Tunnel construction monitoring system and monitoring method
By using machine learning models to identify the seepage area in the image acquisition and processing system in the tunnel, the problem of difficult to monitor the seepage in the tunnel wall during tunnel construction is solved, and the safety of the tunnel structure and construction efficiency are improved.
Patent Information
- Application Number
- CN202410981344.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing tunnel construction monitoring system is difficult to monitor in a timely manner when water seepage in the inner wall of the tunnel, affecting the stability and safety of the tunnel structure.
The image acquisition module in the tunnel, image preprocessing module, image feature extraction module, water seepage monitoring model training module and data analysis and alarm module are used to collect image data in the tunnel through the camera, image preprocessing, feature extraction and water seepage area identification, and the machine is used. The learning model automatically identifies and locates the seepage area and triggers the alarm system.
Timely monitoring and early warning of water seepage in the tunnel, improving the safety and maintenance efficiency of tunnel construction.
Smart Images

Figure CN118941953A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of tunnel construction monitoring, and more specifically, to a tunnel construction monitoring system and a monitoring method. Background Art
[0002] Tunnel construction monitoring involves many aspects to ensure that tunnel projects are carried out in accordance with design requirements, construction specifications and safety standards. The following are some common monitoring aspects:
[0003] Geological and groundwater monitoring: During tunnel construction, geological conditions and groundwater conditions may have an impact on construction. Therefore, it is necessary to monitor factors such as geological structure, formation stability, rock and soil properties, and groundwater level and water pressure.
[0004] Surface deformation monitoring: Tunnel construction may cause deformation of the ground surface, such as settlement, cracks, etc. By monitoring the surface deformation, timely measures can be taken to avoid damage to surrounding buildings and facilities.
[0005] Tunnel internal structure monitoring: The stability and safety of the tunnel internal structure are key. Monitor the deformation, cracks and support system of the tunnel wall, vault, foundation and other structures to ensure construction quality and project safety.
[0006] Groundwater leakage monitoring: Tunnel projects may be affected by groundwater, so it is necessary to monitor whether there is groundwater leakage and water accumulation inside the tunnel, and to take waterproofing measures in a timely manner.
[0007] Safety monitoring: Monitor the safety of the construction site, including the safety of construction workers, equipment and possible dangerous factors during the construction process, and take appropriate measures to ensure construction safety.
[0008] The above are some common aspects of tunnel construction monitoring. The specific monitoring content and methods will vary according to the specific conditions and requirements of the project.
[0009] The document with the prior art publication number CN110081857A provides a real-time surface monitoring system and a monitoring method for a shield construction tunnel. The device is provided with a positioning calibration device and a mobile monitoring device; a surface reflector is attached to the road surface above the construction tunnel, and a building reflector is attached to the street buildings above the construction tunnel to form a fixed reflection reference point. A measuring camera on the outside of a fixed measuring shell is used to obtain a track set on the road surface above the construction tunnel and a mobile robot to obtain a relative position image of the road surface reference point. When the ground sinks or rises due to the disturbance of the shield construction, the mobile monitoring device sinks or rises, and the measuring block is in a balanced state under its own weight, so that the specific up and down floating of the measuring block can be obtained, so that the surface vibration situation can be obtained, and the purpose of real-time surface monitoring of the construction tunnel is achieved. The device has a simple structure and accurate measurement data.
[0010] Although the above-mentioned prior art solution can achieve the relevant beneficial effects through the structure of the prior art, it still has the following defects: when the device is used, due to the construction in the tunnel, in the case of groundwater, water seepage will occur on the inner wall of the tunnel. Since the device is not convenient for timely monitoring the location of water seepage in the tunnel, the water seepage affects the stability and safety of the tunnel structure, and the practicality is poor.
[0011] In view of this, we propose a tunnel construction monitoring system and monitoring method. Summary of the invention
[0012] 1. Technical issues to be solved
[0013] The purpose of the present application is to provide a tunnel construction monitoring system and a monitoring method, which solve the technical problems raised in the above-mentioned background technology and achieve the technical effect of facilitating timely monitoring of the location where water seepage occurs in the tunnel.
[0014] 2. Technical solution
[0015] The present application provides a tunnel construction monitoring system and a monitoring method, including: an in-tunnel image acquisition module, an in-tunnel image preprocessing module, an in-tunnel image feature extraction module, an in-tunnel water seepage monitoring model training module, and a data analysis and alarm module.
[0016] Tunnel image acquisition module: The tunnel image acquisition module collects image data of various positions in the tunnel through a camera;
[0017] Tunnel image preprocessing module: The tunnel image preprocessing module preprocesses the collected images, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing;
[0018] Tunnel image feature extraction module: The tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, color changes, etc., from the pre-processed image;
[0019] Tunnel water seepage monitoring model training module: The tunnel water seepage monitoring model training module uses the processed data and extracted features to train a machine learning model and analyze the collected images to automatically identify and locate water seepage areas;
[0020] Data analysis and alarm module: The data analysis and alarm module transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered.
[0021] As an optional solution to the technical solution of the present application document, the image acquisition module in the tunnel collects image data of various positions in the tunnel through a camera, and the camera is installed on a mobile platform to obtain an all-round view during tunnel construction. The collected image data needs to be transmitted to the central processing system in real time, and the received image data needs to be securely stored for subsequent analysis and retrieval.
[0022] As an optional solution of the technical solution of the present application document, the image preprocessing module in the tunnel preprocesses the collected image, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing. The image enhancement: brightness adjustment: adjust the brightness of the image according to the lighting conditions in the tunnel to make the overall brightness of the image more uniform;
[0023] The edge detection: edge sharpening: strengthening the edge information of the image through a sharpening filter (such as the Laplacian operator) to make the edge clearer.
[0024] As an optional solution of the technical solution of the present application document, the tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, color changes, etc., from the preprocessed image, and detects through color change: water seepage usually causes changes in the color of the inner wall of the tunnel. The feature extraction module can identify potential water seepage areas by comparing the difference between the color value of each pixel and the reference value;
[0025] Through texture analysis: The texture of the seepage surface often changes. The difference between the seepage area and the normal area can be detected through the texture analysis algorithm of the local binary pattern;
[0026] Identification by shape change: Water stains and water marks may cause the shape of surrounding objects to change. The feature extraction module is able to identify possible signs of water seepage by detecting contour changes or shape changes of the area.
[0027] As an optional solution to the technical solution of the present application document, the tunnel water seepage monitoring model training module uses the processed data and extracted features to train the machine learning model of the neural network, analyzes the collected images, and is used to automatically identify and locate the water seepage area. By continuously adjusting the parameters of the model, it is able to accurately identify and locate the water seepage area.
[0028] As an optional solution of the technical solution of the present application document, the data analysis and alarm module transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered and relevant personnel are notified to handle it. It can realize automatic monitoring and early warning of water seepage in the tunnel, and improve the safety and maintenance efficiency during tunnel construction.
[0029] A tunnel construction monitoring system and a monitoring method, comprising the following steps:
[0030] S1. During tunnel construction, a mobile platform is used to drive a camera to move in the tunnel. At this time, the camera collects image data at various locations in the tunnel. The collected image data needs to be transmitted to the central processing system in real time. The received image data needs to be securely stored for subsequent analysis and retrieval;
[0031] S2. Use the tunnel image preprocessing module to preprocess the collected images, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing. Image enhancement: Brightness adjustment: adjust the brightness of the image according to the lighting conditions in the tunnel to make the overall brightness of the image more uniform.
[0032] Edge detection: Edge sharpening: Use sharpening filters (such as Laplacian operator) to enhance the edge information of the image and make the edges clearer;
[0033] S3, then the tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, color changes, etc., from the preprocessed image, and detects through color change: Water seepage usually causes the color of the tunnel inner wall to change. The feature extraction module can identify potential water seepage areas by comparing the difference between the color value of each pixel and the reference value;
[0034] Through texture analysis: The texture of the seepage surface often changes. The difference between the seepage area and the normal area can be detected through the texture analysis algorithm of the local binary pattern;
[0035] Identification by shape change: Water stains and water marks may cause the shape of surrounding objects to change. The feature extraction module can identify possible signs of water seepage by detecting contour changes or shape changes of the area;
[0036] S4. The tunnel seepage monitoring model training module uses the processed data and extracted features to train the machine learning model of the neural network, analyzes the collected images, and is used to automatically identify and locate the seepage area. By continuously adjusting the parameters of the model, the model can accurately identify and locate the seepage area.
[0037] S5. Then the data analysis and alarm module transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered and relevant personnel are notified to handle it. It can realize automatic monitoring and early warning of water seepage in the tunnel, and improve the safety and maintenance efficiency during tunnel construction.
[0038] 3. Beneficial effects
[0039] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
[0040] 1. The present application adopts technical means such as an image acquisition module in a tunnel, thereby effectively solving the technical problems in the prior art, and further realizing the effect of detecting water seepage conditions or trends in the tunnel by collecting image data in real time during tunnel construction and analyzing the images using a water seepage monitoring model in the tunnel, thereby ensuring the safety of the tunnel structure and construction.
[0041] 2. This application realizes that the camera is driven to move in the tunnel to collect image data by setting a driving mechanism. At the same time, by setting a transmission mechanism, the detection seat is driven to rotate while the moving seat moves, thereby realizing the collection of a large range of images in the tunnel and improving the practicality of the device.
[0042] 3. By setting an adjustment seat, the present application can drive the detection seat to be retracted into the storage slot when the device is not in use. At the same time, under the action of the protective plate, the camera on the detection seat is protected to increase the service life of the device. By setting an arc-shaped rack, the cleaning bar can be driven to swing, the camera is cleaned, and the image quality is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 A schematic diagram of the overall structure of a tunnel construction monitoring system and a monitoring method disclosed in a preferred embodiment of the present application, and a flow chart of water seepage monitoring in a tunnel;
[0044] Figure 2 This is a schematic diagram of the overall structure of a tunnel construction monitoring system and a monitoring method disclosed in a preferred embodiment of the present application;
[0045] Figure 3 A schematic cross-sectional view of the overall structure of a tunnel construction monitoring system and a monitoring method disclosed in a preferred embodiment of the present application;
[0046] Figure 4 A schematic cross-sectional view of a moving base and a driving mechanism structure of a tunnel construction monitoring system and a monitoring method disclosed in a preferred embodiment of the present application;
[0047] Figure 5 A schematic cross-sectional view of the structure of the adjustment seat and the transmission mechanism of the tunnel construction monitoring system and the monitoring method disclosed in a preferred embodiment of the present application;
[0048] Figure 6 A schematic cross-sectional view of a detection seat structure of a tunnel construction monitoring system and a monitoring method disclosed in a preferred embodiment of the present application;
[0049] Explanation of the numbers in the figure: 1. Moving seat; 2. Driving mechanism; 3. Adjusting seat; 4. Transmission mechanism; 5. Detection seat; 201. Roller group; 202. Double-axis motor; 203. Driving wheel; 204. Rotating shaft; 205. Transmission wheel; 301. Electric push rod; 101. Arc rack; 102. Storage slot; 103. Protective plate; 401. Transmission rod; 402. Driven wheel; 403. Universal joint; 404. Adjusting wheel; 405. Incomplete bevel gear; 501. Cleaning strip; 502. Gear. DETAILED DESCRIPTION
[0050] The present application is further described in detail below in conjunction with the accompanying drawings.
[0051] Reference Figure 1 A tunnel construction monitoring system and monitoring method, comprising: an in-tunnel image acquisition module, an in-tunnel image preprocessing module, an in-tunnel image feature extraction module, an in-tunnel water seepage monitoring model training module, and a data analysis and alarm module.
[0052] Tunnel image acquisition module: The tunnel image acquisition module collects image data at various locations in the tunnel through a camera;
[0053] Tunnel image preprocessing module: The tunnel image preprocessing module preprocesses the collected images, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing;
[0054] Tunnel image feature extraction module: The tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, color changes, etc., from the preprocessed images;
[0055] Tunnel water seepage monitoring model training module: The tunnel water seepage monitoring model training module uses the processed data and extracted features to train a machine learning model to analyze the collected images for automatic identification and location of water seepage areas;
[0056] Data analysis and alarm module: The data analysis and alarm module transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered.
[0057] The image acquisition module in the tunnel collects image data from various locations in the tunnel through cameras. The cameras are installed on a mobile platform to obtain a full range of views during tunnel construction. The collected image data needs to be transmitted to the central processing system in real time. The received image data needs to be securely stored for subsequent analysis and retrieval.
[0058] The image preprocessing module in the tunnel preprocesses the collected images, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing. Image enhancement: Brightness adjustment: adjust the brightness of the image according to the lighting conditions in the tunnel to make the overall brightness of the image more uniform;
[0059] Edge detection: Edge sharpening: Enhance the edge information of the image through sharpening filters such as the Laplacian operator to make the edges clearer.
[0060] The tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, and color changes, from the preprocessed images. Detection through color changes: Water seepage usually causes changes in the color of the tunnel wall. The feature extraction module can identify potential water seepage areas by comparing the color value of each pixel with the reference value.
[0061] Through texture analysis: The texture of the seepage surface often changes. The difference between the seepage area and the normal area can be detected through the texture analysis algorithm of the local binary pattern;
[0062] Identification by shape change: Water stains and water marks may cause the shape of surrounding objects to change. The feature extraction module is able to identify possible signs of water seepage by detecting contour changes or shape changes of the area.
[0063] The tunnel seepage monitoring model training module uses the processed data and extracted features to train the neural network's machine learning model to analyze the collected images for automatic identification and location of water seepage areas. By continuously adjusting the model's parameters, it can accurately identify and locate water seepage areas.
[0064] The data analysis and alarm module transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered and relevant personnel are notified to handle it. It can realize automatic monitoring and early warning of water seepage in the tunnel, and improve the safety and maintenance efficiency during tunnel construction.
[0065] A tunnel construction monitoring system and a monitoring method, comprising the following steps:
[0066] S1. During tunnel construction, a mobile platform is used to drive a camera to move in the tunnel. At this time, the camera collects image data at various locations in the tunnel. The collected image data needs to be transmitted to the central processing system in real time. The received image data needs to be securely stored for subsequent analysis and retrieval;
[0067] S2. Use the tunnel image preprocessing module to preprocess the collected images, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing. Image enhancement: Brightness adjustment: adjust the brightness of the image according to the lighting conditions in the tunnel to make the overall brightness of the image more uniform.
[0068] Edge detection: Edge sharpening: Use sharpening filters such as the Laplacian operator to enhance the edge information of the image and make the edges clearer;
[0069] S3, then the tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, color changes, etc., from the preprocessed image, and detects through color change: Water seepage usually causes the color of the tunnel inner wall to change. The feature extraction module can identify potential water seepage areas by comparing the difference between the color value of each pixel and the reference value;
[0070] Through texture analysis: The texture of the seepage surface often changes. The difference between the seepage area and the normal area can be detected through the texture analysis algorithm of the local binary pattern;
[0071] Identification by shape change: Water stains and water marks may cause the shape of surrounding objects to change. The feature extraction module can identify possible signs of water seepage by detecting contour changes or shape changes of the area;
[0072] S4. The tunnel seepage monitoring model training module uses the processed data and extracted features to train the machine learning model of the neural network, analyzes the collected images, and is used to automatically identify and locate the seepage area. By continuously adjusting the parameters of the model, the model can accurately identify and locate the seepage area.
[0073] S5. Then the data analysis and alarm module transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered and relevant personnel are notified to handle it. It can realize automatic monitoring and early warning of water seepage in the tunnel, and improve the safety and maintenance efficiency during tunnel construction.
[0074] Reference Figure 2 and Figure 3 A tunnel construction monitoring system and a monitoring method, comprising a moving seat 1, a driving mechanism 2, an adjusting seat 3, a transmission mechanism 4, and a detection seat 5,
[0075] A driving mechanism 2 is rotatably connected to the moving seat 1 , an adjusting seat 3 is slidably arranged inside the moving seat 1 , a transmission mechanism 4 is rotatably connected to the adjusting seat 3 , and a detection seat 5 is connected to the transmission mechanism 4 .
[0076] Reference Figure 4The driving mechanism 2 includes two roller groups 201, which are rotatably connected to the moving seat 1. A dual-axis motor 202 is connected to the middle of one roller group 201, and a driving wheel 203 is connected to the middle of the other roller group 201. A rotating shaft 204 is arranged above the driving wheel 203. The rotating shaft 204 and the moving seat 1 are rotatably connected. Transmission wheels 205 are fixedly arranged at both ends of the rotating shaft 204. The external transmission wheel 205 is meshed with the driving wheel 203 for transmission. The transmission wheel 205 realizes a linkage effect.
[0077] Reference Figure 5 An electric push rod 301 is connected between the adjustment seat 3 and the moving seat 1. The electric push rod 301 realizes the function of driving the detection seat 5 to be moved out and stored.
[0078] Reference Figure 5 The transmission mechanism 4 includes a transmission rod 401, one end of which is rotatably connected to the adjustment seat 3, a driven wheel 402 is connected to the outer wall of the transmission rod 401, and the driven wheel 402 is movably engaged with the transmission wheel 205 for transmission, a universal joint 403 is rotatably connected to the inner wall of the transmission rod 401, and one end of the universal joint 403 is connected to the adjustment wheel 404, and the adjustment wheel 404 is engaged with the arc-shaped rack 101 connected to the moving seat 1 for transmission, and a storage groove 102 is opened on one side of the moving seat 1, and a protective plate 103 is slidably provided at the opening of the storage groove 102. The protective plate 103 realizes the protective function.
[0079] Reference Figure 6 A camera is mounted on the detection seat 5, and a cleaning bar 501 is rotatably connected to one side of the detection seat 5. One side of the cleaning bar 501 is in sliding contact with the camera lens. One end of the cleaning bar 501 is fixedly connected with two gears 502. The gears 502 are meshed with an incomplete bevel gear 405 connected to one end of the universal joint 403 located in the detection seat 5. The cleaning bar 501 can clean the camera lens.
[0080] The implementation principle of a tunnel construction monitoring system and a monitoring method according to an embodiment of the present application is as follows: when the tunnel is under construction, the device is first moved into the tunnel, and then the protective plate 103 is pulled open, and then the electric push rod 301 is used to drive the adjustment seat 3 to move, so that the detection seat 5 moves out of the storage slot 102, and then the double-axis motor 202 is used to drive the roller group 201 to rotate, so that the device moves. At this time, the driving wheel 203 on the roller group 201 drives the rotating shaft 204 connected to the transmission wheel 205 to rotate, and then the transmission rod 401 connected to the driven wheel 402 is driven to rotate through another transmission wheel 205, thereby driving the detection seat 5 to rotate, and collecting images of the inside of the tunnel;
[0081] Then, under the action of the arc-shaped rack 101, the adjusting wheel 404 drives the universal joint 403 to rotate, so that the universal joint 403 drives the incomplete bevel gear 405 to rotate, and the incomplete bevel gear 405 drives the cleaning strip 501 connected to the two gears 502 to swing, so as to clean the camera lens;
[0082] Then, the camera collects image data from various locations in the tunnel. The collected image data needs to be transmitted to the central processing system in real time. The received image data needs to be securely stored for subsequent analysis and retrieval;
[0083] Use the tunnel image preprocessing module to preprocess the collected images, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing. Image enhancement: Brightness adjustment: adjust the brightness of the image according to the lighting conditions in the tunnel to make the overall brightness of the image more uniform
[0084] Edge detection: Edge sharpening: Use sharpening filters such as the Laplacian operator to enhance the edge information of the image and make the edges clearer;
[0085] Then, the tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, and color changes, from the preprocessed images. Color change detection: Water seepage usually causes changes in the color of the tunnel wall. The feature extraction module can identify potential water seepage areas by comparing the color value of each pixel with the reference value.
[0086] Through texture analysis: The texture of the seepage surface often changes. The difference between the seepage area and the normal area can be detected through the texture analysis algorithm of the local binary pattern;
[0087] Identification by shape change: Water stains and water marks may cause the shape of surrounding objects to change. The feature extraction module can identify possible signs of water seepage by detecting contour changes or shape changes of the area;
[0088] The tunnel seepage monitoring model training module uses the processed data and extracted features to train the neural network machine learning model, analyze the collected images, and automatically identify and locate the seepage area. By continuously adjusting the model parameters, it can accurately identify and locate the seepage area.
[0089] The data analysis and alarm module then transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered and relevant personnel are notified to handle it. This can achieve automatic monitoring and early warning of water seepage in the tunnel, thereby improving the safety and maintenance efficiency during tunnel construction.
Claims
1. A tunnel construction monitoring system and monitoring method, comprising: an in-tunnel image acquisition module, an in-tunnel image preprocessing module, an in-tunnel image feature extraction module, an in-tunnel water seepage monitoring model training module, and a data analysis and alarm module, characterized in that: Tunnel image acquisition module: The tunnel image acquisition module collects image data of various positions in the tunnel through a camera; Tunnel image preprocessing module: The tunnel image preprocessing module preprocesses the collected images, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing; Tunnel image feature extraction module: The tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, color changes, etc., from the pre-processed image; Tunnel water seepage monitoring model training module: The tunnel water seepage monitoring model training module uses the processed data and extracted features to train a machine learning model and analyze the collected images to automatically identify and locate water seepage areas; Data analysis and alarm module: The data analysis and alarm module transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered.
2. The tunnel construction monitoring system and monitoring method according to claim 1, characterized in that: The image acquisition module in the tunnel collects image data at various locations in the tunnel through a camera. The camera is installed on a mobile platform to obtain a full-range view during tunnel construction. The collected image data needs to be transmitted to the central processing system in real time, and the received image data needs to be securely stored for subsequent analysis and retrieval.
3. The tunnel construction monitoring system and monitoring method according to claim 1, characterized in that: The tunnel image preprocessing module preprocesses the collected images, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing. The image enhancement: brightness adjustment: adjusts the brightness of the image according to the lighting conditions in the tunnel to make the overall brightness of the image more uniform; The edge detection: edge sharpening: strengthening the edge information of the image through a sharpening filter (such as the Laplacian operator) to make the edge clearer.
4. The tunnel construction monitoring system and monitoring method according to claim 1, characterized in that: The tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, color changes, etc., from the preprocessed image. Color change detection: Water seepage usually causes changes in the color of the inner wall of the tunnel. The feature extraction module can identify potential water seepage areas by comparing the difference between the color value of each pixel and the reference value. Through texture analysis: The texture of the seepage surface often changes. The difference between the seepage area and the normal area can be detected through the texture analysis algorithm of the local binary pattern; Identification by shape change: Water stains and water marks may cause the shape of surrounding objects to change. The feature extraction module is able to identify possible signs of water seepage by detecting contour changes or shape changes of the area.
5. The tunnel construction monitoring system and monitoring method according to claim 1, characterized in that: The tunnel water seepage monitoring model training module uses the processed data and extracted features to train the machine learning model of the neural network, analyzes the collected images, and is used to automatically identify and locate the water seepage area. By continuously adjusting the parameters of the model, it can accurately identify and locate the water seepage area.
6. The tunnel construction monitoring system and monitoring method according to claim 1, characterized in that: The data analysis and alarm module transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered and relevant personnel are notified to handle it. It can realize automatic monitoring and early warning of water seepage in the tunnel, and improve the safety and maintenance efficiency during tunnel construction.
7. A tunnel construction monitoring system and monitoring method, comprising the following steps: S1. During tunnel construction, a mobile platform is used to drive a camera to move in the tunnel. At this time, the camera collects image data at various locations in the tunnel. The collected image data needs to be transmitted to the central processing system in real time. The received image data needs to be securely stored for subsequent analysis and retrieval; S2. Use the tunnel image preprocessing module to preprocess the collected images, including image enhancement, edge detection, etc., to improve the accuracy of subsequent processing. Image enhancement: Brightness adjustment: adjust the brightness of the image according to the lighting conditions in the tunnel to make the overall brightness of the image more uniform; Edge detection: Edge sharpening: Use sharpening filters (such as Laplacian operator) to enhance the edge information of the image and make the edges clearer; S3, then the tunnel image feature extraction module extracts possible water seepage features, such as water stains, water marks, color changes, etc., from the preprocessed image, and detects through color change: Water seepage usually causes the color of the tunnel inner wall to change. The feature extraction module can identify potential water seepage areas by comparing the difference between the color value of each pixel and the reference value; Through texture analysis: The texture of the seepage surface often changes. The difference between the seepage area and the normal area can be detected through the texture analysis algorithm of the local binary pattern; Identification by shape change: Water stains and water marks may cause the shape of surrounding objects to change. The feature extraction module can identify possible signs of water seepage by detecting contour changes or shape changes of the area; S4. The tunnel seepage monitoring model training module uses the processed data and extracted features to train the machine learning model of the neural network, analyzes the collected images, and is used to automatically identify and locate the seepage area. By continuously adjusting the parameters of the model, the model can accurately identify and locate the seepage area. S5. Then the data analysis and alarm module transmits the abnormal detection results to the data storage and analysis module for further data analysis and trend prediction. When water seepage or water seepage trend is detected, the alarm system is triggered and relevant personnel are notified to handle it. It can realize automatic monitoring and early warning of water seepage in the tunnel, and improve the safety and maintenance efficiency during tunnel construction.
Citation Information
Cited By
Ship bilge well monitoring system and method
CN119516447A
Tunnel portal water accumulation state obtaining method based on machine vision and deep learning
CN121095532A
