A non-contact hole inspection method, robot and system for drill and blast tunneling

Abstract

The application belongs to the technical field of underground engineering intelligent construction, and provides a non-contact hole inspection method, a robot and a system for a drill-and-blast method tunnel, which first determines all blast hole positions through a working face image; then at each determined blast hole position, the distance from a measuring point to a continuous point on the working face at different angles is obtained; the maximum distance in the distance from the measuring point to the continuous point on the working face is the blast hole depth, and the inclination angle of the measuring point and the point on the working face corresponding to the maximum distance is the blast hole inclination angle; only distance measurement is needed to realize the detection of the blast hole depth and angle, without an additional calculation process, which is conducive to realizing automatic hole inspection and improving the blast hole detection efficiency.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of underground engineering intelligent construction, and particularly relates to a non-contact hole inspection method, robot and system for a drill-and-blast tunnel. BACKGROUND

[0002] Underground engineering is an important support in the fields of transportation, energy, national defense and water network. In the construction of underground engineering, the drill-and-blast method is widely used due to its advantages of simple construction, strong adaptability and low excavation cost. In particular, it can make up for the shortcomings of the tunneling machine method, avoid the problems of short tunnel economy, large height difference, unsuitable environment, low operation efficiency in complex interbedded geology and high energy supply and transportation requirements in dangerous mountainous areas. The drill-and-blast method is one of the most important construction methods for underground engineering. At present, the drilling and other processes in the construction of drill-and-blast tunnels have been mechanized or even automated, but the blasting process still relies heavily on manual labor, which is a bottleneck for improving work efficiency and reducing labor use.

[0003] Among them, the inspection work of the blast hole is a key joint of the blasting operation, and the accuracy and efficiency of the blast hole inspection are related to whether the blasting effect meets the expectation, whether the explosive loading can be successfully implemented, and whether automatic explosive loading can be achieved. However, a single working surface involves hundreds of blast holes, a large number of inspection personnel are required, the operation time is long, and it is difficult to measure the inclination angle of the blast hole and to digitize the depth of the blast hole. In particular, the blasting operation personnel are located in the dangerous area of the working surface, facing the risk of falling of unstable rock blocks in the exposed surrounding rock, collapse of the surrounding rock and other major safety risks.

[0004] The inventors found that in order to solve the problems of efficiency and safety in the on-site inspection method by the operation personnel, the existing technology adopts a method of combining an image acquisition device and a range finder to identify the pose of the blast hole, and develops a blast hole depth range finder to measure the hole depth, blast hole inclination angle, etc. with the help of a measuring ruler and a laser range finder. Among them, the simple detection of the pose and the depth cannot realize the detection of the overall factors in the blast hole and cannot reflect the quality of the blast hole. When measuring the depth and angle of the blast hole, at least two measuring components such as a measuring ruler and a laser range finder are required to realize, which is not conducive to the realization of automatic hole inspection, and additional calculation is required to determine the angle, affecting the efficiency. SUMMARY

[0005] In order to solve the above problems, the present application provides a non-contact hole inspection method, robot and system for a drill-and-blast tunnel, which realizes the automation, unmanned and rapid detection of blast hole detection. Through simple equipment, the comprehensive detection of the position, depth and obstacles in the blast hole is realized.

[0006] In order to achieve the above purpose, the present application is realized by the following technical scheme:

[0007] In a first aspect, the present application provides a non-contact hole inspection method for a drill-and-blast tunnel, comprising:

[0008] acquiring a working face image;

[0009] determining all blast hole positions according to the working face image;

[0010] at each determined blast hole position, acquiring distances from a measuring point to consecutive points on the working face at different angles; the maximum distance among the distances from the measuring point to the consecutive points on the working face is a blast hole depth, and an inclination angle of the measuring point to a point on the working face corresponding to the maximum distance is a blast hole inclination angle.

[0011] Further, all blast hole openings in the working face image are identified by using an embedded machine learning algorithm to acquire coordinate positions of all blast hole openings in the working face image.

[0012] Further, multiple feature points of a tunnel vault, a left arch spring and a right arch spring in the working face image are selected; coordinates of the feature points in the working face image are matched with coordinates of the same positions in actual tunnel excavation, and coordinate conversion is performed to convert image coordinates of all blast hole openings into real working face plane coordinates.

[0013] Further, the measuring point is adjusted at different angles left and right in a tunnel excavation plane normal direction in a horizontal plane; and the measuring point is adjusted at different angles up and down in the tunnel excavation plane normal direction in a vertical plane.

[0014] Further, a derivative of a laser ranging numerical function in a neighboring area is calculated, and if the derivative has an infinite value, there is an obstacle inside the blast hole.

[0015] Further, the working face image is a working face image.

[0016] In a second aspect, the present application provides a non-contact hole inspection robot for a drill-and-blast tunnel, comprising a chassis, a mechanical arm arranged on the chassis, a laser range finder arranged on the mechanical arm, and an image recognition system arranged on the chassis; when working:

[0017] the working face image is acquired by the image recognition system;

[0018] all blast hole positions are determined according to the working face image;

[0019] at each determined blast hole position, distances from a measuring point to consecutive points on the working face at different angles are acquired by the laser range finder; the maximum distance among the distances from the measuring point to the consecutive points on the working face is a blast hole depth, and an inclination angle of the measuring point to a point on the working face corresponding to the maximum distance is a blast hole inclination angle.

[0020] In a third aspect, the present application further provides a non-contact hole inspection system for a drill-and-blast tunnel, comprising:

[0021] a data acquisition module configured to acquire a working face image;

[0022] a blast hole position determination module configured to determine the positions of all blast holes according to the working face image;

[0023] a hole inspection module configured to, at each determined blast hole position, acquire the distances from a measurement point to consecutive points on the working face at different angles; the maximum distance among the distances from the measurement point to the consecutive points on the working face is the blast hole depth, and the inclination angle of the measurement point to the point on the working face corresponding to the maximum distance is the blast hole inclination angle.

[0024] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the steps of the non-contact hole inspection method for a drill-and-blast tunnel according to the first aspect.

[0025] In a fifth aspect, the present application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the non-contact hole inspection method for a drill-and-blast tunnel according to the first aspect when executing the program.

[0026] Compared with the prior art, the present application has the following advantages:

[0027] 1. The present application first determines the positions of all blast holes through the working face image, and then acquires the distances from a measurement point to consecutive points on the working face at different angles at each determined blast hole position; the maximum distance among the distances from the measurement point to the consecutive points on the working face is the blast hole depth, and the inclination angle of the measurement point to the point on the working face corresponding to the maximum distance is the blast hole inclination angle; the detection of the blast hole depth and angle can be realized only through distance measurement, without the need for additional calculation processes, which is conducive to realizing automatic hole inspection and improving the blast hole detection efficiency.

[0028] 2. The present application can determine whether there is an obstacle inside the blast hole by calculating the derivative of the laser ranging numerical function in the adjacent region, and only through the laser range finder, without the need for additional measurement equipment and measurement objects, thereby realizing the comprehensive detection of the blast hole depth, angle, and internal obstacle. BRIEF DESCRIPTION OF DRAWINGS

[0029] The accompanying drawings, which form a part of this implementation, are used to provide further understanding of this implementation, and the schematic embodiments of this implementation and the description thereof are used to explain this implementation, and do not constitute an improper limitation on this implementation.

[0030] Figure 1This is a flowchart of Embodiment 1 of the present invention;

[0031] Figure 2 This is a schematic diagram of the structure of Embodiment 2 of the present invention;

[0032] The components include: 1. chassis; 2. robotic arm; 3. universal joint; 4. laser rangefinder; and 5. image recognition system. Detailed Implementation

[0033] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0034] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0035] Example 1:

[0036] To improve the efficiency of borehole detection and simplify the detection equipment and computational workload, such as Figure 1 As shown, this embodiment provides a non-contact borehole inspection method for drill-and-blast tunnels, including:

[0037] Acquire images of the working face; these images can be understood as images of the working face; they can be acquired using image acquisition devices such as cameras.

[0038] Based on the working face image, determine the locations of all blast holes;

[0039] At each determined borehole location, the distance from the measurement point to consecutive points on the working surface at different angles is obtained; among the distances from the measurement point to consecutive points on the working surface, the maximum distance is the borehole depth, and the inclination angle of the measurement point relative to the point on the working surface corresponding to the maximum distance is the borehole inclination angle; distance detection can be achieved using a laser rangefinder.

[0040] First, the locations of all boreholes are determined using the working face image. Then, at each determined borehole location, the distances from the measurement point to consecutive points on the working face at different angles are obtained. The maximum distance among these consecutive distances represents the borehole depth, and the inclination angle between the measurement point and the point on the working face corresponding to the maximum distance is the borehole inclination angle. This method allows for the detection of borehole depth and angle solely through distance measurement, eliminating the need for additional calculations. This facilitates automated borehole inspection and improves inspection efficiency.

[0041] Using an embedded machine learning algorithm, all blast holes in the working face image are identified, and the coordinate positions of all blast holes in the working face image are obtained.

[0042] Specifically, the embedded machine learning algorithm can adopt a YOLOv5 algorithm, train the collected blast hole images, establish a blast hole recognition model, and be built in a robot system, so that the robot can automatically recognize the blast hole position.

[0043] Select the crown, left arch foot and right arch foot of the tunnel in the working face image as multiple feature points; measure the coordinates of the feature points in the working face image, match the coordinates with the actual tunnel excavation coordinates at the same position, perform coordinate conversion, and convert the image coordinates of all blast hole openings into real working face plane coordinates.

[0044] Specifically, the coordinate conversion process can be as follows: first, calculate the ratio of the actual distance between any two feature points to the image distance, that is, the ratio of the image coordinates to the actual coordinates. After blast hole recognition, the image coordinates of the blast hole can be obtained, and the real coordinates of the blast hole can be obtained according to the ratio conversion.

[0045] On the horizontal plane, the measurement points are adjusted at different angles in the left and right directions along the normal direction of the tunnel excavation plane; on the vertical plane, the measurement points are adjusted at different angles in the up and down directions along the normal direction of the tunnel excavation plane. Optionally, on the horizontal plane, the measurement points are adjusted at angles of 60° in the left and right directions along the normal direction of the tunnel excavation plane; on the vertical plane, the measurement points are adjusted at angles of 60° in the up and down directions along the normal direction of the tunnel excavation plane; until the laser range finder continuously measures the distance value from the current position to the rock wall, records the horizontal direction tilt angle, the vertical direction tilt angle, and the laser ranging value at the tilt direction.

[0046] The derivative of the laser ranging value function in the adjacent area is calculated, which is as follows under normal circumstances:

[0047]

[0048] In the formula, L is the laser ranging distance; θ is the angle between the laser and the plane of the tunnel face; r and h are the blast hole opening radius and the blast hole depth, respectively, which are known quantities. If the derivative is infinite, there is an obstacle inside the blast hole.

[0049] Embodiment 2:

[0050] As shown in Figure 2 The embodiment provides a non-contact hole inspection robot for a drill-and-blast tunnel, which comprises a chassis 1, a mechanical arm 2 arranged on the chassis 1, a laser range finder 4 arranged on the mechanical arm 2 through a universal joint 3, and an image recognition system 5 arranged on the chassis 1; the universal joint is a multi-directional movable joint, the image recognition system 5 at least comprises an image acquisition device such as a camera, and the laser range finder 4 and the image recognition system 5 are connected with a controller; when working:

[0051] The working face image can be acquired by the image recognition system 5;

[0052] According to the working face image, the positions of all blast holes are determined;

[0053] At each determined blast hole position, the distance from the measuring point to the continuous points on the working face at different angles can be acquired by the laser range finder 4. Among the distances from the measuring point to the continuous points on the working face, the maximum distance is the blast hole depth, and the inclination angle of the measuring point and the point on the working face corresponding to the maximum distance is the blast hole inclination angle. By calculating the derivative of the laser ranging function in the adjacent area, if the derivative has an infinite value, there is an obstacle in the blast hole

[0054] The blast hole checking robot in the embodiment can perform the blast hole checking work before the tunnel blasting explosive loading without people, check whether the blast hole angle and length meet the design requirements, and check whether the debris and other foreign matters in the blast hole cause the explosive loading mispositioning, which is helpful for the accurate implementation of the tunnel blasting scheme and improves the automation level of the blasting operation.

[0055] The laser range finder 4 is assembled on the universal joint 3, the universal joint 3 is assembled on the end of the mechanical arm 2, and the mechanical arm 2 and the image recognition system 5 are assembled on the chassis 1. The image recognition system 5 is used to determine the position of the blast hole mouth, the universal joint 3 is moved to the blast hole mouth area by the mechanical arm 2, the angle of the laser range finder 4 is adjusted by the universal joint 3, the laser range finder 4 measures the distance in real time, the farthest distance is the effective blast hole depth, and the deflection angle of the laser range finder 4 at the farthest distance is the blast hole angle. Finally, the non-contact blast hole checking of the drill and blast method tunnel is realized.

[0056] The mechanical arm 2 is connected to the chassis 1 at the bottom end and placed with the universal joint 3 at the end, can be driven by a motor or a hydraulic pressure, and can be flexibly shortened or lengthened, so that the end of the mechanical arm 2 can reach and contact all the tunnel excavation surface areas.

[0057] The universal joint 3 is arranged at the end of the mechanical arm 2 and connected to the laser range finder 4, can be driven to rotate by a motor or the like, and can be arranged to rotate in a range of 60° left and right in the horizontal plane in the direction of the normal line of the tunnel excavation plane and in a range of 60° up and down in the vertical plane in the direction of the normal line of the tunnel excavation plane, and can dynamically record the horizontal deflection angle and the vertical deflection angle.

[0058] The laser range finder 4 is fixedly installed on the universal joint 3 and can be tilted with the rotation of the universal joint 3. The laser range finder 4 can continuously measure and record the distance from the laser emitter to the rock surface.

[0059] The image recognition system 5 is installed on the chassis 1, can shoot the image of the tunnel face by digital camera shooting and the like, and automatically recognize the characteristics of the blast hole mouth through the built-in embedded machine learning algorithm, and convert the image coordinates and the spatial coordinate position according to the principle of photogrammetry to determine the spatial coordinate position of the blast hole mouth.

[0060] The chassis 1 provides a stable platform for the mechanical arm 2 and places the image recognition system 5. The chassis 1 has the ability to move, can be remotely controlled by personnel, has supporting legs to provide a stable platform during operation, can be connected to the above-mentioned systems, and has the ability to supply power and transmit data.

[0061] The working steps or principles of the embodiment are as follows:

[0062] S1, after the tunnel drilling operation process is completed, the hole inspection robot moves to the tunnel excavation tunnel face area, and the chassis 1 props up the supporting legs to be fixed.

[0063] S2, start the blast hole image recognition system 5, shoot the overall image of the tunnel face, use the embedded machine learning algorithm to recognize all the blast hole mouths in the image, and obtain the coordinate position of all the blast hole mouths in the overall photo of the tunnel face. Select the characteristic points such as the vault, left arch foot and right arch foot in the overall photo of the tunnel face, measure the coordinates of the characteristic points in the picture, match the coordinates with the actual tunnel excavation coordinates at the same position, perform coordinate conversion, and convert the image coordinates of all the blast hole mouths into the plane coordinates of the real tunnel face.

[0064] S3, start the mechanical arm 2, transmit the tunnel face plane coordinates of the blast hole mouth to the mechanical arm 2, and move the end of the mechanical arm 2 to the real blast hole mouth position according to the blast hole mouth coordinates.

[0065] S4, start the universal joint 3 and the laser range finder 4, rotate the universal joint 3 in the left and right direction by 60° in the horizontal plane along the normal direction of the tunnel excavation plane, rotate in the up and down direction by 60° in the vertical plane along the normal direction of the tunnel excavation plane, rotate from left to right and from top to bottom, or rotate from right to left and from bottom to top, continuously measure the distance value from the laser range finder to the rock wall, and record the horizontal inclination angle of the universal joint 3, the vertical inclination angle, and the laser ranging value in the inclined direction.

[0066] S5, select the maximum value of the laser ranging value, which can be considered as the depth of the blast hole. The maximum value of the ranging and the inclination angle are the inclination angle of the blast hole. Calculate the derivative of the laser ranging value function in the adjacent area. If the derivative is infinite, it can be considered that there is an obstacle in the blast hole, and the distance from the obstacle to the blast hole mouth is the distance value of the point where the derivative is infinite.

[0067] S6. Based on the borehole coordinates provided by the image recognition system 5, the robotic arm 2 moves to the next borehole position and repeats steps S4 and S5 until all boreholes are detected.

[0068] S7. The equipment is retrieved from the tunnel face area to the outside of the tunnel, and the blast hole inspection is completed.

[0069] Once implemented, this system enables unmanned borehole inspection, improving operational safety; it achieves automated and digital borehole inspection, using laser ranging to replace manual depth measurement with rubber rods, resulting in more accurate borehole depth detection and enabling digital data upload; it can also measure the borehole tilt angle, facilitating the accurate execution of blasting plans.

[0070] Example 3:

[0071] This embodiment provides a non-contact borehole inspection system for drill-and-blast tunnels, including:

[0072] The data acquisition module is configured to acquire images of the working surface.

[0073] The borehole location determination module is configured to determine the locations of all boreholes based on the working face image.

[0074] The borehole inspection module is configured to: at each determined borehole location, acquire the distance from the measurement point to consecutive points on the working surface at different angles; among the distances from the measurement point to consecutive points on the working surface, the maximum distance is the borehole depth, and the inclination angle between the measurement point and the point on the working surface corresponding to the maximum distance is the borehole inclination angle.

[0075] The working method of the system is the same as that of the non-contact borehole inspection method for drill-and-blast tunnels in Embodiment 1, and will not be repeated here.

[0076] Example 4:

[0077] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the non-contact borehole inspection method for drill-and-blast tunnels described in Embodiment 1.

[0078] Example 5:

[0079] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the non-contact borehole inspection method for drill-and-blast tunnels described in Embodiment 1.

[0080] The above merely provides preferred embodiments of the present embodiment, but is not intended to limit the present embodiment. For those skilled in the art, the present embodiment can have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present embodiment shall fall into the scope of protection of the present embodiment.

Claims

1. A non-contact borehole inspection method for drill-and-blast tunnels, characterized in that, include: Obtain the working surface image; Based on the working face image, determine the locations of all blast holes; At each determined borehole location, the distance from the measurement point to consecutive points on the working surface at different angles is obtained; among the distances from the measurement point to consecutive points on the working surface, the maximum distance is the borehole depth, and the inclination angle of the measurement point to the point on the working surface corresponding to the maximum distance is the borehole inclination angle. Using an embedded machine learning algorithm, all blast holes in the working face image are identified, and the coordinate positions of all blast holes in the working face image are obtained. Select multiple feature points of the tunnel's arch crown, left arch foot, and right arch foot in the working face image; measure the coordinates of the feature points in the working face image, match them with the coordinates of the same positions in the actual tunnel excavation, and perform coordinate transformation to convert the image coordinates of all blast holes into the plane coordinates of the actual working face.

2. The non-contact borehole inspection method for drill-and-blast tunnels as described in claim 1, characterized in that, On the horizontal plane, the measuring points are adjusted to different angles to the left and right along the direction of the tunnel excavation plane normal; on the vertical plane, the measuring points are adjusted to different angles to the up and down along the direction of the tunnel excavation plane normal.

3. The non-contact borehole inspection method for drill-and-blast tunnels as described in claim 1, characterized in that, Calculate the derivative of the laser ranging numerical function in the adjacent area. If the derivative is infinite, then there is an obstacle inside the borehole.

4. The non-contact borehole inspection method for drill-and-blast tunnels as described in claim 1, characterized in that, The working face image is a face image.

5. A non-contact borehole inspection robot for drill-and-blast tunnels, characterized in that, Includes a chassis, a robotic arm mounted on the chassis, a laser rangefinder mounted on the robotic arm, and an image recognition system mounted on the chassis; during operation: The image of the working surface is obtained through the image recognition system. Based on the working face image, the locations of all blast holes are determined; using an embedded machine learning algorithm, all blast hole openings in the working face image are identified, and the coordinate positions of all blast hole openings in the working face image are obtained; multiple feature points of the tunnel's arch crown, left arch foot, and right arch foot in the working face image are selected; the coordinates of the feature points in the working face image are measured and matched with the coordinates of the same positions in the actual tunnel excavation, and coordinate transformation is performed to convert the image coordinates of all blast hole openings into the plane coordinates of the actual working face; At each determined borehole location, the distance from the measurement point to consecutive points on the working surface at different angles is obtained using the laser rangefinder; among the distances from the measurement point to consecutive points on the working surface, the maximum distance is the borehole depth, and the inclination angle between the measurement point and the point on the working surface corresponding to the maximum distance is the borehole inclination angle.

6. A non-contact borehole inspection system for drill-and-blast tunnels, characterized in that, include: The data acquisition module is configured to acquire images of the working surface. The blast hole location determination module is configured to: determine the location of all blast holes based on the working face image; use an embedded machine learning algorithm to identify all blast hole openings in the working face image and obtain the coordinate positions of all blast hole openings in the working face image; select multiple feature points of the tunnel's arch crown, left arch foot, and right arch foot in the working face image; measure the coordinates of the feature points in the working face image, match them with the coordinates of the same positions in the actual tunnel excavation, perform coordinate transformation, and convert the image coordinates of all blast hole openings into the plane coordinates of the actual working face; The borehole inspection module is configured to: at each determined borehole location, acquire the distance from the measurement point to consecutive points on the working surface at different angles; among the distances from the measurement point to consecutive points on the working surface, the maximum distance is the borehole depth, and the inclination angle between the measurement point and the point on the working surface corresponding to the maximum distance is the borehole inclination angle.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the steps of the non-contact borehole inspection method for drill-and-blast tunnels as described in any one of claims 1-4.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the non-contact borehole inspection method for drill-and-blast tunnels as described in any one of claims 1-4.

Images