Method and system for evaluating homogeneity of concrete section at vibration abutted seam of axle

Abstract

The invention provides a method and system for evaluating the homogeneity of a concrete section at an axle vibration abutted seam, and the method comprises the following steps: carrying out a vibration experiment on experimental concrete, and enabling the vibration experiment to be used for simulating the coupling vibration condition of an axle; the experimental concrete is consistent with the concrete at the vibration abutted seam of the axle in attribute; acquiring section image data of the experimental concrete after the vibration experiment; based on the section image data of the experimental concrete, obtaining a gravel distribution diagram used for representing the distribution condition of various gravels in the concrete section area; obtaining a homogeneity evaluation index value according to the gravel distribution map; and calculating the concrete compressive strength based on the homogeneity evaluation index value. According to the distribution condition of the gravels on the concrete section, the layering condition of the gravels on the concrete section influenced by axle vibration can be rapidly evaluated, and the concrete performance can be rapidly evaluated.

Description

Technical Field

[0001] The invention belongs to the technical field of concrete performance monitoring, and in particular relates to a method and system for evaluating the homogeneity of a concrete cross section at a vibration joint of a vehicle bridge. Background Art

[0002] With the development of concrete, researchers' understanding of concrete is also increasing. During the mixing and use of concrete, due to the influence of mechanical action, load, etc., the cross-section of hardened concrete is often unevenly distributed in the vertical direction, generally showing a situation where there is more slurry on the top and sand and gravel concentrated in the lower part. In the vehicle-bridge coupled vibration model, when a car passes the bridge at a certain speed, the axle weight and speed effect of the vehicle will cause the bridge structure to vibrate, and the vibration of the bridge will in turn affect the operation of the vehicle. Such vibration will have a greater impact on the homogeneity of the concrete at the bridge joint, thereby affecting the performance of the bridge and seriously endangering life and property safety. However, the existing technology lacks an effective method for detecting the homogeneity and compressive resistance of concrete at the vibration joint of the vehicle bridge, which seriously affects the evaluation and monitoring of road safety. Summary of the invention

[0003] The purpose of the present invention is to address the deficiencies of the above-mentioned background technology and to provide a method and system for evaluating the homogeneity of concrete cross-sections at vibration joints of vehicle axles. According to the distribution of sand and gravel in the concrete cross-section, it is possible to quickly evaluate the stratification of sand and gravel in the concrete cross-section after the influence of vehicle axle vibration and quickly evaluate the concrete performance.

[0004] The technical solution adopted by the present invention is: a method for evaluating the homogeneity of the concrete cross section at the vibration joint of a bridge, comprising the following steps:

[0005] A vibration test is performed on the experimental concrete, the vibration test is used to simulate the vehicle-bridge coupled vibration condition; the experimental concrete has the same properties as the concrete at the vehicle-bridge vibration joint;

[0006] Collect cross-sectional image data of the experimental concrete after the vibration test; obtain a sand and gravel distribution map for characterizing the distribution of various types of sand and gravel in the concrete cross-sectional area based on the cross-sectional image data of the experimental concrete; obtain a homogeneity evaluation index value according to the sand and gravel distribution map;

[0007] The compressive strength of concrete is calculated based on the homogeneity evaluation index value.

[0008] In the above technical scheme, the cross-sectional image data of concrete is input into the concrete cross-sectional segmentation model, and the sand and gravel distribution map is obtained according to the output of the concrete cross-sectional segmentation model; the concrete cross-sectional segmentation model is generated by training with a deep learning instance segmentation network, and a single sample in its training set includes: the cross-sectional image data of concrete as input, the outer annotation of the concrete cross-sectional area and each sand and gravel target as training labels; the training set is used for the concrete cross-sectional segmentation model after high-order data enhancement processing using the Mosaic, CutMix and ColorJitter methods; the instance segmentation network uses the improved SoloV2 network.

[0009] In the above technical solution, the process of calculating the compressive strength of concrete based on the homogeneity evaluation index value includes:

[0010] Based on the sand and gravel distribution diagram, calculate the percentage set of the area occupied by the sand and gravel in three intervals of equal length along the vertical direction of the concrete, the area set of the Delaunay triangle formed between each sand and gravel, and the shortest center distance set of each sand and gravel and its adjacent sand and gravel;

[0011] According to the above set, the sand and gravel distribution uniformity evaluation index, the Delaunay triangle area set ratio and the set average value of the shortest center distance between adjacent sand and gravel are calculated as the homogeneity evaluation index value;

[0012] The basic concrete compressive strength is calculated based on the homogeneity evaluation index and the sand and gravel content ratio of the experimental concrete;

[0013] The final concrete compressive strength is obtained by adding the basic concrete compressive strength and the correction amount of the vibration test time.

[0014] In the above technical solution, the sand and gravel distribution uniformity evaluation index I P 、Delaunay triangle area set ratio M S The average value of the shortest center distance between adjacent gravels and sandstones is M D , calculated using the following formula:

[0015]

[0016] Where: S0 is the area percentage of the sand and gravel target in the entire concrete cross-sectional area;

[0017] S a , S b , S c They are the percentage of the area of ​​the sand and gravel targets in the three length intervals in the vertical direction of the concrete cross section, unit: pixel 2 ;

[0018]

[0019] In the formula, S i is the area of ​​the ith Delaunay triangle in the concrete cross-section, unit: pixel 2 ; N is the number of Delaunay triangles in the concrete cross-section area; S is the area of ​​the concrete cross-section area, unit: pixel 2 ;

[0020]

[0021] Where D i is the value of the shortest center distance between the i-th adjacent gravels, unit: pixel; N represents the number of adjacent gravels in the concrete cross-section area.

[0022] In the above technical solution, the basic concrete compressive strength W is calculated using the following formula:

[0023] W=A×I P +B×M S +C×M D +D×R+E

[0024] Among them, A, B, C, D, and E are all constants, and R is the sand and gravel ratio of the experimental concrete.

[0025] In the above technical solution, the following formula is used to calculate the concrete compressive strength W T

[0026] W T =W+P T

[0027]

[0028] Among them, P T It represents the correction value based on the vibration test time, x represents the time of the vibration test, in hours; α and F are both constants.

[0029] In the above technical solution, the process of obtaining constants A, B, C, D, and E in the basic concrete compressive strength calculation formula includes:

[0030] The concrete compressive strength of several concrete blocks that have not been subjected to vibration tests is obtained through experiments;

[0031] Obtaining cross-sectional image data of concrete blocks, and then obtaining its sand and gravel distribution map;

[0032] According to the sand and gravel distribution map of each concrete block, the sand and gravel distribution uniformity evaluation index, the Delaunay triangle area set ratio and the set average value of the shortest center distance between adjacent sand and gravel are calculated;

[0033] According to the evaluation index of sand and gravel distribution uniformity of each concrete block, the collective proportion of Delaunay triangle area, the collective average value of the shortest center distance between adjacent sand and gravel, the sand and gravel content ratio, and the compressive strength of concrete, the constants A, B, C, D, and E in the basic concrete compressive strength calculation formula are obtained by fitting calculation.

[0034] In the above technical solution, the constant in the calculation formula of the correction amount based on the vibration test time is obtained as follows:

[0035] Performing vibration tests on the concrete blocks at different vibration durations, respectively, and obtaining the basic concrete compressive strength of the concrete blocks calculated based on the cross-sectional image data after each vibration test and the actual concrete compressive strength of the concrete blocks obtained through the experiment;

[0036] The constant F in the calculation formula of the correction amount based on the vibration test time is obtained by fitting the actual concrete compressive strength and basic concrete compressive strength of several concrete blocks under different vibration durations.

[0037] The present invention also provides a system for evaluating the homogeneity of the concrete cross section at the vibration joint of a vehicle bridge, and the system is used to implement the method for evaluating the homogeneity of the concrete cross section at the vibration joint of a vehicle bridge described in the above technical solution.

[0038] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for evaluating the homogeneity of the concrete cross section at the vibration joint of the vehicle bridge described in the above technical solution is implemented.

[0039] The beneficial effect of the present invention is that the present invention can evaluate the homogeneity state of concrete sections of different types and with different levels of sand and gravel and estimate the compressive strength of the concrete. The present invention not only provides a new type of rapid concrete performance evaluation and estimation method, but also provides a new solution for the research and application development of concrete sand and gravel aggregates.

[0040] Furthermore, the present invention can automatically and accurately identify and segment the distribution of sand and gravel in concrete cross sections through an image-based deep learning instance segmentation network, thereby improving the efficiency and accuracy of obtaining sand and gravel distribution. Compared with traditional manual labeling or simple image processing methods, it has higher applicability and scalability, and is suitable for processing concrete samples of different types and component proportions. The present invention uses Mosaic, CutMix and ColorJitter methods to perform high-order data enhancement on the training set, and uses the improved SoloV2 network to train the instance segmentation model. Through high-order data enhancement, the training set covers a variety of possible concrete cross-section image features, which helps the model better learn the diversified distribution of sand and gravel. The improved SoloV2 network enhances the accuracy and robustness of the segmentation model, making the model applicable to concrete samples under various environmental conditions, and improving the universality and segmentation accuracy of the model.

[0041] Furthermore, the present invention calculates the compressive strength of concrete based on the sand and gravel distribution map. Through the quantitative analysis of the sand and gravel distribution map and the associated calculation of the compressive strength, the error caused by the change of concrete composition and structure can be reduced, making the compressive strength evaluation more objective and accurate. At the same time, this method has a high generalization ability and can adapt to concrete samples of different environments and materials, thereby improving the accuracy of compressive strength prediction.

[0042] Furthermore, the present invention calculates the sand and gravel distribution uniformity evaluation index of the concrete cross section, the area ratio of the Delaunay triangle and the set average of the shortest center distance of adjacent sand and gravel based on the sand and gravel distribution diagram, and by calculating multiple homogeneity evaluation indicators, the homogeneity characteristics inside the concrete can be more comprehensively characterized. The area ratio of the Delaunay triangle and the center distance of adjacent sand and gravel can respectively reflect the spatial layout and compactness of the sand and gravel, thereby more objectively and comprehensively evaluating the homogeneity of the concrete cross section, which is helpful to predict the mechanical properties of the concrete.

[0043] Furthermore, the present invention adopts a basic compressive strength calculation formula, with homogeneity evaluation index, Delaunay triangle area ratio, the average value of the shortest center distance between adjacent sand and gravel, and the sand and gravel content ratio as parameters. Based on the fitting formula of multiple parameters, it can combine the different structural characteristics and component ratios of concrete to accurately reflect the mechanical properties inside the material. By using the homogeneity evaluation index and sand and gravel distribution characteristics, the compressive strength can be predicted more effectively, and the accuracy and scientificity of the compressive strength prediction can be improved.

[0044] Furthermore, the present invention calculates the final concrete compressive strength through the correction amount of the vibration test time, introduces the vibration test time into the compressive strength prediction, and can reflect the influence of the actual vehicle bridge vibration on the concrete structure. The calculation of the correction amount makes the predicted compressive strength closer to the actual stress condition, thereby improving the practicality and accuracy of the compressive strength calculation, and facilitating more accurate application in vehicle bridge structure design and quality assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0046] Figure 2 A schematic diagram of a flow chart of a method for evaluating the homogeneity of concrete cross-sections at a vibration joint of a vehicle bridge according to a specific embodiment;

[0047] Figure 3 It is a schematic diagram for calculating the percentage set of the area occupied by the gravel, the area set of the Delaunay triangle formed between each gravel, and the shortest center distance set between each gravel and its adjacent gravel.

[0048] Figure 4 This is a comparison chart of the calculated and actual values ​​of concrete compressive strength under three types of sand and gravel content ratios.

[0049] Figure 5 This is a comparison chart between the calculated and actual values ​​of concrete compressive strength under simulated vibration of vehicle-bridge coupling. DETAILED DESCRIPTION

[0050] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments to facilitate a clear understanding of the present invention, but they do not constitute a limitation on the present invention.

[0051] Example 1

[0052] like Figure 1 As shown, a method for evaluating the homogeneity of concrete cross-section at a vibration joint of a bridge of the present invention comprises the following steps:

[0053] A vibration test is performed on the experimental concrete, the vibration test is used to simulate the vehicle-bridge coupled vibration condition; the experimental concrete has the same properties as the concrete at the vehicle-bridge vibration joint;

[0054] Collect cross-sectional image data of the experimental concrete after the vibration test; obtain a sand and gravel distribution map for characterizing the distribution of various types of sand and gravel in the concrete cross-sectional area based on the cross-sectional image data of the experimental concrete; obtain a homogeneity evaluation index value according to the sand and gravel distribution map;

[0055] The compressive strength of concrete is calculated based on the homogeneity evaluation index value.

[0056] Specifically, the process of obtaining the sand and gravel distribution map based on the cross-sectional image data of the experimental concrete includes: inputting the cross-sectional image data of the concrete into a concrete cross-sectional segmentation model, and obtaining the sand and gravel distribution map according to the output of the concrete cross-sectional segmentation model.

[0057] Specifically, the process of obtaining the homogeneity evaluation index value according to the sand and gravel distribution map includes:

[0058] Based on the sand and gravel distribution diagram, calculate the percentage set of the area occupied by the sand and gravel in three intervals of equal length along the vertical direction of the concrete, the area set of the Delaunay triangle formed between each sand and gravel, and the shortest center distance set of each sand and gravel and its adjacent sand and gravel;

[0059] According to the above set, the sand and gravel distribution uniformity evaluation index, the Delaunay triangle area set ratio and the set average value of the shortest center distance between adjacent sand and gravel are calculated as homogeneity evaluation indicators.

[0060] Preferably, the sand and gravel distribution uniformity evaluation index I P 、Delaunay triangle area set ratio M S The average value of the shortest center distance between adjacent gravels and sandstones is M D , calculated using the following formula:

[0061]

[0062] Where: S0 is the area percentage of the sand and gravel target in the entire concrete cross-sectional area;

[0063] S a , S b , S c They are the percentage of the area of ​​the sand and gravel targets in the three length intervals in the vertical direction of the concrete cross section, unit: pixel 2 ;

[0064]

[0065] In the formula, S i is the area of ​​the ith Delaunay triangle in the concrete cross-section, unit: pixel 2 ; N is the number of Delaunay triangles in the concrete cross-section area; S is the area of ​​the concrete cross-section area, unit: pixel 2 ;

[0066]

[0067] Where D i is the value of the shortest center distance between the i-th adjacent gravels, unit: pixel; N represents the number of adjacent gravels in the concrete cross-section area.

[0068] Specifically, the process of calculating the compressive strength of concrete based on the homogeneity evaluation index value includes:

[0069] The basic concrete compressive strength is calculated based on the homogeneity evaluation index and the sand and gravel content ratio of the experimental concrete;

[0070] The final concrete compressive strength is obtained by adding the basic concrete compressive strength and the correction amount of the vibration test time.

[0071] Preferably, the basic concrete compressive strength W is calculated using the following formula:

[0072] W=A×I P +B×M S +C×M D +D×R+E

[0073] Among them, A, B, C, D, and E are all constants, and R is the sand and gravel ratio of the experimental concrete.

[0074] Specifically, the concrete compressive strength W is calculated using the following formula: T

[0075] W T =W+P T

[0076]

[0077] Among them, P T It represents the correction value based on the vibration test time, x represents the time of the vibration test, in hours; α and F are both constants.

[0078] Example 2

[0079] In order to implement the concrete cross-section homogeneity evaluation method at the axle vibration joint described in Example 1, Example 2 provides a method for constructing a concrete cross-section homogeneity evaluation system at the axle vibration joint, which is mainly used to generate a concrete cross-section segmentation model and fit the constants in the basic concrete compressive strength calculation formula and the final concrete compressive strength calculation formula, and specifically includes the following steps:

[0080] S1. Three types of concrete with different gravel content were prepared using the scattered gravel filling process (replacing the original mortar ratio of 20%, 30%, and 40%). A total of 30 cubic test blocks with a size of 40×40×40 were prepared. The exposed cross-section of the concrete was cut using a cutting machine to obtain the concrete cross-section image, and the corresponding compressive strength was obtained through experiments.

[0081] The sand and gravel include fine aggregate and coarse aggregate, and the coarse aggregate is 3-10mm granite. The three levels of sand and gravel content are 20%, 30% and 40% replacement of mortar, and the sand and gravel mixing process is a scattered filling sand and gravel process. The concrete block design method is based on the improved Andreasen and Andersen model, the curing age is 28 days, and the compressive strength test block size is a 40×40×40 cubic block.

[0082] The specific method of making concrete test blocks is as follows:

[0083] First, a conventional concrete mortar is prepared using a standard procedure. Subsequently, a layer of mortar is laid horizontally from left to right on the bottom of the concrete mold, followed by a layer of gravel, and the cycle is repeated multiple times. The height of the gravel and mortar layer is limited to 1.5 times the maximum size of the gravel, until the mold is filled with aggregate and mortar layers, and the mixture is then transferred to a vibrating table for compaction.

[0084] S2. Use the concrete section image data obtained in S1 to train the concrete section segmentation model.

[0085] The concrete cross-section segmentation model is generated by deep learning instance segmentation network training, and a single sample in its training set includes: cross-section image data of concrete as input, concrete cross-section peripheral annotations and each sand and gravel target as training labels.

[0086] In the data annotation stage of the dataset, the concrete cross-section target and each gravel target were annotated separately; in the model training stage, the segmentation network used the improved SoloV2 algorithm, and the number of FPN layers was increased so that the network could learn size, color and texture information. In addition, Mosaic, CutMix and ColorJitter methods were used for high-order data enhancement before constructing the training set, test set and validation set.

[0087] The concrete production process and model training set of this embodiment are only used for exemplification and verification of the effectiveness of the method. In actual use, the training data can be as diverse as possible, and concrete cross-sectional images with different aggregate types, sizes, sand and gravel contents, materials and other characteristics can be collected and annotated as much as possible to make the model see richer samples. Transfer learning or few-sample learning can also be used: fine-tuning on different types of concrete data to improve the adaptability of the model; or combined with physical enhancement methods, simulation tools can be used to generate concrete cross-sectional images with different proportions and materials to expand the coverage of the data set.

[0088] At the same time, this embodiment can also use the same method to construct a targeted concrete cross-section segmentation model for the specific type of concrete used in the road surface to be evaluated, which is used in the homogeneity evaluation process described in Example 1, as well as subsequent steps S3 and S4 to generate the corresponding sand and gravel distribution map and homogeneity evaluation index value.

[0089] S3, inputting the concrete cross-section image data obtained by S1 into the trained concrete cross-section segmentation model, and then calculating the corresponding sand and gravel distribution map in the concrete cross-section area.

[0090] When creating a sand and gravel distribution map based on the concrete section perimeter annotations and each sand and gravel target output by the concrete section segmentation model, the trained concrete section segmentation model is used to obtain results with a confidence level of more than 80%, and the results with too small mask area values ​​in the sand and gravel types are eliminated. The binary image and skeleton analysis method is used to create an undirected graph of sand and gravel distribution based on the center of the sand and gravel graph, which is used as the sand and gravel distribution map for subsequent steps.

[0091] S4. For the sand and gravel distribution diagram obtained in S3, calculate the percentage set P of the area occupied by sand and gravel in three intervals of equal length along the vertical direction of the concrete, the area set S of the Delaunay triangle formed between each sand and gravel, and the set D of the shortest center distance between each sand and gravel and its adjacent sand and gravel, and then calculate the homogeneity evaluation index of each concrete specimen according to the above sets.

[0092] Figure 3 The blue, orange, and yellow markers show the calculation results of P, S, and D.

[0093] Concrete sand and gravel distribution uniformity evaluation index I P 、Delaunay triangle area set ratio M S The average value of the shortest center distance between adjacent gravels and sandstones is M D , the calculation method is as follows:

[0094]

[0095] Where: S0 is the area percentage of the sand and gravel target in the entire concrete cross-sectional area;

[0096] S a , S b , S c They are the percentage of the area of ​​the sand and gravel targets in the three length intervals in the vertical direction of the concrete cross section, unit: pixel 2 ;

[0097]

[0098] In the formula, S i is the area of ​​the ith Delaunay triangle in the concrete cross-section, unit: pixel 2 ; N is the number of Delaunay triangles in the concrete cross-section area; S is the area of ​​the concrete cross-section area, unit: pixel 2 ;

[0099]

[0100] Where D i is the value of the shortest center distance between the i-th adjacent gravels, unit: pixel; N represents the number of adjacent gravels in the concrete cross-section area.

[0101] S5. Based on the compressive strength of the concrete specimen obtained from the S1 experiment and the calculation results of S4, Python is used to calculate the basic concrete compressive strength W and I P ,M S ,M D The sand and gravel content ratio R is fitted and the following formula is obtained, which also evaluates the homogeneity of the concrete section from the side:

[0102] W=42.37I P -31.42M S +21.31M D +125.58R-141.40 (1)

[0103] Comparison of the calculated values ​​and test values ​​of concrete compressive strength under different sand and gravel content calculated by fitting formula is shown in Table 1 and Figure 4 , verify the correctness of the fitting formula.

[0104] Table 1 Comparison of calculated and tested values ​​of concrete compressive strength at different sand and gravel content

[0105]

[0106] S6, placing the concrete test block obtained based on S1 into the concrete vibration table, specifying the vibration frequency and amplitude vibration mode, and simulating the vehicle-bridge coupling vibration under different vibration durations. After the vibration process stops, remove the concrete from the vibration table. In this embodiment, the amplitude of the concrete vibration process is set to 3.5mm; the frequency is 5Hz; the vibration mode is the normal mode, vibrating for 15s and stopping for 45s; the vibration action time is calculated from the start of the vibration table. The vibration action time varies from 12-24h.

[0107] The concrete section of the vibrated concrete test block is input into the trained concrete section segmentation model, and then the corresponding sand and gravel distribution map in the concrete section area is calculated. Then, the corresponding basic concrete compressive strength is obtained by the calculation method in S3-S4, and the concrete compressive strength W of the corresponding concrete test block is re-measured. T .

[0108] Based on all experimental results, Python was used to calculate the basic concrete compressive strength W, concrete compressive strength W TThe vibration time x is fitted and the calculation formula of the corrected compressive strength of the vibration specimen is obtained.

[0109] W T =WP T

[0110]

[0111] Where: P T —Correction of the original formula based on vibration time

[0112] x—vibration time, unit: hour

[0113] Comparison of the calculated values ​​of concrete compressive strength under bridge vibration simulation at different vibration times using fitting formula (2) and the experimental values ​​is shown in Table 2 and Figure 5 , verify the correctness of the fitting formula.

[0114] Table 2 Comparison of calculated and tested values ​​of concrete compressive strength at different sand and gravel content

[0115]

[0116] Example 3

[0117] The present invention also provides a system for evaluating the homogeneity of the concrete cross section at the vibration joint of a vehicle bridge, and the system is used to implement the method for evaluating the homogeneity of the concrete cross section at the vibration joint of a vehicle bridge described in the above technical solution.

[0118] Example 4

[0119] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for evaluating the homogeneity of the concrete cross section at the vibration joint of the vehicle bridge described in the above technical solution is implemented.

[0120] Those skilled in the art will appreciate 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. Moreover, 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.

[0121] 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 processor, 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.

[0122] 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.

[0123] 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.

[0124] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

[0125] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

Claims

1. A method for evaluating the homogeneity of concrete cross-section at a bridge vibration joint, characterized in that: The following steps are involved: A vibration test is performed on the experimental concrete, the vibration test is used to simulate the vehicle-bridge coupled vibration condition; the experimental concrete has the same properties as the concrete at the vehicle-bridge vibration joint; Collect cross-sectional image data of the experimental concrete after the vibration test; obtain a sand and gravel distribution map for characterizing the distribution of various types of sand and gravel in the concrete cross-sectional area based on the cross-sectional image data of the experimental concrete; obtain a homogeneity evaluation index value according to the sand and gravel distribution map; The compressive strength of concrete is calculated based on the homogeneity evaluation index value.

2. A method for evaluating the homogeneity of concrete cross-section at a bridge vibration joint according to claim 1, characterized in that: The cross-sectional image data of the concrete is input into the concrete cross-sectional segmentation model, and the sand and gravel distribution map is obtained according to the output of the concrete cross-sectional segmentation model; The concrete section segmentation model is generated by deep learning instance segmentation network training, and a single sample in the training set includes: concrete section image data as input, concrete section peripheral annotation and each sand and gravel target as training labels; the training set is used for the concrete section segmentation model after high-order data enhancement processing using Mosaic, CutMix and ColorJitter methods; the instance segmentation network uses the improved SoloV2 network.

3. The method for evaluating the homogeneity of concrete cross-section at a bridge vibration joint according to claim 1, characterized in that: The process of calculating the compressive strength of concrete based on the homogeneity evaluation index value includes: Based on the sand and gravel distribution diagram, calculate the percentage set of the area occupied by the sand and gravel in three intervals of equal length along the vertical direction of the concrete, the area set of the Delaunay triangle formed between each sand and gravel, and the shortest center distance set of each sand and gravel and its adjacent sand and gravel; According to the above set, the sand and gravel distribution uniformity evaluation index, the Delaunay triangle area set ratio and the set average value of the shortest center distance between adjacent sand and gravel are calculated as the homogeneity evaluation index value; The basic concrete compressive strength is calculated based on the homogeneity evaluation index and the sand and gravel content ratio of the experimental concrete; The final concrete compressive strength is obtained by adding the basic concrete compressive strength and the correction amount of the vibration test time.

4. The method for evaluating the homogeneity of concrete cross-section at a bridge vibration joint according to claim 3, characterized in that: Sand and gravel distribution uniformity evaluation index I P 、Delaunay triangle area set ratio M S The average value of the shortest center distance between adjacent gravels and sandstones is M D , calculated using the following formula: Where: S0 is the area percentage of the sand and gravel target in the entire concrete cross-sectional area; S a , S b , S c They are the percentage of the area of ​​the sand and gravel targets in the three length intervals in the vertical direction of the concrete cross section, unit: pixel 2 ; In the formula, S i is the area of ​​the ith Delaunay triangle in the concrete cross-section, unit: pixel 2 ; N is the number of Delaunay triangles in the concrete cross-section area; S is the area of ​​the concrete cross-section area, unit: pixel 2 ; Where D i is the value of the shortest center distance between the i-th adjacent gravels, unit: pixel; N represents the number of adjacent gravels in the concrete cross-section area.

5. The method for evaluating the homogeneity of concrete cross-section at a bridge vibration joint according to claim 4, characterized in that: The basic concrete compressive strength W is calculated using the following formula: W=A×I P +B×M S +C×M D +D×R+E Among them, A, B, C, D, and E are all constants, and R is the sand and gravel ratio of the experimental concrete.

6. A method for evaluating the homogeneity of concrete cross-section at a bridge vibration joint according to claim 5, characterized in that: The compressive strength of concrete W is calculated using the following formula: T : W T =W+P T Among them, P T It represents the correction value based on the vibration test time, x represents the time of the vibration test, in hours; α and F are both constants.

7. The method for evaluating the homogeneity of concrete cross-section at a bridge vibration joint according to claim 5, characterized in that: The process of obtaining constants A, B, C, D, and E in the basic concrete compressive strength calculation formula includes: The concrete compressive strength of several concrete blocks that have not been subjected to vibration tests is obtained through experiments; Obtaining cross-sectional image data of concrete blocks, and then obtaining its sand and gravel distribution map; According to the sand and gravel distribution map of each concrete block, the sand and gravel distribution uniformity evaluation index, the Delaunay triangle area set ratio and the set average value of the shortest center distance between adjacent sand and gravel are calculated; According to the evaluation index of sand and gravel distribution uniformity of each concrete block, the collective proportion of Delaunay triangle area, the collective average value of the shortest center distance between adjacent sand and gravel, the sand and gravel content ratio, and the compressive strength of concrete, the constants A, B, C, D, and E in the basic concrete compressive strength calculation formula are obtained by fitting calculation.

8. The method for evaluating the homogeneity of concrete cross-section at a bridge vibration joint according to claim 6, characterized in that: The constant in the calculation formula of the correction amount based on the vibration test time is obtained as follows: Performing vibration tests on the concrete blocks at different vibration durations, respectively, and obtaining the basic concrete compressive strength of the concrete blocks calculated based on the cross-sectional image data after each vibration test and the actual concrete compressive strength of the concrete blocks obtained through the experiment; The constant F in the calculation formula of the correction amount based on the vibration test time is obtained by fitting the actual concrete compressive strength and basic concrete compressive strength of several concrete blocks under different vibration durations.

9. A concrete cross-section homogeneity evaluation system at a bridge vibration joint, characterized in that: The system is used to implement the method for evaluating the homogeneity of the concrete cross section at the vibration joint of the vehicle bridge according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for evaluating the homogeneity of the concrete cross section at the vibration joint of the vehicle bridge according to any one of claims 1 to 7 is implemented.

Images