A method for optimizing the strength of road and bridge steel formwork structure

Through multi-dimensional spatial mapping and random sampling technology, the parameter combination of road and bridge steel mold structure is analyzed and optimized, and the inaccurate prediction problem of traditional methods under complex load conditions is solved, which improves the accuracy and safety of the design and reduces costs.

CN118734417BActive Publication Date: 2024-11-05NANTONG HAIXIN ROAD & BRIDGE FORMWORK CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411226964.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-05
Estimated Expiration
2044-09-03

AI Technical Summary

Technical Problem

The traditional road-bridge steel mold structure strength optimization method relies on simple mathematical models and empirical formulas, and it is difficult to fully consider the interaction between complex design parameters and factors in load conditions, resulting in insufficient optimization results, neglecting the potential impact of key parameters, lacking flexibility and adaptation It is difficult to accurately predict especially under extreme load conditions, affects the safety and stability of the structure and increases maintenance costs.

Method used

By collecting design parameters and historical performance data, performing dimension recognition and multi-dimensional spatial mapping, constructing parameter grouping boundary diagrams, sorting parameter influence, using random sampling technology to simulate structural performance, and verifying extreme load conditions through search and iterative analysis of optimal parameter combinations. design feasibility and safety.

Benefits of technology

Improves design accuracy and reliability, enhances performance prediction capabilities under extreme load conditions, optimizes material use, ensures structure strength and durability, and reduces maintenance and repair costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118734417B_ABST
    Figure CN118734417B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of structural optimization, and specifically to a method for optimizing the strength of a road and bridge steel mold structure, the method comprising: collecting design parameters and historical performance data of the road and bridge steel mold structure, performing dimension recognition and multi-dimensional space mapping, converting the data into a multi-dimensional point set, and obtaining a multi-dimensional data mapping set through dimension expansion and space mapping of the data. In the present invention, the design parameters and historical performance data of the road and bridge steel mold structure are converted into a multi-dimensional point set through dimension recognition and multi-dimensional space mapping, the data dimension is expanded, a new perspective on the mutual influence between design parameters is provided, a parameter group boundary diagram is constructed after the similarity of data points is identified, the influence of each parameter is indicated by sorting, simulation and optimization are accurately guided, random sampling and iterative analysis of the optimal parameter combination are adopted, the design accuracy, reliability and prediction ability are improved, the use of materials is optimized, the structural strength and durability are guaranteed, and the design efficiency and economy are increased.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of structural optimization, and in particular to a method for optimizing the structural strength of a road and bridge steel mold. Background Art

[0002] The field of structural optimization technology focuses on improving the performance and cost-effectiveness of engineering structures by applying mathematical models, computer algorithms and engineering principles. In this field, the goal is to design or improve the structure so that it can achieve the best performance indicators, such as lightest weight, lowest cost or highest strength, while meeting all engineering requirements and constraints. Structural optimization technology is widely used in aerospace, automotive manufacturing, civil engineering and other fields, including in the early stages of design, which can greatly improve design quality and efficiency and reduce material and manufacturing costs.

[0003] Among them, the strength optimization method of road and bridge steel formwork structure refers to an optimization technology applied to steel formwork structure in road and bridge construction. The main purpose of this method is to improve the strength and durability of road and bridge steel formwork structure through optimized design, while reducing the weight of the structure and reducing material costs. Under the premise of ensuring safety and reliability, the effect of improving engineering efficiency and economy is achieved. During the optimization process, special attention is paid to the various load conditions encountered by the structure in actual use, such as static load, dynamic load and environmental impact, to ensure that the designed structure can remain stable and safe under various conditions.

[0004] In actual operation, traditional road and bridge steel formwork structural strength optimization methods rely on relatively simple mathematical models and empirical formulas. When dealing with complex design parameters and load conditions, it is difficult to fully refer to the interaction of various factors, resulting in inaccurate optimization results. Sometimes, the potential impact of key parameters is even ignored, increasing the number of iterations and costs of structural design. Traditional methods lack sufficient flexibility and adaptability when simulating and predicting the performance of structures in actual use, especially in the face of extreme load conditions. Due to the limitations of the model, it is difficult to accurately reflect the actual situation. In civil engineering, for specific road and bridge steel formwork structures, traditional optimization methods fail to fully predict the impact of dynamic loads caused by environmental changes, resulting in unsatisfactory performance in actual applications, which not only affects the safety and stability of the structure, but also increases maintenance and repair costs. Summary of the invention

[0005] The present application provides a method for optimizing the strength of road and bridge steel formwork structures, thereby solving the problem that traditional methods for optimizing the strength of road and bridge steel formwork structures rely on relatively simple mathematical models and empirical formulas in actual operations. When dealing with complex design parameters and load conditions, it is difficult to fully refer to the interaction of various factors, resulting in inaccurate optimization results. Sometimes, the potential impact of key parameters is even ignored, increasing the number of iterations and costs of structural design. Traditional methods lack sufficient flexibility and adaptability when simulating and predicting the performance of structures in actual use, especially in the face of predictions under extreme load conditions. Due to the limitations of the model, it is difficult to accurately reflect the actual situation. In civil engineering, for specific road and bridge steel formwork structures, traditional optimization methods fail to fully predict the impact of dynamic loads caused by environmental changes, resulting in performance in actual applications that does not meet expectations, which not only affects the safety and stability of the structure, but also increases maintenance and repair costs.

[0006] In view of the above problems, the present application provides a method for optimizing the structural strength of road and bridge steel formwork.

[0007] The present application provides a method for optimizing the strength of a road and bridge steel mold structure, wherein the method comprises the following steps:

[0008] S1: Collect the design parameters and historical performance data of road and bridge steel formwork structures, perform dimension recognition and multi-dimensional space mapping, transform the data into a multi-dimensional point set, and obtain a multi-dimensional data mapping set through data dimension expansion and space mapping;

[0009] S2: Optimizing the multidimensional data mapping set, grouping data points by identifying similarities, constructing parameter group boundaries and features using spatial proximity, and obtaining a parameter group boundary map;

[0010] S3: Based on the parameter grouping boundary diagram, a sorting operation is performed to arrange the parameters according to the structural strength influence, the influence is compared and the weight is assigned, and a parameter influence sorting table is generated;

[0011] S4: using the parameter influence ranking table, performing simulation operations, using random sampling techniques to simulate structural performance, setting simulation ranges and conditions, collecting analysis results, and obtaining a simulation test result set;

[0012] S5: performing optimization operations according to the simulation test result set, analyzing the optimal parameter combination through searching and iteration, defining optimization objectives and iteration thresholds, adjusting strategies, and constructing an optimal parameter combination solution;

[0013] S6: Based on the optimal parameter combination scheme, perform verification operations, simulate the design performance under extreme loads, define test conditions, perform static loading tests, analyze data, and establish design feasibility and safety assessment results.

[0014] Preferably, the multidimensional data mapping set includes a multidimensional representation of structural weight, cost and durability indicators, the parameter grouping boundary diagram includes the boundary divisions of load type, material properties and design specifications, the parameter influence ranking table includes material strength, cost efficiency and design impact ratings, the simulation test result set includes stress distribution, deformation and durability test result data, the optimal parameter combination scheme includes the adjustment of steel type, cross-sectional size and connection method selection, and the design feasibility and safety assessment results include performance under extreme temperature, vibration load and wind speed conditions.

[0015] Preferably, based on the parameter grouping boundary diagram, a sorting operation is performed to arrange parameters according to their structural strength influence, and the influence is compared and weights are assigned. The specific steps of generating a parameter influence sorting table are as follows:

[0016] S301: Based on the parameter grouping boundary diagram, analyzing the performance indicators and historical data of the parameters in the multiple groups, evaluating the potential impact of the parameters, including building a potential impact evaluation table with reference to the performance variability of the parameters under differentiated conditions;

[0017] S302: Based on the potential influence evaluation table, use decision tree logic to judge the potential positive and negative influences of multiple parameters on structural strength, determine the corresponding weights of each group of parameters by comparing the parameters with each other, and generate a parameter weight comparison table;

[0018] S303: Utilizing the parameter weight comparison table, the parameters in the group are sorted, and referring to the parameter weights and the potential for improving the structural performance, a parameter influence sorting table is formed that comprehensively reflects the parameter influences.

[0019] Preferably, the specific steps of using the parameter influence ranking table, performing simulation operations, using random sampling technology to simulate structural performance, setting simulation ranges and conditions, collecting analysis results, and obtaining a simulation test result set are as follows:

[0020] S401: Based on the data in the parameter influence ranking table, identify key parameters, set a random sampling range for the parameters, adopt a stratified sampling strategy, select key samples, and construct a key parameter sample set;

[0021] S402: Selecting sample points from the key parameter sample set, setting differentiated simulation conditions for the sample points using loop logic, including ambient temperature and load conditions, performing simulation tests on the sample points under each condition, recording test results, and generating a conditional simulation data set;

[0022] S403: Analyze the data in the conditional simulation data set, apply the comparative analysis method, evaluate the structural performance under differentiated parameter values, identify the best and worst performing parameter value ranges through comparative analysis, analyze the comprehensive results of the simulation test, and construct a simulation test result set.

[0023] Preferably, the comparative analysis method is based on the formula

[0024]

[0025] in, Adjusted average performance index, is the performance indicator value within each group, is the weight coefficient of the performance index, Score the system stability, Score the data completeness, is the data processing time, is the number of data points in the group, , , , is the adjustment factor.

[0026] Preferably, according to the simulation test result set, the optimization operation is performed, the optimal parameter combination is analyzed by searching and iterative analysis, the optimization target and iteration threshold are defined, the strategy is adjusted, and the specific steps of constructing the optimal parameter combination scheme are as follows:

[0027] S501: Based on the simulation test result set, the optimization goal is determined to be enhancing structural performance, by setting a starting parameter combination as a reference point, using a sequential search strategy to analyze the parameter space, identifying a parameter combination that preliminarily improves structural performance, and forming a starting parameter improvement plan;

[0028] S502: Based on the initial parameter improvement scheme, the parameter combination is refined by adopting a loop iteration logic, and the structural strength iterative optimization technology is applied to compare the structural performance by gradually adjusting the parameter values. If a better solution is found, the parameter combination is updated to generate a structural strength iterative optimization scheme;

[0029] S503: Utilize the structural strength iterative optimization scheme, iteratively fine-tune the parameter combination, optimize the structural performance with reference to the cost-effectiveness ratio, adopt a local search strategy to optimize the parameter values, lock in the parameter combination that achieves the best performance and cost balance, and construct the optimal parameter combination scheme.

[0030] Preferably, the structural strength iterative optimization technique is performed according to the formula

[0031]

[0032] in, is the optimal stress, is the force applied to the structure, is the load-bearing area of ​​the structure, is the stress concentration factor, which depends on the structure shape and loading conditions. is the safety factor of the structural material, is the elastic modulus of the material, reflecting the material's ability to resist deformation. is the fatigue attenuation coefficient, The designed service life of the structure.

[0033] Preferably, based on the optimal parameter combination scheme, the specific steps of performing verification operations, simulating design performance under extreme loads, defining test conditions, performing static loading tests, analyzing data, and establishing design feasibility and safety assessment results are as follows:

[0034] S601: According to the optimal parameter combination scheme, define test conditions including extreme wind speed, earthquake intensity and environmental factors affecting structural safety, execute test scenarios to cover potential extreme conditions, and build an extreme test condition framework;

[0035] S602: performing a simulated static loading test according to the extreme test condition framework, including applying a predetermined limit load to the road bridge steel formwork and monitoring its response, including displacement and stress distribution, evaluating the performance of the structure under adverse conditions, and generating a static load response record;

[0036] S603: Analyze the static load response record, evaluate the safety margin and performance stability of the structure under extreme conditions by comparing the design standard and the test results, determine the real-time application feasibility of the design, and obtain the design feasibility and safety assessment results.

[0037] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0038] Through dimension identification and multi-dimensional spatial mapping, the design parameters and historical performance data of the road and bridge steel formwork structure are converted into analyzable multi-dimensional point sets, effectively expanding the dimension of the data and performing spatial mapping, providing a new way to analyze the mutual influence between various design parameters. By identifying and grouping the similarities between data points, a parameter group boundary diagram is constructed, which not only increases the clarity of parameter analysis, but also directly indicates the potential influence of each parameter on the structural strength through the parameter influence ranking table, providing an accurate basis for subsequent simulation and optimization operations. The simulation operation uses random sampling technology to accurately simulate the structural performance under differentiated parameter values, and analyzes the optimal parameter combination through search and iteration methods, which not only improves the accuracy and reliability of the design, but also enhances the ability to predict performance under extreme load conditions, improves the efficiency and economy of road and bridge steel formwork structure design, optimizes material use, and ensures the strength and durability of the structure.

[0039] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The present invention provides a schematic diagram of the overall process of a method for optimizing the strength of a road and bridge steel mold structure;

[0041] Figure 2 The present invention proposes a specific flow chart of S1 of a method for optimizing the strength of a road and bridge steel formwork structure;

[0042] Figure 3 The present invention proposes a specific flow chart of S2 of a method for optimizing the strength of a road and bridge steel formwork structure;

[0043] Figure 4 The present invention proposes a specific flow chart of S3 of a method for optimizing the strength of a road and bridge steel formwork structure;

[0044] Figure 5 The present invention proposes a specific flow chart of S4 of a method for optimizing the strength of a road and bridge steel formwork structure;

[0045] Figure 6 The present invention proposes a specific flow chart of S5 of a method for optimizing the strength of a road and bridge steel formwork structure;

[0046] Figure 7 The present invention proposes a specific flow chart of S6 of a method for optimizing the structural strength of a road and bridge steel formwork. DETAILED DESCRIPTION

[0047] The present application provides a method for optimizing the strength of road and bridge steel formwork structures.

[0048] Application Overview

[0049] In the prior art, the traditional road and bridge steel formwork structure strength optimization method relies on relatively simple mathematical models and empirical formulas in actual operation. When dealing with complex design parameters and load conditions, it is difficult to fully refer to the interaction of various factors, resulting in inaccurate optimization results. Sometimes, the potential impact of key parameters is even ignored, increasing the number of iterations and costs of structural design. Traditional methods lack sufficient flexibility and adaptability when simulating and predicting the performance of structures in actual use, especially in the face of extreme load conditions. Due to the limitations of the model, it is difficult to accurately reflect the actual situation. In civil engineering, for specific road and bridge steel formwork structures, traditional optimization methods fail to fully predict the impact of dynamic loads caused by environmental changes, resulting in unsatisfactory performance in actual applications, which not only affects the safety and stability of the structure, but also increases maintenance and repair costs.

[0050] In response to the above technical problems, the overall idea of ​​the technical solution provided by this application is as follows:

[0051] like Figure 1 As shown, the present application provides a method for optimizing the strength of a road and bridge steel mold structure, wherein the method comprises the following steps:

[0052] S1; collect design parameters and historical performance data of road and bridge steel formwork structures, identify the dimensions of the information, convert the data into analyzable multidimensional point sets through multidimensional spatial mapping, expand the dimensions of the data and perform spatial mapping to obtain a multidimensional data mapping set;

[0053] S2; performing a segmentation operation on the multidimensional data mapping set, by identifying the similarities between data points, grouping them to analyze the mutual influence of multiple design parameters, using the spatial proximity of data points to group, optimizing the boundaries and characteristics of multi-parameter groups, and obtaining a parameter grouping boundary diagram;

[0054] S3: Based on the parameter grouping boundary diagram, a sorting operation is performed to arrange the parameters in multiple groups according to their potential influence on the structural strength, compare the influence of multiple groups of parameters, and assign weights according to their potential improvement space on the structural performance to generate a parameter influence sorting table;

[0055] S4; using the data in the parameter influence ranking table, perform simulation operations, and use random sampling technology to simulate the structural performance of multiple parameters under differentiated values, including setting the scope and conditions of the simulation test, collecting and analyzing the test results, and obtaining a simulation test result set;

[0056] S5; perform optimization operations according to the simulation test result set, use search and iteration methods to analyze the optimal parameter combination in the parameter space, define the optimization goal, set the iteration threshold and adjust the search strategy, and construct the optimal parameter combination solution;

[0057] S6; Based on the optimal parameter combination scheme, perform verification operations on the road and bridge steel molds, and test the feasibility and safety of their actual application by simulating the performance of the design under extreme load conditions, including defining test conditions, performing static loading tests and analyzing test data, and establishing design feasibility and safety assessment results.

[0058] The multidimensional data mapping set includes multidimensional representations of structural weight, cost and durability indicators. The parameter grouping boundary diagram includes the boundary divisions of load type, material properties and design specifications. The parameter influence ranking table includes material strength, cost efficiency and design impact ratings. The simulation test result set includes stress distribution, deformation and durability test result data. The optimal parameter combination scheme includes the adjusted steel type, cross-sectional size and connection method selection. The design feasibility and safety assessment results include performance under extreme temperature, vibration load and wind speed conditions.

[0059] Specifically, if Figure 2 As shown, the design parameters and historical performance data of the road and bridge steel mold structure are collected, dimension recognition and multi-dimensional space mapping are performed, the data is converted into a multi-dimensional point set, and a multi-dimensional data mapping set is obtained through the dimension expansion and space mapping of the data;

[0060] S101; collect the design parameters and historical performance data of the road and bridge steel formwork structure, preliminarily organize the road and bridge steel formwork structure data, mark the key information points, including material type, size specification, service life and performance index, and construct the execution process of the data mark set as follows;

[0061] The S101 sub-step is based on the design parameters and historical performance data of the road and bridge steel formwork structure, adopts a data sorting algorithm, uses the Python programming language combined with the Pandas library to clean and sort the data, uses the DataFrame structure to store the data set to ensure that the data is organized in a way that is easy to process, uses the dropna function to remove missing values ​​to ensure data integrity, uses the unique function to identify and mark material types, uses the size function to calculate size specifications, uses the max and min functions to determine the maximum and minimum values ​​of the service life respectively, uses the mean function to calculate the average value of the performance indicator, and uses the concat function to merge the processed data sets to generate a data tag set.

[0062] S102: Using the information in the data tag set, perform dimension recognition operations to determine the key dimensions of the data, including strength, durability, and cost. The dimensions are associated with the data points, and the execution process of generating a dimension association diagram is as follows;

[0063] Sub-step S102 uses the information in the data tag set, adopts the dimension identification algorithm, and uses the Python programming language combined with the Matplotlib library to perform visual analysis of dimensions and data points. The scatter function is used to create scatter plots for each key dimension, strength, durability, and cost in the chart to ensure the visual representation of the dimensions. The groupby function is used to group the data, using strength, durability, and cost as keywords, and the average value of each group is calculated. The plot function is used to draw a dimension association diagram to show the relationship between differentiated dimensions. The dimension association diagram is saved through the savefig function to generate a dimension association diagram.

[0064] S103: Map the data into a preset multidimensional space according to the dimensions and associations identified in the dimension association diagram. The data points occupy key positions in the multidimensional space. The execution process of constructing a multidimensional data mapping set is as follows;

[0065] In sub-step S103, based on the dimensions and associations identified in the dimensional association graph, a multidimensional data mapping algorithm is adopted, and the Python programming language is combined with the SciPy library to realize the mapping of data in a preset multidimensional space. The Multidimensional Scaling (MDS) method is used to input data points and the dimensional association graph to ensure the accurate position of each data point in the multidimensional space. The Euclidean function is used to calculate the Euclidean distance between data points to ensure accurate measurement of the distance. The fit_transform function is used to perform dimensionality reduction processing on the data and map it to a lower dimensional space for visualization and analysis. The distribution diagram of data points in the multidimensional space is drawn by the plot function to generate a multidimensional data mapping set.

[0066] Specifically, if Figure 3 As shown, the multidimensional data mapping set is optimized, the data points are grouped by identifying similarities, the parameter group boundaries and features are constructed by using spatial proximity, and the parameter group boundary map is obtained;

[0067] S201: Perform spatial proximity analysis on the data points in the multidimensional data mapping set, identify data points that are close to each other, and divide the data points into several groups according to spatial proximity to form a preliminary grouping process as follows;

[0068] In sub-step S201, the K-nearest neighbors (KNN) algorithm is used to perform spatial proximity analysis on the data points in the multidimensional data mapping set. The Scikit-learn library is used for implementation. First, the distance metric is selected as the Euclidean distance to calculate the distance between data points. The K value is set to 5, which means that each data point will be compared with its five nearest neighbors. A voting mechanism is used, that is, the group to which the data point belongs is determined by the group with the most data points among its five neighboring data points. Finally, the data points are divided into several groups according to spatial proximity to generate a preliminary grouping.

[0069] S202: Based on the preliminary draft of grouping, the similarity analysis of the data points in each group is refined, and the similarity of the reference dimensions, including the matching degree of the design concept and the use effect, is iteratively determined, and the execution process of generating the grouping refinement diagram is as follows;

[0070] In sub-step S202, a hierarchical clustering algorithm is used to refine the similarity analysis of data points within each group. The ward link method in the Scipy library is used to minimize the variance between all classes as the clustering criterion. The data points in the first draft of the grouping are iteratively clustered based on the matching dimension of design concept and usage effect. During the iteration, the distance threshold is set to half of the initial number of clusters to control the degree of clustering refinement. The hierarchical clustering dendrogram is used to assist in determining the optimal grouping boundary and generate a grouping refinement diagram.

[0071] S203: Based on the group refinement diagram, the design parameters and performance data in the group are analyzed to determine the mutual influence mode and characteristics of the parameters within the group, and the execution process of constructing the parameter group boundary diagram is as follows;

[0072] In sub-step S203, principal component analysis (PCA) and linear regression analysis are used to analyze the design parameters and performance data in the group refinement diagram. PCA is used to reduce the dimension of the data through the Scikit-learn library, and key feature parameters are extracted to simplify the subsequent linear regression analysis. The linear regression model is used to model the relationship between the extracted feature parameters and the performance data. The parameters of the regression model are set, including the regularization coefficient λ is set to 0.01 to prevent overfitting. The least squares method is used to calculate the optimal solution of the parameters. The model identifies the patterns and characteristics of the mutual influence between the design parameters and constructs a parameter grouping boundary diagram.

[0073] Specifically, if Figure 4 As shown, based on the parameter grouping boundary diagram, a sorting operation is performed to arrange the parameters according to the structural strength influence, compare the influence and assign weights, and generate a parameter influence sorting table;

[0074] S301; Based on the parameter grouping boundary diagram, the performance indicators and historical data of the parameters in multiple groups are analyzed, and the potential impact evaluation of the parameters is evaluated, including the performance variability of the reference parameters under differentiated conditions, and the execution process of constructing the potential impact evaluation table is as follows;

[0075] Based on the parameter grouping boundary diagram, sub-step S301 uses the multivariate linear regression analysis method to evaluate the potential impact of the performance indicators and historical data of parameters in multiple groups. It is implemented using Python's Statsmodels library, and the independent variables are set as the historical data and performance indicators of each parameter. The dependent variable is the performance variability of the parameter under differentiated conditions. A regression equation is set for each parameter, and the coefficient of the independent variable in the equation is determined. The coefficient value is obtained by least squares estimation, ensuring that the p value in the estimation process is less than 0.05 to verify the statistical significance of the model. The regression equation results of all parameters are integrated to generate a potential impact evaluation table.

[0076] S302: Based on the potential influence evaluation table, the decision tree logic is used to determine the potential positive and negative effects of multiple parameters on the structural strength, and the corresponding weights of each group of parameters are determined by comparing the parameters with each other. The execution process of generating the parameter weight comparison table is as follows;

[0077] In sub-step S302, based on the potential influence evaluation table, the decision tree algorithm is used to implement logical judgment using Python's Scikit-learn library to analyze the potential positive and negative effects of multiple parameters on structural strength. The data in the potential influence evaluation table is used as input, and the depth of the decision tree is set to 5 to control the complexity of the model and prevent overfitting. The information gain ratio is used to select the optimal segmentation attribute to ensure that the purity after each branch is improved. The impurity of each branch is evaluated by comparing the parameters with each other, and the corresponding weight of each parameter is determined according to its branch weight in the decision tree to generate a parameter weight comparison table.

[0078] S303: Using the parameter weight comparison table, the parameters in the group are sorted, and the parameter weights and the potential for improving the structural performance are referred to to form a parameter influence sorting table that comprehensively reflects the parameter influence. The execution process is as follows;

[0079] The S303 sub-step uses the parameter weight comparison table and a sorting algorithm, specifically a quick sorting algorithm, to sort the parameters within the group. The algorithm is executed using Python's Pandas library, reads the parameter weight comparison table data, uses the parameter weight as the sorting basis, and applies the quick sorting algorithm, which selects an element as a benchmark and reorders the sequence. All elements smaller than the benchmark value are placed in front of the benchmark, and all elements larger than the benchmark value are placed behind the benchmark. The sub-series of elements smaller than the benchmark value and the sub-series of elements larger than the benchmark value are recursively sorted. After the sorting is completed, a parameter influence sorting table that comprehensively reflects the parameter influence is formed based on the parameter weight and the potential for improving the structural performance.

[0080] Specifically, if Figure 5 As shown, the parameter influence ranking table is used to perform simulation operations, random sampling techniques are used to simulate structural performance, simulation ranges and conditions are set, analysis results are collected, and a simulation test result set is obtained;

[0081] S401: Based on the data in the parameter influence ranking table, identify key parameters, set a random sampling range for the parameters, adopt a stratified sampling strategy, select key samples, and construct a key parameter sample set. The execution process is as follows;

[0082] In sub-step S401, based on the data in the parameter influence ranking table, a stratified sampling strategy is adopted. The Python programming language is combined with the stats module of the SciPy library to set the random sampling range for the parameters. The random.choice function of the numpy library is used to set the random seed to ensure the randomness of the sampling. Stats.randint(low, high) is used to define the sampling range of each key parameter, where low and high represent the lower and upper limits of the parameter value, respectively. Stats.bernoulli(p).rvs(size) is used to simulate the probability of occurrence of each parameter, where p represents the probability of the parameter being selected and size represents the sample size. The sample sets of each parameter are merged using the vstack function of the numpy library to generate a sample set of key parameters.

[0083] S402: Select sample points from the key parameter sample set, use loop logic to set differentiated simulation conditions for the sample points, including ambient temperature and load conditions, perform simulation tests on the sample points under each condition, record the test results, and generate the conditional simulation data set. The execution process is as follows;

[0084] Sub-step S402 selects sample points from the key parameter sample set, adopts a conditional simulation algorithm, uses the Python programming language combined with the NumPy library to set the loop logic, sets differentiated simulation conditions for the sample points, uses the numpy.linspace function to generate a range sequence of ambient temperatures, and numpy.random.uniform (low, high, size) to generate a random value sequence for load conditions, where low and high define the minimum and maximum values ​​of the load, and size represents the number of generated values. A for loop is used to traverse each sample point, and each sample point is paired with the generated condition. A custom simulation test function is used to perform simulation tests under each condition, and the test results are recorded in a Pandas DataFrame to generate a conditional simulation data set.

[0085] S403: Analyze the data in the conditional simulation data set, apply the comparative analysis method, evaluate the structural performance under the differentiated parameter values, identify the best and worst performing parameter value ranges through comparative analysis, analyze the comprehensive results of the simulation test, and construct the simulation test result set. The execution process is as follows;

[0086] Sub-step S403 analyzes the data in the conditional simulation data set, adopts comparative analysis method, uses Python programming language combined with Pandas library and Matplotlib library, applies comparative analysis method, evaluates the structural performance under differentiated parameter values, uses Pandas' groupby function to group the data set according to the differentiated parameters, and calculates the average performance index of each group, uses matplotlib.pyplot's bar function to draw a bar chart of the average performance index of each group to show the structural performance under differentiated parameter values, uses Pandas' idxmax and idxmin functions to find the parameter value ranges with the best and worst performance respectively, organizes and summarizes the analysis results, and generates a simulation test result set.

[0087] The comparative analysis method is based on the formula

[0088]

[0089] in, Adjusted average performance index, is the performance indicator value within each group, is the weight coefficient of the performance index, Score the system stability, Score the data completeness, is the data processing time, is the number of data points in the group, , , , is the adjustment factor.

[0090] The execution process is as follows;

[0091] Calculate the weighted average of the performance index values ​​within each group to reflect the importance of different performance indicators. Then, add the system stability score and data integrity score to consider the impact of external factors on the performance indicators. Subtract the data processing time to penalize the parameter settings with low processing efficiency. Correct the denominator, balance the impact of the new parameters, and ensure the accuracy of the average value. Adjustment coefficient obtained through expert rating or historical data analysis , , , Through optimization algorithms, such as genetic algorithms or grid search, adjustments and optimizations are made based on the performance of historical data sets to improve the predictive accuracy and robustness of the model.

[0092] Specifically, if Figure 6 As shown, according to the simulation test result set, the optimization operation is performed, the optimal parameter combination is analyzed through search and iteration, the optimization target and iteration threshold are defined, the strategy is adjusted, and the optimal parameter combination scheme is constructed;

[0093] S501: Based on the simulation test result set, the optimization goal is determined to be to enhance the structural performance. By setting the initial parameter combination as the reference point, the sequential search strategy is used to analyze the parameter space, and the parameter combination that initially improves the structural performance is identified. The execution process of forming the initial parameter improvement plan is as follows;

[0094] Based on the simulation test result set, sub-step S501 determines that the optimization goal is to enhance the structural performance. By setting the starting parameter combination as the benchmark point, a sequential search strategy is used to analyze the parameter space. The Python SciPy library is used for implementation. The parameter combination of the benchmark point is set as the starting point of the search, and the parameter space is traversed sequentially. The parameter value is adjusted along one dimension each time. The step size is set to 1% of the parameter value range to ensure the meticulousness of the search. The performance of each new parameter combination is evaluated, and the performance indicators in the simulation test result set are used as the evaluation criteria. If a new parameter combination is found to improve the performance indicator, the combination is set as the new benchmark point, and the sequential search is continued until adjustments in all dimensions fail to further improve the performance, thus forming a starting parameter improvement plan.

[0095] S502: Based on the initial parameter improvement plan, the parameter combination is refined by using cyclic iteration logic, and the structural strength iterative optimization technology is applied to compare the structural performance by gradually adjusting the parameter values. If a better solution is found, the parameter combination is updated to generate the execution process of the structural strength iterative optimization plan as follows;

[0096] The S502 sub-step is based on the initial parameter improvement scheme, and the parameter combination is refined by loop iterative logic. It is executed using Python's NumPy library, and the parameter combination is selected from the initial parameter improvement scheme as the iteration starting point. The parameter value is gradually adjusted, and the adjustment amplitude of each iteration is set to 10% of the previous performance improvement result. By comparing the changes in structural performance before and after the adjustment, the performance degree is compared using the performance evaluation function defined in the simulation test result set. If the adjusted parameter combination leads to an improvement in the performance evaluation function value, the new parameter combination is updated to the current optimal solution, and the iterative process is repeated until further adjustment cannot significantly improve the performance evaluation function value, and an iterative optimization plan for structural strength is generated.

[0097] Structural strength iterative optimization technology according to the formula

[0098]

[0099] in, is the optimal stress, is the force applied to the structure, is the load-bearing area of ​​the structure, is the stress concentration factor, which depends on the structure shape and loading conditions. is the safety factor of the structural material, is the elastic modulus of the material, reflecting the material's ability to resist deformation. is the fatigue attenuation coefficient, The designed service life of the structure.

[0100] The execution process is as follows;

[0101] Calculate the original force F and the force area , to determine the optimal stress without adjusting the parameters Then, the stress concentration factor is introduced , considering the local stress concentration caused by the structural shape and loading conditions, increase the safety factor , in order to consider the influence of uncertain factors on structural performance, and introduce the elastic modulus of the material , considering the material's ability to resist deformation, and finally introducing the fatigue attenuation coefficient and design service life D, taking into account the impact of changes over time on structural performance, through the introduction and adjustment of this series of parameters, the structural design is continuously optimized to ensure that it remains below the safe stress level throughout the design life. and The determination can be made through historical data analysis, combined with experiments or simulations on material properties, structural shape and usage conditions. This process ensures the scientificity and practicality of parameter adjustment.

[0102] S503: Using the structural strength iterative optimization scheme, iteratively fine-tuning the parameter combination, optimizing the structural performance with reference to the cost-effectiveness ratio, optimizing the parameter values ​​with the local search strategy, locking the parameter combination that balances the best performance and cost, and constructing the execution process of the optimal parameter combination scheme is as follows;

[0103] The S503 sub-step uses the structural strength iterative optimization scheme to iteratively fine-tune the parameter combination, optimizes the structural performance with reference to the cost-effectiveness ratio, adopts a local search strategy to optimize the parameter values, and uses Python's Pandas library and a custom cost-effectiveness analysis function to execute. The cost-effectiveness ratio is defined as the objective function of the optimization, which includes the parameter cost and the performance improvement potential evaluated by the simulation test result set. The local search strategy is used to capture the possibility of improvement in the neighborhood of the current optimal parameter combination. The size of the neighborhood is set to ±5% of the current parameter value. The cost-effectiveness ratio of each parameter combination in the neighborhood is iteratively compared, and the parameter combination with the highest cost-effectiveness ratio is selected as the new optimal solution. The execution is repeated until no better parameter combination is found to construct the optimal parameter combination scheme.

[0104] Specifically, if Figure 7 As shown, based on the optimal parameter combination solution, perform verification operations, simulate the design performance under extreme loads, define test conditions, perform static loading tests, analyze data, and establish design feasibility and safety assessment results;

[0105] S601: Based on the optimal parameter combination scheme, define the test conditions including extreme wind speed, earthquake intensity and environmental factors affecting the structural safety, execute the test scenarios to cover potential extreme conditions, and construct the execution process of the extreme test condition framework as follows;

[0106] In sub-step S601, based on the optimal parameter combination scheme, an extreme condition simulation strategy is adopted. The Python programming language is combined with the SimPy library to define the test conditions, including extreme wind speed, earthquake intensity and environmental factors affecting structural safety. The numpy.linspace function is used to generate a range sequence of extreme wind speeds to ensure that low to high wind speed conditions are covered. The numpy.random.uniform function is used to generate a random value sequence of earthquake intensity, where the parameters low and high define the minimum and maximum values ​​of earthquake intensity, respectively, to ensure that the test scenario covers potential extreme earthquake conditions. The environmental factors affecting structural safety are defined as altitude and humidity. The numpy.random.normal function is used to generate randomly distributed values ​​of altitude and humidity. All conditions are integrated in the SimPy environment, and the simulation is performed to generate an extreme test condition framework.

[0107] S602; Based on the extreme test condition framework, perform simulated static loading test, including applying predetermined limit load to the road bridge steel formwork and monitoring its response, including displacement and stress distribution, to evaluate the performance of the structure under adverse conditions, and generate the static load response record. The execution process is as follows;

[0108] Sub-step S602 adopts a static loading test simulation strategy based on the extreme test condition framework, uses ANSYS software to perform simulated static loading tests, sets predetermined limit load parameters, including maximum allowable displacement and stress thresholds, defines the loading path and applies it to the steel formwork structure of the road and bridge to ensure uniform load distribution, uses the Static Structural analysis system in ANSYS to execute the load application process, monitors the structural response, including real-time recording of displacement and stress distribution, uses the Probe function to obtain displacement and stress data at key locations, organizes and stores all monitoring data in the ANSYS project file, and generates static load response records.

[0109] S603: Analyze the static load response records, evaluate the safety margin and performance stability of the structure under extreme conditions by comparing the design standards and test results, determine the real-time application feasibility of the design, and obtain the execution process of the design feasibility and safety assessment results as follows;

[0110] Sub-step S603 analyzes the static load response records, adopts a performance evaluation strategy, uses the Python programming language combined with the Pandas and SciPy libraries to analyze the data, uses the Pandas library to import the static load response records, organizes the data into a format that is easy to analyze, and uses the statistical functions of the SciPy library, such as ttest_ind, to compare the differences between the design standards and the test results to ensure a statistical comparison analysis of the design standards and the actual test results. By calculating the safety margin and performance stability indicators, the performance of the structure under extreme conditions is evaluated, and the analysis results are summarized to obtain the design feasibility and safety assessment results.

[0111] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.

Claims

1. A method for optimizing the structural strength of a road and bridge steel mold, characterized in that: The method comprises the following steps: Collect the design parameters and historical performance data of road and bridge steel formwork structures, perform dimension recognition and multi-dimensional space mapping, transform the data into a multi-dimensional point set, and obtain a multi-dimensional data mapping set through data dimension expansion and space mapping; The specific steps of the multidimensional data mapping set are as follows: Collect the design parameters and historical performance data of road and bridge steel formwork structures, preliminarily organize the road and bridge steel formwork structure data, mark key information points, including material type, size specifications, service life and performance indicators, and build a data mark set; Using the information in the data tag set, a dimension recognition operation is performed to determine that key dimensions of the data include strength, durability, and cost, and the dimensions are associated with the data points to generate a dimension association graph; According to the dimensions and associations identified in the dimensional association graph, the data is mapped into a preset multidimensional space, with the data points occupying key positions in the multidimensional space, and a multidimensional data mapping set is constructed; Optimizing the multidimensional data mapping set, grouping data points by identifying similarities, constructing parameter group boundaries and features using spatial proximity, and obtaining a parameter group boundary map; The specific steps of the parameter grouping boundary diagram are as follows: Perform spatial proximity analysis on the data points in the multidimensional data mapping set, identify data points that are close to each other, and divide the data points into several groups based on spatial proximity to form a preliminary grouping; Based on the initial grouping, refine the similarity analysis of the data points in each group, refer to the similarity of the dimensions, including the matching degree of design concept and usage effect, iteratively determine the boundaries of the grouping, and generate a grouping refinement diagram; Based on the group refinement diagram, analyze the design parameters and performance data in the group, determine the mutual influence mode and characteristics of the parameters within the group, and construct the parameter group boundary diagram; Based on the parameter grouping boundary diagram, a sorting operation is performed to arrange the parameters according to the structural strength influence, the influence is compared and the weight is assigned, and a parameter influence sorting table is generated; The specific steps of the parameter influence ranking table are as follows: Based on the parameter grouping boundary diagram, analyzing the performance indicators and historical data of the parameters within the multiple groups, evaluating the potential impact of the parameters, including constructing a potential impact evaluation table with reference to the performance variability of the parameters under differentiated conditions; According to the potential influence evaluation table, the decision tree logic is used to judge the potential positive and negative effects of multiple parameters on the structural strength, and the corresponding weights of each group of parameters are determined by mutual comparison between the parameters to generate a parameter weight comparison table; The parameters in the group are sorted by using the parameter weight comparison table, and the parameter weights and the potential for improving the structural performance are referred to to form a parameter influence ranking table that comprehensively reflects the parameter influences; Using the parameter influence ranking table, performing simulation operations, using random sampling techniques to simulate structural performance, setting simulation ranges and conditions, collecting analysis results, and obtaining a simulation test result set; The specific steps of the simulation test result set are as follows: Based on the data in the parameter influence ranking table, identify key parameters, set a random sampling range for the parameters, adopt a stratified sampling strategy, select key samples, and construct a key parameter sample set; Selecting sample points from the key parameter sample set, setting differentiated simulation conditions for the sample points using loop logic, including ambient temperature and load conditions, performing simulation tests on the sample points under each condition, recording test results, and generating a conditional simulation data set; Analyze the data in the conditional simulation data set, apply the comparative analysis method, evaluate the structural performance under differentiated parameter values, identify the best and worst performing parameter value ranges through comparative analysis, analyze the comprehensive results of the simulation test, and construct a simulation test result set; The comparative analysis method is based on the formula ; in, Adjusted average performance index, is the performance indicator value within each group, is the weight coefficient of the performance index, Score the system stability, Score the data completeness, is the data processing time, is the number of data points in the group, , , , is the adjustment factor; According to the simulation test result set, an optimization operation is performed, by searching and iteratively analyzing the optimal parameter combination, defining the optimization target and iteration threshold, adjusting the strategy, and constructing the optimal parameter combination scheme; The specific steps of the optimal parameter combination scheme are as follows: Based on the simulation test result set, the optimization goal is determined to be enhancing structural performance, and by setting a starting parameter combination as a reference point, a sequential search strategy is used to analyze the parameter space, identify a parameter combination that initially improves structural performance, and form a starting parameter improvement plan; Based on the initial parameter improvement scheme, the parameter combination is refined by adopting the loop iteration logic, and the structural strength iterative optimization technology is applied to compare the structural performance by gradually adjusting the parameter values. If a better solution is found, the parameter combination is updated to generate a structural strength iterative optimization scheme; By using the structural strength iterative optimization scheme, the parameter combination is iteratively fine-tuned, the structural performance is optimized with reference to the cost-effectiveness ratio, the parameter values ​​are optimized by adopting a local search strategy, the parameter combination that achieves the best performance and cost balance is locked, and the optimal parameter combination scheme is constructed; The structural strength iterative optimization technique is based on the formula ; in, is the optimal stress, is the force applied to the structure, is the load-bearing area of ​​the structure, is the stress concentration factor, which depends on the structure shape and loading conditions. is the safety factor of the structural material, is the elastic modulus of the material, reflecting the material's ability to resist deformation. is the fatigue attenuation coefficient, The service life designed for the structure; Based on the optimal parameter combination solution, perform verification operations, simulate design performance under extreme loads, define test conditions, perform static loading tests, analyze data, and establish design feasibility and safety assessment results; The specific steps of the design feasibility and safety assessment results are as follows: According to the optimal parameter combination scheme, define test conditions including extreme wind speed, earthquake intensity and environmental factors affecting structural safety, execute test scenarios to cover potential extreme conditions, and build an extreme test condition framework; Perform simulated static loading tests based on the extreme test conditions framework, including applying predetermined extreme loads to the steel formwork of the road bridge and monitoring its response, including displacement and stress distribution, to evaluate the performance of the structure under adverse conditions and generate static load response records; The static load response records are analyzed, and by comparing the design standards and test results, the safety margin and performance stability of the structure under extreme conditions are evaluated, the real-time application feasibility of the design is determined, and the design feasibility and safety assessment results are obtained.

2. The method for optimizing the structural strength of road and bridge steel molds according to claim 1, characterized in that: The multidimensional data mapping set includes a multidimensional representation of structural weight, cost and durability indicators, the parameter grouping boundary diagram includes the boundary division of load type, material properties and design specifications, the parameter influence ranking table includes material strength, cost efficiency and design impact rating, the simulation test result set includes stress distribution, deformation and durability test result data, the optimal parameter combination scheme includes the adjustment of steel type, cross-sectional size and connection method selection, and the design feasibility and safety assessment results include performance under extreme temperature, vibration load and wind speed conditions.