Method and system for acquiring information of surrounding rock and lining structure of operating tunnel

Abstract

The invention discloses an operation tunnel surrounding rock and lining structure information acquisition method and system, and relates to the technical field of tunnel information recognizing.According to the method, images of different angles and distances in the whole range of a tunnel lining structure are acquired, and characteristic quantities reflecting crack width and direction in lining images are extracted; the feature quantity, the tunnel lining point cloud data and the lining live-action three-dimensional model are used for training an image recognition model at the same time to obtain a tunnel lining scanning intelligent recognition model, internal multi-dimensional information of tunnel surrounding rock is detected through an unmanned aerial vehicle, the surrounding rock grade is marked according to the multi-dimensional data, the three-dimensional image recognition model is trained according to the surrounding rock grade, and the tunnel lining scanning intelligent recognition model is obtained. According to the method, the three-dimensional image model of the apparent defect of the surrounding rock is obtained, and then the defect and internal crack information in the surrounding rock and lining structure of the tunnel is accurately identified in combination with the tunnel lining scanning intelligent identification model and the three-dimensional image model of the apparent defect of the surrounding rock, so that a more accurate scheme is provided for subsequent construction and repair of the tunnel.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel information identification, and in particular to a method, system, electronic equipment and storage medium for acquiring information on surrounding rock and lining structure of an operating tunnel. Background Art

[0002] The lining in a tunnel refers to a permanent structure that supports and maintains the long-term stability and durability of the tunnel. Its function is to support and maintain the stability of the tunnel, keep the space required for vehicle operation, prevent the surrounding rock from becoming unstable, and reduce the impact of groundwater. Therefore, the tunnel lining must have sufficient strength, durability, and certain anti-freeze, anti-seepage and anti-erosion properties. The tunnel lining is mainly composed of an arch ring, side walls, inverts and a floor. In order to drain the water in the tunnel, a drainage ditch is also provided in the tunnel. Because the rock mass within the influence range of gravity distribution stress in the tunnel is usually called surrounding rock, and its rock mass properties are different, different lining forms can be used in different surrounding rocks.

[0003] For tunnels that have been in operation for a long time and need to be renovated and expanded in the future, it is necessary to quickly, safely and accurately identify the surface defects of the operating tunnel lining structure such as cracks, seepage, spalling, and information such as cracks, joints, and seepage in the surrounding rocks. Currently, the detection of operating tunnels basically only stays at the surface level of the lining. For the identification of renovated and expanded tunnels, it is difficult to simultaneously identify tunnel lining diseases and surrounding rock defects because the tunnel structure has been improved on the original basis. At the same time, the acquisition of such information usually relies on professional staff to go to the operating tunnel and use some scanning equipment to measure and record.

[0004] In recent years, with the development of UAV, lightweight binocular visual scanning, photogrammetry and sensor technology, especially the research and development and production of miniaturized and lightweight UAV and aerial photography equipment, UAV lightweight binocular visual scanning and UAV oblique photography are increasingly used in tunnel engineering. UAVs can be used to scan the information of tunnel lining and surrounding rock; however, the recognition of scanning results still mainly relies on the combination of subjective experience of professionals and preliminary computer recognition to detect the information of tunnel lining and surrounding rock. However, this method will reduce the accuracy of judging the quality of tunnel lining and surrounding rock, and affect the progress of later construction. Summary of the invention

[0005] The embodiment of the present invention provides a method and system for obtaining information on the surrounding rock and lining structure of an operating tunnel, which can solve the problem in the prior art that the existing methods will reduce the accuracy of judging the quality of the surrounding rock of the tunnel lining.

[0006] An embodiment of the present invention provides a method for obtaining information about surrounding rock and lining structure of an operating tunnel, comprising the following steps:

[0007] Obtain 3D point cloud data of operating tunnel linings;

[0008] Acquire multiple lining images at different angles and distances within the entire range of the operating tunnel lining; extract local brightness information from multiple lining images, and decompose the local brightness information into frequency information and direction information; obtain the lining surface defect feature data of the operating tunnel lining including crack width feature quantity and direction feature quantity based on the frequency information and direction information;

[0009] Generate a tunnel lining scanning intelligent recognition model based on the tunnel lining real-scene model according to the 3D point cloud data and surface defect feature data;

[0010] Obtain multi-dimensional data of the internal information of the surrounding rock behind the tunnel lining, identify the surrounding rock strength based on the multi-dimensional data, and generate a three-dimensional image model of the surrounding rock surface defects;

[0011] The lining image of the operating tunnel to be tested is input into the tunnel lining scanning intelligent recognition model to obtain the apparent defect block of the tunnel lining; the multi-dimensional data of the internal information of the surrounding rock behind the operating tunnel lining to be tested is input into the three-dimensional image model of the apparent defects of the surrounding rock to obtain the strength grade of the tunnel surrounding rock; and the defect information of the lining and surrounding rock structure of the operating tunnel to be tested is identified according to the apparent defect block of the tunnel lining and the strength grade of the tunnel surrounding rock.

[0012] Preferably, the obtaining of three-dimensional point cloud data of the operating tunnel lining includes:

[0013] Use multiple drones to conduct all-round scanning of the operating tunnel, and simultaneously take multi-angle photos of the operating tunnel lining structure from vertical, inclined and horizontal angles to obtain multiple lining images of the operating tunnel lining structure;

[0014] The 3D image modeling software is used to stitch multiple lining images and combine them with the omnidirectional scanning data to obtain a real-life 3D model of the operating tunnel lining structure and identify the 3D point cloud data of the operating tunnel lining in the real-life 3D model.

[0015] Preferably, after the real-life three-dimensional model and three-dimensional point cloud data of the lining structure are obtained, manual annotation is adopted to annotate the lining cracking, water seepage, spalling and crack occurrence, density, width, extension, water outlet point and water outlet of the tunnel lining structure.

[0016] Preferably, decomposing the local brightness information into frequency information and direction information comprises:

[0017] After extracting local brightness information from multiple lining images, the continuous image signals in the multiple lining images are converted into discrete digital signals, specifically, the continuous image signals are discretized in space, and the brightness values ​​of the images are discretized into integers at the same time;

[0018] Perform two-dimensional discrete Fourier transform (2D DFT) on multiple lining images to convert continuous image signals in the lining images from the spatial domain to the frequency domain. After the transformation, each element in the lining image contains frequency information and direction information.

[0019] According to the frequency information and direction information contained in each element, the brightness information of different frequencies and directions in the lining image is obtained, wherein the high-frequency components correspond to the details and texture features of the image, and the low-frequency components correspond to the structure and brightness features of the image.

[0020] Preferably, the tunnel lining scanning intelligent recognition model and the three-dimensional image model of surrounding rock surface defects are both constructed based on a deep learning convolutional neural network (CNN).

[0021] Preferably, after obtaining the strength grade of the tunnel surrounding rock, the tunnel surrounding rock is drilled at the same time, and a point load strength test is performed on the rock obtained by drilling to obtain the strength grade supplement of the tunnel surrounding rock, and the strength grade of the tunnel surrounding rock is corrected according to the strength grade supplement of the tunnel surrounding rock.

[0022] The embodiment of the present invention further provides a system for acquiring information about surrounding rock and lining structure of an operating tunnel, comprising:

[0023] Binocular vision scanning module, used to obtain 3D point cloud data of operating tunnel lining;

[0024] The lining defect recognition module is used to obtain multiple lining images at different angles and distances within the entire range of the operating tunnel lining; extract local brightness information from multiple lining images, and decompose the local brightness information into frequency information and direction information; obtain the lining surface defect feature data of the operating tunnel lining including crack width feature quantity and direction feature quantity based on the frequency information and direction information;

[0025] An image recognition module is used to generate a tunnel lining scanning intelligent recognition model based on the tunnel lining real-scene model according to the three-dimensional point cloud data and the surface defect feature data;

[0026] The surrounding rock strength identification module is used to obtain multi-dimensional data of the internal information of the surrounding rock behind the tunnel lining, identify the surrounding rock strength based on the multi-dimensional data, and generate a three-dimensional image model of the surrounding rock surface defects;

[0027] The information identification module is used to input the lining image of the operating tunnel lining to be tested into the tunnel lining scanning intelligent recognition model to obtain the apparent defect block of the tunnel lining; input the multi-dimensional data of the internal information of the surrounding rock behind the operating tunnel lining to be tested into the three-dimensional image model of the apparent defects of the surrounding rock to obtain the strength grade of the tunnel surrounding rock; and identify the defect information of the lining and surrounding rock structure of the operating tunnel to be tested according to the apparent defect block of the tunnel lining and the strength grade of the tunnel surrounding rock.

[0028] An embodiment of the present invention further provides an electronic device, including a memory and a processor;

[0029] The memory is used to store computer programs;

[0030] The processor is used to implement the steps of the method for obtaining information on the surrounding rock and lining structure of an operating tunnel as described above when executing the computer program stored in the memory.

[0031] An embodiment of the present invention further provides a computer storage medium for storing a computer program, which, when executed by a processor, implements the steps of the method for acquiring information on the surrounding rock and lining structure of an operating tunnel as described above.

[0032] The embodiment of the present invention provides a method and system for obtaining information about surrounding rock and lining structure of an operating tunnel. Compared with the prior art, the method and system have the following beneficial effects:

[0033] The present invention obtains images of different angles and distances within the entire range of the tunnel lining structure, and extracts characteristic quantities reflecting the width and direction of cracks in the lining image. The characteristic quantities, tunnel lining point cloud data and the real-scene three-dimensional model of the lining are used to train the image recognition model at the same time to obtain a tunnel lining scanning intelligent recognition model. The internal multi-dimensional information of the tunnel surrounding rock is detected by an unmanned aerial vehicle, the surrounding rock grade is marked according to the multi-dimensional data, and the three-dimensional image recognition model is trained according to the surrounding rock grade to obtain a three-dimensional image model of the apparent defects of the surrounding rock. Then, the defects and internal crack information in the tunnel surrounding rock and lining structure are accurately identified by combining the tunnel lining scanning intelligent recognition model and the three-dimensional image model of the apparent defects of the surrounding rock. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of the overall process of a method for acquiring information about surrounding rock and lining structure of an operating tunnel provided by an embodiment of the present invention;

[0035] Figure 2 A schematic diagram of the system principle of a method and system for acquiring information about surrounding rock and lining structure of an operating tunnel provided by an embodiment of the present invention;

[0036] Figure 3 A schematic diagram of the system principle disassembly of a method and system for acquiring information about surrounding rock and lining structure of an operating tunnel provided by an embodiment of the present invention;

[0037] Figure 4 A schematic diagram of the electronic device framework of a method and system for acquiring information about surrounding rock and lining structure of an operating tunnel provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0039] See also Figure 2 The embodiment of the present invention provides a method and system for acquiring information on the surrounding rock and lining structure of an operating tunnel, including a UAV platform 100, a lightweight binocular vision scanning module 200, an oblique photography module 300, an image recognition module 400, a surrounding rock information acquisition module 500, an intelligent diagnosis module 600 and a three-dimensional visualization module 700.

[0040] The drone platform 100 is used to control at least one drone to perform flight missions and posture control actions in the target tunnel according to a preset planned route, so as to photograph the tunnel lining in the target tunnel; the drone platform 100 can control at least one drone to perform flight missions and posture control actions in the target tunnel according to the planned route, so as to photograph the tunnel lining in the target tunnel; in addition, the drone platform 100 can control multiple drones to perform flight missions and posture control actions in the target tunnel according to the planned route, thereby improving the accuracy of photographing the tunnel lining, thereby improving the intelligence level of tunnel lining scanning and surrounding rock information acquisition.

[0041] like Figure 3 As shown, the UAV platform 100 includes a data storage and transmission module 101 and a UAV flight control module 102; the data storage and transmission module 101 is used to store point cloud data and image data; the data storage and transmission module 101 provided on the UAV platform 100 can store high-definition point cloud data and image data collected and recorded in real time by the lightweight binocular vision scanning module 200 and the oblique photography module 300, and the storage capacity meets the data collection requirements of a complete tunnel lining scanning task, and at the same time meets the real-time lossless transmission of data under tunnel conditions, ensuring that the main control room outside the tunnel can monitor the UAV platform 10 0 synchronization of control; the UAV flight control module 102 is used to control at least one UAV to perform flight missions and attitude control actions; the UAV flight control module 102 set in the UAV platform 100 can control at least one UAV to perform flight missions and attitude control actions, and the UAV flight control module 102 can share the information of the global navigation satellite module 201, the inertial navigation module 202 and the binocular vision scanning module 203, and at the same time, based on the autonomous route planning function and autonomous navigation function of the UAV platform 100 itself, the autonomous flight and attitude control of the UAV platform 100 under tunnel conditions are realized.

[0042] In addition, the UAV flight control module 102 can transmit data information to the main control room in real time and synchronously through the data storage and transmission module 101 according to the inertial navigation module 202, the binocular vision scanning module 203 and the data acquisition module 301, thereby realizing the UAV flight under manual remote control and realizing the UAV platform 100 to perform detailed scanning and shooting of the tunnel lining.

[0043] The lightweight binocular vision scanning module 200 is used to collect point cloud data of tunnel lining when at least one UAV performs flight missions and posture control actions to improve the feasibility of intelligent tunnel lining scanning; it includes a global navigation satellite module 201, an inertial navigation module 202 and a binocular vision scanning module 203.

[0044] The global navigation satellite module 201 and the inertial navigation module 202 are used to calculate the real-time position and attitude state of the UAV platform 100; the global navigation satellite module 201 and the inertial navigation module 202 can calculate the real-time position and attitude state of the UAV platform 100, and can realize the autonomous flight and position and attitude control of the UAV platform 100 under tunnel conditions based on the autonomous route planning function and autonomous navigation function of the UAV platform 100 itself, thereby improving the intelligence level of tunnel lining scanning; the binocular vision scanning module 203 is used to obtain point cloud data of the tunnel lining; the binocular vision scanning module 203 can quickly obtain three-dimensional coordinate point cloud data of the tunnel lining, and can quickly obtain a high-precision, high-resolution digital surface model of the tunnel lining, thereby improving the accuracy of tunnel data acquisition.

[0045] The oblique photography module 300 is used to collect image data of the tunnel lining and generate a real-scene three-dimensional model of the lining, so as to obtain more complete and accurate surface information of the tunnel lining and improve the accuracy of scanning and identifying the tunnel lining; it includes a data acquisition module 301, an infrared imaging module 302 and a three-dimensional imaging module 303.

[0046] The data acquisition module 301 includes multiple cameras to collect image data of the tunnel lining from multiple different angles at the same time; specifically, the tunnel lining image data is collected from different angles such as vertical and inclined to improve the completeness and accuracy of the tunnel lining surface information; in addition, the data acquisition module 301 can adjust the distance between the drone and the tunnel side wall, as well as the up, down, left and right directions through the drone flight control module 102 according to the actual situation of the tunnel lining, and cooperate with multiple high-definition cameras to obtain all-round image information of the tunnel lining, so as to avoid the lining protrusions from the sunken parts of the joints and cracks, thereby improving the accuracy and reliability of obtaining the actual situation of the tunnel lining.

[0047] The infrared imaging module 302 is used for infrared imaging of the tunnel lining. It is equipped with multiple infrared cameras and simultaneously collects infrared image data of the tunnel lining from different angles such as vertical and inclined, so as to improve the integrity and accuracy of the acquired tunnel lining surface information.

[0048] The three-dimensional imaging module 303 can automatically identify the tunnel lining images taken from different angles and orientations by the data acquisition module 301 and the infrared imaging module 302, and splice and optimize the tunnel lining images through the three-dimensional image modeling software to generate a real-life three-dimensional model of the lining that is consistent with the actual tunnel lining occurrence and has clear concave and convex surface elements, thereby improving the accuracy of the tunnel lining information.

[0049] The image recognition module 400 is used to obtain a tunnel lining scanning intelligent recognition model based on the lining real-scene three-dimensional model, thereby improving the intelligence level of tunnel lining scanning and improving the accuracy of lining surface information recognition; it includes a sample calibration module 401 and a lining defect recognition module 402.

[0050] The sample calibration module 401 is used to mark the surface defects of the lining; based on the generated three-dimensional coordinate point cloud data of the tunnel lining and the real-life three-dimensional model, professional geologists are used to manually mark the occurrence, density, width, extension, etc. of lining cracking, seepage, spalling and cracks, as well as the lining water outlet point and water outlet, etc.; the sample calibration module 401 can dynamically update the sample library. When the surface information of the tunnel lining changes, the sample library is expanded in time by manual annotation by professionals, and the weight of the new samples is increased to train and test the model, so as to avoid a sudden drop in the recognition accuracy of the tunnel lining scanning intelligent recognition model due to a sudden change in the lining surface information, thereby improving the recognition accuracy and reliability of the tunnel lining scanning intelligent recognition model.

[0051] The lining defect recognition module 402 applies Webret transform to the photographic image, decomposes the local brightness information of the photographic image into frequency and directional components, detects feature quantities reflecting the width and direction of the crack from the photographed image, and trains the image recognition model based on the lining apparent defects, point cloud data and the real-scene three-dimensional model of the lining to obtain the tunnel lining scanning intelligent recognition model; the image recognition model can be trained based on the corresponding images of the lining apparent defects, point cloud data and three-dimensional models marked by the sample calibration module 401. After the model training and testing are completed, the actual tunnel lining photographed images are used as verification samples to verify the recognition accuracy and obtain the tunnel lining scanning intelligent recognition model.

[0052] The decomposition of local brightness information is as follows: after extracting the local brightness information from multiple lining images, the continuous image signals in the multiple lining images are converted into discrete digital signals, specifically, the continuous image signals are discretized in space, and the brightness values ​​of the images are discretized into integers at the same time; the multiple lining images are subjected to two-dimensional discrete Fourier transform 2D DFT to convert the continuous image signals in the lining images from the spatial domain to the frequency domain, and after the transformation, each element in the lining image contains frequency information and direction information.

[0053] The frequency and direction information contained in each element is used to obtain the brightness information of different frequencies and directions in the lining image, where the high-frequency components correspond to the details and texture features of the image, and the low-frequency components correspond to the structure and brightness features of the image.

[0054] The surrounding rock information acquisition module 500 is used to detect the internal information of the tunnel surrounding rock when at least one UAV performs the flight mission and posture control action, so as to improve the accuracy of strength identification of the tunnel surrounding rock under multiple disturbances and improve the safety of tunnel construction; it includes an airborne geological radar module 501, a feature input module 502, a surrounding rock strength identification module 503 and a surrounding rock strength correction module 504.

[0055] The airborne geological radar module 501 is used to transmit radar waves and receive signals to detect the internal information of the surrounding rock of the operating tunnel, and at the same time select geological parameters that meet preset conditions to generate input parameters for the surrounding rock strength identification module 503.

[0056] The feature input module 502 can select geological parameters that meet certain conditions as input parameters of the surrounding rock strength identification module 503 in the following steps based on the surrounding rock classification method adopted by the tunnel and the results of the tunnel airborne geological radar identifying the apparent defects of the lining, thereby reducing the manual operation cost and improving the efficiency of the measurement data of the surrounding rock scanning results.

[0057] The surrounding rock strength identification module 503 is used to train and test the neural network model according to the input parameters of the surrounding rock strength identification module 503 in combination with a preset deep learning neural network algorithm, and in combination with the actual surrounding rock strength labeling results, so as to obtain a three-dimensional image model of the apparent defects of the surrounding rock; the neural network model can be trained and tested according to the input parameters determined by the feature input module 502, in combination with the deep learning neural network algorithm, according to the actual surrounding rock grade labeling results, so as to obtain a three-dimensional image model of the apparent defects of the surrounding rock, thereby improving work efficiency while improving construction safety, and the operation is convenient and the steps are simple, which is easy for workers to learn and master.

[0058] The surrounding rock strength correction module 504 is used to perform a point load strength test on the drilled rock according to the on-site drilling conditions, and obtain surrounding rock strength supplementary parameters to correct the recognition results of the three-dimensional image model of the surrounding rock surface defects; the point load strength test can be performed on the drilled rock according to the on-site drilling conditions, and the surrounding rock strength parameters can be supplemented to correct the recognition results of the three-dimensional image model of the surrounding rock surface defects, thereby effectively improving the accuracy of surrounding rock strength identification and improving the safety of tunnel construction.

[0059] The embodiments of the present invention can check whether the data storage and transmission module and the flight control module of the UAV platform are working normally, check whether the lightweight binocular vision scanning module and the oblique photography module carried by the UAV platform are working normally, set the route of the UAV platform, rely on the autonomous navigation flight of the UAV platform, combine the data acquisition module and the data storage and transmission module to shoot and transmit real-time synchronous images, and use manual remote control to assist the flight to ensure that the UAV safely reaches the inside of the tunnel.

[0060] Next, the position information of the UAV platform can be determined based on the global navigation satellite module and the inertial navigation module, and the three-dimensional coordinate point cloud data of the lining can be quickly acquired through the binocular vision scanning module to generate a high-precision, high-resolution digital surface model of the tunnel lining.

[0061] Secondly, according to the actual situation of the lining, the UAV flight control module can be used to adjust the distance between the UAV and the tunnel lining and the up, down, left and right orientation. In combination with multiple high-definition cameras, all-round image information of the lining can be obtained to generate a real-life three-dimensional model of the lining.

[0062] Thirdly, the digital surface model and the real-life three-dimensional model of the lining can be input into the tunnel lining scanning intelligent recognition model to obtain the tunnel lining defect recognition results; at the same time, the tunnel surrounding rock strength grade can be obtained based on the three-dimensional image model of the surrounding rock surface defects, and combined with the surrounding rock strength parameters obtained by the correction module, the tunnel surrounding rock strength identification results can be obtained.

[0063] The present invention controls the drone through the drone platform to perform flight missions and posture control actions in the target tunnel according to the planned route, and collects the point cloud data of the tunnel lining through the lightweight binocular vision scanning module, collects the impact data of the tunnel lining through the oblique photography module, and generates a real-scene three-dimensional model of the lining, thereby obtaining a tunnel lining scanning intelligent recognition model through the image recognition module, and then the surrounding rock information acquisition module uses the airborne geological radar to detect the internal information of the surrounding rock, and obtains the surrounding rock surface information according to the processing results, and obtains the three-dimensional image model of the surrounding rock surface defects, thereby reducing a lot of manual operation costs, and improving the accuracy of surrounding rock strength identification, while improving the safety of tunnel construction. Therefore, it solves the problems in the related technology that the defects of the tunnel lining and the internal information of the surrounding rock are manually identified, which increases a lot of manual operation costs, makes it difficult to ensure the safety of the operators, reduces the accuracy of surrounding rock strength identification, and reduces the safety of the reconstruction and expansion construction of the operating tunnel.

[0064] like Figure 1 As shown, the specific method includes the following steps:

[0065] Step 1: Perform flight missions and posture control actions in the target tunnel according to the preset planned route to photograph the tunnel lining in the target tunnel.

[0066] Step 2: Collect point cloud data of tunnel lining.

[0067] Step 3: Collect the impact data of the tunnel lining, generate a real-life 3D model of the lining, and obtain a tunnel lining scanning intelligent recognition model.

[0068] Step 4: Obtain multi-dimensional data of the internal information of the tunnel surrounding rock, perform intelligent identification of the surrounding rock strength based on the processing results, and generate a three-dimensional image model of the surrounding rock surface defects.

[0069] Step 5: Intelligently diagnose, identify and summarize the apparent defects of lining and surrounding rock.

[0070] Step 6: Combine the tunnel lining scanning intelligent recognition model and the three-dimensional image model of the surrounding rock surface defects to realize a three-dimensional visual transparent geological model that includes the tunnel lining surface information and the internal surrounding rock information.

[0071] The present invention controls a drone through a drone platform to perform flight missions and posture control actions in a target tunnel according to a planned route, collects point cloud data of the tunnel lining through a lightweight binocular vision scanning module, and photographs the tunnel lining in the target tunnel through an oblique photography module; collects image data of the tunnel lining to generate a real-life three-dimensional model of the lining, and then obtains a tunnel lining scanning intelligent recognition model based on the real-life three-dimensional model of the lining; uses a surrounding rock information acquisition module to perform three-dimensional detection and data collection on the surrounding rock behind the lining to generate a three-dimensional image model of the apparent defects of the surrounding rock, combines the tunnel lining scanning intelligent recognition model with the three-dimensional image model of the apparent defects of the surrounding rock, and realizes a three-dimensional visualized transparent geological model that integrates the apparent information of the lining and the internal surrounding rock information, thereby reducing a large amount of manual operation costs, and improving the accuracy of the lining while improving the safety of tunnel construction; solves the problems of manually identifying the tunnel lining scanning and surrounding rock grade, increasing a large amount of manual operation costs, and making it difficult to ensure the safety of operators, reducing the accuracy of surrounding rock strength identification, and reducing the safety of tunnel construction.

[0072] The present invention uses a three-dimensional image model of surrounding rock surface defects based on image recognition technology and deep learning neural network algorithm to achieve standardized identification of tunnel surrounding rock grade, saving a lot of manpower, improving work efficiency, ensuring construction safety, and is easy to operate and has simple steps, which is easy for workers to learn and master, shortens on-site preparation and debugging time, saves time, and is easy to promote and popularize.

[0073] like Figure 4 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, including:

[0074] A memory 1 , a processor 2 , and a computer program stored in the memory 1 and executable on the processor 2 .

[0075] When the processor 2 executes the program, the steps of a method for acquiring information on the surrounding rock of the lining of an operating tunnel provided in the above embodiment are implemented.

[0076] Electronic equipment also includes:

[0077] The communication interface 3 is used for communication between the memory 1 and the processor 2 .

[0078] The memory 1 is used to store computer programs that can be run on the processor 2.

[0079] The memory 1 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0080] If the memory 1, the processor 2 and the communication interface 3 are implemented independently, the communication interface 3, the memory 1 and the processor 2 can be connected to each other through a bus and communicate with each other; the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc.; the bus can be divided into an address bus, a data bus, a control bus, etc.; for the convenience of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0081] If the memory 1, the processor 2 and the communication interface 3 are integrated on a chip, the memory 1, the processor 2 and the communication interface 3 can communicate with each other through an internal interface.

[0082] The processor 2 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0083] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for obtaining information about surrounding rock and lining structure of an operating tunnel, characterized in that: The following steps are involved: Obtain 3D point cloud data of operating tunnel linings; Acquire multiple lining images at different angles and distances over the entire range of the operating tunnel lining; Extract local brightness information from multiple lining images and decompose the local brightness information into frequency information and direction information; obtain the lining surface defect feature data of the operating tunnel lining including crack width feature quantity and direction feature quantity according to the frequency information and direction information; Generate a tunnel lining scanning intelligent recognition model based on the tunnel lining real-scene model according to the 3D point cloud data and surface defect feature data; Obtain multi-dimensional data of the internal information of the surrounding rock behind the tunnel lining, identify the surrounding rock strength based on the multi-dimensional data, and generate a three-dimensional image model of the surrounding rock surface defects; Input the lining image of the operating tunnel lining to be tested into the tunnel lining scanning intelligent recognition model to obtain the apparent defect block of the tunnel lining; input the multi-dimensional data of the internal information of the surrounding rock behind the operating tunnel lining to be tested into the three-dimensional image model of the apparent defects of the surrounding rock to obtain the strength grade of the tunnel surrounding rock; And according to the apparent defective blocks of the tunnel lining and the strength grade of the tunnel surrounding rock, the defect information of the lining and surrounding rock structure of the operating tunnel to be tested is identified.

2. The method for obtaining information about surrounding rock and lining structure of an operating tunnel according to claim 1, characterized in that: The method of obtaining the three-dimensional point cloud data of the operating tunnel lining includes: Use multiple drones to conduct all-round scanning of the operating tunnel, and simultaneously take multi-angle photos of the operating tunnel lining structure from vertical, inclined and horizontal angles to obtain multiple lining images of the operating tunnel lining structure; The 3D image modeling software is used to stitch multiple lining images and combine them with the omnidirectional scanning data to obtain a real-life 3D model of the operating tunnel lining structure and identify the 3D point cloud data of the operating tunnel lining in the real-life 3D model.

3. The method for obtaining information about surrounding rock and lining structure of an operating tunnel according to claim 2, characterized in that: After the real-life three-dimensional model and three-dimensional point cloud data of the lining structure are obtained, manual annotation is adopted to annotate the lining cracking, water seepage, spalling and crack occurrence, density, width, extension, water outlet point and water outlet of the tunnel lining structure.

4. The method for obtaining information about surrounding rock and lining structure of an operating tunnel according to claim 1, characterized in that: The decomposing the local brightness information into frequency information and direction information comprises: After extracting local brightness information from multiple lining images, the continuous image signals in the multiple lining images are converted into discrete digital signals, specifically, the continuous image signals are discretized in space, and the brightness values ​​of the images are discretized into integers at the same time; Perform two-dimensional discrete Fourier transform (2D DFT) on multiple lining images to convert continuous image signals in the lining images from the spatial domain to the frequency domain. After the transformation, each element in the lining image contains frequency information and direction information. According to the frequency information and direction information contained in each element, the brightness information of different frequencies and directions in the lining image is obtained, wherein the high-frequency components correspond to the details and texture features of the image, and the low-frequency components correspond to the structure and brightness features of the image.

5. The method for obtaining information about surrounding rock and lining structure of an operating tunnel according to claim 1, characterized in that: The tunnel lining scanning intelligent recognition model and the three-dimensional image model of surrounding rock surface defects are both constructed based on the deep learning convolutional neural network (CNN).

6. The method for obtaining information about surrounding rock and lining structure of an operating tunnel according to claim 1, characterized in that: After obtaining the strength grade of the tunnel surrounding rock, the tunnel surrounding rock is drilled at the same time, and a point load strength test is performed on the rock obtained by drilling to obtain the strength grade supplement of the tunnel surrounding rock, and the strength grade of the tunnel surrounding rock is corrected according to the strength grade supplement of the tunnel surrounding rock.

7. An information acquisition system for surrounding rock and lining structure of an operating tunnel, characterized in that: include: Binocular vision scanning module, used to obtain 3D point cloud data of operating tunnel lining; The lining defect recognition module is used to obtain multiple lining images at different angles and distances within the entire range of the operating tunnel lining; extract local brightness information from multiple lining images, and decompose the local brightness information into frequency information and direction information; obtain the lining surface defect feature data of the operating tunnel lining including crack width feature quantity and direction feature quantity based on the frequency information and direction information; An image recognition module is used to generate a tunnel lining scanning intelligent recognition model based on the tunnel lining real-scene model according to the three-dimensional point cloud data and the surface defect feature data; The surrounding rock strength identification module is used to obtain multi-dimensional data of the internal information of the surrounding rock behind the tunnel lining, identify the surrounding rock strength based on the multi-dimensional data, and generate a three-dimensional image model of the surrounding rock surface defects; The information identification module is used to input the lining image of the operating tunnel lining to be tested into the tunnel lining scanning intelligent recognition model to obtain the apparent defect block of the tunnel lining; input the multi-dimensional data of the internal information of the surrounding rock behind the operating tunnel lining to be tested into the three-dimensional image model of the apparent defects of the surrounding rock to obtain the strength grade of the tunnel surrounding rock; And according to the apparent defective blocks of the tunnel lining and the strength grade of the tunnel surrounding rock, the defect information of the lining and surrounding rock structure of the operating tunnel to be tested is identified.

8. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer programs; The processor is used to implement the steps of the method for obtaining information on the surrounding rock and lining structure of an operating tunnel as described in any one of claims 1 to 6 when executing the computer program stored in the memory.

9. A computer storage medium, characterized in that Used to store a computer program, which, when executed by a processor, implements the steps of a method for obtaining information on surrounding rock and lining structure of an operating tunnel as described in any one of claims 1 to 6.

Images