Bridge equivalent vehicle load model construction method and system based on accumulated fatigue damage

Abstract

The embodiment of the invention relates to the technical field of bridge safety, and particularly discloses a bridge equivalent vehicle load model construction method and system based on accumulated fatigue damage. According to the embodiment of the invention, through bridge traffic monitoring, vehicle load data is obtained; carrying out distribution rule analysis and probability fitting to generate a probability function model; constructing a fatigue vehicle load model; simplifying the model into an equivalent fatigue damage model; performing model verification and optimization adjustment on the equivalent fatigue damage model to generate an optimized fatigue damage model; and performing multi-scene application deployment. Load monitoring, analysis and probability fitting can be carried out, a probability function model is generated, then fatigue damage evaluation and model simplification are carried out, an equivalent fatigue damage model is constructed, an optimized fatigue damage model is generated by carrying out model verification and optimization adjustment, and then multi-scene application deployment is carried out, so that bridge safety reserve can better conform to the actual situation, and the safety performance of a bridge is improved. And through the cumulative effect of fatigue damage, the accuracy of bridge safety assessment is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of bridge safety, and particularly relates to a method and system for constructing an equivalent vehicle load model of a bridge based on fatigue cumulative damage. Background Art

[0002] As the most important variable load borne by a bridge structure, vehicle load largely determines the safety and service life of the bridge structure during operation. With the more frequent economic cooperation and exchanges between regions, the number and load capacity of trucks actually operating in many areas show an obvious increasing trend. Heavy trucks mainly engaged in freight transportation cause serious structural damage to bridges, and some severely overloaded trucks even cause the collapse and destruction of bridge structures.

[0003] In the prior art, the general design specifications of bridges ensure the healthy operation of bridges with a certain safety redundancy reserve. However, with the rapid development of freight trucks towards large-scale and heavy-load, the applicability of the vehicle load design standard is reduced. In some special areas, it is difficult to provide the necessary safety reserve for the healthy operation of bridge structures, and the safety assessment of vehicle load on bridges only focuses on the impact of single load, while ignoring the cumulative effect of fatigue damage, resulting in inaccurate bridge safety assessment. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for constructing an equivalent vehicle load model of a bridge based on fatigue cumulative damage, aiming to solve the problems proposed in the background art.

[0005] To achieve the above purpose, the embodiments of the present invention provide the following technical solutions: A method for constructing an equivalent vehicle load model of a bridge based on fatigue cumulative damage, the method specifically includes the following steps: Perform bridge traffic monitoring according to a preset acquisition frequency and acquisition duration, obtain vehicle load data, and preprocess the vehicle load data to generate standard load data; Analyze the distribution law of the standard load data to obtain load distribution data, and perform probability fitting on the load distribution data to generate a probability function model; Based on the probability function model, perform fatigue damage assessment to construct a fatigue vehicle load model; Simplify the fatigue vehicle load model into an equivalent fatigue damage model; Generate a simulated fleet, verify the model of the equivalent fatigue damage model to obtain a model verification result, and optimize and adjust the equivalent fatigue damage model to generate an optimized fatigue damage model; Perform multi-scenario application deployment on the optimized fatigue damage model.

[0006] As a further limitation of the technical solution of the embodiment of the present invention, the steps of performing bridge traffic monitoring according to a preset acquisition frequency and acquisition duration, obtaining vehicle load data, and preprocessing the vehicle load data to generate standard load data specifically include the following steps: Periodically generate monitoring signals according to a preset acquisition frequency and acquisition duration; Perform bridge traffic monitoring according to the monitoring signals to obtain vehicle load data; Perform data cleaning and outlier processing on the vehicle load data to generate effective load data; Perform standardization processing on the effective load data to generate standard load data.

[0007] As a further limitation of the technical solution of the embodiment of the present invention, the steps of analyzing the distribution law of the standard load data, obtaining load distribution data, and performing probability fitting on the load distribution data to generate a probability function model specifically include the following steps: Analyze the laws of vehicle type distribution, time distribution, lane distribution, vehicle speed distribution, and vehicle weight distribution of the standard load data to obtain load distribution data; Select a basic probability model; Perform model parameter estimation to obtain basic estimation parameters; Perform probability fitting on the load distribution data according to the basic estimation parameters and the basic probability model to generate a probability function model.

[0008] As a further limitation of the technical solution of the embodiment of the present invention, the steps of performing fatigue damage assessment based on the probability function model and constructing a fatigue vehicle load model specifically include the following steps: Perform fatigue damage impact assessment based on the probability function model and record the impact assessment results; Perform fatigue damage accumulation analysis of different vehicle types on the bridge according to the impact assessment results and record the damage accumulation data; Construct a fatigue vehicle load model according to the damage accumulation data.

[0009] As a further limitation of the technical solution of the embodiment of the present invention, the steps of simplifying the fatigue vehicle load model into an equivalent fatigue damage model specifically include the following steps: Determine the equal equivalence principle; Based on the equal equivalence principle, determine the equivalent axle load and equivalent wheelbase; Perform equivalent simplification on the fatigue vehicle load model according to the equivalent axle load and the equivalent wheelbase to construct an equivalent fatigue damage model; Perform model verification and model confirmation processing on the equivalent fatigue damage model.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the steps of generating a simulated vehicle fleet, validating the equivalent fatigue damage model, obtaining the model validation result, and optimizing and adjusting the equivalent fatigue damage model to generate an optimized fatigue damage model specifically include the following steps: Generate a simulated vehicle fleet; Through the simulated vehicle fleet, perform multi-index model validation on the equivalent fatigue damage model to obtain the model validation result; According to the model validation result, perform parameter adjustment analysis to determine multiple adjustment parameters; According to the multiple adjustment parameters, optimize and adjust the equivalent fatigue damage model to generate an optimized fatigue damage model.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the steps of performing multi-scenario application deployment on the optimized fatigue damage model specifically include the following steps: Perform application deployment of the optimized fatigue damage model in bridge design; Perform application deployment of the optimized fatigue damage model in bridge assessment; Perform application deployment of the optimized fatigue damage model in bridge maintenance.

[0012] A bridge equivalent vehicle load model construction system based on fatigue cumulative damage, the system includes a bridge traffic monitoring unit, a distribution law analysis unit, a fatigue damage assessment unit, a load model simplification unit, a model optimization and adjustment unit, and a scenario application deployment unit, wherein: The bridge traffic monitoring unit is used to perform bridge traffic monitoring according to a preset acquisition frequency and acquisition duration, obtain vehicle load data, and preprocess the vehicle load data to generate standard load data; The distribution law analysis unit is used to analyze the distribution law of the standard load data, obtain load distribution data, and perform probability fitting on the load distribution data to generate a probability function model; The fatigue damage assessment unit is used to perform fatigue damage assessment based on the probability function model and construct a fatigue vehicle load model; The load model simplification unit is used to simplify the fatigue vehicle load model into an equivalent fatigue damage model; The model optimization and adjustment unit is used to generate a simulated vehicle fleet, perform model validation on the equivalent fatigue damage model, obtain the model validation result, and optimize and adjust the equivalent fatigue damage model to generate an optimized fatigue damage model; The scenario application deployment unit is used to perform multi-scenario application deployment on the optimized fatigue damage model.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the bridge traffic monitoring unit specifically includes: A signal generation module, configured to periodically generate monitoring signals according to a preset acquisition frequency and acquisition duration; A bridge traffic monitoring module, configured to perform bridge traffic monitoring according to the monitoring signals and obtain vehicle load data; A data cleaning and outlier processing module, configured to perform data cleaning and outlier processing on the vehicle load data to generate effective load data; A normalization processing module, configured to perform normalization processing on the effective load data to generate standard load data.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the distribution law analysis unit specifically includes: A distribution law analysis module, configured to perform law analysis on the standard load data for vehicle type distribution, time distribution, lane distribution, vehicle speed distribution, and vehicle weight distribution to obtain load distribution data; A basic model selection module, configured to select a basic probability model; A parameter estimation module, configured to perform model parameter estimation to obtain basic estimation parameters; A probability fitting module, configured to perform probability fitting on the load distribution data according to the basic estimation parameters and the basic probability model to generate a probability function model.

[0015] Compared with the prior art, the beneficial effects of the present invention are: In the embodiment of the present invention, by performing bridge traffic monitoring, vehicle load data is obtained; by performing distribution law analysis and probability fitting, a probability function model is generated; a fatigue vehicle load model is constructed; it is simplified into an equivalent fatigue damage model; the equivalent fatigue damage model is verified and optimized to generate an optimized fatigue damage model; and multi-scenario application deployment is performed. It can perform load monitoring, analysis, and probability fitting to generate a probability function model, then perform fatigue damage assessment and model simplification to construct an equivalent fatigue damage model, and through model verification and optimization, an optimized fatigue damage model is generated, and then multi-scenario application deployment is performed, which can make the bridge safety reserve more in line with the actual situation, and improve the accuracy of bridge safety assessment through the cumulative effect of fatigue damage. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0017] Figure 1 Shows the flowchart of the method provided by the embodiment of the present invention.

[0018] Figure 2 Shows the flowchart of generating standard load data in the method provided by the embodiment of the present invention.

[0019] Figure 3 Shows the flowchart of generating a probability function model in the method provided by the embodiment of the present invention.

[0020] Figure 4 Shows the flowchart of constructing a fatigue vehicle load model in the method provided by the embodiment of the present invention.

[0021] Figure 5 Shows the flowchart of simplifying an equivalent fatigue damage model in the method provided by the embodiment of the present invention.

[0022] Figure 6 Shows the flowchart of generating an optimized fatigue damage model in the method provided by the embodiment of the present invention.

[0023] Figure 7 Shows the flowchart of model multi-scenario application deployment in the method provided by the embodiment of the present invention.

[0024] Figure 8 Shows the application architecture diagram of the system provided by the embodiment of the present invention.

[0025] Figure 9 Shows the structural block diagram of the bridge traffic monitoring unit in the system provided by the embodiment of the present invention.

[0026] Figure 10 Shows the structural block diagram of the distribution law analysis unit in the system provided by the embodiment of the present invention. Detailed implementation manners

[0027] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0028] It can be understood that in the prior art, the general design specifications of bridges are based on a certain safety redundancy reserve to ensure the healthy operation of bridges. However, with the rapid development of freight trucks towards large-scale and heavy-load, the applicability of the design standards for vehicle loads has decreased. In some special regions, it is difficult to provide the necessary safety reserve for the healthy operation of bridge structures, and for the safety assessment of bridges by vehicle loads, it is only limited to the impact of single loads, while ignoring the cumulative effect of fatigue damage, resulting in inaccurate bridge safety assessment.

[0029] To solve the above problems, in the embodiments of the present invention, bridge traffic monitoring is carried out according to a preset acquisition frequency and acquisition duration to obtain vehicle load data, and the vehicle load data is preprocessed to generate standard load data; the distribution law of the standard load data is analyzed to obtain load distribution data, and the load distribution data is probabilistically fitted to generate a probability function model; based on the probability function model, fatigue damage assessment is carried out to construct a fatigue vehicle load model; the fatigue vehicle load model is simplified into an equivalent fatigue damage model; a simulated fleet is generated to verify the equivalent fatigue damage model to obtain a model verification result, and the equivalent fatigue damage model is optimized and adjusted to generate an optimized fatigue damage model; the optimized fatigue damage model is deployed for multi-scenario applications. It is possible to perform load monitoring, analysis and probabilistic fitting to generate a probability function model, then perform fatigue damage assessment and model simplification to construct an equivalent fatigue damage model, and by performing model verification and optimization adjustment, generate an optimized fatigue damage model, and then perform multi-scenario application deployment, which can make the bridge safety reserve more in line with the actual situation, and improve the accuracy of bridge safety assessment through the cumulative effect of fatigue damage.

[0030] Figure 1 The flowchart of the method provided by the embodiments of the present invention is shown.

[0031] Specifically, a method for constructing an equivalent vehicle load model of a bridge based on fatigue cumulative damage, the method specifically includes the following steps: Step S101, perform bridge traffic monitoring according to a preset acquisition frequency and acquisition duration to obtain vehicle load data, and preprocess the vehicle load data to generate standard load data.

[0032] In the embodiments of the present invention, monitoring signals are periodically generated according to a preset acquisition frequency and acquisition duration, and then bridge traffic monitoring is carried out according to the monitoring signals to obtain vehicle load data. After that, the vehicle load data is subjected to data cleaning (by using a data deduplication algorithm to eliminate duplicate records caused by sensor failures or data transmission errors, and using data verification rules or machine learning algorithms to identify and correct obviously incorrect data, and for missing data points, interpolation methods or prediction models based on historical data can be used for filling), and outlier processing (using statistical methods or machine learning algorithms to identify outliers in the data and perform processing such as deletion, replacement with the average or median, or retention and marking) is carried out to generate effective load data, and then the effective load data is standardized (scaling the data to a specific range to eliminate the difference in dimensions, and for non-normal distribution data, methods such as logarithmic transformation and Box-Cox transformation can be used to make it closer to a normal distribution) to generate standard load data.

[0033] Specifically, Figure 2The flowchart of generating standard load data in the method provided by the embodiment of the present invention is shown.

[0034] Among them, in the preferred embodiment provided by the present invention, the steps of performing bridge traffic monitoring according to a preset acquisition frequency and acquisition duration, obtaining vehicle load data, and preprocessing the vehicle load data to generate standard load data specifically include the following steps: Step S1011, periodically generate monitoring signals according to a preset acquisition frequency and acquisition duration; Step S1012, perform bridge traffic monitoring according to the monitoring signals to obtain vehicle load data; Step S1013, perform data cleaning and outlier processing on the vehicle load data to generate effective load data; Step S1014, perform standardization processing on the effective load data to generate standard load data.

[0035] Furthermore, the method for constructing the bridge equivalent vehicle load model based on fatigue cumulative damage further includes the following steps: Step S102, analyze the distribution law of the standard load data to obtain load distribution data, and perform probability fitting on the load distribution data to generate a probability function model.

[0036] In the embodiment of the present invention, by analyzing the distribution laws of vehicle type distribution, time distribution, lane distribution, vehicle speed distribution, and vehicle weight distribution of the standard load data, load distribution data is obtained, and a basic probability model (which can be Gaussian distribution, Weibull distribution, lognormal distribution, gamma distribution, etc.) is selected, and methods such as maximum likelihood estimation and moment estimation are used to estimate model parameters to obtain basic estimation parameters. Then, based on the basic estimation parameters and the basic probability model, probability fitting is performed on the load distribution data to generate a probability function model.

[0037] Specifically, Figure 3 The flowchart of generating a probability function model in the method provided by the embodiment of the present invention is shown.

[0038] Among them, in the preferred embodiment provided by the present invention, the steps of analyzing the distribution law of the standard load data to obtain load distribution data, and performing probability fitting on the load distribution data to generate a probability function model specifically include the following steps: Step S1021, analyze the distribution laws of vehicle type distribution, time distribution, lane distribution, vehicle speed distribution, and vehicle weight distribution of the standard load data to obtain load distribution data; Step S1022, select a basic probability model; Step S1023, perform model parameter estimation to obtain basic estimation parameters; Step S1024: According to the basic estimation parameters and the basic probability model, perform probability fitting on the load distribution data to generate a probability function model.

[0039] Specifically, according to the basic estimation parameters and the basic probability model, performing probability fitting on the load distribution data to generate a probability function model, the specific steps are as follows: Based on the payload data, obtain the total sample size and the frequency of each vehicle type. Calculate the ratio of the frequency of each vehicle type to the total sample size to obtain the preliminary vehicle type weight coefficient; combine the engineering construction parameters to calculate the special vehicle type weight coefficient; use the special vehicle type weight coefficient to correct the preliminary vehicle type weight coefficient to obtain the corrected vehicle type weight coefficient; Conduct statistical analysis on the standard load data by vehicle type. For each vehicle type sample, extract the standard load value corresponding to the vehicle type from the standard load data, calculate the arithmetic mean of the standard load values corresponding to the vehicle type as the distribution center value, and obtain the vehicle type Gaussian distribution parameters based on the distribution center value; Obtain the original load data timestamp through the vehicle load data, and determine the day-night influence coefficient through the bridge design specifications; based on the original load data timestamp, statistically obtain the absolute quantity and relative proportion of vehicle passages in each time period, and then combine the day-night influence coefficient to calculate the time correction factor; Obtain the vehicle position data through the vehicle load data, determine the bridge bearing capacity parameters through the bridge design specifications, and statistically obtain the vehicle passage density of each lane per unit time through the vehicle position data to calculate the unit time vehicle passage density value. Combine the unit time vehicle passage density value with the bridge bearing capacity parameters in the way of calculating the distribution difference coefficient to obtain the lane correction factor; Based on the vehicle type Gaussian distribution parameters, perform weighted processing in combination with the corrected vehicle type weight coefficient to obtain the weighted probability density intermediate value of the vehicle type at the target load point; Perform a multiplication operation on the weighted probability density intermediate value of the vehicle type at the target load point and the time correction factor to obtain a product result. On the basis of the product result, introduce the lane correction factor and perform a secondary product correction to obtain a multi-correction superposition value; Perform an algebraic sum on the multi-correction superposition values of all vehicle types at the target load point to obtain the final load probability value, so as to complete the construction of the probability function model.

[0040] Furthermore, the method for constructing the bridge equivalent vehicle load model based on fatigue cumulative damage further includes the following steps: Step S103: Based on the probability function model, perform fatigue damage assessment to construct a fatigue vehicle load model.

[0041] In the embodiment of the present invention, based on the probability function model, fatigue damage impact assessment is carried out, the impact assessment results are recorded, and then, according to the impact assessment results, fatigue damage accumulation analysis of different vehicle types on the bridge is carried out, the contribution rate of each vehicle type to the fatigue damage of the bridge is calculated, the damage accumulation data is recorded, and then, according to the damage accumulation data, a fatigue vehicle load model is constructed.

[0042] Specifically, Figure 4 The flowchart of constructing a fatigue vehicle load model in the method provided by the embodiment of the present invention is shown.

[0043] Among them, in the preferred embodiment provided by the present invention, the fatigue damage assessment is carried out based on the probability function model, and the specific steps of constructing a fatigue vehicle load model include the following: Step S1031, based on the probability function model, carry out fatigue damage impact assessment and record the impact assessment results; Step S1032, according to the impact assessment results, carry out fatigue damage accumulation analysis of different vehicle types on the bridge and record the damage accumulation data; Step S1033, construct a fatigue vehicle load model according to the damage accumulation data.

[0044] Specifically, according to the impact assessment results, carry out fatigue damage accumulation analysis of different vehicle types on the bridge and record the damage accumulation data. The specific steps are as follows: Obtain the key parameters of bridge materials from the bridge structure material database. The key parameters of bridge materials include the material reference stress threshold and the material reference durability index value; Based on the bridge structure material database, obtain the key parameters of bridge materials. The key parameters of bridge materials include the material reference stress threshold and the material reference durability index value; Based on the effective load data, determine the passing frequency of each vehicle type and the corresponding axle weight parameter value. For each vehicle type, use the moving load influence line model to convert the axle weight parameter value of each vehicle type into the stress fluctuation value of the key parts of the bridge; for the passing frequency of each vehicle type, calculate the difference between the maximum stress and the minimum stress caused by the stress fluctuation value of the key parts of the bridge to obtain the dynamic stress amplitude value; Normalize the dynamic stress amplitude value and the material reference stress threshold respectively to obtain the normalized dynamic stress amplitude value and the normalized material reference stress threshold, and calculate the multiple relationship of each normalized dynamic stress amplitude value relative to the normalized material reference stress threshold to obtain the standardized stress coefficient; Based on the vehicle speed parameters obtained from bridge traffic monitoring, divide them into multiple speed intervals, and calculate the speed interval correction influence factor based on the multiple speed intervals; Calculate the division result between the standardized stress coefficient and the reference durability index value, and multiply the division result by the corresponding speed interval correction influence factor to obtain the cumulative damage amount caused by a single load application. Accumulate the cumulative damage amount caused by a single load application to obtain the cumulative damage value of a single vehicle type, and then summarize all the cumulative damage values of single vehicle types according to the cross-vehicle type dimension to obtain the total cumulative damage value. Record the total cumulative damage value as the cumulative damage data.

[0045] Furthermore, the method for constructing the equivalent vehicle load model of a bridge based on fatigue cumulative damage further includes the following steps: Step S104, simplify the fatigue vehicle load model into an equivalent fatigue damage model.

[0046] In the embodiment of the present invention, the equal equivalence principle that the fatigue damage generated by the equivalent vehicle load on the bridge should be equal to the fatigue damage generated by the actual vehicle load is determined, the equivalent axle load and the equivalent wheelbase are determined, and then according to the equivalent axle load and the equivalent wheelbase, the fatigue vehicle load model is equivalently simplified to construct an equivalent fatigue damage model. After that, model verification and model confirmation processing are performed on the equivalent fatigue damage model to verify the accuracy and engineering application requirements of the equivalent model.

[0047] Specifically, Figure 5 Fig. shows the flow chart of simplifying the equivalent fatigue damage model in the method provided by the embodiment of the present invention.

[0048] Among them, in the preferred embodiment provided by the present invention, the simplifying the fatigue vehicle load model into an equivalent fatigue damage model specifically includes the following steps: Step S1041, determine the equal equivalence principle; Step S1042, based on the equal equivalence principle, determine the equivalent axle load and the equivalent wheelbase; Step S1043, according to the equivalent axle load and the equivalent wheelbase, equivalently simplify the fatigue vehicle load model to construct an equivalent fatigue damage model; Step S1044, perform model verification and model confirmation processing on the equivalent fatigue damage model.

[0049] Specifically, based on the equal equivalence principle, determine the equivalent axle load and the equivalent wheelbase. Among them, the specific steps for obtaining the equivalent axle load are as follows: Obtain the material fatigue characteristic database, and obtain the material characteristic parameters based on the material fatigue characteristic database. The material characteristic parameters include the stress sensitivity index and the wheelbase attenuation index; Based on the payload data, extract the actual weighing values of each axle one by one according to the vehicle passing records to obtain the vehicle axle weight table; obtain the vehicle axle position coordinate differences based on the effective load data, and calculate the spacing values between adjacent axles according to the vehicle axle position coordinate differences to obtain the vehicle axle spacing table; match the vehicle axle weights and vehicle axle spacings of the same vehicle in the order of the axles to obtain the vehicle axle system parameter table of axle weight - axle spacing; Perform power operation on the vehicle axle weights using the stress sensitivity index to obtain the axle weight power operation result; perform power operation on the vehicle axle spacings using the negative of the axle spacing attenuation index to obtain the axle spacing power operation result; multiply the axle weight power operation result and the axle spacing power operation result of the same axle position to obtain the single - axle conversion factor; Determine the axle position influence coefficient through the load distribution data, and multiply the single - axle conversion factor by the corresponding axle position influence coefficient to obtain the weighted comprehensive conversion factor; Sum up the weighted comprehensive conversion factors of all axles of the vehicle to obtain the vehicle - level multi - axle cumulative value, and perform the square - root operation of the root number on the vehicle - level multi - axle cumulative value to obtain the equivalent axle weight, where the specific value of the root number is the stress sensitivity index.

[0050] Specifically, according to the equivalent axle weight and the equivalent axle spacing, perform equivalent simplification on the fatigue vehicle load model to construct an equivalent fatigue damage model. Among them, the equivalent fatigue damage model consists of the equivalent axle spacing and the equivalent single - axle load. Obtain the equivalent axle spacing using the actually measured axle spacing value obtained from the payload data. The relationship in the corresponding process is: ; Among them, represents the equivalent axle spacing, characterizing the equivalent spatial action distance of the multi - axle vehicle on the bridge; represents the th actually measured value of the axle spacing, that is, the adjacent axle spacing; represents the th damage weight coefficient generated by the axle spacing, determined according to the axle weight - axle spacing coupling effect; represents the non - linear correction factor, and the value range is , to reflect the non - linear superposition characteristics of the axle spacing; represents the total number of axle spacings; Obtain the equivalent single - axle load using the actually measured axle weight of the vehicle type obtained from the effective load data. The relationship in the corresponding process is: ; Among them, represents the equivalent single - axle load, characterizing the cumulative damage effect of multi - axle and multi - vehicle types; represents the th actually measured value of the axle weight of the vehicle type, represents the The passing speed of the vehicle type represents the reference speed constant; represents the equivalent cycle number coefficient, which is obtained through the monitoring period; represents the load nonlinearity index, and its value range is , which characterizes the stress-strain nonlinearity of the metal material; represents the speed correction index, which reflects the attenuation rate of the dynamic amplification effect.

[0051] Furthermore, the method for constructing the equivalent vehicle load model of the bridge based on fatigue cumulative damage further includes the following steps: Step S105: Generate a simulated vehicle fleet, perform model verification on the equivalent fatigue damage model, obtain the model verification results, and optimize and adjust the equivalent fatigue damage model to generate an optimized fatigue damage model.

[0052] In the embodiment of the present invention, by generating a simulated vehicle fleet, comparing the load effects of the simulated vehicle fleet with the effects of the standard vehicle load model, performing multi-index model verification on the equivalent fatigue damage model, obtaining model verification results including mean square error, root mean square error, and coefficient of determination, etc., then according to the model verification results, performing parameter adjustment analysis to determine multiple adjustment parameters, and further according to the multiple adjustment parameters, optimizing and adjusting the equivalent fatigue damage model to generate an optimized fatigue damage model.

[0053] Specifically, Figure 6 shows the flow chart of generating the optimized fatigue damage model in the method provided by the embodiment of the present invention.

[0054] Among them, in the preferred embodiment provided by the present invention, the steps of generating a simulated vehicle fleet, performing model verification on the equivalent fatigue damage model, obtaining the model verification results, and optimizing and adjusting the equivalent fatigue damage model to generate an optimized fatigue damage model specifically include the following steps: Step S1051: Generate a simulated vehicle fleet; Step S1052: Through the simulated vehicle fleet, perform multi-index model verification on the equivalent fatigue damage model to obtain the model verification results; Step S1053: According to the model verification results, perform parameter adjustment analysis to determine multiple adjustment parameters; Step S1054: According to the multiple adjustment parameters, optimize and adjust the equivalent fatigue damage model to generate an optimized fatigue damage model.

[0055] Specifically, according to the multiple adjustment parameters, optimizing and adjusting the equivalent fatigue damage model to generate an optimized fatigue damage model, the specific steps are as follows: The sensitivity ranking of the key components of the bridge is determined through the model verification results. The control damage error weight, response correlation weight, and parameter stability weight are respectively determined based on the sensitivity ranking of the key components of the bridge. Based on the model verification results, the simulated damage value is obtained. Based on the equivalent fatigue damage model, the equivalent damage value is output and obtained. The difference between the corresponding simulated damage value and the equivalent damage value is calculated for each time point to obtain the difference result. The squares of all difference results are accumulated to obtain the cumulative sum. The square root of the cumulative sum is taken to obtain the damage deviation quantification value. Based on the model verification results, the simulated strain value is obtained. Based on the equivalent fatigue damage model, the equivalent strain value is output and obtained. After the simulated strain value and the equivalent strain value are aligned point by point in time, the Pearson correlation coefficient is calculated to obtain the original response value. According to the actual engineering acceptance standard, the ideal response target value is determined. The original response value is subtracted from the ideal response target value to obtain the response deviation quantification value. Based on the multiple adjustment parameters, the numerical distribution range of each adjustment parameter is statistically analyzed and the parameter characteristic constraint rules are determined simultaneously. Based on the numerical distribution range of each adjustment parameter, the overall stability value of the parameter group is obtained in the form of calculating the degree of dispersion. The parameter characteristic constraint rules are applied to the overall stability value of the parameter group to obtain the parameter stability index value. The damage deviation quantification value is multiplied by the control damage error weight to obtain the first optimization parameter value. The response deviation quantification value is multiplied by the response correlation weight to obtain the second optimization parameter value. The parameter stability index value is multiplied by the parameter stability weight to obtain the third optimization parameter value. The first optimization parameter value, the second optimization parameter value, and the third optimization parameter value are added together to obtain the comprehensive optimization parameter value. Based on the comprehensive optimization parameter value, the equivalent fatigue damage model is optimized and adjusted by adopting an adaptive gradient strategy to generate an optimized fatigue damage model.

[0056] Furthermore, the method for constructing the equivalent vehicle load model of the bridge based on fatigue cumulative damage further includes the following steps: Step S106, perform multi-scenario application deployment on the optimized fatigue damage model.

[0057] In the embodiment of the present invention, the optimized fatigue damage model is applied and deployed for bridge design (optimizing the bridge structure form and material selection to improve the anti-fatigue performance of the bridge), bridge assessment (monitoring the response data of the bridge, evaluating the fatigue damage state of the bridge, and timely discovering potential safety hazards), and bridge maintenance (comparing the fatigue damage prediction results before and after reinforcement, evaluating the effectiveness of the reinforcement measures, and providing guidance for subsequent maintenance work).

[0058] Specifically, Figure 7The flowchart of the multi-scenario application deployment of the model in the method provided by the embodiment of the present invention is shown.

[0059] Among them, in the preferred embodiment provided by the present invention, the multi-scenario application deployment of the optimized fatigue damage model specifically includes the following steps: Step S1061, perform application deployment of the optimized fatigue damage model for bridge design; Step S1062, perform application deployment of the optimized fatigue damage model for bridge assessment; Step S1063, perform application deployment of the optimized fatigue damage model for bridge maintenance.

[0060] Furthermore, Figure 8 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0061] Among them, in another preferred embodiment provided by the present invention, a bridge equivalent vehicle load model construction system based on fatigue cumulative damage includes: The bridge traffic monitoring unit 101 is used to perform bridge traffic monitoring according to a preset acquisition frequency and acquisition duration, obtain vehicle load data, and preprocess the vehicle load data to generate standard load data.

[0062] In the embodiment of the present invention, the bridge traffic monitoring unit 101 periodically generates monitoring signals according to a preset acquisition frequency and acquisition duration, and then performs bridge traffic monitoring according to the monitoring signals to obtain vehicle load data. After that, the vehicle load data is subjected to data cleaning (by using a data deduplication algorithm to eliminate duplicate records caused by sensor failures or data transmission errors, using data verification rules or machine learning algorithms to identify and correct significantly incorrect data, and for missing data points, interpolation methods or prediction models based on historical data can be used for filling), and outlier processing (using statistical methods or machine learning algorithms to identify outliers in the data and perform processing such as deletion, replacement with the average or median, or retention and marking) to generate effective load data, and then the effective load data is standardized (scaling the data to a specific range to eliminate the dimension difference, and for non-normal distribution data, methods such as logarithmic transformation and Box-Cox transformation can be used to make it closer to a normal distribution) to generate standard load data.

[0063] Specifically, Figure 9 The structural block diagram of the bridge traffic monitoring unit 101 in the system provided by the embodiment of the present invention is shown.

[0064] Among them, in the preferred embodiment provided by the present invention, the bridge traffic monitoring unit 101 specifically includes: A signal generation module 1011, configured to periodically generate a monitoring signal according to a preset acquisition frequency and acquisition duration; A bridge traffic monitoring module 1012, configured to perform bridge traffic monitoring according to the monitoring signal and obtain vehicle load data; A data cleaning and outlier processing module 1013, configured to perform data cleaning and outlier processing on the vehicle load data to generate valid load data; A normalization processing module 1014, configured to perform normalization processing on the valid load data to generate standard load data.

[0065] Furthermore, the bridge equivalent vehicle load model construction system based on fatigue cumulative damage further includes: A distribution law analysis unit 102, configured to analyze the distribution law of the standard load data, obtain load distribution data, and perform probability fitting on the load distribution data to generate a probability function model.

[0066] In an embodiment of the present invention, the distribution law analysis unit 102 obtains load distribution data by analyzing the distribution laws of vehicle types, time, lanes, vehicle speeds, and vehicle weights of the standard load data, and selects a basic probability model (which can be a Gaussian distribution, a Weibull distribution, a lognormal distribution, a gamma distribution, etc.), and uses methods such as maximum likelihood estimation and moment estimation to perform model parameter estimation to obtain basic estimation parameters. Furthermore, according to the basic estimation parameters and the basic probability model, probability fitting is performed on the load distribution data to generate a probability function model.

[0067] Specifically, Figure 10 FIG. shows a structural block diagram of the distribution law analysis unit 102 in the system provided by an embodiment of the present invention.

[0068] Wherein, in a preferred embodiment provided by the present invention, the distribution law analysis unit 102 specifically includes: A distribution law analysis module 1021, configured to analyze the distribution laws of vehicle types, time, lanes, vehicle speeds, and vehicle weights of the standard load data to obtain load distribution data; A basic model selection module 1022, configured to select a basic probability model; A parameter estimation module 1023, configured to perform model parameter estimation to obtain basic estimation parameters; A probability fitting module 1024, configured to perform probability fitting on the load distribution data according to the basic estimation parameters and the basic probability model to generate a probability function model.

[0069] Furthermore, the bridge equivalent vehicle load model construction system based on fatigue cumulative damage further includes: The fatigue damage assessment unit 103 is used to conduct fatigue damage assessment based on the probability function model and construct a fatigue vehicle load model.

[0070] In an embodiment of the present invention, the fatigue damage assessment unit 103 conducts fatigue damage impact assessment based on the probability function model, records the impact assessment results, and then conducts fatigue damage cumulative analysis of different vehicle types on the bridge according to the impact assessment results, calculates the contribution rate of each vehicle type to the fatigue damage of the bridge, records the damage cumulative data, and then constructs a fatigue vehicle load model according to the damage cumulative data.

[0071] The load model simplification unit 104 is used to simplify the fatigue vehicle load model into an equivalent fatigue damage model.

[0072] In an embodiment of the present invention, the load model simplification unit 104 determines the equivalent principle that the fatigue damage generated by the equivalent vehicle load on the bridge should be equal to the fatigue damage generated by the actual vehicle load, determines the equivalent axle weight and equivalent wheelbase, and then simplifies the fatigue vehicle load model equivalently according to the equivalent axle weight and equivalent wheelbase to construct an equivalent fatigue damage model. After that, model verification and model confirmation processing are carried out on the equivalent fatigue damage model to verify the accuracy and engineering application requirements of the equivalent model.

[0073] The model optimization and adjustment unit 105 is used to generate a simulated fleet, conduct model verification on the equivalent fatigue damage model, obtain the model verification results, and optimize and adjust the equivalent fatigue damage model to generate an optimized fatigue damage model.

[0074] In an embodiment of the present invention, the model optimization and adjustment unit 105 conducts multi-index model verification on the equivalent fatigue damage model by generating a simulated fleet and comparing the load effect of the simulated fleet with the effect of the standard vehicle load model, obtains the model verification results including mean square error, root mean square error, and coefficient of determination, etc., then conducts parameter adjustment analysis according to the model verification results, determines multiple adjustment parameters, and further optimizes and adjusts the equivalent fatigue damage model according to the multiple adjustment parameters to generate an optimized fatigue damage model.

[0075] The scenario application and deployment unit 106 is used to conduct multi-scenario application deployment on the optimized fatigue damage model.

[0076] In an embodiment of the present invention, the scenario application and deployment unit 106 conducts application deployment of the optimized fatigue damage model in bridge design (optimizing the bridge structure form and material selection to improve the anti-fatigue performance of the bridge), application deployment of bridge assessment (monitoring the response data of the bridge, evaluating the fatigue damage state of the bridge, and timely discovering potential safety hazards), and application deployment of bridge maintenance (comparing the fatigue damage prediction results before and after reinforcement, evaluating the effectiveness of reinforcement measures, and providing guidance for subsequent maintenance work).

[0077] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0078] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0079] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered to be within the scope described in this specification.

[0080] The above-described embodiments merely represent several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

[0081] The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for constructing an equivalent vehicle load model of a bridge based on fatigue cumulative damage, characterized in that The method specifically includes the following steps: Perform bridge traffic monitoring according to a preset acquisition frequency and acquisition duration, obtain vehicle load data, and preprocess the vehicle load data to generate standard load data; Analyze the distribution law of the standard load data to obtain load distribution data, and perform probability fitting on the load distribution data to generate a probability function model; Based on the probability function model, conduct fatigue damage assessment and construct a fatigue vehicle load model; Simplify the fatigue vehicle load model into an equivalent fatigue damage model; Generate a simulated vehicle fleet, verify the equivalent fatigue damage model to obtain a model verification result, and optimize and adjust the equivalent fatigue damage model to generate an optimized fatigue damage model; Deploy the optimized fatigue damage model for multi-scenario applications.

2. The method for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage according to claim 1, wherein The step of performing bridge traffic monitoring according to a preset acquisition frequency and acquisition duration, obtaining vehicle load data, and preprocessing the vehicle load data to generate standard load data specifically includes the following steps: Periodically generate monitoring signals according to a preset acquisition frequency and acquisition duration; Perform bridge traffic monitoring according to the monitoring signals to obtain vehicle load data; Perform data cleaning and outlier processing on the vehicle load data to generate effective load data; Perform standardization processing on the effective load data to generate standard load data.

3. The method for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage according to claim 1, characterized in that, The step of analyzing the distribution law of the standard load data to obtain load distribution data, and performing probability fitting on the load distribution data to generate a probability function model specifically includes the following steps: Analyze the distribution laws of vehicle type, time, lane, vehicle speed, and vehicle weight of the standard load data to obtain load distribution data; Select a basic probability model; Perform model parameter estimation to obtain basic estimation parameters; Based on the basic estimation parameters and the basic probability model, perform probability fitting on the load distribution data to generate a probability function model.

4. The method for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage according to claim 3, wherein Based on the basic estimation parameters and the basic probability model, perform probability fitting on the load distribution data to generate a probability function model. The specific steps are as follows: Based on the effective load data, obtain the total sample size and the frequency of each vehicle type. Calculate the ratio of the frequency of each vehicle type to the total sample size to obtain a preliminary vehicle type weight coefficient; Combined with engineering construction parameters, calculate a special vehicle type weight coefficient; Use the special vehicle type weight coefficient to correct the preliminary vehicle type weight coefficient to obtain a corrected vehicle type weight coefficient; Conduct statistical analysis on the standard load data by vehicle type classification. For each vehicle type sample, extract the standard load value corresponding to the vehicle type from the standard load data, calculate the arithmetic mean of the standard load values corresponding to the vehicle type as the distribution center value, and obtain the vehicle type Gaussian distribution parameters based on the distribution center value; Obtain the time stamp of the original load data through the vehicle load data, and determine the day-night influence coefficient through the bridge design specifications; Based on the time stamp of the original load data, statistically obtain the absolute number and relative proportion of vehicle passages in each time period, and then combined with the day-night influence coefficient, calculate the time correction factor; Vehicle position data is obtained from vehicle load data, bridge bearing capacity parameters are determined according to bridge design specifications, the vehicle passing density of each lane within a unit time is counted based on the vehicle position data to calculate the vehicle passing density value per unit time, and the lane correction factor is obtained by combining the vehicle passing density value per unit time with the bridge bearing capacity parameters in a way of calculating the distribution difference coefficient. Based on the Gaussian distribution parameters of vehicle types, weighted processing is carried out in combination with the corrected vehicle type weight coefficient to obtain the weighted probability density intermediate value of the vehicle type at the target load point. The weighted probability density intermediate value of the vehicle type at the target load point is multiplied by the time correction factor to obtain a product result, and the lane correction factor is introduced on the basis of the product result and a secondary product correction is carried out to obtain a multi-correction superposition value. The multi-correction superposition values of all vehicle types at the target load point are algebraically summed to obtain the final load probability value, thus completing the construction of the probability function model.

5. The method for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage according to claim 4, characterized in that, Based on the probability function model, fatigue damage assessment is carried out, and the construction of the fatigue vehicle load model specifically includes the following steps: Based on the probability function model, fatigue damage impact assessment is carried out, and the impact assessment results are recorded. According to the impact assessment results, fatigue damage accumulation analysis of different vehicle types on the bridge is carried out, and the damage accumulation data is recorded. According to the damage accumulation data, a fatigue vehicle load model is constructed.

6. The method for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage according to claim 5, wherein According to the impact assessment results, fatigue damage accumulation analysis of different vehicle types on the bridge is carried out, and the damage accumulation data is recorded. The specific steps are as follows: Key parameters of bridge materials are obtained based on the bridge structure material database. The key parameters of bridge materials include the material reference stress threshold and the material reference durability index value. Based on the effective load data, the passing frequency of each vehicle type and the corresponding axle weight parameter values are determined for each vehicle type. Using the moving load influence line model, the axle weight parameter values of each vehicle type are converted into stress fluctuation values at key parts of the bridge. For the passing frequency of each vehicle type, the difference between the maximum stress and the minimum stress caused by the stress fluctuation value at the key part of the bridge is calculated to obtain the dynamic stress amplitude value. Normalization processing is respectively carried out on the dynamic stress amplitude value and the material reference stress threshold to obtain the normalized dynamic stress amplitude value and the normalized material reference stress threshold, and the multiple relationship of each normalized dynamic stress amplitude value relative to the normalized material reference stress threshold is calculated to obtain the standardized stress coefficient. Based on bridge traffic monitoring, vehicle speed parameters are obtained, divided into multiple speed intervals based on the vehicle speed parameters, and the speed interval correction influence factor is calculated based on the multiple speed intervals. The division result between the standardized stress coefficient and the reference durability index value is calculated, and the division result is multiplied by the corresponding speed interval correction influence factor to obtain the damage accumulation amount caused by a single load action. The damage accumulation amounts caused by single load actions are accumulated to obtain the damage accumulation value of a single vehicle type, and then all the damage accumulation values of single vehicle types are summarized according to the cross-vehicle type dimension to obtain the total damage accumulation value, and the total damage accumulation value is used as the damage accumulation data and recorded.

7. The method for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage according to claim 6, wherein The simplification of the fatigue vehicle load model into an equivalent fatigue damage model specifically includes the following steps: Determine the equal equivalence principle; Based on the equal equivalence principle, determine the equivalent axle load and the equivalent wheelbase; According to the equivalent axle load and the equivalent wheelbase, perform equivalent simplification on the fatigue vehicle load model to construct an equivalent fatigue damage model; Perform model verification and model confirmation processing on the equivalent fatigue damage model; Among them, based on the equal equivalence principle, to determine the equivalent axle load and the equivalent wheelbase, the specific steps to obtain the equivalent axle load are as follows: Obtain a material fatigue characteristic database, and obtain material characteristic parameters based on the material fatigue characteristic database. The material characteristic parameters include a stress sensitivity index and a wheelbase attenuation index; Based on the payload data, extract the actual weighing values of each axle one by one according to the vehicle passing records to obtain a vehicle axle weight table; obtain the vehicle axle position coordinate difference based on the effective load data, and calculate the spacing value between adjacent axles according to the vehicle axle position coordinate difference to obtain a vehicle axle spacing table; match the vehicle axle weight and the vehicle axle spacing of the same vehicle in the order of the axles to obtain an axle load-wheelbase vehicle axle system parameter table; Perform a power operation on the vehicle axle weight using the stress sensitivity index to obtain an axle weight power operation result; perform a power operation on the vehicle axle spacing using the negative of the wheelbase attenuation index to obtain a wheelbase power operation result; multiply the axle weight power operation result and the wheelbase power operation result of the same axle position to obtain a single-axle conversion factor; Determine the axle position influence coefficient through the load distribution data, and multiply the single-axle conversion factor by the corresponding axle position influence coefficient to obtain a weighted comprehensive conversion factor; Perform a summation operation on the weighted comprehensive conversion factors of all axles of the vehicle to obtain a vehicle-level multi-axle accumulation value, and perform a root extraction operation on the vehicle-level multi-axle accumulation value to obtain the equivalent axle load, where the specific value of the root is the stress sensitivity index.

8. The method for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage according to claim 7, characterized in that The generation of a simulated vehicle fleet, the model verification of the equivalent fatigue damage model, obtaining the model verification result, and the optimization and adjustment of the equivalent fatigue damage model to generate an optimized fatigue damage model specifically include the following steps: Generate a simulated vehicle fleet; Through the simulated vehicle fleet, perform multi-index model verification on the equivalent fatigue damage model to obtain the model verification result; According to the model verification result, perform parameter adjustment analysis to determine multiple adjustment parameters; According to the multiple adjustment parameters, perform optimization and adjustment on the equivalent fatigue damage model to generate an optimized fatigue damage model; Among them, according to the multiple adjustment parameters, perform optimization and adjustment on the equivalent fatigue damage model to generate an optimized fatigue damage model. The specific steps are as follows: Determine the sensitivity ranking of the key components of the bridge through the model verification result, and respectively determine the control damage error weight, the response correlation weight, and the parameter stability weight through the sensitivity ranking of the key components of the bridge; Based on the model verification results, obtain the simulation damage value. Based on the equivalent fatigue damage model, output and obtain the equivalent damage value. Calculate the difference between the corresponding simulation damage value and the equivalent damage value at each time point to obtain the difference result. Sum up the squares of all the difference results to obtain the cumulative sum. Take the square root of the cumulative sum to obtain the damage deviation quantification value; Based on the model verification results, obtain the simulation strain value. Based on the equivalent fatigue damage model, output and obtain the equivalent strain value. After aligning the simulation strain value and the equivalent strain value point by point in terms of time points, calculate the Pearson correlation coefficient to obtain the original response value. Determine the ideal response target value according to the actual engineering acceptance standard, and subtract the original response value from the ideal response target value to obtain the response deviation quantification value; Based on the multiple adjustment parameters, statistically analyze the numerical distribution range of each adjustment parameter and simultaneously determine the parameter characteristic constraint rules. Based on the numerical distribution range of each adjustment parameter, obtain the overall stability value of the parameter group by calculating the degree of dispersion. Apply the parameter characteristic constraint rules to the overall stability value of the parameter group to obtain the parameter stability index value; Multiply the damage deviation quantification value by the control damage error weight to obtain the first optimization parameter value. Multiply the response deviation quantification value by the response correlation weight to obtain the second optimization parameter value. Multiply the parameter stability index value by the parameter stability weight to obtain the third optimization parameter value. Add the first optimization parameter value, the second optimization parameter value, and the third optimization parameter value to obtain the comprehensive optimization parameter value; Based on the comprehensive optimization parameter value, adopt an adaptive gradient strategy to optimize and adjust the equivalent fatigue damage model to generate an optimized fatigue damage model.

9. The method for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage according to claim 1, wherein The multi-scenario application deployment of the optimized fatigue damage model specifically includes the following steps: Conduct application deployment of the optimized fatigue damage model for bridge design; Conduct application deployment of the optimized fatigue damage model for bridge assessment; Conduct application deployment of the optimized fatigue damage model for bridge maintenance.

10. A system for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage, characterized in that, The system applies the method for constructing a bridge equivalent vehicle load model based on fatigue cumulative damage as described in any one of claims 1 to 9 above. The system includes: A bridge traffic monitoring unit, which is used to conduct bridge traffic monitoring according to a preset acquisition frequency and acquisition duration, obtain vehicle load data, and preprocess the vehicle load data to generate standard load data; A distribution law analysis unit, which is used to analyze the distribution law of the standard load data, obtain load distribution data, and perform probability fitting on the load distribution data to generate a probability function model; A fatigue damage assessment unit, which is used to conduct fatigue damage assessment based on the probability function model and construct a fatigue vehicle load model; A load model simplification unit, which is used to simplify the fatigue vehicle load model into an equivalent fatigue damage model; A model optimization and adjustment unit, which is used to generate a simulated vehicle fleet, conduct model verification on the equivalent fatigue damage model, obtain model verification results, and optimize and adjust the equivalent fatigue damage model to generate an optimized fatigue damage model; A scenario application deployment unit, which is used to conduct multi-scenario application deployment of the optimized fatigue damage model.

Images