Bridge bearing capacity degradation degree monitoring method and system based on crack form

Abstract

The invention relates to the technical field of building quality supervision, in particular to a bridge bearing capacity degradation degree monitoring method and system based on crack morphology, and the method comprises the steps: obtaining a bridge image, processing the bridge image into a gray bridge image, carrying out the edge detection of the gray bridge image, and obtaining a bridge edge feature set; performing feature recognition operation based on bridge deformation on the overall form edge features to obtain a bridge deformation score, and performing crack recognition operation on the local crack edge features to obtain a crack recognition result; performing bridge bearing capacity comprehensive calculation on the crack identification result to obtain a primary bridge bearing capacity score, and performing weighted calculation on the primary bridge bearing capacity score according to the bridge deformation score to obtain a bridge bearing capacity score; and obtaining a bearing capacity change sequence of the bridge bearing capacity fractions in a preset time period to construct a bridge bearing capacity change curve of the target bridge. According to the method, the degradation degree of the bridge bearing capacity can be accurately predicted.

Description

Technical Field

[0001] The present invention relates to the technical field of building quality supervision, and in particular to a method and system for monitoring the degradation degree of bridge bearing capacity based on crack morphology. Background Art

[0002] Bridges are an indispensable part of modern transportation infrastructure, carrying a large amount of traffic, cargo transportation, and personnel travel. However, with the increase in the service life of bridges, the increase in traffic volume, the impact of the natural environment, and other external factors, bridge structures may suffer various degrees of damage or deterioration, which may threaten the safety and service life of bridges. Therefore, regular inspection and evaluation of bridges can not only timely discover potential problems of bridges and avoid catastrophic accidents, but also provide a scientific basis for bridge maintenance, reinforcement, and life management.

[0003] Currently, the industry mainly uses drones or handheld scanning equipment to detect cracks in bridges. When cracks exceeding the threshold are found, relevant technicians are arranged to repair them. However, there is a lack of analysis of the degree of degradation of the bridge's bearing capacity, which makes it impossible to predict changes in bridge quality in advance, and the handling of bridge failures is delayed. Summary of the invention

[0004] The present invention provides a method for monitoring the degradation degree of bridge bearing capacity based on crack morphology, the main purpose of which is to accurately predict the degradation degree of bridge bearing capacity and improve bridge safety.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for monitoring the degradation degree of bridge bearing capacity based on crack morphology, comprising: obtaining a bridge image of a target bridge, performing Gaussian filtering on the bridge image to obtain a de-noised bridge image, and graying the de-noised bridge image to obtain a grayscale bridge image, wherein the bridge image includes a bridge visual image and a bridge scanning image; using a pre-constructed Sobel operator to perform an edge detection operation on the grayscale bridge image to obtain a bridge edge feature set, wherein the bridge edge feature set includes overall morphological edge features and local crack edge features; using a pre-constructed bridge bearing capacity prediction model in a pre-trained manner to obtain a bridge edge feature set; A morphological recognition network is used to perform a feature recognition operation based on bridge deformation on the overall morphological edge features to obtain a bridge deformation score, and a crack recognition operation is performed on the local crack edge features to obtain a crack recognition result, wherein the crack recognition result includes crack size and crack distribution, wherein the crack distribution area includes an upper structure, a lower structure and a bridge deck structure; a bearing capacity analysis network pre-constructed in the bridge bearing capacity prediction model is used to perform a comprehensive calculation of the bridge bearing capacity on the crack recognition results to obtain a primary bridge bearing capacity score, and a weighted calculation is performed on the primary bridge bearing capacity score according to the bridge deformation score to obtain a bridge bearing capacity score; a bearing capacity change sequence of the bridge bearing capacity score within a preset time period is obtained, and a bridge bearing capacity change curve of the target bridge is constructed using the bearing capacity change sequence.

[0006] Optionally, the pre-constructed Sobel operator is used to perform an edge detection operation on the grayscale bridge image to obtain a bridge edge feature set, including: using the pre-constructed Sobel operator to perform a convolution operation on the grayscale bridge image in the x- and y-axis directions to obtain a gradient matrix set corresponding to the x- and y-axes; performing a dimensionality reduction operation on the gradient matrix set to obtain a feature sequence set; and performing a binary classification judgment based on edge features on the feature sequence set to obtain a bridge edge feature set.

[0007] Optionally, before using the pre-constructed morphological recognition network in the pre-trained bridge bearing capacity prediction model, the method also includes: obtaining a bridge bearing capacity prediction model including a morphological recognition network and a bearing capacity analysis network; obtaining an initial real bridge sample data set, using a pre-constructed data enhancement algorithm to perform data enhancement on the initial real bridge sample data set to obtain an enhanced real sample data set, and using a pre-constructed bridge physical modeling model to obtain a virtual bridge sample data set; mixing the enhanced real sample data set and the virtual bridge sample data set to obtain a training sample set; according to a pre-constructed K-fold cross-validation algorithm, grouping the training sample set into K training sub-sample sets, and using the K training sub-sample sets to perform model training on the bridge bearing capacity prediction model to obtain K trained bridge bearing capacity prediction models; performing mean calculation on the network model parameters in the K trained bridge bearing capacity prediction models to obtain a trained bridge bearing capacity prediction model.

[0008] Optionally, the using the pre-constructed bearing capacity analysis network in the bridge bearing capacity prediction model to perform comprehensive calculation of the bridge bearing capacity on the crack identification result to obtain a primary bridge bearing capacity score includes: using the pre-constructed bearing capacity analysis network in the bridge bearing capacity prediction model to perform stiffness calculation on the crack identification result to obtain cracking stiffness, wherein the cracking stiffness is expressed as: , where Indicates the cracking stiffness corresponding to the bridge deck where the crack is located. represents the bending stiffness of the normal bridge deck, represents the cracking stiffness of the cracked part, Indicates the cracking bearing capacity of the cracked part, represents the primary bridge bearing capacity fraction; according to the pre-constructed stiffness reduction relationship, the bearing capacity of the cracking stiffness is calculated to obtain the primary bridge bearing capacity fraction, wherein the primary bridge bearing capacity fraction is expressed as: , , where represents the stiffness reduction relation, Indicates The cracking stiffness of the crack part.

[0009] Optionally, before the pre-constructed stiffness reduction relational expression is used, the method further includes: obtaining the crack height, crack width and crack area of ​​each crack according to the crack identification result; calculating the ratio of the crack width and the crack area to obtain the engineering strain, and calculating the ratio of the crack height to the engineering strain to obtain the curvature value; according to the pre-constructed curvature-flexure relationship, using the curvature value to calculate the plastic deflection value, and constructing the stiffness reduction relational expression according to the plastic deflection value, wherein the stiffness reduction relational expression is expressed as: , , where Indicates The curvature value of the crack, Indicates A crack, Indicates A crack, represents the total number of cracks, represents the elastic deflection value, represents the plastic deflection value, express The total deflection value of the cracks.

[0010] Optionally, the overall morphological edge features are subjected to a feature recognition operation based on bridge deformation to obtain a bridge deformation score, including: performing target key point detection on the overall morphological edge features to obtain a key point set, and using the key point set to construct a bridge skeleton structure diagram; using the bridge skeleton structure diagram to perform cosine similarity calculation on a pre-constructed initial bridge structure diagram to obtain a bridge deformation score.

[0011] Optionally, the bearing capacity change sequence of the bridge bearing capacity score within a preset time period is obtained, including: obtaining historical repaired cracks, obtaining the crack size and crack distribution of the historical repaired cracks, and obtaining historical repair information; querying a pre-constructed repair performance table based on the historical repair information to obtain the performance loss percentage of the historical repaired cracks; obtaining the primary bridge bearing capacity score corresponding to the historical repaired cracks to obtain the repaired bearing capacity score, and performing weighted calculation using the performance loss percentage and the repaired bearing capacity score to obtain the repaired loss bearing capacity score; performing difference calculation using the bridge bearing capacity score and the repaired loss bearing capacity score to obtain a corrected bridge bearing capacity score; and constructing a bearing capacity change sequence using the corrected bridge bearing capacity score.

[0012] Optionally, the use of the bearing capacity change sequence to construct the bridge bearing capacity change curve of the target bridge includes: using a pre-constructed database tool to perform an outlier and missing value identification operation on the bearing capacity change sequence to obtain abnormal data location information; obtaining a set of front and rear position data of the abnormal data location information, performing mean calculation on the set of front and rear position data to obtain an intermediate value, and using the intermediate value to perform data filling on the abnormal data location information to obtain an effective bearing capacity change sequence; using a pre-constructed curve fitting algorithm to perform regression calculation on the effective bearing capacity change sequence to obtain the bridge bearing capacity change curve of the target bridge.

[0013] Optionally, after constructing the bridge bearing capacity change curve of the target bridge using the bearing capacity change sequence, the method further includes: predicting a lower limit time point of the bridge bearing capacity based on the bridge bearing capacity change curve and a preset warning threshold; sending the lower limit time point of the bridge bearing capacity to a pre-constructed road administration department database, and obtaining the real time point of the latest bridge failure of the target bridge from the road administration department database; when the real time point is before the lower limit time point of the bridge bearing capacity, storing the real time point of the latest bridge failure to obtain a revised sample set; according to a preset time frequency, using the revised sample set to optimize and train the bridge bearing capacity prediction model to obtain an updated bridge bearing capacity prediction model.

[0014] To achieve the above-mentioned purpose, the present invention also provides a bridge bearing capacity degradation degree monitoring system based on crack morphology, comprising: a bridge image acquisition module, used to acquire a bridge image of a target bridge, perform Gaussian filtering on the bridge image to obtain a de-noised bridge image, and perform grayscale processing on the de-noised bridge image to obtain a grayscale bridge image, wherein the bridge image includes a bridge visual image and a bridge scan image; an edge detection module, used to perform edge detection operations on the grayscale bridge image using a pre-constructed sobel operator to obtain a bridge edge feature set, wherein the bridge edge feature set includes overall morphological edge features and local crack edge features; a bearing capacity analysis module, used to perform feature recognition operations based on bridge deformation on the overall morphological edge features using a pre-constructed morphological recognition network in a pre-trained bridge bearing capacity prediction model operation to obtain a bridge deformation score, and to perform a crack identification operation on the local crack edge features to obtain a crack identification result, wherein the crack identification result includes crack type, crack size and crack distribution, wherein the crack type includes bending cracks and shear cracks, wherein the crack distribution area includes superstructure, substructure and bridge deck structure, and to use the pre-constructed bearing capacity analysis network in the bridge bearing capacity prediction model to perform a comprehensive calculation of the bridge bearing capacity on the crack identification result to obtain a primary bridge bearing capacity score, and to perform a weighted calculation on the primary bridge bearing capacity score according to the bridge deformation score to obtain a bridge bearing capacity score; a bearing capacity monitoring module is used to obtain a bearing capacity change sequence of the bridge bearing capacity score within a preset time period, and to use the bearing capacity change sequence to construct a bridge bearing capacity change curve of the target bridge.

[0015] In order to solve the above problems, the present invention also provides an electronic device, which includes: a memory storing at least one instruction; and a processor executing the instructions stored in the memory to implement the above-mentioned method for monitoring the degree of bridge bearing capacity degradation based on crack morphology.

[0016] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned method for monitoring the degree of bridge bearing capacity degradation based on crack morphology.

[0017] The present invention is to solve the problem described in the background technology. The present invention first obtains a bridge image of the target bridge, wherein the bridge image includes a visual image and a scanned image, and the accuracy of bridge image acquisition can be improved through multi-source data; then a bridge edge feature set is obtained through edge computing, wherein the bridge edge feature set includes overall morphological edge features and local crack edge features, the overall morphological edge features can calculate the bearing capacity from the deformation aspect, and the local crack edge features can calculate the bridge bearing capacity from the accumulation of each crack. In the embodiment of the present invention, a specific calculation is performed through a pre-trained bridge bearing capacity prediction model to obtain a bridge bearing capacity score, and finally the monitoring process of the bridge bearing capacity degradation degree is completed by recording the bearing capacity change sequence. Therefore, the present invention accurately predicts the bridge bearing capacity degradation degree and improves the bridge safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic flow chart of a method for monitoring the degradation degree of bridge bearing capacity based on crack morphology provided by an embodiment of the present invention; Figure 2 A functional module diagram of a bridge bearing capacity degradation degree monitoring system based on crack morphology provided by an embodiment of the present invention; Figure 3 A schematic structural diagram of an electronic device for implementing the method for monitoring the degree of degradation of bridge bearing capacity based on crack morphology provided in one embodiment of the present invention.

[0019] Description of figure markings: 1. electronic device; 10. processor; 11. memory; 12. bus.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0022] The embodiment of the present application provides a method for monitoring the degradation degree of bridge bearing capacity based on crack morphology. The execution subject of the method for monitoring the degradation degree of bridge bearing capacity based on crack morphology includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for monitoring the degradation degree of bridge bearing capacity based on crack morphology can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0023] Reference Figure 1The figure is a flow chart of a method for monitoring the degradation degree of bridge bearing capacity based on crack morphology provided by an embodiment of the present invention. In this embodiment, the method for monitoring the degradation degree of bridge bearing capacity based on crack morphology includes: S1, obtaining a bridge image of a target bridge, performing Gaussian filtering on the bridge image to obtain a de-noised bridge image, and performing grayscale processing on the de-noised bridge image to obtain a grayscale bridge image, wherein the bridge image includes a bridge visual image and a bridge scanning image.

[0024] In the implementation of the present invention, the target bridge is a bridge composed of reinforced concrete, which is a medium-short distance bridge and does not involve auxiliary measures such as cables.

[0025] Specifically, in the embodiment of the present invention, in order to reduce the interference of the environment on the bridge, the bridge image is collected three times in the morning, afternoon and evening, wherein the bridge image includes the bridge visual image and the bridge scanning image. In the embodiment of the present invention, the bridge visual image is obtained by cruising by a drone, and the bridge scanning image is obtained by a professional technician holding a scanning device.

[0026] Furthermore, after obtaining the bridge image, the embodiment of the present invention needs to perform a preprocessing operation on the bridge image to reduce the interference factors and magnitude in the image and improve the accuracy of subsequent image processing.

[0027] Specifically, in the embodiment of the present invention, a noise reduction operation is performed by a Gaussian filter algorithm, and then the image is grayed by a graying method to obtain a gray bridge image. The Gaussian filter algorithm is mainly used to remove noise and details in the image while retaining the edge features of the image. The graying is the process of converting a color image into a gray image, for example, Y = 0.299R + 0.587G + 0.114B, where Y represents gray intensity, and R, G and B represent the values ​​of the red, green and blue color channels, respectively.

[0028] S2. Using a pre-constructed Sobel operator, perform an edge detection operation on the grayscale bridge image to obtain a bridge edge feature set, wherein the bridge edge feature set includes overall morphological edge features and local crack edge features.

[0029] In detail, in an embodiment of the present invention, the pre-constructed Sobel operator is used to perform an edge detection operation on the grayscale bridge image to obtain a bridge edge feature set, including: using the pre-constructed Sobel operator to perform a convolution operation on the x- and y-axis directions of the grayscale bridge image to obtain a gradient matrix set corresponding to the x- and y-axes; performing a dimensionality reduction operation on the gradient matrix set to obtain a feature sequence set; and performing a binary classification judgment based on edge features on the feature sequence set to obtain a bridge edge feature set.

[0030] The sobel operator identifies the edge of an image by calculating the gradient of each pixel in the image. The gradient matrix set refers to a set of convolution matrices with calculated gradients.

[0031] Specifically, in the embodiment of the present invention, the Sobel operator uses two 3×3 convolution kernels to calculate the gradient of the image in the x and y directions respectively. By calculating the gradients in these two directions, the gradient amplitude and direction of each pixel can be obtained, so as to determine whether the feature has edge characteristics such as faults through binary classification, thereby identifying the edge. Among them, in the embodiment of the present invention, average pooling operation and flattening operation are used to reduce the dimension of the feature sequence set, wherein the average pooling operation and flattening operation are feature denoising methods of scenes in neural networks. This solution can also reduce the dimension by other methods such as maximum pooling and principal component analysis.

[0032] Specifically, in an embodiment of the present invention, the bridge edge feature set includes overall morphological edge features and local crack edge features, wherein the overall morphological edge features can evaluate and calculate the bridge bearing capacity from the aspect of overall deformation, while the local crack edge features can calculate the bridge bearing capacity from the accumulation of each crack.

[0033] S3. Utilize the pre-constructed morphological recognition network in the pre-trained bridge bearing capacity prediction model to perform feature recognition operation based on bridge deformation on the overall morphological edge features to obtain a bridge deformation score, and perform crack recognition operation on the local crack edge features to obtain crack recognition results, wherein the crack recognition results include crack size and crack distribution, wherein the crack distribution area includes the superstructure, the substructure and the bridge deck structure.

[0034] The bridge bearing capacity prediction model is a Transformer-based image processing neural network model, which is used to analyze bridge images to obtain the bearing capacity of the bridge. The bridge bearing capacity prediction model includes two parts to be trained: a morphology recognition network and a bearing capacity analysis network.

[0035] In detail, in an embodiment of the present invention, before using the pre-constructed morphological recognition network in the pre-trained bridge bearing capacity prediction model, the method also includes: obtaining a bridge bearing capacity prediction model including a morphological recognition network and a bearing capacity analysis network; obtaining an initial real bridge sample data set, and using a pre-constructed data enhancement algorithm to perform data enhancement on the initial real bridge sample data set to obtain an enhanced real sample data set, and using a pre-constructed bridge physical modeling model to obtain a virtual bridge sample data set; mixing the enhanced real sample data set and the virtual bridge sample data set to obtain a training sample set; according to a pre-constructed K-fold cross-validation algorithm, grouping the training sample set into K training sub-sample sets, and using the K training sub-sample sets to perform model training on the bridge bearing capacity prediction model to obtain K trained bridge bearing capacity prediction models; performing mean calculation on the network model parameters in the K trained bridge bearing capacity prediction models to obtain a trained bridge bearing capacity prediction model.

[0036] In the embodiment of the present invention, the network structure of the bridge bearing capacity prediction model can be trained by a cross entropy loss algorithm and a gradient descent algorithm. However, considering the problem of sample scarcity in the bridge bearing capacity prediction process, the present invention improves the collected initial real bridge sample data set.

[0037] Specifically, in the embodiment of the present invention, the images collected in the initial real bridge sample data set are first enhanced by inverting, mirroring, translating, etc. through a data enhancement algorithm, and some information such as different brightness and contrast is added as noise, thereby obtaining an enhanced real sample data set. Then, the present invention uses finite element analysis (FEA) software (such as ABAQUS, ANSYS, etc.) to simulate the deformation and crack development process of the bridge under different loads to obtain a virtual bridge sample data set.

[0038] The above data set is still insufficient for the model training process. Therefore, in an embodiment of the present invention, the entire data set is evenly divided into K training subsample sets through a K-fold cross-validation algorithm, for example, the K value is 5 or 10, and then for each iteration, a subset is selected from the K subsets as a validation set, and the remaining K-1 subsets are used as training sets. The model is trained on the training set, and then the performance of the model is evaluated on the validation set. This process is repeated K times to obtain K trained bridge bearing capacity prediction models. Finally, the mean of each parameter in the model is calculated by the mean to obtain a trained bridge bearing capacity prediction model.

[0039] Furthermore, in the embodiment of the present invention, the trained bridge bearing capacity prediction model is obtained, and data can be substituted into the model for processing.

[0040] In detail, in an embodiment of the present invention, the feature recognition operation based on bridge deformation is performed on the overall morphological edge features to obtain a bridge deformation score, including: performing target key point detection on the overall morphological edge features to obtain a key point set, and using the key point set to construct a bridge skeleton structure diagram; using the bridge skeleton structure diagram to perform cosine similarity calculation on a pre-constructed initial bridge structure diagram to obtain a bridge deformation score.

[0041] The target key point set in the embodiment of the present invention includes the bridge deck point above each pier, the starting position of the bridge, the bottom and center height of the pier, etc. By building connections between the nearest key points, a bridge skeleton structure diagram can be constructed. Among them, the target key point set is pre-configured by the monitoring personnel, or obtained by identifying significant features of the target bridge. Then, the cosine similarity algorithm is used to calculate the similarity of the bridge skeleton structure diagram to the pre-constructed initial bridge structure diagram, so as to normalize and obtain the bridge deformation score. The higher the similarity, the lower the bridge deformation score. Among them, the cosine similarity algorithm is a measure that evaluates the similarity between two non-zero vectors by calculating the angle between the two vectors.

[0042] In addition, the present invention also uses the bridge bearing capacity prediction model to identify local crack edge features.

[0043] Specifically, in an embodiment of the present invention, the local crack edge features are identified to obtain crack identification results of each crack, such as height, area, width and other information, wherein the crack identification results include crack size and crack distribution, wherein the crack distribution area includes the upper structure, the lower structure and the bridge deck structure.

[0044] S4. Using the pre-constructed bearing capacity analysis network in the bridge bearing capacity prediction model, perform a comprehensive calculation of the bridge bearing capacity on the crack identification results to obtain a primary bridge bearing capacity score, and perform a weighted calculation on the primary bridge bearing capacity score according to the bridge deformation score to obtain a bridge bearing capacity score.

[0045] In detail, in an embodiment of the present invention, the method of using the pre-constructed bearing capacity analysis network in the bridge bearing capacity prediction model to perform comprehensive calculation of the bridge bearing capacity on the crack identification result to obtain a primary bridge bearing capacity score includes: using the pre-constructed bearing capacity analysis network in the bridge bearing capacity prediction model to perform stiffness calculation on the crack identification result to obtain cracking stiffness, wherein the cracking stiffness is expressed as: , where Indicates the cracking stiffness corresponding to the bridge deck where the crack is located. represents the bending stiffness of the normal bridge deck, represents the cracking stiffness of the cracked part, Indicates the cracking bearing capacity of the cracked part, represents the primary bridge bearing capacity fraction; according to the pre-constructed stiffness reduction relationship, the bearing capacity of the cracking stiffness is calculated to obtain the primary bridge bearing capacity fraction, wherein the primary bridge bearing capacity fraction is expressed as: , , where represents the stiffness reduction relation, Indicates The cracking stiffness of the crack part.

[0046] Specifically, in the embodiment of the present invention, the method of identifying and predicting the crack part by a neural network and The stiffness of The stiffness reduction relationship can be used to obtain the primary bridge bearing capacity score.

[0047] Among them, the The stiffness reduction relation needs to be calculated from the information of the specific crack.

[0048] In detail, in an embodiment of the present invention, before the pre-constructed stiffness reduction relational expression is used, the method further includes: obtaining the crack height, crack width and crack area of ​​each crack according to the crack identification result; calculating the ratio of the crack width and the crack area to obtain the engineering strain, and calculating the ratio of the crack height to the engineering strain to obtain the curvature value; according to the pre-constructed curvature-flexure relationship, using the curvature value to calculate the plastic deflection value, and constructing the stiffness reduction relational expression according to the plastic deflection value, wherein the stiffness reduction relational expression is expressed as: , , where Indicates The curvature value of the crack, Indicates A crack, Indicates A crack, represents the total number of cracks, represents the elastic deflection value, represents the plastic deflection value, express The total deflection value of the cracks.

[0049] In the embodiment of the present invention, by integrating the curvature value, it can be obtained The total deflection value of the cracks. Since the bridge uses steel bars in the embodiment of the present invention, only the plastic deflection value can be extracted from the total deflection value. Then, the crack height, area and width collected by the model are substituted into the formula to obtain the primary bridge bearing capacity score.

[0050] In the embodiment of the present invention, in addition to the cracks affecting the bearing capacity of the bridge, the deformation of the bridge structure is also important for the bearing capacity. In the embodiment of the present invention, the bridge bearing capacity score is obtained by weighted calculation of the bridge deformation score, such as 98%, and the primary bridge bearing capacity score.

[0051] S5. Obtain a bearing capacity change sequence of the bridge bearing capacity score within a preset time period, and use the bearing capacity change sequence to construct a bridge bearing capacity change curve of the target bridge.

[0052] In detail, in an embodiment of the present invention, the bearing capacity change sequence of the bridge bearing capacity score within a preset time period is obtained, including: obtaining historical repaired cracks, obtaining the crack size and crack distribution of the historical repaired cracks, and obtaining historical repair information; querying a pre-constructed repair performance table based on the historical repair information to obtain the performance loss percentage of the historical repaired cracks; obtaining the primary bridge bearing capacity score corresponding to the historical repaired cracks to obtain the repaired bearing capacity score, and performing weighted calculation using the performance loss percentage and the repaired bearing capacity score to obtain the repaired loss bearing capacity score; performing difference calculation using the bridge bearing capacity score and the repaired loss bearing capacity score to obtain a corrected bridge bearing capacity score; and constructing a bearing capacity change sequence using the corrected bridge bearing capacity score.

[0053] In the embodiment of the present invention, the bridge image can only monitor the cracks of the bridge that have not been repaired, and it is difficult to observe the cracks that have been repaired in the past. However, the performance of the cracks that have been repaired in the past is not as good as that of the original bridge, which is only about 50% to 60% of the performance of the original bridge. Therefore, the performance loss percentage of the cracks that have been repaired in the past needs to be considered. The performance loss percentage refers to the difference between the bearing capacity performance percentage of the repaired part and the bearing capacity performance percentage before the crack.

[0054] In the embodiment of the present invention, a repair performance table is first obtained, and the repair performance table includes different positions such as bridge decks and bridge piers. The performance of the repairs at each position is different. For example, the performance loss percentage of bridge deck repairs is small, while the performance loss percentage of bridge pier repairs is large. The present invention performs weighted calculation on the primary bridge bearing capacity scores corresponding to the historically repaired cracks and the performance loss percentages of the respective corresponding positions to obtain the repair loss bearing capacity score. Then, the difference calculation is performed based on the bridge bearing capacity score monitored in real time and the repair loss bearing capacity score to obtain the corrected bridge bearing capacity score.

[0055] Then the time sequence is arranged to obtain the bearing capacity change sequence.

[0056] In detail, in an embodiment of the present invention, the use of the bearing capacity change sequence to construct the bridge bearing capacity change curve of the target bridge includes: using a pre-constructed database tool to perform an outlier and missing value identification operation on the bearing capacity change sequence to obtain abnormal data location information; obtaining a front and rear position data set of the abnormal data location information, performing a mean calculation on the front and rear position data set to obtain an intermediate value, and using the intermediate value to perform data filling on the abnormal data location information to obtain an effective bearing capacity change sequence; using a pre-constructed curve fitting algorithm to perform a regression calculation on the effective bearing capacity change sequence to obtain the bridge bearing capacity change curve of the target bridge.

[0057] The database tool has the function of querying data discreteness and missingness, identifying abnormal values ​​in the bearing capacity change sequence through data discreteness, and then filling them through mean calculation. For example, when the data set before and after the abnormal data position information is [34, 35, null value / abnormal value, 36, 35], the middle value 35 of the number can be filled. The abnormal data position information and the middle value can be one or a set.

[0058] After the data processing is completed, a curve fitting algorithm can be used to construct a curve to obtain a bridge bearing capacity change curve, wherein the curve fitting algorithm is a method in statistics and data analysis, which is used to represent the relationship between data points through a curve, and the curve may be composed of polynomials through regression calculation. Among them, regression calculation refers to a method used for statistical analysis, which is mainly used to study the relationship between independent variables and dependent variables. The present invention can change the parameters between each polynomial through regression calculation, thereby making the relationship between bridge bearing capacity and time.

[0059] In the embodiment of the present invention, the bridge degradation degree can be well controlled through the bridge bearing capacity variation curve.

[0060] Furthermore, in another embodiment of the present invention, after constructing the bridge bearing capacity change curve of the target bridge using the bearing capacity change sequence, the method also includes: predicting a lower limit time point of the bridge bearing capacity based on the bridge bearing capacity change curve and a preset warning threshold; sending the lower limit time point of the bridge bearing capacity to a pre-constructed road administration department database, and obtaining the real time point of the latest bridge failure of the target bridge from the road administration department database; when the real time point is before the lower limit time point of the bridge bearing capacity, storing the real time point of the latest bridge failure to obtain a corrected sample set; according to a preset time frequency, using the corrected sample set to optimize and train the bridge bearing capacity prediction model to obtain an updated bridge bearing capacity prediction model.

[0061] In the embodiment of the present invention, an alert threshold can be evaluated according to bridge threat data through expert experience. When the bridge bearing capacity change curve drops to the alert threshold, it needs to be repaired or scrapped. The present invention can obtain the bridge bearing capacity lower limit time point through the bridge bearing capacity change curve. And send it to the pre-built road administration department database, the road administration department database is connected to the system of the corresponding staff, so that the technical staff can arrange the repair work conveniently. When the latest bridge failure occurs before the bridge bearing capacity lower limit time point, it indicates that there is a problem with the bearing capacity prediction. The fault image of the target bridge can be collected and the fault time can be recorded to summarize the corrected sample set, and the model can be optimized using the corrected sample set according to the preset time frequency, so as to ensure the long-term availability of the model.

[0062] The present invention is to solve the problem described in the background technology. The present invention first obtains a bridge image of the target bridge, wherein the bridge image includes a visual image and a scanned image, and the accuracy of bridge image acquisition can be improved through multi-source data; then a bridge edge feature set is obtained through edge computing, wherein the bridge edge feature set includes overall morphological edge features and local crack edge features, the overall morphological edge features can calculate the bearing capacity from the deformation aspect, and the local crack edge features can calculate the bridge bearing capacity from the accumulation of each crack. In the embodiment of the present invention, a specific calculation is performed through a pre-trained bridge bearing capacity prediction model to obtain a bridge bearing capacity score, and finally the monitoring process of the bridge bearing capacity degradation degree is completed by recording the bearing capacity change sequence. Therefore, the present invention accurately predicts the bridge bearing capacity degradation degree and improves the bridge safety.

[0063] like Figure 2 , which is a functional module diagram of a bridge bearing capacity degradation degree monitoring system based on crack morphology provided by an embodiment of the present invention.

[0064] The bridge bearing capacity degradation monitoring system 100 based on crack morphology of the present invention can be installed in an electronic device. According to the functions to be implemented, the bridge bearing capacity degradation monitoring system 100 based on crack morphology can include a bridge image acquisition module 101, an edge detection module 102, a bearing capacity analysis module 103 and a bearing capacity monitoring module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0065] The bridge image acquisition module 101 is used to acquire a bridge image of a target bridge, perform Gaussian filtering on the bridge image to obtain a de-noised bridge image, and grayscale the de-noised bridge image to obtain a grayscale bridge image, wherein the bridge image includes a bridge visual image and a bridge scan image; the edge detection module 102 is used to perform edge detection on the grayscale bridge image using a pre-constructed sobel operator to obtain a bridge edge feature set, wherein the bridge edge feature set includes overall morphological edge features and local crack edge features; the bearing capacity analysis module 103 is used to perform feature recognition operations based on bridge deformation on the overall morphological edge features using a pre-constructed morphological recognition network in a pre-trained bridge bearing capacity prediction model. A bridge deformation score is obtained, and a crack identification operation is performed on the local crack edge features to obtain a crack identification result, wherein the crack identification result includes crack size and crack distribution, wherein the crack distribution area includes the upper structure, the lower structure and the bridge deck structure, and a bearing capacity analysis network pre-constructed in the bridge bearing capacity prediction model is used to perform a comprehensive calculation of the bridge bearing capacity on the crack identification result to obtain a primary bridge bearing capacity score, and a weighted calculation is performed on the primary bridge bearing capacity score according to the bridge deformation score to obtain a bridge bearing capacity score; the bearing capacity monitoring module 104 is used to obtain a bearing capacity change sequence of the bridge bearing capacity score within a preset time period, and use the bearing capacity change sequence to construct a bridge bearing capacity change curve of the target bridge.

[0066] In detail, the modules in the bridge bearing capacity degradation degree monitoring system 100 based on crack morphology in the embodiment of the present invention are used in the same manner as described above. Figure 1 The same technical means as the method for monitoring the degradation degree of bridge bearing capacity based on crack morphology described in the previous section can produce the same technical effects, so they will not be repeated here.

[0067] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing a method for monitoring the degradation degree of bridge bearing capacity based on crack morphology provided by an embodiment of the present invention.

[0068] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a method program for monitoring the degradation degree of bridge bearing capacity based on crack morphology.

[0069] The memory 11 includes at least one type of readable storage medium, including flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the bridge bearing capacity degradation degree monitoring method program based on crack morphology, but also be used to temporarily store data that has been output or is to be output.

[0070] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as a bridge bearing capacity degradation degree monitoring method program based on crack morphology, etc.), and calls data stored in the memory 11, so as to execute various functions of the electronic device 1 and process data.

[0071] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0072] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0073] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0074] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0075] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0076] The program of the method for monitoring the degradation degree of bridge bearing capacity based on crack morphology stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: obtaining a bridge image of the target bridge, performing Gaussian filtering on the bridge image to obtain a de-noised bridge image, and graying the de-noised bridge image to obtain a gray-scale bridge image, wherein the bridge image includes a bridge visual image and a bridge scan image; using a pre-constructed sobel operator to perform edge detection on the gray-scale bridge image to obtain a bridge edge feature set, wherein the bridge edge feature set includes overall morphological edge features and local crack edge features; using a pre-trained The morphological recognition network pre-constructed in the bridge bearing capacity prediction model is used to perform a feature recognition operation based on bridge deformation on the overall morphological edge features to obtain a bridge deformation score, and a crack recognition operation is performed on the local crack edge features to obtain a crack recognition result, wherein the crack recognition result includes crack size and crack distribution, wherein the crack distribution area includes the superstructure, the substructure and the bridge deck structure; using the bearing capacity analysis network pre-constructed in the bridge bearing capacity prediction model, a comprehensive calculation of the bridge bearing capacity is performed on the crack recognition results to obtain a primary bridge bearing capacity score, and a weighted calculation is performed on the primary bridge bearing capacity score according to the bridge deformation score to obtain a bridge bearing capacity score; a bearing capacity change sequence of the bridge bearing capacity score within a preset time period is obtained, and a bridge bearing capacity change curve of the target bridge is constructed using the bearing capacity change sequence.

[0077] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0078] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0079] The present invention also provides a computer-readable storage medium, wherein the computer program is stored in the computer program. When the computer program is executed by a processor of an electronic device, the computer program can achieve: obtaining a bridge image of a target bridge, performing Gaussian filtering on the bridge image to obtain a de-noised bridge image, and graying the de-noised bridge image to obtain a gray-scale bridge image, wherein the bridge image includes a bridge visual image and a bridge scan image; performing edge detection on the gray-scale bridge image using a pre-constructed Sobel operator to obtain a bridge edge feature set, wherein the bridge edge feature set includes overall morphological edge features and local crack edge features; using a pre-trained bridge The morphological recognition network pre-constructed in the bearing capacity prediction model performs a feature recognition operation based on bridge deformation on the overall morphological edge features to obtain a bridge deformation score, and performs a crack recognition operation on the local crack edge features to obtain a crack recognition result, wherein the crack recognition result includes crack size and crack distribution, wherein the crack distribution area includes the superstructure, the substructure and the bridge deck structure; using the bearing capacity analysis network pre-constructed in the bridge bearing capacity prediction model, a comprehensive calculation of the bridge bearing capacity is performed on the crack recognition results to obtain a primary bridge bearing capacity score, and a weighted calculation is performed on the primary bridge bearing capacity score according to the bridge deformation score to obtain a bridge bearing capacity score; obtaining a bearing capacity change sequence of the bridge bearing capacity score within a preset time period, and using the bearing capacity change sequence to construct a bridge bearing capacity change curve of the target bridge.

[0080] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0081] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0083] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for monitoring the degradation degree of bridge bearing capacity based on crack morphology, characterized in that: The method comprises: obtaining a bridge image of a target bridge, performing Gaussian filtering on the bridge image to obtain a de-noised bridge image, and performing grayscale processing on the de-noised bridge image to obtain a grayscale bridge image, wherein the bridge image comprises a bridge visual image and a bridge scanning image; performing edge detection operation on the grayscale bridge image using a pre-constructed sobel operator to obtain a bridge edge feature set, wherein the bridge edge feature set comprises an overall morphological edge feature and a local crack edge feature; performing a morphological recognition network pre-constructed in a pre-trained bridge bearing capacity prediction model to detect the overall morphological edge feature. The invention relates to a method for predicting the bridge bearing capacity of a target bridge, wherein the crack edge features of the target bridge are subjected to a crack recognition operation based on the deformation of the bridge to obtain a bridge deformation score, and a crack recognition operation is performed on the local crack edge features to obtain a crack recognition result, wherein the crack recognition result includes crack size and crack distribution, wherein the crack distribution area includes superstructure, substructure and bridge deck structure; a bearing capacity analysis network pre-constructed in the bridge bearing capacity prediction model is used to perform a comprehensive calculation of the bridge bearing capacity of the crack recognition result to obtain a primary bridge bearing capacity score, and a weighted calculation is performed on the primary bridge bearing capacity score according to the bridge deformation score to obtain a bridge bearing capacity score; a bearing capacity change sequence of the bridge bearing capacity score within a preset time period is obtained, and a bridge bearing capacity change curve of the target bridge is constructed using the bearing capacity change sequence.

2. The method for monitoring the degradation degree of bridge bearing capacity based on crack morphology according to claim 1, characterized in that: The method uses a pre-constructed Sobel operator to perform an edge detection operation on the grayscale bridge image to obtain a bridge edge feature set, including: using a pre-constructed Sobel operator to perform a convolution operation on the x- and y-axis directions of the grayscale bridge image to obtain a gradient matrix set corresponding to the x- and y-axis; performing a dimensionality reduction operation on the gradient matrix set to obtain a feature sequence set; and performing a binary classification judgment based on edge features on the feature sequence set to obtain a bridge edge feature set.

3. The method for monitoring the degradation degree of bridge bearing capacity based on crack morphology according to claim 2, characterized in that: Before using the pre-constructed morphological recognition network in the pre-trained bridge bearing capacity prediction model, the method also includes: obtaining a bridge bearing capacity prediction model including a morphological recognition network and a bearing capacity analysis network; obtaining an initial real bridge sample data set, using a pre-constructed data enhancement algorithm to perform data enhancement on the initial real bridge sample data set to obtain an enhanced real sample data set, and using a pre-constructed bridge physical modeling model to obtain a virtual bridge sample data set; mixing the enhanced real sample data set and the virtual bridge sample data set to obtain a training sample set; according to a pre-constructed K-fold cross-validation algorithm, grouping the training sample set into K training sub-sample sets, and using the K training sub-sample sets to perform model training on the bridge bearing capacity prediction model to obtain K trained bridge bearing capacity prediction models; performing mean calculation on the network model parameters in the K trained bridge bearing capacity prediction models to obtain a trained bridge bearing capacity prediction model.

4. The method for monitoring the degradation degree of bridge bearing capacity based on crack morphology according to claim 3 is characterized in that: The method of using the pre-constructed bearing capacity analysis network in the bridge bearing capacity prediction model to perform comprehensive calculation of the bridge bearing capacity on the crack identification result to obtain a primary bridge bearing capacity score includes: using the pre-constructed bearing capacity analysis network in the bridge bearing capacity prediction model to perform stiffness calculation on the crack identification result to obtain cracking stiffness, wherein the cracking stiffness is expressed as: , where Indicates the cracking stiffness corresponding to the bridge deck where the crack is located. represents the bending stiffness of the normal bridge deck, represents the cracking stiffness of the cracked part, Indicates the cracking bearing capacity of the cracked part, represents the primary bridge bearing capacity fraction; according to the pre-constructed stiffness reduction relationship, the bearing capacity of the cracking stiffness is calculated to obtain the primary bridge bearing capacity fraction, wherein the primary bridge bearing capacity fraction is expressed as: , , where represents the stiffness reduction relation, Indicates The cracking stiffness of the crack part.

5. The method for monitoring the degradation degree of bridge bearing capacity based on crack morphology according to claim 4, characterized in that: Before the pre-constructed stiffness reduction relational expression is used, the method further includes: obtaining the crack height, crack width and crack area of ​​each crack according to the crack identification result; calculating the ratio of the crack width and the crack area to obtain the engineering strain, and calculating the ratio of the crack height to the engineering strain to obtain the curvature value; according to the pre-constructed curvature-flexure relationship, using the curvature value to calculate the plastic deflection value, and constructing the stiffness reduction relational expression according to the plastic deflection value, wherein the stiffness reduction relational expression is expressed as: , , where Indicates The curvature value of the crack, Indicates A crack, Indicates A crack, represents the total number of cracks, represents the elastic deflection value, represents the plastic deflection value, express The total deflection value of the cracks.

6. The method for monitoring the degradation degree of bridge bearing capacity based on crack morphology according to claim 5, characterized in that: The step of performing a feature recognition operation based on bridge deformation on the overall morphological edge features to obtain a bridge deformation score includes: performing target key point detection on the overall morphological edge features to obtain a key point set, and using the key point set to construct a bridge skeleton structure diagram; and using the bridge skeleton structure diagram to perform cosine similarity calculation on a pre-constructed initial bridge structure diagram to obtain a bridge deformation score.

7. The method for monitoring the degradation degree of bridge bearing capacity based on crack morphology according to claim 6, characterized in that: The method for obtaining a bearing capacity change sequence of the bridge bearing capacity score within a preset time period includes: obtaining historical repaired cracks, obtaining the crack size and crack distribution of the historical repaired cracks, and obtaining historical repair information; querying a pre-constructed repair performance table based on the historical repair information to obtain the performance loss percentage of the historical repaired cracks; obtaining the primary bridge bearing capacity score corresponding to the historical repaired cracks to obtain the repaired bearing capacity score, and performing weighted calculation using the performance loss percentage and the repaired bearing capacity score to obtain the repaired loss bearing capacity score; performing difference calculation using the bridge bearing capacity score and the repaired loss bearing capacity score to obtain a revised bridge bearing capacity score; and constructing a bearing capacity change sequence using the revised bridge bearing capacity score.

8. The method for monitoring the degradation degree of bridge bearing capacity based on crack morphology according to claim 7, characterized in that: The method of constructing the bridge bearing capacity change curve of the target bridge by using the bearing capacity change sequence includes: using a pre-constructed database tool to perform an outlier and missing value identification operation on the bearing capacity change sequence to obtain abnormal data location information; obtaining a front and rear position data set of the abnormal data location information, performing mean calculation on the front and rear position data set to obtain an intermediate value, and using the intermediate value to fill in the abnormal data location information to obtain an effective bearing capacity change sequence; using a pre-constructed curve fitting algorithm to perform a regression calculation on the effective bearing capacity change sequence to obtain the bridge bearing capacity change curve of the target bridge.

9. The method for monitoring the degradation degree of bridge bearing capacity based on crack morphology according to claim 8, characterized in that: After constructing the bridge bearing capacity change curve of the target bridge using the bearing capacity change sequence, the method further includes: predicting a lower limit time point of the bridge bearing capacity according to the bridge bearing capacity change curve and a preset warning threshold; sending the lower limit time point of the bridge bearing capacity to a pre-constructed road administration department database, and obtaining the real time point of the latest bridge failure of the target bridge from the road administration department database; when the real time point is before the lower limit time point of the bridge bearing capacity, storing the real time point of the latest bridge failure to obtain a revised sample set; according to a preset time frequency, using the revised sample set to optimize and train the bridge bearing capacity prediction model to obtain an updated bridge bearing capacity prediction model.

10. A bridge bearing capacity degradation monitoring system based on crack morphology, characterized in that: The system includes: a bridge image acquisition module, which is used to acquire a bridge image of a target bridge, perform Gaussian filtering on the bridge image to obtain a de-noised bridge image, and grayscale the de-noised bridge image to obtain a grayscale bridge image, wherein the bridge image includes a bridge visual image and a bridge scan image; an edge detection module, which is used to perform edge detection operations on the grayscale bridge image using a pre-constructed sobel operator to obtain a bridge edge feature set, wherein the bridge edge feature set includes overall morphological edge features and local crack edge features; a bearing capacity analysis module, which is used to perform feature recognition operations based on bridge deformation on the overall morphological edge features using a pre-constructed morphological recognition network in a pre-trained bridge bearing capacity prediction model to obtain to the bridge deformation score, and perform crack recognition operation on the local crack edge features to obtain crack recognition results, wherein the crack recognition results include crack size and crack distribution, wherein the crack distribution area includes superstructure, substructure and bridge deck structure, and use the pre-constructed bearing capacity analysis network in the bridge bearing capacity prediction model to perform comprehensive calculation of bridge bearing capacity on the crack recognition results to obtain a primary bridge bearing capacity score, and perform weighted calculation on the primary bridge bearing capacity score according to the bridge deformation score to obtain a bridge bearing capacity score; a bearing capacity monitoring module is used to obtain a bearing capacity change sequence of the bridge bearing capacity score within a preset time period, and use the bearing capacity change sequence to construct a bridge bearing capacity change curve of the target bridge.

Images