Vehicle load analysis method for bridge based on temperature compensation and related device

Abstract

The application relates to the technical field of vehicle load analysis, and provides a bridge vehicle load analysis method based on temperature compensation and related devices, which comprises the following steps: acquiring a temperature measurement sample data set corresponding to a temperature sensor of a bridge to be detected, and acquiring a strain measurement sample data set corresponding to a strain sensor of the bridge to be detected; performing verification processing on each temperature measurement sample data in the temperature measurement sample data set to obtain a temperature verification sample data set; constructing a temperature-strain analysis model according to the temperature verification sample data set and the strain measurement sample data set; performing temperature compensation processing on the basis of the temperature-strain analysis model according to a to-be-processed temperature data set and a to-be-processed strain data set to obtain a target strain compensation value set; performing vehicle load analysis processing on each target strain compensation value in the target strain compensation value set to obtain a vehicle load analysis result of the bridge to be detected, and improving the accuracy of the vehicle load analysis process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle load analysis and data processing, in particular to a bridge vehicle load analysis method based on temperature compensation and related device. BACKGROUND

[0002] In the field of bridge engineering, vehicle load analysis is crucial for accurately assessing the safety, durability, and long-term performance of bridge structures. Currently, with the continuous development of transportation infrastructure, the traffic volume carried by bridges is increasing, and the types and driving conditions of vehicles are becoming increasingly complex and diverse. In existing vehicle load analysis methods, most methods only focus on a single or a few influencing factors and do not fully consider the comprehensive effects of multiple factors. For example, when calculating vehicle load, only the static design parameters of the bridge and the rated load of the vehicle are considered, and other influencing factors during the actual operation of the bridge are ignored, which leads to inaccurate vehicle load analysis results. Therefore, how to improve the accuracy of the vehicle load analysis process has become a problem to be solved. SUMMARY

[0003] The embodiments of the present application provide a bridge vehicle load analysis method based on temperature compensation and related device, which can construct a temperature strain analysis model according to a temperature measurement sample data set and a strain measurement sample data set, and perform compensation processing on a to-be-processed temperature data set and a to-be-processed strain data set based on the temperature strain analysis model, to improve the accuracy of the obtained target strain compensation value set.

[0004] The first aspect of the embodiments of the present application provides a bridge vehicle load analysis method based on temperature compensation, which comprises:

[0005] Obtain a temperature measurement sample data set corresponding to a temperature sensor of a to-be-detected bridge, and obtain a strain measurement sample data set corresponding to a strain sensor of the to-be-detected bridge;

[0006] Perform verification processing on each temperature measurement sample data in the temperature measurement sample data set to obtain a temperature verification sample data set;

[0007] Construct a temperature strain analysis model according to the temperature verification sample data set and the strain measurement sample data set;

[0008] Perform compensation processing on a to-be-processed temperature data set and a to-be-processed strain data set based on the temperature strain analysis model to obtain a target strain compensation value set;

[0009] Perform vehicle load analysis processing on each target strain compensation value in the target strain compensation value set to obtain a vehicle load analysis result of the to-be-detected bridge.

[0010] In this example, by obtaining a temperature measurement sample data set corresponding to a temperature sensor of a bridge to be detected and obtaining a strain measurement sample data set corresponding to a strain sensor of the bridge to be detected, each temperature measurement sample data in the temperature measurement sample data set can be verified to obtain a temperature verification sample data set, and a temperature-strain analysis model can be constructed according to the temperature verification sample data set and the strain measurement sample data set. Thus, based on the temperature-strain analysis model, temperature compensation processing can be performed according to a to-be-processed temperature data set and a to-be-processed strain data set to obtain a target strain compensation value set, and each target strain compensation value in the target strain compensation value set can be subjected to vehicle load analysis processing to obtain a more accurate vehicle load analysis result of the bridge to be detected. Thus, the temperature strain value caused by the temperature factor can be removed, and the purpose of more accurate vehicle load analysis can be achieved.

[0011] The second aspect of the embodiment of the present application provides a bridge vehicle load analysis device based on temperature compensation, and the device comprises:

[0012] An acquisition module is configured to obtain a temperature measurement sample data set corresponding to a temperature sensor of a bridge to be detected and obtain a strain measurement sample data set corresponding to a strain sensor of the bridge to be detected.

[0013] A first processing module is configured to verify each temperature measurement sample data in the temperature measurement sample data set to obtain a temperature verification sample data set.

[0014] A second processing module is configured to construct a temperature-strain analysis model according to the temperature verification sample data set and the strain measurement sample data set.

[0015] A third processing module is configured to perform compensation processing according to a to-be-processed temperature data set and a to-be-processed strain data set based on the temperature-strain analysis model to obtain a target strain compensation value set.

[0016] A fourth processing module is configured to perform vehicle load analysis processing on each target strain compensation value in the target strain compensation value set to obtain a vehicle load analysis result of the bridge to be detected.

[0017] The third aspect of the embodiment of the present application provides a terminal, which comprises a processor, an input device, an output device and a memory, and the processor, the input device, the output device and the memory are connected to each other. The memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to invoke the program instructions to execute the steps as in the first aspect of the embodiment of the present application.

[0018] A fourth aspect of the embodiments of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application.

[0019] A fifth aspect of the embodiments of the present application provides a computer program product, which includes a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product can be a software installation package. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0021] Figure 1 A structural schematic diagram of a vehicle load analysis system of a bridge based on temperature compensation is provided for the embodiments of the present application;

[0022] Figure 2 A flowchart of a vehicle load analysis method of a bridge based on temperature compensation is provided for the embodiments of the present application;

[0023] Figure 3 A structural schematic diagram of a terminal is provided for the embodiments of the present application;

[0024] Figure 4 A structural schematic diagram of a vehicle load analysis device of a bridge based on temperature compensation is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0025] The technical solutions of the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort fall within the scope of the present application.

[0026] The terms "first", "second", and the like in the description and in the claims of the present application and above drawings are used for distinguishing between similar objects, not for describing a particular sequential order. The terms "comprises", "comprising", "includes", "including" and the like are to be construed open- ended, meaning that they include the listed steps or elements, but not excluding other steps or elements. For example, a process, method, article, or apparatus that comprises a list of steps or elements is not necessarily limited to the listed steps or elements, but can include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

[0027] Reference to "an embodiment" or "the embodiment" in this application means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" or "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all directed to the same embodiment, or to a single alternative embodiment. It is expressly understood that any of the embodiments described herein can be combined with any of the other embodiments unless specifically noted to the contrary.

[0028] In order to better understand the bridge vehicle load analysis method based on temperature compensation provided by the embodiments of the present application, first, the scene of applying the bridge vehicle load analysis method based on temperature compensation is briefly introduced. The bridge bears various vehicle loads in the process of use, and accurate analysis of vehicle load can determine the maximum load and load distribution of the bridge, provide key basis for bridge management and life assessment, and prevent safety problems such as structural damage and excessive deformation of the bridge caused by excessive load. However, the existing vehicle load analysis method has significant limitations. Most of the current vehicle load analysis methods only focus on a single or a few influencing factors, and do not fully consider the comprehensive effect of multiple factors. For example, when calculating the vehicle load, only the static design parameters of the bridge and the rated load of the vehicle are often used, and the influence of temperature change on the mechanical properties of the bridge structure in the actual operation process of the bridge is ignored. The rise and fall of temperature will cause the thermal expansion and contraction of the bridge material, change the stiffness and stress distribution of the bridge, and thus affect the transmission and distribution of the vehicle load on the bridge, and further cause the vehicle load analysis process to be not accurate enough. The embodiments of the present application aim to solve the problem of not accurate enough vehicle load analysis process, and provide a bridge vehicle load analysis method based on temperature compensation. The method can further construct a temperature strain analysis model by using the obtained temperature measurement sample data set and strain measurement sample data set, remove the temperature strain value caused by the temperature factor, obtain strain data that can better reflect the real strain situation, and is beneficial to realize the purpose of more accurate vehicle load analysis.

[0029] The bridge vehicle load analysis method based on temperature compensation can be applied to a bridge vehicle load analysis system based on temperature compensation, Figure 1A structural diagram of a vehicle load analysis system based on temperature compensation of a bridge is shown. As shown in Figure 1 The vehicle load analysis system based on temperature compensation of a bridge can include a data acquisition module, a temperature measurement data verification module, a temperature strain analysis model construction module, a temperature compensation processing module, and a vehicle load analysis module, etc. Among them, the data acquisition module can be responsible for acquiring temperature measurement sample data generated by the temperature sensor on the bridge to be detected, and strain measurement sample data generated by the strain sensor, and can integrate them into corresponding data sets; the temperature measurement data verification module can perform verification operation on each temperature measurement sample data in the temperature measurement sample data set, to output more accurate and reliable temperature verification sample data set through outlier rejection, deviation correction, etc.; the temperature strain analysis model construction module can build a temperature strain analysis model that can reflect the relationship between temperature and strain based on the temperature verification sample data set and the strain measurement sample data set; the temperature compensation processing module can develop temperature compensation operation on the temperature data set to be processed and the strain data set to be processed by means of the constructed temperature strain analysis model, so as to obtain a target strain compensation value set after eliminating the temperature influence; the vehicle load analysis module can further perform vehicle load analysis on each target strain compensation value in the target strain compensation value set, to comprehensively consider various factors, and finally generate more accurate vehicle load analysis results corresponding to the bridge to be detected.

[0030] Please refer to Figure 2 , Figure 2 A flowchart of a vehicle load analysis method based on temperature compensation of a bridge is provided for the embodiments of the present application, which comprises:

[0031] S10: acquiring a temperature measurement sample data set corresponding to a temperature sensor of a bridge to be detected, and acquiring a strain measurement sample data set corresponding to a strain sensor of the bridge to be detected.

[0032] Among them, the temperature measurement sample data set can include temperature measurement sample data measured by one or more temperature sensors equipped on the bridge to be detected within one or more time periods. That is, the temperature measurement sample data can be understood as temperature sample data of multiple time periods corresponding to multiple measurement points measured by each temperature sensor installed on the bridge to be detected. It can be understood that the temperature measurement sample data can reflect the temperature of the environment where the bridge to be detected is located at that time.

[0033] It should be noted that the temperature measurement sample data set and the to-be-processed temperature data set to be mentioned later can be temperature data sets corresponding to different time periods, such as the temperature measurement sample data set can be a temperature data set corresponding to January-December last year, and the to-be-processed temperature data set can be a temperature data set corresponding to January-March this year. The present application does not limit this.

[0034] The strain measurement sample data set can include strain measurement sample data measured by one or more strain sensors equipped on the bridge under test within one or more time periods. That is, the strain measurement sample data can be understood as strain sample data of multiple measurement points in multiple time periods obtained by the strain sensors on the bridge under test. It should be noted that the measurement period of the strain measurement sample data can correspond one by one to the measurement period of the temperature measurement sample data, so that the temperature value and the strain value of the same measurement point in the same period can be analyzed in the subsequent processing process. It can be understood that the strain measurement sample data can reflect the deformation of the bridge structure under the action of various factors.

[0035] It should be noted that the strain measurement sample data set and the to-be-processed strain data set to be mentioned later can be strain data sets corresponding to different time periods, such as the strain measurement sample data set can be a strain data set corresponding to January-December last year, and the to-be-processed strain data set can be a strain data set corresponding to January-March this year. The present application does not limit this.

[0036] It should be noted that since the strain value obtained by the strain sensor can be affected by various factors, among which temperature can be regarded as a more critical influencing factor, temperature changes will cause thermal expansion and contraction of the bridge structure material, and then the strain value measured by the strain sensor includes the vehicle load strain value caused by the vehicle load and the temperature strain value caused by the temperature. Specifically, when the temperature rises, the bridge structure will expand, and even if the bridge is not subjected to external load at this time, the strain sensor can measure a positive strain value. Conversely, when the temperature decreases, the bridge structure shrinks, and the strain sensor can measure a negative strain value.

[0037] The strain caused by temperature changes can be referred to as temperature strain, which is superimposed with the strain generated by the vehicle load borne by the bridge structure, so that the strain value measured by the strain sensor cannot accurately reflect the actual vehicle load state borne by the bridge structure. Therefore, when analyzing and applying the strain measurement sample data of the bridge, the influence of the temperature factor must be considered, and corresponding temperature compensation measures must be taken to eliminate or reduce the interference of the temperature strain, so as to obtain more accurate strain information that can be used to evaluate the health status of the bridge structure. The present application does not limit this.

[0038] S20: verifying each temperature measurement sample data in the temperature measurement sample data set to obtain a temperature verification sample data set.

[0039] The temperature verification sample data set can include one or more temperature verification sample data, which can be understood as more accurate temperature data obtained after verifying each temperature measurement sample data. By verifying the temperature measurement sample data, measurement errors caused by the temperature sensor can be further excluded, thereby ensuring the accuracy and reliability of the temperature data after verification.

[0040] Specifically, each temperature measurement sample data in the temperature measurement sample data set can be cleaned to check whether there are obvious errors or abnormal values in the temperature measurement sample data, such as temperature values exceeding a reasonable range or data missing, and the abnormal data can be corrected or deleted. Optionally, the temperature sensor can be calibrated, such as comparing the temperature sensor with a high-precision standard thermometer to obtain a calibration curve or a calibration coefficient, so that the temperature measurement sample data can be calibrated based on the calibration curve or the calibration coefficient to eliminate the system error of the sensor itself.

[0041] Optionally, a repeatability verification method can be used, such as measuring the temperature of the same test point multiple times to check the repeatability of the temperature measurement data. If the multiple temperature measurement values of the same test point differ greatly, the reason can be further analyzed and adjusted. Optionally, a data filtering method can be used, such as mean filtering or median filtering, to remove noise in the temperature measurement sample data, thereby improving the stability and accuracy of the temperature measurement sample data, which is not limited in the present application.

[0042] S30: constructing a temperature-strain analysis model according to the temperature verification sample data set and the strain measurement sample data set.

[0043] The temperature-strain analysis model can be understood as a model constructed based on the temperature verification sample data set and the strain measurement sample data set to describe the relationship between the temperature and the strain of the bridge structure. By constructing the temperature-strain analysis model, the correlation between the temperature and the strain can be better established, so that the influence of the temperature on the strain can be excluded in the subsequent temperature compensation process, thereby obtaining more accurate and more intuitive vehicle load analysis results.

[0044] It needs to be understood that constructing the temperature strain analysis model according to the temperature calibration sample data and the strain measurement sample data refers to a process of how to construct a temperature strain analysis model for indicating the correlation between temperature and strain according to the temperature calibration sample data and the strain measurement sample data. In step S30, that is, constructing the temperature strain analysis model according to the temperature calibration sample data and the strain measurement sample data, can include the following steps:

[0045] S31: performing feature mapping on the temperature calibration sample data and the strain measurement sample data to obtain a high-dimensional linear feature vector;

[0046] S32: constructing a temperature strain analysis function according to the temperature calibration sample data and the strain measurement sample data;

[0047] S33: determining a temperature strain constraint condition according to the temperature calibration sample data and the strain measurement sample data and the high-dimensional linear feature vector;

[0048] S34: constructing a temperature strain regression optimization function according to the temperature strain analysis function and the temperature strain constraint condition;

[0049] S35: performing optimal solution processing on the temperature strain regression optimization function to obtain a target Lagrange multiplier set and a target temperature strain analysis parameter set;

[0050] S36: constructing a temperature strain analysis model according to the target Lagrange multiplier set and the target temperature strain analysis parameter set.

[0051] The high-dimensional linear feature vector can be understood as a vector representation in a high-dimensional space obtained after feature mapping of the temperature calibration sample data and the strain measurement sample data. The high-dimensional linear feature vector can reflect the feature information of the original data (i.e., the temperature calibration sample data and the strain measurement sample data) in the high-dimensional space, and these feature information can have a linear correlation in the high-dimensional space.

[0052] Specifically, a suitable feature mapping function can be selected according to the data characteristics of the temperature calibration sample data and the strain measurement sample data and the complexity of the problem to be solved (i.e., the correlation between temperature and strain), such as a radial basis kernel function, a linear kernel function, or a polynomial kernel function, to perform feature mapping on the temperature calibration sample data and the strain measurement sample data to obtain a high-dimensional linear feature vector. Optionally, the present application selects a radial basis kernel function to perform feature mapping on the temperature calibration sample data and the strain measurement sample data and obtain a high-dimensional linear feature vector, which does not limit the present application.

[0053] An exemplary process of data integration of the temperature calibration sample data and the strain measurement sample data to obtain a temperature strain data set For example, the process of obtaining the temperature strain data set may refer to the following formula:

[0054]

[0055] wherein, represents the temperature strain data set; represents the first temperature calibration sample data; represents the first strain measurement sample data; represents the second temperature calibration sample data; represents the second strain measurement sample data; represents the nth temperature calibration sample data; represents the nth strain measurement sample data.

[0056] Optionally, the present application adopts a radial basis kernel function to implement the process of feature mapping of the temperature calibration sample data and the strain measurement sample data and obtaining a high-dimensional linear feature vector, which may refer to the following formula:

[0057]

[0058] wherein, is a feature mapping function for mapping input data to a high-dimensional feature space, represents mapping of the ith temperature calibration sample data to the high-dimensional feature space, represents the ith temperature calibration sample data, represents mapping of the ith strain measurement sample data to the high-dimensional feature space, represents the ith strain measurement sample data, represents an index of the temperature calibration sample data or the strain measurement sample data; represents calculation of the similarity between and by using the radial basis kernel function, the present application defines the inner product of two samples (i.e. the temperature calibration sample data and the strain measurement sample data) in the feature space by using the radial basis kernel function, implicitly realizes the mapping to the high-dimensional feature space, and can avoid directly calculating the feature mapping function and performing complex operations in the high-dimensional space in the subsequent calculation process, so as to calculate the inner product of the samples in the high-dimensional feature space without explicitly knowing the specific form of the feature mapping function , and thus is conducive to better model training and prediction and the like; represents calculation by using an exponential function; represents a hyperparameter, which is usually referred to as a kernel coefficient in the related application of the radial basis kernel function; represents a norm, which usually refers to the Euclidean norm; represents a calculation and between the Euclidean distances.

[0059] It should be noted that the radial basis kernel function used in the present application can measure the similarity between two samples (i.e. and ) by calculating the distance between them. Among them, can control the width of the radial basis kernel function, the larger the function is, the narrower the function is, and the better the fitting ability of local data is, but it may cause overfitting; the smaller the function is, the wider the function is, and the better the generalization ability of the model is, but it may cause poor fitting effect, which is not limited in the present application. Optionally, the radial basis kernel function can be used to calculate the similarity between two temperature calibration sample data, i.e. ; the radial basis kernel function can also be used to calculate the similarity between two strain measurement sample data, i.e. , which is not limited in the present application.

[0060] The temperature strain analysis function can be understood as a mathematical function constructed based on the temperature calibration sample data and the strain measurement sample data, which can be used to describe the relationship between the temperature and the strain. Optionally, the temperature strain analysis function can usually include the complexity of the model and the fitting degree of the data, etc., which is not limited in the present application. Optionally, the present application can determine the model parameters based on the principle of solving the optimization problem, which is not limited in the present application.

[0061] The temperature strain constraint condition can be understood as a limiting condition imposed on the parameters or variables of the model according to the characteristics of the temperature calibration sample data and the strain measurement sample data and the actual requirements of solving the problem. The temperature strain constraint condition can further ensure the rationality and feasibility of the model, for example, it can limit the error range between the predicted value and the true value of the model, etc., which is not limited in the present application.

[0062] Specifically, the present application constructs a temperature strain analysis function according to the temperature calibration sample data and the strain measurement sample data, and determines a temperature strain constraint condition according to the temperature calibration sample data and the strain measurement sample data, which can be referred to the following formula:

[0063] Temperature strain analysis function:

[0064]

[0065]

[0066]

[0067]

[0068] wherein, denotes a target weight parameter, denotes a target bias parameter, and is a slack variable, , , and are model parameters; denotes a temperature strain analysis function , , and is determined for model parameters ; denotes an index of temperature check sample data or strain measurement sample data or slack variable, denotes a number of temperature check sample data or strain measurement sample data in a temperature strain data set; denotes a norm of ; is a penalty parameter; denotes a temperature strain constraint condition; denotes an i-th strain measurement sample data; denotes a transpose of a target weight parameter; denotes a feature mapping function mapping input data to a high-dimensional feature space, denotes mapping of an i-th temperature check sample data to a high-dimensional feature space; is an insensitive loss parameter.

[0069] It should be noted that, according to the above temperature strain analysis function and the temperature strain constraint condition, a temperature strain regression optimization function is constructed and obtained based on the principle of a support vector machine regression process, that is, the temperature strain regression optimization function is constituted by the temperature strain analysis function and the temperature strain constraint condition as a whole, which is not limited by the present application. The support vector machine regression process can be understood as finding an optimal hyperplane (in a high-dimensional feature space) to fit the data, so that the error of the model on the training data is as small as possible, while keeping the complexity of the model low to avoid overfitting.

[0070] wherein, can be regarded as an objective function, which can be used to control the complexity of the model, so that the model has good generalization ability; denotes a weight vector The smaller the norm square of the error, the simpler the model and the stronger the generalization ability. The error of the training data can be regarded as a penalty term, It can be a preset constant for balancing model complexity and training error. The larger the penalty, the more severe the error, and the model will tend to reduce the training error, but may cause overfitting. Optionally, the initial value of the penalty parameter can be determined by the empirical value method, such as in the support vector machine, when processing general classification or regression problems, the initial value of C can be set to 1, and C=1 can achieve a relatively reasonable balance between model complexity and training error. Optionally, cross-validation or grid search method can also be used to determine the initial value of the penalty parameter, which is not limited in the present application. The insensitive loss parameter can represent the error in the range of , which can be used to control the fitting accuracy of the model to the data. and are slack variables, which can allow the data points to deviate from the ideal fitting line to a certain extent during the model training process, in order to handle noise and outliers in the data. Optionally, a rough value range of the insensitive loss parameter can be determined by the empirical value method, for example, in the regression problem, if the noise level of the data is low, a smaller τ value such as 0.01 can be selected; if the noise level is high, a larger τ value such as 0.1 can be selected, which is not limited in the present application. Optionally, cross-validation or grid search method can also be used to determine the initial value of the insensitive loss parameter, which is not limited in the present application.

[0071] Specifically, the temperature strain constraint condition represents that for each data point , the error between the predicted value and the true value should be within the range of , otherwise a certain deviation is allowed through the slack variables and , and is penalized in the objective function.

[0072] Further, the optimal solution processing of the temperature strain regression optimization function can be understood as adjusting the model parameters , , and based on the temperature strain data set to further obtain the target Lagrange multiplier set and the target temperature strain analysis parameter set (i.e. adjusted , , and ), to find a balance between minimizing model complexity and minimizing training error; wherein the radial basis kernel function can help the model to better handle the nonlinear relationship by mapping the data to a high-dimensional feature space, thereby better reducing the complexity of the model in the optimal solution process to train a more accurate model.

[0073] The target Lagrange multiplier set can include one or more target Lagrange multipliers, which can be understood as a set of Lagrange multipliers obtained after the optimal solution process of the temperature strain regression optimization function. The target Lagrange multiplier can be used to determine the parameters and structure of the model in the process of constructing the temperature strain analysis model.

[0074] The target temperature strain analysis parameter set can include one or more target temperature strain analysis parameters, which can be understood as a set of parameters obtained after solving the temperature strain regression optimization function. These parameters can be used together with the target Lagrange multiplier to construct the final temperature strain analysis model, thereby achieving the goal of describing the relationship between temperature and strain.

[0075] It should be understood that based on the sequence minimum optimization algorithm, the optimal solution process of the temperature strain regression optimization function to obtain the target Lagrange multiplier set and the target temperature strain analysis parameter set refers to the process of how to perform the optimal solution process on the temperature strain regression optimization function to obtain the optimal model parameters. In step S35, i.e., based on the sequence minimum optimization algorithm, the optimal solution process of the temperature strain regression optimization function to obtain the target Lagrange multiplier set and the target temperature strain analysis parameter set can include the following steps:

[0076] S351: based on the sequence minimum optimization algorithm and the Lagrange multiplier method, performing dual conversion on the temperature strain regression optimization function to obtain a temperature strain dual function;

[0077] S352: selecting a reference Lagrange multiplier from the initialized Lagrange multiplier set;

[0078] S353: based on the reference Lagrange multiplier, performing optimal solution on the temperature strain dual function to obtain a target Lagrange multiplier set;

[0079] S354: calculating the bias according to each target Lagrange multiplier in the target Lagrange multiplier set to obtain a target bias parameter;

[0080] S355: calculating the weight vector according to each target Lagrange multiplier in the target Lagrange multiplier set to obtain a target weight parameter;

[0081] S356: determining a target temperature strain analysis parameter set according to the target bias parameter and the target weight parameter.

[0082] Wherein, a sequence minimum optimization algorithm (SMO) can be used to solve the quadratic programming problem in the support vector machine, the core of which is to select two Lagrange multipliers for optimization each time, and constantly iterate until the convergence condition is met. In the step of the optimal solution processing of the present application, the essence is also to process similar optimization problems, that is, to solve the optimal Lagrange multiplier and model parameter for the temperature strain regression optimization function.

[0083] The temperature strain dual function can be understood as a function obtained by dual conversion of the temperature strain regression optimization function by the Lagrange multiplier method, which is used to further solve the model parameter. In the process of optimal solution processing, the original problem (i.e. the aforementioned temperature strain regression optimization function) can be converted into its dual problem. The dual problem has the same optimal solution as the original problem under certain conditions, and the dual problem is usually easier to solve.

[0084] Optionally, the process of dual conversion of the temperature strain regression optimization function based on the sequence minimum optimization algorithm and the Lagrange multiplier method to obtain the temperature strain dual function can be referred to the following formula:

[0085]

[0086]

[0087]

[0088] Wherein, and is the Lagrange multiplier (such as the i-th group of Lagrange multipliers), is the i-th strain measurement sample data, is the temperature calibration sample data sample, represents the index of the temperature calibration sample data or the strain measurement sample data or the Lagrange multiplier, represents the number of temperature calibration sample data or strain measurement sample data in the temperature strain data set, is the insensitive loss parameter, and is the Lagrange multiplier (such as the j-th group of Lagrange multipliers), is the similarity between and calculated by using the radial basis kernel function; and represents the maximum value of the temperature strain dual function calculated for the i-th group of Lagrange multipliers; ​is a constraint condition of the temperature strain dual function, is a penalty parameter.

[0089] The initialization Lagrange multiplier set can include one or more initialization Lagrange multipliers, which can be understood as the initial values of the Lagrange multipliers preset before starting the optimization solution. It can be understood that the initialization Lagrange multipliers can be regarded as the starting point of the subsequent iterative solution, and the present application does not make any limitation. The reference Lagrange multiplier can be a Lagrange multiplier selected from the initialization Lagrange multiplier set for optimizing the solution of the temperature strain dual function.

[0090] It should be noted that during the optimal solution process, the present application can divide a large optimization problem into multiple small sub-problems, and each time a set of Lagrange multipliers (i.e. reference Lagrange multipliers) is selected for optimization solution, while fixing other Lagrange multipliers, to simplify the quadratic optimal solution problem into a binary quadratic optimal solution problem that is easier to solve, so that the Lagrange multipliers can be updated iteratively in the subsequent process until the convergence condition is met, and then the target Lagrange multiplier set is obtained. The target Lagrange multiplier set can include one or more target Lagrange multipliers, which can be understood as a set of optimal Lagrange multipliers obtained after optimizing the solution of the temperature strain dual function. Specifically, the convergence condition can be set to the update amount of the Lagrange multiplier being less than the update threshold, or the change amount of the objective function value being less than the change threshold, and the present application does not make any limitation.

[0091] After obtaining the target Lagrange multiplier set, the bias can be further calculated according to the target Lagrange multiplier to obtain the target bias parameter. Specifically, the sample points that satisfy the Karush-Kuhn-Tucker (KKT) condition can be selected to calculate the bias, and the present application does not make any limitation.

[0092] For example, the sample points that satisfy the KKT condition are , the target Lagrange multiplier obtained by solving is and For example, the process of calculating the bias , can be seen from the following formula:

[0093]

[0094]

[0095] wherein, represents strain measurement sample data satisfying the KKT condition; represents temperature verification sample data satisfying the KKT condition; and is a target Lagrange multiplier; represents an index of temperature verification sample data or strain measurement sample data or a Lagrange multiplier; represents a number of temperature verification sample data or strain measurement sample data in a temperature strain data set; represents a similarity between and calculated by using a radial basis kernel function; and represents a target bias parameter; represents an insensitive loss parameter.

[0096] Further, a weight vector can be calculated according to the target Lagrange multiplier, so as to obtain a target weight parameter. For example, the target Lagrange multiplier obtained by solving is and For example, the process of calculating the weight vector can refer to the following formula:

[0097]

[0098] wherein, represents a target weight parameter; and represents a target Lagrange multiplier; represents an index of temperature verification sample data or strain measurement sample data or a Lagrange multiplier; represents a number of temperature verification sample data or strain measurement sample data in a temperature strain data set; represents a feature mapping function for mapping input data to a high-dimensional feature space, represents mapping the i-th temperature verification sample data to a high-dimensional feature space. It should be noted that in actual calculation, the can be obtained indirectly by using a kernel function, without directly solving The present application does not make any limitation.

[0099] It should be noted that after the optimal solution processing, a temperature strain analysis model can be constructed according to the target Lagrange multiplier set and the target temperature strain analysis parameter set. For example, the target Lagrange multiplier obtained by solving is and For example, the obtained temperature strain analysis model can refer to the following formula:

[0100]

[0101] wherein, is a temperature strain analysis model, used for predicting a strain value corresponding to the temperature data to be processed; ​​any of the to-be-processed temperature data in the to-be-processed temperature data set; strain data predicted by the temperature strain analysis model, i.e., the temperature strain evaluation data to be mentioned later; and denotes a target Lagrange multiplier; denotes an index of the temperature verification sample data or the strain measurement sample data or the Lagrange multiplier; denotes the number of the temperature verification sample data or the strain measurement sample data in the temperature strain data set; the similarity between and is calculated using a radial basis kernel function; denotes a target bias parameter.

[0102] S40: performing temperature compensation processing based on the temperature strain analysis model according to the to-be-processed temperature data set and the to-be-processed strain data set to obtain a target strain compensation value set.

[0103] The target strain compensation value set can include one or more target strain compensation values, which can be understood as strain values that can more accurately reflect the real strain condition of the bridge after excluding the temperature influence after temperature compensation processing.

[0104] It should be understood that the temperature compensation processing based on the temperature strain analysis model according to the to-be-processed temperature data set and the to-be-processed strain data set to obtain the target strain compensation value set refers to a process of how to perform compensation processing based on the constructed temperature strain analysis model to obtain a target strain compensation value set that can reflect the real strain condition after excluding the temperature influence. In step S40, i.e., the temperature compensation processing based on the temperature strain analysis model according to the to-be-processed temperature data set and the to-be-processed strain data set to obtain the target strain compensation value set, the following steps can be included:

[0105] S41: performing temperature strain analysis processing based on the temperature strain analysis model according to each to-be-processed temperature data in the to-be-processed temperature data set to obtain a temperature strain evaluation data set;

[0106] S42: performing compensation processing according to the temperature strain evaluation data set and the to-be-processed strain data set to obtain a reference compensation strain data set;

[0107] S43: performing compensation result correction processing on each reference compensation strain data in the reference compensation strain data set to obtain a corrected strain compensation value set;

[0108] S44: Perform stability assessment processing on each modified strain compensation value in the set of modified strain compensation values ​​to obtain the set of target strain compensation values.

[0109] The set of temperature data to be processed may include one or more temperature data points. These temperature data points can be understood as those requiring temperature strain analysis and subsequent compensation processing. Specifically, the temperature data to be processed can be based on a temperature strain analysis model. Temperature strain analysis is performed to predict the strain value caused by temperature factors, i.e., to obtain temperature strain assessment data. This application does not impose any restrictions on this.

[0110] Optionally, based on the temperature strain analysis model, the process of performing temperature strain analysis on each temperature data point in the set of temperature data to be processed to obtain a temperature strain evaluation data set can be found in the following formula:

[0111]

[0112] in, This represents temperature strain assessment data; and Indicates the target Lagrange multiplier; This represents the radial basis function kernel function, which can be used in practical calculations. To calculate temperature strain assessment data; This represents the temperature verification sample data of the i-th temperature; This represents the temperature data to be processed; This represents the target bias parameter.

[0113] The reference compensated strain data set may include one or more reference compensated strain data sets. These reference compensated strain data sets can be understood as data that more accurately reflects the actual strain of the vehicle load after temperature compensation processing. Optionally, the process of obtaining the reference compensated strain data set by performing temperature compensation processing on the temperature strain evaluation data set and the strain data set to be processed can be found in the following formula:

[0114]

[0115] in, For reference compensation strain data; The strain measurement sample data obtained from actual measurements, i.e., the strain data to be processed; This is data for temperature strain assessment. It should be noted that by using this formula, the strain component caused by temperature changes can be removed from the strain data to be processed, resulting in strain data that better reflects the strain caused by vehicle load.

[0116] The modified strain compensation value set can include one or more modified strain compensation values, which can be understood as strain data obtained by further modifying the reference compensation strain data. Since the temperature strain analysis model can have some errors, and other factors not considered in the actual environment, the reference compensation strain data calculated can be modified. Specifically, a correction coefficient can be obtained through statistical analysis of historical data, and the reference compensation strain data can be fine-tuned based on the correction coefficient to obtain more accurate modified strain compensation values. Specifically, a linear correction coefficient method can be used to find a suitable linear correction coefficient through statistical analysis of historical data, and the reference compensation strain data can be linearly adjusted using the coefficient. Alternatively, a filter algorithm correction method can be used to effectively remove noise and outliers in the data, making the modified strain compensation values smoother and more accurate. Common filter algorithms include moving average filtering and Kalman filtering, which are not limited by the present application. Alternatively, a machine learning-based correction method can be used to modify the reference compensation strain data using machine learning algorithms such as neural networks, support vector regression, etc., which are not limited by the present application.

[0117] Further, after the compensation result modification process, the stability of each modified strain compensation value can be evaluated to evaluate the stability of the obtained strain data. Alternatively, the stability evaluation process can include checking the data fluctuation, whether there are outliers, and other data quality evaluation processes, which are not limited by the present application.

[0118] Specifically, related statistical indicators of the strain compensation values, such as mean, standard deviation, variance, etc., can be calculated based on the modified strain compensation values to evaluate the stability and reliability of the compensation results. Alternatively, if the statistical indicators fluctuate abnormally, it may indicate that there is a problem with the compensation process, and the model or data processing steps need to be rechecked for problems. Further, the strain compensation values can be compared and verified with historical data or a preset reference value. Alternatively, if the difference between the two is within an acceptable range, the compensation result is considered reasonable; otherwise, the cause needs to be further analyzed and adjusted accordingly, which is not limited by the present application.

[0119] S50: Perform vehicle load analysis on each target strain compensation value in the target strain compensation value set to obtain a vehicle load analysis result of the bridge to be detected.

[0120] The vehicle load analysis result can be used to indicate the analysis result about the vehicle load characteristics and the bridge response after the vehicle load analysis processing of each target strain compensation value. The vehicle load analysis result can comprehensively understand the mechanical behavior of the bridge under the action of the vehicle load, timely find potential safety hazards, and can be used for evaluating the safety and durability of the bridge, and can provide strong technical support for the design, scientific management and maintenance of the bridge.

[0121] Specifically, the vehicle load analysis result can include but is not limited to the load size (such as the specific values of the static load and the dynamic load generated by different types of vehicles on the bridge), the load distribution (i.e. the distribution law of the vehicle load on different positions of the bridge (such as the midspan, the support point, etc.) or different lanes (such as the load near the outer lane may be relatively small, and the middle lane may bear a larger load due to the high frequency of vehicle passing)), the change of the load borne by the bridge in different time periods (such as in the traffic peak period, the bridge may frequently bear a larger load, while in the night or in the traffic valley period, the load is relatively small), the load change frequency (specifically, the frequency characteristics of the load change with time can be determined through time domain and frequency domain analysis, such as high frequency load change may be related to the vibration, impact and other factors of the vehicle, while low frequency load change may be related to the driving speed change of the vehicle, the long-term deformation of the bridge and other factors), and the bridge response characteristics (such as the strain condition of the bridge under the action of the vehicle load, including the size, distribution and change law of the strain) and the vibration frequency, amplitude and other characteristics of the bridge under the excitation of the vehicle load, which are not limited in the present application.

[0122] It should be understood that the vehicle load analysis processing of each target strain compensation value in the target strain compensation value set to obtain the vehicle load analysis result of the bridge to be detected refers to the process of performing vehicle load analysis according to the target strain compensation value after temperature compensation processing to obtain more accurate vehicle load analysis result. In step S50, that is, the vehicle load analysis processing of each target strain compensation value in the target strain compensation value set to obtain the vehicle load analysis result of the bridge to be detected can include the following steps:

[0123] S51: performing time domain feature extraction on each target strain compensation value in the target strain compensation value set to obtain a strain time domain feature data set;

[0124] S52: performing frequency domain feature extraction on each target strain compensation value in the target strain compensation value set to obtain a strain frequency domain feature data set;

[0125] S53: performing static load calculation according to the strain time domain feature data set, the strain frequency domain feature data set, and the bridge structure parameter of the bridge to be detected, to obtain a vehicle static load data set;

[0126] S54: performing dynamic load calculation according to the strain time domain feature data set, the strain frequency domain feature data set, the vehicle dynamic driving data set, and the vehicle static load data set, to obtain a vehicle dynamic load data set;

[0127] S55: performing vehicle load analysis processing according to the vehicle static load data set and the vehicle dynamic load data set, to obtain a vehicle load analysis result of the bridge to be detected.

[0128] The strain time domain feature data set can include one or more strain time domain feature data, which can be used to indicate the feature data reflecting the change of strain with time after time domain feature extraction of the target strain compensation value. Optionally, the strain time domain feature data set can include but is not limited to the peak value of strain, the average value of strain, the change rate of strain with time, the vibration period, etc., which are not limited in the present application.

[0129] The strain frequency domain feature data set can include one or more strain frequency domain feature data, which can be used to indicate the feature data reflecting the dynamic vibration of the bridge caused by the vehicle during driving after frequency domain feature extraction of the target strain compensation value. Optionally, the strain frequency domain feature data set can include but is not limited to the frequency distribution of bridge vibration, the energy proportion of each frequency component, the low frequency component, etc., which are not limited in the present application.

[0130] The vehicle static load data set can include one or more vehicle static load data, which can be used to indicate the load data obtained after static load calculation according to the strain peak value, the strain average value, etc. in the strain time domain feature data set, the low frequency component reflecting the static or slow movement of the vehicle in the strain frequency domain feature data set, and the bridge structure parameter of the bridge to be detected. Optionally, the strain time domain feature data can be used for impact load calculation or load time history analysis, and the strain frequency domain feature data can be used for vibration frequency analysis or load identification and separation processing, which are not limited in the present application.

[0131] The bridge structure parameter of the bridge to be detected can be understood as a parameter related to the bridge structure to be detected. The bridge structure parameter can include but is not limited to span, beam height, cross-section characteristics (such as cross-sectional area, moment of inertia, etc.), and elastic modulus, etc., which are not limited in the present application. Specifically, the structural mechanics principle can be used, and the vehicle static load data can be calculated and obtained based on the above data, so as to help understand the stress condition of the bridge under the static or approximately static state of the vehicle.

[0132] The vehicle dynamic load data set can include one or more vehicle dynamic load data, which can be used to indicate the load data obtained after the dynamic load calculation of the vehicle dynamic driving data set and the vehicle static load data set according to the strain time domain characteristic data set such as the change rate of strain with time, vibration period, etc., the strain frequency domain characteristic data set such as the bridge vibration frequency distribution, the energy proportion of each frequency component, etc.

[0133] The vehicle dynamic driving data set can include one or more vehicle dynamic driving data, which can be understood as data for reflecting the dynamic effect of the vehicle during driving. The vehicle dynamic driving data can include but is not limited to driving speed, acceleration, vibration and impact, etc., which are not limited in the present application. Specifically, the static load can be corrected based on the foregoing data by introducing a dynamic coefficient or the like method, so as to obtain the vehicle dynamic load data. Specifically, the vehicle dynamic driving data can be obtained by the vehicle-mounted sensor installed on the vehicle, such as a speed sensor, an acceleration sensor, a vibration sensor or an impact sensor. Optionally, the vehicle dynamic driving data can also be obtained by the bridge monitoring system, such as the strain gauge or the optical fiber sensor installed on the bridge, or the camera or the image recognition device on the bridge, which are not limited in the present application.

[0134] Further, the vehicle dynamic load data set and the vehicle static load data set obtained can be further analyzed, such as the load condition of different time periods and different lanes can be counted, or the load distribution of different types of vehicles can be calculated, so as to further obtain the vehicle load analysis result of the bridge to be detected according to the analysis result, which is beneficial to more accurately evaluate the safety of the bridge, and is helpful for more accurate bridge maintenance and bridge management, which are not limited in the present application.

[0135] It can be seen that in the above scheme, by acquiring the temperature measurement sample data set corresponding to the temperature sensor of the bridge to be detected and acquiring the strain measurement sample data set corresponding to the strain sensor of the bridge to be detected, each temperature measurement sample data in the temperature measurement sample data set can be verified and processed to obtain a temperature verification sample data set, and further according to the temperature verification sample data set and the strain measurement sample data set, a temperature-strain analysis model is constructed, so that based on the temperature-strain analysis model, temperature compensation processing can be performed according to the to-be-processed temperature data set and the to-be-processed strain data set to obtain a target strain compensation value set, and further vehicle load analysis processing can be performed on each target strain compensation value in the target strain compensation value set to obtain a more accurate vehicle load analysis result of the bridge to be detected, which can remove the temperature strain value caused by the temperature factor and is beneficial to achieve the purpose of more accurate vehicle load analysis.

[0136] Consistent with the above embodiments, please refer to Figure 3 , Figure 3 A structural schematic diagram of a terminal provided by the embodiment of the present application is shown in Figure 3 , which includes a processor, an input device, an output device and a memory, and the processor, the input device, the output device and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions, and the above program includes instructions for performing the following steps;

[0137] Acquiring a temperature measurement sample data set corresponding to a temperature sensor of a bridge to be detected, and acquiring a strain measurement sample data set corresponding to a strain sensor of the bridge to be detected;

[0138] Verifying and processing each temperature measurement sample data in the temperature measurement sample data set to obtain a temperature verification sample data set;

[0139] According to the temperature verification sample data set and the strain measurement sample data set, a temperature-strain analysis model is constructed;

[0140] Based on the temperature-strain analysis model, compensation processing is performed according to a to-be-processed temperature data set and a to-be-processed strain data set to obtain a target strain compensation value set;

[0141] Vehicle load analysis processing is performed on each target strain compensation value in the target strain compensation value set to obtain a vehicle load analysis result of the bridge to be detected.

[0142] In this example, by acquiring a temperature measurement sample data set corresponding to a temperature sensor of the bridge to be detected and acquiring a strain measurement sample data set corresponding to a strain sensor of the bridge to be detected, each temperature measurement sample data in the temperature measurement sample data set can be verified to obtain a temperature verification sample data set, and a temperature-strain analysis model can be further constructed according to the temperature verification sample data set and the strain measurement sample data set. Thus, based on the temperature-strain analysis model, compensation processing can be performed according to a to-be-processed temperature data set and a to-be-processed strain data set to obtain a target strain compensation value set, and then each target strain compensation value in the target strain compensation value set can be subjected to vehicle load analysis processing to obtain a more accurate vehicle load analysis result of the bridge to be detected, which can remove temperature strain values caused by temperature factors and is beneficial to achieving the purpose of more accurate vehicle load analysis.

[0143] The above describes the scheme of the embodiments of the present application mainly from the perspective of the process of executing the method. It can be understood that, in order to implement the above functions, the terminal includes a hardware structure and / or a software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the unit and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0144] The embodiments of the present application can divide the terminal into functional units according to the above method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative and is only a logical function division. When actually implemented, there can be another division method.

[0145] Consistent with the above, please refer to Figure 4 , Figure 4 A structural schematic diagram of a vehicle load analysis device for a bridge based on temperature compensation is provided for the embodiments of the present application. As shown in Figure 4 , the device includes:

[0146] The acquisition module 101 is configured to acquire a temperature measurement sample data set corresponding to a temperature sensor of the bridge to be detected and acquire a strain measurement sample data set corresponding to a strain sensor of the bridge to be detected.

[0147] The first processing module 102 is configured to perform verification processing on each temperature measurement sample data in the temperature measurement sample data set to obtain a temperature verification sample data set.

[0148] The second processing module 103 is configured to construct a temperature strain analysis model according to the temperature verification sample data set and the strain measurement sample data set.

[0149] The third processing module 104 is configured to perform compensation processing on a to-be-processed temperature data set and a to-be-processed strain data set based on the temperature strain analysis model to obtain a target strain compensation value set.

[0150] The fourth processing module 105 is configured to perform vehicle load analysis processing on each target strain compensation value in the target strain compensation value set to obtain a vehicle load analysis result of the to-be-detected bridge.

[0151] In a possible implementation, the second processing module is configured to construct a temperature strain analysis model according to the temperature verification sample data set and the strain measurement sample data set, and specifically configured to:

[0152] perform feature mapping on the temperature verification sample data and the strain measurement sample data to obtain a high-dimensional linear feature vector;

[0153] construct a temperature strain analysis function according to the temperature verification sample data and the strain measurement sample data;

[0154] determine a temperature strain constraint condition according to the temperature verification sample data, the strain measurement sample data, and the high-dimensional linear feature vector;

[0155] construct a temperature strain regression optimization function according to the temperature strain analysis function and the temperature strain constraint condition;

[0156] perform optimal solving processing on the temperature strain regression optimization function based on a sequential minimal optimization algorithm to obtain a target Lagrange multiplier set and a target temperature strain analysis parameter set;

[0157] construct a temperature strain analysis model according to the target Lagrange multiplier set and the target temperature strain analysis parameter set.

[0158] In a possible implementation, the second processing module is configured to perform optimal solving processing on the temperature strain regression optimization function based on a sequential minimal optimization algorithm to obtain a target Lagrange multiplier set and a target temperature strain analysis parameter set, and specifically configured to:

[0159] The temperature strain regression optimization function is dually converted based on a sequence minimum optimization algorithm and a Lagrange multiplier method to obtain a temperature strain dual function;

[0160] A reference Lagrange multiplier is selected from an initialized Lagrange multiplier set;

[0161] The temperature strain dual function is optimized and solved based on the reference Lagrange multiplier to obtain a target Lagrange multiplier set;

[0162] A bias is calculated according to each target Lagrange multiplier in the target Lagrange multiplier set to obtain a target bias parameter;

[0163] A weight vector is calculated according to each target Lagrange multiplier in the target Lagrange multiplier set to obtain a target weight parameter;

[0164] The target bias parameter and the target weight parameter are used to determine a target temperature strain analysis parameter set.

[0165] In one possible implementation, the third processing module is configured to perform compensation processing based on the temperature strain analysis model and according to a set of to-be-processed temperature data and a set of to-be-processed strain data to obtain a set of target strain compensation values, and specifically configured to:

[0166] The temperature strain analysis model is used to perform temperature strain analysis processing according to each piece of to-be-processed temperature data in the set of to-be-processed temperature data to obtain a set of temperature strain evaluation data;

[0167] The set of temperature strain evaluation data and the set of to-be-processed strain data are used to perform compensation processing to obtain a set of reference compensation strain data;

[0168] Each piece of reference compensation strain data in the set of reference compensation strain data is subjected to compensation result correction processing to obtain a set of corrected strain compensation values;

[0169] Each corrected strain compensation value in the set of corrected strain compensation values is subjected to stability evaluation processing to obtain the set of target strain compensation values.

[0170] In one possible implementation, the fourth processing module is configured to perform vehicle load analysis processing on each target strain compensation value in the set of target strain compensation values to obtain a vehicle load analysis result of the to-be-detected bridge, and specifically configured to:

[0171] Each target strain compensation value in the set of target strain compensation values is subjected to time-domain feature extraction to obtain a set of strain time-domain feature data;

[0172] performing frequency domain feature extraction on each target strain compensation value in the target strain compensation value set to obtain a strain frequency domain feature data set;

[0173] performing static load calculation according to the strain time domain feature data set, the strain frequency domain feature data set, and a bridge structure parameter of the bridge to be detected to obtain a vehicle static load data set;

[0174] performing dynamic load calculation according to the strain time domain feature data set, the strain frequency domain feature data set, the vehicle dynamic driving data set, and the vehicle static load data set to obtain a vehicle dynamic load data set;

[0175] performing vehicle load analysis processing according to the vehicle static load data set and the vehicle dynamic load data set to obtain a vehicle load analysis result of the bridge to be detected.

[0176] The embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all steps of any one of the vehicle load analysis methods of the bridge based on temperature compensation described in the above method embodiments.

[0177] The embodiment of the present application further provides a computer program product, which comprises a non-transitory computer readable storage medium storing a computer program, and the computer program causes a computer to execute part or all steps of any one of the vehicle load analysis methods of the bridge based on temperature compensation described in the above method embodiments.

[0178] It should be noted that, for each of the above method embodiments, in order to simply describe, each is described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the action order described, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0179] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0180] In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the division of the apparatus embodiments described above is merely an example, and the division can be other forms. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0181] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they can be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0182] In addition, the functional units in each embodiment of the application can be integrated into a processing unit, or each unit can be physically present separately, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software program module.

[0183] The integrated unit, if realized in the form of a software program module and sold or used as an independent product, can be stored in a computer readable memory. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0184] Those of ordinary skill in the art can understand that all or part of the steps of the various methods in the above embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer readable memory, which can include a flash disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0185] The above has carried out the detailed introduction to the embodiment of the application, the principle and implementation mode of the application have been described by applying specific examples in this paper, the above embodiment explanation is only used for helping understanding the method of the application and its core idea; at the same time, for the general technical personnel in the art, according to the idea of the application, the specific implementation mode and application range will have the change, and the above is described, the content of the specification should not be understood as the limitation of the application.

Claims

1. A method for analyzing vehicle loads on bridges based on temperature compensation, characterized in that, The method includes: Acquire the set of temperature measurement sample data corresponding to the temperature sensor of the bridge under test, and acquire the set of strain measurement sample data corresponding to the strain sensor of the bridge under test; Each temperature measurement sample in the temperature measurement sample data set is verified to obtain a temperature verification sample data set. Based on the temperature calibration sample data set and the strain measurement sample data set, a temperature strain analysis model is constructed. Based on the temperature strain analysis model, compensation processing is performed according to the set of temperature data to be processed and the set of strain data to be processed to obtain the target strain compensation value set. Vehicle load analysis is performed on each target strain compensation value in the target strain compensation value set to obtain the vehicle load analysis results of the bridge to be tested. The step of constructing a temperature-strain analysis model based on the temperature calibration sample data set and the strain measurement sample data set includes: The temperature calibration sample data and the strain measurement sample data are subjected to feature mapping to obtain a high-dimensional linear feature vector. Based on the temperature calibration sample data and the strain measurement sample data, a temperature strain analysis function is constructed. Based on the temperature calibration sample data, the strain measurement sample data, and the high-dimensional linear eigenvector, the temperature strain constraint conditions are determined. Based on the temperature strain analysis function and the temperature strain constraints, a temperature strain regression optimization function is constructed. Based on the sequence minimum optimization algorithm, the temperature strain regression optimization function is optimally solved to obtain the target Lagrange multiplier set and the target temperature strain analysis parameter set. A temperature strain analysis model is constructed based on the target set of Lagrange multipliers and the target set of temperature strain analysis parameters.

2. The vehicle load analysis method for bridges based on temperature compensation according to claim 1, characterized in that, The sequential minimum optimization algorithm is used to optimally solve the temperature strain regression optimization function, resulting in the target Lagrange multiplier set and the target temperature strain analysis parameter set, including: Based on the sequential minimum optimization algorithm and the Lagrange multiplier method, the temperature strain regression optimization function is transformed into a dual function to obtain the temperature strain dual function. Select a reference Lagrange multiplier from the initialized set of Lagrange multipliers; The temperature strain dual function is optimized and solved based on the reference Lagrange multipliers to obtain the target Lagrange multiplier set; The bias is calculated based on each target Lagrange multiplier in the target Lagrange multiplier set to obtain the target bias parameters; The target weight parameters are obtained by calculating the weight vector for each target Lagrange multiplier in the target Lagrange multiplier set. The target temperature strain analysis parameter set is determined based on the target bias parameter and the target weight parameter.

3. The vehicle load analysis method for bridges based on temperature compensation according to any one of claims 1 or 2, characterized in that, The compensation process based on the temperature-strain analysis model, using the set of temperature data and the set of strain data to be processed, yields a set of target strain compensation values, including: Based on the temperature strain analysis model, temperature strain analysis is performed on each temperature data to be processed in the temperature data set to be processed to obtain a temperature strain evaluation data set. Compensation processing is performed based on the temperature strain assessment data set and the strain data set to be processed to obtain a reference compensated strain data set; Each reference compensation strain data in the reference compensation strain data set is subjected to compensation result correction processing to obtain a set of corrected strain compensation values; A stability assessment is performed on each of the modified strain compensation values ​​in the set of modified strain compensation values ​​to obtain the set of target strain compensation values.

4. The vehicle load analysis method for bridges based on temperature compensation according to claim 3, characterized in that, The process of performing vehicle load analysis on each target strain compensation value in the target strain compensation value set to obtain the vehicle load analysis results of the bridge under test includes: Time-domain features are extracted from each target strain compensation value in the target strain compensation value set to obtain a strain time-domain feature data set; Frequency domain features are extracted from each target strain compensation value in the target strain compensation value set to obtain a strain frequency domain feature data set; Static load calculations are performed based on the strain time-domain characteristic data set, the strain frequency-domain characteristic data set, and the bridge structural parameters of the bridge to be tested to obtain the vehicle static load data set. Dynamic load calculation is performed based on the strain time-domain characteristic data set, strain frequency-domain characteristic data set, vehicle dynamic driving data set, and vehicle static load data set to obtain the vehicle dynamic load data set. Vehicle load analysis is performed based on the vehicle static load data set and the vehicle dynamic load data set to obtain the vehicle load analysis results of the bridge to be tested.

5. A vehicle load analysis device for bridges based on temperature compensation, characterized in that, The device includes: The acquisition module is used to acquire the set of temperature measurement sample data corresponding to the temperature sensor of the bridge under test, and to acquire the set of strain measurement sample data corresponding to the strain sensor of the bridge under test. The first processing module is used to perform verification processing on each temperature measurement sample data in the temperature measurement sample data set to obtain a temperature verification sample data set. The second processing module is used to construct a temperature strain analysis model based on the temperature calibration sample data set and the strain measurement sample data set. The third processing module is used to perform temperature compensation processing based on the temperature strain analysis model and the set of temperature data to be processed and the set of strain data to be processed, so as to obtain a set of target strain compensation values. The fourth processing module is used to perform vehicle load analysis processing on each target strain compensation value in the target strain compensation value set to obtain the vehicle load analysis results of the bridge to be tested. The second processing module is used to construct a temperature-strain analysis model based on the temperature calibration sample data set and the strain measurement sample data set, specifically for: The temperature calibration sample data and the strain measurement sample data are subjected to feature mapping to obtain a high-dimensional linear feature vector. Based on the temperature calibration sample data and the strain measurement sample data, a temperature strain analysis function is constructed. Based on the temperature calibration sample data, the strain measurement sample data, and the high-dimensional linear eigenvector, the temperature strain constraint conditions are determined. Based on the temperature strain analysis function and the temperature strain constraints, a temperature strain regression optimization function is constructed. Based on the sequence minimum optimization algorithm, the temperature strain regression optimization function is optimally solved to obtain the target Lagrange multiplier set and the target temperature strain analysis parameter set. A temperature strain analysis model is constructed based on the target set of Lagrange multipliers and the target set of temperature strain analysis parameters.

6. The vehicle load analysis device for bridges based on temperature compensation according to claim 5, characterized in that, The second processing module is used to perform optimal solution processing on the temperature strain regression optimization function based on the sequential minimum optimization algorithm, to obtain the target Lagrange multiplier set and the target temperature strain analysis parameter set, specifically for: The temperature strain regression optimization function is dualized using the sequential minimum optimization algorithm and the Lagrange multiplier method to obtain the temperature strain dual function. Select a reference Lagrange multiplier from the initialized set of Lagrange multipliers; The temperature strain dual function is optimized and solved based on the reference Lagrange multipliers to obtain the target Lagrange multiplier set; The bias is calculated based on each target Lagrange multiplier in the target Lagrange multiplier set to obtain the target bias parameters; The target weight parameters are obtained by calculating the weight vector for each target Lagrange multiplier in the target Lagrange multiplier set. The target temperature strain analysis parameter set is determined based on the target bias parameter and the target weight parameter.

7. A terminal, characterized in that, The system includes a processor, an input device, an output device, and a memory, which are interconnected. The memory stores a computer program, which includes program instructions. The processor is configured to invoke the program instructions to execute the vehicle load analysis method for temperature-compensated bridges as described in any one of claims 1-4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the vehicle load analysis method for temperature-compensated bridges as described in any one of claims 1-4.

Images