Tunnel deterioration evaluation method, system, and storage medium

Abstract

The application provides a tunnel deterioration evaluation method, system and storage medium, and belongs to the technical field of deterioration evaluation, and specifically comprises the following steps: constructing a matching model group according to a matching image analysis model of different historical lining images, determining a matching analysis group of the tunnel by changing the recognition results of the risk positions and the abnormal lining positions in the matching model group in different historical detection periods, taking the position of the worst analysis result belonging to the matching analysis group in any historical detection period as the recognized risk position, and determining a deterioration evaluation processing strategy of the tunnel according to the distribution deviation of the recognized risk positions in different historical detection periods, so that the reliability of the recognition processing of the deterioration risk is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of deterioration evaluation, and particularly relates to a tunnel deterioration evaluation method, system and storage medium. BACKGROUND

[0002] In order to realize the deterioration evaluation processing of the tunnel, the existing technical solution obtains the safety evaluation level of the current tunnel through different combinations of the two indexes of the deterioration degree and the deterioration potential, thereby providing strong support for the early detection and processing of the tunnel disease, but the following technical problems exist:

[0003] When the deterioration of the tunnel is evaluated, due to the differences in humidity and train vibration at different positions of different tunnels, the cracking and block falling of the lining at different positions in the same tunnel and the deterioration of the lining at different positions in different tunnels are different, so if the same deterioration analysis model is used for the deterioration evaluation analysis and processing of the tunnel, the accuracy of the deterioration analysis and processing result cannot be guaranteed.

[0004] To solve the above technical problems, the application provides a tunnel deterioration evaluation method, system and storage medium. SUMMARY

[0005] To achieve the purpose of the application, the application adopts the following technical solutions:

[0006] Specifically, in a first aspect, the application provides a tunnel deterioration evaluation method, which specifically comprises:

[0007] S1 determines the abnormal position of the lining in the tunnel from the lining image of the tunnel, determines the matching image analysis model of different historical lining images and the variable risk position of the abnormal position of the lining from the change of the abnormal position of the lining in the historical lining images between different historical detection periods;

[0008] S2 obtains the distribution data of the variable risk position in the tunnel, and determines whether the lining image variable risk of the tunnel meets the requirements in combination with the detection result of the lining image of the variable risk position, and if so, proceeds to the next step;

[0009] S3 constructs a matching model group according to the matching image analysis model of different historical lining images, and determines the matching analysis group of the tunnel from the identification result of the variable risk position and the abnormal position of the lining in the matching model group in different historical detection periods;

[0010] S4 takes the position of the worst analysis result belonging to the matching analysis group in any historical detection period as the identification risk position, and determines the deterioration evaluation processing strategy of the tunnel from the distribution deviation of the identification risk position in different historical detection periods.

[0011] A further technical solution is that the lining image is determined based on the acquisition results of the tunnel detection equipment.

[0012] A further technical solution is that the abnormal location of the lining is the location where cracks exist in the lining image.

[0013] A further technical solution is that the matching image analysis model of the historical lining image is determined based on the changes of the historical lining image in the previous historical detection period. Specifically, the image analysis model whose deviation from the changes of the historical lining image in the previous historical detection period and the changes of the prediction results of the image analysis model based on the historical lining image in the previous historical detection period as input is within a preset deviation range is used as the matching image analysis model.

[0014] A further technical solution involves determining the location of the risk of change in the abnormal lining position as follows:

[0015] Based on the changes in historical lining images of abnormal lining locations during different historical detection periods, matching image analysis models for different historical lining images are determined.

[0016] Based on the deviation of the matching image analysis model for different historical lining images, the number of historical lining images corresponding to different matching image analysis models is determined.

[0017] The matching image analysis model with the maximum number of corresponding historical lining images is used as the target analysis model. Based on the number of historical lining images corresponding to the target analysis model, it is determined whether the lining anomaly location is a location with a risk of change.

[0018] A further technical solution is that the method for determining the tunnel deterioration assessment and treatment strategy is as follows:

[0019] By analyzing the distribution deviations of identified risk locations in different historical monitoring periods, the number of deviations in identified risk locations between different historical monitoring periods can be determined.

[0020] Based on the number of deviations from other historical monitoring periods in identifying risk locations, the deviation identification period in the historical monitoring period is determined;

[0021] The deterioration assessment and treatment strategy for the tunnel is determined based on the number of deviation identification periods.

[0022] A further technical solution is that the identification deviation period is a historical detection period in which there are identification risk locations compared to other historical monitoring periods.

[0023] On the other hand, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the tunnel degradation assessment method described above when running the computer program.

[0024] On the other hand, the present invention provides a computer storage medium storing a computer program, which, when executed in a computer, causes the computer to perform the aforementioned tunnel degradation assessment method.

[0025] The beneficial effects of this invention are as follows:

[0026] Based on the distribution data of variable risk locations in the tunnel and the detection results of the lining images of variable risk locations, it is determined whether the variable risk of the tunnel lining image meets the requirements. It not only considers the number of variable risk locations in the tunnel, but also the difference in fall risk caused by the difference in the detection results of the lining image. This enables the screening of tunnels with large lining image variable risks from multiple dimensions, and also lays the foundation for further adopting differentiated degradation assessment and processing strategies based on the differences in lining image variable risks.

[0027] Based on the distribution deviation of identified risk locations in different historical inspection periods, a deterioration assessment and treatment strategy for tunnels was determined. This enabled the assessment of the changes in identified risk locations in tunnels over different historical inspection periods, thereby enabling the screening of tunnels with poor patterns of deterioration changes and the determination of differentiated deterioration assessment and treatment strategies. This avoids the technical problem of high risk of fall accidents due to low accuracy of deterioration assessment and treatment results.

[0028] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0029] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0030] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0031] Figure 1 This is a flowchart of a tunnel deterioration assessment method;

[0032] Figure 2This is a flowchart illustrating the method for determining the location of abnormal lining locations with potential risks.

[0033] Figure 3 This is a flowchart illustrating the method for determining the matching analysis group of tunnels;

[0034] Figure 4 This is a flowchart illustrating the method for determining the deterioration assessment and treatment strategy for tunnels. Detailed Implementation

[0035] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0036] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that other elements / components / etc. may exist in addition to the listed elements / components / etc.

[0037] Example 1

[0038] To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, a tunnel deterioration assessment method is provided, which specifically includes:

[0039] S1 uses the tunnel lining image to determine the location of the lining anomaly in the tunnel, and uses the changes in the lining anomaly location in the historical lining images between different historical detection periods to determine the matching image analysis model of different historical lining images and the risk location of the change in the lining anomaly location.

[0040] Furthermore, the lining image is determined based on the acquisition results of the tunnel detection equipment.

[0041] Specifically, the abnormal location of the lining is the location where cracks are present in the lining image.

[0042] It should be noted that the matching image analysis model for the historical lining image is determined based on the changes in the historical lining image from the previous historical detection period. Specifically, the image analysis model whose deviation from the changes in the historical lining image from the previous historical detection period and the changes in the prediction results of the image analysis model based on the historical lining image from the previous historical detection period as input are within a preset deviation range is used as the matching image analysis model.

[0043] In one possible embodiment, if the predicted change of the historical lining image from the previous historical detection period is consistent with the actual predicted result, it is used as the matching image analysis model.

[0044] Specifically, such as Figure 2 As shown, the method for determining the location of the lining anomaly is as follows:

[0045] Based on the changes in historical lining images of abnormal lining locations during different historical detection periods, matching image analysis models for different historical lining images are determined.

[0046] Based on the deviation of the matching image analysis model for different historical lining images, the number of historical lining images corresponding to different matching image analysis models is determined.

[0047] The matching image analysis model with the maximum number of corresponding historical lining images is used as the target analysis model. Based on the number of historical lining images corresponding to the target analysis model, it is determined whether the lining anomaly location is a location with a risk of change.

[0048] Specifically, when the number of historical lining images corresponding to the target analysis model is too large, that is, greater than a certain threshold, it indicates that the variation pattern of the abnormal lining location is relatively fixed, and therefore it can be determined that it does not belong to the variation risk location.

[0049] In another possible embodiment, the method for determining the location of the risk of change in the lining anomaly is as follows:

[0050] Based on the changes in historical lining images of abnormal lining locations during different historical detection periods, matching image analysis models for different historical lining images are determined.

[0051] Based on the deviation of the matching image analysis model for different historical lining images, the number of historical lining images corresponding to different matching image analysis models is determined.

[0052] The model distribution discrepancy ratio is determined by the ratio of the number of matching image analysis models at the lining anomaly location to the number of historical lining images. Based on the model distribution discrepancy ratio, it is determined whether the lining anomaly location is a location with a risk of change.

[0053] Specifically, when the model distribution dispersion ratio is too large, it indicates that there are too many image analysis models at the lining anomaly location. Therefore, the lining anomaly location can be directly identified as a change risk location. Specifically, it can be determined by a threshold. If the value is greater than the threshold, it is considered a change risk location.

[0054] Furthermore, the distribution data of the variable risk locations in the tunnel includes the number of variable risk locations.

[0055] S2 acquires the distribution data of the variable risk locations in the tunnel, and combines it with the detection results of the lining image of the variable risk locations to determine that the variable risk of the tunnel lining image meets the requirements, and then proceeds to the next step.

[0056] Specifically, determining that the risk of changes in the tunnel lining image meets the requirements includes:

[0057] The number of variable risk locations is determined based on the distribution data of variable risk locations in the tunnel;

[0058] Based on the detection results of the lining images at different variable risk locations, the fall risk locations among the variable risk locations are determined;

[0059] By analyzing the distribution data of the fall risk locations, it is determined whether the risk of changes in the tunnel lining image meets the requirements.

[0060] Specifically, the image of the lining at the change risk location is used as the input to the image classification model. Based on the output of the image classification model, i.e. whether there is a fall risk, it is determined whether the change risk location is a fall risk location.

[0061] Understandably, when the number of potential fall locations is too high, i.e., more than 10 potential fall locations, it can be determined that the tunnel lining image variation risk does not meet the requirements.

[0062] Furthermore, when the risk of changes in the tunnel lining image does not meet the requirements, the worst value of the degradation assessment results of the lining images at different lining locations under different image analysis models is used to determine the degradation assessment results for different lining locations.

[0063] Specifically, the lining image is used as the input of the image analysis model. The output of the image analysis model, i.e. the degradation assessment result, is between 0 and 1. The larger the degradation assessment result, the higher the degradation risk of the lining image.

[0064] S3 constructs a matching model group based on the matching image analysis model of different historical lining images, and determines the matching analysis group of the tunnel based on the identification results of the change risk location and the lining anomaly location in the matching model group during different historical detection periods;

[0065] It should be noted that the matching model group is a group of models constructed by freely combining the matching image analysis models of all historical lining images.

[0066] Specifically, such as Figure 3 As shown, the method for determining the matching analysis group of the tunnel is as follows:

[0067] Using the matching image analysis model of the location of the change risk and the location of the lining anomaly, the historical lining images of the matching image analysis model in the matching model group are determined and used as matching images;

[0068] The identification percentage of the risk of change is determined by the average proportion of the matching images of different risk of change locations in the historical lining images; the identification percentage of the lining anomaly locations is determined by the average proportion of the matching images of different lining anomaly locations in the historical lining images.

[0069] The identification percentages of the variable risk locations and the identification percentages of the lining anomaly locations are used to determine whether the matching model group is a matching analysis group.

[0070] Specifically, the matching analysis group is the matching model group with the largest proportion of identification of abnormal lining locations within a preset proportion range and the largest proportion of identification of change risk locations.

[0071] S4 will use the position of the worst analysis result belonging to the matching analysis group in any historical detection period as the risk identification position, and determine the deterioration assessment and treatment strategy of the tunnel based on the distribution deviation of the risk identification positions in different historical detection periods.

[0072] Specifically, such as Figure 4 As shown, the method for determining the deterioration assessment and treatment strategy for the tunnel is as follows:

[0073] By analyzing the distribution deviations of identified risk locations in different historical monitoring periods, the number of deviations in identified risk locations between different historical monitoring periods can be determined.

[0074] Based on the number of deviations from other historical monitoring periods in identifying risk locations, the deviation identification period in the historical monitoring period is determined;

[0075] The deterioration assessment and treatment strategy for the tunnel is determined based on the number of deviation identification periods.

[0076] Furthermore, the identification deviation period refers to a historical detection period in which there are identified risk locations compared to other historical monitoring periods.

[0077] It should be noted that the tunnel deterioration assessment and processing strategy is determined based on the number of deviation identification time periods, specifically including:

[0078] When the number of deviation identification time periods exceeds the preset threshold for the number of identification time periods, the worst value of the deterioration evaluation processing result of the lining image at different lining positions under different image analysis models in the matching analysis group is used to determine the deterioration evaluation processing result of different lining positions.

[0079] When the number of deviation identification time periods is not greater than the preset threshold for the number of identification time periods, the deterioration assessment results of different lining positions are determined according to the preset strategy based on the deterioration assessment results of the lining images of different lining positions under different image analysis models in the matching analysis group.

[0080] It is understood that the preset strategy is to take the degradation assessment result with the most image analysis models that have the same degradation assessment result as the degradation assessment result of the lining position.

[0081] It should be further explained that when the number of deviation identification time periods is not greater than the preset threshold for the number of identification time periods, if the number of identified risk locations is large, i.e., greater than the threshold, the degradation assessment result of the identified risk locations will be set as the worst value of the degradation assessment processing result of the lining image under different image analysis models in the matching analysis group. Other locations will be determined using the preset strategy. When the number of identified risk locations is small, all locations will be determined using the preset strategy.

[0082] Example 2

[0083] On the other hand, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the tunnel degradation assessment method described above when running the computer program.

[0084] In another embodiment, determining that the risk of lining image variation in the tunnel meets the requirements specifically includes:

[0085] The number of variable risk locations is determined based on the distribution data of variable risk locations in the tunnel;

[0086] It should be noted that in the above steps, it is necessary to determine whether the number of variable risk locations meets the requirements. When the number of variable risk locations is large, it can be directly determined that the variable risk of the tunnel lining image meets the requirements. Specifically, it can be determined by exceeding a preset threshold.

[0087] Furthermore, even if the number of variable risk locations meets the requirements, if the number of variable risk locations is within a certain range, the number is still relatively small. Therefore, even if a fall occurs, the impact on the overall safety status of the tunnel is controllable. Thus, it can be directly determined that the variable risk of the tunnel lining image meets the requirements.

[0088] If the number of variable risk locations is not too small, it is necessary to further determine the interval between variable risk locations. If there is a unit area with a number of variable risk locations greater than the preset number of locations, it is also determined that the variable risk of the tunnel lining image does not meet the requirements. Only when there is no unit area with a number of variable risk locations greater than the preset number of locations can the fall risk location be determined.

[0089] Based on the detection results of the lining images at different variable risk locations, the fall risk locations among the variable risk locations are determined;

[0090] It should be noted that if there are too many fall risk locations or no fall risk locations, then no other data needs to be determined, and it can be directly determined whether the tunnel lining image change risk meets the requirements.

[0091] Specifically, if there are no locations with a risk of falling, it can be directly determined that the risk of changes in the tunnel lining image meets the requirements. However, if there are locations with a risk of falling, and the number of such locations is large, then the risk of changes in the lining image must be large. Therefore, it can be directly determined that the risk of changes in the tunnel lining image does not meet the requirements.

[0092] By analyzing the distribution data of the fall risk locations, the proportion of fall risk locations among the variable risk locations is determined. Combined with the number of variable risk locations, it is determined whether the variable risk of the tunnel lining image meets the requirements.

[0093] It is understandable that when the number of variable risk locations is too large and the proportion of fall risk locations among the variable risk locations is too large, a threshold method can be used to determine whether it is too many or too large. In this case, it can be determined that the variable risk of the tunnel lining image does not meet the requirements. In other cases, it can be determined that the variable risk of the tunnel lining image meets the requirements.

[0094] In one possible embodiment, even if the number of variable risk locations is not too large and the proportion of fall risk locations among the variable risk locations is not too large, the variable risk value can be determined by multiplying the preset proportional factor corresponding to the number of variable risk locations with the proportion of fall risk locations among the variable risk locations. When the variable risk value is greater than 0.2, it is determined that the variable risk of the tunnel lining image does not meet the requirements.

[0095] Example 3

[0096] On the other hand, the present invention provides a computer storage medium storing a computer program, which, when executed in a computer, causes the computer to perform the aforementioned tunnel degradation assessment method.

[0097] Optionally, the method for determining the deterioration assessment and treatment strategy for the tunnel is as follows:

[0098] By analyzing the distribution deviations of identified risk locations in different historical monitoring periods, the number of deviations in identified risk locations between different historical monitoring periods can be determined.

[0099] It should be noted that in the above steps, it is necessary to determine whether the number of identified risk locations meets the requirements and whether the average number of deviations of identified risk locations between different historical monitoring periods meets the requirements. It can be understood that when the number of identified risk locations is large or the average number of deviations of identified risk locations between different historical monitoring periods is large, in order to prevent the risk of falling due to the risk locations caused by identification deviations, the worst value of the degradation assessment processing result of the lining images of different lining locations under different image analysis models in the matching analysis group is used to determine the degradation assessment processing result of different lining locations.

[0100] Specifically, if the number of identified risk locations is too high or the average number of deviations in the number of identified risk locations between different historical monitoring periods is too high, then the requirements are not met, and a threshold method can be used to determine whether the number is too high.

[0101] It should also be noted that when the number of identified risk locations is small and the number of deviations in the number of identified risk locations between different historical monitoring periods is within the preset range, it indicates that the risk of falling due to the risk location caused by the identification deviation is small. Therefore, the degradation assessment results of different lining locations are determined according to the preset strategy based on the degradation assessment results of the lining images of different lining locations under different image analysis models in the matching analysis group.

[0102] Based on the number of deviations from other historical monitoring periods in identifying risk locations, the deviation identification period in the historical monitoring period is determined;

[0103] For example, when the number of identification deviation periods is large, the risk of identification deviation is high. Therefore, the worst value of the deterioration assessment processing result of the lining image at different lining positions under different image analysis models in the matching analysis group is used to determine the deterioration assessment processing result of different lining positions. Specifically, a threshold method is used to determine the result. When the number of identification deviation periods is small, the process proceeds to the next step.

[0104] Based on the number of deviation identification periods and the number of identified risk locations, an identification risk value is determined, and a deterioration assessment and treatment strategy for the tunnel is determined based on the identification risk value.

[0105] In one possible embodiment, the risk value can be determined by the product or mean of the number of deviation identification periods and the number of risk identification locations, or by a mathematical model.

[0106] Specifically, when the identified risk value is greater than the preset risk threshold, the worst value of the degradation assessment processing result of the lining image at different lining locations under different image analysis models in the matching analysis group is used to determine the degradation assessment processing result of different lining locations. In other cases, the degradation assessment processing result of the lining image at different lining locations under different image analysis models in the matching analysis group is used to determine the degradation assessment processing result of different lining locations according to the preset strategy.

[0107] It should also be noted that the value range of the degradation assessment result is between 0 and 1. When there are a large number of degradation risk locations with a degradation assessment result greater than 0.6, a threshold method can be used to determine the specific degradation assessment result for different lining locations. The worst value of the degradation assessment result of the lining image under different image analysis models is used to determine the degradation assessment result for different lining locations.

[0108] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0109] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0110] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for assessing tunnel deterioration, characterized in that, Specifically, it includes: The location of lining anomalies in the tunnel is determined by the lining images of the tunnel. The changes in the lining anomaly locations in historical lining images between different historical detection periods are used to determine the matching image analysis model for different historical lining images and the risk location of the changes in the lining anomaly locations. Obtain the distribution data of the variable risk locations in the tunnel, and combine it with the detection results of the lining image of the variable risk locations. When it is determined that the variable risk of the lining image of the tunnel meets the requirements, proceed to the next step. A matching model group is constructed based on the matching image analysis model of different historical lining images. The matching analysis group of the tunnel is determined by the identification results of the change risk location and the lining anomaly location in the matching model group during different historical detection periods. The worst analysis result belonging to the matching analysis group in any historical detection period is used as the risk identification location. Based on the distribution deviation of the identified risk locations in different historical detection periods, the deterioration assessment and treatment strategy of the tunnel is determined. The matching model group is a group of models constructed by freely combining the matching image analysis models of all historical lining images; The method for determining the matching analysis group of the tunnel is as follows: Using the matching image analysis model of the location of the change risk and the location of the lining anomaly, the historical lining images of the matching image analysis model in the matching model group are determined and used as matching images; The identification percentage of the risk of change is determined by the average proportion of the matching images of different risk of change locations in the historical lining images; the identification percentage of the lining anomaly locations is determined by the average proportion of the matching images of different lining anomaly locations in the historical lining images. The identification percentages of the variable risk locations and the identification percentages of the lining anomaly locations are used to determine whether the matching model group is a matching analysis group.

2. The tunnel deterioration assessment method as described in claim 1, characterized in that, The lining image is determined based on the results acquired by the tunnel detection equipment.

3. The tunnel deterioration assessment method as described in claim 1, characterized in that, The abnormal location of the lining is the location where cracks are found in the lining image.

4. The tunnel deterioration assessment method as described in claim 1, characterized in that, The matching image analysis model for the historical lining images is determined based on the changes in the historical lining images compared to the previous historical detection period.

5. The tunnel deterioration assessment method as described in claim 1, characterized in that, The method for determining the location of the abnormal lining location with potential for change is as follows: Based on the changes in historical lining images of abnormal lining locations during different historical detection periods, matching image analysis models for different historical lining images are determined. Based on the deviation of the matching image analysis model for different historical lining images, the number of historical lining images corresponding to different matching image analysis models is determined. The matching image analysis model with the maximum number of corresponding historical lining images is used as the target analysis model. Based on the number of historical lining images corresponding to the target analysis model, it is determined whether the lining anomaly location is a location with a risk of change.

6. The tunnel deterioration assessment method as described in claim 1, characterized in that, The distribution data of variable risk locations in the tunnel includes the number of variable risk locations.

7. The tunnel deterioration assessment method as described in claim 1, characterized in that, Determining that the risk of image variation in the tunnel lining meets the requirements specifically includes: The number of variable risk locations is determined based on the distribution data of variable risk locations in the tunnel; Based on the detection results of the lining images at different variable risk locations, the fall risk locations among the variable risk locations are determined; By analyzing the distribution data of the fall risk locations, it is determined whether the risk of changes in the tunnel lining image meets the requirements.

8. The tunnel deterioration assessment method as described in claim 1, characterized in that, The method for determining the deterioration assessment and treatment strategy for the tunnel is as follows: By analyzing the distribution deviations of identified risk locations in different historical monitoring periods, the number of deviations in identified risk locations between different historical monitoring periods can be determined. Based on the number of deviations from other historical monitoring periods in identifying risk locations, the deviation identification period in the historical monitoring period is determined; The deterioration assessment and treatment strategy for the tunnel is determined based on the number of deviation identification periods.

9. A computer system, comprising: A memory and processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a tunnel degradation assessment method according to any one of claims 1-8.

10. A computer storage medium storing a computer program thereon, which, when executed in a computer, causes the computer to perform a tunnel degradation assessment method according to any one of claims 1-8.

Images