Real-time bridge stress detection method and system based on big data

Through big data technology and dynamic weighing and counters, vehicle load information is obtained, combined with ridge regression and finite element analysis, the accuracy and reliability problems of traditional bridge stress monitoring methods are solved, and more intuitive stress distribution display and bridge structure are achieved. health assessment improves safety and maintenance efficiency.

CN118641083BActive Publication Date: 2024-11-08JIANGSU QINZHI CONSTR ENG CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411109895.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-08
Estimated Expiration
2044-08-14

AI Technical Summary

Technical Problem

Traditional bridge stress monitoring methods are disturbed by external environmental factors, lack accuracy and reliability, and lack intuitive data display, making it difficult to detect structural problems in a timely manner and maintain them.

Method used

Using real-time bridge stress detection method based on big data, reduce environmental impact through vehicle load and stress correlation models, use dynamic weighing and counters to obtain weight and quantity information, perform feature extraction and ridge regression analysis, combining finite element grid and Hu Ke's law calculates stress and creates a three-dimensional visual interface to show the stress distribution.

Benefits of technology

It improves the accuracy and reliability of bridge stress monitoring, achieves more intuitive data display, discovers structural problems in advance, improves the safety and stability of bridges, and enhances managers' decision-making support capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118641083B_ABST
    Figure CN118641083B_ABST
Patent Text Reader

Abstract

The present invention relates to a real-time bridge stress detection method and system based on big data, and specifically to the field of structural monitoring and safety. The method obtains weight information data and quantity information data of vehicles passing through a bridge within a unit time, realizes real-time monitoring and recording of vehicle load conditions, and pre-processes the obtained weight information data and quantity information data to ensure the accuracy and consistency of vehicle load data. The maximum weight characteristics, average weight characteristics, weight distribution characteristics and flow change characteristics of the weight information data and quantity information data of vehicles passing through the bridge within a unit time are extracted, the optimal regularization parameter is selected through cross-validation, the regression coefficient vector is calculated using the closed-form solution formula of ridge regression, an association matrix is ​​constructed for the influence law of vehicle load data on bridge stress, the bridge stress is calculated through Hooke's law, a three-dimensional visualization interface is created, the vector representation of the stress of each structural component of the bridge is displayed, and the monitoring and maintenance efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of structural monitoring and safety, and more specifically, to a real-time bridge stress detection method and system based on big data. Background Art

[0002] As our country accelerates infrastructure construction, many roads and bridges have been put into operation, and maintenance and management have become crucial. With the development of big data technology, new possibilities have been provided for the operation and maintenance of bridges.

[0003] Traditional stress monitoring methods usually rely on sensor technology, which monitors stress in real time through sensors installed on bridge structures. However, interference from external environmental factors has always been a challenge for traditional sensors. Especially in bridge stress detection, environmental changes such as wind force may affect the accuracy and reliability of sensors, bringing certain difficulties to the monitoring and maintenance of structures.

[0004] Traditional stress monitoring methods are usually digital and lack visual icons, images, and videos to clearly display the data, making it difficult for managers to intuitively understand the data and make corresponding decisions. Summary of the invention

[0005] The present invention aims at the technical problems existing in the prior art and provides a real-time bridge stress detection method and system based on big data. Based on the vehicle load and stress correlation model, the influence of external environmental factors can be reduced, and the accuracy and reliability of the monitoring results can be improved. By studying the relationship between vehicle load and bridge stress, the stress condition of the bridge can be predicted more accurately, which is helpful to discover structural problems in advance and repair them in time, thereby improving the safety and stability of the bridge. The stress distribution of each structural component of the bridge is displayed through a three-dimensional visualization interface, and the bearing capacity and safety status of the bridge structural components are evaluated in combination with the vehicle load data change diagram, so that the monitoring results are more intuitive and operational, and the managers' understanding of the bridge structure status and decision support are improved to solve the problems raised in the above background technology.

[0006] The technical solution of the present invention to solve the above technical problem is as follows: A real-time bridge stress detection method based on big data comprises the following steps:

[0007] S101. Obtaining weight information data and quantity information data of vehicles passing through the bridge per unit time, and preprocessing the obtained weight information data and quantity information data;

[0008] S102. Extract the maximum weight feature, average weight feature and weight distribution feature of the weight information data of vehicles passing through the bridge per unit time, extract the flow change feature of the number information data of vehicles passing through the bridge per unit time, and form a feature vector matrix according to the extraction order to perform distribution matching normalization;

[0009] S103. Select the optimal regularization parameter through cross-validation for the features normalized by distribution matching, adjust the weight matrix and penalty matrix, calculate the regression coefficient vector using the closed-form solution formula of ridge regression, and describe the relationship between the features normalized by distribution matching and the bridge stress data;

[0010] S104. Import the bridge geometry model and discretize it into finite element meshes, construct a correlation matrix based on the influence of vehicle load data on bridge stress, and calculate bridge stress using Hooke's law;

[0011] S105. Create a three-dimensional visualization interface to display the vector representation of the stress of each structural component of the bridge, add support for user interactive operations, draw vehicle load data change diagrams, stress change diagrams of each structural component of the bridge, and evaluate the bearing capacity and safety status of each structural component of the bridge;

[0012] In a preferred embodiment, in S101, a dynamic weighing scale is installed at the bridge entrance to obtain weight information data of vehicles passing through the bridge per unit time in real time, counters are installed at the bridge entrance and exit, the counter at the bridge entrance is used to obtain the number information data of vehicles passing through the bridge entrance per unit time, and the counter at the bridge exit is used to check the number information data of vehicles passing through the bridge entrance and exit per unit time, the weight information data and number information data of vehicles passing through the bridge are marked and integrated into vehicle load data, the dynamic weighing scale and the counter are used as nodes, and a distributed remote management platform with the dynamic weighing scale and the counter as transmission nodes is deployed, and the vehicle load data is received, stored and processed in real time using the wireless network.

[0013] Furthermore, the distributed remote management platform is used to check whether there are null values ​​and missing values ​​in the vehicle load data, whether the value range of the vehicle load data is within the valid range, and whether there are anomalies and duplicate records in the vehicle load data through the constraints of uniqueness and consistency. For different existing situations, the subject is determined and divided into different subject partitions. The corresponding vehicle load data records are deleted through each partition, and the vehicle load data is filled accordingly using the mean filling method.

[0014] In a preferred embodiment, in S102, the maximum weight feature of the weight information data of vehicles passing through the bridge per unit time is extracted to reflect the maximum stress borne by the bridge, the average weight feature of the weight information data of vehicles passing through the bridge per unit time is extracted to reflect the daily stress load of the bridge, the weight distribution feature of the weight information data of vehicles passing through the bridge per unit time is extracted to reflect the change and distribution of the weight information data of vehicles passing through the bridge per unit time, the flow change feature of the number information data of vehicles passing through the bridge per unit time is extracted to reflect the change of vehicle flow per unit time, the maximum weight feature, the average weight feature, the weight distribution feature and the flow change feature are combined into a feature vector matrix in the extraction order, and mapped to the dynamic distribution of the nonlinear transformation for distribution matching normalization, and the specific formula is:

[0015]

[0016] in represents the nth feature normalized by distribution matching, Represents the nth feature in the eigenvector matrix.

[0017] In a preferred embodiment, in S103, the features normalized by distribution matching are combined into a design matrix, the regression coefficient is initialized as a zero vector, a regularization term is added to solve the overfitting problem of the ordinary least squares method, the strength of the regularization term is controlled by a non-negative regularization parameter, a list of candidate non-negative regularization parameters is created by grid search, the features normalized by distribution matching are divided into K folds, the optimal regularization parameter is selected by cross-validation, the weighting matrix and the penalty matrix are adjusted, and the regression coefficient vector is calculated using the closed-form solution formula of ridge regression, and the specific formula is:

[0018]

[0019] in, represents the regression coefficient vector, represents the design matrix, Represents a weighted matrix, which assigns different importance weights to different features that have been normalized by distribution matching. represents the nth feature normalized by distribution matching, represents the regularization parameter of ridge regression, Represents the penalty matrix, which makes some regression coefficients zero vectors. Represents the penalty strength, which is used to balance the overfitting and underfitting of ridge regression. represents the identity matrix, The bridge stress data is represented, and the relationship between the features normalized by distribution matching and the bridge stress data is described by the regression coefficient vector, which helps to understand the influence law on the bridge stress.

[0020] In a preferred embodiment, in S104, the bridge geometry model is imported and the cross-sectional properties of each structural component of the bridge are marked and defined. The bridge geometry model is discretized into finite element grids using finite element software, and the support and constraint conditions of each structural component of the bridge geometry model are defined. The features normalized by distribution matching are combined as part of the vehicle load loading, and the influence of vehicle load data on bridge stress is constructed into an association matrix. The bridge stress is calculated by Hooke's law, and the specific formula is:

[0021]

[0022] in, A vector representation of the stresses in each structural component of the bridge, The correlation matrix that represents the influence of vehicle load data on bridge stress, represents the global inverse stiffness matrix of each structural component of the bridge, represents the load vector represented by the vehicle load data, Represents the material elasticity matrix of each structural component of the bridge.

[0023] In a preferred embodiment, in S105, a three-dimensional visualization interface is created, and the vector representation of the stress of each structural component of the bridge is displayed on the imported bridge geometric model. Support for user interactive operations is added, and the models of each structural component of the bridge can be freely rotated, enlarged and reduced to view the stress distribution at different angles. The vehicle load data and the vector representation of the stress of each structural component of the bridge are marked on the bridge geometric model by labels, and a line graph is used to draw a graph of the change of vehicle load data per unit time, and a curve graph is used to draw a graph of the change of stress of each structural component of the bridge at different time points and different load conditions, and the bearing capacity and safety status of each structural component of the bridge are evaluated, and the relevant staff are informed to take timely repair measures by means of alarm lights.

[0024] In a preferred embodiment, it includes an acquisition processing module, a feature extraction module, a stress association module, a stress detection module and a visual alarm module;

[0025] Collection and processing module: Install a dynamic weighing scale to obtain the weight information data of vehicles passing through the bridge in real time per unit time, use the counter at the bridge entrance to obtain the number information data of vehicles passing through the bridge entrance per unit time, and pre-process the obtained weight information data and number information data;

[0026] Feature extraction module: extracts the maximum weight feature, average weight feature, weight distribution feature and flow change feature of the weight information data and quantity information data of vehicles passing through the bridge per unit time, and forms a feature vector matrix according to the extraction order for distribution matching normalization;

[0027] Stress association module: select the optimal regularization parameter through cross-validation for the features normalized by distribution matching, adjust the weight matrix and penalty matrix, and use the closed-form solution formula of ridge regression to calculate the regression coefficient vector to describe the relationship between the features normalized by distribution matching and the bridge stress data;

[0028] Stress detection module: import the bridge geometry model, divide it into finite element meshes using finite element software, construct a correlation matrix based on the influence of vehicle load data on bridge stress, and calculate bridge stress using Hooke's law;

[0029] Visual alarm module: Create a 3D visualization interface to display the vector representation of stress of each structural component of the bridge, add support for user interactive operations, draw vehicle load data change graphs, stress change graphs of each structural component of the bridge, and evaluate the load-bearing capacity and safety status of each structural component of the bridge;

[0030] The beneficial effects of the present invention are as follows: by installing dynamic weighing scales and counters, the weight and quantity information data of vehicles passing through the bridge in unit time can be obtained and recorded in real time, thereby improving the monitoring efficiency and accuracy of vehicle load conditions; a distributed remote management platform with dynamic weighing scales and counters as transmission nodes is deployed, and the vehicle load data is received, stored and processed in real time by wireless networks, thereby improving the efficiency and real-time performance of data transmission, making the monitoring system more intelligent and convenient; by checking the integrity, scope and consistency of vehicle load data, and adopting uniqueness and consistency constraints, the recognition and processing of data anomalies and duplicate records can be realized, thereby ensuring the accuracy and reliability of vehicle load data; according to different situations, themes are determined and divided into different theme partitions, and the corresponding vehicle load data records are deleted through each partition, which is helpful for more Better organize and manage data, improve data processing efficiency and visualization results, effectively help analyze the weight and number of vehicles passing through the bridge per unit time, provide strong support for the health assessment and load management of bridge structures, establish a relationship model between features and bridge stress data through the ridge regression method, optimize the regression analysis process, further improve the accuracy and generalization ability of the model, and provide strong support for the health monitoring and management of bridge structures. By comprehensively considering the geometric shape, material properties and load conditions of the bridge, more accurate and reliable calculation results are provided for the stress analysis of the structure, providing a scientific basis for engineering design and evaluation work, helping to ensure the safe operation and use of the bridge, creating a three-dimensional visualization interface to achieve intuitive stress distribution display, ensure the safety of the bridge structure, and improve monitoring and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flow chart of the method of the present invention;

[0032] Figure 2 This is a system structure block diagram of the present invention.

[0033] Figure 3 The vector representation of stress of the present invention is displayed on the three-dimensional visualization interface of the bridge geometric model. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0035] In the description of this application, 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. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0036] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0037] Example 1

[0038] This embodiment provides Figure 1 The real-time bridge stress detection method based on big data specifically includes the following steps:

[0039] S101. Obtaining weight information data and quantity information data of vehicles passing through the bridge per unit time, and preprocessing the obtained weight information data and quantity information data;

[0040] S102. Extract the maximum weight feature, average weight feature and weight distribution feature of the weight information data of vehicles passing through the bridge per unit time, extract the flow change feature of the number information data of vehicles passing through the bridge per unit time, and form a feature vector matrix according to the extraction order to perform distribution matching normalization;

[0041] S103. Select the optimal regularization parameter through cross-validation for the features normalized by distribution matching, adjust the weight matrix and penalty matrix, calculate the regression coefficient vector using the closed-form solution formula of ridge regression, and describe the relationship between the features normalized by distribution matching and the bridge stress data;

[0042] S104. Import the bridge geometry model and discretize it into finite element meshes, construct a correlation matrix based on the influence of vehicle load data on bridge stress, and calculate bridge stress using Hooke's law;

[0043] S105. Create a three-dimensional visualization interface to display the vector representation of the stress of each structural component of the bridge, add support for user interactive operations, draw vehicle load data change graphs, stress change graphs of each structural component of the bridge, and evaluate the load-bearing capacity and safety status of each structural component of the bridge.

[0044] Example 2

[0045] This embodiment provides Figure 2 The real-time bridge stress detection system based on big data specifically includes: an acquisition and processing module, a feature extraction module, a stress correlation module, a stress detection module and a visual alarm module;

[0046] Collection and processing module: Install a dynamic weighing scale to obtain the weight information data of vehicles passing through the bridge in real time per unit time, use the counter at the bridge entrance to obtain the number information data of vehicles passing through the bridge entrance per unit time, and pre-process the obtained weight information data and number information data;

[0047] Feature extraction module: extracts the maximum weight feature, average weight feature, weight distribution feature and flow change feature of the weight information data and quantity information data of vehicles passing through the bridge per unit time, and forms a feature vector matrix according to the extraction order for distribution matching normalization;

[0048] Stress association module: select the optimal regularization parameter through cross-validation for the features normalized by distribution matching, adjust the weight matrix and penalty matrix, and use the closed-form solution formula of ridge regression to calculate the regression coefficient vector to describe the relationship between the features normalized by distribution matching and the bridge stress data;

[0049] Stress detection module: import the bridge geometry model, divide it into finite element meshes using finite element software, construct a correlation matrix based on the influence of vehicle load data on bridge stress, and calculate bridge stress using Hooke's law;

[0050] Visual alarm module: Create a 3D visualization interface to display the vector representation of stress of each structural component of the bridge, add support for user interactive operations, draw vehicle load data change graphs, stress change graphs of each structural component of the bridge, and evaluate the load-bearing capacity and safety status of each structural component of the bridge;

[0051] S101. Obtaining weight information data and quantity information data of vehicles passing through the bridge per unit time, and preprocessing the obtained weight information data and quantity information data;

[0052] Furthermore, a dynamic weighing scale is installed at the entrance of the bridge to obtain weight information data of vehicles passing through the bridge per unit time in real time, and counters are installed at the entrance and exit of the bridge. The counter at the entrance of the bridge is used to obtain the number information data of vehicles passing through the entrance of the bridge per unit time, and the counter at the exit of the bridge is used to check the number information data of vehicles passing through the entrance and exit of the bridge per unit time. The weight information data and number information data of vehicles passing through the bridge are marked and integrated into vehicle load data, so as to realize real-time monitoring and recording of vehicle load conditions. The dynamic weighing scale and the counter are used as nodes, and a distributed remote management platform with the dynamic weighing scale and the counter as transmission nodes is deployed. The wireless network is used to receive, store and process vehicle load data in real time, so as to improve the efficiency and real-time performance of vehicle load data transmission.

[0053] Furthermore, the distributed remote management platform is used to check whether there are null values ​​and missing values ​​in the vehicle load data, whether the value range of the vehicle load data is within the valid range, and whether there are abnormalities and duplicate records in the vehicle load data through the constraints of uniqueness and consistency. For different existing situations, the subject is determined and divided into different subject partitions. The corresponding vehicle load data records are deleted through each partition, and the mean filling method is used to fill the vehicle load data accordingly, so as to control the quality of the vehicle load data and ensure the accuracy and consistency of the vehicle load data.

[0054] Furthermore, the uniqueness constraint is used to ensure that a single vehicle load data is unique and not affected by other vehicle load data, and the consistency constraint is used to focus on whether the vehicle load data are consistent with each other in terms of logical relationship, data format and relative timeliness.

[0055] S102. Extract the maximum weight feature, average weight feature and weight distribution feature of the weight information data of vehicles passing through the bridge per unit time, extract the flow change feature of the number information data of vehicles passing through the bridge per unit time, and form a feature vector matrix according to the extraction order to perform distribution matching normalization;

[0056] Furthermore, the maximum weight feature of the weight information data of vehicles passing through the bridge per unit time is extracted to reflect the maximum stress borne by the bridge. According to the basic principles of material mechanics, the stress borne by the bridge is proportional to the weight information data of vehicles passing through the bridge. Therefore, the maximum weight feature per unit time is used to reflect the maximum stress borne by the bridge per unit time. The average weight feature of the weight information data of vehicles passing through the bridge per unit time is extracted to reflect the daily stress load of the bridge. According to the basic principles of material mechanics, the average weight feature per unit time is used to reflect the daily stress load of the bridge. The weight distribution characteristics of the weight information data reflect the changes and distribution of the weight information data of vehicles passing through the bridge per unit time. Among them, the number and weight distribution of vehicles passing through the bridge will be different, revealing the diversity and concentration of vehicle weight per unit time. According to the basic principles of material mechanics, the weight distribution characteristics per unit time are used to reflect the changes and distribution of the weight information data of vehicles passing through the bridge per unit time, and the flow change characteristics of the number of vehicles passing through the bridge per unit time are extracted to reflect the changes in vehicle flow per unit time. The maximum weight characteristics, average weight characteristics, weight distribution characteristics and flow change characteristics are combined into a feature vector matrix in the order of extraction, and mapped to the dynamic distribution of nonlinear transformation for distribution matching normalization. The specific formula is:

[0057]

[0058] in represents the nth feature normalized by distribution matching, Represents the nth feature in the feature vector matrix. Traditional mean normalization is static, but distribution matching normalization can dynamically adjust the distribution of extracted features according to actual data through the dynamic distribution of nonlinear transformation, and better capture the changing relationship and complex relationship between the extracted features.

[0059] S103. Select the optimal regularization parameter through cross-validation for the features normalized by distribution matching, adjust the weight matrix and penalty matrix, calculate the regression coefficient vector using the closed-form solution formula of ridge regression, and describe the relationship between the features normalized by distribution matching and the bridge stress data;

[0060] Furthermore, the features normalized by distribution matching are combined into a design matrix, which can better describe the relationship between features and stress and help understand the influence on bridge stress. The regression coefficient is initialized as a zero vector, and a regularization term is added to solve the overfitting problem of the ordinary least squares method, effectively control the complexity of the model, and improve the generalization ability of the ridge regression model. The strength of the regularization term is controlled by a non-negative regularization parameter, and a list of candidate non-negative regularization parameters is created through grid search. The features normalized by distribution matching are divided into K folds, and the optimal regularization parameter is selected through cross-validation to improve the accuracy and robustness of the ridge regression model, thereby better describing the relationship between features and bridge stress. The weighting matrix and the penalty matrix are adjusted, and the regression coefficient vector is calculated using the closed-form solution formula of ridge regression. The specific formula is:

[0061]

[0062] in, represents the regression coefficient vector, represents the design matrix, whose rows correspond to bridge stresses and whose columns correspond to the features normalized by distribution matching, Represents a weighted matrix, which assigns different importance weights to different features that have been normalized by distribution matching. represents the nth feature normalized by distribution matching, represents the regularization parameter of ridge regression, Represents the penalty matrix, adds penalty terms and makes some regression coefficients zero vectors, Represents the penalty strength, which is used to balance the overfitting and underfitting of ridge regression. represents the identity matrix, The bridge stress data is represented, and the relationship between the features normalized by distribution matching and the bridge stress data is described by the regression coefficient vector, which helps to understand the influence law on the bridge stress.

[0063] S104. Import the bridge geometry model and discretize it into finite element meshes, construct a correlation matrix based on the influence of vehicle load data on bridge stress, and calculate the bridge stress using Hooke's law;

[0064] Furthermore, the bridge geometry model is imported and the cross-sectional properties of each structural component of the bridge are marked and defined. The bridge geometry model is discretized into finite element grids using finite element software, and the support and constraint conditions of each structural component of the bridge geometry model are defined. The influence of material properties and structural boundary conditions combined with vehicle load data on structural stress is considered more comprehensively. The characteristics of the combination after distribution matching normalization are used as part of the vehicle load loading. The influence of vehicle load data on bridge stress is constructed into an association matrix, and the influence of vehicle load data on the stress of the bridge structure is quantitatively described. The bridge stress is calculated by Hooke's law. The specific formula is:

[0065]

[0066] in, A vector representation of the stresses in each structural component of the bridge, The correlation matrix that represents the influence of vehicle load data on bridge stress, represents the global inverse stiffness matrix of each structural component of the bridge, represents the load vector represented by the vehicle load data, Represents the material elasticity matrix of each structural component of the bridge.

[0067] Furthermore, the specific experimental parameters of vehicle load data are shown in Table 1, and the specific experimental parameters of bridge stress are shown in Table 2:

[0068] Table 1

[0069]

[0070] Table 2

[0071]

[0072] S105. Create a three-dimensional visualization interface to display the vector representation of the stress of each structural component of the bridge, add support for user interactive operations, draw vehicle load data change diagrams, stress change diagrams of each structural component of the bridge, and evaluate the bearing capacity and safety status of each structural component of the bridge;

[0073] Create a 3D visualization interface, display the vector representation of the stress of each structural component of the bridge on the imported bridge geometry model, realize intuitive stress distribution display, help users understand the stress situation of the bridge structure, add support for user interactive operations, freely rotate, zoom in and out the model of each structural component of the bridge, view the stress distribution at different angles, mark the vehicle load data and the vector representation of the stress of each structural component of the bridge on the bridge geometry model by labeling, use a line graph to draw a graph of the change of vehicle load data per unit time, use a curve graph to draw a graph of the change of stress of each structural component of the bridge at different time points and different load conditions, and evaluate the bearing capacity and safety status of each structural component of the bridge, inform the relevant staff to take repair measures in time through the alarm light, ensure the safety of the bridge structure, and improve the efficiency of monitoring and maintenance.

[0074] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0075] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0077] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0079] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0080] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A real-time bridge stress detection method based on big data, characterized in that: The specific steps include: S101. Obtaining weight information data and quantity information data of vehicles passing through the bridge per unit time, and preprocessing the obtained weight information data and quantity information data; S102. Extract the maximum weight feature, average weight feature and weight distribution feature of the weight information data of vehicles passing through the bridge per unit time, extract the flow change feature of the number information data of vehicles passing through the bridge per unit time, and form a feature vector matrix according to the extraction order to perform distribution matching normalization; Extract the maximum weight feature of the weight information data of vehicles passing through the bridge per unit time to reflect the maximum stress borne by the bridge; extract the average weight feature of the weight information data of vehicles passing through the bridge per unit time to reflect the daily stress load of the bridge; extract the weight distribution feature of the weight information data of vehicles passing through the bridge per unit time to reflect the change and distribution of the weight information data of vehicles passing through the bridge per unit time; extract the flow change feature of the number information data of vehicles passing through the bridge per unit time to reflect the change of traffic flow per unit time; compose the maximum weight feature, average weight feature, weight distribution feature and flow change feature into a feature vector matrix in the order of extraction, and map them to the dynamic distribution of nonlinear transformation for distribution matching normalization; The specific formula for the distribution matching normalization is: ; in represents the nth feature normalized by distribution matching, Represents the nth feature in the feature vector matrix; S103. Select the optimal regularization parameter through cross-validation for the features normalized by distribution matching, adjust the weight matrix and penalty matrix, calculate the regression coefficient vector using the closed-form solution formula of ridge regression, and describe the relationship between the features normalized by distribution matching and the bridge stress data; The features normalized by distribution matching are combined into a design matrix, the regression coefficient is initialized as a zero vector, a regularization term is added to solve the overfitting problem of the ordinary least squares method, the strength of the regularization term is controlled by a non-negative regularization parameter, a list of candidate non-negative regularization parameters is created by grid search, the optimal regularization parameter is selected by cross-validation, the weight matrix and the penalty matrix are adjusted, and the regression coefficient vector is calculated using the closed-form solution formula of ridge regression, and the relationship between the features normalized by distribution matching and the bridge stress data is described by the regression coefficient vector; The specific formula for calculating the regression coefficient vector is: ; in, represents the regression coefficient vector, represents the design matrix, Represents a weighted matrix, which assigns different importance weights to different features that have been normalized by distribution matching. represents the nth feature normalized by distribution matching, represents the regularization parameter of ridge regression, Represents the penalty matrix, which makes some regression coefficients zero vectors. Represents the penalty strength, which is used to balance the overfitting and underfitting of ridge regression. represents the identity matrix, Represents bridge stress data; S104. Import the bridge geometry model and discretize it into finite element meshes, construct a correlation matrix based on the influence of vehicle load data on bridge stress, and calculate bridge stress using Hooke's law; Import the bridge geometry model and mark and define the cross-sectional properties of each structural component of the bridge. Use finite element software to discretize the bridge geometry model into finite element meshes, define the support and constraint conditions of each structural component of the bridge geometry model, combine the normalized features after distribution matching as part of the vehicle load loading, construct a correlation matrix of the influence of vehicle load data on bridge stress, and calculate the bridge stress through Hooke's law; The specific formula for calculating bridge stress using Hooke's law is: ; in, A vector representation of the stresses in each structural component of the bridge, The correlation matrix that represents the influence of vehicle load data on bridge stress, represents the global inverse stiffness matrix of each structural component of the bridge, represents the load vector represented by the vehicle load data, Represent the material elasticity matrix of each structural component of the bridge; S105. Create a three-dimensional visualization interface to display the vector representation of the stress of each structural component of the bridge, add support for user interactive operations, draw vehicle load data change graphs, stress change graphs of each structural component of the bridge, and evaluate the load-bearing capacity and safety status of each structural component of the bridge.

2. The real-time bridge stress detection method based on big data according to claim 1 is characterized in that: In the S101, a dynamic weighing scale is installed at the bridge entrance to obtain weight information data of vehicles passing through the bridge in unit time in real time, counters are installed at the bridge entrance and exit, the counter at the bridge entrance is used to obtain the number information data of vehicles passing through the bridge entrance in unit time, and the counter at the bridge exit is used to check the number information data of vehicles passing through the bridge entrance and exit in unit time, the weight information data and the number information data of vehicles passing through the bridge are marked and integrated into vehicle load data, and the preprocessing includes using a distributed remote management platform to check whether there are null values ​​and missing values ​​in the vehicle load data, checking whether the value range of the vehicle load data is within a valid range, checking whether there are abnormalities and duplicate records in the vehicle load data through uniqueness and consistency constraints, determining topics for different existing situations and dividing them into different topic partitions, deleting corresponding vehicle load data records through each partition, and using the mean filling method to fill the vehicle load data accordingly.

3. The real-time bridge stress detection method based on big data according to claim 1 is characterized in that: In the S105, a three-dimensional visualization interface is created, and the vector representation of the stress of each structural component of the bridge is displayed on the imported bridge geometric model. Support for user interactive operations is added, and vehicle load data and the vector representation of the stress of each structural component of the bridge are marked on the bridge geometric model by labels. A line graph is used to draw a graph of the change of vehicle load data per unit time, and a curve graph is used to draw a graph of the change of stress of each structural component of the bridge at different time points and under different load conditions.

4. A real-time bridge stress detection system based on big data, using the real-time bridge stress detection method based on big data as described in any one of claims 1 to 3, characterized in that: It includes an acquisition and processing module, a feature extraction module, a stress association module, a stress detection module and a visual alarm module; Collection and processing module: Install a dynamic weighing scale to obtain the weight information data of vehicles passing through the bridge in real time per unit time, use the counter at the bridge entrance to obtain the number information data of vehicles passing through the bridge entrance per unit time, and pre-process the obtained weight information data and number information data; Feature extraction module: extracts the maximum weight feature, average weight feature, weight distribution feature and flow change feature of the weight information data and quantity information data of vehicles passing through the bridge per unit time, and forms a feature vector matrix according to the extraction order for distribution matching normalization; Stress association module: select the optimal regularization parameter through cross-validation for the features normalized by distribution matching, adjust the weight matrix and penalty matrix, and use the closed-form solution formula of ridge regression to calculate the regression coefficient vector to describe the relationship between the features normalized by distribution matching and the bridge stress data; Stress detection module: import the bridge geometry model, divide it into finite element meshes using finite element software, construct a correlation matrix based on the influence of vehicle load data on bridge stress, and calculate bridge stress using Hooke's law; Visual Alarm Module: Create a 3D visualization interface to display the vector representation of stress in each structural component of the bridge, add support for user interactive operations, draw vehicle load data change graphs, stress change graphs of each structural component of the bridge, and evaluate the load-bearing capacity and safety status of each structural component of the bridge.