Automatic secondary fastening method and system for roadway supporting component

Abstract

The invention belongs to the field of mine intelligent construction, and provides an automatic roadway support component secondary fastening method and system for solving the problem of low roadway support intelligent degree, and the method comprises the steps: obtaining and processing a three-dimensional image of a roadway roof, and obtaining the point cloud data of the roadway roof; on the basis of comparison between the point cloud data and standard template point cloud data, estimating pose information of the roadway roof support component; the mechanical arm is controlled to move to the position below the roadway top plate supporting component based on the pose information, an image of the roadway top plate supporting component is collected, the loose roadway top plate supporting component is determined based on the image of the roadway top plate supporting component, and the loose roadway top plate supporting component is precisely positioned through a minimum circumcircle positioning method; according to the precise positioning result, the mechanical arm is controlled to conduct secondary fastening on the loose roadway roof supporting part, stability is good, precision is high, manpower input is reduced, the intelligent degree of mine roadway roof supporting is improved, and safety of roadway supporting is improved.

Description

Technical Field

[0001] The present invention belongs to the field of mine tunnel roof support safety protection and mine intelligent construction, and particularly relates to an automated tunnel support component secondary fastening method and system. Background Art

[0002] After excavation of underground coal mine tunnels, production stresses are redistributed. If roof support is not promptly maintained, the surrounding rock of the underground coal mine tunnels is likely to experience displacement, deformation, and damage. Therefore, to ensure the safe and smooth progress of underground coal mine tunneling, it is necessary to strengthen the control and management of roof support during tunneling. Bolting is the preferred support method for coal mine tunnels in my country. This method primarily utilizes supporting components such as anchors, trays, anchoring agents, steel belts, and mesh. The anchor's primary function is to resist shear and tensile stresses. The tray, the contact element between the surrounding rock and the end of the anchor, primarily applies appropriate torque to the nut, pressing the surface of the tunnel against the tray. This provides preload to the anchor, which is then diffused into the coal and rock mass, effectively improving the stress state of the surrounding rock. This prevents the opening of surrounding rock joints and fissures, structural surface sliding, and delamination.

[0003] To further enhance the stability of the tunnel roof support, the nuts securing the anchor bolts, cables, and trays must be tightened again after the first support is completed. This task requires dedicated workers, a significant amount of time, and materials, resulting in low efficiency. Summary of the Invention

[0004] In order to solve at least one of the above-mentioned technical problems existing in the prior art, the present invention provides an automated secondary fastening method and system for tunnel support components.

[0005] According to the first aspect, this embodiment provides an automated secondary fastening method for tunnel support components, comprising the following steps:

[0006] Acquiring a three-dimensional image of the tunnel roof and processing the three-dimensional image of the tunnel roof to obtain point cloud data of the tunnel roof;

[0007] estimating the position and posture information of the roadway roof support components based on the comparison of the point cloud data with the standard template point cloud data;

[0008] Controlling the robot arm to move to below the tunnel roof support component based on the posture information, while collecting images of the tunnel roof support component, determining loose tunnel roof support components based on the images of the tunnel roof support components, and then using a minimum circumscribed circle positioning method to achieve precise positioning of the loose tunnel roof support components;

[0009] According to the result of the precise positioning, the robotic arm is controlled to perform secondary tightening on the loose tunnel roof support component.

[0010] Preferably, processing the three-dimensional image of the tunnel roof includes:

[0011] The three-dimensional image of the tunnel roof is filtered using a Gaussian filter, and then point cloud key point detection algorithm is used to extract point cloud features, and the extracted point cloud features are segmented.

[0012] Preferably, comparing the point cloud data with the standard template point cloud data includes:

[0013] The KD-Tree nearest neighbor search method is used to search for and compare the point cloud data in the standard template point cloud data. Object recognition is performed based on the comparison results, and the objects corresponding to the standard template point cloud data are matched to estimate the position information of the tunnel roof support components.

[0014] Preferably, it also includes:

[0015] The positions of all the tunnel roof support components are determined based on the tunnel roof support component images, and the robotic arm is controlled to perform secondary tightening of all the tunnel roof support components.

[0016] According to a second aspect, this embodiment provides an automated secondary fastening system for roadway support components, which can be applied to the system described in the first aspect and any preferred embodiment, including:

[0017] Mobile robots for moving in the lanes;

[0018] A mechanical arm is mounted on the upper end of the mobile robot, and is used for the mobile robot to control the mechanical arm to perform secondary tightening of the tunnel roof support component according to the received posture information;

[0019] a first image acquisition device, mounted on the front upper portion of the mobile robot, for acquiring a three-dimensional image of the tunnel roof;

[0020] The second image acquisition device is installed at the end of the execution part of the robotic arm and is used to acquire images of the tunnel roof support components.

[0021] Preferably, the positions of the mobile robot and the second image acquisition device are calibrated.

[0022] Preferably, the first image acquisition device is a binocular structured light camera; and the second image acquisition device is a monocular camera.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The present invention adopts advanced machine vision methods to perform secondary tightening of the tunnel roof support components, which has good stability and high precision, reduces manpower input, improves the intelligence level of mine tunnel roof support, and enhances the safety of tunnel support. At the same time, the present invention realizes the three-dimensional scanning technology of mine tunnels, and monitors the deformation of the tunnel roof in real time through the collected three-dimensional image of the tunnel roof, which can also be used to assist in the positioning of underground equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 This is a flow chart of the secondary fastening method for automated roadway support components;

[0027] Figure 2 This is a structural diagram of the secondary fastening system for automated tunnel support components;

[0028] In the figure: 1-robot; 2-first image acquisition device; 3-robotic arm; 4-second image acquisition device. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention are clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other implementations derived by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts are within the scope of protection of the present invention.

[0030] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions under which the present invention can be implemented. Therefore, they have no substantive technical significance. Any structural modification, change in proportional relationship or adjustment of size should fall within the scope of the technical content disclosed in the present invention without affecting the efficacy and purpose that can be achieved by the present invention. It should be noted that in this specification, relational terms such as first and second are only used to distinguish one entity from several other entities, and do not necessarily require or imply any actual relationship or order between these entities.

[0031] The embodiments of the present invention are further described in detail below with reference to the accompanying drawings.

[0032] like Figure 2 As shown, an embodiment of the present invention provides a structural schematic diagram of an automated secondary fastening system for tunnel support components, the system comprising: a mobile robot 1 for moving in a tunnel;

[0033] A mechanical arm 3 is mounted on the upper end of the mobile robot 1 and is used for the mobile robot 1 to control the mechanical arm 3 to perform secondary tightening of the tunnel roof support components according to the received posture information;

[0034] A first image acquisition device 2 is installed at the front upper end of the mobile robot 1 and is used to acquire a three-dimensional image of the tunnel roof;

[0035] The second image acquisition device 4 is installed at the end of the execution part of the mechanical arm 3 and is used to acquire images of the tunnel roof support components.

[0036] Optionally, position calibration is performed on the mobile robot 1 and the second image acquisition device 4 .

[0037] Optionally, the first image acquisition device 2 is a binocular structured light camera; the second image acquisition device 4 is a monocular camera.

[0038] In this embodiment, the binocular structured light camera can perform a global scan as the mobile robot 1 moves, calculate the positional relationship between the roof tray in the mine tunnel and the mobile robot 1 based on the global scanning results, form a three-dimensional image of the tunnel roof, determine the posture information of the support components to be fastened based on the three-dimensional image of the tunnel roof, and establish a DQN (Deep Q-Network) network model at the same time. According to the positional relationship between the roof tray and the mobile robot 1, the autonomous movement path of the robot arm 3 is planned, and then the robot arm 3 is controlled to move to the bottom of the roof tray, and then the tunnel roof support components are precisely positioned by the monocular camera.

[0039] In this embodiment, to determine the three-dimensional coordinates of the tunnel roof support components, calibration is required between the second image acquisition device 4 and the mobile robot 1. Because the second image acquisition device 4 is mounted on the robotic arm 3, its position relative to the mobile robot 1 is fixed. Calibration can be performed based on the rotational and translational relationship between the mobile robot 1 and the robotic arm 3.

[0040] like Figure 1 As shown, an embodiment of the present invention provides an automated secondary fastening method for tunnel support components, comprising the following steps:

[0041] S1: Acquire a three-dimensional image of the tunnel roof, and process the three-dimensional image of the tunnel roof to obtain point cloud data of the tunnel roof.

[0042] Optionally, processing the three-dimensional image of the tunnel roof includes: filtering the three-dimensional image of the tunnel roof using a Gaussian filter, then extracting point cloud features using a point cloud key point detection algorithm, and segmenting the extracted point cloud features.

[0043] In this embodiment, when the first image acquisition device 2 acquires the three-dimensional image of the tunnel roof, it will be affected by natural light or diffuse reflection of laser by the object surface, so Gaussian filtering is used to filter the three-dimensional image of the tunnel roof.

[0044] In this embodiment, the Intrinsic Shape Signatures (ISS) algorithm is used to extract point cloud features. The ISS feature ISS(M) of a feature point M is calculated by describing the local shape information of the point cloud, which is the core of point cloud feature extraction.

[0045] ISS(M)=λ1(M)×λ2(M)

[0046] Where λ1(M) and λ2(M) are the principal curvatures of the feature point M.

[0047] After obtaining the point cloud features, the random sample consensus algorithm (RANSAC) is used to segment the extracted point cloud features because there are multiple object features in the three-dimensional image of the tunnel roof.

[0048] S2: Based on the comparison between the point cloud data and the standard template point cloud data, the position information of the tunnel roof support components is estimated.

[0049] Optionally, based on the comparison between the point cloud data and the standard template point cloud data, it includes: using the KD-Tree nearest neighbor search method to search in the standard template point cloud data for comparison with the point cloud data, performing object recognition according to the comparison results, matching the objects corresponding to the standard template point cloud data, and estimating the posture information of the tunnel roof support components.

[0050] In this embodiment, point cloud object recognition is achieved by matching the standard template point cloud data with the segmented point cloud features. A nearest neighbor search method (k-Dimensional Tree, KD-Tree) is used to search the standard template point cloud dataset for 3D point clouds of objects that are similar to the point cloud data collected in the actual project.

[0051] In this embodiment, the pose information of the point cloud data of the standard template is used to estimate the pose information of the point cloud at the actual engineering site.

[0052] S3: Based on the posture information, the robot arm 3 is controlled to move to the bottom of the tunnel roof support component, and at the same time, the image of the tunnel roof support component is collected, and the loose tunnel roof support component is determined based on the image of the tunnel roof support component, and then the minimum circumscribed circle positioning method is used to achieve precise positioning of the loose tunnel roof support component.

[0053] In this embodiment, after the position of the tunnel roof support component is obtained by the first image acquisition device 2, the robotic arm 3 is controlled to move to the bottom of the tunnel roof support component, and the second image acquisition device 4 is started to collect the image of the tunnel roof support component. According to the characteristics of the nut in the tunnel roof support component, the minimum circumscribed circle positioning method is used to determine whether the nut is a loose component. When the nut is a loose component, the robotic arm 3 is controlled to perform precise positioning. Otherwise, the robotic arm 3 is controlled to move to the bottom of other tunnel roof support components, and the loose tunnel roof support component is re-determined to achieve precise positioning of the loose tunnel roof support component.

[0054] In this embodiment, when the tunnel roof support component can be an anchor rod or an anchor cable, its position is determined based on the image of the tunnel roof support component, and the installation position and characteristics of the nut in the tunnel roof support component are determined based on the point cloud target recognition result. The minimum circumscribed circle positioning method is used to accurately position the loose nut and improve the positioning speed.

[0055] S4: Based on the result of the precise positioning, the robotic arm 3 is controlled to perform secondary tightening on the loose tunnel roof support component.

[0056] Optionally, the method further includes: determining the positions of all the tunnel roof support components based on the tunnel roof support component image, and controlling the robot arm 3 to perform secondary tightening on all the tunnel roof support components.

[0057] In this embodiment, the second image acquisition device 4 is used to collect the position information of all tunnel roof support components. After the robotic arm 3 completes the secondary tightening of all loose tunnel roof support components, the robotic arm 3 is controlled again to retighten the remaining tunnel roof support components to increase the stability and reliability of the roof.

[0058] The present invention adopts advanced machine vision methods to perform secondary tightening of the tunnel roof support components, which has good stability and high precision, reduces manpower input, improves the intelligence level of mine tunnel roof support, and enhances the safety of tunnel support. At the same time, the present invention realizes the three-dimensional scanning technology of mine tunnels, and monitors the deformation of the tunnel roof in real time through the collected three-dimensional image of the tunnel roof, which can also be used to assist in the positioning of underground equipment.

[0059] The foregoing description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed herein should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A secondary fastening method for automated tunnel support components, characterized in that: The steps include: Acquiring a three-dimensional image of the tunnel roof and processing the three-dimensional image of the tunnel roof to obtain point cloud data of the tunnel roof; estimating the position and posture information of the roadway roof support components based on the comparison of the point cloud data with the standard template point cloud data; Based on the posture information, the robot arm (3) is controlled to move to the bottom of the tunnel roof support component, and an image of the tunnel roof support component is collected at the same time. The loose tunnel roof support component is determined based on the image of the tunnel roof support component, and then a minimum circumscribed circle positioning method is used to achieve precise positioning of the loose tunnel roof support component. According to the result of the precise positioning, the mechanical arm (3) is controlled to perform secondary tightening on the loose tunnel roof support component.

2. The method for secondary fastening of automated tunnel support components according to claim 1, characterized in that: Processing the three-dimensional image of the tunnel roof includes: The three-dimensional image of the tunnel roof is filtered using a Gaussian filter, and then point cloud key point detection algorithm is used to extract point cloud features, and the extracted point cloud features are segmented.

3. The method for secondary fastening of automated tunnel support components according to claim 1, characterized in that: Comparing the point cloud data with the standard template point cloud data includes: The KD-Tree nearest neighbor search method is used to search for and compare the point cloud data in the standard template point cloud data. Object recognition is performed based on the comparison results, and the objects corresponding to the standard template point cloud data are matched to estimate the position information of the tunnel roof support components.

4. The method for secondary fastening of automated tunnel support components according to claim 1, characterized in that: Also includes: The positions of all the tunnel roof support components are determined based on the tunnel roof support component images, and the mechanical arm (3) is controlled to perform secondary tightening of all the tunnel roof support components.

5. An automated secondary fastening system for tunnel support components, capable of executing the automated secondary fastening method for tunnel support components according to any one of claims 1 to 4, characterized in that: include: A mobile robot (1) for moving in the lane; A mechanical arm (3) is mounted on the upper end of the mobile robot (1), and is used for the mobile robot (1) to control the mechanical arm (3) to perform secondary fastening on the tunnel roof support component according to the received posture information; A first image acquisition device (2) is installed at the front upper end of the mobile robot (1) and is used to acquire a three-dimensional image of the tunnel roof; The second image acquisition device (4) is installed at the end of the execution part of the mechanical arm (3) and is used to acquire images of the tunnel roof support components.

6. The automated secondary fastening system for tunnel support components according to claim 5, characterized in that: Position calibration is performed on the mobile robot (1) and the second image acquisition device (4).

7. The automated secondary fastening system for tunnel support components according to claim 5, characterized in that: The first image acquisition device (2) is a binocular structured light camera; the second image acquisition device (4) is a monocular camera.

Images