A Smart Design Method for Composite Beam Bridge Deck Based on GEP+TCN+GA

Abstract

This invention provides an intelligent design method for composite beam bridge decks based on GEP+TCN+GA, belonging to the field of composite beam bridge deck design technology. This invention innovatively combines an improved gene expression programming algorithm with finite element simulation and static loading tests to achieve high-precision mathematical modeling of the boundary conditions of composite beam bridge decks, breaking through the limitations of traditional empirical formulas and significantly improving the automation and accuracy of boundary condition expression. By combining the efficient temporal prediction capability of the temporal convolutional network algorithm with the intelligent optimization framework of the genetic algorithm, a closed-loop intelligent design system is formed, capable of quickly and accurately predicting the mechanical response of the deck and finding the optimal design scheme under complex multi-parameter conditions. This not only improves design efficiency and accuracy and reduces simulation computational resource consumption, but also enhances the model's generalization ability and practical engineering applicability, fully meeting the demands of modern composite beam bridge deck structure design for intelligence, refinement, and efficiency.

Description

Technical Field

[0001] This invention relates to the field of composite beam bridge deck design technology, specifically to an intelligent design method for composite beam bridge decks based on GEP+TCN+GA. Background Technology

[0002] With the rapid development of transportation infrastructure, composite beam bridges, as a common bridge structure, directly impact their load-bearing capacity and service life through their panel design. Traditional composite beam bridge panel design methods rely heavily on empirical formulas or finite element simulations, which struggle to account for complex boundary conditions and nonlinear mechanical behavior under multiple working conditions. Furthermore, simulation calculations are costly and time-consuming. In practical engineering, panel stress involves various influencing factors, such as boundary constraint stiffness, rotational stiffness, and pressure membrane effects. These factors exhibit complex coupling relationships that traditional modeling methods cannot accurately describe. Moreover, existing designs lack a closed-loop optimization mechanism that integrates simulation and experimental data, hindering the intelligent and efficient design process and limiting the accuracy of composite beam bridge panel structure optimization design and its engineering application.

[0003] The prior art, disclosed in CN116776427A, presents a parametric modeling method and system for longitudinal stiffeners of a spatial curved panel in a steel box girder bridge. It includes the following steps: S10: Open the main window of the TeklaStructure platform and input the spatial geometric arrangement rules parameters of the longitudinal stiffener group of the curved panel; S20: Input the cross-sectional shapes of longitudinal stiffeners not found in the window definition library into the Tekla platform database; S30: Obtain the coordinate library of the intersection points of each longitudinal stiffener and the transverse diaphragm structure parts; S40: Input the opening shape parameters of the longitudinal stiffeners corresponding to the cross-section of the longitudinal stiffeners from the window. While it can intelligently design the bridge deck, it cannot describe the coupling relationships under complex working conditions, resulting in insufficient intelligence and flexibility, and making it difficult to meet the design requirements for intelligence and efficiency.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent design method for composite beam bridge decks based on GEP+TCN+GA, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A smart design method for composite beam bridge deck based on GEP+TCN+GA, the specific steps of which include:

[0008] S1: Construct a finite element model of the composite beam bridge, simulate it, construct a boundary condition database for the composite beam bridge deck based on the simulation results, and construct a calculation model for the boundary conditions of the composite beam bridge deck based on the GEP algorithm and the boundary condition database.

[0009] S2: Construct composite beam bridge deck specimens and conduct multi-parameter static loading tests to reflect the pressure membrane effect during the stress process of composite beam bridge decks, and revise the calculation model of the boundary conditions of composite beam bridge decks based on the test data.

[0010] S3: Simulate the stress process of composite beam bridge deck based on the modified calculation model, and construct a mechanical performance database of composite beam bridge deck based on the simulation results;

[0011] S4: Construct the TCN algorithm model, and based on the TCN algorithm model and the mechanical performance database of composite beam bridge deck, simulate and predict the stress process of composite beam bridge deck.

[0012] S5: Establish the optimization design framework of the GA algorithm, and embed the calculation model of the boundary conditions of the composite beam bridge deck and the TCN algorithm model into the GA algorithm. Evaluate the fitness of the boundary conditions and mechanical properties of the composite beam bridge deck, and search for the optimal design scheme based on the evaluation results to complete the intelligent design of the composite beam bridge deck.

[0013] Preferably, in step S1, the boundary conditions include lateral constraint stiffness, lateral constraint eccentricity, and rotational constraint stiffness.

[0014] When constructing a computational model for the boundary conditions of a composite beam bridge deck using the GEP algorithm, the least squares method, tournament algorithm, and population update strategy are used to improve the GEP algorithm. The specific logic is as follows:

[0015] The real constants in the GEP algorithm are fitted using the least squares method;

[0016] The tournament algorithm is used to enhance the population selection pressure and diversity in the GEP algorithm, and the tournament size is set in the range of 3 to 7.

[0017] The population update strategy is used to improve the global search capability and convergence speed of the GEP algorithm, and the population size in the population update strategy is set in the range of 50 to 200.

[0018] Preferably, the calculation model expression for the boundary conditions of the composite beam bridge deck is as follows:

[0019] BC i =c i ·f(P i )

[0020] In the formula BC i c represents the parameter size of the i-th group of boundary condition combinations. i f(P) represents the real constant corresponding to the i-th set of boundary conditions. i P represents the basic design function for the i-th set of boundary conditions. i The vector represents the i-th group of boundary conditions, where the subscript i indicates the index of the boundary condition, and m indicates the total number of boundary conditions.

[0021] Preferably, in step S2, the variable parameters during the static loading test include lateral constraint stiffness, lateral constraint eccentricity, rotational constraint stiffness, plate thickness, and reinforcement ratio.

[0022] The pressure film effect is expressed as:

[0023]

[0024] In the formula σ p Represents the additional stress on the pressure membrane, ∈ p k represents the strain generated by the pressure membrane. p k represents the sensitivity coefficient for the pressure film effect. p ∈[0.1,0.5], where ∈0 represents the critical strain threshold and β represents the coefficient of the quadratic term;

[0025] The revised calculation model for the boundary conditions of the composite beam bridge deck is expressed as follows:

[0026] BC i ′=c i ·f(P i )+a i ·σ p

[0027] In the formula BC i ′ represents the parameter size of the modified i-th group of boundary conditions, a i a represents the sensitivity coefficient of the i-th group of boundary condition parameters to the pressure film effect. i ∈[0.05,0.3].

[0028] Preferably, in step S3, the mechanical performance database of the composite beam bridge deck is constructed based on the simulation results, including: the parameter values ​​of the modified boundary conditions, the additional stress of the pressure membrane, the strain generated by the pressure membrane, and the deformation rate of the composite beam bridge deck.

[0029] Preferably, in step S4, the input to the TCN algorithm model is a database of the mechanical properties of the composite beam bridge deck. The TCN model structure consists of 4 to 6 convolutional layers, including causal convolutional layers and dilated convolutional layers. It contains residual modules to alleviate the gradient vanishing problem, and the convolutional kernels use an adaptive dilation coefficient, which is calculated as follows:

[0030]

[0031] In the formula d l Let represent the dilation coefficient of the l-th convolutional layer, γ represent the growth factor, γ∈[1.5,2], and d base This represents the initial expansion coefficient. This indicates rounding down to the nearest integer.

[0032] Preferably, in step S5, when evaluating the fitness of the boundary conditions and mechanical properties of the composite beam bridge deck, the initial population of the GA algorithm is set based on the design parameters, which include: the number of main beams, the size of the main beams, the spacing between transverse diaphragms, and the stiffness of the transverse diaphragms, and the design scheme is encoded into a multidimensional parameter vector.

[0033] Preferably, when evaluating the fitness of the boundary conditions and mechanical properties of composite beam bridge decks, the fitness function expression is:

[0034]

[0035] In the formula, F represents the fitness score, w1, w2, and w3 are all weighting coefficients, and w1 + w2 + w3 = 1, P represents the bearing capacity of the design scheme, and P req δ represents the load-bearing capacity requirement, v represents the deformation of the design scheme, and v represents the deformation of the design scheme. limit M represents the deformation threshold, and M represents the material usage of the main beam in the design scheme. ref This indicates the reference material usage of the main beam;

[0036] After the evaluation is completed, the design scheme with the highest fitness score will be selected as the optimal design scheme.

[0037] Compared with the prior art, the beneficial effects of the present invention are:

[0038] This invention innovatively combines an improved gene expression programming algorithm with finite element simulation and static loading tests to achieve high-precision mathematical modeling of boundary conditions for composite beam bridge decks. This overcomes the limitations of traditional empirical formulas and significantly improves the automation and accuracy of boundary condition expression. By combining the efficient temporal prediction capabilities of temporal convolutional network algorithms with the intelligent optimization framework of genetic algorithms, a closed-loop intelligent design system integrating model building, performance prediction, and design optimization is formed. This system can quickly and accurately predict the mechanical response of the deck and find the optimal design scheme under complex multi-parameter conditions. This method not only improves design efficiency and accuracy and reduces simulation computational resource consumption, but also enhances the model's generalization ability and practical engineering applicability, fully meeting the demands of modern composite beam bridge deck structure design for intelligence, refinement, and efficiency. Attached Figure Description

[0039] Figure 1This is a schematic diagram of the overall method flow of the present invention;

[0040] Figure 2 This is a schematic diagram illustrating the fitting error between the computational model of this invention and traditional empirical formulas;

[0041] Figure 3 This diagram illustrates the prediction errors of the TCN algorithm model of this invention and the traditional RNN algorithm model. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0043] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0044] Example:

[0045] Please see Figures 1-3 The present invention provides a technical solution:

[0046] A smart design method for composite beam bridge deck based on GEP+TCN+GA, the specific steps of which include:

[0047] S1: Construct a finite element model of the composite beam bridge, simulate it, construct a boundary condition database for the composite beam bridge deck based on the simulation results, and construct a calculation model for the boundary conditions of the composite beam bridge deck based on the GEP algorithm and the boundary condition database.

[0048] In step S1, the boundary conditions include lateral constraint stiffness, lateral constraint eccentricity, and rotational constraint stiffness.

[0049] When constructing a computational model for the boundary conditions of a composite beam bridge deck using the GEP algorithm (i.e., gene expression programming algorithm), the least squares method, tournament algorithm, and population update strategy are used to improve the GEP algorithm. The specific logic is as follows:

[0050] The real constants in the GEP algorithm are fitted using the least squares method;

[0051] The tournament algorithm is used to enhance the population selection pressure and diversity in the GEP algorithm, and the tournament size is set in the range of 3 to 7.

[0052] The population update strategy is used to improve the global search capability and convergence speed of the GEP algorithm, and the population size in the population update strategy is set in the range of 50 to 200.

[0053] Specifically, finite element models can be constructed using tools such as ANSYS to generate simulation data under different boundary conditions (lateral constraint stiffness / eccentricity, etc.) in batches. Then, an improved GEP algorithm (tournament selection + least squares fitting) is used to mine the nonlinear relationships between parameters, encoding the design parameters into genotypes (tree structure). Candidate expressions are generated through genetic operations (crossover, mutation), and finally, the optimal model is selected, thus constructing the expression for the computational model of the composite beam bridge deck boundary conditions. This method can consider different detailed features and working conditions of the structure, ensuring the model's broad representativeness and accuracy. Using the GEP algorithm to automatically mine boundary condition formulas to replace traditional empirical formulas improves the automation and accuracy of boundary condition modeling. Furthermore, incorporating least squares fitting, tournament selection, and population update strategies into the GEP algorithm improves the model's search efficiency and fitting accuracy, enhancing the model's practicality and accuracy.

[0054] The calculation model expression for the boundary conditions of the composite beam bridge deck is as follows:

[0055] BC i =c i ·f(P i )

[0056] In the formula BC i c represents the parameter size of the i-th boundary condition group. i f(P) represents the real constant corresponding to the i-th set of boundary conditions. i P represents the basic design function for the i-th set of boundary conditions. i The vector represents the i-th group of boundary conditions, where the subscript i indicates the index of the boundary condition, and m indicates the total number of boundary conditions.

[0057] As can be seen from this computational model, it is an explicit mathematical expression based on symbolic regression, used to describe the nonlinear relationship between the boundary condition parameters and design variables of composite beam bridge decks. It automatically extracts the mathematical expressions of boundary conditions from finite element simulation and experimental data using an improved GEP (Genetic Expression Programming) algorithm. The model expresses boundary conditions using a linear combination, but the basic design function itself can be a nonlinear function (such as a polynomial, exponential, or trigonometric function), thus capturing the complex coupling relationships between parameters. Where c... i The model can be obtained by fitting finite element data using an improved least squares method (e.g., Tikhonov regularization) and then back-calibrated using the results of static loading tests. The basic design functions can be determined automatically based on engineering or expert experience, or the optimal form can be automatically selected from a function library using the GEP algorithm. Compared to traditional boundary condition modeling methods (such as purely empirical formulas or black-box neural networks), this model directly outputs analytical mathematical formulas, eliminating the need for repeated calls to finite element software. Furthermore, due to the diversity of basic design functions, it can accurately fit complex mechanical phenomena such as pressure film effects, thus achieving a balance between computational efficiency and accuracy. Moreover, by training the initial model using finite element data and then correcting the data through subsequent static loading tests, a closed-loop modeling process driven by both simulation and experimentation is formed, resulting in stronger generalization ability than purely data-driven methods in traditional approaches.

[0058] S2: Construct composite beam bridge deck specimens and conduct multi-parameter static loading tests to reflect the pressure membrane effect during the stress process of composite beam bridge decks, and revise the calculation model of the boundary conditions of composite beam bridge decks based on the test data.

[0059] In step S2, during the static loading test, the varying parameters include lateral constraint stiffness, lateral constraint eccentricity, rotational constraint stiffness, plate thickness, and reinforcement ratio.

[0060] The pressure film effect is expressed as:

[0061]

[0062] In the formula σ p Represents the additional stress on the pressure membrane, ∈ p k represents the strain generated by the pressure membrane. p k represents the sensitivity coefficient for the pressure film effect. p ∈[0.1,0.5], where ∈0 represents the critical strain threshold and β represents the coefficient of the quadratic term.

[0063] As can be seen from the formula for calculating the pressure membrane, the first-order term in the first half of the formula is suitable for describing the small strain stage, i.e., ∈ pThe saturation effect of <∈0 occurs when stress growth slows down. The quadratic term in the latter half of the formula describes the large strain stage, i.e., ∈ p The geometric nonlinear strengthening effect is ≥∈0, where stress increases faster. The critical strain threshold is determined by the cracking threshold of concrete, generally taken as 0.002 to 0.003. The quadratic term coefficient is determined by the reinforcement ratio, reflecting the contribution of the steel reinforcement; that is, the higher the reinforcement ratio, the larger the quadratic term coefficient. Its specific value can be determined based on engineering experience.

[0064] The revised calculation model for the boundary conditions of the composite beam bridge deck is expressed as follows:

[0065] BC i ′=c i ·f(P i )+a i ·σ p

[0066] In the formula BC i ′ represents the parameter size of the modified i-th group of boundary conditions, a i a represents the sensitivity coefficient of the i-th group of boundary condition parameters to the pressure film effect. i ∈[0.05,0.3].

[0067] As can be seen from the revised calculation model, a is superimposed on the original calculation model. i ·σ p To reflect the influence of the pressure film effect, the initial value of the sensitivity coefficient can be determined based on engineering experience, and then updated by fitting based on the data of static loading test, which is used to quantify the response intensity of boundary conditions to the film effect.

[0068] When constructing composite beam bridge deck specimens, the specimens can be set as 2m×1.5m composite beam bridge deck specimens (e.g., steel beam + concrete slab). Then, adjust various parameters such as slab thickness and reinforcement ratio according to the orthogonal experimental table. When conducting static loading tests, an MTS hydraulic servo system can be used, with a reaction frame and distribution beam configured to achieve four-point bending loading. A 10×10 strain gauge grid is arranged at the bottom of the composite beam bridge deck to monitor the strain distribution generated by the pressure membrane. Then, displacement sensors are used to measure mid-span deflection and end slippage, and pressure sensors are used to measure support reaction force to calculate constraint stiffness.

[0069] The basic steps for the experiment should be set up in the following order:

[0070] Preloading: Apply 10% of the ultimate load to eliminate contact gaps;

[0071] Staged loading: Loading is performed in 20% increments until failure, with each stage lasting 5 minutes;

[0072] Data acquisition: Record strain, displacement, and crack development under each load level;

[0073] Post-processing: Extract the relationship curve between strain and additional stress generated by the pressure film, and fit k... p Parameters such as β.

[0074] In actual testing, adjustments can be made based on engineering requirements or expert experience.

[0075] In this embodiment, the modified computational model of the composite beam bridge deck boundary conditions and traditional empirical formulas are used to predict the boundary conditions. Traditional empirical formulas are mostly based on mechanical theories in structural engineering and summaries of numerous engineering experiments. They typically use linear or simplified nonlinear functions to express the relationship between the boundary condition parameters (such as constraint stiffness) and design variables (such as geometric dimensions and material properties) of the composite beam bridge deck, generally obtained through empirical fitting. Here, the lateral constraint stiffness is taken as the research object, and the traditional empirical formula uses a typical linear fitting model. The specific fitting results are shown in the table below:

[0076] Table 1: Fitting error of lateral constraint stiffness

[0077]

[0078]

[0079] From the table and Figure 2 As can be seen, the error of the improved GEP model is generally less than 1.5%, indicating that the model can accurately characterize complex boundary conditions and capture the coupling effects of multiple factors. It is superior to the traditional empirical formula and improves the accuracy of design parameters. The error of the traditional empirical formula is generally between 5% and 10% and is relatively large, reflecting that it is based on simplification assumptions and linear approximation. The error of the GEP model remains stable, while the error of the empirical formula fluctuates greatly in the high stiffness range, indicating that the empirical formula has poor stability under extreme working conditions. This shows that it is difficult to adapt to the real situation of variable boundary conditions and complex structures, and it is only suitable for rough estimation under complex working conditions such as pressure membranes.

[0080] This step, through the combination of refined experimental design and physical-driven modeling, enables the nonlinear thin film effect model to be applied to the elastic, plastic and failure stages simultaneously, achieving full-condition coverage. It can provide highly reliable input for subsequent TCN prediction and GA optimization, forming a complete technology chain of "experiment-simulation-optimization" and completing the intelligent design closed loop.

[0081] S3: Simulate the stress process of the composite beam bridge deck based on the modified computational model, and construct a mechanical performance database of the composite beam bridge deck based on the simulation results. The mechanical performance database of the composite beam bridge deck based on the simulation results includes: the magnitude of the modified boundary condition parameters, the additional stress of the pressure membrane, the strain generated by the pressure membrane, and the deformation rate of the composite beam bridge deck.

[0082] Specifically, the mechanical properties database can be constructed in the following order:

[0083] Parameter space definition: Determine the parameter range, such as lateral constraint stiffness: 500~2000kN / mm, plate thickness: 120~250mm, reinforcement ratio: 0.5%~2.5%, etc., which can be determined based on engineering experience. Latin hypercube sampling (LHS) is used to generate 10^4 sets of parameter combinations to ensure uniform spatial coverage.

[0084] Parallel simulation computation: ANSYS parametric scripts are deployed based on an HPC cluster, and various parameters are output;

[0085] Data cleaning and labeling: Remove non-convergent cases and add data labels.

[0086] This step, through big data generation driven by physical models and intelligent database architecture design, achieves high coverage of actual engineering scenarios, improves data completeness, provides high-quality input for subsequent TCN and GA, greatly improves the overall solution optimization efficiency, and can also form a reusable design experience library through data mining, thereby reducing the reliance on expert experience or engineering experience.

[0087] S4: Construct the TCN algorithm model, and based on the TCN algorithm model and the mechanical performance database of composite beam bridge deck, simulate and predict the stress process of composite beam bridge deck.

[0088] In step S4, the input to the TCN algorithm model (i.e., the temporal convolutional network algorithm) is the mechanical performance database of the composite beam bridge deck. The TCN model structure consists of 4 to 6 layers of causal convolutions and dilated convolutions, including residual modules to alleviate the gradient vanishing problem, and the convolution kernels use an adaptive dilation coefficient, which is calculated as follows:

[0089]

[0090] In the formula d l Let represent the expansion coefficient of the l-th layer, γ represent the growth factor, γ∈[1.5,2], and d base This represents the initial expansion coefficient. This indicates rounding down the value within the parentheses. Using an adaptive expansion coefficient can accurately capture the long-term temporal dependence of bridge deck stress (such as creep effects), helping to reduce the problems of insufficient long-term dependency modeling and difficulty in multi-scale feature fusion in traditional time-series prediction methods for bridge deck stress analysis.

[0091] In this embodiment, the TCN algorithm model with the above settings and the traditional RNN algorithm model are used to predict the simulated deformation of the finite element method. The traditional TCN algorithm model adopts the standard RNN algorithm model (i.e., the standard recurrent neural network model), with two hidden layers, the activation function is tanh, the output layer is a fully connected layer, the output is a single predicted value, there is no residual module, the loss function is the mean squared error, the optimizer is Adam, and the learning rate is set to 0.001. The specific prediction results are shown in the table below:

[0092] Table 2: Deformation prediction error in finite element simulation

[0093]

[0094]

[0095] From the table above and Figure 3 As can be seen, the TCN model with the residual module has a stable error of less than 1%, and the error remains basically unchanged with time. This indicates that TCN effectively captures the long-term time dependence and multi-scale characteristics of the structural response, and the prediction results are highly close to the finite element simulation. In contrast, the traditional RNN has a larger error (3%-7%), and the error increases with the time step. This reflects that RNN has a gradient vanishing problem in long sequence prediction, making it difficult to stably and accurately simulate complex nonlinear dynamic responses. Therefore, compared with the RNN model commonly used in existing technologies, in such complex working conditions and with long processing times, the TCN model has a smaller and more stable error, making it superior to traditional methods.

[0096] This step, by fusing adaptive expansion TCN with multimodal data, achieves higher detection accuracy and faster prediction speed compared to traditional time-series prediction methods. It can analyze and reveal the implicit relationship between design parameters and mechanical response, providing a closed-loop intelligent driving capability from data to decision for composite beam bridge deck design.

[0097] S5: Establish the optimization design framework of GA algorithm (i.e., genetic algorithm), and embed the calculation model of the boundary conditions of composite beam bridge deck and TCN algorithm model into GA algorithm. Evaluate the fitness of boundary conditions and mechanical properties of composite beam bridge deck, and search for the optimal design scheme based on the evaluation results to complete the intelligent design of composite beam bridge deck.

[0098] Specifically, the forward pass of data between models involves passing the candidate schemes (such as the main beam dimensions) generated by GA to the TCN model to predict the mechanical response; the backward correction involves feeding the fitness score back to the GEP model to dynamically adjust the boundary condition parameters, thereby forming a closed loop of "optimization-prediction-correction".

[0099] In step S5, when evaluating the fitness of the boundary conditions and mechanical properties of the composite beam bridge deck, the initial population of the GA algorithm is set based on the design parameters, including the number of main beams, main beam dimensions, diaphragm spacing, and diaphragm stiffness. The design scheme is then encoded into a multi-dimensional parameter vector. Using the modified boundary condition model to quickly calculate constraint reactions, instead of finite element analysis, significantly reduces the solution time.

[0100] When evaluating the fitness of the boundary conditions and mechanical properties of composite beam bridge decks, the fitness function expression is:

[0101]

[0102] In the formula, F represents the fitness score, w1, w2, and w3 are all weighting coefficients, and w1 + w2 + w3 = 1, P represents the bearing capacity of the design scheme, and P req δ represents the load-bearing capacity requirement, and δ represents the deformation of the design scheme. limit M represents the deformation threshold, and M represents the material usage of the main beam in the design scheme. ref This indicates the amount of main beam material used for reference.

[0103] The fitness function quantifies the load-bearing capacity, deformation, and material usage in a unified manner, and achieves dynamic trade-offs between objectives through weighting coefficients. For example, in the preliminary design stage, the safety threshold is prioritized as the optimization objective, with w1 = 0.7, w2 = 0.2, and w3 = 0.1. In the subsequent detailed design stage, the objectives need to be balanced with each other, with w1 = 0.4, w2 = 0.3, and w3 = 0.3.

[0104] After the evaluation is completed, the design scheme with the highest fitness score will be selected as the optimal design scheme.

[0105] In summary, this invention innovatively combines an improved gene expression programming algorithm with finite element simulation and static loading tests to achieve high-precision mathematical modeling of the boundary conditions of composite beam bridge decks. This overcomes the limitations of traditional empirical formulas and significantly improves the automation and accuracy of boundary condition expression. By combining the efficient temporal prediction capability of temporal convolutional network algorithms with the intelligent optimization framework of genetic algorithms, a closed-loop intelligent design system integrating model construction, performance prediction, and design optimization is formed. This system can quickly and accurately predict the mechanical response of the deck and find the optimal design scheme under complex multi-parameter conditions. This method not only improves design efficiency and accuracy and reduces simulation computational resource consumption, but also enhances the model's generalization ability and practical engineering applicability, fully meeting the demands of modern composite beam bridge deck structure design for intelligence, refinement, and efficiency.

[0106] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0107] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0108] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0109] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A smart design method for composite beam bridge decks based on GEP+TCN+GA, characterized in that, The specific steps include: S1: Construct a finite element model of the composite beam bridge, simulate it, construct a boundary condition database for the composite beam bridge deck based on the simulation results, and construct a calculation model for the boundary conditions of the composite beam bridge deck based on the GEP algorithm and the boundary condition database. Boundary conditions include lateral constraint stiffness, lateral constraint eccentricity, and rotational constraint stiffness; When constructing a computational model for the boundary conditions of a composite beam bridge deck using the GEP algorithm, the least squares method, tournament algorithm, and population update strategy are used to improve the GEP algorithm. The specific logic is as follows: The real constants in the GEP algorithm are fitted using the least squares method; The tournament algorithm is used to enhance the population selection pressure and diversity in the GEP algorithm, and the tournament size is set in the range of 3 to 7. The population update strategy is used to improve the global search capability and convergence speed of the GEP algorithm, and the population size in the population update strategy is set in the range of 50~200. The calculation model expression for the boundary conditions of the composite beam bridge deck is as follows: In the formula Indicates the first The magnitude of the parameters of the group boundary condition combination. Indicates the first The real constants corresponding to the set of boundary conditions, Indicates the first Basic design functions for group boundary conditions. Indicates the first Vector of boundary conditions, subscript Indices representing boundary conditions. Indicates the total number of boundary conditions; S2: Construct composite beam bridge deck specimens and conduct multi-parameter static loading tests to reflect the pressure membrane effect during the stress process of composite beam bridge deck, and revise the calculation model of the boundary conditions of composite beam bridge deck based on the test data. When conducting static loading tests, the varying parameters include lateral constraint stiffness, lateral constraint eccentricity, rotational constraint stiffness, plate thickness, and reinforcement ratio. The pressure film effect is expressed as: In the formula This indicates the additional stress on the pressure membrane. This represents the strain generated by the pressure membrane. The sensitivity coefficient representing the pressure film effect. , This represents the critical strain threshold. Represents the coefficient of the quadratic term; The revised calculation model for the boundary conditions of the composite beam bridge deck is expressed as follows: In the formula Indicates the corrected number The magnitude of the parameters of the group boundary conditions, Indicates the first Sensitivity coefficients of the set of boundary condition parameters to the pressure film effect. ; S3: Simulate the stress process of composite beam bridge deck based on the modified calculation model, and construct a mechanical performance database of composite beam bridge deck based on the simulation results; S4: Construct the TCN algorithm model, and based on the TCN algorithm model and the mechanical performance database of composite beam bridge deck, simulate and predict the stress process of composite beam bridge deck. S5: Establish the optimization design framework of the GA algorithm, and embed the calculation model of the boundary conditions of the composite beam bridge deck and the TCN algorithm model into the GA algorithm. Evaluate the fitness of the boundary conditions and mechanical properties of the composite beam bridge deck, and search for the optimal design scheme based on the evaluation results to complete the intelligent design of the composite beam bridge deck.

2. The intelligent design method for composite beam bridge deck based on GEP+TCN+GA according to claim 1, characterized in that: In step S3, the mechanical performance database of the composite beam bridge deck is constructed based on the simulation results, including: the parameter magnitude of the modified boundary conditions, the additional stress of the pressure membrane, the strain generated by the pressure membrane, and the deformation rate of the composite beam bridge deck.

3. The intelligent design method for composite beam bridge deck based on GEP+TCN+GA according to claim 2, characterized in that: In step S4, the input to the TCN algorithm model is a database of the mechanical properties of the composite beam bridge deck. The TCN model structure consists of 4 to 6 convolutional layers, including causal convolutional layers and dilated convolutional layers. It contains residual modules to alleviate the gradient vanishing problem, and the convolutional kernels use an adaptive dilation coefficient, which is calculated as follows: In the formula Indicates the first The dilation coefficient of the convolutional layer, Indicates growth factor, , This represents the initial expansion coefficient. This indicates rounding down to the nearest integer.

4. The intelligent design method for composite beam bridge deck based on GEP+TCN+GA according to claim 1, characterized in that: In step S5, when evaluating the fitness of the boundary conditions and mechanical properties of the composite beam bridge deck, the initial population of the GA algorithm is set based on the design parameters, which include: the number of main beams, the size of the main beams, the spacing between transverse diaphragms, and the stiffness of the transverse diaphragms. The design scheme is then encoded into a multidimensional parameter vector.

5. The intelligent design method for composite beam bridge deck based on GEP+TCN+GA according to claim 4, characterized in that: When evaluating the fitness of the boundary conditions and mechanical properties of composite beam bridge decks, the fitness function expression is: In the formula Indicates fitness score, , , Both represent weighting coefficients, and , Indicates the load-bearing capacity of the design scheme. Indicates load-bearing capacity requirements. Describing the deformation of the design scheme, Indicates the deformation threshold. This indicates the amount of material used in the main beams of the design scheme. This indicates the reference material usage of the main beam; After the evaluation is completed, the design scheme with the highest fitness score will be selected as the optimal design scheme.

Images