Tunnel crack damage parameterization analysis method and device

Abstract

The application discloses a tunnel crack damage parameterization analysis method and device, wherein the method comprises the following steps: establishing a disease database by taking a tunnel section as a unit according to tunnel crack damage detection data; acquiring key characteristic parameters of the tunnel crack damage detection data to form a parameterization data sequence; setting different weights for each key characteristic parameter in the parameterization data sequence; determining the similarity between current tunnel crack damage detection data and historical tunnel crack detection data; matching the current tunnel crack damage detection data with the historical tunnel crack detection data according to the similarity, and classifying the current tunnel crack damage detection data according to a matching result; and evaluating the grade of the current tunnel crack damage detection data according to the key characteristic parameters of the current tunnel crack damage detection data and the classification result. The application can improve the processing efficiency of disease detection data, realize rapid classification of disease detection data, and evaluate the grade of tunnel crack damage.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel detection, in particular to a tunnel crack damage parameterization analysis method and device. BACKGROUND

[0002] This section is intended to provide background or context to the embodiments of the application recited in the claims. The description herein does not constitute admission that the prior publication, square, or context, is prior art to the present application.

[0003] In recent years, the operating mileage of railway tunnels has reached 6437 km. Due to the variability of geological and hydrological conditions and the complexity of service environment, there are many types of defects and diseases in the operating tunnels. With the increase of operating time, the workload of tunnel maintenance and repair increases year by year. The lining is located directly above the line, and its quality and service state directly affect the safety of railway transportation. Practice has shown that the lining is a weak link of the problem of work equipment and affects the safety of operation, and is the focus of detection. Due to the complex geological conditions behind the lining, the disease development mechanism is not clear, and the disease has a certain development process, so it is necessary to use related instruments and equipment to carry out periodic detection, scientifically and reasonably evaluate the lining structure state, and realize accurate repair and state repair of tunnel facilities, which is of great significance to the safety of railway operation.

[0004] At present, the traditional tunnel crack damage exceeds a certain scale, and it is difficult to realize the matching of periodic detection data in a short time by manual method. With the development of rapid camera inspection equipment, the amount of disease data returned from the field is large, and the disease data is updated quickly. The technical personnel need to match and check the cracks one by one to solve the problems of data duplication, false alarm and missed alarm, which brings tedious work to the equipment maintenance party and reduces the timeliness of the detection data. For the diseases found in each detection, the management party still needs to spend a lot of time to carry out disease rechecking, comparison and evaluation. SUMMARY

[0005] The tunnel crack damage parameterization analysis method provided by the embodiments of the present application can improve the processing efficiency of disease detection data, realize rapid classification of disease detection data, and evaluate the grade of tunnel crack damage. The method comprises:

[0006] Establishing a disease database by taking tunnel segments as units for tunnel crack damage detection data;

[0007] Obtaining key characteristic parameters of tunnel crack damage detection data from the disease database to form a parameterization data sequence with the key characteristic parameters;

[0008] Setting different weights for each key characteristic parameter in the parameterization data sequence;

[0009] Determine the similarity between the current tunnel crack disease detection data and the historical tunnel crack detection data according to the key characteristic parameters of the current tunnel crack disease detection data, the key characteristic parameters of the historical tunnel crack detection data, and the corresponding weights.

[0010] Match the current tunnel crack disease detection data with the historical tunnel crack detection data according to the similarity, and classify the current tunnel crack disease detection data according to the matching result.

[0011] According to the key characteristic parameters of the current tunnel crack disease detection data and the classification result, the tunnel crack grade of the current tunnel crack disease detection data is evaluated.

[0012] The embodiment of the application also provides a tunnel crack disease parameterization analysis device to improve the processing efficiency of disease detection data, realize fast classification of disease detection data, and evaluate the grade of tunnel crack.

[0013] The disease database establishment module is used to establish a disease database by taking a tunnel section as a unit for the tunnel crack disease detection data.

[0014] The parameterized data sequence construction module is used to obtain the key characteristic parameters of the tunnel crack disease detection data from the disease database, and form a parameterized data sequence by using the key characteristic parameters.

[0015] The weight setting module is used to set different weights for each key characteristic parameter in the parameterized data sequence.

[0016] The similarity determination module is used to determine the similarity between the current tunnel crack disease detection data and the historical tunnel crack detection data according to the key characteristic parameters of the current tunnel crack disease detection data, the key characteristic parameters of the historical tunnel crack detection data, and the corresponding weights.

[0017] The crack disease detection data classification module is used to match the current tunnel crack disease detection data with the historical tunnel crack detection data according to the similarity, and classify the current tunnel crack disease detection data according to the matching result.

[0018] The tunnel crack grade evaluation module is used to evaluate the tunnel crack grade of the current tunnel crack disease detection data according to the key characteristic parameters of the current tunnel crack disease detection data and the classification result.

[0019] The embodiment of the application also provides a computer device, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the tunnel crack disease parameterization analysis method described above when executing the computer program.

[0020] The embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the tunnel crack damage parameterization analysis method.

[0021] The embodiment of the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the tunnel crack damage parameterization analysis method.

[0022] In the embodiment of the present application, the crack damage detection data is classified by the similarity between the current crack damage detection data and the historical crack damage detection data, and the key characteristic parameters of the crack damage detection data are involved in the process of solving the similarity, and the key characteristic parameters are obtained in the disease database without increasing additional workload and are simple to operate, and then the grade of the crack is evaluated according to the key characteristic parameters of the crack damage detection data and the classification result, the processing efficiency of the crack damage detection data is improved, the analysis of the crack damage detection data is realized, the crack damage detection data is quickly classified, and the grade of the tunnel crack is evaluated. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor. In the drawings:

[0024] Figure 1 The flow chart of the tunnel crack damage parameterization analysis method in the embodiment of the present application;

[0025] Figure 2 The schematic diagram of the computer device in the embodiment of the present application;

[0026] Figure 3 The tunnel crack damage distribution diagram in the embodiment of the present application;

[0027] Figure 4 The schematic diagram of the tunnel crack damage parameterization analysis device in the embodiment of the present application;

[0028] Figure 5 The schematic diagram of the specific tunnel crack damage parameterization analysis device in the embodiment of the present application. DETAILED DESCRIPTION

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0030] like Figure 1 This is a flowchart of the parameterized analysis method for tunnel crack damage in this embodiment of the invention. In this embodiment, the crack damage detection data is classified based on the similarity between current crack damage detection data and historical crack damage detection data. The process of solving for the similarity involves key feature parameters of the crack damage detection data. These key feature parameters are obtained from the damage database, requiring no additional workload and simplifying the operation. Then, based on the key feature parameters of the crack damage detection data and the classification results, the crack damage level is assessed, and the level assessment results are synchronized to the damage database to ensure real-time updates of the damage database. This improves the processing efficiency of crack damage detection data and realizes the analysis of crack damage detection data. The method includes:

[0031] Step 101: Establish a disease database by tunnel segment based on the tunnel segment detection data;

[0032] Step 102: Obtain key feature parameters from the tunnel cracking disease detection data from the disease database, and form a parameterized data sequence using the key feature parameters;

[0033] Step 103: Set different weights for each key feature parameter in the parameterized data sequence;

[0034] Step 104: Determine the similarity between the current tunnel crack detection data and the historical tunnel crack detection data based on the key feature parameters of the current tunnel crack detection data, the key feature parameters of the historical tunnel crack detection data, and the corresponding weights.

[0035] Step 105: Match the current tunnel crack and defect detection data with the historical tunnel crack and defect detection data based on similarity, and classify the current tunnel crack and defect detection data according to the matching results;

[0036] Step 106: Based on the key characteristic parameters and classification results of the current tunnel cracking and disease detection data, evaluate the tunnel cracking level of the current tunnel cracking and disease detection data.

[0037] The following provides a detailed explanation of each step.

[0038] In step 101, the tunnel crack and defect detection data are used to establish a defect database based on tunnel segments.

[0039] In step 102, key characteristic parameters of the tunnel crack disease detection data are obtained from the disease database to form a parameterized data sequence with the key characteristic parameters.

[0040] In an embodiment, the parameterized data sequence is formed with the key characteristic parameters, including: classifying and encoding the key characteristic parameters to form the parameterized data sequence.

[0041] In a specific embodiment, the parameterized data sequence is expressed as follows:

[0042] L(i)={P0, P1, P2, P3, P4};

[0043] In the formula, L(i) represents the parameterized data sequence; P0 represents the crack line, P0: {-1, 1}, P0=1 represents that the crack is located on the upper line, and P0=-1 represents that the crack is located on the lower line; P1 represents the crack position, P1: {1, 2, 3}, P1=1 represents that the crack is located on the side wall, P1=2 represents that the crack is located on the haunch, and P1=3 represents that the crack is located on the vault; P2 represents the crack center mileage; P3 represents the crack length; and P4 represents the crack shape, using the sine value of the angle between the crack center axis and the horizontal line.

[0044] In step 103, different weights are set for the key characteristic parameters in the parameterized data sequence.

[0045] In an embodiment, the key characteristic parameters include one or any combination of the position, mileage, length, and shape.

[0046] In step 104, the similarity between the current tunnel crack disease detection data and the historical tunnel crack detection data is determined according to the key characteristic parameters of the current tunnel crack disease detection data, the key characteristic parameters of the historical tunnel crack detection data, and the corresponding weights.

[0047] In an embodiment, the similarity between the current tunnel crack disease detection data and the historical tunnel crack detection data is determined according to the key characteristic parameters of the current tunnel crack disease detection data, the key characteristic parameters of the historical tunnel crack detection data, and the corresponding weights, including:

[0048] According to the tunnel section, the current tunnel crack disease detection data is grouped;

[0049] The historical tunnel crack detection data corresponding to the group in the disease database is called;

[0050] The similarity between the current tunnel crack disease detection data and the historical tunnel crack detection data in each group is determined one by one according to the key characteristic parameters of the current tunnel crack disease detection data, the key characteristic parameters of the historical tunnel crack detection data, and the corresponding weights.

[0051] In a specific embodiment, different parameter weights are assigned to each key feature parameter in the parameterized data sequence, and the similarity between the current tunnel crack detection data and the historical tunnel crack detection data is calculated, including:

[0052] The similarity calculation method is as follows:

[0053] ;

[0054] In the formula For the similarity calculation results, For the first The weights of key feature parameters, The algebraic sum of the key feature parameters is 1, that is... Key feature parameters include location, mileage, length, and shape, with location having a weighting coefficient. =0.2, mileage weighting coefficient =0.3, length weighting coefficient =0.2, shape weight coefficient =0.3. This represents the key characteristic parameters of the tunnel crack detection data for the current period. These represent the key characteristic parameters of historical tunnel crack detection data.

[0055] In step 105, the current tunnel crack and defect detection data are matched with the historical tunnel crack and defect detection data based on similarity, and the current tunnel crack and defect detection data are classified according to the matching results.

[0056] In one embodiment, the current tunnel crack and defect detection data are categorized based on the matching results, including:

[0057] Successfully matched current tunnel crack and defect detection data are classified as existing cracks, unmatched historical tunnel crack and defect detection data are classified as missed cracks, and unmatched current tunnel crack and defect detection data are classified as newly added cracks.

[0058] In a specific embodiment, the matching process includes: first, grouping the current tunnel crack and defect detection data according to tunnel segments; then, retrieving historical tunnel crack and defect detection data from the defect database based on the tunnel segments; and finally, calculating the similarity of each historical tunnel crack and defect detection data point with respect to the current tunnel crack and defect detection data. This process involves calculating the similarity between one of the i historical detection data points and j cracks in the current detection data, then calculating the similarity between the next historical detection data point and j cracks in the current detection data, resulting in an i×j similarity matrix.

[0059] The similarity matrix in the range of 95%-105% is defined as a successful match, and the remaining range is defined as a failed match. The current tunnel crack damage detection data that matches successfully is classified as existing cracks; the cracks that are not matched in the historical tunnel crack damage detection data are classified as missed cracks; and the current tunnel crack damage detection data that does not match successfully is classified as new cracks.

[0060] In step 106, according to the key feature parameters of the current tunnel crack damage detection data and the classification results, the current tunnel crack damage detection data is evaluated for tunnel crack grade.

[0061] In an embodiment, the historical tunnel crack damage detection data classified as missed cracks and the current tunnel crack damage detection data classified as new cracks are respectively entered into the disease database.

[0062] In a specific embodiment, according to the classification results, the length increment, number change, shape change, and repair state of the existing cracks are evaluated, and the crack grade is evaluated based on existing standards; the influence of the shape of the new crack on the safety of the lining is evaluated, and is included in the database as the focus of the next detection; for the missed cracks, the current detection data is updated, and the grade is evaluated, and the evaluation results are included in the disease database.

[0063] As a specific embodiment, a 60m segment of a certain tunnel is taken as an example for illustration. There are 10 cracks in this stage, where L is the crack length and W is the crack width. The specific distribution is shown in Figure 3 .

[0064] For the 10 cracks distributed in this segment, the feature parameters are sorted out and the parameterized data sequence is formed. The parameters in the sequence are shown in Table 1.

[0065] Table 1 Parameterized representation of tunnel lining cracks

[0066]

[0067] P0 represents the crack line, P0: {-1, 1}, when P0=1 represents that the crack is located on the upper line, and P0=-1 represents that the crack is located on the lower line. The line is a way of distinguishing the left and right tracks of double-track railways, and the left side facing the large mileage direction is the lower line, and the other side is the upper line. Practice shows that most of the tunnel lining cracks are symmetrically distributed, so the positive and negative are distinguished in the parameterized representation to avoid confusion of cracks symmetrically distributed at the same mileage.

[0068] P1 represents the location of the crack, where P1 = {1, 2, 3}. P1=1 indicates the crack is located in the sidewall, P1=2 indicates the crack is located in the arch waist, and P1=3 indicates the crack is located in the arch crown. The tunnel lining area is divided into sidewalls, arch waist, and arch crown according to height. Cracks at different locations have varying degrees of impact on the lining's stress, with cracks at the arch crown having the most severe impact on tunnel safety. Therefore, the height and location of the crack are used as one of the characteristic parameters.

[0069] P2 represents the center mileage of the crack. The center mileage of the crack is the position of the midpoint of the crack along the line direction. The number of cracks within the unit length is a key indicator for determining the condition of a segment, therefore the center mileage of the crack is used as one of the characteristic parameters.

[0070] P3 represents the crack length. Crack length is the distance between the start and end points of the crack, and it is a key indicator for judging whether the crack has developed after matching the data from each detection. Therefore, crack length is used as one of the characteristic parameters.

[0071] P4 represents the crack morphology, using the sine of the angle between the crack's central axis and the horizontal line. The angle ranges from [0, 180°]. Similarity is calculated using the corresponding sine value, ranging from [0, 1]. Practice shows that circumferential cracks account for approximately 95% and have a relatively small impact on lining safety; longitudinal and oblique cracks account for 5% and have a significant impact on lining safety, requiring close attention. Therefore, the crack angle is used as one of the characteristic parameters.

[0072] Due to factors such as systematic errors and human error, the characteristic parameters of crack damage may vary slightly from one detection to another. Based on practical experience, the mileage error in the lining appearance image is approximately ±1m, the length error is approximately 10%, and the angle error is approximately 1°; for the same crack, the row type and location parameters remain largely unchanged across different detection results. Figure 3 The 10 cracks in the model are superimposed with random errors within the above error range to simulate the changed crack characteristic parameters, as shown in Table 2.

[0073] Table 2 Characteristic parameters after tunnel lining cracking changes

[0074]

[0075] Calculate the similarity before and after the crack damage change using the formula:

[0076] ;

[0077] In the formula For the similarity calculation results, For the first The weight of each attribute, The algebraic sum of the parameters is 1, that is... The position weight coefficient =0.2, mileage weight coefficient =0.3, length weight coefficient =0.2, shape weight coefficient =0.3. represent the respective characteristic parameters of the current tunnel crack detection data, represent the respective characteristic parameters of the historical tunnel crack detection data; subscript used to distinguish cracks before and after changes, subscript used to distinguish different characteristic parameters of cracks. P0 is a crack line parameter, when P0=1, it represents an uplink, and when P0=-1, it represents a downlink.

[0078] The calculation results are shown in Table 3:

[0079] Table 3 Similarity of tunnel lining cracks before and after changes

[0080]

[0081] According to the calculation results in the table, when there is an error in the characteristic parameters of the cracks in the detection results, the matching degree of the same crack has a 5% deviation, therefore, a certain threshold needs to be set to complete the matching of the crack disease data. According to experience, the similarity threshold is set to 95%-105%, and when it is within the threshold, it is defined as the same crack, and further deterioration state assessment is carried out. For cracks outside the threshold, manual checking is used to classify and process the cracks.

[0082] On the basis of automatic matching, manual checking is supplemented to complete the classification of the current crack detection data. Considering the possible situations encountered in periodic detection data, the crack data is divided into existing cracks, new cracks, missed cracks and misjudged cracks.

[0083] According to the crack disease characteristic parameters and development, the crack disease grade assessment is carried out, and the disease database is updated.

[0084] For the lining crack data obtained by periodic detection, the length, shape and development status are analyzed, and the assessment is carried out according to “Railway Bridge and Tunnel Building Deterioration Assessment Part 2: Tunnel” (Q / CR 405.2-2019). According to the assessment results, the database is updated to realize the dynamic management of periodic detection data.

[0085] The embodiment of the application also provides a tunnel crack disease parameterization analysis device, as described in the following embodiment. Since the principle of solving the problem of the device is similar to that of the tunnel crack disease parameterization analysis method, the implementation of the device can be referred to the implementation of the tunnel crack disease parameterization analysis method, and the repeated parts will not be described again. Figure 4Figure 1 is a schematic diagram of a tunnel crack damage parameterization analysis device according to an embodiment of the present application. The device comprises:

[0086] The disease database establishment module 401 is configured to establish a disease database by taking tunnel segments as units for the tunnel crack damage detection data.

[0087] The parameterization data sequence construction module 402 is configured to obtain key characteristic parameters of the tunnel crack damage detection data from the disease database, and form a parameterization data sequence by using the key characteristic parameters.

[0088] The weight setting module 403 is configured to set different weights for the key characteristic parameters in the parameterization data sequence.

[0089] The similarity determination module 404 is configured to determine the similarity between the current tunnel crack damage detection data and the historical tunnel crack detection data according to the key characteristic parameters of the current tunnel crack damage detection data, the key characteristic parameters of the historical tunnel crack detection data, and the corresponding weights.

[0090] The crack damage detection data classification module 405 is configured to match the current tunnel crack damage detection data with the historical tunnel crack detection data according to the similarity, and classify the current tunnel crack damage detection data according to the matching result.

[0091] The tunnel crack grade evaluation module 406 is configured to evaluate the tunnel crack grade of the current tunnel crack damage detection data according to the key characteristic parameters of the current tunnel crack damage detection data and the classification result.

[0092] In an embodiment, the parameterization data sequence construction module 402 is specifically configured to classify and encode the key characteristic parameters to form the parameterization data sequence.

[0093] In an embodiment, the key characteristic parameters include one or any combination of position, mileage, length, and shape.

[0094] In an embodiment, the similarity determination module 404 is specifically configured to:

[0095] group the current tunnel crack damage detection data according to the tunnel segments;

[0096] call the historical tunnel crack detection data corresponding to the groups in the disease database;

[0097] determine the similarity between the current tunnel crack damage detection data and the historical tunnel crack detection data in each group one by one according to the key characteristic parameters of the current tunnel crack damage detection data, the key characteristic parameters of the historical tunnel crack detection data, and the corresponding weights.

[0098] In an embodiment, the crack damage detection data classification module 405 is specifically used for:

[0099] The current tunnel crack damage detection data that matches successfully is classified as existing crack damage, the historical tunnel crack damage detection data that does not match successfully is classified as missed crack damage, and the current tunnel crack damage detection data that does not match successfully is classified as new crack damage.

[0100] Figure 5 The schematic diagram of the specific tunnel crack damage parameterization analysis device in the embodiment of the present application, in an embodiment, further includes a disease database updating module 501, which is used for:

[0101] The historical tunnel crack damage detection data classified as missed crack damage and the current tunnel crack damage detection data classified as new crack damage are respectively recorded into the disease database.

[0102] The embodiment of the present application also provides a computer device, Figure 2 The schematic diagram of the computer device in the embodiment of the present application, the computer device 200 includes a memory 210, a processor 220, and a computer program 230 stored on the memory 210 and executable on the processor 220, and the processor 220 executes the computer program 230 to realize the tunnel crack damage parameterization analysis method described above.

[0103] The embodiment of the present application also provides a computer device, including a memory, a processor and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to realize the tunnel crack damage parameterization analysis method described above.

[0104] The embodiment of the present application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the tunnel crack damage parameterization analysis method described above.

[0105] The embodiment of the present application also provides a computer program product, the computer program product includes a computer program, and the computer program is executed by the processor to realize the tunnel crack damage parameterization analysis method described above.

[0106] In the embodiment of the present application, the crack damage detection data is classified by similarity between the current crack damage detection data and the historical crack damage detection data, and the key characteristic parameters of the crack damage detection data are involved in the process of solving the similarity, which are obtained in the disease database without increasing additional workload and are simple to operate. Then, the crack level is evaluated according to the key characteristic parameters of the crack damage detection data and the classification result, the processing efficiency of the crack damage detection data is improved, the analysis of the crack damage detection data is realized, the crack damage detection data is quickly classified, and the crack level of the tunnel is evaluated.

[0107] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can 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-ROMs, optical storage, etc.) containing computer-usable program code.

[0108] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams 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 apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the flow Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified by one or more of the flows and / or blocks.

[0109] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implements the flow Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks

[0110] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a device for implementing the flow Figure 1 one or more flows and / or blocksFigure 1 the steps of the functions specified in the one or more blocks.

[0111] The above-described embodiments of the present application are merely intended to further explain the purpose, technical solutions and advantages of the present application, and are not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A parameterized analysis method for tunnel cracking defects, characterized in that, include: A disease database was established using tunnel segments as units based on the tunnel damage detection data. Key feature parameters of tunnel crack damage detection data are obtained from the disease database, and parameterized data sequences are formed from the key feature parameters; Different weights are assigned to each key feature parameter in the parameterized data sequence; Based on the key feature parameters of the current tunnel crack and defect detection data, the key feature parameters of the historical tunnel crack and defect detection data, and the corresponding weights, the similarity between the current tunnel crack and defect detection data and the historical tunnel crack and defect detection data is determined. Based on similarity, the current tunnel crack and defect detection data are matched with historical tunnel crack and defect detection data, and the current tunnel crack and defect detection data are classified according to the matching results. Based on the key characteristic parameters and classification results of the current tunnel cracking and disease detection data, the tunnel cracking level is assessed. The specific representation of the parameterized data sequence is shown below: L(i)={P0, P1, P2, P3, P4}; In the formula, L(i) represents the parameterized data sequence; P0 represents the row of the crack, P0: {-1, 1}, where P0=1 indicates the crack is located in the upper row, and P0=-1 indicates the crack is located in the lower row; P1 represents the location of the crack, P1: {1, 2, 3}, where P1=1 indicates the crack is located in the sidewall, P1=2 indicates the crack is located in the arch waist, and P1=3 indicates the crack is located in the arch crown; P2 represents the mileage of the crack center; P3 represents the crack length; and P4 represents the crack shape, which is the sine of the angle between the crack centerline and the horizontal line. The similarity between current tunnel crack detection data and historical tunnel crack detection data is calculated using the following formula: ； In the formula For the similarity calculation results, For the first The weights of key feature parameters, The algebraic sum of the key feature parameters is 1. Key feature parameters include location, mileage, length, and shape, with location having a weighting coefficient. =0.2, mileage weighting coefficient =0.3, length weighting coefficient =0.2, shape weight coefficient =0.3, This represents the key characteristic parameters of the tunnel crack detection data for the current period. These represent the key characteristic parameters of historical tunnel crack detection data.

2. The method as described in claim 1, characterized in that, The process of forming parameterized data sequences based on key feature parameters includes classifying and encoding key feature parameters to form parameterized data sequences.

3. The method as described in claim 1, characterized in that, Based on the key characteristic parameters of the current tunnel crack and defect detection data, the key characteristic parameters of the historical tunnel crack and defect detection data, and the corresponding weights, the similarity between the current tunnel crack and defect detection data and the historical tunnel crack and defect detection data is determined, including: Based on tunnel segments, the current tunnel crack and defect detection data are grouped; Retrieve historical tunnel crack detection data for the corresponding group in the disease database; Based on the key characteristic parameters of the current tunnel crack detection data, the key characteristic parameters of the historical tunnel crack detection data, and the corresponding weights, the similarity between the current tunnel crack detection data and the historical tunnel crack detection data within each group is determined one by one.

4. The method as described in claim 1, characterized in that, Based on the matching results, the current tunnel crack and defect detection data are categorized, including: Successfully matched current tunnel crack and defect detection data are classified as existing cracks, unmatched historical tunnel crack and defect detection data are classified as missed cracks, and unmatched current tunnel crack and defect detection data are classified as newly added cracks.

5. The method as described in claim 4, characterized in that, Also includes: Historical tunnel crack detection data classified as missed cracks and current tunnel crack detection data classified as newly added cracks will be entered into the disease database respectively.

6. A parameterized analysis device for tunnel cracking defects, characterized in that, include: The disease database establishment module is used to establish a disease database by tunnel segment based on the tunnel segment detection data of tunnel cracks and defects. The parameterized data sequence construction module is used to obtain key feature parameters from the tunnel crack disease detection data from the disease database, and to form a parameterized data sequence based on the key feature parameters; The weight setting module is used to assign different weights to each key feature parameter in the parameterized data sequence; The similarity determination module is used to determine the similarity between the current tunnel crack and defect detection data and the historical tunnel crack and defect detection data based on the key feature parameters of the current tunnel crack and defect detection data, the key feature parameters of the historical tunnel crack and defect detection data, and the corresponding weights. The crack damage detection data classification module is used to match the current tunnel crack damage detection data with historical tunnel crack damage detection data based on similarity, and classify the current tunnel crack damage detection data according to the matching results; The tunnel damage level assessment module is used to assess the tunnel damage level based on the key characteristic parameters and classification results of the current tunnel damage detection data. The specific representation of the parameterized data sequence is shown below: L(i)={P0, P1, P2, P3, P4}; In the formula, L(i) represents the parameterized data sequence; P0 represents the row of the crack, P0: {-1, 1}, where P0=1 indicates the crack is located in the upper row, and P0=-1 indicates the crack is located in the lower row; P1 represents the location of the crack, P1: {1, 2, 3}, where P1=1 indicates the crack is located in the sidewall, P1=2 indicates the crack is located in the arch waist, and P1=3 indicates the crack is located in the arch crown; P2 represents the mileage of the crack center; P3 represents the crack length; and P4 represents the crack shape, which is the sine of the angle between the crack centerline and the horizontal line. The similarity between current tunnel crack detection data and historical tunnel crack detection data is calculated using the following formula: ； In the formula For the similarity calculation results, For the first The weights of key feature parameters, The algebraic sum of the key feature parameters is 1. Key feature parameters include location, mileage, length, and shape, with location having a weighting coefficient. =0.2, mileage weighting coefficient =0.3, length weighting coefficient =0.2, shape weight coefficient =0.3, This represents the key characteristic parameters of the tunnel crack detection data for the current period. These represent the key characteristic parameters of historical tunnel crack detection data.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

9. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

Images