Cable-stayed bridge stress-resistant steel structure optimization method and system

Abstract

The application relates to the technical field of steel process optimization, and provides a cable-stayed bridge stress-resistant steel structure optimization method and system.The method comprises the following steps: collecting an initial steel production process to manufacture steel, and generating sample steel; a preset modulus is configured based on an actual application scene; the sample steel is subjected to modulus detection to determine a modulus difference value; a multi-dimensional performance requirement is determined based on the actual application scene to generate a performance weight distribution; the modulus difference value and the multi-dimensional performance requirement are input into a process optimization decision model to output a global optimal adjustment sequence; and the initial steel production process is mapped and covered based on the global optimal adjustment sequence to generate an optimized production process to produce and prepare a same-batch target steel. The method can solve the problem that, in the steel production process, the actual application is not considered, and the steel quality is unqualified, and can improve the quality and service life of the steel.

Description

Technical Field

[0001] This application relates to the field of steel processing optimization technology, specifically to a method and system for optimizing the stress-resistant steel structure of a cable-stayed bridge. Background Technology

[0002] Steel is an important material widely used in various fields. From large military products such as airplanes, missiles, and aircraft carriers to small everyday products such as refrigerators and washing machines, steel is indispensable.

[0003] Because steel has a wide variety of uses, the quality requirements for steel are also different for different products. At present, steel production is carried out according to fixed production processes without analyzing the usage environment and needs of steel, resulting in steel products that cannot meet actual usage requirements.

[0004] In summary, existing technologies suffer from the problem of substandard steel quality due to a lack of consideration for actual application conditions during the steel production process. Summary of the Invention

[0005] Therefore, it is necessary to provide a method and system for optimizing the stress-resistant steel structure of cable-stayed bridges to address the aforementioned technical problems.

[0006] A method for optimizing the stress-resistant steel structure of a cable-stayed bridge includes: acquiring an initial steel production process to manufacture steel and generate sample steel; configuring a preset modulus based on the actual application scenario of the target steel; performing modulus testing on the sample steel, comparing the evaluation result with the preset modulus, and determining the modulus difference; determining multi-dimensional performance requirements based on the actual application scenario, configuring weights based on the multi-dimensional performance requirements, and generating a performance weight distribution; inputting the modulus difference and the multi-dimensional performance requirements into a process optimization decision model, and outputting a globally optimal adjustment sequence, wherein the process optimization decision model embeds a multi-objective optimization algorithm, and the performance weight distribution corresponds to a multi-objective mapping; and mapping and covering the initial steel production process based on the globally optimal adjustment sequence to generate an optimized production process for the production of the same batch of target steel.

[0007] In one embodiment, configuring the preset modulus based on the actual application scenario of the target steel further includes: determining pressure-bearing data based on the actual application scenario of the target steel; wherein the pressure-bearing data includes stress source, stress magnitude, and stress location; determining critical resistance based on the stress source, stress magnitude, and stress location; and obtaining the preset modulus based on the critical resistance.

[0008] In one embodiment, the method further includes: using the multidimensional performance requirements as an index to collect multiple sets of production optimization schemes; mapping and associating the multidimensional performance requirements with the multiple sets of production optimization schemes to train and generate the process optimization decision model, wherein the process optimization decision model has multiple optimization spaces corresponding to the multidimensional performance requirements; identifying the multiple optimization spaces based on the performance weight distribution; and embedding the multi-objective optimization algorithm into the process optimization decision model to complete the optimization of the model operation mechanism.

[0009] In one embodiment, the method further includes: inputting the modulus difference and the multidimensional performance requirements into the process optimization decision model, outputting multiple sets of preferred solutions based on the multiple optimization spaces; traversing the multiple sets of preferred solutions, performing global optimization based on the multi-objective optimization algorithm, and outputting the global optimal adjustment sequence, wherein the multiple sets of preferred solutions are labeled with weights.

[0010] In one embodiment, the method further includes: performing an application impact assessment on the multidimensional performance requirements to determine the degree of performance impact; and configuring and generating the performance weight distribution based on the degree of performance impact.

[0011] In one embodiment, the step of evaluating the modulus of the sample steel, comparing the evaluation result with the preset modulus, and determining the modulus difference further includes: evaluating the structural strain of the sample steel to generate a first modulus; evaluating the material strain of the sample steel to generate a second modulus; generating the evaluation result based on the first modulus and the second modulus; mapping the evaluation result to the preset modulus, calculating the difference based on the mapping result to generate a multi-level modulus difference; and using the multi-level modulus difference as the modulus difference value.

[0012] In one embodiment, the method further includes: preparing steel based on the optimized production process and obtaining production monitoring data; performing analysis on the production monitoring data to determine whether there is abnormal production data; when there is abnormal production data, locating the data source to identify the abnormal process node; and issuing an alarm for the abnormal process node.

[0013] A stress-resistant steel structure optimization system for cable-stayed bridges includes:

[0014] A sample steel generation module is used to collect initial steel production processes to manufacture steel and generate sample steel.

[0015] A preset modulus configuration module is used to configure a preset modulus based on the actual application scenario of the target steel.

[0016] The modulus difference determination module is used to perform modulus testing on the sample steel, compare the evaluation result with the preset modulus, and determine the modulus difference.

[0017] A performance weight distribution generation module is used to determine multi-dimensional performance requirements based on the actual application scenario, configure weights based on the multi-dimensional performance requirements, and generate a performance weight distribution.

[0018] A global optimal adjustment sequence output module is used to input the modulus difference and the multidimensional performance requirements into the process optimization decision model and output the global optimal adjustment sequence. The process optimization decision model embeds a multi-objective optimization algorithm, and the performance weight distribution corresponds to the multi-objective mapping.

[0019] An optimized production process generation module is used to map and cover the initial steel production process based on the globally optimal adjustment sequence, and generate an optimized production process for the production and preparation of the same batch of target steel.

[0020] The aforementioned method and system for optimizing the stress-resistant steel structure of cable-stayed bridges can solve the problem of substandard steel quality caused by neglecting practical application considerations during steel production. The method involves: collecting initial steel production process data to manufacture sample steel; configuring a preset modulus based on the actual application scenario of the target steel; performing modulus testing on the sample steel, comparing the evaluation results with the preset modulus to determine the modulus difference; determining multi-dimensional performance requirements based on the actual application scenario, configuring weights based on these requirements to generate a performance weight distribution; inputting the modulus difference and the multi-dimensional performance requirements into a process optimization decision model, outputting a globally optimal adjustment sequence. This process optimization decision model embeds a multi-objective optimization algorithm, and the performance weight distribution corresponds to a multi-objective mapping; mapping and covering the initial steel production process based on the globally optimal adjustment sequence to generate an optimized production process for the production of the same batch of target steel, thereby improving the quality and service life of the steel.

[0021] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0022] Figure 1 This application provides a flowchart illustrating a method for optimizing the stress-resistant steel structure of a cable-stayed bridge.

[0023] Figure 2 This application provides a flowchart illustrating the process of obtaining a preset modulus in the optimization method for the stress-resistant steel structure of a cable-stayed bridge.

[0024] Figure 3 This application provides a flowchart illustrating the process of determining the modulus difference in an optimization method for the stress-resistant steel structure of a cable-stayed bridge.

[0025] Figure 4 This application provides a structural schematic diagram of a stress-resistant steel structure optimization system for cable-stayed bridges.

[0026] Figure labeling: 1. Sample steel generation module; 2. Preset modulus configuration module; 3. Modulus difference determination module; 4. Performance weight distribution generation module; 5. Global optimal adjustment sequence output module; 6. Optimized generation process generation module. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0028] like Figure 1 As shown, this application provides a method for optimizing the stress-resistant steel structure of a cable-stayed bridge, the method comprising:

[0029] Step S100: Collect the initial steel production process to manufacture steel and generate sample steel;

[0030] Step S200: Configure the preset modulus based on the actual application scenario of the target steel;

[0031] like Figure 2 As shown, in one embodiment, step S200 of this application further includes:

[0032] Step S210: Determine the pressure-bearing data based on the actual application scenario of the target steel;

[0033] Step S220: Wherein, the pressure data includes stress source, stress magnitude, and stress location;

[0034] Step S230: Determine the critical resistance based on the stress source, the stress magnitude, and the stress location;

[0035] Step S240: Based on the critical resistance, obtain the preset modulus.

[0036] Specifically, an initial steel production process is obtained, and steel is produced using this process to obtain sample steel. The actual application scenario of the target steel is then determined, such as a cable-stayed bridge. The target steel refers to steel produced according to demand. The stress values ​​experienced by the steel in this actual application scenario are analyzed. These stress values ​​refer to the combined stress values ​​exerted on the steel by surrounding objects, obtaining bearing capacity data. This data includes the stress source, stress magnitude, and stress location. The stress source refers to the object causing stress to the steel, and the stress location refers to the location where the steel is subjected to stress.

[0037] The maximum compressive strength that the steel needs to withstand, i.e., the critical resistance, is obtained based on the stress source, stress magnitude, and stress location. Finally, a preset modulus is obtained based on the specific value of the critical resistance. This modulus includes the material modulus and the structural modulus, which is the ratio of steel stress to steel strain, used to measure the steel's stress resistance. A larger modulus value indicates stronger stress resistance. By analyzing the actual pressure environment of the steel, the preset modulus is obtained, providing parameter support for further optimization of the steel production process.

[0038] Step S300: Perform modulus testing on the sample steel, compare the evaluation result with the preset modulus, and determine the modulus difference;

[0039] like Figure 3 As shown, in one embodiment, step S300 of this application further includes:

[0040] Step S310: Perform structural strain assessment on the sample steel to generate the first modulus;

[0041] Step S320: Perform material strain assessment on the sample steel to generate a second modulus;

[0042] Step S330: Generate the evaluation result based on the first modulus and the second modulus;

[0043] Step S340: Map the evaluation result to the preset modulus, calculate the difference based on the mapping result, and generate multi-level modulus difference;

[0044] Step S350: Use the multi-level modulus difference as the modulus difference value.

[0045] Specifically, a strain assessment is performed on the structure of the sample steel, that is, the maximum stress value that the steel can withstand is evaluated based on the shape, thickness, and specifications of the steel, generating a first modulus. The material used to manufacture the sample steel is obtained, and a strain assessment is performed on the material to generate a second modulus. The modulus assessment result of the sample steel is obtained, which includes the first modulus and the second modulus. The first modulus is subtracted from the structural modulus to obtain the structural modulus difference, and the second modulus is subtracted from the material modulus to obtain the material modulus difference. Multiple levels of modulus differences are constructed using these structural modulus differences, and these multiple levels of modulus differences are used as modulus difference values. By obtaining these modulus difference values, the modulus difference between the sample steel and the target steel can be more intuitively obtained, thus providing specific data for improving the modulus of the target steel.

[0046] Step S400: Determine multi-dimensional performance requirements based on the actual application scenario, configure weights based on the multi-dimensional performance requirements, and generate a performance weight distribution;

[0047] In one embodiment, step S400 of this application further includes:

[0048] Step S410: Conduct an application impact assessment on the multidimensional performance requirements to determine the degree of performance impact;

[0049] Step S420: Based on the degree of performance impact, configure and generate the performance weight distribution.

[0050] Specifically, a demand analysis is conducted on the actual application scenarios of steel to obtain multi-dimensional performance requirements, including stress resistance, oxidation resistance, corrosion resistance, and other performance indicators. The application impact assessment of these multi-dimensional performance requirements is then performed. This assessment evaluates the degree of influence of individual performance indicators on the overall application of the steel. For example, if the steel is used as the main steel structure in building construction, the stress resistance requirement has the greatest impact, followed by the corrosion resistance requirement, while other performance indicators have a smaller impact. The performance impact degree of each performance indicator is determined. Different weights are assigned according to the performance impact degree; the greater the performance impact, the greater the weight value. Specific weight values ​​can be customized by those skilled in the art, and a performance weight distribution is generated based on the weight value settings. Obtaining this performance weight distribution provides a reference for further optimization of the production process.

[0051] Step S500: Input the modulus difference and the multidimensional performance requirements into the process optimization decision model, and output the global optimal adjustment sequence. The process optimization decision model embeds a multi-objective optimization algorithm, and the performance weight distribution corresponds to the multi-objective mapping.

[0052] In one embodiment, step S500 of this application further includes:

[0053] Step S510: Using the multidimensional performance requirements as an index, collect and obtain multiple sets of production optimization schemes;

[0054] Step S520: Map and associate the multidimensional performance requirements with the multiple sets of production optimization schemes, and train and generate the process optimization decision model, wherein the process optimization decision model has multiple optimization spaces corresponding to the multidimensional performance requirements;

[0055] Step S530: Identify the multiple optimization spaces based on the performance weight distribution;

[0056] Step S540: Embed the multi-objective optimization algorithm into the process optimization decision model to complete the optimization of the model operation mechanism.

[0057] Specifically, based on big data technology, data is collected on steel production processes using the multi-dimensional performance requirements as data search conditions to obtain multiple sets of production optimization schemes. Corresponding production optimization schemes are obtained based on the performance requirements, and a mapping set between the performance requirements and the production optimization schemes is constructed. A process optimization decision model is built, consisting of multiple optimization spaces, each corresponding to a performance requirement. The process optimization decision model is trained using data from the mapping set, and the multiple optimization spaces in the process optimization decision model are identified according to the performance weight distribution, that is, the weight values ​​corresponding to the performance requirement indicators are assigned to the optimization spaces. Finally, the multi-objective optimization algorithm is embedded into the process optimization decision model. The multi-objective optimization algorithm refers to comprehensively optimizing multiple objective parameters to obtain the optimal solution, including weighted calculation methods, genetic algorithms, etc., to obtain the process optimization decision model. By obtaining the process optimization decision model, the accuracy of obtaining the optimal process parameters is improved.

[0058] In one embodiment, step S500 of this application further includes:

[0059] Step S550: Input the modulus difference and the multidimensional performance requirements into the process optimization decision model, and output multiple sets of optimal solutions based on the multiple optimization spaces;

[0060] Step S560: Traverse the multiple sets of preferred solutions, perform global optimization based on the multi-objective optimization algorithm, and output the global optimal adjustment sequence, wherein the multiple sets of preferred solutions are labeled with weights.

[0061] Specifically, the modulus difference and the multidimensional performance requirements are input into the process optimization decision model for optimization space matching. Multiple optimal solution sets are obtained through multiple optimization spaces, each representing a process optimization scheme. These optimal solution sets are labeled with weights from the optimization spaces. A multi-objective optimization algorithm is then used for global optimization. By comprehensively evaluating multiple optimized process schemes and balancing their mutual influences, a globally optimal adjustment sequence is obtained. This globally optimal adjustment sequence includes multiple optimized process schemes. Obtaining this globally optimal adjustment sequence provides process support for the next step of steel production.

[0062] Step S600: Based on the global optimal adjustment sequence, the initial steel production process is mapped and covered to generate an optimized production process for the production and preparation of the same batch of target steel.

[0063] In one embodiment, step S600 of this application further includes:

[0064] Step S610: Prepare steel based on the optimized production process and obtain production monitoring data;

[0065] Step S620: Analyze the production monitoring data to determine if there is any abnormal production data;

[0066] Step S630: When the abnormal production data exists, locate the data source to determine the abnormal process node;

[0067] Step S640: Issue an alarm for the abnormal process node.

[0068] Specifically, the process parameters that differ in the initial steel production process are optimized according to the globally optimal adjustment sequence to generate an optimized production process. The same batch of target steel is then produced according to this optimized process. Each production stage in the steel production process is monitored to obtain production monitoring data. This production monitoring data is compared against standard production data thresholds. If the production monitoring data does not meet the standard production data thresholds, it is determined to be abnormal production data. The abnormal data source is located based on the data acquisition time to identify the abnormal process node, which refers to a specific production stage. An alarm message is generated based on the abnormal process node and sent to front-line production management personnel. This method solves the problem of substandard steel quality caused by neglecting practical application considerations during steel production, thereby improving the quality and service life of the steel.

[0069] In one embodiment, such as Figure 4The system provided is a stress-resistant steel structure optimization system for cable-stayed bridges, comprising: a sample steel generation module 1, a preset modulus configuration module 2, a modulus difference determination module 3, a performance weight distribution generation module 4, a global optimal adjustment sequence output module 5, and an optimized generation process generation module 6, wherein:

[0070] Sample steel generation module 1 is used to collect initial steel production process data to manufacture steel and generate sample steel.

[0071] The preset modulus configuration module 2 is used to configure a preset modulus based on the actual application scenario of the target steel.

[0072] Modulus difference determination module 3 is used to perform modulus testing on the sample steel, compare the evaluation result with the preset modulus, and determine the modulus difference.

[0073] The performance weight distribution generation module 4 is used to determine multi-dimensional performance requirements based on the actual application scenario, configure weights based on the multi-dimensional performance requirements, and generate a performance weight distribution.

[0074] The global optimal adjustment sequence output module 5 is used to input the modulus difference and the multidimensional performance requirements into the process optimization decision model and output the global optimal adjustment sequence. The process optimization decision model embeds a multi-objective optimization algorithm, and the performance weight distribution corresponds to the multi-objective mapping.

[0075] The optimized production process generation module 6 is used to map and cover the initial steel production process based on the global optimal adjustment sequence, and generate an optimized production process for the production and preparation of the same batch of target steel.

[0076] In one embodiment, the system further includes:

[0077] A pressure-bearing data determination module is used to determine pressure-bearing data based on the actual application scenario of the target steel.

[0078] The pressure data coverage module refers to the module in which the pressure data includes stress source, stress magnitude, and stress location.

[0079] A critical resistance determination module is used to determine the critical resistance based on the stress source, the stress magnitude, and the stress location.

[0080] A preset modulus acquisition module is used to acquire the preset modulus based on the critical resistance.

[0081] In one embodiment, the system further includes:

[0082] A production optimization scheme acquisition module is used to collect and acquire multiple sets of production optimization schemes by using the multidimensional performance requirements as an index.

[0083] A process optimization decision model generation module is used to map and associate the multidimensional performance requirements with the multiple sets of production optimization schemes, and train and generate the process optimization decision model. The process optimization decision model has multiple optimization spaces corresponding to the multidimensional performance requirements.

[0084] A spatial identification module is used to identify the multiple optimization spaces based on the performance weight distribution;

[0085] An optimization algorithm embedding module is used to embed the multi-objective optimization algorithm into the process optimization decision model to complete the optimization of the model operation mechanism.

[0086] In one embodiment, the system further includes:

[0087] A multi-set optimal solution output module is used to input the modulus difference and the multi-dimensional performance requirements into the process optimization decision model, and output multiple sets of optimal solutions based on the multiple optimization spaces.

[0088] A global optimal adjustment sequence output module is used to traverse the multiple sets of preferred solutions, perform global optimization based on the multi-objective optimization algorithm, and output the global optimal adjustment sequence, wherein the multiple sets of preferred solutions are labeled with weights.

[0089] In one embodiment, the system further includes:

[0090] An impact assessment module is used to assess the application impact of the multidimensional performance requirements and determine the degree of performance impact.

[0091] A performance weight distribution generation module is configured to generate the performance weight distribution based on the degree of performance impact.

[0092] In one embodiment, the system further includes:

[0093] The first modulus generation module is used to evaluate the structural strain of the steel sample and generate a first modulus.

[0094] The second modulus generation module is used to evaluate the material strain of the steel sample and generate a second modulus.

[0095] An evaluation result generation module is configured to generate the evaluation result based on the first modulus and the second modulus.

[0096] A multi-level modulus difference generation module is used to map the evaluation result with the preset modulus, calculate the difference based on the mapping result, and generate a multi-level modulus difference.

[0097] A modulus difference acquisition module is used to obtain the multi-level modulus difference as the modulus difference value.

[0098] In one embodiment, the system further includes:

[0099] A production monitoring data acquisition module is used to acquire production monitoring data based on the optimized production process for steel preparation.

[0100] An abnormal production data judgment module is used to analyze and dissect the production monitoring data to determine whether there is abnormal production data.

[0101] An abnormal process node determination module is used to locate and determine the abnormal process node when the abnormal production data exists.

[0102] An anomaly alarm module is used to issue alarms for the abnormal process nodes.

[0103] In summary, this application provides a method and system for optimizing the stress-resistant steel structure of a cable-stayed bridge, which has the following technical advantages:

[0104] 1. This invention addresses the problem of substandard steel quality caused by neglecting practical application considerations during steel production. By generating a globally optimal adjustment sequence to optimize the initial steel production process, the quality and service life of the steel can be improved.

[0105] 2. By constructing a process optimization decision model to find the optimal process parameters, the accuracy of obtaining the optimal process parameters can be improved.

[0106] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0107] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for optimizing the stress-resistant steel structure of a cable-stayed bridge, characterized in that, The method includes: The initial steel production process is collected to manufacture steel and generate sample steel. Configure a preset modulus based on the actual application scenario of the target steel; The modulus of the steel sample is tested, and the evaluation result is compared with the preset modulus to determine the modulus difference. Based on the actual application scenario, multi-dimensional performance requirements are determined, and weights are configured based on the multi-dimensional performance requirements to generate a performance weight distribution. The modulus difference and the multidimensional performance requirements are input into the process optimization decision model, and the globally optimal adjustment sequence is output. The process optimization decision model embeds a multi-objective optimization algorithm, and the performance weight distribution corresponds to the multi-objective mapping. Based on the global optimal adjustment sequence, the initial steel production process is mapped and covered to generate an optimized production process for the production and preparation of the same batch of target steel. The configuration of the preset modulus based on the actual application scenario of the target steel includes: Based on the actual application scenarios of the target steel, the pressure-bearing data are determined; The pressure data includes the stress source, stress magnitude, and stress location; Based on the stress source, the stress magnitude, and the stress location, the critical resistance is determined; Based on the critical resistance, the preset modulus is obtained.

2. The method as described in claim 1, characterized in that, The step of inputting the modulus difference and the multidimensional performance requirements into the process optimization decision model includes, prior to: Using the aforementioned multidimensional performance requirements as an index, multiple sets of production optimization solutions are collected and obtained. The multidimensional performance requirements are mapped and associated with the multiple sets of production optimization schemes, and the process optimization decision model is trained and generated. The process optimization decision model has multiple optimization spaces, which correspond to the multidimensional performance requirements. Based on the performance weight distribution, the multiple optimization spaces are identified; The multi-objective optimization algorithm is embedded into the process optimization decision model to complete the optimization of the model operation mechanism.

3. The method as described in claim 2, characterized in that, include: The modulus difference and the multidimensional performance requirements are input into the process optimization decision model, and multiple sets of optimal solutions are output based on the multiple optimization spaces. The multiple sets of preferred solutions are traversed, and global optimization is performed based on the multi-objective optimization algorithm to output the globally optimal adjustment sequence, wherein the multiple sets of preferred solutions are labeled with weights.

4. The method as described in claim 1, characterized in that, include: An application impact assessment is conducted on the aforementioned multidimensional performance requirements to determine the degree of performance impact; Based on the degree of performance impact, the performance weight distribution is generated.

5. The method as described in claim 1, characterized in that, The process of evaluating the modulus of the sample steel, comparing the evaluation result with the preset modulus, and determining the modulus difference includes: The structural strain of the steel sample was evaluated to generate the first modulus; The sample steel was subjected to material strain evaluation to generate a second modulus; The evaluation result is generated based on the first modulus and the second modulus; The evaluation results are mapped to the preset modulus, and the difference is calculated based on the mapping results to generate multi-level modulus differences; The multi-level modulus difference is used as the modulus difference value.

6. The method as described in claim 1, characterized in that, include: Steel is prepared based on the optimized production process, and production monitoring data is obtained. The production monitoring data is dissected and analyzed to determine whether there is any abnormal production data; When the abnormal production data exists, the abnormal process node is determined by locating the data source. An alarm is issued for the abnormal process node.

7. A stress-resistant steel structure optimization system for cable-stayed bridges, characterized in that, The system is used to execute the method for optimizing the stress-resistant steel structure of a cable-stayed bridge as described in any one of claims 1-6, the system comprising: A sample steel generation module is used to collect initial steel production processes to manufacture steel and generate sample steel. A preset modulus configuration module is used to configure a preset modulus based on the actual application scenario of the target steel. The modulus difference determination module is used to perform modulus testing on the sample steel, compare the evaluation result with the preset modulus, and determine the modulus difference. A performance weight distribution generation module is used to determine multi-dimensional performance requirements based on the actual application scenario, configure weights based on the multi-dimensional performance requirements, and generate a performance weight distribution. A global optimal adjustment sequence output module is used to input the modulus difference and the multidimensional performance requirements into the process optimization decision model and output the global optimal adjustment sequence. The process optimization decision model embeds a multi-objective optimization algorithm, and the performance weight distribution corresponds to the multi-objective mapping. An optimized production process generation module is used to map and cover the initial steel production process based on the globally optimal adjustment sequence, and generate an optimized production process for the production and preparation of the same batch of target steel.

Images