Coal gangue recognition device based on AI vision

Abstract

The utility model discloses a coal gangue recognition device based on AI vision, which comprises a mounting plate, a transmission mechanism fixedly mounted on the upper surface of the mounting plate, a connecting plate fixedly mounted at one end of the transmission mechanism, a [-shaped connecting plate at one end, and a coal gangue recognition vision camera and an obstacle avoidance mechanism fixedly mounted on the lower surface of the [-shaped connecting plate, the obstacle avoidance mechanism is located at the lower end of the coal gangue recognition visual camera, a mounting frame is fixedly mounted at one end of the mounting plate, an AI visual recognition host is fixedly mounted on the upper surface of the mounting frame, and the coal gangue recognition visual camera is in signal connection with the AI visual recognition host. Through the design of the transmission mechanism and the obstacle avoidance mechanism, the automatic obstacle avoidance device has an automatic obstacle avoidance effect, so that the situation that the coal gangue identification visual camera is damaged due to collision of coal gangue can be avoided.

Description

Technical Field

[0001] The utility model relates to the technical field of AI vision recognition, in particular to a coal gangue recognition device based on AI vision. Background Art

[0002] Machine vision is a rapidly developing branch of artificial intelligence. Simply put, machine vision is the use of machines instead of human eyes to make measurements and judgments. The machine vision system converts the captured target into image signals through machine vision products, transmits them to a dedicated image processing system, obtains the morphological information of the captured target, and converts it into digital signals based on pixel distribution, brightness, color and other information; the image system performs various operations on these signals to extract the characteristics of the target, and then controls the operation of the equipment on site based on the judgment results. Many high-precision product inspections are performed using AI visual inspection equipment.

[0003] For example, the patent with the national authorized patent announcement number CN206074461U discloses a coal rock identification device based on machine vision, which mainly includes a processing unit, a light source and a camera. The light source is used to illuminate the coal rock object, the camera is used to collect the coal rock object image, and the processing unit includes a main control module, a light source control module, a coal rock identification module, a storage module, and a communication module. The operation of each part of the control device is performed to store, transmit, process and identify the coal rock object image, and the identification result is transmitted to the coal mining machine controller through the communication module. The device has a simple structure, is easy to deploy, has strong adaptability, and has a high recognition rate. It can identify the type of the current coal rock object in real time, and provide reliable coal rock identification information for production processes such as automated mining, automated coal caving, and automated gangue selection.

[0004] However, the above-mentioned coal and rock identification device based on machine vision does not have the function of avoiding obstacles during the process of ore identification. Larger or higher ores may collide with one side of the camera through the force transmitted, causing damage to the camera. Utility Model Content

[0005] The purpose of the utility model is to provide a coal gangue identification device based on AI vision to solve the problem that in the process of ore identification proposed in the above background technology, the device has no obstacle avoidance function and the camera may be damaged by the collision of the transmitted ore.

[0006] In order to achieve the above purpose, the utility model provides the following technical solutions:

[0007] A coal gangue recognition device based on AI vision, comprising: a mounting plate, a transmission mechanism is fixedly installed on the upper surface of the mounting plate, one end of the transmission mechanism is fixedly installed with a connecting plate, one end of the connecting plate is in a U shape, a coal gangue recognition vision camera and an obstacle avoidance mechanism are fixedly installed on the lower surface of the connecting plate in the U shape, the obstacle avoidance mechanism is located at the lower end of the coal gangue recognition vision camera, one end of the mounting plate is fixedly installed with a mounting frame, an AI vision recognition host is fixedly installed on the upper surface of the mounting frame, and the coal gangue recognition vision camera is in signal connection with the AI vision recognition host.

[0008] Preferably, the transmission mechanism includes a motor, the motor is fixedly installed on the upper surface of the mounting plate, the output shaft of the motor penetrates through the mounting plate and a ball screw is fixedly installed at the end, the ball screw is rotatably installed at one end of the mounting plate, a docking frame is installed on the outer surface of the ball screw by ball transmission, and one end of the docking frame is fixedly installed with a connecting plate.

[0009] Preferably, two guide rail rods are fixedly installed inside the mounting plate, and the docking frame is slidably installed on the outer surfaces of the two guide rail rods.

[0010] Preferably, the obstacle avoidance mechanism includes a docking plate, the docking plate is fixedly installed on the lower surface of the connecting plate, a sleeve is fixedly installed on the lower surface of the docking plate, and a distance sensor is inserted into the sleeve.

[0011] Preferably, the distance sensor is of the Bluetooth transmission type, the signal output end of the distance sensor is connected to the signal receiving end of the controller through Bluetooth, and the control output end of the controller is electrically connected to the electric control end of the motor.

[0012] Preferably, a threaded portion is provided on the outer surface of the distance sensor, and two flange nuts are threadedly installed on the outer surface of the threaded portion. The two flange nuts can threadedly abut against both sides of the sleeve and limit and fix the distance sensor in the sleeve.

[0013] Compared with the prior art, the beneficial effects of the present utility model are:

[0014] 1. Through the design of the transmission mechanism, the obstacle avoidance mechanism, the coal gangue recognition vision camera and the AI vision recognition host, coal gangue is a solid waste discharged during the coal mining process and the coal washing process. It is a black-gray rock with a lower carbon content and harder than coal that is associated with the coal seam during the coal formation process. During the coal washing process, it is necessary to pick out the coal gangue. When picking out the coal gangue, the coal gangue recognition vision camera and the AI vision recognition host are used to identify and mark the coal gangue, and then the marked coal gangue will be screened out of the coal mine by the machinery in the next process;

[0015] In the process of screening out coal gangue, if the height of the coal gangue is higher than the current position of the coal gangue identification visual camera, it will be identified by the obstacle avoidance mechanism, and then the obstacle avoidance mechanism will drive the transmission mechanism to drive the connecting plate to move upward to raise the height position of the coal gangue identification visual camera until the obstacle avoidance mechanism can no longer identify the coal gangue and stops. Then, after staying for ten seconds, the obstacle avoidance mechanism will drive the transmission mechanism to drive the connecting plate to restore its original height, thereby achieving the effect of obstacle avoidance, thereby preventing the coal gangue identification visual camera from being hit by coal gangue and causing damage.

[0016] 2. Through the design of motor, ball screw, docking frame and distance sensor, in the process of screening out coal gangue, if the height of coal gangue is higher than the coal gangue recognition visual camera at the current position and the distance is 50 cm, the coal gangue higher than the coal gangue recognition visual camera will cover one end of the distance sensor, so that it can be recognized by the distance sensor. Then the distance sensor will transmit the signal to the controller via Bluetooth. After receiving the signal, the controller will control the motor to drive the ball screw through the control end to drive the docking frame to rise horizontally, so that the docking frame can drive the coal gangue recognition visual camera to move horizontally. The visual camera and the distance sensor move upward to raise the height position of the gangue recognition visual camera until the distance sensor cannot recognize the gangue, then it stops rising and stays at the current height for ten seconds. After ten seconds, the higher gangue will be transmitted to the rear end and screened out. Then the distance sensor will send a reset signal to the signal receiving end of the controller again. Then the controller will control the motor to drive the connecting plate to return to the original height position, thereby achieving the effect of obstacle avoidance, thereby preventing the gangue recognition visual camera from being hit by gangue and causing damage.

[0017] When the distance sensor is disassembled and replaced, the staff only needs to unscrew the flange nut from the outer surface thread of the threaded part of the outer surface of the distance sensor, and then the distance sensor can be pulled out from the casing to achieve the purpose of disassembly. Then, the new distance sensor can be inserted into the casing and installed on the outer surface of the threaded part through the flange nut thread, and the flange nut is made to touch one end of the casing, so as to fix the distance sensor in the casing and make it convenient to disassemble and replace. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the overall structure of the coal gangue identification device based on AI vision of the utility model;

[0019] Figure 2 This is a schematic diagram of the AI ​​visual recognition host structure of the utility model;

[0020] Figure 3 It is a schematic diagram of the transmission mechanism structure of the utility model;

[0021] Figure 4This is a schematic structural diagram of the obstacle avoidance mechanism of the present utility model.

[0022] In the figure: 1. mounting plate; 101. mounting frame; 2. transmission mechanism; 201. motor; 202. ball screw; 203. docking frame; 204. guide rail rod; 3. connecting plate; 4. coal gangue recognition vision camera; 401. AI vision recognition host; 5. obstacle avoidance mechanism; 501. docking plate; 502. sleeve; 503. distance sensor; 504. threaded part; 505. flange nut. Specific embodiments

[0023] Next, the technical solutions in the embodiments of the present utility model will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present utility model. Obviously, the described embodiments are only a part of the embodiments of the present utility model, rather than all the embodiments. Based on the embodiments of the present utility model, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present utility model.

[0024] Please refer to Figure 1-Figure 4 , the present utility model provides the following technical solutions:

[0025] As Figure 1-Figure 2 shown, an AI vision-based coal gangue recognition device includes: a mounting plate 1, a transmission mechanism 2 is fixedly installed on the upper surface of the mounting plate 1, one end of the transmission mechanism 2 is fixedly installed with a connecting plate 3, one end of the connecting plate 3 is in a U shape, a coal gangue recognition vision camera 4 and an obstacle avoidance mechanism 5 are fixedly installed on the lower surface of the U-shaped connecting plate 3, the obstacle avoidance mechanism 5 is located below the coal gangue recognition vision camera 4, one end of the mounting plate 1 is fixedly installed with a mounting frame 101, an AI vision recognition host 401 is fixedly installed on the upper surface of the mounting frame 101, and the coal gangue recognition vision camera 4 is signal-connected to the AI vision recognition host 401.

[0026] Through the design of the transmission mechanism 2, the obstacle avoidance mechanism 5, the coal gangue recognition vision camera 4 and the AI vision recognition host 401, coal gangue is a solid waste discharged during the coal mining process and the coal washing process. It is a black-gray rock with a lower carbon content and harder than coal that is associated with the coal seam during the coal formation process. During the coal washing process, it is necessary to pick out the coal gangue. When picking out the coal gangue, the coal gangue recognition vision camera 4 and the AI vision recognition host 401 are used to identify and mark the coal gangue, and then the marked coal gangue will be screened out of the coal mine by the machinery in the next process;

[0027] In the process of screening out coal gangue, if there is coal gangue whose height is higher than the current position of the coal gangue identification visual camera 4, it will be identified by the obstacle avoidance mechanism 5, and then the obstacle avoidance mechanism 5 will drive the transmission mechanism 2 to drive the connecting plate 3 to move upward to raise the height position of the coal gangue identification visual camera 4, until the obstacle avoidance mechanism 5 can no longer identify the coal gangue, it will stop, and then after staying for ten seconds, the obstacle avoidance mechanism 5 will drive the transmission mechanism 2 to drive the connecting plate 3 to restore its original height, thereby achieving the effect of obstacle avoidance, thereby preventing the coal gangue identification visual camera 4 from being hit by coal gangue and causing damage.

[0028] like Figure 3-Figure 4 As shown, the transmission mechanism 2 includes a motor 201, which is fixedly mounted on the upper surface of the mounting plate 1. The output shaft of the motor 201 passes through the mounting plate 1 and a ball screw 202 is fixedly mounted on the end. The ball screw 202 is rotatably mounted on one end of the mounting plate 1. A docking frame 203 is installed on the outer surface of the ball screw 202 for ball transmission, and a connecting plate 3 is fixedly mounted on one end of the docking frame 203.

[0029] Two sets of guide rails 204 are fixedly installed in the installation plate 1 , and the docking frame 203 is slidably installed on the outer surfaces of the two sets of guide rails 204 .

[0030] The obstacle avoidance mechanism 5 comprises a docking plate 501 , which is fixedly mounted on the lower surface of the connecting plate 3 , a sleeve 502 is fixedly mounted on the lower surface of the docking plate 501 , and a distance sensor 503 is inserted into the sleeve 502 .

[0031] The distance sensor 503 is of Bluetooth transmission type. The signal output end of the distance sensor 503 is connected to the signal receiving end of the controller via Bluetooth. The control output end of the controller is electrically connected to the electric control end of the motor 201 .

[0032] A threaded portion 504 is provided on the outer surface of the distance sensor 503 , and two sets of flange nuts 505 are threadedly installed on the outer surface of the threaded portion 504 . The two sets of flange nuts 505 can be threadedly contacted on both sides of the sleeve 502 to fix the distance sensor 503 in the sleeve 502 .

[0033] Through the design of the motor 201, the ball screw 202, the docking frame 203 and the distance sensor 503, in the process of screening out the gangue, if there is a gangue whose height is higher than the gangue identification visual camera 4 at the current position and the distance is fifty centimeters, the gangue higher than the gangue identification visual camera 4 will cover one end of the distance sensor 503, so that it can be identified by the distance sensor 503, and then the distance sensor 503 will transmit the signal to the controller via Bluetooth. After receiving the signal, the controller will control the motor 201 through the control end to drive the ball screw 202 to drive the docking frame 203 to rise horizontally, so that the docking frame 20 3 can drive the gangue recognition visual camera 4 and the distance sensor 503 to move upward to raise the height position of the gangue recognition visual camera 4, until the distance sensor 503 can no longer recognize the gangue, then it will stop rising and stay at the current height for ten seconds, after which the higher gangue will be transmitted to the rear end and screened out, then the distance sensor 503 will again send a reset signal to the signal receiving end of the controller, then the controller will control the motor 201 to drive the connecting plate 3 to return to the original height position, thereby achieving the effect of obstacle avoidance, thereby preventing the gangue recognition visual camera 4 from being hit by the gangue and causing damage;

[0034] When replacing the distance sensor 503, the staff only needs to unscrew the flange nut 505 from the outer surface of the threaded portion 504 on the outer surface of the distance sensor 503, and then the distance sensor 503 can be pulled out from the sleeve 502 to achieve the purpose of disassembly. Then, the new distance sensor 503 can be inserted into the sleeve 502, and threadedly installed on the outer surface of the threaded portion 504 through the flange nut 505, and the flange nut 505 is made to touch one end of the sleeve 502, so as to limit and fix the distance sensor 503 in the sleeve 502, making it convenient to replace.

[0035] According to the above technical scheme, the working steps of this scheme are summarized and sorted out: coal gangue is solid waste discharged during the coal mining and coal washing processes. It is a kind of black-gray rock with low carbon content and harder than coal that is associated with coal seams during the coal formation process. In the coal washing process, coal gangue needs to be picked out. When selecting coal gangue, the coal gangue recognition visual camera 4 and the AI ​​visual recognition host 401 will be used to identify and mark the coal gangue. Then the marked coal gangue will be screened out of the coal mine by the machinery in the next process;

[0036] In the process of screening out coal gangue, if there is coal gangue whose height is higher than the coal gangue identification visual camera 4 at the current position and the distance is fifty centimeters, the coal gangue higher than the coal gangue identification visual camera 4 will cover one end of the distance sensor 503, so that it can be identified by the distance sensor 503, and then the distance sensor 503 will transmit the signal to the controller via Bluetooth. After receiving the signal, the controller will control the motor 201 through the control end to drive the ball screw 202 to drive the docking frame 203 to rise horizontally, so that the docking frame 203 can drive the coal gangue identification visual camera 4 and the distance sensor 503 to move upward to raise the height position of the coal gangue identification visual camera 4, until the distance sensor 503 can no longer identify the coal gangue, it will stop rising and stay at the current height for ten seconds. After ten seconds, the higher coal gangue will be transmitted to the rear end and screened out, and then the distance sensor 503 will send a reset signal to the signal receiving end of the controller again, and then the controller will control the motor 201 to drive the connecting plate 3 to return to its original height position.

[0037] Among them, it is worth mentioning that the AI ​​visual recognition host 401 can use the AI-9000 series visual analysis host, the controller can use the S7-200 ultra-miniaturized PLC controller, and the distance sensor 503 can use the infrared distance sensor with model GP2Y0A02YK0F.

[0038] In summary: the coal gangue recognition device based on AI vision has the function of automatic obstacle avoidance, thereby preventing the coal gangue recognition visual camera from being hit by coal gangue and causing damage.

[0039] Parts not involved in the present invention are the same as the prior art or can be implemented by the prior art. Although the embodiments of the present invention have been shown and described, it is understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the attached claims and their equivalents.

Claims

1. A coal gangue identification device based on AI vision, characterized in that: Including: An installation plate (1), on the upper surface of the installation plate (1), a transmission mechanism (2) is fixedly installed. One end of the transmission mechanism (2) is fixedly installed with a connecting plate (3). One end of the connecting plate (3) is in a U shape. On the lower surface of the connecting plate (3) in the U shape, a coal gangue recognition vision camera (4) and an obstacle avoidance mechanism (5) are fixedly installed. The obstacle avoidance mechanism (5) is located below the coal gangue recognition vision camera (4). One end of the installation plate (1) is fixedly installed with an installation frame (101). On the upper surface of the installation frame (101), an AI vision recognition host (401) is fixedly installed. The coal gangue recognition vision camera (4) is signal-connected to the AI vision recognition host (401).

2. The coal gangue identification device based on AI vision according to claim 1 is characterized in that: The transmission mechanism (2) includes a motor (201). The motor (201) is fixedly installed on the upper surface of the installation plate (1). The output shaft of the motor (201) penetrates through the installation plate (1) and its end is fixedly installed with a ball screw (202). The ball screw (202) is rotatably installed at one end of the installation plate (1). A docking frame (203) is installed on the outer surface of the ball screw (202) by ball transmission. One end of the docking frame (203) is fixedly installed with a connecting plate (3).

3. The coal gangue identification device based on AI vision according to claim 2 is characterized in that: Two guide rail rods (204) are fixedly installed inside the installation plate (1). The docking frame (203) is slidably installed on the outer surfaces of the two guide rail rods (204).

4. The coal gangue identification device based on AI vision according to claim 3 is characterized in that: The obstacle avoidance mechanism (5) includes a docking plate (501). The docking plate (501) is fixedly installed on the lower surface of the connecting plate (3). A sleeve (502) is fixedly installed on the lower surface of the docking plate (501). A distance sensor (503) is inserted into the sleeve (502).

5. The coal gangue identification device based on AI vision according to claim 4 is characterized in that: The distance sensor (503) is of the Bluetooth transmission type. The signal output end of the distance sensor (503) is connected to the signal receiving end of the controller through Bluetooth. The control output end of the controller is electrically connected to the electric control end of the motor (201).

6. The coal gangue identification device based on AI vision according to claim 5 is characterized in that: A threaded portion (504) is arranged on the outer surface of the distance sensor (503). Two flange nuts (505) are threadedly installed on the outer surface of the threaded portion (504). The two flange nuts (505) can threadedly abut against both sides of the sleeve (502) and limit and fix the distance sensor (503) inside the sleeve (502).

Images