An anchor rod drilling machine automatic hole finding positioning system and method based on machine vision

Abstract

The application provides a kind of anchor rod drilling rig automatic hole finding positioning system and method based on machine vision, belongs to anchor rod drilling rig automatic hole finding positioning technical field;In order to solve the technical problems of low precision, poor efficiency and poor adaptability of automatic scheme when artificial operation during anchor rod support, the technical scheme is that: binocular vision camera and laser displacement sensor are arranged on the anchor rod drilling rig vehicle body, drilling rig controller, inclination sensor, industrial switch, drilling rig electric control box and communication module are arranged inside the anchor rod drilling rig vehicle body, the drilling rig controller is connected with other modules or components through wire, positioning target and wireless AP base station are also arranged in the roadway, and the communication module is wirelessly connected with the wireless AP base station through wireless network;Positioning console is arranged in the control room, and positioning control computer, core switch and drilling positioning server are also arranged in the positioning console;The application is applied to anchor rod drilling rig automatic hole finding positioning.

Description

Technical Field

[0001] This invention provides an automatic hole-finding and positioning system and method for anchor drilling rigs based on machine vision, belonging to the field of automatic hole-finding and positioning technology for anchor drilling rigs. Background Technology

[0002] In mine roadway support operations, the use of rock bolts is an important means to ensure the stability of the surrounding rock. Before carrying out rock bolt support, it is necessary to drill holes in the support area. The currently used manual drilling method has the following main drawbacks:

[0003] Low positioning accuracy: Manually marking the drilling position is affected by the operator's experience, and the error usually exceeds ±10mm, which is difficult to meet the requirements of high-precision support.

[0004] Low efficiency: Each hole positioning takes 3-5 minutes, which will seriously affect the work progress in long-distance tunnel construction;

[0005] Poor environmental adaptability: The dust, humidity and low light conditions in the well make manual observation difficult, and problems such as accidental drilling and missed drilling are likely to occur.

[0006] To address the aforementioned shortcomings, corresponding automatic anchor bolt hole finding and positioning methods have been proposed, such as laser hole finding, monocular vision positioning, and mechanical limiting device drilling. However, laser guidance schemes rely on preset coordinates and cannot adapt to rock surface deformation, resulting in significantly increased errors in fractured surrounding rock. Monocular vision positioning is limited by two-dimensional image information and cannot accurately calculate the spatial pose relationship between the drill bit and the hole position. Mechanical limiting devices have limited adjustment range and cannot achieve dynamic compensation under complex rock surfaces. Summary of the Invention

[0007] To address the technical problems existing in the background art, the present invention adopts the following technical solution: providing an automatic hole finding and positioning system for anchor drilling rigs based on machine vision, including an anchor drilling rig vehicle body and a control room set in a roadway, wherein a binocular vision camera and a laser displacement sensor are installed on the anchor drilling rig vehicle body, and a drilling rig controller, an inclination sensor, an industrial switch, a drilling rig electrical control box, and a communication module are installed inside the anchor drilling rig vehicle body;

[0008] Positioning targets and wireless AP base stations were also set up inside the alleyway;

[0009] The control room is equipped with a positioning console, which also contains a positioning control computer, a core switch, and a drilling positioning server.

[0010] The drilling rig controller is connected to the binocular vision camera, laser displacement sensor, tilt sensor, industrial switch, drilling rig electrical control box, and communication module via wires.

[0011] The communication module is wirelessly connected to the wireless AP base station via a wireless network;

[0012] The wireless AP base station is connected to the core switch via wires, and the core switch is connected to the positioning control computer and the drilling positioning server via wires respectively.

[0013] The wireless AP base station is wirelessly connected to the positioning target via a wireless network.

[0014] The anchor drilling rig is also equipped with explosion-proof lighting, and the control terminal of the explosion-proof lighting is connected to an industrial switch via a wire.

[0015] The binocular vision camera includes a left camera and a right camera, which are specifically arranged horizontally on the drilling rig crossbeam of the anchor drilling rig body via shock-absorbing brackets.

[0016] The laser displacement sensor is specifically mounted on a bracket on the side of the drill bit of the anchor drilling rig.

[0017] The measurement axis of the laser displacement sensor is set at a 30° angle to the drill rod.

[0018] The drilling rig controller is specifically connected to the drilling rig electrical control box via a PROFINET bus, an EtherCAT network cable, or a Modbus RTU bus.

[0019] A method for positioning an automatic hole-finding and positioning system for anchor drilling rigs based on machine vision includes the following positioning steps:

[0020] Step 1: The drilling rig controller receives data collected by the laser displacement sensor and the tilt sensor respectively. After analyzing and processing the collected data, the drilling rig controller sends it to the communication module.

[0021] Step 2: Control the drilling rig controller to communicate with the drilling rig electrical control box to obtain the drilling rig's operating parameters, and send the drilling rig's operating parameters to the communication module;

[0022] The obtained operating parameters include drill bit rotation speed ω and feed rate v, which are defined to satisfy ω=kv, where k is the material correlation coefficient;

[0023] Step 3: Control the drilling rig controller to receive image data acquired by the binocular vision camera and perform preprocessing, including image binarization, image enhancement, and stereo correction.

[0024] Step 4: The control communication module communicates with the core switch set up in the control room via a wireless AP base station;

[0025] Step 5: Control the positioning targets set up in the tunnel to send their position parameters to the wireless AP base station in real time via the wireless network;

[0026] Step 6: Estimate the acquisition distance by using the structural parameters of the anchor drilling robot and the transformation relationship between the coordinate axes, and calculate the spatial distance between the camera position and the target when acquiring images;

[0027] Step 7: Using the functional relationship between the acquisition distance and the radius of the anchor bolt borehole in the image, determine the radius of the anchor bolt borehole at any distance, and then determine the center coordinates and maximum and minimum radii of the anchor bolt borehole;

[0028] Step 8: Based on the geometric constraints of the maximum and minimum radii of the anchor bolt boreholes, use the Hough transform with adaptive radius parameter adjustment to detect the anchor bolt boreholes on the steel strip, and use linear slope and geometric constraints to achieve three-dimensional matching of the anchor hole profile;

[0029] Step 9: Determine the spatial coordinates of the anchor hole center in the camera coordinate system based on the principle of binocular vision positioning;

[0030] Step 10: The anchor bolt drilling rig body, based on the determined spatial coordinates of the anchor hole center, launches and installs the anchor bolt into the corresponding anchor hole.

[0031] The specific method for step six is ​​as follows:

[0032] Based on the transformation relationship between various coordinate systems, the transformation relationship between the camera coordinate system and the body coordinate system is obtained, and the three-dimensional coordinates of the camera coordinate system in the world coordinate system are obtained in real time through the body positioning method.

[0033] Construct the camera coordinate system, the reference coordinate system, and the world coordinate system respectively:

[0034] Wherein, the spatial coordinates of point A on the camera plane in the camera coordinate system are defined as follows: C A = (x1, y1, z1), and convert it to the world coordinate system. W The coordinates in A=(x2,y2,z2) can be transformed using the following formula:

[0035] ;

[0036] in, This indicates the transformation relationship between the camera coordinate system and the body coordinate system, and This indicates the transformation relationship between the fuselage coordinate system and the world coordinate system;

[0037] Define the coordinates of point B on the target in the world coordinate system as WB=(x3,y(3),z(3)), where x(3) and y(3) are unknowns;

[0038] The acquisition distance can be approximated as the distance between point A on the camera and point B on the steel strip, expressed as:

[0039] ;

[0040] To mitigate the impact of the difference between the X and Y axes, an attenuation coefficient α is introduced, and the formula for calculating spatial distance becomes:

[0041] .

[0042] The specific method for step seven is as follows:

[0043] Based on the target contour fitting completed in step six, the following compensation rule is adopted to compensate for the influence of the distance between the camera and the target on the center distance between the targets:

[0044] ;

[0045] Where, x i and y i This represents the coordinates of the i-th target in the image.

[0046] The specific method for step eight is as follows:

[0047] The target center coordinates are obtained through parameter-adaptive Hough circle detection.

[0048] The circular function is defined as follows:

[0049] x = x0 + r0cosα;

[0050] y = y0 + r0sinα;

[0051] Where r0 is the target radius, x0 and y0 are the target center coordinates, x and y are the image coordinates, and α represents the angle, with a value range of 0° to 360°.

[0052] Since the contours on the image are oriented, the coordinates of the center of the circle can be arranged from smallest to largest in the horizontal direction, and are defined as follows:

[0053] O l1 (u l1 , v l1 ), O l2 (u l2 , v l2 ), O l3 (u l3 , v l3 ), ...,O lm (u lm , v lm () represents the coordinates of the center point of the anchor bolt borehole in the image captured by the left-hand camera;

[0054] O r1 (u r1, v r1 ), O r2 (u r2 , v r2 ), O r3 (u r3 , v r3 ), ....,O rn (u rn , v rn ( ) represents the coordinates of the center point of the anchor bolt borehole in the image captured by the camera on the right.

[0055] The coordinates are arranged in ascending order of horizontal pixel coordinate values. Based on the fact that the pixel coordinate values ​​of the same point in the vertical direction are the same in the left and right images, three-dimensional matching is performed on the centers of different anchor bolt boreholes to complete the three-dimensional matching of the target center and determine the spatial coordinates of the target center.

[0056] Then, the stereo matching accuracy of the target center is verified by the directionality of the contour:

[0057] Define that if the i-th point on the left and the j-th point on the right are a pair of matching points, then i±p and j±p on the image are a pair of matching points;

[0058] Furthermore, the distance between two adjacent matching points is basically the same, with a small fluctuation range, and the expression is:

[0059] |O li O li+1 | = O rj O rj+1 .

[0060] The specific method for step nine is as follows:

[0061] The coordinates of the target center are calculated using an ideal model of a binocular vision system.

[0062] Define X respectively W Y W Z W For world coordinates, X C Y C Z C U represents camera coordinates, and u and v represent pixel plane coordinates; O l and O r B is the optical center of the two cameras, B is the distance between the two cameras, and f is the focal length; C l and C r These are perpendicular to the camera's optical axis Z. C The left and right image planes;

[0063] For stereo correction, point A (X, Y, Z) is a point in the world coordinate system, and its response points in the image plane are a1(u1, v1) and a2(u2, v2), respectively. Based on similar triangles, the transformation formula between the world coordinate system and the image coordinate system is:

[0064] ;

[0065] The above formula is used to calculate the coordinates of any point in space, where f′ is one of the inherent parameters, obtained through camera calibration;

[0066] By identifying and matching circles, the pixel coordinates in the borehole image can be determined, including the coordinates in the left and right images;

[0067] Based on the calibration results and the segmentation and stereo matching results, the spatial coordinates of a point are calculated using the following formula:

[0068] y = kx + b;

[0069] Where k is the slope of the line and b is the ordinate of the origin.

[0070] The advantages of this invention compared to existing technologies are as follows: This invention proposes a high-precision, interference-resistant automatic hole-finding and positioning scheme for anchor drilling rigs. It uses a monocular camera and a binocular camera working together, utilizing binocular stereo vision to capture images of steel strips on the tunnel roof. The captured images undergo a series of preprocessing operations such as image enhancement, noise reduction, and stereo correction. Simultaneously, it employs a circle detection algorithm with parameter adaptive Hough transform, which can automatically adjust the maximum and minimum radii of the anchor holes according to their actual distance, facilitating accurate and rapid identification and segmentation of the anchor hole contours. Furthermore, it uses a matching method based on the slope of the line where the anchor hole is located and geometric constraints to achieve rapid image matching. Compared to manual positioning, stability and robustness are improved. This invention solves the problems of low accuracy and poor efficiency in traditional manual operations, as well as the insufficient adaptability of existing automation schemes, and is suitable for support operations in underground tunnels such as mines and tunnels. Attached Figure Description

[0071] The present invention will be further described below with reference to the accompanying drawings:

[0072] Figure 1 This is a schematic diagram of the circuit structure of the automatic hole finding and positioning system for anchor drilling machines of the present invention;

[0073] Figure 2 This is a schematic diagram of the binocular vision system model used in calculating target coordinates in this invention;

[0074] The meanings of the numbers in the diagram are as follows: 1 is the anchor drilling rig body, 2 is the binocular vision camera, 3 is the laser displacement sensor, 4 is the drilling rig controller, 5 is the tilt sensor, 6 is the explosion-proof lighting, 7 is the industrial switch, 9 is the drilling rig electrical control box, 10 is the communication module, 11 is the positioning target, 12 is the positioning control console, 13 is the wireless AP base station, 15 is the positioning control computer, 16 is the core switch, and 17 is the drilling positioning server. Detailed Implementation

[0075] like Figure 1 and Figure 2 As shown, this invention provides an automatic hole-finding and positioning scheme for anchor drilling rigs based on machine vision. It mainly establishes a predictive model to determine the correlation between the radius of the target circular hole in the image and the shooting distance. Based on the structural model of the anchor drilling robot and relevant sensor data, the shooting distance range is determined. Utilizing the inherent geometric constraints of adjacent anchor holes, the Hough transform of the adaptive parameter adjustment method is used to accurately identify the anchor holes. Furthermore, linear slope and geometric constraints are used to match the anchor hole contours, and the spatial coordinates of the anchor hole center in the camera coordinate system are determined based on the binocular vision positioning principle. This achieves high-precision, highly interference-resistant automatic hole-finding and positioning. Experimental verification shows that the positioning accuracy of this method can reach 95.2%, with an absolute error of approximately 1.52 mm, effectively improving drilling accuracy and auxiliary efficiency. Even under conditions with a dust concentration of 200 mg / m³, it can maintain a 95% recognition rate, and the single-hole positioning time is shortened to less than 30 seconds. It can be widely applied in scenarios such as coal mine roadway support, tunnel anchoring construction, and underground space reinforcement projects.

[0076] Furthermore, the machine vision-based automatic hole finding and positioning system for anchor drilling rigs provided by the present invention includes an anchor drilling rig vehicle 1 installed in a roadway and a positioning control console 12 installed in a control room.

[0077] The outer side of the anchor drilling rig vehicle body 1 is equipped with a binocular vision camera 2, a laser displacement sensor 3, a drilling rig controller 4, an tilt sensor 5, and an explosion-proof lighting lamp 6.

[0078] The interior of the anchor drilling rig vehicle body 1 is equipped with an industrial switch 7, a drilling rig electrical control box 9, and a communication module 10.

[0079] Circular positioning targets 11 and wireless AP base stations 13 are also installed in the alleyway;

[0080] The positioning control console 12 is also equipped with a positioning control computer 15, a core switch 16, and a drilling positioning server 17.

[0081] The drilling rig controller 4 is connected to the binocular vision camera 2, the laser displacement sensor 3, the tilt sensor 5, the industrial switch 7, and the communication module 10 via wires. The industrial switch 7 is connected to the explosion-proof lighting lamp 6 via wires.

[0082] The drilling rig controller 4 is specifically connected to the drilling rig electrical control box 9 via a PROFINET bus, an EtherCAT network cable, or a Modbus RTU bus.

[0083] The communication module 10 is specifically wirelessly connected to the wireless AP base station 13 via radio electromagnetic waves;

[0084] The wireless AP base station 13 is connected to the core switch 16 via optical fiber;

[0085] The wireless AP base station 13 is specifically connected to the positioning target 11 wirelessly via radio electromagnetic waves;

[0086] The core switch 16 is connected to the positioning control computer 15 and the drilling positioning server 17 via optical fibers.

[0087] Furthermore, the aforementioned binocular vision camera 2 uses a 2-megapixel global shutter camera with a frame rate of no less than 30fps and a built-in LED fill light;

[0088] The laser displacement sensor 3 has a measurement accuracy of ±0.1mm and a measurement distance of 50-300mm;

[0089] The 5G communication module 10 supports the 5G NR standard, operates at a frequency of 3.5GHz, and has a transmission latency of less than 10ms.

[0090] The positioning target 11 is made of a high reflectivity material and has specific geometric pattern markings on its surface.

[0091] The explosion-proof lighting lamp 6 has a color temperature of 5000K and an adjustable illuminance range of 100-1000 lux.

[0092] Based on the above positioning system, the present invention also provides an automatic hole-finding and positioning method for anchor drilling rigs based on machine vision, specifically including the following positioning control steps:

[0093] Step 1: Install a drilling rig controller 4 on the anchor drilling rig body 1 to receive data collected by the laser displacement sensor 3 and the tilt sensor 5 respectively, and send the collected data to the communication module 10; the laser displacement data is calculated using the formula d=ct / 2, where c is the speed of light and t is the round-trip time of the laser.

[0094] Step 2: Control the drilling rig controller 4 to communicate with the drilling rig electrical control box 9 via PROFINET bus or Modbus RTU bus to obtain the drilling rig operating parameters and send the operating parameters to the communication module 10; the operating parameters include the drill bit speed ω and the feed speed v, which satisfy ω=kv, where k is the material correlation coefficient.

[0095] Step 3: Control the drilling rig controller 4 to receive image data acquired by the binocular vision camera 2, use the Otsu method to binarize the image, and use the median filtering method to effectively eliminate salt-and-pepper noise, thereby completing comprehensive image preprocessing.

[0096] Step 4: The control communication module 10 communicates with the core switch 16 set up in the control room through the wireless AP base station 13. The data transmission delay Δt≤10ms meets the real-time requirements.

[0097] Step 5: The circular positioning target 11 set up in the control tunnel transmits its position parameters to the wireless AP base station 13 in real time via radio electromagnetic waves; through parameter-adaptive Hough circle detection, the target is accurately located, thereby obtaining its precise pixel coordinates. The circle function is defined as follows:

[0098] x = x0 + r0cosα;

[0099] y = y0 + r0sinα;

[0100] Where r0 is the target radius, x0 and y0 are the target center coordinates, x and y are the image coordinates, and α represents the angle, with a value range of 0° to 360°.

[0101] Step Six: Calculate the spatial distance between the camera position and the target during image acquisition. Displacement and angle sensors mounted on each joint of the robotic arm were used to accurately measure joint variables in real time. A De Naveit-Hartenberg parameter table was constructed based on the robotic arm and structural parameters of the drilling and anchoring robot. The transformation relationship between the camera coordinate system and the body coordinate system was obtained through the transformation relationships between various coordinate systems. The three-dimensional coordinates of the camera coordinate system in the world coordinate system were obtained in real time using the body positioning method. A camera coordinate system, a reference coordinate system, and a world coordinate system were constructed. The spatial coordinates of point A on the camera plane in the camera coordinate system are... C A = (x1, y1, z1), and convert it to the world coordinate system. W The coordinates of A=(x2,y2,z2) are shown below:

[0102] ;

[0103] in This indicates the transformation relationship between the camera coordinate system and the body coordinate system, and This indicates the transformation relationship between the body coordinate system and the world coordinate system, both of which can be determined based on the principles of robot kinematics.

[0104] The size of the coal mine roadway is fixed. The coordinates of point B on the target in the world coordinate system are WB=(x3,y(3),z(3)), where x(3) and y(3) are unknowns. The acquisition distance can be approximately expressed as the distance between point A on the camera and point B on the steel belt:

[0105] ;

[0106] To ensure the steel strip remains within the camera's field of view, the variations between points A and B along the X and Y axes are minimal. Experimental results show that the measured distance is primarily determined by the difference along the Z axis. To mitigate the impact of the difference between the X and Y axes, an attenuation coefficient, denoted by α, is introduced. Experimental results indicate that the value of α should be 1.1, and its calculation expression is:

[0107] ;

[0108] Therefore, the above method is used to calculate the sampling distance, and then determine the maximum and minimum radii.

[0109] Step 7: Obtain the center coordinates and radius information of the anchor holes. Based on Step 6, the target contour can be fitted. However, considering that the distance between the camera and the target will affect the center distance between the targets, the following rule formula needs to be used:

[0110] ;

[0111] Where, x i and y i This represents the coordinates of the i-th target in the image.

[0112] Based on the above method, the radius parameter can be obtained through a target radius prediction model on the image and adaptively adjusted. The Hough detection method with adaptive parameter adjustment is then used to fit the anchor hole contour on the image to obtain the target's center coordinates and radius information.

[0113] Step 8: Perform stereo matching. Based on the image segmentation in the above steps, the pixel coordinates of the target center can be determined. Since the contours on the image are oriented, the coordinates of the center of the circle can be arranged from smallest to largest in the horizontal direction, defined as follows:

[0114] O l1 (u l1 , v l1 ), O l2 (u l2 , v l2 ), O l3 (ul3 , v l3 ), ...,O lm (u lm , v lm () represents the coordinates of the center point of the anchor bolt borehole in the image captured by the left camera;

[0115] O r1 (u r1 , v r1 ), O r2 (u r2 , v r2 ), O r3 (u r3 , v r3 ), ....,O rn (u rn , v rn () represents the coordinates of the center point of the anchor bolt borehole in the image captured by the right camera;

[0116] They are arranged in ascending order of horizontal pixel coordinate values. Theoretically, the pixel coordinate values ​​of the same point in the vertical direction are the same in the left and right images. This characteristic can be used to perform stereo matching of different anchor bolt borehole centers. Since noise will cause some errors in the corrected image, the corrected image will also have some errors. Multiple experiments show that the vertical coordinate error of the same point on the left and right images is less than 8 pixels. Therefore, we set the threshold to 10, and stereo matching can be performed on any point on the left image. In this way, the three-dimensional matching of the target center can be completed quickly, and the spatial coordinates of the target center can be determined.

[0117] The stereo matching accuracy of the target center can be verified based on the directionality of the contour. If the i-th point on the left and the j-th point on the right are a matching pair, then i±p and j±p on the image are also a matching pair. Furthermore, the distance between adjacent matching points is approximately the same, with minimal fluctuation.

[0118] |O li O li+1 | = O rj O rj+1 ;

[0119] Step 9: Calculate the coordinates of the target center:

[0120] An ideal model based on a binocular vision system, such as Figure 2 As shown, X is defined. W Y W Z W For world coordinates, X C Y C Z C U represents camera coordinates, and u and v represent pixel plane coordinates; Ol and O r B is the optical center of the two cameras, B is the distance between the two cameras, and f is the focal length; C l and C r They are perpendicular to Z C The left and right image planes (of the camera's optical axis). A parallel optical system between the two cameras is the ideal configuration, but in reality, most configurations do not follow this principle. Therefore, stereo correction is an essential step before determining the position of points in space. Point A (X, Y, Z) is a point in the world coordinate system, and its corresponding points in the image plane are a1(u1, v1) and a2(u2, v2), respectively. Due to the similarity of triangles, we can express the transformation formula between the world coordinate system and the image coordinate system as follows:

[0121] ;

[0122] The above formula can be used to calculate the coordinates of a point; f′ is one of the inherent parameters, obtained through camera calibration. By identifying and matching circles, we can determine the pixel coordinates in the borehole image, including the coordinates in the left and right images. Based on the calibration results and the segmentation and stereo matching results, the spatial coordinates of a point are calculated using the formula y=kx+b (k is the slope of the line, and b is the ordinate of the origin). Due to the coordinate transformation relationship, the spatial coordinates of the target are transformed into the coordinate system of the anchoring drilling robot body, thereby facilitating the precise and rapid movement of the drilling rig towards the target.

[0123] The hole-finding and localization method provided by this invention first preprocesses the acquired image, including image binarization, image enhancement, and stereo correction. Then, it uses the Canny edge detection method to process the image, dividing the steel strip into regions of interest (ROIs) based on the upper and lower edge lines. On this basis, the acquisition distance is estimated through the transformation relationship between the structural parameters of the anchor drilling robot and the coordinate axes. Using the functional relationship between the acquisition distance and the radius of the anchor drilling hole in the image, the radius at any distance is determined. Finally, based on the geometric constraints of the maximum and minimum radii, the anchor drilling holes on the steel strip are detected using an adaptively adjusted Hough transform of the radius parameter. Experimental results show that the proposed anchor drilling hole detection method based on adaptive parameter Hough transform has high accuracy and can effectively eliminate invalid results.

[0124] This invention employs a high-precision industrial binocular camera as the vision acquisition module, with the left and right cameras arranged horizontally and precisely calibrated to a distance of 250mm. Its workflow is as follows: the left and right cameras synchronously trigger image acquisition, then the acquired images undergo preprocessing, including noise reduction and enhancement operations, and finally the processed images are transmitted to an industrial switch via a gigabit network port.

[0125] The laser ranging module used in this invention is mounted on the side support of the drill bit, with its measuring axis forming a 30° angle with the drill rod. The module's operation includes: first, emitting a modulated laser beam and receiving the reflected signal; then, calculating the real-time distance value through the phase difference; and finally, outputting the measurement data through an RS485 interface.

[0126] The central control unit used in this invention adopts a sandwich structure design. The bottom layer is an FPGA, which is responsible for the synchronous acquisition of sensor data; the middle layer is an ARM processor, which runs the control algorithm; and the top layer is a communication interface module, which is responsible for communicating with external devices.

[0127] This invention employs a dual-channel redundancy design to ensure reliable data transmission. The data transmission path is as follows: sensor data is first transmitted to an industrial switch, then transmitted to the core switch via a 5G module or wireless AP base station, and finally reaches the control computer.

[0128] In terms of mechanical connections, the positioning system of this invention features a binocular camera fixed to the drill rig beam via a shock-absorbing bracket to reduce the impact of vibration on image acquisition. The laser sensor uses a quick-release interface for easy maintenance and replacement. All cables are protected by cable chains to prevent wear and tear.

[0129] Regarding electrical connections: the sensors are powered by 24V DC to ensure safety and reliability. All actuators are connected via a CAN bus to enable rapid data transmission and timely response to control commands. A fiber optic backbone network connects to the control room, ensuring stable transmission of large amounts of data.

[0130] In terms of data flow: image data is transmitted from the camera to the switch, then preliminarily processed by the FPGA, and then transmitted to the ARM processor for further processing. Control commands are transmitted from the ARM processor to the electrical control box via the CAN bus to control the actions of the actuators. Status feedback signals are transmitted from the sensors to the PLC, and then to the control computer to achieve closed-loop control of the system.

[0131] The positioning system provided by this invention mainly performs the following working steps during operation:

[0132] Step 1: System Initialization:

[0133] During the system initialization phase, the binocular camera performs automatic focusing and exposure calibration, the laser sensor completes temperature compensation, and each module establishes communication connections and performs self-tests.

[0134] Step 2: Environmental Scan:

[0135] During the environmental scanning phase, the drilling rig remained stationary. A binocular camera acquired three sets of stereo images, each set spaced 10° apart. Simultaneously, a laser sensor scanned the rock surface contours to obtain three-dimensional information about the environment.

[0136] Step 3: Feature Recognition

[0137] In the feature recognition stage, the vision system detects natural feature points of the rock mass and matches them with corresponding features in the left and right images. Combined with ranging data acquired by the laser sensor, the three-dimensional coordinates of the feature points are calculated.

[0138] Step 4: Hole Positioning:

[0139] During the hole positioning stage, the target hole position is matched according to the design drawings, and the deviation between the current drill bit and the target hole position is calculated, including the horizontal deviation ΔX, the vertical deviation ΔY, and the angular deviation Δθ.

[0140] Step 5: Pose Adjustment

[0141] During the position adjustment phase, the actions of the drilling rig's actuators are controlled, including: adjusting the horizontal position of the drill bit through a hydraulic cylinder, adjusting the angle of the drill rod through a pitch motor, and correcting the orientation of the drill bit through a rotating platform, thereby achieving precise positioning of the drill bit.

[0142] Step 6: Accuracy Verification:

[0143] During the accuracy verification phase, data from the current location is reacquired, and the residual error is calculated. If the residual error does not meet the requirements, steps 4 and 5 are repeated until the accuracy requirements are met.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for positioning an automatic borehole finding and positioning system for a machine vision-based anchor drilling rig, the system comprising an anchor drilling rig body and a control room installed in a roadway, characterized in that: A binocular vision camera and a laser displacement sensor are arranged on the body of the anchor rod drilling machine, and a drilling machine controller, an inclination sensor, an industrial switch, a drilling machine electric control box and a communication module are arranged in the body of the anchor rod drilling machine; A positioning target and a wireless AP base station are further arranged in the roadway; A positioning console is arranged in the control room, and a positioning control computer, a core switch and a drilling positioning server are further arranged in the positioning console; The positioning method comprises the following steps: Step one: the drilling machine controller receives data collected by the laser displacement sensor and the inclination sensor respectively, and sends the analyzed and processed data to the communication module; Step two: the drilling machine controller communicates with the drilling machine electric control box to obtain the operating parameters of the drilling machine, and sends the operating parameters of the drilling machine to the communication module; The obtained operating parameters include the drilling head rotating speed ω and the feeding speed v, and ω=kv is defined, wherein k is a material related coefficient; Step three: the drilling machine controller receives image data collected by the binocular vision camera and performs preprocessing, including image binarization, image enhancement and stereo correction processing; Step four: the communication module communicates with the core switch arranged in the control room through the wireless AP base station; Step five: the positioning target arranged in the roadway sends the position parameters to the wireless AP base station in real time through the wireless network; Step six: the collection distance is estimated by the transformation relationship between the structural parameters of the anchor rod drilling robot and the coordinate axes, and the spatial distance between the camera position and the target during image collection is calculated, and the specific method is as follows: The conversion relationship between the camera coordinate system and the body coordinate system is obtained based on the conversion relationship of each coordinate system, and the three-dimensional coordinates of the camera coordinate system in the world coordinate system are obtained in real time by the body positioning method; The camera coordinate system, the reference coordinate system and the world coordinate system are constructed respectively; Wherein, define the space coordinates of point A on the camera plane in the camera coordinate system as C A=(x1,y1,z1), and convert it to the coordinates in the world coordinate system W A=(x2,y2,z2), and the conversion formula is: ； wherein, represents the conversion relationship between the camera coordinate system and the body coordinate system, and represents the conversion relationship between the body coordinate system and the world coordinate system. The coordinates of point B on the target in the world coordinate system are defined as WB=(x3, y3, z3), wherein x3 and y3 are unknown numbers; The collection distance can be approximately expressed as the distance between point A on the camera and point B on the steel belt, and the expression is as follows: ； In order to reduce the influence of the difference between the X axis and the Y axis, the attenuation coefficient β is introduced, and the calculation formula of the spatial distance is as follows: d=βd1=1.1|(z2-z3)| Step seven: the function relationship between the collection distance and the anchor rod drilling radius in the image is used to determine the radius of the anchor rod drilling at any distance, and then the center coordinates and the maximum and minimum radius of the anchor rod drilling are determined, and the specific method is as follows: Based on the profile fitting of the target completed in step six, the following compensation rules are used to compensate the distance between the camera and the target and the center distance between the targets: ； where x i and y i represent the coordinates of the i-th target in the image; Step eight: according to the geometric constraint condition of the maximum and minimum radius of the anchor rod drilling, the steel belt anchor rod drilling is detected by using the Hough transform with adaptive adjustment of the radius parameter, and the linear slope and geometric constraint are used to realize the stereo matching of the anchor hole profile; Step nine: the spatial coordinates of the anchor hole center in the camera coordinate system are determined according to the binocular vision positioning principle; Step ten: the anchor rod drilling machine body installs the anchor rod into the corresponding anchor hole according to the determined spatial coordinates of the anchor hole center.

2. A method of positioning according to claim 1, wherein: The drill controller is connected with the binocular vision camera, the laser displacement sensor, the inclination sensor, the industrial switch, the drill electric control box and the communication module through wires respectively; The communication module is wirelessly connected with the wireless AP base station through a wireless network; The wireless AP base station is connected with the core switch through wires, and the core switch is connected with the positioning control computer and the drill hole positioning server through wires respectively; The wireless AP base station is wirelessly connected with the positioning target through a wireless network.

3. A method of positioning according to claim 2, c h a r a c t e r i s e d i n that: An explosion-proof illuminating lamp is further arranged on the anchor rod drill vehicle body, and a control end of the explosion-proof illuminating lamp is connected with the industrial switch through wires.

4. The method of positioning of a machine vision based automatic hole finding positioning system of a roof bolter as claimed in claim 2, wherein: The binocular vision camera comprises a left camera and a right camera, and the left camera and the right camera are horizontally arranged on the drill beam of the anchor rod drill vehicle body through damping supports.

5. The method of positioning of a machine vision based automatic hole finding positioning system of a roof bolter as claimed in claim 2, wherein: The laser displacement sensor is specifically installed on the bracket on the side of the drill bit of the anchor rod drill vehicle body. The measurement axis of the laser displacement sensor is arranged at an angle of 30° with the drill rod.

6. A method of positioning according to claim 2, wherein: The drill controller is specifically connected with the drill electric control box through a PROFINET bus, or through an EtherCAT network cable, or through a Modbus RTU bus.

7. A method of positioning according to claim 1, wherein: The specific method of step eight is as follows: The target center coordinates are obtained through parameter adaptive Hough circle detection: The circular function is defined as follows: x = x0 + r0cosθ; y = y0 + r0sinθ; Wherein, r0 is the target radius, x0 and y0 are the target center coordinates, x and y are image coordinates, and θ represents an angle, and the value range is 0° to 360°. Since the profile on the image is directional, the coordinates of the center are arranged from small to large in the horizontal direction, and are defined as follows: O l1 (u l1 , v l1 ), O l2 (u l2 , v l2 ), O l3 (u l3 , v l3 ),...,O lm (u lm , v lm ) are the coordinates of the center point of the anchor rod drilling in the image shot by the left camera; O r1 (u r1 , v r1 ), O r2 (u r2 , v r2 ), O r3 (u r3 , v r3 ),....,O rn (u rn , v rn ) are the coordinates of the center point of the anchor hole in the image taken by the right camera; The above coordinates are arranged in ascending order of horizontal pixel coordinate values, and the pixel coordinate values of the same point in the vertical direction based on the left and right two images are the same, the three-dimensional matching of the target center is completed by matching different anchor rod drilling centers, and the spatial coordinates of the target center are determined; Then the stereoscopic matching accuracy of the target center is verified through the directionality of the profile: If the i-th point on the left and the j-th point on the right are a group of matching points, then i±p and j±p on the image are a group of matching points; In addition, the distance between the adjacent two matching points is basically the same, and the fluctuation range is small, and the expression is as follows: |O li O li+1 | = O rj O rj+1 .

8. A method of positioning according to claim 7, wherein: The specific method of step nine is as follows: The ideal model of the binocular vision system is used to calculate the coordinates of the target center: X W , Y W , Z W are world coordinates, X C , Y C , Z C are camera coordinates, u and v are pixel plane coordinates; O l and O r are optical centers of the two cameras, B is the distance between the two cameras, f is the focal length; C l and C r are left and right image planes perpendicular to the camera optical axis Z C , respectively. Stereo correction is performed, and point A (X, Y, Z) is a point in the world coordinate system, and its response points in the image plane are a1(u1, v1) and a2(u2, v2) respectively, and the conversion formula between the world coordinate system and the image coordinate system is obtained according to similar triangles: ； The above formula is used to calculate the coordinates of any point in space, wherein f' is one of the inherent parameters, which is obtained through camera calibration; The pixel coordinates in the drilling image are determined by recognizing and matching the circles, including the coordinates in the left and right images; According to the calibration results and the segmentation and stereo matching results, the spatial coordinates of a point are calculated, and the calculation formula is as follows: y = kx + b; Wherein, k is the slope of the straight line, and b is the vertical coordinate of the origin.

Images