Tunnel water leakage area identification method, device, equipment and medium

Abstract

The application provides a tunnel water leakage area identification method, device, equipment and medium. The method comprises the following steps: obtaining target water leakage data of a target tunnel; inputting the target water leakage data into a preset sensitive area detection model to obtain sensitive areas of the target tunnel output by the sensitive area detection model and types corresponding to each sensitive area; inputting the target water leakage data into a preset water leakage screening model to obtain water leakage areas of the target tunnel output by the water leakage screening model; and identifying actual water leakage areas of the target tunnel based on the sensitive areas of the target tunnel, the types corresponding to each sensitive area and the water leakage areas of the target tunnel. The application can improve the accuracy of tunnel water leakage area identification.

Description

Technical Field

[0001] This invention relates to the field of water leakage detection technology, and in particular to a method, device, equipment and medium for identifying water leakage areas in tunnels. Background Technology

[0002] As tunnels are used continuously after construction, water leakage will inevitably occur. This leakage will further erode and damage the tunnel, affecting its structural stability and potentially causing safety accidents. Therefore, it is crucial to identify leakage areas promptly and accurately in order to facilitate tunnel maintenance.

[0003] In the face of interference from the complex background of tunnels, extracting areas of water leakage first requires filtering out image data containing leakage. Currently, a common method is to use the YOLO network to locate these areas. However, using the traditional YOLO network for leakage area filtering easily leads to numerous false alarms, meaning non-leakage areas are incorrectly identified as leakage areas, thus affecting the accuracy of tunnel leakage identification. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for identifying water seepage areas in tunnels, thereby improving the accuracy of identifying water seepage areas in tunnels.

[0005] In a first aspect, embodiments of the present invention provide a method for identifying tunnel seepage areas, including:

[0006] Obtain target leakage water data for the target tunnel;

[0007] The target leakage data is input into a preset sensitive area detection model to obtain the sensitive areas of the target tunnel output by the sensitive area detection model, as well as the type corresponding to each sensitive area; wherein, the sensitive area detection model is trained based on leakage data of different types of sensitive areas in the tunnel and each type of sensitive area;

[0008] The target leakage data is input into a preset leakage screening model to obtain the leakage area of ​​the target tunnel output by the leakage screening model; wherein, the leakage screening model is trained based on the tunnel's leakage data and the corresponding leakage area.

[0009] Based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage areas of the target tunnel, the actual leakage areas of the target tunnel are identified.

[0010] In one possible implementation, before identifying the actual leakage area of ​​the target tunnel based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage area of ​​the target tunnel, the method further includes:

[0011] Obtain the confidence level of the type corresponding to each sensitive region output by the sensitive region detection model;

[0012] All sensitive areas in the target tunnel whose confidence levels are within a preset range are identified as the true sensitive areas of the target tunnel.

[0013] Based on the actual sensitive areas, update the sensitive areas of the target tunnel and the type corresponding to each sensitive area.

[0014] In one possible implementation, based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage areas of the target tunnel, the actual leakage areas of the target tunnel are identified, including:

[0015] Based on the type corresponding to the sensitive area of ​​the target tunnel, determine the first probability of water leakage occurring in the sensitive area of ​​the target type; wherein, the target type is determined based on the type corresponding to the sensitive area of ​​the target tunnel;

[0016] Based on the sensitive area of ​​the target tunnel, the first probability of water leakage occurring in the sensitive area of ​​the target type, and the water leakage area of ​​the target tunnel, calculate the second probability of water leakage occurring in the sensitive area of ​​each target type.

[0017] Based on the second probability, the actual water leakage area of ​​the target tunnel is determined.

[0018] In one possible implementation, based on the sensitive area of ​​the target tunnel, the first probability of water leakage occurring in the sensitive area of ​​the target type, and the water leakage area of ​​the target tunnel, a second probability of water leakage occurring in the sensitive area of ​​each target type is calculated, including:

[0019] Based on the sensitive areas of the target tunnel, the sensitive areas corresponding to each target type of the target tunnel are determined, and according to the sensitive areas corresponding to each target type of the target tunnel and the leakage areas of the target tunnel, the third probability of leakage occurring in the sensitive areas of each target type is calculated respectively.

[0020] Based on the first probability and the third probability of water leakage occurring in the sensitive area of ​​the target type, the second probability of water leakage in the target tunnel occurring in the sensitive area of ​​each target type is calculated.

[0021] In one possible implementation, determining the actual leakage area of ​​the target tunnel based on the second probability includes:

[0022] For each target type of sensitive area, determine whether the second probability that the leakage of the target tunnel occurs in the sensitive area of ​​that target type is greater than a preset probability;

[0023] If the second probability of a sensitive area of ​​a target type is less than or equal to a preset probability, then the sensitive area corresponding to that target type is determined as a false alarm area.

[0024] If the second probability of a sensitive area of ​​the target type is greater than the preset probability, then the sensitive area corresponding to the target type is determined as the actual leakage area of ​​the target tunnel.

[0025] In one possible implementation, based on the sensitive area corresponding to each target type of the target tunnel and the leakage area of ​​the target tunnel, a third probability of leakage occurring in the sensitive area of ​​each target type is calculated, including:

[0026] According to the expression: Calculate the third probability of water leakage occurring in the sensitive area for each target type;

[0027] In the formula, P(B|A) i A represents the third probability of water leakage occurring within the sensitive area of ​​the i-th target type. i B represents the bounding box of the sensitive area corresponding to the i-th target type, and B represents the bounding box of the water leakage area of ​​the target tunnel.

[0028] In one possible implementation, based on the first probability and the third probability of water leakage occurring in the sensitive area of ​​the target type, a second probability of water leakage occurring in the sensitive area of ​​each target type is calculated, including:

[0029] According to the expression: Calculate the second probability that the water leakage of the target tunnel occurs in the sensitive area for each target type;

[0030] In the formula, P(A) i |B) represents the second probability that the water leakage of the target tunnel occurs in the sensitive area of ​​the i-th target type, P(A) i P(B|A) represents the first probability of water leakage occurring in the sensitive area of ​​the i-th target type. i P(A) represents the third probability of water leakage occurring within the sensitive area of ​​the i-th target type. j P(B|A) represents the first probability of water leakage occurring in the sensitive area of ​​the j-th target type. j) represents the third probability of water leakage occurring in the sensitive area of ​​the j-th target type, and n represents the set of all target types in the target tunnel.

[0031] Secondly, embodiments of the present invention provide a tunnel seepage area identification device, comprising:

[0032] The acquisition module is used to acquire target seepage water data of the target tunnel;

[0033] The detection module is used to input the target leakage data into a preset sensitive area detection model to obtain the sensitive areas of the target tunnel output by the sensitive area detection model, as well as the type corresponding to each sensitive area; wherein, the sensitive area detection model is trained based on leakage data of different types of sensitive areas in the tunnel and each type of sensitive area;

[0034] The filtering module is used to input the target leakage data into a preset leakage filtering model to obtain the leakage area of ​​the target tunnel output by the leakage filtering model; wherein, the leakage filtering model is trained based on the tunnel's leakage data and the corresponding leakage area.

[0035] The identification module is used to identify the actual leakage area of ​​the target tunnel based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage area of ​​the target tunnel.

[0036] Thirdly, embodiments of the present invention provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect or any possible implementation thereof.

[0037] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect or any possible implementation thereof.

[0038] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0039] This invention employs a sensitive area detection model and a leakage screening model to detect target leakage data in a target tunnel. This allows for the identification of sensitive areas within the target tunnel where leakage may occur, the corresponding type of each sensitive area, and identified leakage areas that have already occurred. Furthermore, by considering the sensitive areas, their corresponding types, and the leakage areas, the actual leakage areas in the target tunnel can be identified. This approach fully considers sensitive areas prone to leakage within the target tunnel, eliminating false alarms caused by identifying only leakage areas, thus achieving accurate identification of tunnel leakage areas and improving the accuracy of leakage area identification. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart illustrating the implementation of a method for identifying seepage areas in tunnels, as provided in an embodiment of the present invention.

[0042] Figure 2 This is a pie-shaped schematic diagram of water leakage occurring in different types of sensitive areas provided in the embodiments of the present invention;

[0043] Figure 3 This is a flowchart illustrating the implementation of another method for identifying tunnel seepage areas provided in this embodiment of the invention.

[0044] Figure 4 These are schematic diagrams of different types of sensitive areas provided in embodiments of the present invention;

[0045] Figure 5 This is a schematic diagram of a water leakage identification result provided in an embodiment of the present invention;

[0046] Figure 6 This is a schematic diagram of another water leakage identification result provided in an embodiment of the present invention;

[0047] Figure 7 This is a schematic diagram of the tunnel seepage area identification device provided in an embodiment of the present invention;

[0048] Figure 8 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0049] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0050] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0051] The inventors have discovered that when using a YOLO network to identify water leakage areas in tunnels, non-leakage areas are sometimes mistakenly identified as leakage areas. This results in a large number of false alarms in the identification results, affecting the accuracy of water leakage identification. Therefore, a water leakage area identification method that can accurately identify water leakage areas is needed.

[0052] To reduce false alarms and improve the accuracy of identifying leakage areas, the inventors discovered that tunnel leakage occurs in certain patterns, typically appearing in relatively fixed areas on the tunnel lining surface. Based on this, in this embodiment, two YOLO networks are used to detect leakage data. One YOLO network detects areas prone to leakage (sensitive areas in the tunnel), while the other detects actual leakage areas. The actual leakage areas in the tunnel are then determined by combining the detected sensitive areas and the identified leakage areas. This method reduces false alarms caused by focusing solely on identifying leakage areas, accurately identifying the areas where leakage actually occurs in the tunnel.

[0053] Figure 1 The implementation flowchart of the tunnel seepage area identification method provided in the embodiments of the present invention is described in detail below:

[0054] Step S101: Obtain target seepage water data for the target tunnel.

[0055] In this embodiment, the leakage data can be images acquired during a defect inspection of the target tunnel. These images can be obtained by taking pictures based on actual detection markers marked in the tunnel.

[0056] Optionally, the acquired images can be preprocessed. For example, the image size can be adjusted according to preset requirements to obtain the target leakage data; or the image can be segmented, and the segmented image can be used as the target leakage data. This improves the accuracy of subsequent detection using the model.

[0057] Step S102: Input the target leakage data into the preset sensitive area detection model to obtain the sensitive areas of the target tunnel output by the sensitive area detection model, as well as the type corresponding to each sensitive area; wherein, the sensitive area detection model is trained based on the leakage data of different types of sensitive areas in the tunnel and each type of sensitive area.

[0058] In this embodiment, the preset sensitive area detection model can be obtained by training the YOLOv8 (You Only Look Once version 8) model using leakage water data from different types of sensitive areas in the tunnel and for each type of sensitive area.

[0059] Here, by using a sensitive area detection model to detect the target leakage data, we can obtain the sensitive areas of the target tunnel in the leakage data, as well as the type and confidence level of each sensitive area. The detected sensitive area can be represented as a bounding box, with the area inside the bounding box being the corresponding sensitive area; the confidence level indicates the degree of credibility of the type corresponding to the sensitive area of ​​the target tunnel.

[0060] Before the sensitive region detection model outputs the sensitive regions, along with their corresponding types and confidence levels, each confidence level is evaluated. Sensitive regions with confidence levels greater than a preset confidence level are considered reliable and their corresponding data can be output; sensitive regions with confidence levels less than or equal to the preset confidence level are considered unreliable and their corresponding data will not be output. The preset confidence level can be 0.25, 0.3, 0.4, or 0.5, etc.

[0061] Step S103: Input the target leakage data into the preset leakage screening model to obtain the leakage area of ​​the target tunnel output by the leakage screening model; wherein, the leakage screening model is trained based on the leakage data of the tunnel and the corresponding leakage area.

[0062] In this embodiment, the preset leakage screening model can be obtained by training a YOLOv8 model using the leakage data of the tunnel and the corresponding leakage areas. Here, by detecting the target leakage data through the leakage screening model, the leakage areas of the target tunnel in the target leakage data can be obtained. The detected leakage area can also be represented as a bounding box, with the corresponding leakage area inside the bounding box.

[0063] Step S104: Based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage areas of the target tunnel, the actual leakage areas of the target tunnel are identified.

[0064] In this embodiment, by considering the type corresponding to each sensitive area and comparing the sensitive areas and leakage areas of the target tunnel, the actual leakage areas of the target tunnel can be accurately identified. For example, the actual leakage area can be determined by the overlapping areas of the sensitive areas and leakage areas of the target tunnel; alternatively, the probability of leakage occurring in the sensitive areas can be calculated based on the sensitive areas and leakage areas of the target tunnel, and the actual leakage area of ​​the target tunnel can be determined based on the calculated probability.

[0065] This invention employs a sensitive area detection model and a leakage screening model to detect target leakage data in a target tunnel. This allows for the identification of sensitive areas within the target tunnel where leakage may occur, the corresponding type of each sensitive area, and identified leakage areas that have already occurred. Furthermore, by considering the sensitive areas, their corresponding types, and the leakage areas, the actual leakage areas in the target tunnel can be identified. This approach fully considers sensitive areas prone to leakage within the target tunnel, eliminating false alarms caused by identifying only leakage areas, thus achieving accurate identification of tunnel leakage areas and improving the accuracy of leakage area identification.

[0066] In some embodiments, before identifying the actual leakage area of ​​the target tunnel based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage area of ​​the target tunnel, the confidence level of the type corresponding to each sensitive area output by the sensitive area detection model can be obtained first; all sensitive areas in the target tunnel whose confidence levels are within a preset range are determined as the real sensitive areas of the target tunnel; and then the sensitive areas of the target tunnel and the type corresponding to each sensitive area are updated according to the real sensitive areas.

[0067] In this embodiment, the sensitive region detection model also outputs the confidence score of the type corresponding to each sensitive region. This confidence score represents the credibility of the type corresponding to each sensitive region output by the model. The preset confidence score within the model may be set low to ensure that all possible sensitive regions can be output. However, the detection and identification of sensitive regions and their corresponding types may contain errors. Therefore, the sensitive regions output by the model can be further filtered based on the confidence score of the sensitive regions to retain the true sensitive regions and delete the remaining sensitive regions that are unlikely to be true sensitive regions. This achieves the updating of the sensitive regions of the target tunnel and the type corresponding to each sensitive region.

[0068] Here, the confidence level typically ranges from 0 to 1. For example, the preset range can be any of the following: 0.5 to 1, 0.6 to 1, 0.75 to 1, and 0.8 to 1, etc.

[0069] In some embodiments, based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage areas of the target tunnel, the actual leakage areas of the target tunnel are identified. First, based on the type corresponding to the sensitive areas of the target tunnel, a first probability of leakage occurring in the sensitive areas of the target type can be determined; wherein, the target type is determined based on the type corresponding to the sensitive areas of the target tunnel. Then, based on the sensitive areas of the target tunnel, the first probability of leakage occurring in the sensitive areas of the target type, and the leakage areas of the target tunnel, a second probability of leakage occurring in the sensitive areas of each target type is calculated. Finally, based on the second probability, the actual leakage areas of the target tunnel are determined.

[0070] In this embodiment, the probability of water leakage occurring in sensitive areas of the target tunnel can be calculated to screen for leakage areas and identify the actual leakage areas. Specifically, a first probability of water leakage occurring in a sensitive area is calculated. Then, conditional probabilities are calculated using the first probability of water leakage occurring in sensitive areas of the target tunnel and the target type, along with the actual leakage areas of the target tunnel. This yields a second probability of water leakage occurring in sensitive areas of each target type, allowing for the screening of leakage areas and sensitive areas of each target type. This accurately identifies the areas in the target tunnel where water leakage actually occurs, reducing the interference of false alarms.

[0071] Here, the types of sensitive areas in the tunnel differ, and the probability of water leakage in each sensitive area also differs. Therefore, we can first determine the initial probability of water leakage in a sensitive area based on its type. Specifically, the event that a sensitive area of ​​type i might leak water can be represented by A. i To represent this, the first probability that the i-th type of sensitive area may leak water can be represented by P(A i ) is used to represent this.

[0072] Optionally, before determining the first probability of water leakage in the sensitive areas of the target tunnel based on the type of sensitive area corresponding to the target tunnel, water leakage data of tunnels similar to the target tunnel can be obtained first. By analyzing and statistically processing this water leakage data, the types and probabilities of water leakage-prone areas in the tunnel can be obtained. Therefore, based on the statistically determined types and probabilities of water leakage-prone areas, the first probability corresponding to each type of sensitive area in the target tunnel can be determined.

[0073] See Figure 2 The diagram shown is a pie chart illustrating water leakage in different types of sensitive areas. Figure 2The data shows the probability of water leakage in five types of sensitive areas: 68.01% for circumferential joints, 12.03% for longitudinal joints, 8.13% for cross joints, 8.77% for grouting holes, and 3.06% for bolt holes. Based on these statistics, the first probability of water leakage in each type of sensitive area within the target tunnel can be determined.

[0074] Optionally, based on the second probability, the actual leakage area of ​​the target tunnel can be determined. This can be done by determining whether the second probability of the leakage of the target tunnel occurring in the sensitive area of ​​that target type is greater than a preset probability for each type of target sensitive area. If the second probability of the sensitive area of ​​that target type is less than or equal to the preset probability, then the sensitive area corresponding to that target type is determined as a false alarm area. If the second probability of the sensitive area of ​​that target type is greater than the preset probability, then the sensitive area corresponding to that target type is determined as the actual leakage area of ​​the target tunnel.

[0075] In this embodiment, if the second probability of a sensitive area of ​​a target type is less than or equal to a preset probability, it indicates that the possibility of water leakage occurring in the sensitive area of ​​that target type is low. Therefore, the sensitive area of ​​that target type can be identified as a false alarm area and deleted. If the second probability of a sensitive area of ​​a target type is greater than the preset probability, it indicates that water leakage is very likely to occur in the sensitive area of ​​that target type, thereby allowing the actual water leakage area of ​​the target tunnel to be screened.

[0076] For example, the preset probability can be any of the following: 0%, 5%, 10%, 15%, 20%, 25%, and 30%, etc. If the preset probability is set to 0, it means that the sensitive area corresponding to the target type with a second probability of 0 is unlikely to leak water, and it can be identified as a false alarm area and deleted; while the sensitive area corresponding to the target type with a second probability greater than 0 is very likely to leak water, and the sensitive area corresponding to the target type with a second probability greater than 0 can be identified as the actual water leakage area of ​​the target tunnel.

[0077] In some embodiments, see Figure 3The flowchart of another method for identifying tunnel leakage areas shows that, based on the first probability of leakage occurring in the sensitive areas of the target tunnel and the sensitive areas of the target type, and the leakage areas of the target tunnel, the second probability of leakage occurring in the sensitive areas of each target type is calculated. First, based on the sensitive areas of the target tunnel, the sensitive areas corresponding to each target type of the target tunnel are determined. Then, based on the sensitive areas corresponding to each target type of the target tunnel and the leakage areas of the target tunnel, the third probability of leakage occurring in the sensitive areas of each target type is calculated. Finally, based on the first and third probabilities of leakage occurring in the sensitive areas of the target type, the second probability of leakage occurring in the sensitive areas of each target type is calculated.

[0078] In this embodiment, the second probability of water leakage in the target tunnel occurring in the sensitive area for each target type can be calculated by calculating conditional probabilities. Here, Bayes' theorem can be used for probability calculation. Bayes' theorem describes how the probability of a hypothesis changes given relevant evidence or information; its core idea is to calculate unknown probabilities using known probabilities.

[0079] For example, using prior knowledge (such as the probability of random event A occurring P(A) and the probability of random event B occurring P(B)), observed outcomes (such as the probability of random event B occurring given that random event A has occurred P(B|A)), and Bayes' theorem, the posterior probability (P(A|B)) can be calculated to obtain the probability of random event A occurring given that random event B has occurred. The formula for this calculation can be expressed as:

[0080] Accordingly, in this embodiment, the event that water leakage may occur in the i-th type of sensitive area in the target tunnel can be represented by random event A. i In other words, the event that a leak has occurred in the leak area detected by the leak screening model can be represented by random event B. Each random event A... i If the events are mutually exclusive, then the formula for the total probability of water leakage occurring in the target tunnel can be: In the formula, P(B) represents the probability of water leakage in the target tunnel, and P(A) represents the probability of water leakage in the target tunnel. i |B) represents the probability that water leakage in the target tunnel occurs in the i-th type of sensitive area, and N represents all types of sensitive areas where water leakage may occur, which may include: circumferential joint area, longitudinal joint area, cross joint area, grouting hole area and bolt hole area.

[0081] Optionally, in this embodiment, based on the first and third probabilities of water leakage occurring in the sensitive areas of each target type, the second probability of water leakage in the target tunnel occurring in the sensitive areas of each target type is calculated, which can be based on the expression: Calculate the second probability that water leakage from the target tunnel occurs in the sensitive area for each target type; where P(A i |B) represents the second probability that the water leakage in the target tunnel occurs in the sensitive area of ​​the i-th target type, P(A) i P(B|A) represents the first probability of water leakage occurring in the sensitive area of ​​the i-th target type. i P(A) represents the third probability of water leakage occurring within the sensitive area of ​​the i-th target type. j P(B|A) represents the first probability of water leakage occurring in the sensitive area of ​​the j-th target type. j ) represents the third probability of water leakage occurring in the sensitive area of ​​the j-th target type, and n represents the set of all target types in the target tunnel.

[0082] In some feasible embodiments, the sensitive region detection model detects only one sensitive region, and the target type corresponding to this sensitive region is 'a'. Then, it can be determined according to the expression: P(A) a |B)=P(B|A a ), calculate the second probability that water leakage from the target tunnel occurs in a sensitive area of ​​this target type. Where P(A a |B) represents the second probability that water leakage in the target tunnel occurs in a sensitive area of ​​target type a, P(B|A) a ) represents the third probability of water leakage occurring within a sensitive area of ​​target type a, where a represents the target type corresponding to the sensitive area detected by the sensitive area detection model.

[0083] When a sensitive region detection model detects two sensitive regions simultaneously in the same image (water leakage data), and the two sensitive regions correspond to different types, with one sensitive region corresponding to target type 'a' and the other sensitive region corresponding to target type 'b', then the following expression can be used: Calculate the second probability that water leakage in the target tunnel occurs in a sensitive area of ​​that target type. Here, i represents the target type corresponding to the sensitive area detected by the sensitive area detection model, and its value can be a or b, and n represents the set of all target types in the target tunnel, including a and b.

[0084] It can be seen that by obtaining the third probability of water leakage occurring within the sensitive area of ​​each target type, the second probability of water leakage in the target tunnel occurring within the sensitive area of ​​each target type can be accurately calculated. For a given area, the third probability of water leakage occurring within the sensitive area of ​​each target type is actually the probability of the target tunnel leaking within that area, given that the area is a sensitive area of ​​the target type. Therefore, the third probability can be calculated using the sensitive area corresponding to each target type of the target tunnel and the water leakage area of ​​the target tunnel.

[0085] Optionally, based on the sensitive areas and leakage areas corresponding to each target type of the target tunnel, the third probability of leakage occurring within the sensitive areas of each target type is calculated, which can be based on the expression: Calculate the third probability of water leakage occurring in the sensitive area for each target type; where P(B|A) i A represents the third probability of water leakage occurring within the sensitive area of ​​the i-th target type. i B represents the bounding box of the sensitive area corresponding to the i-th target type, and B represents the bounding box of the water seepage area of ​​the target tunnel.

[0086] In this embodiment, the third probability of water leakage occurring within the sensitive area of ​​each target type can be calculated using the intersection-union ratio (IUR) formula. This IUR formula measures the degree of overlap between the bounding boxes of the sensitive area and the leakage area. The intersection region is the common area of ​​the two bounding boxes, which can be obtained by calculating the intersection coordinates of the two bounding boxes in the horizontal and vertical directions, determining the length and width of the common region, and then multiplying them. The union region is the area corresponding to the two bounding boxes, which can be obtained by calculating the sum of the areas of the two bounding boxes and then subtracting the area of ​​the intersection region. The IUR value ranges from 0 to 1, where 0 indicates no overlap and 1 indicates complete overlap.

[0087] In some feasible embodiments, see Figure 4 The diagram illustrates different types of sensitive areas, which may include: circumferential seam areas, longitudinal seam areas, cross seam areas, grouting hole areas, and bolt hole areas. Random event A. i This includes: random event A1 where water leakage occurs in the circumferential joint area, random event A2 where water leakage occurs in the longitudinal joint area, random event A3 where water leakage occurs in the cross joint area, random event A4 where water leakage occurs in the grouting hole area, and random event A5 where water leakage occurs in the bolt hole area.

[0088] The probability of water leakage in the circumferential joint area is 68.01%, the probability of water leakage in the longitudinal joint area is 12.03%, the probability of water leakage in the cross joint area is 8.13%, the probability of water leakage in the grouting hole area is 8.77%, and the probability of water leakage in the bolt hole area is 3.06%. Therefore, the probabilities of each random event are: P(A1) = 68.01%, P(A2) = 12.03%, P(A3) = 8.13%, P(A4) = 8.77%, and P(A5) = 3.06%.

[0089] See Figure 5 The diagram shown illustrates a water leakage identification result. Figure 5 There are two sensitive regions: a longitudinal seam region with a confidence level of 0.84 and a bolt hole region with a confidence level of 0.64. Figure 5 There are two leakage areas, one of which overlaps with the longitudinal joint area, and the other overlaps with the bolt hole area. Therefore, we can use the following expression: Calculate the second probability that water leakage in the target tunnel occurs in the longitudinal joint region, and according to the expression: Calculate the second probability that water leakage in the target tunnel occurs in the bolt hole area.

[0090] The intersection-exchange-union (IUU) formula yields the following probabilities: the third probability of water leakage occurring in the longitudinal joint area is P(B|A2) = 0.20, and the third probability of water leakage occurring in the bolt hole area is P(B|A5) = 0.13. Therefore, the second probability of water leakage in the target tunnel occurring in the longitudinal joint area is P(A2|B) = 0.86, and the second probability of water leakage in the target tunnel occurring in the bolt hole area is P(A5|B) = 0.14. If the preset probability is 0, then the final determined actual water leakage areas of the target tunnel are the identified longitudinal joint area and bolt hole area.

[0091] See Figure 6 Another schematic diagram showing the results of water leakage identification is shown in [the diagram]. Figure 6 There are three sensitive areas: a longitudinal seam area and two grouting hole areas. Figure 6 There are two leakage areas, both of which overlap with the longitudinal joint area but do not overlap with the grouting hole area. Therefore, it can be directly determined that no leakage occurred in the two grouting hole areas. The leakage areas detected by the model also correspond to a confidence level (e.g., ...). Figure 6 As shown, the confidence levels for the two leakage areas are 0.88 and 0.89, respectively. This confidence level represents the reliability of the leakage areas output by the model. The leakage areas can also be updated based on this confidence level. The specific update method can refer to the update method for sensitive areas mentioned above, and will not be elaborated further here.

[0092] It can also be based on the expression: Calculate the second probability that water leakage in the target tunnel occurs in the longitudinal joint area.

[0093] The intersection-exchange-union (IoU) formula can be used to calculate the third probability of water leakage occurring in the sensitive area corresponding to the longitudinal joint region as P(B|A2) = 0.528. Therefore, the second probability of water leakage in the target tunnel occurring in the longitudinal joint region is P(A2|B) = P(B|A2) = 0.528. If the preset probability is 0, the final determined actual water leakage area of ​​the target tunnel is the identified longitudinal joint region, while the grouting hole region can be marked as a false alarm area and deleted.

[0094] This invention employs a sensitive area detection model and a leakage screening model to detect leakage data in a target tunnel. This allows for the identification of potentially leaking sensitive areas within the tunnel, their corresponding types, and identified leakage areas that have already occurred. By considering these sensitive areas, their types, and the identified leakage areas, the actual leakage areas in the target tunnel can be identified. This approach fully considers sensitive areas prone to leakage, eliminating false alarms caused by relying solely on leakage area identification, thus achieving accurate identification of leakage areas and improving the accuracy of leakage area detection. Specifically, the sensitive area detection model uses confidence scores to screen for sensitive areas, retaining genuinely sensitive areas and removing those with low probability of being genuine. By calculating the posterior probability using Bayes' theorem, the conditional probability of leakage occurring in each type of sensitive area can be accurately calculated, quantifying the event of leakage in a sensitive area and thus accurately screening for actual leakage areas in the target tunnel, improving the accuracy of leakage area detection.

[0095] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0096] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0097] Figure 7 A schematic diagram of the tunnel seepage area identification device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0098] like Figure 7 As shown, the tunnel water leakage area identification device 70 includes:

[0099] Module 71 is used to acquire target seepage water data of the target tunnel;

[0100] The detection module 72 is used to input the target leakage data into the preset sensitive area detection model to obtain the sensitive areas of the target tunnel output by the sensitive area detection model, as well as the type corresponding to each sensitive area; wherein, the sensitive area detection model is trained based on the leakage data of different types of sensitive areas in the tunnel and each type of sensitive area;

[0101] The filtering module 73 is used to input the target leakage data into the preset leakage filtering model to obtain the leakage area of ​​the target tunnel output by the leakage filtering model; wherein, the leakage filtering model is trained based on the tunnel leakage data and the corresponding leakage area.

[0102] The identification module 74 is used to identify the actual leakage area of ​​the target tunnel based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage area of ​​the target tunnel.

[0103] In one possible implementation, the identification module 74 is also used for:

[0104] Obtain the confidence score of the type corresponding to each sensitive region output by the sensitive region detection model;

[0105] All sensitive areas in the target tunnel whose confidence levels are within a preset range are identified as the true sensitive areas of the target tunnel.

[0106] Based on the actual sensitive areas, update the sensitive areas of the target tunnel and the type corresponding to each sensitive area.

[0107] In one possible implementation, the identification module 74 is specifically used for:

[0108] Based on the type of the sensitive area corresponding to the target tunnel, determine the first probability of water leakage occurring in the sensitive area of ​​the target type; whereby the target type is determined based on the type of the sensitive area corresponding to the target tunnel.

[0109] Based on the first probability of water leakage occurring in the sensitive areas of the target tunnel and the sensitive areas of the target type, and the water leakage areas of the target tunnel, calculate the second probability of water leakage occurring in the sensitive areas of each target type.

[0110] Based on the second probability, the actual leakage area of ​​the target tunnel is determined.

[0111] In one possible implementation, the identification module 74 is specifically used for:

[0112] Based on the sensitive areas of the target tunnel, the sensitive areas corresponding to each target type of the target tunnel are determined, and according to the sensitive areas corresponding to each target type of the target tunnel and the leakage areas of the target tunnel, the third probability of leakage occurring in the sensitive areas of each target type is calculated respectively.

[0113] Based on the first and third probabilities of water leakage occurring in the sensitive areas of each target type, the second probability of water leakage occurring in the sensitive areas of each target type is calculated.

[0114] In one possible implementation, the identification module 74 is specifically used for:

[0115] For each target type of sensitive area, determine whether the second probability that the leakage of the target tunnel occurs in the sensitive area of ​​that target type is greater than the preset probability;

[0116] If the second probability of a sensitive area of ​​a target type is less than or equal to a preset probability, then the sensitive area corresponding to that target type is determined as a false alarm area.

[0117] If the second probability of a sensitive area of ​​a target type is greater than the preset probability, then the sensitive area corresponding to that target type is determined as the actual leakage area of ​​the target tunnel.

[0118] In one possible implementation, the identification module 74 is specifically used for:

[0119] According to the expression: Calculate the third probability of water leakage occurring in the sensitive area for each target type;

[0120] In the formula, P(B|A) i A represents the third probability of water leakage occurring within the sensitive area of ​​the i-th target type. i B represents the bounding box of the sensitive area corresponding to the i-th target type, and B represents the bounding box of the water seepage area of ​​the target tunnel.

[0121] In one possible implementation, the identification module 74 is specifically used for:

[0122] According to the expression: Calculate the second probability that water leakage from the target tunnel occurs in the sensitive area for each target type;

[0123] In the formula, P(A) i |B) represents the second probability that the water leakage in the target tunnel occurs in the sensitive area of ​​the i-th target type, P(A) i P(B|A) represents the first probability of water leakage occurring in the sensitive area of ​​the i-th target type. iP(A) represents the third probability of water leakage occurring within the sensitive area of ​​the i-th target type. j P(B|A) represents the first probability of water leakage occurring in the sensitive area of ​​the j-th target type. j ) represents the third probability of water leakage occurring in the sensitive area of ​​the j-th target type, and n represents the set of all target types in the target tunnel.

[0124] Figure 8 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 8 As shown, the electronic device 80 of this embodiment includes: a processor 81, a memory 82, and a computer program 83 stored in the memory 82 and executable on the processor 81. When the processor 81 executes the computer program 83, it implements the steps in the various tunnel seepage area identification method embodiments described above, for example... Figure 1 Steps S101 to S104 are shown. Alternatively, when processor 81 executes computer program 83, it implements the functions of each module in the above-described device embodiments, for example... Figure 7 The functions of modules 71 to 74 are shown.

[0125] For example, computer program 83 can be divided into one or more modules / units, one or more of which are stored in memory 82 and executed by processor 81 to complete the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 83 in electronic device 80. For example, computer program 83 can be divided into... Figure 7 Modules 71 to 74 are shown.

[0126] Electronic device 80 may include, but is not limited to, processor 81 and memory 82. Those skilled in the art will understand that... Figure 8 This is merely an example of electronic device 80 and does not constitute a limitation on electronic device 80. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0127] The processor 81 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0128] The memory 82 can be an internal storage unit of the electronic device 80, such as a hard disk or RAM. The memory 82 can also be an external storage device of the electronic device 80, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 82 can include both internal and external storage units of the electronic device 80. The memory 82 is used to store computer programs and other programs and data required by the electronic device. The memory 82 can also be used to temporarily store data that has been output or will be output.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0130] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0131] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0132] In the embodiments provided by this invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0133] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0134] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0135] If integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0136] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for identifying water seepage areas in tunnels, characterized in that, include: Obtain target leakage water data for the target tunnel; The target leakage data is input into a preset sensitive area detection model to obtain the sensitive areas of the target tunnel output by the sensitive area detection model, as well as the type corresponding to each sensitive area; wherein, the sensitive area detection model is trained based on leakage data of different types of sensitive areas in the tunnel and each type of sensitive area; The target leakage data is input into a preset leakage screening model to obtain the leakage area of ​​the target tunnel output by the leakage screening model; wherein, the leakage screening model is trained based on the tunnel's leakage data and the corresponding leakage area. Based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage areas of the target tunnel, the actual leakage areas of the target tunnel are identified, including: Based on the type corresponding to the sensitive area of ​​the target tunnel, determine the first probability of water leakage occurring in the sensitive area of ​​the target type; wherein, the target type is determined based on the type corresponding to the sensitive area of ​​the target tunnel; Based on the sensitive areas of the target tunnel, the sensitive areas corresponding to each target type of the target tunnel are determined, and according to the sensitive areas corresponding to each target type of the target tunnel and the leakage areas of the target tunnel, the third probability of leakage occurring in the sensitive areas of each target type is calculated respectively. According to the expression: Calculate the third probability of water leakage occurring in the sensitive area for each target type; In the formula, Indicates the first The third probability of water leakage occurring in sensitive areas of a certain target type. Indicates the first The bounding boxes of sensitive regions corresponding to different target types. The bounding box represents the area of ​​water leakage in the target tunnel; According to the expression: Calculate the second probability that the water leakage of the target tunnel occurs in the sensitive area for each target type; In the formula, This indicates that the water leakage in the target tunnel occurred in the first... The second probability of a sensitive region for a target type. Indicates the first The first probability of water leakage occurring in sensitive areas of this target type. Indicates the first The third probability of water leakage occurring in sensitive areas of a certain target type. Indicates the first The first probability of water leakage occurring in sensitive areas of this target type. Indicates the first The third probability of water leakage occurring in sensitive areas of a certain target type. This represents the set of all target types within the target tunnel; Based on the second probability, the actual water leakage area of ​​the target tunnel is determined.

2. The method for identifying tunnel seepage areas according to claim 1, characterized in that, Before identifying the actual leakage area of ​​the target tunnel based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage area of ​​the target tunnel, the method further includes: Obtain the confidence level of the type corresponding to each sensitive region output by the sensitive region detection model; All sensitive areas in the target tunnel whose confidence levels are within a preset range are identified as the true sensitive areas of the target tunnel. Based on the actual sensitive areas, update the sensitive areas of the target tunnel and the type corresponding to each sensitive area.

3. The method for identifying tunnel seepage areas according to claim 1 or 2, characterized in that, Based on the second probability, the actual water leakage area of ​​the target tunnel is determined, including: For each target type of sensitive area, determine whether the second probability that the leakage of the target tunnel occurs in the sensitive area of ​​that target type is greater than a preset probability; If the second probability of a sensitive area of ​​a target type is less than or equal to a preset probability, then the sensitive area corresponding to that target type is determined as a false alarm area. If the second probability of a sensitive area of ​​the target type is greater than the preset probability, then the sensitive area corresponding to the target type is determined as the actual leakage area of ​​the target tunnel.

4. A device for identifying tunnel seepage areas, characterized in that, include: The acquisition module is used to acquire target seepage water data of the target tunnel; The detection module is used to input the target leakage data into a preset sensitive area detection model to obtain the sensitive areas of the target tunnel output by the sensitive area detection model, as well as the type corresponding to each sensitive area; wherein, the sensitive area detection model is trained based on leakage data of different types of sensitive areas in the tunnel and each type of sensitive area; The filtering module is used to input the target leakage data into a preset leakage filtering model to obtain the leakage area of ​​the target tunnel output by the leakage filtering model; wherein, the leakage filtering model is trained based on the tunnel's leakage data and the corresponding leakage area. The identification module is used to identify the actual leakage area of ​​the target tunnel based on the sensitive areas of the target tunnel and the type corresponding to each sensitive area, as well as the leakage area of ​​the target tunnel. The identification module is specifically used for: Based on the type corresponding to the sensitive area of ​​the target tunnel, determine the first probability of water leakage occurring in the sensitive area of ​​the target type; wherein, the target type is determined based on the type corresponding to the sensitive area of ​​the target tunnel; Based on the sensitive areas of the target tunnel, the sensitive areas corresponding to each target type of the target tunnel are determined, and according to the sensitive areas corresponding to each target type of the target tunnel and the leakage areas of the target tunnel, the third probability of leakage occurring in the sensitive areas of each target type is calculated respectively. According to the expression: Calculate the third probability of water leakage occurring in the sensitive area for each target type; In the formula, Indicates the first The third probability of water leakage occurring in sensitive areas of a certain target type. Indicates the first The bounding boxes of sensitive regions corresponding to different target types. The bounding box represents the area of ​​water leakage in the target tunnel; According to the expression: Calculate the second probability that the water leakage of the target tunnel occurs in the sensitive area for each target type; In the formula, This indicates that the water leakage in the target tunnel occurred in the first... The second probability of a sensitive region for a target type. Indicates the first The first probability of water leakage occurring in sensitive areas of this target type. Indicates the first The third probability of water leakage occurring in sensitive areas of a certain target type. Indicates the first The first probability of water leakage occurring in sensitive areas of this target type. Indicates the first The third probability of water leakage occurring in sensitive areas of a certain target type. This represents the set of all target types within the target tunnel; Based on the second probability, the actual water leakage area of ​​the target tunnel is determined.

5. An electronic device comprising a memory and a processor, the memory for storing a computer program, the processor for calling and running the computer program stored in the memory, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 3 above.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 3 above.

Images