second BP neural network model for the dead load intensity in the label; the dead load intensity includes the self-weight of the main beam, the dead load of the second phase of the railway, the dead load of the second phase of the highway, and the weight of ancillary facilities; Based on the above x The system is trained using the labels for the number of railway lanes, highway lanes, main girder type, main girder material, bridge type, and main girder span length to obtain a model for predicting the bridge. y The third BP neural network model for equivalent torsional mass in the label.
[0012] In one embodiment, the sizes of the first BP neural network model and the second BP neural network model are: The activation function used is the ReLU function; the size of the third BP neural network model is... The activation function used is the ReLU function.
[0013] This application also provides an intelligent design system for the equivalent single beam of a cable-stayed bridge, applying the intelligent design method for the equivalent single beam of a cable-stayed bridge as described in any of the above claims, which includes: The interactive module is configured to: set the basic design parameters of the cable-stayed bridge, including the number of railway lanes, the number of highway lanes, the reference wind speed at the bridge site, the main beam type, the main beam material, the bridge type, and the main beam segment length; The design parameter generation module is configured to generate the equivalent single beam design parameters of the cable-stayed bridge based on the basic design indicators using a BP neural network model. The design parameters include cross-sectional properties, dead load intensity, and equivalent torsional mass. The finite element model building module is configured to build a finite element model of the equivalent single beam based on the design parameters of the equivalent single beam.
[0014] The beneficial effects of the technical solutions provided in this application include: This application provides an intelligent design method for the equivalent single beam of a cable-stayed bridge. First, basic design indicators are set, and then the design parameters of the equivalent single beam are quickly generated based on a BP neural network model, thereby establishing a finite element model. This reduces the reliance on the experience of designers and lowers the difficulty of determining design parameters. Especially when it is necessary to compare different schemes, the method generates the corresponding design parameters of the equivalent single beam according to different basic design indicators, which greatly improves the efficiency of scheme comparison and provides a reference for the design decision of the main beam of the cable-stayed bridge. Attached Figure Description
[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 This is a flowchart illustrating the steps of an intelligent design method for an equivalent single beam of a cable-stayed bridge according to an embodiment of the present invention.
[0017] Figure 2 As shown in one embodiment of the present invention x Tags and Correspondence y A diagram of the label.
[0018] Figure 3 This is a schematic diagram of the finite element model of an equivalent single beam in one embodiment of the present invention.
[0019] Figure 4 This is a schematic diagram illustrating the difference rate based on manual design and the method in one embodiment of the present invention.
[0020] In the figure: 1. Model element; 2. Total constant load intensity; 3. Equivalent torsional mass point. Detailed Implementation
[0021] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.
[0022] This application provides an intelligent design method for the equivalent single beam of a cable-stayed bridge, which can solve the technical problems of difficulty in determining the design parameters of the equivalent single beam and long comparison time of the scheme in related technologies.
[0023] like Figure 1 As shown, Figure 1 This is a flowchart illustrating the steps of an intelligent design method for an equivalent single beam of a cable-stayed bridge according to an embodiment of the present invention.
[0024] This embodiment provides an intelligent design method for the equivalent single beam of a cable-stayed bridge, which includes the following steps: Step S1: Set the basic design parameters for cable-stayed bridges. The basic design parameters include the number of railway lanes, the number of highway lanes, the reference wind speed at the bridge site, the main beam type, the main beam material, the bridge type, and the main beam section length. Step S2: Based on the BP neural network model, the basic design indicators are used to generate the design parameters of the equivalent single beam of the cable-stayed bridge. The design parameters include cross-sectional properties, dead load intensity, and equivalent torsional mass. Step S3: Establish a finite element model of the equivalent single beam based on the design parameters of the equivalent single beam.
[0025] This embodiment provides an intelligent design method for the equivalent single beam of a cable-stayed bridge. First, basic design indicators are set, and then the design parameters of the equivalent single beam are quickly generated based on a BP neural network model, thereby establishing a finite element model. This reduces the reliance on the experience of designers and lowers the difficulty of determining design parameters. Especially when it is necessary to compare different schemes, the method generates corresponding design parameters of the equivalent single beam according to different basic design indicators, which greatly improves the efficiency of scheme comparison and provides a reference for the design decision of the main beam of the cable-stayed bridge.
[0026] The following provides a detailed explanation of each step.
[0027] A back propagation neural network (BP neural network) is a multi-layer feedforward artificial neural network. The structure of a BP neural network includes an input layer, one or more hidden layers, and an output layer. Each layer consists of multiple "neurons" (nodes), and layers are connected by weighted connections.
[0028] Its working principle is as follows: 1. Forward propagation: The input signal (such as basic design parameters) enters from the input layer, passes through the hidden layers, is weighted and summed layer by layer, and undergoes nonlinear transformation by applying activation functions, finally producing the result (such as the design parameters of an equivalent single beam) in the output layer. 2. Backward propagation (core learning mechanism): When there is an error between the actual output of the network and the expected output (i.e., the true value in the training data), the network will propagate the error from the output layer to the input layer and automatically adjust the connection weights and biases between neurons in each layer according to the magnitude of the error. 3. Iterative training: By repeatedly performing the cycle of "forward propagation → error calculation → back propagation → weight adjustment" with a large amount of sample data, the neural network gradually "learns" the complex mapping relationship between input features and output targets, ultimately achieving high-precision prediction capabilities.
[0029] In this application, the output equivalent single beam design parameters and the input basic design indicators are difficult to describe with simple formulas or linear regression. The BP neural network model is convenient for handling multiple inputs and multiple outputs.
[0030] In one embodiment, the process of establishing a BP neural network model includes: Step S201: Establish a dataset based on the design schemes of multiple cable-stayed bridges. The dataset includes the design schemes of each cable-stayed bridge. x Tags and y Label, x The labels represent the basic design specifications for each cable-stayed bridge. y The labels represent the design parameters of the equivalent single beam for each cable-stayed bridge. Specifically, cable-stayed bridges include cable-stayed bridges, suspension bridges, and cable-stayed-suspension combined system bridges.
[0031] Step S202: Train the BP neural network model based on the dataset to obtain a model for predicting design parameters.
[0032] Specifically, based on the established dataset, the three neural network models were trained multiple times to achieve a certain level of accuracy.
[0033] By using the above scheme, the existing real design schemes of cable-stayed bridges can be used as training datasets to quickly extract and summarize the design rules and experiences between basic design indicators and equivalent single beam design parameters. The resulting BP neural network model has strong applicability and replaces the process of relying on manual experience for calculation and analogy, so as to achieve high-speed and accurate prediction of design parameters and ensure that the output design parameters conform to engineering practice.
[0034] In one embodiment, in step S201, x Tags and yThe dead load intensity in the label is extracted from the design scheme of cable-stayed bridges.
[0035] In one embodiment, in step S201, y The cross-sectional properties and equivalent torsional mass in the label are calculated based on the unit load method: A finite element model of the main beam was established based on the design scheme of the cable-stayed bridge. Equal and opposite cross-sectional forces are applied at both ends of the finite element model to obtain the cross-sectional properties of an equivalent single beam. Calculate the equivalent torsional mass based on the cross-sectional properties of an equivalent single beam.
[0036] The above scheme provides a standard calculation method for cross-sectional properties and equivalent torsional mass, ensuring physical rationality.
[0037] In one embodiment, applying equal and opposite cross-sectional internal forces at both ends of the finite element model to obtain the cross-sectional properties of an equivalent single beam includes: Equal and opposite axial tensile forces are applied to both ends of the finite element model, and the relative axial displacement between the two ends of the finite element model is calculated to obtain the equivalent cross-sectional area of the equivalent single beam. Equal vertical bending moments of opposite directions are applied to both ends of the finite element model, and the relative vertical displacements at both ends of the finite element model are calculated to obtain the equivalent vertical bending moment of inertia of the equivalent single beam. Equal and opposite transverse bending moments are applied to both ends of the finite element model, and the relative transverse displacements at both ends of the finite element model are calculated to obtain the equivalent transverse bending moment of inertia of the equivalent single beam. Equal and opposite torques are applied to both ends of the finite element model, and the relative torsional angles at both ends of the finite element model are calculated to obtain the equivalent torsional moment of inertia of the equivalent single beam.
[0038] In one embodiment, the formula for calculating the equivalent cross-sectional area is: ; The formula for calculating the equivalent vertical bending moment of inertia is: ; The formula for calculating the equivalent lateral bending moment of inertia is: ; The formula for calculating the equivalent torsional moment of inertia is: ; in, These are the axial tensile force, vertical bending moment, lateral bending moment, and torque applied to the finite element model, respectively. l The total length of the main beam; These are the elastic modulus and Poisson's ratio of the main beam material, respectively. for N Axial displacement of one end of the main beam relative to the other end under load; for Vertical displacement of one end of the main beam relative to the other end under action; for Lateral displacement of one end of the main beam relative to the other end under action; for T The torsional angle of one end of the main beam relative to the other end under action.
[0039] In one embodiment, calculating the equivalent torsional mass based on the cross-sectional properties of an equivalent single beam includes: The calculation formula is: ; in, These are the density of the main beam material and the spacing between main beam sections, respectively.
[0040] like Figure 2 As shown, Figure 2 This is a schematic diagram of the x-label and the corresponding y-label in one embodiment of the present invention.
[0041] In one embodiment, step S202, training a BP neural network model based on a dataset to predict design parameters, includes: Step S2021, based on x The system is trained using the number of railway lanes, number of highway lanes, reference wind speed at the bridge site, main girder type, main girder material, and bridge type listed in the labels to obtain data for prediction. y The first BP neural network model for the cross-sectional characteristics of the label; Step S2022, based on x The system is trained using the number of railway lanes, number of highway lanes, reference wind speed at the bridge site, main girder type, main girder material, and bridge type listed in the labels to obtain data for prediction. y The second BP neural network model for dead load intensity in the label; dead load intensity includes the self-weight of the main beam, the dead load of the second phase of the railway, the dead load of the second phase of the highway, and the weight of ancillary facilities; Step S2023, based on x The system is trained using the labels for the number of railway lanes, the number of highway lanes, the type of main girder, the material of the main girder, the type of bridge, and the length of the main girder segment to obtain data for prediction. y The third BP neural network model for equivalent torsional mass in the label.
[0042] Through the above scheme, three independent BP neural network models are trained to predict the cross-sectional properties, dead load intensity, and equivalent torsional mass of the equivalent single beam, respectively. Task decomposition makes each neural network model more focused, simpler in structure, more efficient in training, and easier to interpret, debug, and extend. At the same time, the three design parameters are ultimately used to establish a finite element model to achieve division of labor, collaboration, and parallel prediction.
[0043] In one embodiment, the size of the first BP neural network model and the second BP neural network model is The activation function used is the ReLU function; the size of the third BP neural network model is... The activation function used is the ReLU function.
[0044] This application also provides an intelligent design system for the equivalent single beam of a cable-stayed bridge, which applies the intelligent design method for the equivalent single beam of a cable-stayed bridge as described above, and includes: The interactive module is configured to set the basic design parameters for cable-stayed bridges, including the number of railway lanes, the number of highway lanes, the reference wind speed at the bridge site, the main beam type, the main beam material, the bridge type, and the main beam segment length. The design parameter generation module is configured to generate the equivalent single beam design parameters of the cable-stayed bridge based on the basic design indicators using a BP neural network model. The design parameters include cross-sectional properties, dead load intensity, and equivalent torsional mass. The finite element model building module is configured to: build a finite element model of an equivalent single beam based on the design parameters of the equivalent single beam.
[0045] The functions of each module have been explained above and will not be repeated here.
[0046] The following is a specific example for illustration.
[0047] The intelligent design method for the equivalent single beam of a cable-stayed bridge is as follows: Step S1: Designers set the basic design parameters of the cable-stayed bridge in the interactive module: number of railway lanes: 8; number of highway lanes: 4; reference wind speed at the bridge site: 28m / s; main girder type: steel truss girder; main girder material: Q370; bridge type: suspension bridge; main girder segment length: 14m.
[0048] Step S2: The design parameter generation module generates the equivalent single beam design parameters for cable-stayed bridges based on the BP neural network model.
[0049] Cross-sectional properties: Equivalent cross-sectional area: 2.9m² 2 Equivalent vertical bending moment of inertia: 208.5 m 4 Equivalent lateral bending moment of inertia: 550.5 m 4 Equivalent torsional moment of inertia: 90.1 m 4 ; Dead load intensity: Main beam self-weight: 418kN / m; Railway Phase II dead load: 80kN / m; Highway Phase II dead load: 270kN / m; Weight of auxiliary facilities: 15.5kN / m; Equivalent torsional mass: 9,611.3 t•m 2 .
[0050] Step S3: The finite element model building module builds a finite element model of the equivalent single beam based on the design parameters of the equivalent single beam.
[0051] like Figure 3 and Figure 4 As shown, where, Figure 3 This is a schematic diagram of the finite element model of an equivalent single beam in one embodiment of the present invention. Figure 4 This is a schematic diagram illustrating the difference rate based on manual design and the method in one embodiment of the present invention.
[0052] from Figure 4 It can be seen that the design parameters of the equivalent single beam generated by this method are within 5% of those of the manual design, indicating that the design parameters of the equivalent single beam generated by this method are reasonable and accurate, and the time required is only a few seconds, which greatly improves the design efficiency.
[0053] It should be noted that the sequence numbers of the embodiments in this application are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not represent a sequential order, nor do they limit "first," "second," and "third" to different types.
[0054] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.
[0055] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.
[0056] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.
[0057] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.
Claims
1. An intelligent design method for an equivalent single beam of a cable-stayed bridge, characterized in that, It includes the following steps: The basic design parameters for cable-stayed bridges are set, including the number of railway lanes, the number of highway lanes, the reference wind speed at the bridge site, the main girder form, the main girder material, the bridge type, and the main girder segment length. Based on the BP neural network model, the basic design indicators are used to generate the equivalent single beam design parameters of the cable-stayed bridge. The design parameters include cross-sectional properties, dead load intensity, and equivalent torsional mass. A finite element model of the equivalent single beam is established based on the design parameters of the equivalent single beam.
2. The intelligent design method for an equivalent single beam of a cable-stayed bridge as described in claim 1, characterized in that, The process of establishing the BP neural network model includes: A dataset was established based on the design schemes of multiple cable-stayed bridges, the dataset including the design schemes of each of the cable-stayed bridges. x Tags and y The label, the x The labels are the basic design parameters for each of the cable-stayed bridges. y The labels represent the design parameters of the equivalent single beam for each cable-stayed bridge. The dataset is used for training to obtain a BP neural network model for predicting the design parameters.
3. The intelligent design method for an equivalent single beam of a cable-stayed bridge as described in claim 2, characterized in that, The x Labels and descriptions y The constant load intensity in the label is extracted from the design scheme of the cable-stayed bridge.
4. The intelligent design method for an equivalent single beam of a cable-stayed bridge as described in claim 2, characterized in that, The y The cross-sectional properties and equivalent torsional mass in the label are calculated based on the unit load method: A finite element model of the main beam is established based on the design scheme of the cable-stayed bridge. Equal and opposite cross-sectional forces are applied to both ends of the finite element model to obtain the cross-sectional properties of the equivalent single beam. The equivalent torsional mass is calculated based on the cross-sectional properties of the equivalent single beam.
5. The intelligent design method for an equivalent single beam of a cable-stayed bridge as described in claim 4, characterized in that, Applying equal and opposite internal forces at both ends of the finite element model to obtain the cross-sectional properties of the equivalent single beam includes: Equal and opposite axial tensile forces are applied to both ends of the finite element model, and the relative axial displacement between the two ends of the finite element model is calculated to obtain the equivalent cross-sectional area of the equivalent single beam. Equal and opposite vertical bending moments are applied to both ends of the finite element model, and the relative vertical displacements at both ends of the finite element model are calculated to obtain the equivalent vertical bending moment of inertia of the equivalent single beam. Equal and opposite transverse bending moments are applied to both ends of the finite element model, and the relative transverse displacements at both ends of the finite element model are calculated to obtain the equivalent transverse bending moment of inertia of the equivalent single beam. Equal and opposite torques are applied to both ends of the finite element model, and the relative torsional angles between the two ends of the finite element model are calculated to obtain the equivalent torsional moment of inertia of the equivalent single beam.
6. The intelligent design method for an equivalent single beam of a cable-stayed bridge as described in claim 5, characterized in that, The formula for calculating the equivalent cross-sectional area is: ; The formula for calculating the equivalent vertical bending moment of inertia is as follows: ; The formula for calculating the equivalent lateral bending moment of inertia is as follows: ; The formula for calculating the equivalent torsional moment of inertia is as follows: ; in, These are the axial tensile force, vertical bending moment, lateral bending moment, and torque applied to the finite element model, respectively. l The total length of the main beam; These are the elastic modulus and Poisson's ratio of the main beam material, respectively. for N Axial displacement of one end of the main beam relative to the other end under load; for Vertical displacement of one end of the main beam relative to the other end under action; for Lateral displacement of one end of the main beam relative to the other end under action; for T The torsional angle of one end of the main beam relative to the other end under action.
7. The intelligent design method for an equivalent single beam of a cable-stayed bridge as described in claim 6, characterized in that, The calculation of the equivalent torsional mass based on the cross-sectional properties of the equivalent single beam includes: The calculation formula is: ; in, These are the density of the main beam material and the spacing between main beam sections, respectively.
8. The intelligent design method for an equivalent single beam of a cable-stayed bridge as described in claim 2, characterized in that, The step of training a BP neural network model based on the dataset to predict the design parameters includes: Based on the above x The system is trained using the number of railway lanes, number of highway lanes, reference wind speed at the bridge site, main girder type, main girder material, and bridge type listed in the labels to obtain a model for predicting the bridge. y The first BP neural network model for the cross-sectional characteristics of the label; Based on the above x The system is trained using the number of railway lanes, number of highway lanes, reference wind speed at the bridge site, main girder type, main girder material, and bridge type listed in the labels to obtain a model for predicting the bridge. y The second BP neural network model for the dead load intensity in the label; the dead load intensity includes the self-weight of the main beam, the dead load of the second phase of the railway, the dead load of the second phase of the highway, and the weight of ancillary facilities; Based on the above x The system is trained using the labels for the number of railway lanes, highway lanes, main girder type, main girder material, bridge type, and main girder span length to obtain a model for predicting the bridge. y The third BP neural network model for equivalent torsional mass in the label.
9. The intelligent design method for an equivalent single beam of a cable-stayed bridge as described in claim 8, characterized in that, The dimensions of the first BP neural network model and the second BP neural network model are The activation function used is the ReLU function; the size of the third BP neural network model is... The activation function used is the ReLU function.
10. An intelligent design system for the equivalent single beam of a cable-stayed bridge, employing the intelligent design method for the equivalent single beam of a cable-stayed bridge as described in any one of claims 1 to 9, characterized in that, It includes: The interactive module is configured to: set the basic design parameters of the cable-stayed bridge, including the number of railway lanes, the number of highway lanes, the reference wind speed at the bridge site, the main beam type, the main beam material, the bridge type, and the main beam segment length; The design parameter generation module is configured to generate the equivalent single beam design parameters of the cable-stayed bridge based on the basic design indicators using a BP neural network model. The design parameters include cross-sectional properties, dead load intensity, and equivalent torsional mass. The finite element model building module is configured to build a finite element model of the equivalent single beam based on the design parameters of the equivalent single beam.