Data augmentation method and data augmentation device

Abstract

The application discloses a data augmentation method and a data augmentation device, and relates to the technical field of bridge performance prediction. The method comprises the following steps: acquiring design parameters of a reinforced concrete beam component and corrosion experiment sample data of the reinforced concrete beam component conforming to the design parameters; establishing a reinforced concrete beam finite element model according to the design parameters; establishing a steel bar corrosion expansion model; inputting the corrosion experiment sample data into the reinforced concrete beam finite element model by taking the steel bar corrosion expansion model as a boundary condition, so as to correct the behavior of surface concrete cracking caused by concrete surface corrosion expansion simulated by the reinforced concrete beam finite element model, and generate augmented mapping relationship data of the corrected steel bar corrosion rate spatial distribution and crack width distribution. The application realizes data augmentation of the mapping relationship between the two, provides a data basis for establishment of a relationship model of the two, and is beneficial to realization of probabilistic prediction of long-term performance of a reinforced concrete structure.

Description

Technical Field

[0001] The present application relates to the technical field of bridge performance prediction, and in particular to a data augmentation method and a data augmentation device. Background Art

[0002] Rebar corrosion is a major problem that degrades the performance of reinforced concrete structures. Rebar corrosion can cause cracking and spalling of concrete, reducing the structure's load-bearing capacity and leading to long-term performance degradation.

[0003] In existing technology, a common approach is to describe the relationship between the degree of steel corrosion and crack width based on empirical and mechanical models. By identifying the random variables involved in predicting steel corrosion and establishing a relationship between the amount of steel corrosion and crack width, the uncertainty in predicting structural degradation is reduced. However, this approach oversimplifies the prediction of the remaining service life of bridge structures by ignoring the spatial variability of the steel corrosion process.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art.

[0005] Application Contents

[0006] The main purpose of this application is to provide a data augmentation method to solve the technical problem that the existing reinforced concrete degradation prediction method oversimplifies the prediction of the remaining service life of bridge structures.

[0007] To achieve the above objectives, this application proposes a data augmentation method, which includes:

[0008] Obtaining design parameters of a reinforced concrete beam component and corrosion test sample data of the reinforced concrete beam component that meets the design parameters; the corrosion test sample data includes mapping relationship data between a spatial distribution of steel corrosion rate and a crack width distribution; the crack width is a crack width on the surface of the reinforced concrete beam component;

[0009] According to the design parameters, a finite element model of a reinforced concrete beam is established;

[0010] Establish a steel bar corrosion expansion model;

[0011] The steel bar corrosion expansion model is used as a boundary condition, and the corrosion test sample data is input into the reinforced concrete beam finite element model to correct the behavior of the reinforced concrete beam finite element model simulating the surface corrosion expansion of concrete causing surface concrete cracking, and to generate augmented mapping relationship data of the corrected spatial distribution of steel bar corrosion rate and crack width distribution.

[0012] In one embodiment, the step of obtaining design parameters of a reinforced concrete beam component and corrosion test sample data of the reinforced concrete beam component that meets the design parameters includes:

[0013] Obtaining design parameters of reinforced concrete beam components, including component length, cross-sectional dimensions, concrete strength, cover thickness, and steel bar diameter;

[0014] The corrosion test sample data obtained by subjecting a reinforced concrete beam component meeting the design parameters to accelerated corrosion by electricity is obtained.

[0015] In one embodiment, the step of obtaining the corrosion test sample data obtained by subjecting a reinforced concrete beam component meeting the design parameters to accelerated corrosion by electrical current includes:

[0016] Obtaining first corrosion test sample data obtained by subjecting a reinforced concrete beam component meeting the design parameters to accelerated corrosion under different current conditions; wherein the first corrosion test sample data includes mapping relationship data between a spatial distribution of steel bar corrosion rates and crack width distributions along the length of the steel bars under different current conditions;

[0017] According to the spatial distribution of steel bar corrosion rate along the length direction under different current conditions, the spatial distribution of steel bar corrosion rate under different corrosion rates is determined;

[0018] According to the spatial distribution of steel bar corrosion rate under different corrosion rates, the average steel bar corrosion rate is determined;

[0019] According to the average steel bar corrosion rate, mapping relationship data between the steel bar corrosion rate spatial distribution and the crack width distribution is generated.

[0020] In one embodiment, the steps of inputting the corrosion test sample data into the reinforced concrete beam finite element model using the steel bar corrosion expansion model as a boundary condition to correct the behavior of the reinforced concrete beam finite element model simulating surface concrete cracking caused by concrete surface corrosion expansion, and generating augmented mapping relationship data of the corrected steel bar corrosion rate spatial distribution and crack width distribution include:

[0021] Determining the average corrosion rate of the steel bars and the standard deviation of the steel bar corrosion rate based on the corrosion test sample data, and determining a logarithmic function relationship between the average corrosion rate of the steel bars and the standard deviation of the steel bar corrosion rate by a fitting method;

[0022] Introducing relevant equations of finite element simulation, and determining relevant distance parameters of the relevant equations of finite element simulation according to the design parameters;

[0023] Using the steel bar corrosion expansion model as a boundary condition and based on the relevant equations of the finite element simulation, the expansion displacement of each unit of the reinforced concrete beam finite element model is calculated to perform a finite element simulation of the surface concrete cracking process caused by concrete surface corrosion expansion;

[0024] The logarithmic function relationship is input into the reinforced concrete beam finite element model to generate the spatial distribution of steel corrosion rate and corresponding crack width distribution data that obey the logarithmic function relationship.

[0025] In one embodiment, the step of inputting the logarithmic function relationship into the reinforced concrete beam finite element model to generate the spatial distribution of steel corrosion rate and corresponding crack width distribution data that obey the logarithmic function relationship includes:

[0026] The logarithmic function relationship is input into the reinforced concrete beam finite element model, and the variability characteristic parameters of the corrosion space are simulated using the Nataf transformation method to generate crack width distribution data corresponding to the spatial distribution of the steel corrosion rate that obeys the logarithmic function relationship.

[0027] In one embodiment, the correlation equation of the finite element simulation includes an exponential correlation function, and the exponential correlation function is specifically:

[0028]

[0029] Among them, ρ i,j is the function value of the correlation between steel bar units, L is the correlation distance parameter of the correlation equation, τ=x i -x j It is the center distance between two adjacent steel bar units along the length of the steel bar.

[0030] In one embodiment, the step of establishing the steel bar corrosion expansion model includes:

[0031] The corrosion distribution curve of the elliptical expression is introduced to simulate the corrosion expansion behavior of each steel bar section to establish the steel bar corrosion expansion model; wherein, the corrosion distribution curve of the elliptical expression is:

[0032]

[0033] u θ is the function value of the corrosion distribution curve, R is the original radius of the steel bar, u1 is the maximum corrosion layer thickness closest to the concrete surface, u2 is the corrosion layer thickness away from the concrete surface, and u θ is the corrosion distribution curve function value of the ellipse expression.

[0034] In one embodiment, the steps of inputting the corrosion test sample data into the reinforced concrete beam finite element model using the steel bar corrosion expansion model as a boundary condition to correct the behavior of the reinforced concrete beam finite element model simulating surface concrete cracking caused by concrete surface corrosion expansion, and generating augmented mapping relationship data of the corrected steel bar corrosion rate spatial distribution and crack width distribution include:

[0035] The steel bar corrosion expansion model is used as a boundary condition, and the corrosion test sample data is input into the reinforced concrete beam finite element model to correct the behavior of the reinforced concrete beam finite element model in simulating surface concrete cracking caused by concrete surface corrosion expansion. The step of generating the corrected augmented mapping relationship data between the spatial distribution of steel bar corrosion rate and the crack width distribution is cyclically executed until the data volume of the augmented mapping relationship data reaches a preset target data volume, and then the step of generating the corrected augmented mapping relationship data between the spatial distribution of steel bar corrosion rate and the crack width distribution is stopped.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a data augmentation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data augmentation method described above.

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

[0038] The design parameters of the reinforced concrete beam component and the corrosion test sample data of the reinforced concrete beam component that meets the design parameters are obtained; the corrosion test sample data includes the mapping relationship data between the spatial distribution of the steel corrosion rate and the crack width distribution; the crack width is the crack width on the surface of the reinforced concrete beam component; according to the design parameters, a reinforced concrete beam finite element model is established; a steel corrosion expansion model is established; with the steel corrosion expansion model as the boundary condition, the corrosion test sample data is input into the reinforced concrete beam finite element model to correct the behavior of the reinforced concrete beam finite element model simulating the surface corrosion expansion of concrete causing surface concrete cracking, and generate the augmented mapping relationship data of the corrected steel corrosion rate spatial distribution and crack width distribution. In this way, the present application realizes the data augmentation of the mapping relationship data between the spatial distribution of the steel corrosion rate and the crack width distribution, providing a data basis for the establishment of the relationship model between the two. Therefore, the corrosion of the internal steel bars can be predicted by the surface crack width, and the probabilistic prediction of the long-term performance of the reinforced concrete structure can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0041] Figure 1 A flowchart of the first embodiment of the data augmentation method of this application is provided;

[0042] Figure 2 A schematic structural diagram of a reinforced concrete beam member provided in one embodiment of the present application;

[0043] Figure 3 A schematic structural diagram of a three-dimensional reinforced concrete beam finite element model generated by an embodiment of the data augmentation method of this application;

[0044] Figure 4 A schematic diagram of the structure of a steel bar corrosion and expansion model generated by an embodiment of the data augmentation method of this application;

[0045] Figure 5 A spatial distribution map of steel bar corrosion rates generated by the first embodiment of the data augmentation method of this application;

[0046] Figure 6 A scatter plot of data samples of the augmented mapping relationship between the corrected spatial distribution of steel bar corrosion rate and crack width distribution generated by the first embodiment of the data augmentation method of the present application;

[0047] Figure 7 Schematic diagram of the device structure of the hardware operating environment involved in the data augmentation method in the embodiment of the present application.

[0048] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0050] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0051] The main solution of the embodiment of the present application is: obtaining the design parameters of the reinforced concrete beam component and obtaining the experimental parameters based on the design parameters; establishing a three-dimensional reinforced concrete beam finite element model based on the design parameters and the experimental parameters; establishing a steel corrosion and expansion model based on the three-dimensional reinforced concrete beam finite element model; based on the steel corrosion and expansion model, determining the first mapping relationship between the spatial distribution of steel corrosion rate and the crack width distribution.

[0052] Technical terms involved in the embodiments of this application:

[0053] Nataf Transformation:

[0054] Nataf transform is a technique used in numerical calculation and probability analysis, which can be applied to finite element analysis. When performing numerical calculations, it is often necessary to solve the problem of uncertainty transfer caused by the uncertainty of geometry, boundary conditions or material parameters. The core idea of ​​​​Nataf transform is to transform the uncertainty of random variables into variables of known distribution through linear transformation, so that the problem is easier to handle in the new variable space. Specifically, Nataf transform transforms the original random variables into new variables by introducing a linear transformation matrix, making the correlation structure between the new variables simpler or easier to handle. In this way, the original problem can be transformed into a solution in the new variable space, thereby simplifying the problem handling and solution process.

[0055] Marginal cumulative density function of the inverse of the standard Gaussian distribution:

[0056] The inverse marginal cumulative density function of the standard Gaussian distribution is the inverse function of a given probability value in the standard Gaussian distribution. It returns the value of the variable corresponding to the given probability. The standard Gaussian distribution, also known as the normal distribution or bell curve, is a common continuous probability distribution in statistics. Its probability density function is a bell-shaped curve, symmetric about the mean, and has two parameters: the mean and the standard deviation. In the standard Gaussian distribution, the mean is 0 and the standard deviation is 1. In statistics, the inverse marginal cumulative density function (inverse CDF) is a function that accepts a probability value (usually between 0 and 1) and returns the value of the variable corresponding to that probability value. In other words, the inverse CDF provides an inverse mapping, converting probabilities into variable values.

[0057] Monte Carlo method:

[0058] The Monte Carlo method is a numerical computational technique based on random sampling, used to solve a variety of complex problems, particularly in the fields of probability and statistics. Specifically, the Monte Carlo method simulates the uncertainty or randomness of a problem by generating a large number of random samples. These samples are then used to perform numerical calculations to obtain approximate solutions to the problem. The core idea of ​​this method is to approximate the behavior of complex systems through random sampling, thereby solving problems that are difficult to solve using traditional numerical methods. Although the results of the Monte Carlo method are approximate, they become increasingly accurate as the number of samples increases.

[0059] Cholesky decomposition:

[0060] Cholesky decomposition is a numerical decomposition method used to decompose a symmetric positive definite matrix into the product of a lower triangular matrix and its transpose. It can be used to solve linear equations, calculate the determinant of a matrix, and perform least squares fitting.

[0061] Finite Element Method:

[0062] The finite element method is a numerical analysis technique that divides a complex continuous system into many simple geometric units, called finite elements. Each finite element represents a small part of the system whose behavior can be approximated by a simple mathematical description. These finite elements are connected at nodes to form a mesh or grid network, and the entire system is discretized into a finite number of finite elements. In the finite element method, the behavior of each finite element is mathematically modeled and connected together to form a model of the entire system. This model is usually expressed as a system of linear or nonlinear algebraic equations, whose solutions describe the behavior of the system. By numerically solving this system of equations, an approximate solution to the system can be obtained.

[0063] Fitting method:

[0064] Fitting methods are a set of statistical techniques used to determine the relationship between observed data and one or more theoretical models and to use these models to predict or explain unknown data. Fitting methods are typically used to find the mathematical function or curve that best fits the observed data, and these functions or curves can be used to predict or infer unknown data. Common fitting methods include least squares, nonlinear least squares, polynomial fitting, and local fitting.

[0065] In the embodiments of the present application, for ease of description, the following description is made by taking a data augmentation device for identifying data augmentation as the execution subject.

[0066] In chloride environments, steel corrosion is a major cause of performance degradation in reinforced concrete structures and has become a global problem over the past few decades. The cost of repairing corroded reinforced concrete structures is considerable. Worldwide, over $100 billion is spent annually on maintaining and repairing corroded concrete infrastructure. The passive film of steel bars is relatively stable in the highly alkaline environment of concrete. However, when this passive film is destroyed by chloride ion attack, steel bars corrode. The volume expansion of corrosion products can cause cracking and even spalling of the protective concrete layer. Aggressive media from outside the structure can more easily reach the steel bar surface, accelerating the corrosion process. As the cross-sectional area of ​​the steel bars and the bond strength between concrete and steel bars decrease significantly, the bearing capacity also decreases, leading to service failure and deterioration of long-term structural performance.

[0067] Among the structural inspection methods, visual inspection is a low-cost and versatile technology for assessing the degree of deterioration of existing reinforced structures and has been widely used in formulating maintenance strategies for existing bridges. For corroded reinforced concrete structures, the width of the concrete surface cracks caused by steel corrosion is the most commonly used visual inspection indicator. Many researchers have attempted to link the crack width with the corrosion state of the steel bars (i.e., cross-sectional area loss) and have proposed many empirical models and mechanical models to describe the relationship between the degree of steel corrosion and the crack width. Once the random variables involved in predicting steel corrosion are determined and the relationship between the amount of steel corrosion and the width of the corrosion crack is established, the update theory and nonlinear filtering techniques can be applied to reduce the uncertainty in predicting structural performance degradation.

[0068] Due to the combined influence of multiple factors, such as varying environmental exposure conditions, concrete cover thickness, and construction quality, steel corrosion exhibits spatially non-uniform distribution. Corrosion crack widths on bridge surfaces also exhibit spatially random and non-uniform distribution. The structural bearing capacity of bridge components strongly depends on the local conditions of their reinforcement. Therefore, ignoring the spatial variability of steel corrosion oversimplifies the prediction of the remaining service life of bridge structures.

[0069] This application provides a solution that can augment the currently limited experimental data through numerical simulation to establish a database of the spatial distribution of steel corrosion rate and crack width distribution. Specifically, the design parameters of the reinforced concrete beam component and the corrosion test sample data of the reinforced concrete beam component that meets the design parameters are obtained; the corrosion test sample data includes the mapping relationship data between the spatial distribution of steel corrosion rate and the crack width distribution; the crack width is the crack width on the surface of the reinforced concrete beam component; according to the design parameters, a reinforced concrete beam finite element model is established; a steel corrosion expansion model is established; with the steel corrosion expansion model as the boundary condition, the corrosion test sample data is input into the reinforced concrete beam finite element model to correct the behavior of the reinforced concrete beam finite element model simulating the surface corrosion expansion of concrete causing surface concrete cracking, and generate the augmented mapping relationship data of the corrected steel corrosion rate spatial distribution and crack width distribution. In this way, this application realizes the data augmentation of the mapping relationship data between the spatial distribution of steel corrosion rate and crack width distribution, providing a data basis for the establishment of the relationship model between the two. As a result, the corrosion of the internal steel bars can be predicted by the surface crack width, realizing the probabilistic prediction of the long-term performance of reinforced concrete structures.

[0070] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions. The following uses a data augmentation device as an example to illustrate this embodiment and the following embodiments.

[0071] Based on this, the embodiment of the present application provides a data augmentation method for the mapping relationship between steel bar corrosion distribution and crack width distribution, please refer to Figure 1 The data augmentation method for the mapping relationship between steel bar corrosion distribution and crack width distribution includes steps S10 to S40:

[0072] Step S10, obtaining design parameters of a reinforced concrete beam component and corrosion test sample data of the reinforced concrete beam component that meets the design parameters; the corrosion test sample data includes mapping relationship data between the spatial distribution of steel corrosion rate and the crack width distribution; the crack width is the crack width on the surface of the reinforced concrete beam component;

[0073] It should be noted that obtaining the design parameters of reinforced concrete beam components can include obtaining component length, cross-sectional dimensions (such as width, height, length), concrete strength (such as concrete of different strengths such as C25 and C30), protective layer thickness, steel bar diameter, steel bar type, steel bar yield strength and tensile strength, reinforcement ratio (number, diameter, spacing of main bars and stirrups), and steel bar placement position and other design parameters. In this way, based on similarity theory, the proportion of the experimental model can be designed to ensure that the model can reflect the mechanical behavior of the prototype in the experiment, and the experimental environmental conditions (such as temperature, humidity, medium, etc.) are set. The electric corrosion experiment is carried out, and an image acquisition device is arranged at the bottom of the concrete beam component to obtain the appearance and width changes of cracks on the surface of the reinforced concrete beam component to obtain corrosion sample corrosion test sample data. It is understandable that the internal steel bar corrosion of the reinforced concrete beam component can be detected by X-ray technology. It is understandable that experiments can be carried out according to multiple predetermined schemes, and the changes in all key corrosion test sample data are recorded to evaluate the corrosion changes of the steel bars, the morphology and width changes of the surface cracks, etc. In this embodiment, the spatial distribution data of the steel bar corrosion rate, the crack width distribution data and the mapping relationship data therebetween of the reinforced concrete beam component that meets the design parameters obtained after the experiment can be obtained.

[0074] Step S20, establishing a finite element model of a reinforced concrete beam according to the design parameters;

[0075] In this embodiment, when establishing a 3D reinforced concrete beam finite element model, to reduce the complexity of the model, some parameters that have little impact on the mapping relationship between steel bar corrosion distribution and crack width distribution can be ignored, assumed, or replaced with similar simulation methods. For example, since the compressive behavior of concrete has little impact on the calculation of corrosion-induced crack width, it can be assumed that the compressive behavior of concrete is that of an ideal elastic material. Corrosion expansion can be considered as a displacement imposed on the interface between the steel bar and concrete. Therefore, when establishing a 3D reinforced concrete beam finite element model, the steel bar can be simulated as a "hole," and radial displacement can be applied to simulate non-uniform corrosion around the steel bar and along the steel bar axis to represent the spatial expansion of steel bar corrosion. For another example, several assumptions can be made in the simulation of the corrosion expansion process, including: First, rust can be considered rigid, and its deformation can be ignored. Second, the impact of corrosion on the longitudinal steel bar on the crack width caused by corrosion near adjacent longitudinal steel bars is not considered, and only the relationship between the longitudinal steel bar corrosion rate distribution and the crack width caused by corrosion is considered. Third, the effect of stirrups on crack width is ignored in the finite element model. In this way, this embodiment can simplify the complexity of establishing a three-dimensional reinforced concrete beam finite element model without affecting the subsequent analysis of the mapping relationship between steel corrosion distribution and crack width distribution based on the three-dimensional reinforced concrete beam finite element model.

[0076] Step S30, establishing a steel bar corrosion expansion model;

[0077] In one feasible implementation, step S30 includes step S31:

[0078] Step S31, introducing the corrosion distribution curve of the elliptical expression to simulate the corrosion expansion behavior of each steel bar section to establish the steel bar corrosion expansion model; wherein the corrosion distribution curve of the elliptical expression is:

[0079]

[0080] u θ is the function value of the corrosion distribution curve, R is the original radius of the steel bar, u1 is the maximum corrosion layer thickness closest to the concrete surface, u2 is the corrosion layer thickness away from the concrete surface, and u θ is the corrosion distribution curve function value of the ellipse expression.

[0081] It should be noted that the elliptical expression, as a continuous function, can more accurately describe the uneven expansion of steel bar corrosion. It can reflect the complex distribution characteristics of corrosion on the steel bar cross section, such as the coexistence of localized severe corrosion and mild corrosion, thereby simulating the differential impact of localized corrosion on the structure. The shape of the semi-ellipse is determined by the ratio u2 / u1, which can be assumed here to be 1 / 30.

[0082] Step S40: Using the steel bar corrosion expansion model as a boundary condition, the corrosion test sample data is input into the reinforced concrete beam finite element model to correct the behavior of the reinforced concrete beam finite element model simulating concrete surface corrosion expansion causing surface concrete cracking, and generate augmented mapping relationship data of the corrected steel bar corrosion rate spatial distribution and crack width distribution.

[0083] It should be noted that in the simulation of the steel bar corrosion and expansion process, after the steel bar begins to rust, the rust can expand freely. Once the voids in the porous area are completely filled with rust, the expansion of the rust will exert pressure on the surrounding concrete, thereby generating tensile stress and causing concrete cracking. Not all rust will cause an increase in stress and initial cracking of the covering concrete. Some rust may penetrate into the porous area between the steel bar and the surrounding concrete. This method assumes that the porous area is uniform and its thickness δ can be 12.5μm. During the free expansion stage of the corrosion product, the rust volume V per unit length l is rust1 It can be expressed as:

[0084] V rust1 =V poro +V steel1

[0085] Among them, V poro is the volume of corrosion products that penetrate into the porous area of ​​the steel / concrete interface (i.e., 2πRδl), V steel1 is the volume of corroded steel bars during the free expansion phase of rust products. Once the voids in the porous area are completely filled with rust, tensile stress will be generated in the surrounding concrete. After the voids are filled with rust, the volume of rust per unit length l is V rust2 for:

[0086] V rust2 =V exp +V steel2

[0087] V exp =πRl(u1+3u2) / 2

[0088] Among them, V exp is the expansion volume per unit length l, V steel2 is the volume of the steel bar corroded after the voids are filled with rust, u1 is the maximum corrosion layer thickness closest to the concrete surface, u2 is the corrosion layer thickness away from the concrete surface, and R is the original radius of the steel bar. rust =V rust1 +V rust2It comes from three interrelated processes, each of which is directly or indirectly related to steel corrosion. Specifically, first, the total amount of corrosion includes the rust associated with the consumed steel bars. Among them, the corrosion occurs directly on the surface of the steel bars, and the volume of the rust products is larger than the original volume of the steel bars, causing the physical volume of the steel bars themselves to expand. Second, the total amount of corrosion includes the rust associated with the penetration into the porous area of ​​the steel bar / concrete interface. Among them, the iron oxide produced during the corrosion process can penetrate from the surface of the steel bars into the tiny gaps or pores between the steel bars and the concrete. This penetration will further aggravate the bond failure between the steel bars and the concrete, and may also form rust channels, promote the intrusion of more water and corrosive media, and accelerate the corrosion process. Third, the total amount of corrosion includes the rust associated with the expansion pressure on the surrounding concrete. Among them, the volume expansion of the rust products will exert pressure on the surrounding concrete, causing the concrete to crack or peel, reducing the integrity and durability of the structure. Since all rust is produced by steel corrosion, the relationship is:

[0089] V rust =βV steel

[0090] Where V rust is the total amount of rust, V rust is the volume of all corroded steel bars, and β is the volume expansion ratio of corrosion products, which can be assumed to be 2.0.

[0091] Some rust will flow out of the structure through the cracks caused by corrosion and penetrate into the surrounding concrete. The amount of rust that penetrates into the surrounding concrete depends on different experimental conditions. For example, when conducting experiments by accelerating corrosion through electricity, the amount of rust that penetrates into the surrounding concrete depends on the current density level during the experiment. Lower current densities easily provide opportunities for rust to fill the pores of the surrounding concrete. On the contrary, when the current density is high, some rust is not likely to induce cracking in the surrounding concrete. Therefore, the corrosion rate η′ in the expansion simulation is not the same as the corrosion rate η measured in the experiment. In order to simplify this problem, a calibration factor can be introduced. Taking into account the impact current density I corr and the average corrosion rate of steel bars η a The influence of pressure on the formation of corrosion cracks. The relationship between η and η′ can be:

[0092]

[0093] Where η′ is the corrosion rate in the expansion simulation, η is the corrosion rate measured experimentally, is the calibration coefficient, I corr is the impulse current density, η a is the average corrosion rate of steel bars, ξ1 can be 0.903, ξ2 can be 10.3, ξ3 can be 24.2, and ξ4 can be -0.663.

[0094] u1 is the maximum corrosion layer thickness closest to the concrete surface, u1 is taken as the first parameter of the rust layer model, and u1 can be input into the finite element model. Wherein, u1 is determined by η, and the relationship is:

[0095]

[0096] Wherein, η is the corrosion rate measured by experiment, is a calibration coefficient, R is the original radius of the steel bar; δ is the thickness of the porous area, which can be 12.5 μm.

[0097] In an implementation, the step S40 includes a step S41:

[0098] Step S41, input the corrosion experiment sample data into the reinforced concrete beam finite element model with the steel bar corrosion expansion model as the boundary condition, correct the behavior of the surface concrete cracking caused by the corrosion expansion of the concrete surface in the reinforced concrete beam finite element model, and execute the step of generating the augmented mapping relationship data of the corrected steel bar corrosion rate spatial distribution and crack width distribution in a loop until the data amount of the augmented mapping relationship data reaches the preset target data amount, and then stop executing the step of generating the augmented mapping relationship data of the corrected steel bar corrosion rate spatial distribution and crack width distribution. In this way, multiple sets of augmented mapping relationship data can be obtained.

[0099] In this embodiment, the corrosion distribution of the reinforced concrete beam finite element model is simulated and calculated with the steel bar corrosion expansion model as the boundary condition. In addition, the mapping relationship data between the steel bar corrosion rate spatial distribution and the crack width distribution in the corrosion experiment sample data can be used to correct the corrosion rate simulated in the reinforced concrete beam finite element model, and then the augmented data with more accurate relationship between the two can be obtained. In this way, this embodiment realizes data augmentation of the mapping relationship data between the steel bar corrosion rate spatial distribution and the crack width distribution, and provides a data basis for the relationship model between the two. Therefore, the corrosion of the internal steel bar can be predicted through the surface crack width, and the long-term performance of the reinforced concrete structure can be probabilistically predicted.

[0100] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above embodiment one can refer to the above introduction, and will not be repeated hereinafter. On this basis, the step S10 includes steps S11-S12:

[0101] Step S11, obtaining the design parameters of the reinforced concrete beam component; wherein the design parameters include component length, cross-sectional size, concrete strength, protective layer thickness and steel bar diameter;

[0102] Step S12: obtaining the corrosion test sample data obtained by subjecting a reinforced concrete beam member meeting the design parameters to accelerated corrosion by electrical current.

[0103] In this embodiment, the electric accelerated corrosion experiment can accelerate the corrosion rate of steel bars by applying direct current to simulate the corrosion process in the natural environment. Among them, the positive electrode is connected to the steel bar and the negative electrode is connected to the electrolyte (such as simulated seawater or sodium sulfate solution) to form an electrolytic cell, which can accelerate the anodic dissolution process of the steel bar. The corrosion current density of the steel bar can be measured regularly by electrochemical techniques such as electrochemical impedance spectroscopy (EIS) and linear polarization resistance (LPR). Combined with the weight loss method, the average corrosion rate and distribution of the steel bar are calculated. The unevenness of the corrosion rate will cause the steel bar corrosion rate in some areas to be much higher than that in other areas. Among them, the internal corrosion of reinforced concrete beam components can be explored. During the corrosion of steel bars, the crack width around the steel bar corrosion area generally presents an uneven distribution, which corresponds to the distribution of the steel bar corrosion rate. The crack width near the corrosion hotspot area (area with high corrosion rate) is generally larger. In this embodiment, the corrosion test sample data obtained by the electric accelerated corrosion of the reinforced concrete beam component that meets the design parameters can be used for subsequent statistical analysis and finite element analysis simulation to quantify the mapping relationship between the two and provide corrosion test sample data support.

[0104] Based on the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above-mentioned second embodiment can be referred to the above introduction and will not be repeated hereafter. On this basis, the step S12 includes steps S121 to S124:

[0105] Step S121, obtaining first corrosion test sample data obtained by subjecting a reinforced concrete beam component meeting the design parameters to accelerated corrosion under different current conditions; wherein the first corrosion test sample data includes mapping relationship data between the spatial distribution of steel bar corrosion rate and crack width distribution along the length direction of the steel bar under different current conditions.

[0106] It should be noted that the experimenters were able to run a current through the reinforced concrete beam under different current conditions to simulate the corrosion process of the steel bars in a real environment. Since electric current accelerates the corrosion rate of the steel bars, the rate and extent of corrosion can be controlled by adjusting the current. The experiment recorded the corrosion rate distribution along the length of the steel bars and the accompanying crack width distribution. This data constituted the first corrosion experiment sample data and was input into the data augmentation equipment.

[0107] Step S122, determining the spatial distribution of steel bar corrosion rates under different corrosion rates according to the spatial distribution of steel bar corrosion rates along the length direction of the steel bar under different current conditions;

[0108] Step S123, determining the average corrosion rate of the steel bars according to the spatial distribution of the steel bar corrosion rates under different corrosion rates;

[0109] Step S124: generating mapping relationship data between the spatial distribution of steel bar corrosion rates and crack width distribution according to the average steel bar corrosion rate.

[0110] It is understandable that in reinforced concrete beam components under high current conditions, the steel bars corrode faster, while in reinforced concrete beam components under low current conditions, the steel bars corrode relatively slowly. In this embodiment, the data augmentation device can obtain the average steel bar corrosion rate based on the first corrosion test sample data to identify the corrosion rate distribution pattern under different corrosion rate conditions, and then generate mapping relationship data between the spatial distribution of steel bar corrosion rate and crack width distribution.

[0111] Based on the third embodiment of the present application, in the fourth embodiment of the present application, the same or similar contents as those in the third embodiment can be referred to above and will not be described in detail. On this basis, the step S40 includes steps S41 to S44:

[0112] Step S41: determining the average corrosion rate of the steel bars and the standard deviation of the steel bar corrosion rate according to the corrosion test sample data, and determining the logarithmic function relationship between the average corrosion rate of the steel bars and the standard deviation of the steel bar corrosion rate by a fitting method;

[0113] Step S42: introducing relevant equations of finite element simulation, and determining relevant distance parameters of the relevant equations of finite element simulation according to the design parameters;

[0114] Step S43: using the steel bar corrosion expansion model as a boundary condition and based on the relevant equations of the finite element simulation, calculating the expansion displacement of each unit of the reinforced concrete beam finite element model to perform a finite element simulation of the surface concrete cracking process caused by concrete surface corrosion expansion;

[0115] Step S44: inputting the logarithmic function relationship into the reinforced concrete beam finite element model to generate the spatial distribution of steel corrosion rate and corresponding crack width distribution data that obey the logarithmic function relationship.

[0116] In this embodiment, the statistical characteristic parameter (i.e., standard deviation) can be obtained based on the sample data of the spatial distribution of the steel bar corrosion rate, and the logarithmic function relationship between the corrosion rate standard deviation and the average corrosion rate can be determined by a fitting method, which can be specifically determined as:

[0117] υ=0.08η a 0.5

[0118] Among them, υ is the standard deviation of steel corrosion rate, which is the first function value; η a is the average corrosion rate of steel bars.

[0119] In one feasible implementation, step S42 includes step S421:

[0120] In step S421, the relevant equation of the finite element simulation includes an exponential correlation function, and the exponential correlation function is specifically:

[0121]

[0122] Among them, ρ i,j is the function value of the correlation between steel bar units, L is the correlation distance parameter of the correlation equation, τ=x i -x j It is the center distance between two adjacent steel bar units along the length of the steel bar.

[0123] In another feasible implementation, the step S44 includes step S441:

[0124] Step S441: input the logarithmic function relationship into the reinforced concrete beam finite element model, and use the Nataf transformation method to simulate the variability characteristic parameters of the corrosion space to generate crack width distribution data corresponding to the spatial distribution of the steel corrosion rate that obeys the logarithmic function relationship.

[0125] It should be noted that since the corrosion of steel bars has great uncertainty along the length of the steel bars, it is necessary to simulate it through a probabilistic method, while the spatial variability of steel bar corrosion can be simulated through a logarithmic distribution. The logarithmic distribution combined with the Nataf transformation method can take the corrosion correlation between steel bar units into account in the simulation. Among them, the correlation between the corrosion of steel bar units can be characterized by the relevant equations of finite element simulation, and the exponential correlation function is used to express ρ i,j :

[0126]

[0127] Among them, ρ i,j is the function value of the correlation between steel bar units, L is the correlation distance parameter of the correlation equation, τ=x i -x j It is the center distance between two adjacent steel bar units along the length of the steel bar.

[0128] It should be noted that the Nataf transform can be used to convert any random variable into a standard Gaussian distribution, and the n-dimensional related random vector X = [X1, X2, ..., X n The marginal cumulative density function of ] is The correlation coefficient matrix is ​​ρ = [ρ i,j]. Through Nataf transformation, X can be transformed into an independent standard normal variable Y = [Y i The process of Nataf transformation is: the relevant standard normal variable Y = [Y i ] can be converted from X by the following formula:

[0129]

[0130] Among them, y j For [Y i ], is the marginal cumulative density function, Φ -1 (·) is the marginal cumulative density function of the inverse of the standard Gaussian distribution. The correlation coefficient matrix of Y is ρ0=[ρ 0i,j ].ρ i,j and ρ 0i,j The relationship between them is shown as follows:

[0131]

[0132] Among them, φ2(y i ,y j ρ 0i,j ) from Eq.

[0133]

[0134] Given, and They are the related variables x i and x j The mean of and They are the related variables x i and x j The standard deviation of .

[0135] Among them, ρ 0i,j It can be obtained by i,j The relationship between the two can be simplified as follows:

[0136] ρ 0i,j =P j,k ·ρ i,j

[0137] P ij It can be estimated by polynomial approximation as follows:

[0138]

[0139] The parameters p1 to p4 can be calculated by Monte Carlo method. 0i,j ρ0 can be decomposed into a lower triangular matrix and an upper triangular matrix by Cholesky decomposition, as shown below:

[0140] P0 = A · A T

[0141] where A = [a i,j ] is a lower triangular matrix. Thus, the variable Y can be represented as a product of A and an independent standard normal variable U, as shown in the following equation:

[0142] Y = A · U

[0143] The relationship between the independent standard normal variable U and the original correlated variable X can be established as the equation:

[0144]

[0145] In this embodiment, the corrosion correlation between the reinforcement units is considered in the simulation by the probability method, and the log distribution of the Nataf transformation method can be combined to simulate the variability characteristic parameters of the corrosion space, and based on this, the reinforcement corrosion rate space distribution and the corresponding crack width distribution data conforming to the log function relationship are generated, and the augmented mapping relationship data of the corrected reinforcement corrosion rate space distribution and the crack width distribution are obtained.

[0146] Based on the first embodiment of the present application, in the fifth embodiment of the present application, the same or similar contents as the above embodiment one can refer to the above introduction, and the subsequent will not be described in detail. On this basis, the step S20 includes steps S21-S23:

[0147] Step S21: According to the design parameters, a concrete model is established by introducing an eight-node solid element method;

[0148] Step S22: Based on the concrete model, the tensile behavior of the concrete model is simulated by introducing a linear softening curve of fracture energy;

[0149] Step S23: Based on the tensile behavior of the concrete model, a three-dimensional reinforced concrete beam finite element model is established.

[0150] In this embodiment, when performing finite element analysis, the concrete structure can be divided into multiple three-dimensional eight-node solid elements. Each element has eight vertices, which can more accurately capture complex geometric shapes and stress distribution. Among them, the concrete shows nonlinear behavior in the tensile process, especially brittle fracture after reaching the limit state. This embodiment describes the process of concrete from the initial appearance of microcracks to complete fracture by using a linear softening curve, that is, the phenomenon that the stress-strain relationship of concrete gradually softens (i.e. stress decreases while strain continues to increase). Among them, the fracture energy (G f) can measure a material's ability to absorb energy before fracture, quantifying this softening behavior. The crack bandwidth parameter, h, is also introduced to characterize the width of cracks in concrete. In this embodiment, the crack bandwidth h is simplified to the cube root of the grid cell volume to ensure that the crack width matches the model's discretization level, improving the rationality of the simulation.

[0151] It should be noted that the CEB-FIP (Joint Committee of the International Concrete Institute and the European Concrete Institute) model code is one of the international standards for the design and analysis of concrete structures. The 2010 version of the model code provides a method for calculating the fracture energy of concrete. This embodiment can accurately evaluate the energy absorption capacity of concrete during the fracture process through the 2010 version of the model. It can be assumed that concrete is an ideal elastic material when under pressure, ignoring the plastic deformation or damage that may occur in actual concrete under high pressure, so as to simplify the data analysis of the model and focus on the tensile and corrosion problems of concrete. In this embodiment, the corrosion of steel bars causes volume expansion, which can be simulated by applying displacement at the interface between the steel bars and the concrete. In this way, the non-uniform expansion behavior caused by corrosion is taken into account, and the spatial variation of this corrosion phenomenon along the axis of the steel bars is simulated.

[0152] In this embodiment, during the finite element modeling process, the steel bars are not directly modeled as solids. Instead, a "hole" is created in their location (i.e., the space occupied by the steel bars is deducted). The expansion effect of the steel bars is simulated by applying radial displacement to the concrete elements surrounding the hole. This simplifies the modeling of the interaction between steel and concrete while effectively capturing the complex stress state caused by steel corrosion. Thus, this embodiment proposes a numerical simulation method for establishing a three-dimensional reinforced concrete beam finite element model. This method aims to comprehensively analyze the mechanical response of reinforced concrete structures under the influence of steel corrosion, including crack formation and expansion, and the interaction between concrete and steel. This provides an important data foundation for determining the first mapping relationship between steel corrosion distribution and crack width distribution.

[0153] For example, based on the first to fifth embodiments of the present application, in one embodiment of the present application, please refer to Figure 2 , Figure 2 This is a schematic diagram of the structure of a reinforced concrete beam member provided in one embodiment of the present application. Figure 2 The reinforced concrete beam member shown includes one longitudinal reinforcement and the cross section of the beam is 80×140 mm. 2 , length is 1460mm.

[0154] It should be noted that by conducting an electrical accelerated corrosion experiment, the mapping relationship data between the spatial distribution of steel bar corrosion rate and the crack width distribution on the surface of reinforced concrete components at different corrosion levels can be obtained. Specifically, different experimental conditions can be used in the experiment to obtain multiple groups of corrosion test sample data. For example, the steel bar diameter can be 13mm or 19mm, the protective layer thickness can be 10mm or 20mm, and the current density can be 10μA / cm 2 , 50μA / cm 2 , 100μA / cm 2 , 200μA / cm 2 , 500μA / cm 2 or 1000μA / cm 2 .

[0155] Please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of a three-dimensional reinforced concrete beam finite element model generated by an embodiment of the data augmentation method of this application. In this embodiment, the relevant equations of the finite element simulation can be introduced, and the relevant distance parameters of the relevant equations of the finite element simulation can be determined based on the design parameters. 31.4 mm can be selected as the relevant distance parameter, and the corrosion rate of each unit along the length of the steel bar can be calculated. The Nataf transform method can be introduced to simulate the variability characteristic parameters of the corrosion space to generate crack width distribution data corresponding to the spatial distribution of steel bar corrosion rates that obey the logarithmic function relationship.

[0156] Please refer to Figure 4 and Figure 5 , Figure 4 This is a schematic diagram of the structure of the steel bar corrosion expansion model generated by the first embodiment of the data augmentation method of this application. Figure 5 This is a spatial distribution diagram of steel bar corrosion rate generated by the first embodiment of the data augmentation method of this application. The steel bar can be simulated as a "hole" and the non-uniform corrosion around the steel bar and along the axis of the steel bar can be simulated by applying radial displacement to represent the spatial expansion of steel bar corrosion. The spatial distribution of steel bar corrosion rate is substituted into the steel bar corrosion expansion model by means of correction coefficients, and the expansion displacement data of the unit node applied to the steel bar concrete interface is calculated to simulate the corrosion expansion of the steel bar. Among them, Figure 4 u in θ is the function value of the corrosion distribution curve (i.e., the function value of the rust layer thickness), R is the original radius of the steel bar, u1 is the maximum corrosion layer thickness closest to the concrete surface, u2 is the corrosion layer thickness on the side away from the concrete surface, S1 is the area of ​​the steel bar that actually loses its effective cross-sectional area after corrosion; S2 is the area occupied by the rust layer after corrosion; θ represents the angle, and r represents the polar coordinate system. Figure 5 The average corrosion rate of steel bars η is shown ina Spatial distribution of steel bar corrosion rate along the length direction when the corrosion rate is 5%, 10% and 15%.

[0157] Please refer to Figure 6 , Figure 6 The data sample scatter plot of the first mapping relationship between steel bar corrosion distribution and crack width distribution generated by the first embodiment of the data augmentation method of this application. The spatial distribution of steel bar corrosion rate under different corrosion degrees can be generated by multiple samplings, and the concrete surface crack width distribution results generated under each corrosion distribution are matched one by one. The data augmentation of the first mapping relationship between steel bar corrosion distribution (i.e., different corrosion rates) and crack width distribution can be obtained as follows: Figure 6 As shown in Figure 1, where C is the protective layer thickness and d is the steel bar diameter. The sequence-to-sequence mapping database obtained in this embodiment can be used as a training dataset for training a neural network model (sequence-to-sequence data model). The spatial distribution of steel bar corrosion rate inside a concrete structure can be predicted by detecting crack width distribution on the surface, thereby achieving a probabilistic prediction of the long-term performance of the concrete structure.

[0158] Please refer to Figure 7 , which shows a schematic structural diagram of a data augmentation device suitable for implementing an embodiment of the present application. The data augmentation device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the data augmentation device are also stored in RAM1004. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. The communication devices 1009 can allow the data augmentation device to communicate with other devices wirelessly or by wire to exchange data. Although the figures show a data augmentation device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have instead.

[0159] The data augmentation device provided by the application adopts the data augmentation method in the above-mentioned embodiments, and can solve the technical problem that the existing deterioration prediction method of reinforced concrete excessively simplifies the prediction of the remaining service life of the bridge structure. Compared with the prior art, the beneficial effects of the data augmentation device provided by the application are the same as those of the data augmentation method of the mapping relationship between the steel corrosion distribution and the crack width distribution provided by the above-mentioned embodiments, and other technical features in the data augmentation device are the same as those disclosed in the above-mentioned embodiment method, and will not be repeated here.

[0160] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0161] The above only describes some embodiments of the application, and does not limit the patent scope of the application, and any equivalent structural transformation made by using the content of the application specification and drawings, or directly / indirectly applied to other related technical fields within the technical concept of the application is included in the patent protection scope of the application.

Claims

1. A data augmentation method, characterized in that: The method comprises: Obtaining design parameters of a reinforced concrete beam component and corrosion test sample data of the reinforced concrete beam component that meets the design parameters; the corrosion test sample data includes mapping relationship data between a spatial distribution of steel corrosion rate and a crack width distribution; the crack width is a crack width on the surface of the reinforced concrete beam component; According to the design parameters, a finite element model of a reinforced concrete beam is established; Establish a steel bar corrosion expansion model; Determining the average corrosion rate of the steel bars and the standard deviation of the steel bar corrosion rate based on the corrosion test sample data, and determining a logarithmic function relationship between the average corrosion rate of the steel bars and the standard deviation of the steel bar corrosion rate by a fitting method; Introducing relevant equations of finite element simulation, and determining relevant distance parameters of the relevant equations of finite element simulation according to the design parameters; Using the steel bar corrosion expansion model as a boundary condition and based on the relevant equations of the finite element simulation, the expansion displacement of each unit of the reinforced concrete beam finite element model is calculated to perform a finite element simulation of the surface concrete cracking process caused by concrete surface corrosion expansion; The logarithmic function relationship is input into the reinforced concrete beam finite element model, and the variability characteristic parameters of the corrosion space are simulated using the Nataf transformation method to generate the spatial distribution of steel corrosion rate and the corresponding crack width distribution data that obey the logarithmic function relationship, and obtain the corrected augmented mapping relationship data of the spatial distribution of steel corrosion rate and crack width distribution.

2. The method according to claim 1, wherein The step of obtaining design parameters of reinforced concrete beam components and corrosion test sample data of reinforced concrete beam components that meet the design parameters includes: Obtaining design parameters of reinforced concrete beam components, including component length, cross-sectional dimensions, concrete strength, cover thickness, and steel bar diameter; The corrosion test sample data obtained by subjecting a reinforced concrete beam component meeting the design parameters to accelerated corrosion by electricity is obtained.

3. The method according to claim 2, wherein The step of obtaining the corrosion test sample data obtained by subjecting the reinforced concrete beam component meeting the design parameters to accelerated corrosion by electricity comprises: Obtaining first corrosion test sample data obtained by subjecting a reinforced concrete beam component meeting the design parameters to accelerated corrosion under different current conditions; wherein the first corrosion test sample data includes mapping relationship data between a spatial distribution of steel bar corrosion rates and crack width distributions along the length of the steel bars under different current conditions; According to the spatial distribution of steel bar corrosion rate along the length direction under different current conditions, the spatial distribution of steel bar corrosion rate under different corrosion rates is determined; According to the spatial distribution of steel bar corrosion rate under different corrosion rates, the average steel bar corrosion rate is determined; According to the average steel bar corrosion rate, mapping relationship data between the steel bar corrosion rate spatial distribution and the crack width distribution is generated.

4. The method according to claim 1, wherein The relevant equations of the finite element simulation include an exponential correlation function, which is specifically: in, is the function value of the correlation between the corrosion of steel bar elements, is the correlation distance parameter of the correlation equation, It is the center distance between two adjacent steel bar elements along the length of the steel bar.

5. The method according to claim 1, wherein The step of establishing a finite element model of a reinforced concrete beam according to the design parameters comprises: According to the design parameters, a concrete model is established by introducing an eight-node solid element method; Based on the concrete model, the tensile behavior of the concrete model is simulated by introducing a linear softening curve of fracture energy; Based on the tensile behavior of the concrete model, a three-dimensional finite element model of the reinforced concrete beam is established.

6. The method according to claim 1, wherein The steps of establishing the steel bar corrosion expansion model include: The corrosion distribution curve of the elliptical expression is introduced to simulate the corrosion expansion behavior of each steel bar section to establish the steel bar corrosion expansion model; wherein, the corrosion distribution curve of the elliptical expression is: is the original radius of the reinforcement, is the maximum corrosion layer thickness closest to the concrete surface, is the thickness of the corrosion layer on the side away from the concrete surface, is the corrosion distribution curve function value of the ellipse expression.

7. The data augmentation method according to claim 1, wherein: Also includes: The step of generating the augmented mapping relationship data of the corrected spatial distribution of the steel bar corrosion rate and the crack width distribution is cyclically executed until the data amount of the augmented mapping relationship data reaches a preset target data amount, and then the step of generating the augmented mapping relationship data of the corrected spatial distribution of the steel bar corrosion rate and the crack width distribution is stopped.

8. A data augmentation device, characterized in that: The data augmentation device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data augmentation method according to any one of claims 1 to 7.

Images