Underground detection method and device based on robot

Abstract

The invention relates to the technical field of mine detection, in particular to an underground detection method and device based on a robot. The method comprises the following steps: controlling a robot to perform primary inspection according to inspection paths for node communication of a to-be-inspected node, a mine detection terminal point and a movement starting point of the robot; in response to an obstacle scanned by a laser radar carried by the robot in the one-time inspection process, if the width of the obstacle is greater than a first preset threshold value and the elevation is greater than a second preset threshold value, marking the inspection path as a closed path; all closed paths in the map are removed, the shortest path is taken as a target, other inspection paths are communicated to plan an optimal path for the robot to carry out secondary inspection, and the robot is controlled to carry out secondary inspection so as to identify potential risks of the mine laneway; the problem that after an accident occurs, the accident risk is large due to the fact that manual field measurement is conducted and whether underground repair work can be conducted or not is judged can be effectively solved.

Description

Technical Field

[0001] The present application relates to the technical field of mine detection, and in particular to a robot-based underground detection method and device. Background Art

[0002] The geological structure of the area where the mine is located is complex, such as faults and folds. The instability of these structures will cause the movement of surface or underground rock strata. In addition, the movement of coal and rock strata caused by coal mining itself leads to frequent rock bursts, which squeezes the surrounding rock strata of the mine tunnels and suddenly increases the unsafe factors.

[0003] At present, mine inspections are mostly organized before accidents occur, while after accidents occur, manual on-site measurements are conducted to determine whether underground repair work can be carried out, which poses a high risk of accidents. Summary of the invention

[0004] Based on this, it is necessary to provide a robot-based underground detection method and device to address the above technical problems.

[0005] In a first aspect, the present application provides a method for underground detection based on a robot, the method comprising:

[0006] Mark the end point of mine detection based on the map of the acquired mine tunnels, as well as multiple nodes to be inspected in the mine work;

[0007] Connect the nodes to be inspected, the end point of the mine detection and the starting point of the robot's movement to obtain multiple inspection paths for the robot, and control the robot to perform an inspection along each inspection path;

[0008] In response to an obstacle being scanned by the laser radar carried by the robot during an inspection, two-dimensional point cloud data of the mine tunnel at the corresponding position is obtained, and the width and elevation information of the obstacle are identified based on the two-dimensional point cloud data;

[0009] If the width of the obstacle is greater than the first preset threshold and the elevation is greater than the second preset threshold, the inspection path is marked as a closed path; the mark of the closed path is used to instruct the staff to carry out repairs;

[0010] Eliminate each closed path in the map, connect the remaining inspection paths with the shortest path as the goal, plan the optimal path for the robot to perform a secondary inspection, and control the robot to perform a secondary inspection to identify potential risks in the mine tunnels.

[0011] In one embodiment, the step of identifying potential risks in a mine tunnel includes:

[0012] During the robot's secondary inspection, the robot acquires image data of the mine tunnel based on the camera it carries;

[0013] Construct an image recognition model, obtain mine tunnel defect images according to defect types and input them into the image recognition model to obtain a trained image recognition model; defect types include surrounding rock cracks and surrounding rock deformation;

[0014] The image data is input into the trained image recognition model according to the inspection path to obtain the defect types existing in the inspection path and the location distribution corresponding to each defect type.

[0015] In one embodiment, the method further comprises:

[0016] In response to the defect type being a surrounding rock crack, the depth of the surrounding rock crack and the cracking degree distribution are determined by laser scanning the corresponding position of the surrounding rock crack;

[0017] Based on the pre-acquired structural strength of the surrounding rock, the depth of the surrounding rock cracks and the distribution of the cracking degree, the stress intensity at the corresponding position of the surrounding rock cracks is evaluated;

[0018] In response to the defect type being surrounding rock deformation, the deformation amount of the position corresponding to the surrounding rock deformation is scanned by laser;

[0019] Based on the structural strength of the surrounding rock and the deformation amount at the corresponding position of the surrounding rock deformation, the stress intensity at the corresponding position of the surrounding rock deformation is evaluated;

[0020] According to the location distribution of the defect locations and the stress intensity of the defect locations, the digital twin technology is used to simulate the risk probability of overall collapse of the corresponding inspection path, and when the risk probability is greater than the first preset percentage, a danger warning message is output; the danger warning information is used to indicate the increase in the number of support structures and the strength of the support structures.

[0021] In one embodiment, the robot includes a positive pressure explosion-proof and electrostatic protection structure; the method further includes:

[0022] Conduct gas concentration detection along the inspection route;

[0023] In response to the gas concentration at the gas accumulation location exceeding a preset concentration, calling parameter data of a fan closest to the gas accumulation location; the parameter data includes air supply volume and fan speed;

[0024] Determine whether the fan speed is less than the preset speed. If so, output a fan fault prompt message. If not, obtain the actual air volume of the fan based on the air volume detection device carried by the robot;

[0025] If the actual air volume is less than the supply air volume by more than a third preset threshold, a ventilation duct blockage prompt message is output.

[0026] In one embodiment, the method further comprises:

[0027] When the actual air volume is not less than the air supply volume exceeding the third preset threshold, obtaining the distance between the surrounding rock crack and the gas accumulation position;

[0028] If the distance between the surrounding rock crack and the gas accumulation position is less than the preset distance, the gas concentration at the corresponding position of the surrounding rock crack is obtained at a preset time interval, and the change in gas concentration per unit time is calculated;

[0029] The air volume of the fan is adjusted based on the cross-sectional area of ​​the mine tunnel, the distance between the fan and the gas extraction pipeline, and the change in gas concentration per unit time.

[0030] In one embodiment, the method further comprises:

[0031] After the second inspection is completed, each closed path is counted and the location of the obstacles on the closed path is marked as a re-inspection node;

[0032] The interval distances between each re-inspection node are calculated respectively, and each re-inspection node is connected in the map with the shortest distance as the target and the motion path cannot be repeated as the restriction condition to obtain the re-inspection path;

[0033] The robot is controlled to perform re-inspection along the re-inspection path to identify the remaining obstacles in each closed path.

[0034] In one embodiment, the node to be inspected includes an emergency shelter chamber; the method further includes:

[0035] Obtain information on energy supply conditions in the emergency shelter chamber to determine the energy supply location;

[0036] During the re-inspection process, the robot's energy reserve is monitored, and based on the energy reserve, the robot's travel distance and the shortest distance between the robot's current position and each energy supply location are calculated;

[0037] In response to the difference between the feasible path and the shortest path being lower than a second preset percentage, controlling the robot to stop rechecking and move to an energy supply position corresponding to the shortest path;

[0038] The interval distances between each re-inspection node and the energy supply position corresponding to the shortest distance are recalculated, and the re-inspection path is replanned with the restriction that the movement path between each re-inspection node cannot be repeated.

[0039] In a second aspect, the present application provides a robot-based downhole detection device, the device comprising:

[0040] A marking module, used to mark the end point of mine detection and multiple nodes to be inspected in the mine work based on the map of the acquired mine tunnel;

[0041] The control module is used to connect the node to be inspected, the end point of the mine detection and the starting point of the robot's movement to obtain multiple inspection paths of the robot, and control the robot to perform an inspection according to each inspection path;

[0042] An acquisition module is used to obtain two-dimensional point cloud data of the mine tunnel at the corresponding position in response to an obstacle being scanned by the laser radar carried by the robot during an inspection, and to identify the width and elevation information of the obstacle based on the two-dimensional point cloud data;

[0043] The marking module is further used to mark the inspection path as a closed path if the width of the obstacle is greater than a first preset threshold and the elevation is greater than a second preset threshold; the mark of the closed path is used to instruct the staff to perform repairs;

[0044] The path planning module is used to eliminate the closed paths in the map, connect the remaining inspection paths with the shortest path as the goal, plan the optimal path for the robot to perform secondary inspection, and control the robot to perform secondary inspection to identify potential risks in mine tunnels.

[0045] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in the first aspect of the present application are implemented.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present application.

[0047] The above-mentioned robot-based underground detection method and device can mark the end point of the mine detection that needs to be inspected and the nodes to be inspected based on the acquired mine tunnel map, and connect the marked nodes with the robot's moving starting point, and then control the robot to perform an inspection to scan the obstacles that block the mine tunnel, and combine the two-dimensional point cloud data to determine the width and elevation information of the obstacles to judge whether the staff can pass smoothly, so as to achieve the purpose of effective path identification and provide correct path instructions for subsequent work; then the inaccessible paths are eliminated as closed paths, and according to the passable inspection paths, the optimal path is planned for a second inspection with the shortest path as the goal, so as to quickly traverse each inspection path, further identify the potential risks of the mine tunnel, and thus effectively avoid the problem of high accident risks caused by manual on-site measurement and judgment of whether underground repair work can be carried out after the accident occurs. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A flowchart of the steps of planning a path and performing a primary inspection and a secondary inspection in an embodiment;

[0050] Figure 2 A flowchart of the steps of defect identification in one embodiment;

[0051] Figure 3 A flowchart of the steps of stress distribution identification in one embodiment;

[0052] Figure 4 A flowchart of the steps of checking a fan in one embodiment;

[0053] Figure 5 A flowchart of the steps of adjusting the air supply volume of a fan in one embodiment;

[0054] Figure 6 A flowchart of the steps of reviewing path planning in one embodiment;

[0055] Figure 7 A flowchart of steps for re-planning a re-inspection path taking energy replenishment into consideration in one embodiment;

[0056] Figure 8 The figure is a framework diagram of a robot-based downhole detection device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0059] In an exemplary embodiment, a method for analyzing cigarette user feedback is provided, such as Figure 1As shown, the method includes the following steps S102 to S110. Among them:

[0060] S102, marking the mine detection end point and a plurality of mine working nodes to be inspected based on the acquired map of the mine tunnel.

[0061] Specifically, the end point of mine detection is used to indicate the farthest position from the robot's moving starting point that needs to be reached during the mine detection process; the nodes to be inspected may include the location of mine tunnel collapse predicted by survey, and may also include emergency refuge chambers for emergency evacuation, as well as various transfer mechanisms located between the end point of mine detection and the moving starting point.

[0062] S104, connecting the node to be inspected, the mine detection end point and the robot's movement starting point to obtain multiple inspection paths of the robot, and controlling the robot to perform an inspection along each inspection path.

[0063] Specifically, multiple inspection paths are divided by connecting nodes, and inspection planning is carried out one by one according to the inspection paths. After the inspection of any inspection path is completed, corresponding measures can be taken to deal with the actual collapse of each inspection path and adjust the status of the robot in time.

[0064] Furthermore, by identifying according to the path, when the inspection process takes a long time, the working position of other identified inspection paths will not be occupied.

[0065] S106, in response to an obstacle being scanned by the laser radar carried by the robot during an inspection process, two-dimensional point cloud data of the mine tunnel at the corresponding position is obtained, and the width and elevation information of the obstacle are identified based on the two-dimensional point cloud data.

[0066] Specifically, the step of identifying the width and elevation information of the obstacle based on the two-dimensional point cloud data may include filtering the two-dimensional point cloud data to remove noise and outliers in the point cloud; converting the filtered two-dimensional point cloud data to a polar coordinate system, and segmenting the obstacle from the ground based on the elevation and angle information of the obstacle (which can be based on RANSAC; Random Sample Consensus algorithm); clustering the non-ground points after the point cloud segmentation to identify individual obstacles, and then performing feature extraction on the clustered point cloud data to obtain the width and elevation information of the obstacle.

[0067] S108, if the width of the obstacle is greater than the first preset threshold and the elevation is greater than the second preset threshold, the inspection path is marked as a closed path; the mark of the closed path is used to instruct the staff to perform repairs.

[0068] Specifically, the first threshold value can be set according to the width of the lane that the staff can easily pass through, and the second threshold value can be set according to the height of the obstacle that the staff can easily pass through. The specific values ​​of the first threshold value and the second threshold value can be set based on the actual situation during the specific implementation process, and no specific restrictions are made here.

[0069] S110, eliminating each closed path in the map, and connecting the remaining inspection paths with the shortest path as the goal to plan the optimal path for the robot to perform a secondary inspection, and controlling the robot to perform a secondary inspection to identify potential risks in the mine tunnels.

[0070] Specifically, the total distances that the robot needs to move through the inspection paths after removing the closed paths in different orders can be calculated respectively, and a combination of inspection paths with the shortest total distance can be selected.

[0071] Furthermore, the potential risks that need to be identified during the secondary inspection process may be locations where collapse may occur, or locations where falling objects, water seepage, and gas may occur, which requires longer working time. Therefore, by shortening the route that the inspection requires to return, delays in secondary identification can be avoided.

[0072] In an exemplary embodiment, during an inspection process, if the robot cannot cross an obstacle, the robot abandons the current inspection path and moves to the next planned inspection path to continue the first inspection.

[0073] The embodiment of the present application aims to provide a robot-based underground detection method and device, which can mark the end point of the mine detection that needs to be inspected and the nodes to be inspected based on the acquired mine tunnel map, and connect the marked nodes with the robot's movement starting point, and then control the robot to perform an inspection to scan the obstacles that block the mine tunnel, and determine the width and elevation information of the obstacles in combination with the two-dimensional point cloud data to judge whether the staff can pass smoothly, so as to achieve the purpose of effective path identification and provide correct path instructions for subsequent work; then the inaccessible paths are eliminated as closed paths, and according to the passable inspection paths, the optimal path is planned for a second inspection with the shortest path as the goal, so as to quickly traverse each inspection path, further identify the potential risks of the mine tunnel, and effectively avoid the problem of high accident risks caused by manual on-site measurement and judgment of whether underground repair work can be carried out after the accident occurs.

[0074] In an exemplary embodiment, Figure 2 As shown, the step of identifying potential risks in a mine tunnel includes the following steps S1102 to S1106. Among them:

[0075] S1102, during the secondary inspection of the robot, image data of the mine tunnel is obtained based on the camera carried by the robot.

[0076] S1104, constructing an image recognition model, obtaining mine tunnel defect images according to defect types and inputting them into the image recognition model to obtain a trained image recognition model; defect types include surrounding rock cracks and surrounding rock deformations.

[0077] Specifically, mine tunnel defect images for training image recognition models can be collected based on surrounding rock cracks and surrounding rock deformations that occur in other mines with the same tunnel type, and the image recognition model can be trained by extracting defect features of different defect types.

[0078] Furthermore, since the severity of surrounding rock cracks and surrounding rock deformations varies, it is necessary to ensure a sufficient number of mine tunnel defect images for training the image recognition model.

[0079] S1106, inputting the image data into the trained image recognition model according to the inspection path, obtaining the defect types existing in the inspection path and the position distribution corresponding to each defect type.

[0080] Specifically, the dangerous locations are marked by the location distribution of defect types, so as to effectively avoid secondary collapse of the defective locations causing loss of life and property during the mine tunnel maintenance process.

[0081] In an exemplary embodiment, Figure 3 As shown, the method further includes the following steps S202 to S210.

[0082] in:

[0083] S202, in response to the defect type being a surrounding rock crack, determining the depth and cracking degree distribution of the surrounding rock crack by laser scanning a corresponding position of the surrounding rock crack.

[0084] Specifically, by laser scanning the crack and returning information including distance, zenith distance, slope and reflectivity, the three-dimensional coordinate information of a certain point of the measured crack is obtained; the recognition algorithm involved can be transformed through the existing algorithm and will not be repeated here.

[0085] S204: Based on the pre-acquired structural strength of the surrounding rock, the depth of the surrounding rock cracks, and the distribution of the cracking degree, the stress intensity at the position corresponding to the surrounding rock cracks is evaluated.

[0086] It is understandable that in the event of rock bursts and other phenomena, the pressure on the upper layer of the surrounding rock changes, resulting in the pressure exceeding the surrounding rock stress and causing cracks in the surrounding rock; therefore, by evaluating the depth and distribution of the cracks, combined with the structural strength of the surrounding rock itself, the stress intensity of the surrounding rock at the corresponding position of the crack can be estimated.

[0087] S206, in response to the defect type being surrounding rock deformation, scanning the deformation amount at a position corresponding to the surrounding rock deformation by laser.

[0088] Specifically, the deformation amount can be determined by the height difference between the position with the maximum deformation and the position without deformation determined during the laser scanning process.

[0089] S208, based on the structural strength of the surrounding rock and the deformation amount of the surrounding rock at the corresponding position, evaluate the stress intensity at the position corresponding to the deformation of the surrounding rock.

[0090] Specifically, when the surrounding rock does not crack, it means that the pressure on the surrounding rock is still within the stress intensity range. Therefore, based on the structural strength of the surrounding rock and the deformation amount of the surrounding rock at the corresponding position of the deformation, the stress intensity at the corresponding position of the surrounding rock deformation can be evaluated.

[0091] S210, based on the position distribution of the defect location and the stress intensity of the defect location, the digital twin technology is used to simulate the risk probability of overall collapse of the corresponding inspection path, and when the risk probability is greater than a first preset percentage, a danger warning message is output; the danger warning information is used to indicate an increase in the number of support structures and the strength of the support structures.

[0092] Specifically, if there are multiple defects in any inspection path, the surrounding rock section may have excessive pressure on the upper coal strata, thus facing the risk of overall collapse. Therefore, digital twin technology is used to simulate the probability of overall collapse in the case of multiple defects.

[0093] Furthermore, during the simulation process, it is also possible to estimate the surrounding rock stress at the non-defective position through the defect position, so as to more accurately consider the stress changes of the entire inspection path.

[0094] Furthermore, the first preset percentage can be obtained by combining the percentage obtained by estimating the risk of surrounding rock collapse by the same method when collapse occurs in other coal mines, combined with other possible causes of collapse for risk assessment, and no specific restrictions are made here.

[0095] In an exemplary embodiment, the robot includes a positive pressure explosion-proof and electrostatic protection structure, such as Figure 4 As shown, the method further includes the following steps S302 to S308. Among them:

[0096] S302, performing gas concentration detection along the inspection route.

[0097] Specifically, under normal circumstances, based on coal mine design, gas concentration should be controlled below the dangerous level. However, when phenomena such as ground pressure impact occur, gas leakage may occur in the surrounding rock, coal seams and other geological strata, thereby increasing the gas concentration.

[0098] Specifically, the robot adopts positive pressure explosion-proof and electrostatic protection structure can effectively avoid igniting methane, carbon monoxide and other substances in the gas, and can therefore be used for gas concentration detection.

[0099] S304, in response to the gas concentration at the gas accumulation location exceeding the preset concentration, calling the parameter data of the fan closest to the gas accumulation location; the parameter data includes the air supply volume and the fan speed.

[0100] Specifically, gas accumulation may also be caused by fan failure or exhaust pipe blockage or breakage during collapse.

[0101] S306, determining whether the fan speed is less than a preset speed, if so, outputting a fan fault prompt message, if not, obtaining the actual air volume of the fan based on the air volume detection device carried by the robot;

[0102] S308: If the actual air volume is less than the air supply volume by more than a third preset threshold, output a ventilation duct blockage prompt message.

[0103] Specifically, the actual air volume is less than the supply air volume by more than a third threshold value, which is used to indicate that there is a certain level of difference between the actual air volume and the preset air volume, indicating that the ventilation pipe is blocked.

[0104] In an exemplary embodiment, Figure 5 As shown, the method further includes the following steps S402 to S406. Among them:

[0105] S402: When the actual air volume is not less than the air supply volume exceeding the third preset threshold, the distance between the surrounding rock crack and the gas accumulation position is obtained.

[0106] Specifically, the actual air volume is not less than the air volume exceeding the third preset threshold, indicating that the ventilation system is not damaged, but other possible causes of gas leakage have occurred. Therefore, the gas accumulation is eliminated by judging the relationship between surrounding rock cracks and gas leakage.

[0107] S404: If the distance between the surrounding rock fracture and the gas accumulation position is less than a preset distance, the gas concentration at the position corresponding to the surrounding rock fracture is obtained at a preset time interval, and the change in gas concentration per unit time is calculated.

[0108] Specifically, since the location where the robot detects that the gas concentration exceeds the standard during its movement is not necessarily the location with the highest gas concentration, when calculating the gas concentration at the location with the highest gas concentration, it is necessary to consider the gas concentration caused by the gas leakage from the new crack location and the gas existing in the mine itself. Therefore, it is necessary to calculate the gas concentration at the crack location to determine the change in the concentration of the leaked gas.

[0109] S406, adjusting the air supply volume of the fan based on the cross-sectional area of ​​the mine tunnel, the distance between the fan and the gas extraction pipeline, and the change in gas concentration per unit time.

[0110] Specifically, the air supply volume is adjusted to reduce the gas concentration just below the flammable value.

[0111] Specifically, the spatial volume between the fan and the gas extraction pipeline can be calculated based on the cross-sectional area of ​​the mine tunnel and the distance between the fan and the gas extraction pipeline. The time required for the gas concentration in the space (inspection path) to rise to a flammable concentration can be determined based on the spatial volume. The fan air supply can be adjusted based on the time amount so that the increase in the fan air supply within the time amount exceeds the change in gas concentration. The increase in air supply is used to represent the increase in air supply based on the original air supply designed for gas evacuation.

[0112] In an exemplary embodiment, Figure 6 As shown, the method further includes the following steps S502 to S506.

[0113] in:

[0114] S502, after the second inspection is completed, each closed path is counted, and the position of the obstacle on the closed path is marked as a re-inspection node.

[0115] Specifically, the robot may not be able to cross a closed path due to obstacles, so planning the mobile path according to the inspection path will result in too many repeated inspection paths, and it is impossible to effectively calculate the shortest distance between the inspection paths. Therefore, targeting the fault object can effectively avoid repeated motion paths.

[0116] S504, respectively calculating the interval distances between the re-inspection nodes, and connecting the re-inspection nodes in the map with the shortest distance as the goal and the motion path being non-repeatable as the restriction condition, to obtain a re-inspection path;

[0117] S506, controlling the robot to perform re-inspection along the re-inspection path to identify remaining obstacles in each closed path.

[0118] Specifically, there may be multiple obstacles in a patrol path, so only identifying obstacles from one direction cannot improve the efficiency of obstacle identification. By connecting the re-inspection nodes, the packaging robot can effectively traverse the path at both ends of the obstacle.

[0119] In an exemplary embodiment, the node to be inspected includes an emergency shelter chamber; Figure 7 As shown, the method further includes the following steps S602 to S608. Among them:

[0120] S602, obtaining information on energy supply conditions in the emergency shelter chamber to determine the energy supply location.

[0121] Specifically, an emergency refuge chamber is a special facility designed in underground workplaces such as coal mines to provide a safe refuge in emergency situations. It is usually located at a certain depth underground and is equipped with necessary survival facilities such as oxygen supply, food, water, communication equipment, energy supply, etc., for miners to survive in the short term in the event of an accident or emergency.

[0122] S604, monitoring the energy reserve of the robot during the re-inspection process, and calculating the travel distance of the robot and the shortest distance between the current position of the robot and each energy supply position based on the energy reserve.

[0123] S606, in response to the difference between the feasible path distance and the shortest path distance being lower than a second preset percentage, controlling the robot to stop rechecking and move to an energy supply position corresponding to the shortest path distance;

[0124] S608, recalculating the interval distances between each re-inspection node and the energy supply position corresponding to the shortest distance, and re-planning the re-inspection path with the restriction that the movement path between each re-inspection node cannot be repeated.

[0125] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0126] Based on the same inventive concept, the embodiment of the present application also provides a robot-based downhole detection device for implementing the robot-based downhole detection method mentioned above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations of one or more embodiments of the robot-based downhole detection device provided below can refer to the above limitations of the robot-based downhole detection method, and will not be repeated here.

[0127] Second, as Figure 8 As shown, the present application provides a robot-based downhole detection device 800, the device comprising:

[0128] A marking module 801 is used to mark the mine detection end point and multiple nodes to be inspected in the mine work based on the acquired map of the mine tunnel;

[0129] The control module 802 is used to connect the node to be inspected, the end point of the mine detection and the movement starting point of the robot to obtain multiple inspection paths of the robot, and control the robot to perform an inspection according to each inspection path;

[0130] The acquisition module 803 is used to obtain the two-dimensional point cloud data of the mine tunnel at the corresponding position in response to an obstacle being scanned by the laser radar carried by the robot during an inspection process, and to identify the width and elevation information of the obstacle based on the two-dimensional point cloud data;

[0131] The marking module 801 is further used to mark the inspection path as a closed path if the width of the obstacle is greater than a first preset threshold and the elevation is greater than a second preset threshold; the mark of the closed path is used to instruct the staff to perform repairs;

[0132] The path planning module 804 is used to eliminate the closed paths in the map, connect the remaining inspection paths with the shortest path as the goal, plan the optimal path for the robot to perform secondary inspection, and control the robot to perform secondary inspection to identify potential risks in the mine tunnels.

[0133] Each module in the robot-based downhole detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0134] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the remote update method of the above application when executing the computer program.

[0135] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the automatic deployment and recovery method of the buoy as described above.

[0136] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the automatic deployment and recovery method of the buoy as described above.

[0137] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0138] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0139] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for underground detection based on a robot, characterized in that: The method comprises: Mark the end point of mine detection based on the map of the acquired mine tunnels, as well as multiple nodes to be inspected in the mine work; Connecting the node to be inspected, the mine detection end point and the movement starting point of the robot to obtain multiple inspection paths of the robot, and controlling the robot to perform an inspection along each inspection path; In response to an obstacle being scanned by the laser radar carried by the robot during the one inspection process, two-dimensional point cloud data of the mine tunnel at the corresponding position is acquired, and the width and elevation information of the obstacle are identified based on the two-dimensional point cloud data; If the width of the obstacle is greater than a first preset threshold and the elevation is greater than a second preset threshold, the inspection path is marked as a closed path; the mark of the closed path is used to instruct the staff to perform repairs; The closed paths in the map are eliminated, and the remaining inspection paths are connected with the shortest path as the goal to plan the optimal path for the robot to perform a secondary inspection, and the robot is controlled to perform a secondary inspection to identify potential risks in the mine tunnel.

2. The method according to claim 1, characterized in that The step of identifying the potential risks of the mine tunnel includes: During the secondary inspection by the robot, image data of the mine tunnel is acquired based on a camera carried by the robot; Constructing an image recognition model, acquiring the mine tunnel defect image according to the defect type and inputting it into the image recognition model to obtain a trained image recognition model; the defect type includes surrounding rock cracks and surrounding rock deformation; The image data is input into the trained image recognition model according to the inspection path to obtain the defect types existing in the inspection path and the position distribution corresponding to each defect type.

3. The method according to claim 2, characterized in that The method further comprises: In response to the defect type being a surrounding rock crack, a corresponding position of the surrounding rock crack is scanned by laser to determine the depth and cracking degree distribution of the surrounding rock crack; Based on the pre-acquired structural strength of the surrounding rock, the depth of the surrounding rock cracks, and the cracking degree distribution, the stress intensity at the position corresponding to the surrounding rock cracks is evaluated; In response to the defect type being surrounding rock deformation, scanning the deformation amount of the position corresponding to the surrounding rock deformation by laser; Based on the structural strength of the surrounding rock and the deformation amount of the position corresponding to the deformation of the surrounding rock, the stress intensity at the position corresponding to the deformation of the surrounding rock is evaluated; According to the position distribution of the defect positions and the stress intensity of the defect positions, the digital twin technology is used to simulate the risk probability of overall collapse of the corresponding inspection path, and when the risk probability is greater than a first preset percentage, a danger warning message is output; the danger warning message is used to indicate the increase in the number of support structures and the strength of the support structures.

4. The method according to claim 3, characterized in that The robot includes a positive pressure explosion-proof and electrostatic protection structure; the method further includes: Performing gas concentration detection along the inspection route; In response to the gas concentration at the gas accumulation location exceeding a preset concentration, calling parameter data of a fan closest to the gas accumulation location; the parameter data includes air supply volume and fan speed; Determine whether the fan speed is less than a preset speed, and if so, output a fan fault prompt message; if not, obtain the actual air volume of the fan based on the air volume detection device carried by the robot; If the actual air volume is less than the air supply volume by more than a third preset threshold, a ventilation duct blockage prompt message is output.

5. The method according to claim 4, characterized in that The method further comprises: When the actual air volume is not less than the air supply volume by more than a third preset threshold, obtaining the distance between the surrounding rock crack and the gas accumulation position; If the distance between the surrounding rock crack and the gas accumulation position is less than a preset distance, the gas concentration at the position corresponding to the surrounding rock crack is obtained at a preset time interval, and the change in gas concentration per unit time is calculated; The air supply volume of the fan is adjusted based on the cross-sectional area of ​​the mine tunnel, the distance between the fan and the gas extraction pipeline, and the change in gas concentration per unit time.

6. The method according to claim 1, characterized in that The method further comprises: After the secondary inspection is completed, each of the closed paths is counted, and the positions of obstacles on the closed paths are marked as re-inspection nodes; The interval distances between the re-inspection nodes are calculated respectively, and the re-inspection nodes are connected in the map with the shortest distance as the target and the motion path being non-repeatable as the restriction condition to obtain the re-inspection path; The robot is controlled to perform re-inspection along the re-inspection path to identify remaining obstacles in each of the closed paths.

7. The method according to claim 6, characterized in that The node to be inspected includes an emergency shelter chamber; the method further includes: Obtaining information on energy supply conditions in the emergency shelter chamber to determine an energy supply location; During the rechecking process, the remaining energy of the robot is monitored, and based on the remaining energy, a distance that the robot can travel and the shortest distance between the current position of the robot and each of the energy replenishment positions are calculated; In response to the difference between the feasible path and the shortest path being lower than a second preset percentage, controlling the robot to stop rechecking and move to an energy supply position corresponding to the shortest path; The interval distances between each re-inspection node and the energy supply position corresponding to the shortest distance are recalculated, and the re-inspection path is re-planned with the restriction that the movement path between each re-inspection node cannot be repeated.

8. A robot-based downhole detection device, characterized in that: The device comprises: A marking module, used to mark the end point of mine detection and multiple nodes to be inspected in the mine work based on the map of the acquired mine tunnel; A control module, used for connecting the node to be inspected, the mine detection end point and the movement starting point of the robot to obtain multiple inspection paths of the robot, and controlling the robot to perform an inspection according to each inspection path; an acquisition module, configured to acquire two-dimensional point cloud data of a mine tunnel at a corresponding position in response to an obstacle being scanned by the laser radar carried by the robot during the one inspection process, and to identify the width and elevation information of the obstacle based on the two-dimensional point cloud data; The marking module is further used to mark the inspection path as a closed path if the width of the obstacle is greater than a first preset threshold and the elevation is greater than a second preset threshold; the mark of the closed path is used to instruct the staff to perform repairs; A path planning module is used to eliminate the closed paths in the map, connect the remaining inspection paths with the shortest path as the goal, plan the optimal path for the robot to perform a secondary inspection, and control the robot to perform a secondary inspection to identify potential risks in the mine tunnels.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images