Autonomous material crushing method of rail type hydraulic robot based on AI positioning

Abstract

The invention discloses a rail type hydraulic robot autonomous material crushing method based on AI positioning, and belongs to the technical field of ore extraction. Identifying whether the large materials are stuck or not; when materials are blocked, the obtained geometric center coordinates of the large materials are converted into space coordinates, the walking mechanism is adjusted to move to the horizontal coordinates of the large materials through the space coordinates, and the impact hammer moves to the geometric center position of the large materials by controlling the included angle between the large arm oil cylinder and the Z axis and the included angle between the small arm oil cylinder and the Z axis of the mechanical arm, so that the large materials are crushed. According to the method, unmanned and intelligent autonomous crushing operation of the large-block materials in the crushing station is achieved, the large-block materials are prevented from being blocked in the crushing station, the operation efficiency of the crushing station is improved, work of workers in a severe environment is reduced, and manpower and safety are reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of ore mining, and in particular relates to a method for autonomously crushing materials by a track-type hydraulic robot based on AI positioning. Background Art

[0002] In open-pit mines, after ore mining, mining dump trucks carry ore to the receiving hopper of the open-pit mine crushing station and dump it. The ore material is transported to the crusher with the plate feeder for crushing. Due to the different sizes of ore materials, large pieces of material are easily stuck in the receiving hopper of the plate feeder or above the crushing chamber, causing blockage, affecting the subsequent dumping of ore and affecting equipment production. At present, large pieces of material are still removed by workers on site operating hydraulic crushing machinery to break large ores. The on-site working environment is relatively complex and harsh, with high labor intensity, low work efficiency, poor safety and high occupational hazards. Summary of the invention

[0003] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a method for autonomously crushing materials by a track-type hydraulic robot based on AI positioning.

[0004] The technical solution adopted by the invention is: a method for autonomous material crushing of a track-type hydraulic robot based on AI positioning. The technical key points are that it includes an initialization step, which is characterized in that it also includes the following steps: identifying whether a large piece of material is stuck; when stuck, converting the acquired geometric center coordinates of the large piece of material into spatial coordinates, and using the spatial coordinates to adjust the walking mechanism to move to the horizontal coordinate of the large piece of material, and by controlling the angle between the mechanical arm's arm cylinder, the arm cylinder and the Z axis, the impact hammer is moved to the geometric center position of the large piece of material to crush the large piece of material.

[0005] Furthermore, the process of converting the geometric center coordinates of the obtained bulk material into spatial coordinates is as follows:

[0006] The coordinates (x0, y0) of the geometric center point of the bulk material on the image are converted into the coordinates (X1, Y1) in the spatial plane. The method is:

[0007] Set the center point of the image plane as the origin of the image plane, set the AI ​​recognition camera lens as the origin of the space coordinate, and according to the pinhole imaging principle, set the point where the image origin is projected on the ground through the pinhole as the origin of the space plane coordinate. The direction from the crushing chamber along the plate feeder to the receiving hopper is the positive direction of the X-axis, the direction perpendicular to the X-axis and pointing to the direction of the robot arm track is the positive direction of the Y-axis, and the direction perpendicular to the ground downward is the positive direction of the Z-axis. Use AI recognition to automatically obtain the coordinates of the geometric center point of the bulk material on the image (x0, y0), and calculate the coordinates of the geometric center point of the bulk material in space (X1, Y1) according to the pinhole imaging principle.

[0008] Furthermore, by controlling the angle θ between the mechanical arm's big arm oil cylinder and the negative direction of the Z axis, and the angle ω between the small arm oil cylinder and the positive direction of the Z axis, the mechanical arm's breaker hammer can be aligned with the geometric center point of the bulk material for crushing;

[0009] Because θ and ω are a set of related data, the corresponding relationship is:

[0010]

[0011] Where: θ is the angle between the arm cylinder and the negative direction of the Z axis; ω is the angle between the arm cylinder and the positive direction of the Z axis;

[0012] Y1 is the y coordinate value from the geometric center point of the bulk material to the origin of the spatial coordinate; Y2 is the y coordinate value from the center line of the robot track to the origin of the spatial coordinate; Z1 is the z coordinate value from the geometric center point of the bulk material to the origin of the spatial coordinate; Z2 is the z coordinate value from the base point of the boom cylinder to the origin of the spatial coordinate;

[0013] When θ takes a fixed value θ1, the corresponding ω is also a fixed value ω1, then the value of ω1 is:

[0014]

[0015] Where: θ1 is a certain value of the angle between the hydraulic cylinder of the robot arm and the negative direction of the Z axis; ω1 is a corresponding value of the angle between the hydraulic cylinder of the forearm and the positive direction of the Z axis.

[0016] The beneficial effects of the present invention are: a method for autonomously crushing materials by a rail-type hydraulic robot based on AI positioning, identifying whether a large piece of material is stuck; when the material is stuck, the geometric center coordinates of the acquired large piece of material are converted into spatial coordinates, and the spatial coordinates are used to adjust the movement of the walking mechanism to the horizontal coordinate of the large piece of material, and the angle between the mechanical arm's big arm cylinder, the small arm cylinder and the Z axis is controlled to move the impact hammer to the geometric center position of the large piece of material to crush the large piece of material. This method realizes the unmanned, intelligent and autonomous crushing operation of large pieces of material in the crushing station, prevents large pieces of material from being stuck in the crushing station, improves the operating efficiency of the crushing station, reduces the work of staff in harsh environments, and reduces the number of people and increases safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A diagram showing the relationship between an object and a real or virtual phase in an embodiment of the present invention;

[0019] Figure 2 is a diagram showing the relationship between the image plane and the space plane in an embodiment of the present invention;

[0020] Figure 3 A schematic diagram of a spatial plane coordinate system in an embodiment of the present invention;

[0021] Figure 4 Schematic diagram of the coordinates of the center point of a bulk material in the camera plane in an embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram of the coordinates of the center point of a bulk material in a spatial plane in an embodiment of the present invention;

[0023] Figure 6 Schematic diagram of the relative relationship between the bulk material and the robot arm base in an embodiment of the present invention;

[0024] Figure 7 Schematic diagram of a robotic arm crushing large pieces of material in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the following is a brief description of the present invention in conjunction with the attached Figure 1-Figure 7 The present invention is further described in detail with reference to the accompanying drawings and specific embodiments.

[0026] This embodiment adopts a method of autonomous material crushing by a rail-type hydraulic robot based on AI positioning, which is implemented by a PLC controller, a camera using a Hikvision AI camera (model: DS-2XA8247F-GTS, focal length 10mm), a Gray busbar and an inclinometer, and a hydraulic mechanical arm. The PLC controller is connected to the host computer system, and the AI ​​camera, Gray busbar, inclinometer and hydraulic mechanical arm are respectively connected to the programmable logic control system.

[0027] The AI ​​camera is installed above the receiving hopper of the crushing station, with the camera plane parallel to the ground. The Gray busbar is installed on the side of the robotic arm track and laid along the track. The inclinometer is installed at the joint of the boom cylinder and the arm cylinder to measure the angle between the boom cylinder, the arm cylinder and the vertical direction.

[0028] The process of crushing materials in this embodiment includes the following steps:

[0029] Step 1: Turn on the device;

[0030] Step 2: System self-check to determine whether the signals of each sensor are normal and to identify equipment faults;

[0031] Step 3: Determine whether the real fault has been cleared, unlock the program soft hold fault, if the soft fault is unlocked, the real fault has been cleared, go to step 4, if the soft fault is not unlocked, the real fault has not been cleared, continue to step 2;

[0032] Step 4: Determine whether the automatic readiness conditions are met; if so, the system can run and execute step 5; otherwise, execute steps 1-4;

[0033] Step 5: Submit an application for operating conditions to the main control room;

[0034] Step 6: Select automatic mode or remote control mode. If automatic mode is selected, go to step 7, otherwise go to step 14;

[0035] Step 7: One-click automatic start;

[0036] Step 8: Use the bulk recognition function of the AI ​​video recognition system to continuously detect whether there is a large block of material stuck. If there is a large block of material stuck, execute step 9 to calculate the coordinates of the geometric center point of the large block of material. Otherwise, continue to execute step 8;

[0037] Step 9: Convert the coordinates (x0, y0) of the geometric center of the bulk material on the image into the coordinates (X1, Y1) in the spatial plane using the following method:

[0038] Set the center point of the image plane as the origin of the image plane, set the AI ​​recognition camera lens as the origin of the space coordinates, and according to the pinhole imaging principle, set the point where the image origin is projected on the ground through the pinhole as the origin of the space plane coordinates. Set the direction from the crushing chamber along the plate feeder to the receiving hopper as the positive direction of the X axis, the direction perpendicular to the X axis and pointing to the robot arm track as the positive direction of the Y axis, and the direction perpendicular to the ground downward as the positive direction of the Z axis. Figure 1 The AI ​​recognition software can automatically give the coordinates (x0, y0) of the geometric center point of the bulk material on the image, and calculate the coordinates (X1, Y1) of the geometric center point of the bulk material in space based on the pinhole imaging principle.

[0039] According to the similar triangle relationship △oOp≈△oO'P, we can get:

[0040]

[0041] Again in the camera plane:

[0042]

[0043] In the spatial plane:

[0044]

[0045] From the above formula, we can get:

[0046]

[0047] again l 2 =a 2 +h 2

[0048] Therefore:

[0049]

[0050] From the triangle similarity relation △oOp≈△oO'P, we can know that:

[0051]

[0052] And l 2 =a 2 +h 2

[0053] Therefore The z-axis coordinate of the geometric center point of the bulk material can be obtained:

[0054]

[0055] Thus, the coordinates of the geometric center point of the bulk material in space (X1, Y1, Z1) can be obtained.

[0056]

[0057] In the above formula, α is the angle between the geometric center point of the bulk material on the image and the x-axis; h is the length of the line segment oO, which is the focal length of the AI ​​recognition camera and is a known device parameter h = 10 mm; H is the length of the line segment oO'; a is the length of the line segment Op; l is the length of the line segment op; β is the angle between the geometric center point of the bulk material and the Z-axis; L is the length of the line segment oP, which can be measured by the AI ​​recognition camera + laser radar, L = 6 meters;

[0058] Note: The coordinates of the geometric center of the bulk material given by the AI ​​bulk recognition software are (8, 6); the measured length L from the AI ​​recognition camera to the geometric center of the bulk material is 6 meters. The calculated spatial coordinates of the geometric center of the bulk material are (3.39, 2.54, 4.24);

[0059] Step 10: The main PLC controller starts the sound and light alarm, and the program is preset for 30 seconds to control the walking mechanism of the robot arm to move. The moving distance can be measured by the Gray bus. When the walking mechanism moves to the same X coordinate as the geometric center point of the bulk material, the walking mechanism stops. At this time, the coordinates of the robot arm base on the spatial plane are (3.39, 3);

[0060] Step 11: The main PLC controller controls the robot arm, and by controlling the angle between the robot arm's big arm cylinder and the small arm cylinder and the Z axis, the impact hammer moves to the geometric center of the bulk material to crush the bulk material. The crushing time is 45 seconds.

[0061] Step 11 requires the angle between the robot arm's upper arm cylinder, the lower arm cylinder and the Z axis. The method is:

[0062] The spatial coordinates of the robot arm base are (X1, Y2, Z2), where Y2 is the coordinate of the center line of the robot arm track, which can be measured as Y2=3.0; since the height of the robot arm base relative to the AI ​​recognition camera is fixed, the Z2 value can be measured as Z2=3.5; the spatial coordinates of the robot arm base are (3.39, 5.0, 3.5).

[0063] The length of the boom cylinder is known to be L1 = 2.5 meters, the length of the forearm cylinder is known to be L2 = 1.5 meters, the angle between the boom cylinder and the negative direction of the Z axis measured by the inclinometer is θ, the angle between the forearm cylinder and the positive direction of the Z axis measured by the inclinometer is ω, and the spatial coordinates of the impact hammer are taken as (x, y, z). According to the geometric relationship, we can get:

[0064]

[0065] The mechanical arm impact hammer breaks the bulk material, so the spatial coordinates of the impact hammer are equal to the geometric center point of the bulk material: x = X1

[0066] y=Y1

[0067] z=Z1

[0068] have to:

[0069] L1sinθ+L2sinω=Y2-Y1 and 0°<θ<90°, 0°<ω<90°

[0070] L1cosθ-L2cosω=Z2-Z1 and 0°<θ<90°, 0°<ω<90°

[0071] Note: (X1, Y2, Z2) are the spatial coordinates of the robot arm base; (x, y, z) are the spatial coordinates of the robot arm impact hammer; L1 is the length of the robot arm's big arm cylinder; L2 is the length of the robot arm's small arm cylinder; θ is the angle between the big arm cylinder and the negative direction of the Z axis; ω is the angle between the small arm cylinder and the positive direction of the Z axis;

[0072] From the above formula, we can see that θ and ω are a set of related data. When the appropriate θ=θ1=15° is taken,

[0073]

[0074] The main PLC controller controls the robotic arm. When the angle between the upper arm cylinder and the negative direction of the Z axis is appropriately θ=θ1=15°, and the angle between the lower arm cylinder and the positive direction of the Z axis is ω=ω1≈29.7°, the robotic arm can crush large pieces of material.

[0075] Therefore, the main PLC controller controls the robotic arm to break the stuck large pieces of material by moving the robotic arm to the track at the same position as the x-coordinate of the geometric center point of the large piece of material, controlling the big arm cylinder to rotate to an angle of θ1≈15° with the negative direction of the Z axis, and controlling the small arm cylinder to rotate to an angle of ω1≈29.7° with the positive direction of the Z axis, and then the impact hammer is aimed at the geometric center point of the large piece of material for breaking.

[0076] Step 12: The AI ​​video recognition system can automatically determine whether the bulk material is broken. If it is broken, go to step 13, otherwise go to step 11;

[0077] Step 13: The main PLC controls the robot arm to retract and the walking mechanism to return to the origin of the equipment;

[0078] Step 14: Task completed, system shut down.

[0079] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for autonomous material crushing by a rail-type hydraulic robot based on AI positioning, comprising an initialization step, characterized in that: The following steps are also included: Identify whether the bulk material is stuck; when the material is stuck, convert the geometric center coordinates of the bulk material into spatial coordinates, and use the spatial coordinates to adjust the walking mechanism to move to the horizontal coordinate of the bulk material. By controlling the angle between the mechanical arm's boom cylinder, forearm cylinder and the Z axis, the impact hammer is moved to the geometric center of the bulk material to crush the bulk material.

2. The method for autonomous material crushing by a rail-type hydraulic robot based on AI positioning as claimed in claim 1 is characterized in that: The process of converting the geometric center coordinates of the acquired bulk material into spatial coordinates is as follows: The coordinates (x0, y0) of the geometric center point of the bulk material on the image are converted into the coordinates (X1, Y1) in the spatial plane. The method is: Set the center point of the image plane as the origin of the image plane, set the AI ​​recognition camera lens as the origin of the space coordinate, and according to the pinhole imaging principle, set the point where the image origin is projected on the ground through the pinhole as the origin of the space plane coordinate. The direction from the crushing chamber along the plate feeder to the receiving hopper is the positive direction of the X-axis, the direction perpendicular to the X-axis and pointing to the direction of the robot arm track is the positive direction of the Y-axis, and the direction perpendicular to the ground downward is the positive direction of the Z-axis. Use AI recognition to automatically obtain the coordinates of the geometric center point of the bulk material on the image (x0, y0), and calculate the coordinates of the geometric center point of the bulk material in space (X1, Y1) according to the pinhole imaging principle.

3. The method for autonomous material crushing by a rail-type hydraulic robot based on AI positioning as claimed in claim 1 is characterized in that: The angle θ between the upper arm oil cylinder and the negative direction of the Z axis and the angle ω between the lower arm oil cylinder and the positive direction of the Z axis are controlled: the corresponding relationship between θ and ω is: Wherein, θ is the angle between the arm cylinder and the negative direction of the Z axis; ω is the angle between the arm cylinder and the positive direction of the Z axis; Y1 is the y coordinate value from the geometric center point of the bulk material to the origin of the spatial coordinate; Y2 is the y coordinate value from the center line of the robot track to the origin of the spatial coordinate; Z1 is the z coordinate value from the geometric center point of the bulk material to the origin of the spatial coordinate; Z2 is the z coordinate value from the base point of the arm cylinder to the origin of the spatial coordinate; When θ takes a fixed value θ1, the corresponding ω is also a fixed value ω1, then the value of ω1 is: Wherein, θ1 is a certain value of the angle between the hydraulic cylinder of the robot arm and the negative direction of the Z axis; ω1 is a corresponding value of the angle between the hydraulic cylinder of the forearm and the positive direction of the Z axis.

Images