Data augmentation methods, devices, storage media, and computer program products thereof

Abstract

This application discloses a data augmentation method, device, storage medium, and computer program product, relating to the field of bridge performance prediction technology. The method includes: obtaining the spatial distribution of steel reinforcement corrosion rate; determining the standard deviation of the steel reinforcement corrosion rate based on the spatial distribution; and determining the logarithmic function relationship between the standard deviation and the average corrosion rate of the steel reinforcement through a fitting method; simulating the spatial distribution of the steel reinforcement corrosion rate using the Nataf transform method based on the standard deviation and the average corrosion rate to generate a steel reinforcement corrosion rate distribution that follows a logarithmic distribution, and inputting this distribution into a finite element model of a reinforced concrete beam to obtain the crack width distribution; iteratively executing the above steps until a termination condition is met, at which point the calculation ends and returns to establish the mapping relationship between the spatial distribution of steel reinforcement corrosion rate and the crack width distribution. This application can solve the problem that the data available for obtaining this sequence-sequence mapping relationship under existing laboratory conditions is very limited.

Description

Technical Field

[0001] This application relates to the field of long-term performance degradation prediction technology for bridges, and in particular to a data augmentation method and apparatus, storage medium and computer program product thereof. Background Technology

[0002] In chloride-rich environments, steel corrosion is a major cause of performance degradation in reinforced concrete structures. The passivation film on steel bars is relatively stable in the highly alkaline environment of concrete. When this passivation film is damaged by chloride ion erosion, corrosion occurs in the steel bars. The volume expansion of corrosion products leads to cracking and even spalling of the concrete cover. External corrosive media can more easily reach the steel bar surface, accelerating the corrosion process. With a significant decrease in the cross-sectional area of ​​the steel bars and the bond strength between the concrete and the steel bars, the load-bearing capacity also decreases, leading to service performance failure and long-term structural degradation.

[0003] In structural inspection methods, visual inspection is a low-cost and universal technique for assessing the deterioration of existing reinforced concrete structures, and it has been widely used in developing maintenance strategies for existing bridges. For corroded reinforced concrete structures, the width of surface cracks caused by steel corrosion is the most commonly used visual inspection indicator. Many researchers have attempted to link the state of steel corrosion (i.e., cross-sectional area loss) with crack width, and have proposed numerous empirical and mechanical models to describe the relationship between the degree of steel corrosion and crack width. Once the random variables involved in predicting steel corrosion are identified and the relationship between the amount of steel corrosion and crack width is established, update theories and nonlinear filtering techniques can be applied to reduce the uncertainty in predicting structural performance deterioration.

[0004] Due to the combined influence of various factors, such as different environmental exposure conditions, concrete cover thickness, and construction quality, steel reinforcement corrosion exhibits a non-uniform spatial distribution. Simultaneously, the crack width of corrosion on the bridge structure surface also exhibits randomness and non-uniformity in spatial distribution. The structural load-bearing capacity of reinforced concrete beam members strongly depends on the local conditions of their reinforcement. Ignoring the spatial variability of steel reinforcement corrosion would lead to an oversimplification of the prediction of the remaining service life of the bridge structure. Therefore, establishing the relationship between steel reinforcement corrosion rate distribution and crack width distribution (i.e., a sequence-to-sequence mapping relationship) is crucial for the performance analysis and prediction of bridge structures. However, data for obtaining such a sequence-to-sequence mapping relationship under existing laboratory conditions is very limited. Summary of the Invention

[0005] The main objective of this application is to propose a data augmentation method and its apparatus, storage medium, and computer program product, which aims to address the problem that the data available for obtaining such sequence-sequence mapping relationships under existing laboratory conditions is very limited.

[0006] To achieve the above objectives, the data augmentation method proposed in this application includes:

[0007] The spatial distribution of corrosion rate along the length of the steel bar is obtained. Based on the spatial distribution of corrosion rate along the length of the steel bar, the standard deviation of steel bar corrosion rate is determined. The logarithmic function relationship between the standard deviation of steel bar corrosion rate and the average corrosion rate of steel bar is determined by fitting method.

[0008] Based on the standard deviation and average corrosion rate of steel bars, the Nataf transformation method is used to simulate the spatial distribution of corrosion rate of steel bars along the length direction to generate a steel bar corrosion rate distribution that follows a logarithmic distribution. This is then input into the finite element model of the reinforced concrete beam to obtain the crack width distribution corresponding to the steel bar corrosion rate distribution that follows a logarithmic distribution.

[0009] The process iteratively executes steps to obtain the spatial distribution of corrosion rate along the length of the reinforcing bars. Based on this spatial distribution, the standard deviation of the corrosion rate is determined. A fitting method is used to establish the logarithmic function relationship between the standard deviation and the average corrosion rate of the reinforcing bars. Then, based on the standard deviation and average corrosion rate, the Nataf transform method is used to simulate the spatial distribution of corrosion rate along the length of the reinforcing bars, generating a logarithmic corrosion rate distribution. This distribution is then input into the finite element model of the reinforced concrete beam to obtain the crack width distribution corresponding to the logarithmic corrosion rate distribution. The process continues until a termination condition is met, at which point the calculation ends and returns to establish the mapping relationship between the spatial distribution of the reinforcing bar corrosion rate and the crack width distribution.

[0010] In one embodiment, the logarithmic relationship between the standard deviation of the steel reinforcement corrosion rate and the average corrosion rate of the steel reinforcement is as follows:

[0011]

[0012] in, For the standard deviation of steel corrosion rate, This represents the average corrosion rate of the reinforcing steel.

[0013] In one embodiment, the step of simulating the spatial distribution of steel corrosion rate along its length using the Nataf transform method based on the standard deviation and average corrosion rate of the steel reinforcement to generate a logarithmic steel corrosion rate distribution, and inputting this distribution into the finite element model of the reinforced concrete beam to obtain the crack width distribution corresponding to the logarithmic steel corrosion rate distribution, specifically includes:

[0014] Based on the standard deviation and average corrosion rate of steel bars, the Nataf transformation method is used to simulate the spatial distribution of corrosion rate of steel bars along the length direction, so as to generate a steel bar corrosion rate distribution that follows a logarithmic distribution.

[0015] Obtain the calibration coefficients, input the steel corrosion rate distribution that follows a logarithmic distribution into the steel corrosion expansion model, and calculate the expansion displacement of the unit nodes applied to the reinforced concrete interface.

[0016] The expansion displacement of the element nodes applied to the reinforced concrete interface is input into the finite element model of the reinforced concrete beam to simulate the non-uniform corrosion around the steel bars and along the steel bar axis, and the crack width distribution corresponding to the steel bar corrosion rate distribution that follows a logarithmic distribution is obtained.

[0017] In one embodiment, the non-uniform corrosion around the reinforcing bar will generate non-uniform radial expansion pressure on the surrounding concrete. A corrosion distribution curve is used to express the corrosion expansion behavior of each reinforcing bar cross-section. The expression of the corrosion distribution curve is as follows:

[0018]

[0019] in, The function value corresponding to the corrosion distribution curve. The original radius of the reinforcing bar. The maximum corrosion layer thickness closest to the concrete surface. The thickness of the corrosion layer on the side furthest from the concrete surface.

[0020] In one embodiment, the relationship between the expansion displacement of the unit nodes applied to the reinforced concrete interface is:

[0021]

[0022] in, The unit node expansion displacement applied to the reinforced concrete interface is also the maximum corrosion layer thickness closest to the concrete surface. η The corrosion rate was measured in the experiment. Here, R is the calibration coefficient, and R is the original radius of the reinforcing bar. The thickness of the porous region formed at the steel / concrete interface.

[0023] In one embodiment, the establishment of the finite element model of the reinforced concrete beam specifically includes the following steps:

[0024] The fracture softening curve is input into the concrete model to simulate the tensile behavior of concrete.

[0025] A finite element model of a reinforced concrete beam is established based on the tensile behavior of concrete.

[0026] In one embodiment, the steps for obtaining the corrosion rate distribution of the reinforcing bar along its length specifically include:

[0027] Obtain the design parameters of the reinforced concrete beam member, including the length, cross-sectional dimensions, concrete strength, concrete cover thickness, and steel bar diameter of the reinforced concrete beam member;

[0028] Based on the design parameters of reinforced concrete beams, an accelerated corrosion test was conducted on the reinforced concrete beam members to obtain the spatial distribution of corrosion rate along the length of the reinforcing bars.

[0029] In addition, to achieve the above objectives, this application also proposes a data augmentation device, which includes a memory, a processor, and a data augmentation program stored in the memory and executable on the processor, the data augmentation program being configured to implement the steps of the data augmentation method as described above.

[0030] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a data augmentation program is stored, and when the data augmentation program is executed, it implements the steps of the data augmentation method as described above.

[0031] In addition, to achieve the above objectives, this application also proposes a computer program product, which includes a data augmentation program that, when executed, implements the steps of the data augmentation method as described above.

[0032] This application obtains the spatial distribution of corrosion rate along the length of the reinforcing steel bars, determines the standard deviation of the corrosion rate based on this spatial distribution, and establishes the logarithmic function relationship between the standard deviation and the average corrosion rate of the reinforcing steel bars using a fitting method. Based on the standard deviation and average corrosion rate, the Nataf transform method is used to simulate the spatial distribution of corrosion rate along the length of the reinforcing steel bars to generate a logarithmic corrosion rate distribution, which is then input into a finite element model of a reinforced concrete beam to obtain the crack width distribution corresponding to the logarithmic corrosion rate distribution. The above steps are repeated until a termination condition is met, at which point the calculation ends and returns to establish the mapping relationship between the spatial distribution of the reinforcing steel corrosion rate and the crack width distribution. Thus, this application can generate artificial data samples with the same characteristics as experimental samples, thereby expanding the data on the relationship between the spatial distribution of steel corrosion rate and crack width distribution. By detecting the crack width distribution on the surface of reinforced concrete beam members, the spatial distribution of steel corrosion rate inside the concrete structure can be predicted, realizing the probabilistic prediction of the long-term performance of the concrete structure. This provides a new data foundation for establishing a performance degradation evaluation of corroded concrete structures based on detection information, and also provides data-level support for the performance evaluation of bridge components affected by corrosion in coastal environments. It has profound significance for the formulation of maintenance strategies for the entire life cycle of bridges under the influence of corrosion. Attached Figure Description

[0033] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart illustrating an embodiment of the data augmentation method of this application is provided;

[0036] Figure 2 A flowchart illustrating another embodiment of the data augmentation method of this application is provided;

[0037] Figure 3 A flowchart is provided for yet another embodiment of the data augmentation method of this application;

[0038] Figure 4 A flowchart is provided for yet another embodiment of the data augmentation method of this application;

[0039] Figure 5 A schematic diagram provided for an embodiment of the data augmentation method of this application;

[0040] Figure 6 A front structural schematic diagram of a reinforced concrete beam member provided in an embodiment of the data augmentation method of this application;

[0041] Figure 7 A side view of a reinforced concrete beam member provided in an embodiment of the data augmentation method of this application;

[0042] Figure 8 A schematic diagram of a finite element model of a reinforced concrete beam provided for an embodiment of the data augmentation method of this application;

[0043] Figure 9 A logarithmic distribution map of steel corrosion rate is provided as an embodiment of the data augmentation method of this application.

[0044] Figure 10 A schematic diagram of a steel reinforcement corrosion expansion model provided for an embodiment of the data augmentation method of this application;

[0045] Figure 11 A schematic diagram of a steel reinforcement corrosion expansion model provided for another embodiment of the data augmentation method of this application;

[0046] Figure 12A scatter plot of data samples showing the mapping relationship between the steel corrosion rate distribution and crack width distribution generated by an embodiment of the data augmentation method of this application;

[0047] Figure 13 This is a schematic diagram of the device structure of the hardware operating environment involved in the data augmentation method of this 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 Implementation

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

[0050] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0051] In chloride-rich environments, steel corrosion is a major cause of performance degradation in reinforced concrete structures. The passivation film on steel bars is relatively stable in the highly alkaline environment of concrete. When this passivation film is damaged by chloride ion erosion, corrosion occurs in the steel bars. The volume expansion of corrosion products leads to cracking and even spalling of the concrete cover. External corrosive media can more easily reach the steel bar surface, accelerating the corrosion process. With a significant decrease in the cross-sectional area of ​​the steel bars and the bond strength between the concrete and the steel bars, the load-bearing capacity also decreases, leading to service performance failure and long-term structural degradation.

[0052] In structural inspection methods, visual inspection is a low-cost and universal technique for assessing the deterioration of existing reinforced concrete structures, and it has been widely used in developing maintenance strategies for existing bridges. For corroded reinforced concrete structures, the width of surface cracks caused by steel corrosion is the most commonly used visual inspection indicator. Many researchers have attempted to link the state of steel corrosion (i.e., cross-sectional area loss) with crack width, and have proposed numerous empirical and mechanical models to describe the relationship between the degree of steel corrosion and crack width. Once the random variables involved in predicting steel corrosion are identified and the relationship between the amount of steel corrosion and crack width is established, update theories and nonlinear filtering techniques can be applied to reduce the uncertainty in predicting structural performance deterioration.

[0053] Due to the combined influence of various factors, such as different environmental exposure conditions, concrete cover thickness, and construction quality, steel reinforcement corrosion exhibits a non-uniform spatial distribution. Similarly, the crack width of corrosion on the bridge structure surface also shows randomness and non-uniformity in space. The structural load-bearing capacity of reinforced concrete beam members strongly depends on the local conditions of their reinforcement. Ignoring the spatial variability of steel reinforcement corrosion would lead to an oversimplification of the prediction of the remaining service life of the bridge structure. Therefore, establishing the relationship between steel reinforcement corrosion rate distribution and crack width distribution (i.e., a sequence-to-sequence mapping relationship) is crucial for the performance analysis and prediction of bridge structures. However, existing data on obtaining such a sequence-to-sequence mapping relationship under laboratory conditions are very limited.

[0054] To address the aforementioned issues, this application proposes a data augmentation method.

[0055] It should be noted that the execution subject of the data augmentation method of this application can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions. The following description uses a data augmentation device as the execution subject to illustrate this embodiment and the subsequent embodiments.

[0056] Based on this, this application provides a data augmentation method, please refer to... Figure 1 The data augmentation method includes steps S10 to S30:

[0057] S10. Obtain the spatial distribution of corrosion rate along the length of the steel bar. Based on the spatial distribution of corrosion rate along the length of the steel bar, determine the standard deviation of the steel bar corrosion rate. Then, determine the logarithmic function relationship between the standard deviation of the steel bar corrosion rate and the average corrosion rate of the steel bar through a fitting method.

[0058] In this embodiment, the design parameters of the reinforced concrete beam member are manually acquired, including but not limited to the member's length, cross-sectional dimensions, concrete strength, protective layer thickness, rebar diameter, rebar type, rebar yield strength and tensile strength, reinforcement ratio (number, diameter, and spacing of main bars and stirrups), and rebar placement. Based on similarity theory, the scale of the experimental model can be designed to ensure that the model reflects the mechanical behavior of the prototype in the experiment. Environmental conditions for the experiment (such as temperature, humidity, and medium) can be set to conduct corrosion or durability tests on the reinforced concrete beam member. Data acquisition devices such as strain gauges and displacement sensors are placed at key locations on the reinforced concrete beam member to monitor parameters such as stress, strain, and deflection, and to obtain the occurrence and development of cracks. This yields, but is not limited to, the corrosion rate distribution along the length of the rebar, the crack width distribution on the concrete member surface, and the corresponding rebar corrosion location distribution. The corrosion rate distribution along the length of the rebar, the crack width distribution on the concrete member surface, and the rebar corrosion location distribution are then stored as sample data in a data augmentation device.

[0059] When performing data augmentation, the data augmentation device extracts the spatial distribution of corrosion rate of steel bars along the length direction from the sample data. Using the standard deviation formula and the mean formula, the standard deviation of steel bar corrosion rate and the average corrosion rate of steel bars are calculated. The standard deviation of steel bar corrosion rate is also known as the characteristic parameter of corrosion spatial variability. Then, the relationship between the standard deviation of steel bar corrosion and the average corrosion rate of steel bars is determined by fitting method.

[0060] Based on the above, it should be noted that 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 interpret 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. Commonly used fitting methods include least squares, nonlinear least squares, polynomial fitting, and local fitting methods.

[0061] In one embodiment of this application, the relationship between the standard deviation of the steel corrosion rate and the average corrosion rate of the steel is a logarithmic function, specifically:

[0062]

[0063] in, For the standard deviation of steel corrosion rate, This represents the average corrosion rate of the reinforcing steel.

[0064] S20. Based on the standard deviation of steel corrosion rate and the average corrosion rate of steel, the Nataf transformation method is used to simulate the spatial distribution of corrosion rate of steel along the length direction to generate a steel corrosion rate distribution that follows a logarithmic distribution. This is then input into the finite element model of the reinforced concrete beam to obtain the crack width distribution corresponding to the steel corrosion rate distribution that follows a logarithmic distribution.

[0065] In this embodiment, since the corrosion of reinforcing bars has significant uncertainty along its length, it needs to be simulated using probabilistic methods. The spatial variability of reinforcing bar corrosion (standard deviation of reinforcing bar corrosion rate) is simulated using a logarithmic distribution. Combining the logarithmic distribution of the Nataf transform method allows the corrosion correlation between reinforcing bar elements to be considered in the simulation.

[0066] Specifically, the corrosion correlation between steel reinforcement units can be characterized by an autocorrelation function, expressed using an exponential correlation function. :

[0067]

[0068] in, This is a function value used to represent the corrosion correlation between steel reinforcement units; This parameter represents the relevant length and can be obtained based on the corrosion rate distribution of the reinforcing steel along its length in the above embodiments. In this embodiment, L It is 31.4mm; It is the center-to-center distance between two adjacent steel reinforcement units along the length of the steel reinforcement.

[0069] It should be noted that the Nataf transformation can be used to convert any random variable into a standard Gaussian distribution. n dimensional related random vectors The edge cumulative density function is The correlation coefficient matrix is Through Nataf transformation, It can be converted into an independent standard normal variable. The Nataf transformation process is as follows: [Related standard normal variables] It can be obtained from the following formula Transformation:

[0070]

[0071] in, for array elements, For edge cumulative density function, It is the marginal cumulative density function of the inverse of the standard Gaussian distribution. The correlation coefficient matrix of Y is... . and The relationship between them is shown in the following formula:

[0072]

[0073] in, From the equation

[0074]

[0075] Give, and These are the relevant variables and The mean; and These are the relevant variables and The standard deviation.

[0076] in, It can be done The calculation shows that the relationship between the two can be simplified by the following formula:

[0077]

[0078] It can be approximated by a polynomial as follows:

[0079]

[0080] Among them, parameters to It can be calculated using the Monte Carlo method. The obtained... Cholesky decomposition can be used to decompose It can be decomposed into a lower triangular matrix and an upper triangular matrix, as shown in the following equation:

[0081]

[0082] in, It is a lower triangular matrix. Therefore, the variable Y can be represented as... The product of the independent standard normal variable U and the variable U is shown in the following formula:

[0083]

[0084] The relationship between the independent standard normal variable U and the original correlated variable X can be established as an equation:

[0085]

[0086]

[0087]

[0088] ;

[0089] After generating a steel corrosion rate distribution that follows a logarithmic distribution, the data augmentation device inputs this steel corrosion rate distribution into a finite element model of a reinforced concrete beam. The finite element model of the reinforced concrete beam is then used to simulate the surface concrete cracking process caused by surface corrosion expansion, thereby obtaining the crack width distribution corresponding to the steel corrosion rate distribution that follows a logarithmic distribution.

[0090] S30. The process iteratively executes steps to obtain the spatial distribution of the corrosion rate of the reinforcing bars along the length direction. Based on this spatial distribution, the standard deviation of the corrosion rate is determined. The logarithmic function relationship between the standard deviation and the average corrosion rate is then determined using a fitting method. Finally, based on the standard deviation and average corrosion rate, the Nataf transform method is used to simulate the spatial distribution of the corrosion rate along the length direction to generate a logarithmic corrosion rate distribution. This distribution is then input into the finite element model of the reinforced concrete beam to obtain the crack width distribution corresponding to the logarithmic corrosion rate distribution. The process continues until the termination condition is met, at which point the calculation ends and returns to establish the mapping relationship between the spatial distribution of the corrosion rate and the crack width distribution.

[0091] In this embodiment, steps S10 to S20 are executed cyclically. By sampling multiple times, spatial distributions of steel corrosion rate under different corrosion levels are generated. The crack width distribution on the concrete surface generated under each steel corrosion rate spatial distribution is matched one-to-one. This process continues until the number of steel corrosion rate spatial distributions and crack width distributions both reach the target number of samples. This indicates that the number of steel corrosion rate spatial distributions and crack width distributions has met the conditions for establishing a mapping relationship. The calculation ends and returns to establish the mapping relationship between steel corrosion rate spatial distribution and crack width distribution. Artificial data samples with the same characteristics as the experimental samples are generated, thereby expanding the data on the relationship between steel corrosion rate spatial distribution and crack width distribution.

[0092] This application obtains the spatial distribution of corrosion rate along the length of the reinforcing steel bars, determines the standard deviation of the corrosion rate based on this spatial distribution, and establishes the logarithmic function relationship between the standard deviation and the average corrosion rate of the reinforcing steel bars using a fitting method. Based on the standard deviation and average corrosion rate, the Nataf transform method is used to simulate the spatial distribution of corrosion rate along the length of the reinforcing steel bars to generate a logarithmic corrosion rate distribution, which is then input into a finite element model of a reinforced concrete beam to obtain the crack width distribution corresponding to the logarithmic corrosion rate distribution. The above steps are repeated until a termination condition is met, at which point the calculation ends and returns to establish the mapping relationship between the spatial distribution of the reinforcing steel corrosion rate and the crack width distribution. Thus, this application can generate artificial data samples with the same characteristics as experimental samples, thereby expanding the data on the relationship between the spatial distribution of steel corrosion rate and crack width distribution. By detecting the crack width distribution on the surface of reinforced concrete beam members, the spatial distribution of steel corrosion rate inside the concrete structure can be predicted, realizing the probabilistic prediction of the long-term performance of the concrete structure. This provides a new data foundation for establishing a performance degradation evaluation of corroded concrete structures based on detection information, and also provides data-level support for the performance evaluation of bridge components affected by corrosion in coastal environments. It has profound significance for the formulation of maintenance strategies for the entire life cycle of bridges under the influence of corrosion.

[0093] In one embodiment of this application, please refer to Figure 2 S20 specifically includes S21~S23:

[0094] S21. Based on the standard deviation of steel corrosion rate and the average corrosion rate of steel, the Nataf transformation method is used to simulate the spatial distribution of steel corrosion rate along the length direction to generate a steel corrosion rate distribution that follows a logarithmic distribution.

[0095] It should be noted that the above content has already described the generation process of the steel corrosion rate distribution that follows a logarithmic distribution. For details, please refer to the above content. This embodiment and the following embodiments will not repeat the description.

[0096] S22. Input the steel corrosion rate distribution that follows a logarithmic distribution into the steel corrosion expansion model, and calculate the expansion displacement of the unit nodes applied to the reinforced concrete interface.

[0097] S23. Input the expansion displacement of the unit nodes applied to the reinforced concrete interface into the finite element model of the reinforced concrete beam to simulate the non-uniform corrosion around the steel bars and along the steel bar axis, and obtain the crack width distribution corresponding to the steel bar corrosion rate distribution that follows a logarithmic distribution.

[0098] It should be noted that both the steel reinforcement corrosion expansion model and the reinforced concrete beam finite element model are pre-stored in the data augmentation device. The steel reinforcement corrosion expansion model is used to simulate the corrosion expansion of the concrete surface, while the reinforced concrete beam finite element model is used to simulate the cracking process of the concrete surface caused by corrosion. The combined effect of the two models is primarily used for the finite element simulation of the cracking process of the concrete surface caused by corrosion expansion.

[0099] To reduce the complexity of establishing models for steel reinforcement corrosion expansion and finite element models of reinforced concrete beams, parameters that have little impact on obtaining the mapping relationship between the spatial distribution of steel corrosion rate and crack width distribution can be ignored, assumed, or simulated using similar methods. For example, since the compressive behavior of concrete has little impact on the calculation results of crack width caused by corrosion, the compressive behavior of concrete can be assumed to be that of an ideal elastic material. The steel reinforcement corrosion expansion model can be regarded as the expansion displacement of element nodes applied to the reinforced concrete interface, that is, the radial displacement applied to the reinforced concrete interface. When establishing the finite element model of the reinforced concrete beam, the steel reinforcement can be simulated as a "hole," and the non-uniform corrosion around the steel reinforcement and along the steel reinforcement axis can be simulated by applying radial displacement to represent the spatial expansion of steel reinforcement corrosion. For example, several assumptions can be made in the simulation of the corrosion expansion process, including: First, rust can be regarded as rigid, and its deformation can be ignored. Second, the influence of steel reinforcement corrosion on the crack width caused by corrosion near adjacent longitudinal steel reinforcement is not considered; only the relationship between the spatial distribution of steel corrosion rate of longitudinal steel reinforcement and the crack width caused by corrosion is considered. Third, the influence of stirrups on crack width is ignored in the finite element model. In this way, the complexity of establishing the steel corrosion expansion model and the finite element model of the reinforced concrete beam can be simplified, without affecting the subsequent analysis of the mapping relationship between the spatial distribution of steel corrosion rate and crack width distribution based on the steel corrosion expansion model and the finite element model of the reinforced concrete beam.

[0100] In one embodiment of this application, please refer to Figure 3 The establishment of the finite element model of the reinforced concrete beam specifically includes steps S201~S202:

[0101] S201. Input the fracture softening curve into the concrete model to simulate the tensile behavior of concrete.

[0102] S202. Based on the tensile behavior of concrete, a finite element model of a reinforced concrete beam is established.

[0103] In this embodiment, the concrete structure can be divided into multiple three-dimensional eight-node solid elements. Each element has eight vertices, enabling more precise capture of complex geometries and stress distributions. Concrete exhibits nonlinear behavior during tension, particularly exhibiting brittle fracture after reaching its ultimate limit. This embodiment uses a linear softening curve to describe the process of concrete from the initial appearance of microcracks to complete fracture, i.e., the gradual softening of the stress-strain relationship (i.e., stress decreases while strain continues to increase). Fracture energy (…) is introduced. G f This can measure a material's ability to absorb energy before fracture, thus quantifying this softening behavior. Furthermore, crack bandwidth is introduced. h This parameter characterizes the width of crack propagation in concrete. It defines the crack bandwidth. h The value is the cube root of the mesh element volume, designed to ensure that the crack width matches the discreteness of the model, thereby improving the rationality of the simulation.

[0104] 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 uses the 2010 version model to accurately assess the energy absorption capacity of concrete during the fracture process. It can be assumed that concrete is an ideal elastic material under compression, ignoring the plastic deformation or damage that may occur in actual concrete under high pressure, to simplify the data analysis of the model and facilitate a focus on the tensile and corrosion problems of concrete.

[0105] In this embodiment, the volume expansion caused by steel corrosion can be simulated by applying displacement at the reinforced concrete interface. This accounts for the non-uniform expansion behavior caused by corrosion and simulates the spatial variation of this corrosion phenomenon along the steel reinforcement axis. In the finite element model, the steel reinforcement is not directly modeled as a solid; instead, a "hole" is created at its location (i.e., the space occupied by the steel reinforcement is subtracted), and the expansion effect of the steel reinforcement is simulated by applying radial displacement to the concrete elements around the hole. This simplifies the modeling of the interaction between the steel reinforcement and concrete and effectively captures the complex stress state caused by steel corrosion. Thus, this embodiment proposes a numerical simulation method for establishing a finite element model of a reinforced concrete beam, aiming to comprehensively analyze the mechanical response of reinforced concrete structures under steel corrosion, including crack formation and propagation, as well as the interaction between concrete and steel reinforcement. This provides an important data foundation for determining the mapping relationship between the spatial distribution of steel corrosion rate and crack width distribution.

[0106] In this embodiment, the data augmentation device inputs the generated rebar corrosion rate distribution, which follows a logarithmic distribution, into the rebar corrosion expansion model. The rebar corrosion expansion model can obtain the expansion displacement of the unit nodes applied to the reinforced concrete interface. The expansion displacement of the unit nodes of the reinforced concrete interface is then input into the finite element model of the reinforced concrete beam. The finite element model of the reinforced concrete beam simulates the non-uniform corrosion around the rebar and along the rebar axis, and obtains the crack width distribution corresponding to the rebar corrosion rate distribution that follows a logarithmic distribution.

[0107] In one embodiment of this application, since non-uniform corrosion around the reinforcing bars will generate non-uniform radial expansion pressure on the surrounding concrete, the corrosion distribution curve of an elliptical expression can be used to describe the corrosion expansion behavior of each reinforcing bar cross-section. As a continuous function, the elliptical expression can accurately describe the non-uniformity of corrosion expansion of the reinforcing bar cross-section, reflecting the distribution characteristics of corrosion on the reinforcing bar cross-section, such as the coexistence of severe and slight corrosion, and simulating the differences in the impact of localized corrosion on the structure.

[0108] In one embodiment of this application, the expression for the corrosion distribution curve is:

[0109]

[0110] in, The function value corresponding to the corrosion distribution curve. The original radius of the reinforcing bar. The maximum corrosion layer thickness closest to the concrete surface. The thickness of the corrosion layer on the side furthest from the concrete surface.

[0111] It should be noted that the shape of the ellipse is determined by... Decision, here it is assumed .

[0112] In one embodiment of this application, after the reinforcing steel begins to corrode, the rust can expand freely. Once the voids in the porous area between the reinforcing steel and the surrounding concrete are completely filled with rust, the expansion of the rust will exert pressure on the surrounding concrete, thereby generating tensile stress and causing the concrete to crack. Not all rust will lead to increased stress and initial cracking of the overburden concrete; some rust may penetrate into the porous area. This application assumes that the porous area is uniform and its thickness is... δ It can be 12.5µm. During the free expansion stage of corrosion products, the unit length... l rust volume It can be represented as:

[0113]

[0114] in, It is the volume of corrosion products that penetrate into the porous region of the steel / concrete interface (i.e., 2π). Rδl ), This refers to the volume of steel reinforcement corroded during the free expansion stage 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 length of each unit... l rust volume for:

[0115]

[0116]

[0117] in, It is a unit length l The expansion volume, It refers to the volume of steel bars corroded after the gaps were filled with rust. The maximum corrosion layer thickness closest to the concrete surface. The thickness of the corrosion layer on the side furthest from the concrete surface. The original radius of the reinforcing bar.

[0118] Total amount of rust = + The corrosion originates from three interrelated processes, each directly or indirectly related to steel reinforcement corrosion. Specifically, first, the total corrosion includes corrosion that occupies the consumed steel reinforcement. In this case, corrosion occurs directly on the steel reinforcement surface, and the volume of the corrosion products (mainly iron oxide) is larger than the original steel reinforcement volume, causing the steel reinforcement itself to expand in volume. Second, the total corrosion includes corrosion that penetrates into the porous areas of the steel reinforcement / concrete interface. In this case, the iron oxide produced during corrosion can penetrate from the steel reinforcement surface into the tiny gaps or pores between the steel reinforcement and concrete. This penetration further exacerbates the bond breakdown between the steel reinforcement and concrete and may also form corrosion channels, promoting the intrusion of more moisture and corrosive media, accelerating the corrosion process. Third, the total corrosion includes corrosion that exerts expansion pressure on the surrounding concrete. In this case, the volume expansion of the corrosion products exerts pressure on the surrounding concrete, causing the concrete to crack or spall, reducing the structural integrity and durability. Since all rust is produced by steel reinforcement corrosion, the relationship is:

[0119]

[0120] in This represents the total amount of rust. For the volume of all corroded steel bars, It is the volume expansion ratio of the corrosion products, which can be assumed to be 2.0.

[0121] Some rust can seep out of the structure through cracks caused by corrosion and penetrate into the surrounding concrete. The amount of rust penetrating into the surrounding concrete depends on different experimental conditions. For example, in experiments using accelerated corrosion via electrical current, the amount of rust penetrating into the surrounding concrete depends on the current density level during the experiment. Lower current densities provide more opportunities for rust to fill the pores of the surrounding concrete. Conversely, at higher current densities, some rust is less likely to induce cracking in the surrounding concrete. Therefore, the corrosion rate in expansion simulations... Not consistent with the corrosion rate measured in experiments η Similarly, to simplify this problem, a calibration coefficient can be introduced. To take into account the influence of impact current density and average corrosion rate of steel bars on the pressure that causes corrosion cracks. and The relationship between them can be:

[0122]

[0123]

[0124] in, η represents the corrosion rate in the expansion simulation, and η represents the corrosion rate measured experimentally. For calibration coefficients, I corr For the impact current density, The average corrosion rate of the reinforcing steel. It can be 0.903. It can be 10.3. It can be 24.2. It can be −0.663.

[0125] In one embodiment of this application, To determine the maximum corrosion layer thickness closest to the concrete surface, it can be... The expansion displacement of the element nodes applied to the reinforced concrete interface is input into the finite element model of the reinforced concrete beam. Depend on The decision is based on the following relationship:

[0126]

[0127] Where η is the corrosion rate measured in the experiment. Here, R is the calibration coefficient, and R is the original radius of the reinforcing bar. The thickness of the porous region can be 12.5 µm.

[0128] Thus, this embodiment can simulate and calculate the total amount of corrosion based on the finite element model of reinforced concrete beams, and can take into account the corrosive effects of corrosion on steel bars and concrete, as well as the influence of impact current density and average steel bar corrosion rate on the pressure causing corrosion cracks under different experimental conditions. The simulated corrosion rate is corrected using calibration coefficients to improve the accuracy of finite element simulation, so as to better quantify the mapping relationship between the spatial distribution of steel bar corrosion rate and crack width distribution.

[0129] In one embodiment of this application, please refer to Figure 4 The establishment of the spatial distribution of corrosion rate along the length of the reinforcing steel bar specifically includes steps S101~S102:

[0130] S101. Obtain the design parameters of the reinforced concrete beam member, including the length, cross-sectional dimensions, concrete strength, concrete cover thickness, and steel bar diameter of the reinforced concrete beam member;

[0131] In this embodiment, regarding length and cross-sectional dimensions, for longer beams, the larger mid-span bending moment makes them prone to initial crack formation in the tension zone. Once the reinforcing steel begins to corrode, the crack width may rapidly expand due to the reduction in the effective cross-section of the reinforcing steel. For beams with larger cross-sectional dimensions, the larger moment of inertia makes cracking relatively less likely, but if corrosion does occur, internal corrosion is difficult to detect and repair is more challenging. Regarding concrete strength, high-strength concrete provides better crack resistance and slows the formation of initial cracks. However, the reinforcing steel in high-strength concrete is more susceptible to alkali-aggregate reaction or chloride ion corrosion. These factors accelerate steel corrosion, and the reduction in the cross-section of the reinforcing steel caused by corrosion increases stress concentration, thereby exacerbating the propagation of existing cracks. Regarding the protective layer thickness, the thickness of the protective layer directly affects the degree of contact between the reinforcing steel and the external corrosive medium. For example, a thinner protective layer makes the reinforcing steel more susceptible to corrosion, accelerating the corrosion process and potentially forming severe corrosion pits in localized areas. This leads to a reduction in the cross-section of the reinforcing steel in these areas, promoting the formation and rapid propagation of cracks. Conversely, a thicker protective layer can effectively slow down the corrosion process and reduce the occurrence and propagation of cracks. Regarding the diameter of reinforcing bars, although large-diameter reinforcing bars can improve the load-bearing capacity, their surface corrosion is more likely to form obvious corrosion pits, which will exert greater local pressure on the surrounding concrete and promote the formation and propagation of cracks. Conversely, small-diameter reinforcing bars cause a more uniform cross-sectional loss and may have a relatively smaller impact on the distribution of crack width, but they will increase the density of reinforcing bars and affect the quality of concrete pouring.

[0132] Therefore, the length, cross-sectional dimensions, concrete strength, concrete cover thickness, and steel bar diameter of reinforced concrete beam members are crucial in establishing the data augmentation that maps the spatial distribution of steel bar corrosion rate to the crack width distribution, and should all be taken into account in experimental analysis.

[0133] S102. Based on the design parameters of reinforced concrete beams, an accelerated corrosion test was conducted on the reinforced concrete beam members to obtain the spatial distribution of corrosion rate of the reinforcing bars along the length direction.

[0134] In this embodiment, the accelerated corrosion experiment using electricity simulates the corrosion process in the natural environment by applying direct current to the steel bars of the reinforced concrete beam, thus accelerating the corrosion rate of the steel bars. Specifically, the positive terminal of the DC power supply is connected to the steel bars, and the negative terminal is connected to an electrolyte (such as simulated seawater or sodium sulfate solution), forming an electrolytic cell that accelerates the dissolution process of the steel bars. Electrochemical techniques such as electrochemical impedance spectroscopy (EIS) and linear polarization resistance (LPR) can be used to periodically measure the corrosion current density of the steel bars. Combined with the weight loss method, the average corrosion rate and its distribution of the steel bars can be calculated. The non-uniformity of the corrosion rate will cause the corrosion rate of the steel bars in some areas to be much higher than in other areas. X-ray technology, digital image processing technology, or ultrasonic detection can be used to monitor the formation and propagation process of cracks on and inside the reinforced concrete surface. Special attention can be paid to the crack dynamics near the steel bar corrosion area, because the concrete in these areas is subjected to additional stress due to the expansion of the steel bars, making them prone to cracking. As corrosion progresses, the crack width around the steel bar corrosion area exhibits a non-uniform distribution, corresponding to the distribution of the steel bar corrosion rate. The crack width is larger near corrosion hotspots (areas with high corrosion rates).

[0135] In summary, this application, through electrolytically accelerated corrosion experiments on reinforced concrete beam members, can obtain, but is not limited to, the spatial distribution of corrosion rate of reinforcing bars along the length direction, as well as the crack width distribution on the surface of the concrete member and the corresponding distribution of corrosion location of reinforcing bars. This can provide experimental data support for subsequent statistical analysis and finite element analysis simulations, thereby broadening the mapping relationship between the spatial distribution of reinforcing bar corrosion rate and crack width.

[0136] For example, please refer to Figures 5 to 12 , Figure 6 and Figure 7 The reinforced concrete beam member shown includes one longitudinal steel bar, and the beam's cross-section is 80 × 140 mm. 2The steel bar is 1460 mm in length. Through accelerated corrosion experiments with an electric current, the spatial distribution of steel bar corrosion rate and the crack width distribution on the surface of reinforced concrete beam members under different corrosion levels can be obtained. Specifically, different experimental parameters can be used, such as a steel bar diameter of 13 mm or 19 mm, a protective layer thickness of 10 mm or 20 mm, and an electric current density of 10 μA / cm². 2 50μA / cm 2 100μA / cm 2 200μA / cm2, 500μA / cm 2 Or 1000 μA / cm 2 Furthermore, based on the spatial distribution of the corrosion rate of the reinforcing bars along the length direction under experimental conditions, the standard deviation and average deviation formulas can be used to calculate the standard deviation and average corrosion rate of the reinforcing bars under experimental conditions. The relationship between the standard deviation and average corrosion rate of the reinforcing bars is determined to be a logarithmic function through a fitting method. Based on the standard deviation and average corrosion rate of the reinforcing bars, the Nataf transform method can be introduced to simulate the spatial distribution of the corrosion rate along the length direction of the reinforcing bars, thereby generating a reinforcing bar corrosion rate distribution that follows a logarithmic distribution. See details... Figure 9 , Figure 9 The data shows the corrosion rate distribution of reinforcing bars along their length when the average corrosion rate is 5%, 10%, and 15%, respectively, and is input into [the database / system]. Figure 10 and Figure 11 The steel corrosion expansion model shown calculates the expansion displacement of the element nodes applied at the reinforced concrete interface, simulating the corrosion expansion of the steel reinforcement. The expansion displacement of the element nodes applied at the reinforced concrete interface can be input to... Figure 8 A finite element model of a reinforced concrete beam was used to obtain the crack width distribution corresponding to the logarithmic distribution of steel corrosion rate. Finally, by generating steel corrosion rate distributions under different corrosion levels through multiple samplings, and by mapping the crack width distributions on the concrete surface under each steel corrosion rate distribution to a specific value, data augmentation of the mapping relationship between the spatial distribution of steel corrosion rate and the crack width distribution can be obtained. Specifically, as shown below... Figure 12 As shown. Among them, C For the thickness of the protective layer, d The diameter of the reinforcing bar is denoted as . 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 pattern). It can predict the spatial distribution of steel bar corrosion inside a concrete structure by detecting the crack width distribution on the surface, thereby achieving probabilistic prediction of the long-term performance of the concrete structure.

[0137] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the data augmentation method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0138] This application provides a data augmentation device; please refer to [reference needed]. Figure 13 The data augmentation device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the data augmentation method in Embodiment 1 above.

[0139] The following is for reference. Figure 13 The diagram illustrates a structural schematic suitable for implementing the data augmentation device in the embodiments of this application. The data augmentation device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers.

[0140] It should be noted that, Figure 13 The data augmentation device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments described in this application.

[0141] like Figure 13As shown, the data augmentation device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the data augmentation device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected 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, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the data augmentation device to communicate wirelessly or wiredly with other devices to exchange data. Although the figures show data augmentation devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0142] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a data augmentation program carried on a computer-readable medium, the data augmentation program containing program code for performing the methods shown in the flowcharts. In such embodiments, the data augmentation program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the data augmentation program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0143] The data augmentation device provided in this application, employing the data augmentation method described in the above embodiments, can solve the problem that the data available for obtaining this type of sequence-sequence mapping relationship is very limited under existing laboratory conditions. Compared with the prior art, the beneficial effects of the data augmentation device provided in this application are the same as those of the data augmentation method provided in the above embodiments, and other technical features of this data augmentation device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0144] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0145] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0146] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., data augmentation program) stored thereon, which are used to execute the data augmentation method in the above embodiments.

[0147] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0148] The aforementioned computer-readable storage medium may be included in the data augmentation device; or it may exist independently and not assembled into the data augmentation device.

[0149] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the data augmentation device, cause the data augmentation device to perform data augmentation on the mapping relationship between the steel corrosion rate distribution and the crack width distribution based on the stochastic finite element method.

[0150] Data augmentation program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0151] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0152] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0153] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a data augmentation program) for executing the above-described data augmentation method. This addresses the problem that the amount of data available for obtaining this type of sequence-sequence mapping relationship is very limited under existing laboratory conditions. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the data augmentation method provided in the above embodiments, and will not be repeated here.

[0154] This application also provides a computer program product, including a data augmentation program, which, when executed, implements the steps of the data augmentation method described above.

[0155] The computer program product provided in this application can solve the problem that the data for obtaining such sequence-sequence mapping relationships is very limited under existing laboratory conditions. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the data augmentation method provided in the above embodiments, and will not be repeated here.

[0156] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A data augmentation method, characterized in that, include: The spatial distribution of corrosion rate along the length of the steel bar is obtained. Based on the spatial distribution of corrosion rate along the length of the steel bar, the standard deviation of steel bar corrosion rate is determined. The logarithmic function relationship between the standard deviation of steel bar corrosion rate and the average corrosion rate of steel bar is determined by fitting method. Based on the standard deviation and average corrosion rate of steel bars, the Nataf transformation method is used to simulate the spatial distribution of corrosion rate of steel bars along the length direction to generate a steel bar corrosion rate distribution that follows a logarithmic distribution. This is then input into the finite element model of the reinforced concrete beam to obtain the crack width distribution corresponding to the steel bar corrosion rate distribution that follows a logarithmic distribution. The process iteratively executes steps to obtain the spatial distribution of corrosion rate along the length of the reinforcing bars. Based on this spatial distribution, the standard deviation of the corrosion rate is determined. A fitting method is used to establish the logarithmic function relationship between the standard deviation and the average corrosion rate of the reinforcing bars. Then, based on the standard deviation and average corrosion rate, the Nataf transform method is used to simulate the spatial distribution of corrosion rate along the length of the reinforcing bars, generating a logarithmic corrosion rate distribution. This distribution is then input into the finite element model of the reinforced concrete beam to obtain the crack width distribution corresponding to the logarithmic corrosion rate distribution. The process continues until a termination condition is met, at which point the calculation ends and returns to establish the mapping relationship between the spatial distribution of the reinforcing bar corrosion rate and the crack width distribution.

2. The data augmentation method as described in claim 1, characterized in that, The logarithmic relationship between the standard deviation of the steel reinforcement corrosion rate and the average steel reinforcement corrosion rate is as follows: in, For the standard deviation of steel corrosion rate, This represents the average corrosion rate of the reinforcing steel.

3. The data augmentation method as described in claim 1, characterized in that, The steps of simulating the spatial distribution of steel corrosion rate along its length using the Nataf transform method based on the standard deviation and average corrosion rate of steel bars to generate a logarithmic steel corrosion rate distribution, and inputting this distribution into the finite element model of the reinforced concrete beam to obtain the crack width distribution corresponding to the logarithmic steel corrosion rate distribution, specifically include: Based on the standard deviation and average corrosion rate of steel bars, the Nataf transformation method is used to simulate the spatial distribution of corrosion rate of steel bars along the length direction, so as to generate a steel bar corrosion rate distribution that follows a logarithmic distribution. The corrosion rate distribution of steel bars, which follows a logarithmic distribution, is input into the steel bar corrosion expansion model to calculate the expansion displacement of the element nodes applied to the reinforced concrete interface. The expansion displacement of the element nodes applied to the reinforced concrete interface is input into the finite element model of the reinforced concrete beam to simulate the non-uniform corrosion around the steel bars and along the steel bar axis, and the crack width distribution corresponding to the steel bar corrosion rate distribution that follows a logarithmic distribution is obtained.

4. The data augmentation method as described in claim 3, characterized in that, The non-uniform corrosion around the reinforcing bars will generate non-uniform radial expansion pressure on the surrounding concrete. A corrosion distribution curve is used to express the corrosion expansion behavior of each reinforcing bar section. The expression of the corrosion distribution curve is as follows: in, The function value corresponding to the corrosion distribution curve. The original radius of the reinforcing bar. The maximum corrosion layer thickness closest to the concrete surface. The thickness of the corrosion layer on the side furthest from the concrete surface.

5. The data augmentation method as described in claim 3, characterized in that, The relationship between the expansion displacement of the element nodes applied to the reinforced concrete interface is as follows: in, The unit node expansion displacement applied to the reinforced concrete interface is also the maximum corrosion layer thickness closest to the concrete surface. η The corrosion rate was measured in the experiment. Here, R is the calibration coefficient, and R is the original radius of the reinforcing bar. The thickness of the porous region formed at the steel / concrete interface.

6. The data augmentation method as described in claim 3, characterized in that, The establishment of the finite element model of the reinforced concrete beam specifically includes the following steps: The fracture softening curve is input into the concrete model to simulate the tensile behavior of concrete. A finite element model of a reinforced concrete beam is established based on the tensile behavior of concrete.

7. The data augmentation method as described in claim 1, characterized in that, The steps for obtaining the spatial distribution of corrosion rate along the length of the reinforcing steel bars specifically include: Obtain the design parameters of the reinforced concrete beam member, including the length, cross-sectional dimensions, concrete strength, concrete cover thickness, and steel bar diameter of the reinforced concrete beam member; Based on the design parameters of reinforced concrete beams, an accelerated corrosion test was conducted on the reinforced concrete beam members to obtain the spatial distribution of corrosion rate along the length of the reinforcing bars.

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

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and the storage medium stores a data augmentation program, which, when executed, implements the steps of the data augmentation method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a data augmentation program that, when executed, implements the steps of the data augmentation method as described in any one of claims 1 to 7.

Images