A coal mine underground anchor protection equipment anchor hole accurate positioning control method and computer equipment

Abstract

The present application belongs to the technical field of coal mine automation control, and specifically relates to a coal mine underground anchor protection equipment anchor hole accurate positioning control method and computer equipment. The method comprises the following steps: S1: adjusting the distance between the camera and the anchor hole to a fixed depth; S2: collecting image data of the anchor hole by the camera to determine the current anchor hole position; S3: calculating the fine adjustment speed of the drilling rig fine adjustment mechanism according to the current anchor hole position and the target anchor hole position; S4: starting fine adjustment movement according to the fine adjustment speed calculated in S3; and S5: repeating steps S2-S4 until the drill rod moves to the target point, at which time the fine adjustment speed is 0, and the fine adjustment is completed. The present application uses a camera instead of human eyes and automatic control instead of manual operation to realize the movement of the anchor protection equipment drilling rig, thereby reducing the labor intensity of workers, improving the work efficiency and the intelligent level of anchor protection operation, and ensuring the positioning accuracy.

Description

Technical Field

[0001] This invention belongs to the field of coal mine automation control technology, specifically a method and computer equipment for precise positioning control of anchor holes in underground coal mine anchoring equipment. Background Technology

[0002] Anchoring equipment is a key component of coal mine tunneling. Currently, the commonly used vehicle-mounted anchoring equipment only achieves electro-hydraulic automated operation for a few drilling and anchoring actions. Determining anchor hole positions and adjusting the drill frame's position still require manual labor, resulting in high labor intensity and low efficiency. This is a problem that must be solved to achieve intelligent anchoring equipment. Furthermore, the high levels of dust in underground coal mines and the fact that tunneling occurs in unsupported areas pose serious threats to the personal safety of operators. To improve the speed of anchor bolt support, enhance operator safety, and reduce labor intensity, full automation of processes such as drill frame position adjustment is urgently needed.

[0003] During underground coal mine tunnel excavation, rock bolt support is primarily used to control the deformation of the surrounding rock. Currently, when drilling and anchoring underground, the drilling rig requires manual operation using a hydraulic handle or remote control. The rig is moved until the drill rod is directly below the steel strip anchor hole, at which point the drill rod begins to feed. This manual method is labor-intensive, requires highly skilled workers, and poses certain safety hazards. Summary of the Invention

[0004] To address the aforementioned problems, this invention provides a method for precise positioning and control of anchor holes in underground coal mine anchoring equipment, as well as a computer device.

[0005] This invention adopts the following technical solution: a method for precise positioning and control of anchor holes in underground coal mine anchoring equipment, comprising:

[0006] S1: Adjust the camera distance from the anchor hole to a fixed depth;

[0007] S2: The camera acquires image data of the anchor hole to determine the current anchor hole position;

[0008] S3: Calculate the fine-tuning speed of the drill frame fine-tuning mechanism based on the current anchor hole position and the target anchor hole position;

[0009] S4: Start fine-tuning movement based on the fine-tuning speed calculated in S3;

[0010] S5: Repeat steps S2-S4 until the drill pipe moves to the target point. At this point, the fine-tuning speed is 0, and the fine-tuning ends.

[0011] In some embodiments, step S2 includes:

[0012] S21: Collect image data of the anchor holes and input the image data into the super-resolution reconstruction network for super-resolution reconstruction;

[0013] S22: Identify anchor holes in the image;

[0014] S23: Extract the edge of the anchor hole;

[0015] S24: Determine the coordinates of the anchor hole center in the pixel coordinate system.

[0016] In some embodiments, step S23 includes:

[0017] Extract the image region where the anchor hole is located;

[0018] The local binarization algorithm is used to calculate the average gray level and standard deviation within the neighborhood window of each pixel;

[0019] Binarization is performed using dynamic thresholding;

[0020] Anchor hole edges are identified by closed contours.

[0021] In some embodiments, step S24 includes:

[0022] 1) Constructing an elliptic image function ;

[0023] 2) Construct a vector from the coordinates of the identified edge points. ,in, i = 1, 2, 3, ..., n , n The parameter vector represents the number of edge points obtained. , , ;

[0024] 3) Use the Moore-Penrose pseudoinverse to solve for Ax=y, and obtain the parameter vector x such that the Euclidean distance between Ax and y is equal. Minimum;

[0025] 4) After fitting the ellipse, calculate the center position. ;

[0026] 5) Calculate the distance from each edge point to the center. Among the edge points whose distance from the center is greater than the threshold, remove the point that is farthest from the center.

[0027] 6) Obtain the new edge point group n 1. Repeat steps 3), 4), and 5) to calculate the new center until the distance of all edge points from the new center is within the set threshold. The resulting center is the anchor hole center.

[0028] In some embodiments, step S3 includes: forward and backward fine-tuning speeds. v x and left and right fine adjustment speed v y .

[0029] In some embodiments, in step S3:

[0030] Forward and backward fine-tuning speed v x and left and right fine adjustment speed v y Calculate using the following formula;

[0031]

[0032] In the formula, Z For camera depth information, f This represents the distance from the camera's optical center to the imaging plane. For servo gain, u The current anchor hole in the pixel coordinate system u p Direction value, u d The target anchor hole in the pixel coordinate system u p Direction value; v The current anchor hole in the pixel coordinate system v p Direction value, v d The target anchor hole in the pixel coordinate system v p Direction value.

[0033] In some embodiments, the camera is mounted inside the drilling frame of the anchoring equipment's robotic arm, facing vertically upwards.

[0034] In some embodiments, step S4 involves using a drill frame front and rear fine-tuning mechanism. x Fine-tuning of the direction is performed using the drill frame's left-right fine-tuning mechanism. y Fine-tuning of direction.

[0035] A computer device, comprising:

[0036] One or more processors or processing units

[0037] The system memory is used to store the program data of the precise positioning control method for anchor holes of the underground anchoring equipment in coal mines.

[0038] The bus that connects the system memory and the processing unit.

[0039] In some embodiments, one or more external devices also communicate with the computer device;

[0040] A network adapter communicates with one or more networks and communicates with other modules of a computer device via a bus.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. This invention patent constructs a visual servo control system for an eye-in-hand type anchoring device; the camera is fixed at a suitable position on the drill frame, and as the drill frame moves, it provides a basis for better acquisition of target steel strip anchor holes in the tunnel.

[0043] 2. A precise positioning control method for anchor holes of anchoring equipment is proposed. An image-based visual servo motion control strategy is adopted to ensure the accuracy of the positioning control system of the anchoring equipment's robotic arm, solve the problem of precise positioning of the robotic arm of the anchoring equipment, and improve the positioning accuracy of the anchor holes of the anchoring equipment.

[0044] 3. This invention patent uses a camera instead of the human eye and automatic control instead of manual operation to realize the movement of the drilling frame of the anchoring equipment, which reduces the labor intensity of workers, improves work efficiency and the level of intelligence of anchoring operations, and ensures positioning accuracy. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the anchoring equipment structure;

[0046] Figure 2 A diagram showing the camera's installation location;

[0047] Figure 3 This is a schematic diagram of the coordinate system of this application;

[0048] Figure 4 The schematic diagram for this application has been slightly modified;

[0049] Figure 5 Schematic diagram of computer equipment;

[0050] Figure 6 This is a flowchart of the present invention. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] like Figure 6 As shown, a method for precise positioning and control of anchor holes in underground coal mine anchoring equipment includes the following:

[0053] S1: Adjust the camera distance from the anchor hole to a fixed depth.

[0054] Anchoring equipment drill arm and drill frame positioning structure, such as Figure 1 Three drive mechanisms are used as fine-tuning mechanisms to complete the precise positioning of the anchor hole. First, the drill frame lifting fine-tuning mechanism is used to adjust the drill frame to a fixed height, that is, the distance between the camera and the anchor hole is adjusted to a fixed depth.

[0055] This paper employs an image-based visual servo motion control strategy. A visual detection system, such as... Figure 2 The anchor hole positioning camera adopts an eye-in-hand configuration and is installed in a suitable position inside the drilling frame of the anchor protection equipment's robotic arm, with its direction vertically upward.

[0056] S2: The camera acquires image data of the anchor hole to determine the current anchor hole position.

[0057] S21: Collect image data of the anchor holes and input the region of interest of the image data into the super-resolution reconstruction network for super-resolution reconstruction.

[0058] Specifically, given that anchor hole images have simple target features and are prone to image homogenization, data augmentation is performed on the sample data to improve the generalization ability and robustness of the anchor hole recognition model. First, the original image is rotated 90°, 180°, horizontally flipped, and Gaussian blurred. Then, a generative adversarial network is used to generate new images to achieve data augmentation, aiming to improve the robustness of the anchor hole recognition model.

[0059] Anchor hole image super-resolution reconstruction:

[0060] Anchor holes refer to the circular holes pre-drilled for anchors on the steel strip supporting the roof of underground coal mines. Image quality directly affects the effectiveness of anchor hole recognition models in identifying anchor holes. The clearer the image, the more information it contains, which is more beneficial for subsequent anchor hole recognition and localization. Some details in the anchor hole image are important, such as the anchor hole edges and the anchor mesh wires inside the hole. Image super-resolution can recover high-frequency information lost during image subsampling, improving image perception quality and contributing to increased accuracy in computer vision tasks.

[0061] The super-resolution reconstruction network structure EDSR, similar to SRResNet, is adopted. However, the model does not have ReLU activation layers outside the residual modules, and its baseline model also lacks residual scaling layers, using only 64-dimensional feature maps for each convolutional layer. The baseline model is expanded by adjusting the number of depth layers, feature channels, and scaling factors. Furthermore, an upsampling factor of ×2 is used to train the model, accelerating the training process and improving the final reconstruction performance. Simplifying the residual network for image super-resolution reconstruction aims to make the anchor hole recognition model more lightweight.

[0062] S22: Identify anchor holes in the image.

[0063] Anchor hole identification model establishment:

[0064] To improve the quality of anchor hole images acquired underground in coal mines, super-resolution reconstruction of the region of interest images was performed and used as input for subsequent recognition models.

[0065] To further improve recognition speed, meet the requirements for accurate recognition, and support subsequent anchor hole center extraction algorithms, an attention mechanism is added to the end of the YOLOv4 bottleneck network. This enhances the learning of anchor hole target features in the image, improving the network's performance in recognizing anchor holes. The ECA attention module, a type of channel attention module, strengthens the channel features of the input feature map. Furthermore, the final ECA module output does not change the size of the input feature map. As a plug-and-play attention module, it can be easily added to the end of the YOLOv4 bottleneck network. Introducing the ECA attention mechanism at the end of the YOLOv4 bottleneck network allows the network to focus more on the anchor holes to be detected, further improving the recognition performance and effectiveness of anchor holes on steel strips.

[0066] For embedded deployments, YOLOv4 suffers from issues such as excessively large convolutional models, slow recognition speed, and high storage space consumption of weight files. Employing a lightweight network for its backbone alleviates these problems. Furthermore, due to the limited variety of anchor holes in anchor bolt support sites, the lightweight network further improves recognition speed. MobileNetV2 is a lightweight CNN network focused on mobile or embedded devices. It uses an inverse residual structure and a linear layer at the end of the structure, significantly reducing parameters and computational load with a slight decrease in accuracy, making it suitable for deployment on embedded devices.

[0067] S23: Extract the edge of the anchor hole.

[0068] The center of the target anchor frame obtained from anchor hole identification does not coincide with the center of the anchor hole on the steel strip. Therefore, the center of the target anchor frame cannot be directly used as the coordinate for anchor hole positioning. The following study investigates the method for determining the anchor hole center.

[0069] After identifying the anchor holes, the edges of the anchor holes need to be extracted first in order to calculate the center position of the anchor holes.

[0070] (1) Extract the image region where the anchor hole is located based on the target anchor frame determined by the anchor hole recognition model;

[0071] (2) Use the local binarization algorithm to calculate the average gray level and standard deviation within the neighborhood window of each pixel;

[0072]

[0073]

[0074] (3) Binarization is performed using dynamic thresholding;

[0075]

[0076] (4) Identify the edge of the anchor hole by the closed contour.

[0077] S24: Determine the coordinates of the anchor hole center in the pixel coordinate system.

[0078] 1) Constructing an elliptic image function ;

[0079] 2) Construct a vector from the coordinates of the identified edge points. ,in, i = 1, 2, 3, ..., n , n The parameter vector represents the number of edge points obtained. , , ;

[0080] 3) Use the Moore-Penrose pseudoinverse to solve for Ax=y, and obtain the parameter vector x such that the Euclidean distance between Ax and y is equal. Minimum;

[0081] 4) After fitting the ellipse, calculate the center position. ;

[0082] 5) Calculate the distance from each edge point to the center. Among the edge points whose distance from the center is greater than the threshold, remove the point that is farthest from the center.

[0083] 6) Obtain the new edge point group n 1. Repeat steps 3), 4), and 5) to calculate the new center until the distance of all edge points from the new center is within the set threshold. The resulting center is the anchor hole center.

[0084] S3: Calculate the fine-tuning speed of the drill frame fine-tuning mechanism based on the acquired image data.

[0085] The purpose of the vision control scheme is to reduce errors. e Minimize, as in equation (1). S It is the current image feature. These are the desired image features. S It consists of features directly obtained from image data. The control accuracy is independent of camera calibration and hand-eye calibration accuracy, enabling precise control of the robotic arm of anchoring equipment in complex environments.

[0086] (1)

[0087] The transformation matrix between the pixel coordinate system and the image coordinate system is given by equation (2), where, and These represent the physical dimensions of each pixel along the horizontal and vertical axes of the imaging plane, respectively; that is, the length of one pixel is... millimeters The unit is "millimeters per pixel"; This is the tilt factor, used to correct for slight tilt of the imaging plane. The point where the camera's optical axis intersects the imaging plane, i.e., the origin of the image coordinate system. Oi Coordinates in pixel coordinate system. u , v () is a point in the pixel coordinate system; x , y () is a point in the image coordinate system.

[0088] (2)

[0089] Transformation matrix between camera coordinate system and image coordinate system: Ignoring imaging distortion, equation (3) can be obtained from similar triangles, where, f It represents the distance from the camera's optical center to the imaging plane, i.e., the camera's focal length. , , , , , f These six parameters are the camera's intrinsic parameters, and the Zhang Zhengyou calibration method is used for intrinsic parameter calibration.

[0090] (3)

[0091] Equation (3) can be written in matrix form as follows:

[0092] (4)

[0093] The camera in the world coordinate system is in terms of velocity Movement, such as Figure 3 P is a point in the workspace, and the coordinates of point P relative to the camera coordinate system are (X , Y , Z The velocity of this point relative to the camera coordinate system is given by equation (5):

[0094] (5)

[0095] in, It is the instantaneous linear velocity at the origin of the camera coordinate system. It is the instantaneous angular velocity of the origin of the camera coordinate system.

[0096] Written in scalar form as:

[0097] (6)

[0098] (7)

[0099] (8)

[0100] From equation (3), we get

[0101] (9)

[0102] (10)

[0103] Using the derivative rule and scalar formula, we can obtain:

[0104] (11)

[0105] Once the camera is adjusted to a fixed distance from the anchor hole, the drill frame undergoes further fine-tuning in both forward / backward and left / right directions. At this point, the drill frame's movement speed is... Here, an image-based hand-eye vision servo control law is used to adjust the drill frame fine-tuning mechanism, so that the current anchor hole image features are moved to the desired anchor hole image feature position. Let... It is the current anchor hole image feature in the image coordinate system. The desired anchor hole image features, and the error of the anchor hole image features. e As shown in equation (12).

[0106] (12)

[0107] (13)

[0108] From equation (11), we get:

[0109] (14)

[0110] The camera uses an eye-in-hand mounting method, so the camera speed is the same as the drill string's movement speed. Therefore:

[0111] (15)

[0112] To ensure the stability of the controller closed-loop system, it is assumed that a proportional controller based on the Lyapunov method is used, and the error decreases exponentially due to decoupling, i.e.: .

[0113] We can deduce that:

[0114] (16)

[0115] Therefore, the speed of the drill frame fine-tuning mechanism can be determined based on the target feature coordinates and fixed depth information. Z Calculated.

[0116] Based on Lyapunov candidate functions, the designed controller guarantees the stability of the closed-loop system.

[0117] S4: Start fine-tuning the movement based on the fine-tuning speed calculated in S3.

[0118] S5: Repeat steps S2-S4 until the drill pipe moves to the target point. At this point, the fine-tuning speed is 0, and the fine-tuning ends.

[0119] To implement the above embodiments, this application also proposes a computer program product that, when the instruction processor in the computer program product is executed, performs the control method for the movement of the robotic arm as proposed in the foregoing embodiments of this application.

[0120] Figure 5 A block diagram of an exemplary computer device suitable for implementing embodiments of the present application is shown. Figure 5 The computer device 12 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0121] like Figure 5 As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0122] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0123] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0124] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media, and may provide a disk drive for reading and writing to removable non-volatile disks (e.g., "floppy disks"), and an optical disc drive for reading and writing to removable non-volatile optical discs (e.g., compact disc read-only memory (CD-ROM), digital video disc read-only memory (DVD-ROM), or other optical media). In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.

[0125] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this disclosure.

[0126] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0127] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the methods mentioned in the foregoing embodiments.

[0128] 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 precise positioning and control of anchor holes in underground coal mine anchoring equipment, characterized in that, include: S1: Adjust the camera distance from the anchor hole to a fixed depth; S2: The camera acquires image data of the anchor hole to determine the current anchor hole position; Step S2 includes: S21: Collect image data of the anchor holes and input the image data into the super-resolution reconstruction network for super-resolution reconstruction; S22: Identify anchor holes in the image; S23: Extract the edge of the anchor hole; S24: Determine the coordinates of the anchor hole center in the pixel coordinate system; Step S24 includes: 1) Constructing an elliptic image function ; 2) Construct a vector from the coordinates of the identified edge points. ,in, i = 1, 2, 3, ..., n , n The parameter vector represents the number of edge points obtained. , , ; 3) Use the Moore-Penrose pseudoinverse to solve for Ax = y, and obtain the parameter vector x such that the Euclidean distance between Ax and y is equal. Minimum; 4) After fitting the ellipse, calculate the center position. ; 5) Calculate the distance from each edge point to the center. Among the edge points whose distance from the center is greater than the threshold, remove the point that is farthest from the center. 6) Obtain the new edge point group n 1. Repeat steps 3), 4), and 5) to calculate the new center until the distance of all edge points from the new center is within the set threshold. The resulting center is the anchor hole center. S3: Calculate the fine-tuning speed of the drill frame fine-tuning mechanism based on the current anchor hole position and the target anchor hole position; In step S3, the fine-tuning speed includes: forward and backward fine-tuning speed. v x and left and right fine adjustment speed v y ; Forward and backward fine-tuning speed v x and left and right fine adjustment speed v y Calculate using the following formula: In the formula, Z For camera depth information, f This represents the distance from the camera's optical center to the imaging plane. For servo gain, u The current anchor hole in the pixel coordinate system u p Direction value, u d The target anchor hole in the pixel coordinate system u p Direction value; v The current anchor hole in the pixel coordinate system v p Direction value, v d The target anchor hole in the pixel coordinate system v p Direction value; S4: Start fine-tuning movement based on the fine-tuning speed calculated in S3; S5: Repeat steps S2-S4 until the drill pipe moves to the target point. At this point, the fine-tuning speed is 0, and the fine-tuning ends.

2. The method for precise positioning and control of anchor holes in underground coal mine anchoring equipment according to claim 1, characterized in that, Step S23 includes: Extract the image region where the anchor hole is located; The local binarization algorithm is used to calculate the average gray level and standard deviation within the neighborhood window of each pixel; Binarization is performed using dynamic thresholding; Anchor hole edges are identified by closed contours.

3. The method for precise positioning and control of anchor holes in underground coal mine anchoring equipment according to claim 1, characterized in that, The camera is installed inside the drilling frame of the anchoring equipment, facing vertically upwards.

4. The method for precise positioning and control of anchor holes in underground coal mine anchoring equipment according to claim 1, characterized in that, In step S4, a fine-tuning mechanism for the drill frame is used. x Fine-tuning of the direction is performed using the drill frame's left-right fine-tuning mechanism. y Fine-tuning of direction.

5. A computer device, characterized in that, include: One or more processing units (16). The system memory (28) is used to store program data for the precise positioning control method of anchor holes of underground anchoring equipment in coal mines as described in any one of claims 1-2; Bus (18) connecting system memory (28) and processing unit (16).

6. The computer device according to claim 5, characterized in that, It also includes one or more external devices (14) communicating with the computer device; The network adapter (20) communicates with one or more networks and communicates with other modules of the computer device via a bus (18).

Images