Method and device for integrated monitoring and early warning of tunnel excavation face

Abstract

The invention relates to the technical field of tunnel construction, in particular to an integrated monitoring and early warning method and equipment for a tunnel excavation face, the equipment integrates at least a laser radar, a camera, at least one gas sensor, a processor and other electronic components, and three-dimensional point cloud data of the tunnel excavation face are collected through the laser radar; early warning is carried out on surrounding rock disasters of the tunnel excavation face; real-time image data of a tunnel excavation face are collected through a camera and are submitted to a deep learning model to carry out flowing water area identification so as to carry out early warning of mud burst and water burst disasters; at least one gas sensor is arranged to detect concentration values of different types of gases in a tunnel where a tunnel excavation face is located so as to carry out gas disaster early warning; according to the scheme, multiple functions are integrated, surrounding rock disaster early warning, mud burst and water burst disaster early warning and gas disaster early warning can be achieved through one device, higher intelligence and convenience are achieved, and the operation risk of site construction personnel is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction, and in particular to a method and equipment for integrated monitoring and early warning of tunnel excavation faces. Background Art

[0002] Drilling and blasting is a commonly used construction method for railway tunnels. The tunnel excavation surface formed by the drilling and blasting method is unstable, complex, and high-risk. There are surrounding rock disasters such as surrounding rock extrusion deformation (soft rock sections) and local block falling (hard rock sections), gas disasters such as gas, CO and NOx, and the risk of sudden mud and water disasters. As a result, this area has become the main area for sudden disasters during tunnel construction, which can easily endanger the lives and safety of on-site construction workers and increase the difficulty of on-site construction.

[0003] At present, traditional instruments such as displacement meters, compasses, strain gauges, and convergence rulers are often used to monitor surrounding rock disasters on tunnel excavation faces. These instruments not only rely on manual monitoring, but also cannot provide continuous and overall monitoring. Mud and water disasters are often monitored using advanced geological prediction methods such as seismic waves, electricity, and magnetism, as well as deployed devices. These methods involve a large workload, are time-consuming, and inefficient. In addition, the measurement work interferes with on-site construction, and human factors have a significant impact on measurement accuracy, resulting in unstable measurement results. Gas disasters are often monitored using single-function sensors, which have relatively single functions and cannot be integrated with other systems. Summary of the invention

[0004] The purpose of the present invention is to provide a method and equipment for integrated monitoring and early warning of tunnel excavation faces, which can simultaneously carry out integrated monitoring of surrounding rock disasters, gas disasters and sudden mud and water disasters on the tunnel excavation face to ensure the quality and safety of railway tunnel projects.

[0005] In order to achieve the above purpose, the technical solution adopted by the embodiment of the present invention is as follows:

[0006] In the first aspect, an embodiment of the present invention provides a method for integrated monitoring and early warning of tunnel excavation faces, the method comprising: receiving three-dimensional point cloud data collected by a laser radar emitting a laser beam to the tunnel excavation face, screening out evaluation data from the three-dimensional point cloud data, constructing an evaluation template based on the evaluation data, and traversing the distance values ​​between subsequently collected real-time three-dimensional point cloud data and the evaluation template; if there are more than a threshold number of real-time three-dimensional point cloud data whose distance values ​​are greater than a predetermined threshold, a tunnel excavation face surrounding rock disaster early warning is issued; receiving real-time image data collected by a camera on the tunnel excavation face, identifying the real-time image data through a pre-built deep learning model, and if the area of ​​flowing water in the real-time image data is greater than a set threshold, a mud and water gushing disaster early warning is issued; receiving gas concentration data monitored by at least one gas sensor on the tunnel where the tunnel excavation face is located, and if the gas concentration data exceeds the corresponding concentration threshold, a gas disaster early warning is issued.

[0007] In the second aspect, an embodiment of the present invention further provides a device for integrated monitoring and early warning of tunnel excavation faces, the device comprising a laser radar, a camera, at least one gas sensor and a processor, the laser radar emitting a laser beam to the tunnel excavation face to collect three-dimensional point cloud data, and transmitting the data to the processor, the processor filtering out evaluation data from the three-dimensional point cloud data, constructing an evaluation template based on the evaluation data, and traversing the distance values ​​between subsequently collected real-time three-dimensional point cloud data and the evaluation template, if there are more than a threshold number of real-time three-dimensional point cloud data with distance values ​​greater than a predetermined threshold, then a tunnel excavation face surrounding rock disaster early warning is performed; the camera collects real-time image data of the tunnel excavation face, and transmits the data to the processor, the processor identifies the real-time image data through a pre-built deep learning model, and if the area of ​​flowing water in the real-time image data is greater than a set threshold, then a mud and water gushing disaster early warning is performed; the at least one gas sensor monitors the gas concentration data of the tunnel where the tunnel excavation face is located, and transmits the data to the processor, if the gas concentration data exceeds the corresponding concentration threshold, then a gas disaster early warning is performed.

[0008] An embodiment of the present invention provides a method and device for integrated monitoring and early warning of tunnel excavation faces. The device integrates at least a laser radar, a camera, at least one gas sensor, a processor and other electronic components. The laser radar is used to collect three-dimensional point cloud data of the tunnel excavation face to warn of surrounding rock disasters on the tunnel excavation face; the camera is used to collect real-time image data of the tunnel excavation face, and the data is submitted to a deep learning model for water flow area identification to warn of mud and water sudden disasters; at least one gas sensor is set to detect the concentration values ​​of different types of gases in the tunnel where the tunnel excavation face is located to warn of gas disasters; the solution integrates multiple functions and can realize surrounding rock disaster warnings, mud and water sudden disaster warnings and gas disaster warnings through one device, which is more intelligent and convenient, and effectively reduces the operating risks of on-site construction personnel.

[0009] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic structural diagram of a device for integrated monitoring and early warning of tunnel excavation surface provided by an embodiment of the present invention is shown.

[0012] Figure 2 A schematic diagram of surrounding rock disaster early warning monitoring provided by an embodiment of the present invention is shown.

[0013] Figure 3 A schematic flow chart of a method for integrated monitoring and early warning of tunnel excavation face provided by an embodiment of the present invention is shown.

[0014] Diagram:

[0015] 100-equipment for integrated monitoring and early warning of tunnel excavation face; 110-data acquisition unit; 111-laser radar; 112-camera; 113-gas sensor; 120-data processing unit; 130-communication control unit; 140-data storage unit; 150-early warning unit; 151-alarm light; 152-display screen; 153-buzzer; 121-surrounding rock disaster processing unit; 122-mud and water disaster processing unit; 123-gas disaster processing unit. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0017] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0018] Please refer to Figure 1 , is a schematic diagram of the structure of a device 100 for integrated monitoring and early warning of tunnel excavation surface provided by an embodiment of the present invention, the device 100 for integrated monitoring and early warning of tunnel excavation surface includes a data acquisition unit 110, a data processing unit 120, a communication control unit 130, a data storage unit 140 and an early warning unit 150. Among them, the data acquisition unit 110, the data processing unit 120, the data storage unit 140 and the early warning unit 150 are connected in communication through the communication control unit 130 to transfer data to each other, and the communication control unit 130 mainly includes the communication protocol adopted by each unit for data transmission.

[0019] It should be noted that the data acquisition unit 110, the data processing unit 120, the communication control unit 130, the data storage unit 140 and the early warning unit 150 can be integrated as one or separately provided. For example, the above units can be integrated into one device, or the data acquisition unit 110, the data processing unit 120, the communication control unit 130, the data storage unit 140 can be integrated, and only the early warning unit 150 can be provided separately. For example, the data acquisition unit 110 and the communication control unit 130 can be integrated, and the data processing unit 120, the data storage unit 140 and the early warning unit 150 can be integrated, etc.

[0020] Furthermore, the data acquisition unit 110 includes a laser radar 111, a camera 112, and at least one gas sensor 113. The laser radar 111 is composed of a transmitting system, a photoelectric receiver, and a control system. It transmits a laser beam to the tunnel excavation surface in a cyclic scanning manner, and uses the received echo information to obtain the distance and three-dimensional space data to form the three-dimensional point cloud data of the tunnel excavation surface. It can scan 10 frames of point cloud data every second, and the multiple frames of point cloud data are accumulated and spliced ​​to form the three-dimensional point cloud data of the tunnel excavation surface to be monitored. The camera 112 converts the light source signal into an electrical signal through the image sensor of the internal sensor system, thereby obtaining multiple frames of visible light images of the tunnel excavation surface, and each frame of the image is the two-dimensional image data to be monitored. The at least one gas sensor 113 uses an electrochemical sensor to generate current by the oxidation-reduction reaction of the collected gas on the electrode, and obtains the one-dimensional concentration data of the gas to be monitored after internal signal amplification. Then, the data acquisition unit 110 transmits the collected one-dimensional concentration data, two-dimensional image data and three-dimensional point cloud data to the data processing unit 120 through the communication control unit 130 for further analysis, and also transmits the data to the data storage unit 140 for storage. The data storage unit 140 stores the three-dimensional point cloud data (including three-dimensional coordinates and RGB information), two-dimensional image data and one-dimensional concentration data (including gas type, gas concentration, monitoring time), etc., for easy access and data traceability at any time.

[0021] The data processing unit 120 is a processor, which specifically includes a surrounding rock disaster processing unit 121 , a mud and water gushing disaster processing unit 122 , and a gas disaster processing unit 123 .

[0022] The surrounding rock disaster processing unit 121 is used to receive the three-dimensional point cloud data collected by the laser radar 111. It should be noted that the laser radar 111 is integrated with an IMU (Inertial measurement unit), an accelerometer, a mass block, and a spring. The IMU unit is used to collect the three-axis acceleration of the laser radar 111. In addition, under the influence of gravity, the mass block in the accelerometer will compress the spring in the vertical direction, equivalently recording the acceleration in one direction vertically upward, and decomposing the acceleration into the three-axis acceleration according to the posture of the IMU unit in space to obtain the three-axis acceleration after removing the gravity acceleration, and monitor whether the laser radar 111 is moving based on the acceleration data after removing the gravity acceleration from the three-axis acceleration. When the laser radar 111 is in a stationary state, the three-dimensional point cloud data it collects is valid data. Figure 2As shown, it is a schematic diagram of a surrounding rock disaster early warning monitoring provided by an embodiment of the present invention. Then, a predetermined number of continuous point cloud data whose states have not changed are screened out from the above three-dimensional point cloud data and spliced ​​as evaluation data, such as splicing the point cloud data that has not changed for 40 consecutive frames during initialization as evaluation data; Poisson reconstruction is then used to construct a triangulated evaluation network template for the evaluation data respectively. In order to accurately process the tunnel excavation surface, the triangulated evaluation network template is grid-blocked according to predetermined specifications to obtain a final evaluation template; finally, the real-time three-dimensional point cloud data collected subsequently is traversed in turn, the m points of the K nearest neighbors of each point are retained, the corresponding evaluation template is found, the Euclidean distance between the m points and the evaluation template is calculated, and the minimum distance is taken as the point cloud distance of the current point until all points are calculated; finally, it is determined whether the distance of each point cloud exceeds the set distance threshold, and whether the number of point clouds exceeding the distance threshold meets the number threshold. If both are satisfied, it indicates that there is a risk of deformation or surrounding rock falling on the current tunnel excavation surface, and a surrounding rock disaster early warning signal is issued.

[0023] The mud and water disaster processing unit 122 is used to receive the real-time image data collected by the camera 112 on the tunnel excavation surface, and identify the real-time image data through a pre-built deep learning model. If the area of ​​flowing water in the real-time image data is greater than the set threshold, a mud and water disaster warning is issued. The structure of the deep learning model is as follows: the model adopts a double U-shaped architecture, and the network includes Encoder and Decoder modules. The image multi-scale feature extraction part of U2-Net is a contraction network. First, the feature map size is reduced by downsampling. In this process, the network extracts shallow information. Then, dilation convolution is performed without adjusting the image size to better achieve multi-scale extraction. The preliminary effective feature layer extracted from the multi-scale feature is upsampled by the bilinear interpolation method to restore it to the size of the original image. The 6 feature maps obtained by the feature extraction part are concant spliced, and the prediction probability after the final fusion is obtained through the convolution layer and the sigmoid activation function. Furthermore, the process of building the deep learning model is as follows: collect multiple target image data of the tunnel excavation surface through the camera 112 in advance, mark each target image data respectively, such as the mark can be but not limited to dry area, wet area and water area; then use the marked multiple target image data to train the deep learning model to obtain the built deep learning model. In actual recognition, the above real-time image data is converted into a tensor through the pre-built deep learning model, and the tensor is identified, and the dry area, wet area and water area in the real-time image data are marked with different colors, such as marking the dry area as green, the wet area as red, and the water area as yellow. If the area of ​​water in the real-time image data is greater than the set threshold, a mud and water disaster warning is issued, thereby realizing a quantitative analysis of the apparent groundwater in the tunnel.

[0024] The gas disaster processing unit 123 is used to receive the gas concentration data of the tunnel where the tunnel excavation face is located monitored by at least one gas sensor 113. If the gas concentration data exceeds the corresponding concentration threshold, a gas disaster warning is issued. Specifically, in the embodiment of the present invention, the gas sensor 113 is set to 5, and one gas sensor is used to monitor a gas concentration value, so different numbers of gas sensors can be set according to the type of gas actually monitored. Further, the 5 gas sensors set in the embodiment of the present invention are respectively used to monitor the oxygen (O2) concentration, carbon monoxide (CO) concentration, carbon dioxide (CO2) concentration, methane (CH4) concentration and hydrogen sulfide (H2S) concentration. If any gas concentration exceeds the corresponding concentration threshold, a gas disaster warning will be issued. Further, in the embodiment of the present invention, the concentration thresholds of each gas to be monitored are set to be that the concentration threshold of oxygen concentration shall not be less than 20%, the concentration threshold of carbon monoxide concentration shall not be higher than 30%, the concentration threshold of carbon dioxide concentration shall not be higher than 0.5%, the concentration threshold of methane concentration shall not be higher than 1%, and the concentration threshold of hydrogen sulfide concentration shall not be higher than 10%. It should be noted that the current gas concentration value = gas concentration high bit × 256 + gas concentration low bit.

[0025] After each unit in the data processing unit 120 (surrounding rock disaster processing unit 121, mud and water sudden disaster processing unit 122 and gas disaster processing unit 123) analyzes and processes the data sent by the data acquisition unit 110 (lidar 111, camera 112 and gas sensor 113), if there is any risk of surrounding rock disaster, mud and water sudden disaster, or gas disaster, an early warning reminder will be issued in time through the early warning unit 150 so that on-site construction personnel can respond immediately.

[0026] The early warning unit 150 includes one or more of an alarm light 151, a display screen 152 and a buzzer 153. The alarm light 151 will respond to the early warning signal at a certain frequency, where red indicates a surrounding rock disaster early warning signal, yellow indicates a mud and water disaster early warning signal, blue indicates a gas disaster early warning signal, and the normal white light state is always on when there is no early warning. The buzzer 153 responds to the three disaster early warning signals or calculation results at a certain frequency. The display screen 152 displays the type of disaster currently occurring and the type of gas corresponding to the gas disaster. It should be noted that the alarm light 151, the display screen 152 and the buzzer 153 can alarm at the same time, or they can be alarmed in any combination according to the user's settings.

[0027] It can be seen that the device 100 for integrated monitoring and early warning of tunnel excavation faces provided by the embodiment of the present invention integrates the real-time monitoring and early warning modules of surrounding rock disasters, sudden mud and water gushing disasters, and gas disasters on the tunnel excavation face to form an integrated monitoring and early warning system for multi-source disasters, thereby realizing real-time monitoring and early warning of surrounding rock disasters, sudden mud and water gushing disasters, and gas disasters, and effectively protecting the lives of on-site construction personnel.

[0028] Please refer to Figure 3 , is a flow chart of a method for integrated monitoring and early warning of tunnel excavation surface provided by an embodiment of the present invention, the method is applied to a device 100 for integrated monitoring and early warning of tunnel excavation surface, the method comprising:

[0029] S110, receiving the three-dimensional point cloud data collected by the laser radar emitting a laser beam to the tunnel excavation surface, filtering out evaluation data from the three-dimensional point cloud data, constructing an evaluation template based on the evaluation data, and traversing the distance values ​​between the subsequently collected real-time three-dimensional point cloud data and the evaluation template; if there are more than a threshold number of real-time three-dimensional point cloud data whose distance values ​​are greater than a predetermined threshold, then issuing a tunnel excavation surface surrounding rock disaster warning.

[0030] Specifically, the laser radar 111 is composed of a transmitting system, a photoelectric receiver and a control system. It transmits a laser beam to the tunnel excavation surface in a cyclic scanning manner, and uses the received echo information to obtain distance and three-dimensional spatial data to form three-dimensional point cloud data of the tunnel excavation surface. It can scan 10 frames of point cloud data every second, and accumulate and splice multiple frames of point cloud data to form three-dimensional point cloud data to be monitored on the tunnel excavation surface, and transmit the collected three-dimensional point cloud data to the surrounding rock disaster processing unit 121 for analysis and identification.

[0031] like Figure 2 As shown, it is a schematic diagram of a surrounding rock disaster early warning monitoring provided by an embodiment of the present invention. Then, a predetermined number of continuous point cloud data whose states have not changed are screened out from the above three-dimensional point cloud data and spliced ​​as evaluation data, such as splicing the point cloud data that has not changed for 40 consecutive frames during initialization as evaluation data; Poisson reconstruction is then used to construct a triangulated evaluation network template for the evaluation data respectively. In order to accurately process the tunnel excavation surface, the triangulated evaluation network template is grid-blocked according to predetermined specifications to obtain a final evaluation template; finally, the real-time three-dimensional point cloud data collected subsequently is traversed in turn, the m points of the K nearest neighbors of each point are retained, the corresponding evaluation template is found, the Euclidean distance between the m points and the evaluation template is calculated, and the minimum distance is taken as the point cloud distance of the current point until all points are calculated; finally, it is determined whether the distance of each point cloud exceeds the set distance threshold, and whether the number of point clouds exceeding the distance threshold meets the number threshold. If both are satisfied, it indicates that there is a risk of deformation or surrounding rock falling on the current tunnel excavation surface, and a surrounding rock disaster early warning signal is issued.

[0032] S120, receiving real-time image data collected by a camera on the tunnel excavation surface, identifying the real-time image data through a pre-built deep learning model, and issuing a mud and water disaster warning if the area of ​​flowing water in the real-time image data is greater than a set threshold.

[0033] Specifically, the camera 112 converts the light source signal into an electrical signal through the image sensor of the internal sensor system, thereby obtaining multiple frames of visible light images of the tunnel excavation surface, each frame of which is the two-dimensional image data to be monitored, and transmits the two-dimensional image data to the mud and water disaster processing unit 122 for analysis and processing. The construction process of the deep learning model is: in advance, the camera 112 collects multiple target image data of the tunnel excavation surface, and marks each target image data respectively, such as the mark can be but not limited to dry area, wet area and water flow area; and then uses the marked multiple target image data to train the deep learning model to obtain the constructed deep learning model. During actual identification, the real-time image data is converted into a tensor through a pre-built deep learning model, and the tensor is identified. The dry areas, wet areas and flowing water areas in the real-time image data are marked with different colors, such as marking the dry areas as green, the wet areas as red, and the flowing water areas as yellow. If the area of ​​flowing water in the real-time image data is larger than the set threshold, a mud and water disaster warning is issued, thereby realizing quantitative analysis of the apparent groundwater in the tunnel.

[0034] S130, receiving gas concentration data monitored by at least one gas sensor on the tunnel where the tunnel excavation face is located, and if the gas concentration data exceeds a corresponding concentration threshold, issuing a gas disaster warning.

[0035] Specifically, the at least one gas sensor 113 uses an electrochemical sensor to generate current through an oxidation-reduction reaction of the collected gas on the electrode, obtains one-dimensional concentration data of the gas to be monitored after internal signal amplification, and transmits the concentration data to the gas disaster processing unit 123 for analysis and processing.

[0036] In the embodiment of the present invention, the gas sensor 113 is set to 5, and one gas sensor is used to monitor a gas concentration value, so different numbers of gas sensors can be set according to the type of gas actually monitored. Further, the 5 gas sensors 113 set in the embodiment of the present invention are used to monitor the concentration of oxygen (O2), carbon monoxide (CO), carbon dioxide (CO2), methane (CH4) and hydrogen sulfide (H2S), respectively. If the concentration of any gas exceeds the corresponding concentration threshold, a gas disaster warning will be issued. Further, in the embodiment of the present invention, the concentration threshold of each gas to be monitored is set to be that the concentration threshold of oxygen concentration shall not be less than 20%, the concentration threshold of carbon monoxide concentration shall not be higher than 30%, the concentration threshold of carbon dioxide concentration shall not be higher than 0.5%, the concentration threshold of methane concentration shall not be higher than 1%, and the concentration threshold of hydrogen sulfide concentration shall not be higher than 10%. It should be noted that the current gas concentration value = gas concentration high bit × 256 + gas concentration low bit.

[0037] The warning reminders of the surrounding rock disaster warning, mud and water disaster warning, and gas disaster warning are issued through the warning unit 150. The warning unit 150 includes one or more of the alarm light 151, the display screen 152, and the buzzer 153. The alarm light 151 will respond to the warning signal at a certain frequency, where red indicates the surrounding rock disaster warning signal, yellow indicates the mud and water disaster warning signal, and blue indicates the gas disaster warning signal. Normally, the white state is always on when there is no warning. The buzzer 153 responds to the three disaster warning signals or calculation results at a certain frequency. The display screen 152 displays the type of disaster currently occurring and the type of gas corresponding to the gas disaster. It should be noted that the alarm light 151, the display screen 152, and the buzzer 153 can alarm at the same time, or they can be alarmed in any combination according to the user's settings.

[0038] In summary, an embodiment of the present invention provides a method and device for integrated monitoring and early warning of tunnel excavation faces. The device integrates at least laser radar, a camera, at least one gas sensor, a processor and other electronic components. The laser radar is used to collect three-dimensional point cloud data of the tunnel excavation face to warn of surrounding rock disasters on the tunnel excavation face; the camera is used to collect real-time image data of the tunnel excavation face, and the data is submitted to a deep learning model for water flow area identification to warn of sudden mud and water gushing disasters; at least one gas sensor is set to detect the concentration values ​​of different types of gases in the tunnel where the tunnel excavation face is located to warn of gas disasters; the solution integrates multiple functions and can realize surrounding rock disaster warnings, sudden mud and water gushing disaster warnings and gas disaster warnings through one device, which is more intelligent and convenient, and effectively reduces the operational risks of on-site construction personnel.

[0039] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0040] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0041] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0042] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention. It should be noted that similar numbers and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0043] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for integrated monitoring and early warning of tunnel excavation surface, characterized in that: The method comprises: Receive the three-dimensional point cloud data collected by the laser radar emitting a laser beam to the tunnel excavation surface, filter out evaluation data from the three-dimensional point cloud data, build an evaluation template based on the evaluation data, and traverse the distance values ​​between the subsequently collected real-time three-dimensional point cloud data and the evaluation template. If there are more than a threshold number of real-time three-dimensional point cloud data with distance values ​​greater than a predetermined threshold, then issue a tunnel excavation surface surrounding rock disaster warning; Receive real-time image data collected by a camera on the tunnel excavation surface, identify the real-time image data through a pre-built deep learning model, and issue a mud and water disaster warning if the area of ​​flowing water in the real-time image data is greater than a set threshold; Receive gas concentration data of the tunnel where the tunnel excavation face is located monitored by at least one gas sensor, and issue a gas disaster warning if the gas concentration data exceeds a corresponding concentration threshold.

2. The method for integrated monitoring and early warning of tunnel excavation face according to claim 1, characterized in that: The step of filtering out evaluation data from the three-dimensional point cloud data comprises: A predetermined number of continuous point cloud data whose states have not changed are selected from the three-dimensional point cloud data and spliced ​​as evaluation data.

3. The method for integrated monitoring and early warning of tunnel excavation face according to claim 1, characterized in that: The step of constructing an evaluation template based on the evaluation data comprises: Using Poisson reconstruction to construct a triangulated evaluation network template for each of the evaluation data; The triangulated evaluation network template is grid-blocked according to predetermined specifications to obtain an evaluation template.

4. The method for integrated monitoring and early warning of tunnel excavation face according to claim 3, characterized in that: The step of traversing the distance value between the subsequently collected real-time three-dimensional point cloud data and the evaluation template comprises: According to the grid blocks of the evaluation template, the distance value between the subsequently collected real-time three-dimensional point cloud data and the evaluation template in the corresponding grid block is calculated.

5. The method for integrated monitoring and early warning of tunnel excavation face according to claim 1, characterized in that: The process of building the deep learning model includes: Collecting a plurality of target image data of the tunnel excavation surface by the camera; Marking each of the target image data respectively, wherein the marks include a dry area, a wet area, and a flowing water area; The deep learning model is trained using the labeled multiple target image data to obtain a constructed deep learning model.

6. The method for integrated monitoring and early warning of tunnel excavation face according to claim 5, characterized in that: The step of identifying the real-time image data by using a pre-built deep learning model, and providing an early warning of mud and water gushing disaster if the area of ​​flowing water in the real-time image data is greater than a set threshold, comprises: The real-time image data is converted into a tensor through a pre-built deep learning model, and the tensor is identified, and the dry area, wet area and flowing water area in the real-time image data are marked with different colors. If the area of ​​flowing water in the real-time image data is larger than the set threshold, a mud and water disaster alarm is issued.

7. The method for integrated monitoring and early warning of tunnel excavation face according to claim 1, characterized in that: The gas sensors include five, which are respectively used to monitor the oxygen concentration, carbon monoxide concentration, carbon dioxide concentration, methane concentration and hydrogen sulfide concentration. If the concentration of any gas exceeds the corresponding concentration threshold, a gas disaster warning is issued.

8. The method for integrated monitoring and early warning of tunnel excavation face according to claim 7, characterized in that: The concentration threshold of the oxygen concentration shall not be lower than 20%, the concentration threshold of the carbon monoxide concentration shall not be higher than 30%, the concentration threshold of the carbon dioxide concentration shall not be higher than 0.5%, the concentration threshold of the methane concentration shall not be higher than 1%, and the concentration threshold of the hydrogen sulfide concentration shall not be higher than 10%.

9. The method for integrated monitoring and early warning of tunnel excavation face according to claim 1, characterized in that: The tunnel excavation face surrounding rock disaster warning, mud and water gushing disaster warning, and gas disaster warning are issued by warning lights with different colors according to set frequencies, and / or by buzzers with different frequencies.

10. An integrated monitoring and early warning device for tunnel excavation surface, characterized in that: The device includes a laser radar, a camera, at least one gas sensor and a processor. The laser radar emits a laser beam to the tunnel excavation surface to collect three-dimensional point cloud data, and transmits it to the processor, the processor filters out evaluation data from the three-dimensional point cloud data, builds an evaluation template based on the evaluation data, and traverses the distance values ​​between the subsequently collected real-time three-dimensional point cloud data and the evaluation template. If there are real-time three-dimensional point cloud data with a distance value greater than a predetermined threshold value exceeding a threshold value, a tunnel excavation surface surrounding rock disaster warning is issued; The camera collects real-time image data of the tunnel excavation surface and transmits it to the processor. The processor recognizes the real-time image data through a pre-built deep learning model. If the area of ​​flowing water in the real-time image data is greater than a set threshold, a mud and water gushing disaster warning is issued; The at least one gas sensor monitors gas concentration data of the tunnel where the tunnel excavation face is located and transmits the data to the processor. If the gas concentration data exceeds a corresponding concentration threshold, a gas disaster warning is issued.

Images