Reinforced concrete structure model construction method and device and medium

Abstract

The invention relates to a reinforced concrete structure model construction method and device and a medium. The method comprises the steps that a first finite element model is established according to geometric parameters of a bridge basic structure; obtaining a material constitutive relation of the bridge structure according to a reinforced concrete structure tensile experiment; determining a first crack width calculation formula based on section model construction of the fiber beam column unit; embedding the material constitutive relation and a first crack width calculation formula into a first finite element model; inputting a structural load effect, and obtaining a structural performance degradation parameter and a structural crack parameter by using the first finite element model; according to the invention, the technology of more accurate reinforced concrete structure simulation based on the fiber beam column unit is realized, and the technical problem of difficult reinforcement crack simulation in the reinforced concrete structure is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of real-time simulation of bridge structures, and in particular to a reinforced concrete structure model construction method, device and medium. Background Art

[0002] The number of bridges is increasing, and the traffic volume is also increasing. The operation and maintenance supervision of bridges is becoming increasingly important. How to ensure the safe operation of bridges is an area that needs to be studied and explored in the future. In fact, not only bridges, but also other transportation facilities are facing such problems, such as tunnels, slopes, etc.

[0003] Safety monitoring of bridge facilities during operation is a very important field. In recent years, this field has also made some progress, but the current technology is still at the level of alarm and trend analysis of monitoring thresholds. In addition, the simulation model of the bridge during operation is only established in the monitoring scheme design stage, and can only simulate a single status quo.

[0004] How to realize real-time online simulation of bridge structure is a key research direction. At present, the technology mainly uses software to perform finite element simulation analysis, but this method still has many problems, such as:

[0005] 1) Based on the simple finite element model of elastic analysis, the updated model is difficult to predict the full process response of the structure;

[0006] 2) The updates based on dynamic response are far more than those based on static response, and generally only low-order modes are identified. However, low-order modal information mainly reflects the overall behavior of the structure, and is more sensitive to factors such as the environment and boundary conditions than to local damage. High-order modes that can reflect local damage are difficult to be excited in actual structures.

[0007] 3) There are many technologies for crack detection and identification, but there is currently no method to apply crack damage information to model updating. Summary of the invention

[0008] In view of the problems existing in the above background technology, the present invention provides a method, device and medium for constructing a reinforced concrete structure model. The specific technical solution is as follows:

[0009] A reinforced concrete structure model construction method comprises the following steps:

[0010] S1: Establish the first finite element model according to the geometric parameters of the basic structure of the bridge;

[0011] S2: The material constitutive relation of the bridge structure itself obtained from the tensile test of reinforced concrete structure, wherein the formula of the material constitutive relation is:

[0012]

[0013] ε t =f t / E c

[0014] Among them, σ c is the structural stress, ε is the structural strain, ε t is the concrete crack strain, E c is the structural elastic modulus, f t is the compressive strength of concrete;

[0015] S3: Based on the construction of the cross-section model of the fiber beam-column unit, a first crack width calculation formula is determined, and the first crack width calculation formula is:

[0016]

[0017] Where ω is the first crack width, L m is the average crack space length;

[0018] S4: embedding the material constitutive relationship and the first crack width calculation formula into the first finite element model;

[0019] S5: inputting a structural load action, wherein the structural load action is an applied force, and obtaining a structural performance degradation parameter and a structural crack parameter using the first finite element model;

[0020] S6: Determine a single load condition according to the structural type of the bridge, where the single load condition at least includes a concentrated force and a uniformly distributed load;

[0021] S7: According to the first finite element model, select key material performance parameters of the fiber beam-column model, wherein the key material performance parameters at least include the elastic modulus E of the steel bars in the reinforced concrete. r , elastic model of concrete E c ;

[0022] S8: inputting the single load condition and the key material performance parameters into the first finite element model, and obtaining a structural response through simulation calculation of the first finite element model, wherein the structural response includes at least a displacement of the main beam, a stress of the main beam, and a crack width;

[0023] S9: Using the root mean square error as a loss function to train the artificial neural network to obtain an artificial neural network proxy model, the formula of the loss function is:

[0024]

[0025] Among them, PF is the loss function, MSE is the root mean square error, T is the sample size of the training set, and e i is the network error of the i-th data point in the training set, t i is the true value in the training set, α i Automatically generated predictions for artificial neural network proxy models;

[0026] S10: obtaining test output parameters of the structure to be evaluated, and obtaining updated structural performance parameters of the model through inverse normalization calculation according to the artificial neural network proxy model;

[0027] S11: inputting the structural performance parameters updated by the model into the first finite element model to obtain a second finite element model that can truly reflect the structural state;

[0028] S12: Calculate a second crack width ω′ according to the second finite element model, and determine the performance state of the bridge reinforced concrete according to the second crack width ω′.

[0029] In a preferred implementation, embedding the material constitutive relation and the first crack width calculation formula into the first finite element model includes:

[0030] Embedding the material constitutive relation into a pre-processing program of the first finite element model as a subroutine of the first finite element model;

[0031] The first crack width calculation formula is used as a subroutine of the first finite element model and embedded into a post-processing program of the first finite element model.

[0032] In a preferred implementation, the S7 further includes: setting upper and lower limits of the key material performance parameters, and taking 1% of the upper and lower limits as intervals to generate a data set of the key material performance parameters.

[0033] In a preferred implementation, the method of using the root mean square error as a loss function to train the artificial neural network specifically includes:

[0034] The single load condition and the structural response are used as input and output training data respectively, and are brought into the loss function to perform adaptive iterative training on the artificial neural network. When the loss value is reduced to an allowable value, the training is automatically stopped and the artificial neural network proxy model is output.

[0035] In a preferred implementation, the test output parameters include at least static response data and dynamic response data, the static response data are output parameters of the static test, the dynamic response data are output parameters of the dynamic test, and the load effect of the test output parameters is consistent with the single load condition.

[0036] In a preferred implementation, judging the performance and structural state of the bridge reinforced concrete according to the second crack width ω′ specifically includes:

[0037] The second crack width ω′ and the structural crack limit ω limit For comparison:

[0038]

[0039] Among them, η ω is the performance structural state parameter of the bridge reinforced concrete, when η ω When η is less than 0.8, the performance and structure of the bridge reinforced concrete are in a safe state. ω When it is between 0.8 and 0.1, the performance and structure state of the bridge reinforced concrete is close to danger. ω When it is greater than 1, the performance and structural state of the bridge reinforced concrete is in a dangerous state.

[0040] A reinforced concrete structure model building device, comprising:

[0041] at least one processor; and,

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] 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:

[0044] Establishing a first finite element model according to geometric parameters of the basic structure of the bridge;

[0045] The material constitutive relationship of the bridge structure is obtained according to the tensile test of reinforced concrete structure, wherein the formula of the material constitutive relationship is:

[0046]

[0047] ε t =f t / E c

[0048] Among them, σ c is the structural stress, ε is the structural strain, ε t is the concrete crack strain, E c is the structural elastic modulus, f t is the compressive strength of concrete;

[0049] Based on the construction of the cross-section model of the fiber beam-column unit, the first crack width calculation formula is determined, and the first crack width calculation formula is:

[0050]

[0051] Where ω is the first crack width, L m is the average crack space length;

[0052] embedding the material constitutive relation and the first crack width calculation formula into the first finite element model;

[0053] Inputting a structural load action, and obtaining a structural performance degradation parameter and a structural crack parameter using the first finite element model, wherein the structural load action is an applied force;

[0054] Determine a single load condition according to the structural type of the bridge, wherein the single load condition includes at least a concentrated force and a uniformly distributed load;

[0055] According to the first finite element model, the key material performance parameters of the fiber beam-column model are selected, and the key material performance parameters at least include the elastic modulus E of the steel bars in the reinforced concrete. r , elastic model of concrete E c ;

[0056] Inputting the single load condition and the key material performance parameters into the first finite element model, and obtaining a structural response through simulation calculation of the first finite element model, wherein the structural response includes at least a displacement of the main beam, a stress of the main beam, and a crack width;

[0057] The root mean square error is used as the loss function to train the artificial neural network to obtain the artificial neural network proxy model. The formula of the loss function is:

[0058]

[0059] Among them, PF is the loss function, MSE is the root mean square error, T is the sample size of the training set, and e i is the network error of the i-th data point in the training set, t i is the true value in the training set, α i Automatically generated predictions for artificial neural network proxy models;

[0060] Acquire the test output parameters of the structure to be evaluated, and obtain the updated structural performance parameters of the model through inverse normalization calculation according to the artificial neural network proxy model;

[0061] Inputting the structural performance parameters updated by the model into the first finite element model to obtain a second finite element model that can truly reflect the structural state;

[0062] The second crack width ω′ is calculated according to the second finite element model, and the performance state of the bridge reinforced concrete is determined according to the second crack width ω′.

[0063] A non-volatile computer storage medium stores a computer program, wherein the non-volatile computer storage medium stores a computer program, and when the non-volatile computer program is executed by a processor, any one of the reinforced concrete structure model building methods is implemented.

[0064] Beneficial effects of the present invention:

[0065] (1) The present invention realizes a technology for more accurate simulation of reinforced concrete structures based on fiber beam-column units, solving the technical problem of difficulty in simulating steel bar cracks in reinforced concrete structures;

[0066] (2) The present invention realizes a technology that can perform model correction only by testing the structural response, which solves the technical problem that the traditional method requires simultaneous measurement of load conditions and structural response;

[0067] (3) The present invention realizes a technology for evaluating structural performance based on the crack state of the structure, solving the technical problem that traditional finite element method is difficult to evaluate the structure by simulating the crack state of the structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 The figure is a schematic diagram of the process of constructing the method in the present invention. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0070] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0071] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0072] In the present invention, unless otherwise clearly specified and limited, terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be connected, detachably connected, or integrated; it can be mechanically connected or electrically connected; it can be directly connected or indirectly connected through an intermediate medium, or it can be the internal connection of two elements.

[0073] like Figure 1 As shown, the present invention discloses a method for constructing a reinforced concrete structure model, comprising the following steps:

[0074] S1: Establish the first finite element model according to the geometric parameters of the basic structure of the bridge;

[0075] S2: The material constitutive relation of the bridge structure itself obtained from the tensile test of reinforced concrete structure, wherein the formula of the material constitutive relation is:

[0076]

[0077] ε t =f t / E c

[0078] Among them, σ c is the structural stress, ε is the structural strain, ε t is the concrete crack strain, E c is the structural elastic modulus, f t is the compressive strength of concrete;

[0079] S3: Based on the construction of the cross-section model of the fiber beam-column unit, a first crack width calculation formula is determined, and the first crack width calculation formula is:

[0080]

[0081] Where ω is the first crack width, L m is the average crack space length;

[0082] S4: embedding the material constitutive relationship and the first crack width calculation formula into the first finite element model;

[0083] Specifically, embedding the material constitutive relation and the first crack width calculation formula into the first finite element model includes:

[0084] Embedding the material constitutive relation into a pre-processing program of the first finite element model as a subroutine of the first finite element model;

[0085] The first crack width calculation formula is used as a subroutine of the first finite element model and embedded into a post-processing program of the first finite element model;

[0086] The present invention embeds the material constitutive relationship and the crack width calculation formula into the pre-processing module and the post-processing module respectively, improves the function of the first finite element model, and lays a calculation foundation for subsequent calculations.

[0087] S5: inputting a structural load action, wherein the structural load action is an applied force, and obtaining a structural performance degradation parameter and a structural crack parameter using the first finite element model;

[0088] S6: Determine a single load condition according to the structural type of the bridge, where the single load condition at least includes a concentrated force and a uniformly distributed load;

[0089] S7: According to the first finite element model, select key material performance parameters of the fiber beam-column model, wherein the key material performance parameters at least include the elastic modulus E of the steel bars in the reinforced concrete. r , elastic model of concrete E c ;

[0090] Specifically, the upper and lower limits of the key material performance parameters are set, and 1% of the upper and lower limits are taken as intervals to generate the data set of the key material performance parameters.

[0091] S8: inputting the single load condition and the key material performance parameters into the first finite element model, and obtaining a structural response through simulation calculation of the first finite element model, wherein the structural response includes at least a displacement of the main beam, a stress of the main beam, and a crack width;

[0092] S9: Using the root mean square error as a loss function to train the artificial neural network to obtain an artificial neural network proxy model, the formula of the loss function is:

[0093]

[0094] Among them, PF is the loss function, MSE is the root mean square error, T is the sample size of the training set, and e i is the network error of the i-th data point in the training set, t i is the true value in the training set, α iAutomatically generated predictions for artificial neural network surrogate models.

[0095] Specifically include:

[0096] The single load condition and the structural response are used as input and output training data respectively, and are brought into the loss function to perform adaptive iterative training on the artificial neural network. When the loss value is reduced to an allowable value, the training is automatically stopped, the allowable value is set to 0.001, and the artificial neural network proxy model is output.

[0097] S10: obtaining test output parameters of the structure to be evaluated, and obtaining updated structural performance parameters of the model through inverse normalization calculation according to the artificial neural network proxy model;

[0098] In a preferred implementation, the test output parameters include at least static response data and dynamic response data, the static response data are output parameters of the static test, the dynamic response data are output parameters of the dynamic test, and the load effect of the test output parameters is consistent with the single load condition.

[0099] S11: inputting the structural performance parameters updated by the model into the first finite element model to obtain a second finite element model that can truly reflect the structural state;

[0100] S12: Calculate a second crack width ω′ according to the second finite element model, and determine the performance state of the bridge reinforced concrete according to the second crack width ω′.

[0101] Specifically, the second crack width ω′ and the structural crack limit ω limit For comparison:

[0102]

[0103] Among them, η ω is the performance structural state parameter of the bridge reinforced concrete, when η ω When η is between 0.5 and 0.8, the performance and structure of the bridge reinforced concrete are in a safe state. ω When it is between 0.8 and 0.1, the performance and structure state of the bridge reinforced concrete is close to danger. ω When it is greater than 1, the performance and structural state of the bridge reinforced concrete is in a dangerous state.

[0104] A reinforced concrete structure model building device, comprising:

[0105] at least one processor; and,

[0106] a memory communicatively connected to the at least one processor; wherein,

[0107] 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:

[0108] Establishing a first finite element model according to geometric parameters of the basic structure of the bridge;

[0109] The material constitutive relationship of the bridge structure is obtained according to the tensile test of reinforced concrete structure, wherein the formula of the material constitutive relationship is:

[0110]

[0111] ε t =f t / E c

[0112] Among them, σ c is the structural stress, ε is the structural strain, ε t is the concrete crack strain, E c is the structural elastic modulus, f t is the compressive strength of concrete;

[0113] Based on the construction of the cross-section model of the fiber beam-column unit, the first crack width calculation formula is determined, and the first crack width calculation formula is:

[0114]

[0115] Where ω is the first crack width, L m is the average crack space length;

[0116] embedding the material constitutive relation and the first crack width calculation formula into the first finite element model;

[0117] Inputting a structural load action, and obtaining a structural performance degradation parameter and a structural crack parameter using the first finite element model, wherein the structural load action is an applied force;

[0118] Determine a single load condition according to the structural type of the bridge, wherein the single load condition includes at least a concentrated force and a uniformly distributed load;

[0119] According to the first finite element model, the key material performance parameters of the fiber beam-column model are selected, and the key material performance parameters at least include the elastic modulus E of the steel bars in the reinforced concrete. r , elastic model of concrete E c ;

[0120] Inputting the single load condition and the key material performance parameters into the first finite element model, and obtaining a structural response through simulation calculation of the first finite element model, wherein the structural response includes at least a displacement of the main beam, a stress of the main beam, and a crack width;

[0121] The root mean square error is used as the loss function to train the artificial neural network to obtain the artificial neural network proxy model. The formula of the loss function is:

[0122]

[0123] Among them, PF is the loss function, MSE is the root mean square error, T is the sample size of the training set, and e i is the network error of the i-th data point in the training set, t i is the true value in the training set, α i Automatically generated predictions for artificial neural network proxy models;

[0124] Acquire the test output parameters of the structure to be evaluated, and obtain the updated structural performance parameters of the model through inverse normalization calculation according to the artificial neural network proxy model;

[0125] Inputting the structural performance parameters updated by the model into the first finite element model to obtain a second finite element model that can truly reflect the structural state;

[0126] The second crack width ω′ is calculated according to the second finite element model, and the performance state of the bridge reinforced concrete is determined according to the second crack width ω′.

[0127] A non-volatile computer storage medium, wherein a computer program is stored in the non-volatile computer storage medium, and when the non-volatile computer program is executed by a processor, any one of the reinforced concrete structure model construction methods described above is implemented

[0128] The present invention realizes a technology for more accurate simulation of reinforced concrete structures based on fiber beam-column units, solving the technical problem of difficulty in simulating steel bar cracks in reinforced concrete structures;

[0129] The present invention realizes a technology that can correct the model only by testing the structural response, which solves the technical problem that the traditional method requires simultaneous measurement of the load condition and the structural response.

[0130] The present invention realizes a technology for evaluating structural performance based on the crack state of the structure, and solves the technical problem that traditional finite element method is difficult to evaluate the structure by simulating the crack state of the structure.

[0131] The above is only a preferred embodiment of the present invention, and its description is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that several improvements and modifications can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A reinforced concrete structure model construction method, characterized in that: The following steps are involved: S1: Establish the first finite element model according to the geometric parameters of the basic structure of the bridge; S2: The material constitutive relation of the bridge structure obtained from the tensile test of reinforced concrete structure, wherein the formula of the material constitutive relation is: e t =f t / E c Among them, σ c is the structural stress, ε is the structural strain, ε t is the concrete crack strain, E c is the structural elastic modulus, f t is the compressive strength of concrete; S3: Based on the cross-sectional model of the fiber beam-column unit, a first crack width calculation formula is determined, where the first crack width calculation formula is: Where ω is the first crack width, L m is the average crack space length; S4: embedding the material constitutive relationship and the first crack width calculation formula into the first finite element model; S5: inputting a structural load action, wherein the structural load action is an applied force, and obtaining a structural performance degradation parameter and a structural crack parameter using the first finite element model; S6: Determine a single load condition according to the structural type of the bridge, where the single load condition at least includes a concentrated force and a uniformly distributed load; S7: According to the first finite element model, select key material performance parameters of the fiber beam-column model, wherein the key material performance parameters at least include the elastic modulus E of the steel bars in the reinforced concrete. r , elastic model of concrete E c ; S8: inputting the single load condition and the key material performance parameters into the first finite element model, and obtaining a structural response through simulation calculation of the first finite element model, wherein the structural response at least includes a displacement of the main beam, a stress of the main beam, and a crack width; S9: Using the root mean square error as a loss function to train the artificial neural network to obtain an artificial neural network proxy model, the formula of the loss function is: Among them, PF is the loss function, MSE is the root mean square error, T is the sample size of the training set, and e i is the network error of the i-th data point in the training set, t i is the true value in the training set, α i Automatically generated predictions for artificial neural network proxy models; S10: obtaining test output parameters of the structure to be evaluated, and obtaining updated structural performance parameters of the model through inverse normalization calculation according to the artificial neural network proxy model; S11: inputting the structural performance parameters updated by the model into the first finite element model to obtain a second finite element model that can truly reflect the structural state; S12: Calculate a second crack width ω′ according to the second finite element model, and determine the performance state of the bridge reinforced concrete according to the second crack width ω′.

2. The reinforced concrete structure model construction method according to claim 1, characterized in that: Embedding the material constitutive relation and the first crack width calculation formula into the first finite element model includes: Embedding the material constitutive relation into a pre-processing program of the first finite element model as a subroutine of the first finite element model; The first crack width calculation formula is used as a subroutine of the first finite element model and embedded into a post-processing program of the first finite element model.

3. The reinforced concrete structure model construction method according to claim 1, characterized in that: The S7 further includes: setting upper and lower limits of the key material performance parameters, and taking 1% of the upper and lower limits as intervals to generate a data set of the key material performance parameters.

4. The reinforced concrete structure model construction method according to claim 1, characterized in that: The method of using the root mean square error as the loss function to train the artificial neural network specifically includes: The single load condition and the structural response are used as input and output training data respectively, and are brought into the loss function to perform adaptive iterative training on the artificial neural network. When the loss value is reduced to an allowable value, the training is automatically stopped and the artificial neural network proxy model is output.

5. The reinforced concrete structure model construction method according to claim 1, characterized in that: The test output parameters include at least static response data and dynamic response data, the static response data are output parameters of the static test, the dynamic response data are output parameters of the dynamic test, and the load effect of the test output parameters is consistent with the single load condition.

6. The reinforced concrete structure model construction method according to claim 1, characterized in that: The step of judging the performance and structural state of the bridge reinforced concrete according to the second crack width ω′ specifically includes: The second crack width ω′ and the structural crack limit ω limit For comparison: Among them, η ω is the performance structural state parameter of the bridge reinforced concrete, when η ω When η is less than 0.8, the performance and structure of the bridge reinforced concrete are in a safe state. ω When it is between 0.8 and 0.1, the performance and structure state of the bridge reinforced concrete is close to danger. ω When it is greater than 1, the performance and structural status of the bridge reinforced concrete is in a dangerous state.

7. A reinforced concrete structure model building device, characterized in that: include: at least one processor; as well as, 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: Establishing a first finite element model according to geometric parameters of the basic structure of the bridge; The material constitutive relationship of the bridge structure is obtained according to the tensile test of reinforced concrete structure, wherein the formula of the material constitutive relationship is: e t =f t / E c Among them, σ c is the structural stress, ε is the structural strain, ε t is the concrete crack strain, E c is the structural elastic modulus, f t is the compressive strength of concrete; Based on the construction of the cross-section model of the fiber beam-column unit, the first crack width calculation formula is determined, and the first crack width calculation formula is: Where ω is the first crack width, L m is the average crack space length; embedding the material constitutive relation and the first crack width calculation formula into the first finite element model; Inputting a structural load action, and obtaining a structural performance degradation parameter and a structural crack parameter using the first finite element model, wherein the structural load action is an applied force; Determine a single load condition according to the structural type of the bridge, wherein the single load condition includes at least a concentrated force and a uniformly distributed load; According to the first finite element model, the key material performance parameters of the fiber beam-column model are selected, and the key material performance parameters at least include the elastic modulus E of the steel bars in the reinforced concrete. r , elastic model of concrete E c ; Inputting the single load condition and the key material performance parameters into the first finite element model, and obtaining a structural response through simulation calculation of the first finite element model, wherein the structural response includes at least a displacement of the main beam, a stress of the main beam, and a crack width; The root mean square error is used as the loss function to train the artificial neural network to obtain the artificial neural network proxy model. The formula of the loss function is: Among them, PF is the loss function, MSE is the root mean square error, T is the sample size of the training set, and e i is the network error of the i-th data point in the training set, t i is the true value in the training set, α i Automatically generated predictions for artificial neural network proxy models; Acquire the test output parameters of the structure to be evaluated, and obtain the updated structural performance parameters of the model through inverse normalization calculation according to the artificial neural network proxy model; Inputting the structural performance parameters updated by the model into the first finite element model to obtain a second finite element model that can truly reflect the structural state; The second crack width ω′ is calculated according to the second finite element model, and the performance state of the bridge reinforced concrete is determined according to the second crack width ω′.

8. A non-volatile computer storage medium, characterized in that: The non-volatile computer storage medium stores a computer program, and when the non-volatile computer program is executed by a processor, the reinforced concrete structure model construction method according to any one of claims 1 to 6 is implemented.

Images