A method, apparatus, equipment and storage medium for evaluating the load-bearing capacity of bridge groups.
By using the analytic hierarchy process (AHP) and clustering algorithms, the bridge group is divided into sub-bridge groups and clusters, and the load-bearing capacity evaluation coefficients of characteristic bridges are determined. This solves the problem that existing technologies cannot evaluate all bridges in a region, and achieves full coverage evaluation of the bridge group.
Patent Information
- Application Number
- CN202311630350.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-30
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-11-30
AI Technical Summary
Existing technologies cannot assess the load-bearing capacity of all bridges in a region. Typically, only bridges of high importance can be selected for assessment using the analytic hierarchy process, and the status of unmonitored bridges cannot be detected.
The analytic hierarchy process (AHP) is used to divide the bridge group into sub-bridge groups, and then the sub-bridge groups are further divided into bridge clusters using a clustering algorithm. The load-bearing capacity evaluation coefficients of the characteristic bridges are determined and assigned to other bridges within the bridge clusters, thereby achieving the evaluation of all bridges.
It enables the assessment of the load-bearing capacity of all bridges in the region, avoids cost constraints, and can predict the condition of unmonitored bridges and conduct an overall condition assessment of the bridge group.
Smart Images

Figure CN117574773B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of bridge group performance evaluation, and in particular to a method, apparatus, equipment, and computer-readable storage medium for evaluating the load-bearing capacity of bridge groups. Background Technology
[0002] Bridge health monitoring involves monitoring and assessing the structural condition of bridges to issue early warning signals when the project experiences severe abnormalities in weather, traffic conditions, or operational status, providing a basis and guidance for bridge maintenance, repair, and management decisions. Due to cost limitations, current technologies cannot assess the load-bearing capacity of all bridges in a bridge group within a region. Typically, the analytic hierarchy process (AHP) is used to select high-importance bridges for load-bearing capacity assessment. However, this method, which focuses on assessing the load-bearing capacity of high-importance bridges, fails to detect the load-bearing capacity of unmonitored bridges within the group, thus preventing a comprehensive assessment of the load-bearing capacity of the entire bridge group within the region. Summary of the Invention
[0003] The purpose of this invention is to provide a method, apparatus, device, and computer-readable storage medium for evaluating the load-bearing capacity of bridge groups. This method is applied to the field of bridge group performance evaluation. The method uses the analytic hierarchy process (AHP) to divide a bridge group in a region into multiple sub-bridge groups according to their importance. The bridges in the sub-bridge groups are then clustered to obtain multiple bridge clusters. By evaluating the load-bearing capacity of characteristic bridges within the bridge clusters, the load-bearing capacity of all bridges in the region can be evaluated.
[0004] To address the aforementioned technical problems, this invention provides a method for evaluating the load-bearing capacity of bridge groups, comprising:
[0005] The target area is divided into multiple sub-bridge groups based on the analytic hierarchy process.
[0006] Based on a clustering algorithm, the bridges in each of the sub-bridge groups are divided into multiple bridge clusters;
[0007] Determine the load-bearing capacity evaluation coefficients for the characteristic bridges within the bridge cluster;
[0008] The load-bearing capacity evaluation coefficient of the featured bridge is assigned to the other bridges in the corresponding bridge cluster;
[0009] The load-bearing capacity of all bridges in the bridge group is evaluated based on the load-bearing capacity evaluation coefficient.
[0010] Optionally, the method of dividing the bridge group within the target area into multiple sub-bridge groups based on the analytic hierarchy process includes:
[0011] A bridge evaluation system is constructed based on technical condition, load level, service life, total crack length, bridge location, and span length.
[0012] Based on the analytic hierarchy process (AHP), the bridge scores of all bridges in the bridge group within the target area are given under the bridge evaluation system.
[0013] Based on the bridge rating, all bridges in the bridge group are classified into multiple sub-bridge groups.
[0014] Optionally, the clustering algorithm is used to divide the bridges in each sub-bridge group into multiple bridge clusters, including:
[0015] The bridge clustering attributes are determined based on the service life, the span length, and the total length of the cracks.
[0016] Based on the bridge clustering attributes, a clustering algorithm is used to divide the bridges in each sub-bridge group into multiple bridge clusters.
[0017] Optionally, determining the load-bearing capacity evaluation coefficients of the characteristic bridges within the bridge cluster includes:
[0018] Construct a database of theoretical values for structural and material performance parameters of different types of bridges under different span lengths;
[0019] Based on the theoretical value database of various types of bridges, corresponding material performance parameter prediction models are trained.
[0020] Obtain the target structural performance parameters and target span length of the characteristic bridges within the bridge cluster;
[0021] The target structural performance parameters and the target span length are input into the corresponding material performance parameter prediction model to obtain the target material performance parameters of the characteristic bridge;
[0022] The load-bearing capacity evaluation coefficient is calculated based on the target material performance parameters.
[0023] Optionally, the structural performance parameters are any combination of deflection, strain, and crack width, and the material performance parameters are any combination of the main beam's elastic modulus, the main beam's mass density, and the prestressing tendon material strength.
[0024] Optional, also includes:
[0025] The future load-bearing performance evaluation coefficients are obtained by fitting and predicting based on the aforementioned load-bearing performance evaluation coefficients;
[0026] The future load-bearing capacity of the bridge is assessed based on the aforementioned future load-bearing capacity evaluation coefficients.
[0027] Optional, also includes:
[0028] Obtain the average maintenance cost of all bridges in the bridge group and the future load-bearing capacity evaluation coefficient of each bridge at a preset future time after maintenance is completed;
[0029] A safety function is constructed based on the future load-bearing capacity evaluation coefficients, and a cost function is constructed based on the average maintenance cost.
[0030] Bridges to be maintained are selected from the bridge group based on the aforementioned safety function and cost function as constraints.
[0031] To solve the above-mentioned technical problems, the present invention provides a bridge group load-bearing capacity evaluation device, comprising:
[0032] The first module is used to divide the bridge group within the target area into multiple sub-bridge groups based on the analytic hierarchy process.
[0033] The second module is used to divide the bridges in each sub-bridge group into multiple bridge clusters based on a clustering algorithm.
[0034] The third module is used to determine the load-bearing capacity evaluation coefficient of the characteristic bridges within the bridge cluster;
[0035] The fourth module is used to assign the load-bearing performance evaluation coefficient of the characteristic bridge to the other bridges in the corresponding bridge cluster;
[0036] The fifth module is used to evaluate the load-bearing capacity of all bridges in the bridge group based on the load-bearing capacity evaluation coefficient.
[0037] To solve the above-mentioned technical problems, the present invention provides a bridge group load-bearing capacity assessment device, comprising:
[0038] Memory, used to store computer programs;
[0039] A processor, used to implement any of the bridge group load-bearing performance evaluation methods when executing the computer program.
[0040] To address the aforementioned technical problems, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement any of the bridge group load-bearing performance evaluation methods described above.
[0041] As can be seen, the method of this invention divides the bridge group within the target area into multiple sub-bridge groups based on the analytic hierarchy process (AHP); it then divides the bridges in each sub-bridge group into multiple bridge clusters based on a clustering algorithm; it determines the load-bearing capacity evaluation coefficient of characteristic bridges within each bridge cluster; it assigns the load-bearing capacity evaluation coefficient of the characteristic bridges to the remaining bridges within the corresponding bridge cluster; and it evaluates the load-bearing capacity of all bridges within the bridge cluster based on the load-bearing capacity evaluation coefficient. By evaluating the load-bearing capacity of characteristic bridges within the clustered bridge groups, it achieves load-bearing capacity evaluation of all bridges within the area, avoiding the problem that cost limitations prevent the evaluation of the load-bearing capacity of all bridges in a bridge group within the area. Attached Figure Description
[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0043] Figure 1 A flowchart illustrating a method for evaluating the load-bearing capacity of a bridge group, provided in an embodiment of the present invention;
[0044] Figure 2 This is a structural block diagram of a bridge group load-bearing performance evaluation device provided in an embodiment of the present invention. Detailed Implementation
[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0046] The following combination Figure 1 , Figure 1 A flowchart of a method for evaluating the load-bearing capacity of a bridge group provided in an embodiment of the present invention, the method may include:
[0047] S101: Based on the analytic hierarchy process, the bridge group within the target area is divided into multiple sub-bridge groups.
[0048] When there are many bridges in the target area, data collection for each bridge is time-consuming and costly. Currently, the most important bridges in the entire road network are selected by using the analytic hierarchy process or genetic algorithm. The load-bearing capacity of these bridges is then assessed. However, this method cannot perceive or predict the load-bearing capacity of unmonitored bridges, and therefore cannot link the monitoring of individual bridges with the overall state of the bridge group under the conditions of the entire road network.
[0049] In this embodiment, the bridge group in the target area can be divided into multiple sub-bridge groups based on the analytic hierarchy process. The bridge group includes all the bridges in the target area. Since the urban traffic network is often composed of many small and medium-span bridges, the bridge group in this embodiment can also be all the small and medium-span bridges in the target area.
[0050] This embodiment does not limit the specific method of dividing the bridge group into sub-bridge groups using the analytic hierarchy process (AHP). Generally, it is possible to pre-compile inspection reports, maintenance reports, design documents, load test data, traffic information, and environmental information of the bridge group within the target area to generate a bridge group database. Further, a bridge evaluation system is constructed based on the bridge database. In this embodiment, the bridge evaluation system may include the bridge's technical condition, load rating, service life, total crack length, bridge location, and span length.
[0051] Under the bridge evaluation system, a judgment matrix is constructed based on the analytic hierarchy process (AHP), weight vectors are calculated, and consistency checks are performed to obtain the bridge scores for all bridges in the target area. Based on the bridge scores, the bridge groups are classified into multiple sub-bridge groups. This embodiment does not limit the specific classification method. Generally, the highest bridge score can be set as A, the lowest bridge score as B, and the bridges in the segment A-(AB) / 4 to A can be identified as particularly important bridges, the bridges in the segment A-2(AB) / 3 to A-(AB) / 4 as important bridges, and the remaining bridges as general bridges, thus obtaining three sub-bridge groups.
[0052] S102: Based on the clustering algorithm, the bridges in each sub-bridge group are divided into multiple bridge clusters.
[0053] This embodiment can divide the bridges in each sub-bridge group into multiple bridge clusters based on a clustering algorithm. Since bridges with similar service lives and structural parameters often exhibit the same performance degradation trend, this embodiment does not limit the specific clustering method. Generally, the bridge clustering attributes of the target bridges can be determined based on their service life, span length, and total crack length. Based on these attributes, the K-means clustering method is used to divide the bridges in each sub-bridge group into multiple bridge clusters. The K-means clustering method is a clustering algorithm based on Euclidean distance, where the bridges in each cluster are those with the most similar attributes.
[0054] S103: Determine the load-bearing capacity evaluation coefficients for characteristic bridges within a bridge cluster.
[0055] S104: Assign the load-bearing performance evaluation coefficient of the characteristic bridge to the other bridges in the corresponding bridge cluster.
[0056] After multiple iterations of the clustering algorithm, a characteristic bridge can be extracted from each bridge cluster. The characteristic bridge is the most representative bridge in the bridge cluster. In this embodiment, the load-bearing performance evaluation coefficient of the characteristic bridge in the bridge cluster can be determined. The load-bearing performance evaluation coefficient of the characteristic bridge is assigned to the other bridges in the corresponding bridge cluster. Thus, in this embodiment, all bridges in the bridge group have the corresponding load-bearing performance evaluation coefficient.
[0057] The load-bearing capacity evaluation coefficient in this embodiment is a numerical value used to characterize the load-bearing capacity of the bridge. The load-bearing capacity of the bridge in this embodiment can be characterized by the degree of degradation of the bridge's material properties. That is, this embodiment can calculate the loss coefficient based on the target material performance parameters and the initial material performance parameters of the characteristic bridge, and average the loss coefficients of various types of target material performance parameters to obtain the load-bearing capacity evaluation coefficient. The calculation method is as follows:
[0058]
[0059] In the formula, λ is the load-bearing capacity evaluation coefficient, n is the number of types of target material performance parameters, and α i Let β be the target material performance parameter of the i-th type. i These are the initial material performance parameters for the i-th type. This embodiment does not limit the specific method for obtaining the initial material performance parameters; generally, bridges have parameter records after construction.
[0060] This embodiment does not limit the method of obtaining the target material performance parameters of the characteristic bridge. Generally, the material performance parameters can be predicted based on the structural performance parameters by training a neural network model.
[0061] A theoretical database of structural and material performance parameters for different types of bridges under different span lengths is constructed. Based on the theoretical database of each type of bridge, a corresponding material performance parameter prediction model is trained. The target structural performance parameters and target span lengths of characteristic bridges within the bridge cluster are obtained. The target structural performance parameters and target span lengths are input into the corresponding material performance parameter prediction model to obtain the target material performance parameters of the characteristic bridges. The load-bearing capacity evaluation coefficient is calculated based on the target material performance parameters.
[0062] Firstly, since there are many types of bridges, such as hollow slab beam bridges, solid slab beam bridges, T-beam bridges, small box girder bridges, truss arch bridges, rigid frame arch bridges and tied arch bridges, the correspondence between structural performance parameters and material performance parameters of different types of bridges at different span lengths may not be the same. In this embodiment, a theoretical value database of structural performance parameters and material performance parameters of different types of bridges at different span lengths can be constructed.
[0063] This embodiment does not limit the construction method of the theoretical value database. The corresponding material performance parameters can be directly calculated based on the structural performance parameters. Alternatively, the bridge can be modeled using finite element software to obtain a theoretical value database of structural performance parameters and material performance parameters for various types of bridges under different span lengths.
[0064] This embodiment does not limit the specific types of structural performance parameters. Since most highway bridges in my country are small- to medium-span bridges, but currently lack scientific monitoring indicators for these bridges, this embodiment can construct a defect database including a defect type database, a defect location database, and a defect cause database. Statistical analysis of this database can determine the locations where defects are prone to occur for different bridge types, as well as the types of defects that most endanger the bridge's load-bearing capacity. Furthermore, on-site inspections of the bridge can be conducted, and an on-site inspection report can be generated. Based on the defect database and the on-site inspection report, it can be determined that when the bridge type is a small- to medium-span bridge, its structural performance parameters can be any combination of deflection, strain, and crack width. This embodiment also does not limit the specific types of material performance parameters; generally, any combination of elastic modulus, mass density, and prestressing tendon material strength is acceptable.
[0065] This embodiment constructs a dataset based on theoretical values for various types of bridges, using material performance parameters as labels for span length and structural performance parameters. A corresponding material performance parameter prediction model is trained using this dataset; that is, each type of bridge has its own corresponding material performance parameter prediction model. This embodiment does not limit the type of model or the training method. The material performance parameter prediction model trained in this embodiment is reusable; it can be retrained to obtain a new model when the dataset is updated.
[0066] By inputting the collected target structural performance parameters and target span length of the characteristic bridge into the corresponding bridge type's material performance parameter prediction model, the target material performance parameters of the characteristic bridge can be obtained. The load-bearing capacity evaluation coefficient of the characteristic bridge can then be calculated using the target material performance parameters.
[0067] S105: Evaluate the load-bearing capacity of all bridges in the bridge group based on the load-bearing capacity evaluation coefficient.
[0068] In this embodiment, the load-bearing performance of all bridges in a bridge group can be evaluated based on the load-bearing performance evaluation coefficient. The characteristic bridge is the most representative bridge in the bridge cluster. The bridge group in the target area is eventually divided into multiple bridge clusters. The load-bearing performance evaluation coefficient of the characteristic bridge can be assigned to the other bridges in the corresponding bridge cluster. Then, all bridges in the bridge group have a load-bearing performance evaluation coefficient. The load-bearing performance of all bridges in the bridge group is evaluated based on the load-bearing performance evaluation coefficient.
[0069] Bridge degradation is generally manifested as a decline in load-bearing capacity. Degradation prediction is essentially the prediction of a bridge's load-bearing capacity, which is fundamentally the structure's ability to resist external loads and prevent the bridge from collapsing. A significant portion of the reduction in structural resistance is due to the degradation of material strength. In this embodiment, the evaluation coefficients calculated characterize the load-bearing capacity in the form of the degree of material strength reduction, thereby assessing the bridge's load-bearing capacity based on the degree of bridge degradation.
[0070] Furthermore, this embodiment can also predict the future load-bearing capacity of a bridge based on load-bearing capacity evaluation coefficients. This embodiment does not limit the specific prediction method; generally, the future load-bearing capacity evaluation coefficients of the bridge can be obtained through fitting prediction based on the load-bearing capacity evaluation coefficients, and the future load-bearing capacity of the bridge can be evaluated based on these coefficients. This embodiment can store the calculated load-bearing capacity evaluation coefficients. When a certain number are stored, an LSTM (Long Short Term Memory) neural network model can be trained using the load-bearing capacity evaluation coefficient dataset. By fitting and predicting using the trained LSTM neural network model, the future load-bearing capacity evaluation coefficients for future moments can be obtained, thereby evaluating the future load-bearing capacity of the bridge.
[0071] Furthermore, in this embodiment, maintenance decision analysis can be performed on the bridge group within the target area to identify bridges that require management and maintenance. This embodiment can obtain the future load-bearing capacity evaluation coefficient of the bridges within the bridge group at a preset future time after maintenance is completed. This embodiment does not limit the value of the preset future time; it can generally be five years later.
[0072] This embodiment can construct a safety function based on the future load-bearing capacity assessment coefficients of bridges within a bridge group. This embodiment does not limit the specific form of the safety function, but it can generally be expressed as follows:
[0073]
[0074] In the formula, S is the safety function, m is the number of bridges to be maintained, and λ(t) is the future load-bearing capacity evaluation coefficient at a future time t after the bridge maintenance is completed. In this embodiment, after the bridge maintenance is completed, its load-bearing capacity evaluation coefficient can be set to 0.9. Substituting this value into the degradation curve obtained by fitting the LSTM neural network model, the future load-bearing capacity evaluation coefficient at a preset future time t after the bridge maintenance is completed can be obtained.
[0075] Furthermore, this embodiment can construct a cost function based on the average maintenance cost. This embodiment is not limited to a specific construction method, but it can generally be as follows:
[0076] C = mC a ;
[0077] In the formula, C is the cost function, C a Let m be the average maintenance cost of the bridge, and m be the number of bridges requiring maintenance.
[0078] This embodiment does not limit the specific method for determining the number of bridges to be maintained. Generally, a genetic algorithm can be used to select bridges to be maintained from the bridge group under constraints of a safety function and a cost function. Based on the genetic algorithm, the population is encoded and initialized. If there are N bridges in the target area requiring maintenance decision analysis, then chromosome x is defined as an N-dimensional binary vector, and each component x... i (i = 1, ..., N) represents whether to select the i-th bridge for maintenance. For example, (1, 0, ..., 0) means only the bridge with sequence number 1 is selected for maintenance. Generally, the population size can be set to 2000 individuals and the number of generations to 200. The solution m maximizes the safety function value and minimizes the cost function value. If the constraints are met, the optimal value is output. If the constraints are not met, crossover and mutation are performed on the individuals, iterating to the next generation, and the calculation continues until the optimal solution is obtained.
[0079] Based on the above embodiments, the present invention evaluates the load-bearing capacity of characteristic bridges within a cluster of bridges obtained by clustering, thereby achieving load-bearing capacity evaluation of all bridges in the region, avoiding the problem that it is impossible to evaluate the load-bearing capacity of all bridges in a group of bridges in the region due to cost limitations.
[0080] The following is a specific embodiment of a bridge load-bearing capacity evaluation method provided by the present invention, which may include:
[0081] A bridge evaluation system is constructed based on technical condition, load level, service life, total crack length, bridge location, and span length.
[0082] Based on the analytic hierarchy process (AHP), bridge scores are given for all small and medium-span bridges in the target area under the bridge evaluation system.
[0083] Based on bridge rating, small and medium-span bridges are classified into multiple sub-bridge groups.
[0084] Bridge clustering attributes are determined based on service life, span length, and total crack length.
[0085] Based on the bridge clustering attributes, the K-means clustering method is used to divide each sub-bridge group into multiple bridge clusters;
[0086] Construct a database of theoretical values for deflection and material properties of various types of small- and medium-span bridges at different span lengths;
[0087] Based on the theoretical value database, prediction models for material performance parameters of various types of small and medium-span bridges were trained.
[0088] Obtain the target deflection and target span length of the characteristic bridges within each bridge cluster, and input the material performance parameter prediction model corresponding to the type of the characteristic bridge to obtain the target material performance parameters;
[0089] Calculate the loss coefficient based on the target material performance parameters and the initial material performance parameters;
[0090] The load-bearing capacity evaluation coefficient is obtained by averaging the loss coefficients of the performance parameters of various types of target materials.
[0091] The load-bearing capacity evaluation coefficient of the characteristic bridge is assigned to the other bridges in the corresponding bridge cluster;
[0092] The load-bearing capacity is evaluated based on the load-bearing capacity evaluation coefficient of small and medium-span bridges within the target area.
[0093] The following combination Figure 2 , Figure 2 This is a structural block diagram of a bridge group load-bearing capacity evaluation device provided in an embodiment of the present invention. The device may include:
[0094] The first module 100 is used to divide the bridge group in the target area into multiple sub-bridge groups based on the analytic hierarchy process.
[0095] The second module 200 is used to divide the bridges in each of the sub-bridge groups into multiple bridge clusters based on a clustering algorithm;
[0096] The third module 300 is used to determine the load-bearing performance evaluation coefficient of the characteristic bridges within the bridge cluster;
[0097] The fourth module 400 is used to assign the load-bearing performance evaluation coefficient of the characteristic bridge to the other bridges in the corresponding bridge cluster.
[0098] The fifth module 500 is used to evaluate the load-bearing capacity of all bridges in the bridge group based on the load-bearing capacity evaluation coefficient.
[0099] Based on the above embodiments, the present invention evaluates the load-bearing capacity of characteristic bridges within a cluster of bridges obtained by clustering, thereby achieving load-bearing capacity evaluation of all bridges in the region, avoiding the problem that it is impossible to evaluate the load-bearing capacity of all bridges in a group of bridges in the region due to cost limitations.
[0100] Based on the above embodiments, the first module 100 may include:
[0101] The first unit is used to construct a bridge evaluation system based on technical condition, load level, service life, total crack length, bridge location and span length.
[0102] The second unit is used to give the bridge scores of all bridges in the bridge group in the target area based on the analytic hierarchy process under the bridge evaluation system.
[0103] The third unit is used to classify all bridges in the bridge group into multiple sub-bridge groups based on the bridge rating.
[0104] Based on the above embodiments, the second module 200 may include:
[0105] The fourth unit is used to determine the bridge clustering attributes based on the service life, the span length, and the total length of the cracks;
[0106] The fifth unit is used to divide the bridges in each sub-bridge group into multiple bridge clusters based on the bridge clustering attributes using a clustering algorithm.
[0107] Based on the above embodiments, the third module 300 may include:
[0108] Unit 6 is used to construct a database of theoretical values for structural and material performance parameters of different types of bridges under different span lengths;
[0109] The seventh unit is used to train a corresponding material performance parameter prediction model based on the theoretical value database of various types of bridges;
[0110] The eighth unit is used to obtain the target structural performance parameters and target span length of the characteristic bridges within the bridge cluster;
[0111] The ninth unit is used to input the target structural performance parameters and the target span length into the corresponding material performance parameter prediction model to obtain the target material performance parameters of the feature bridge.
[0112] The tenth unit is used to calculate the load-bearing performance evaluation coefficient based on the target material performance parameters.
[0113] Based on the above embodiments, the structural performance parameters are any combination of deflection, strain, and crack width, and the material performance parameters are any combination of the main beam's elastic modulus, the main beam's mass density, and the prestressing tendon material strength.
[0114] Based on the above embodiments, the device may further include:
[0115] The sixth module is used to perform fitting and prediction based on the load-bearing performance evaluation coefficients to obtain future load-bearing performance evaluation coefficients;
[0116] The seventh module is used to assess the future load-bearing capacity of the bridge based on the aforementioned future load-bearing capacity assessment coefficients.
[0117] Based on the above embodiments, the device may further include:
[0118] The eighth module is used to obtain the average maintenance cost of all bridges in the bridge group and the future load-bearing performance evaluation coefficient of each bridge at a preset future time after maintenance is completed.
[0119] The ninth module is used to construct a safety function based on the future load-bearing capacity evaluation coefficient and a cost function based on the average maintenance cost.
[0120] The tenth module is used to select bridges to be maintained from the bridge group based on the safety function and the cost function as constraints.
[0121] Based on the above embodiments, the present invention also provides a bridge group load-bearing performance evaluation device. This device may include a memory and a processor. The memory stores a computer program, and when the processor calls the computer program in the memory, it can implement the steps provided in the above embodiments. Of course, the device may also include various necessary network interfaces, power supplies, and other components.
[0122] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by an execution terminal or processor, can implement the method provided in the embodiments of the present invention; the storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0123] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
Claims
1. A method for evaluating the load-bearing capacity of bridge groups, characterized in that, include: The target area is divided into multiple sub-bridge groups based on the analytic hierarchy process. Based on a clustering algorithm, the bridges in each of the sub-bridge groups are divided into multiple bridge clusters; Determine the load-bearing capacity evaluation coefficients for the characteristic bridges within the bridge cluster; The load-bearing capacity evaluation coefficient of the featured bridge is assigned to the other bridges in the corresponding bridge cluster; The load-bearing capacity of all bridges in the bridge group is evaluated based on the aforementioned load-bearing capacity evaluation coefficient. The determination of the load-bearing capacity evaluation coefficients for characteristic bridges within the bridge cluster includes: Construct a database of theoretical values for structural and material performance parameters of different types of bridges under different span lengths; Based on the theoretical value database of various types of bridges, corresponding material performance parameter prediction models are trained. Obtain the target structural performance parameters and target span length of the characteristic bridges within the bridge cluster; The target structural performance parameters and the target span length are input into the corresponding material performance parameter prediction model to obtain the target material performance parameters of the characteristic bridge; The load-bearing capacity evaluation coefficient is calculated based on the target material performance parameters; The structural performance parameters are any combination of deflection, strain, and crack width, and the material performance parameters are any combination of the main beam's elastic modulus, the main beam's mass density, and the prestressing tendon material strength.
2. The method for evaluating the load-bearing capacity of bridge groups according to claim 1, characterized in that, The analytic hierarchy process (AHP) divides the bridge group within the target area into multiple sub-bridge groups, including: A bridge evaluation system is constructed based on technical condition, load level, service life, total crack length, bridge location, and span length. Based on the analytic hierarchy process (AHP), the bridge scores of all bridges in the bridge group within the target area are given under the bridge evaluation system. Based on the bridge rating, all bridges in the bridge group are classified into multiple sub-bridge groups.
3. The method for evaluating the load-bearing capacity of bridge groups according to claim 2, characterized in that, The clustering algorithm divides the bridges in each sub-bridge group into multiple bridge clusters, including: The bridge clustering attributes are determined based on the service life, the span length, and the total length of the cracks. Based on the bridge clustering attributes, a clustering algorithm is used to divide the bridges in each sub-bridge group into multiple bridge clusters.
4. The method for evaluating the load-bearing capacity of bridge groups according to claim 1, characterized in that, Also includes: The future load-bearing performance evaluation coefficients are obtained by fitting and predicting based on the aforementioned load-bearing performance evaluation coefficients; The future load-bearing capacity of the bridge is assessed based on the aforementioned future load-bearing capacity evaluation coefficients.
5. The method for evaluating the load-bearing capacity of bridge groups according to claim 4, characterized in that, Also includes: Obtain the average maintenance cost of all bridges in the bridge group and the future load-bearing capacity evaluation coefficient of each bridge at a preset future time after maintenance is completed; A safety function is constructed based on the future load-bearing capacity evaluation coefficients, and a cost function is constructed based on the average maintenance cost. Bridges to be maintained are selected from the bridge group based on the aforementioned safety function and cost function as constraints.
6. A device for evaluating the load-bearing capacity of a bridge group, characterized in that, include: The first module is used to divide the bridge group within the target area into multiple sub-bridge groups based on the analytic hierarchy process. The second module is used to divide the bridges in each sub-bridge group into multiple bridge clusters based on a clustering algorithm. The third module is used to determine the load-bearing capacity evaluation coefficient of the characteristic bridges within the bridge cluster; The fourth module is used to assign the load-bearing performance evaluation coefficient of the characteristic bridge to the other bridges in the corresponding bridge cluster; The fifth module is used to evaluate the load-bearing capacity of all bridges in the bridge group based on the load-bearing capacity evaluation coefficient. The determination of the load-bearing capacity evaluation coefficients for characteristic bridges within the bridge cluster includes: Construct a database of theoretical values for structural and material performance parameters of different types of bridges under different span lengths; Based on the theoretical value database of various types of bridges, corresponding material performance parameter prediction models are trained. Obtain the target structural performance parameters and target span length of the characteristic bridges within the bridge cluster; The target structural performance parameters and the target span length are input into the corresponding material performance parameter prediction model to obtain the target material performance parameters of the characteristic bridge; The load-bearing capacity evaluation coefficient is calculated based on the target material performance parameters; The structural performance parameters are any combination of deflection, strain, and crack width, and the material performance parameters are any combination of the main beam's elastic modulus, the main beam's mass density, and the prestressing tendon material strength.
7. A bridge group load-bearing capacity assessment device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the bridge group load-bearing capacity evaluation method as described in any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the bridge group load-bearing performance evaluation method as described in any one of claims 1 to 5.
Citation Information
Patent Citations
Bridge cluster dynamic evaluation method, device and equipment and readable storage medium
CN113569315A
