CN111906050A - Coal and gangue sorting system and method based on video analysis - Google Patents

Abstract

The invention provides a coal and gangue sorting system and method based on video analysis, and belongs to the technical field of artificial intelligent machines of mines. The system mainly comprises a central processing unit, a camera, a near infrared light source and a sorting control unit. The near-infrared light source is used for carrying out infrared detection and light supplement on the coal rock sample, and the camera is used for collecting video information. The central processing unit comprises a control module, a near-infrared light source control module, a video processing module, a prediction module and a communication module, and is used for controlling the operation of each part, processing, identifying and transmitting the coal rock video information to the communication module. And the communication module transmits the identification information to the sorting control unit, and commands and controls the air blowing device and the mechanical arm. The coal and gangue sorting system is simple in structure, high in recognition rate and strong in adaptability, can realize real-time recognition and information transmission, guarantees timeliness and accuracy of coal and gangue sorting, improves coal and gangue sorting efficiency, guarantees safety of personnel and effectively saves cost.

Description

Coal gangue sorting system and method based on video analysis

technical field

The invention relates to the technical field of mining machinery, in particular to a coal gangue sorting system and method based on video analysis.

Background technique

Coal gangue sorting is a process in which coal and gangue are automatically identified by a method and sorted by machines. With the enhancement of coal mining intensity, a lot of manpower is often required to sort coal and gangue. The coal gangue separation system can be widely used in the production process such as raw coal gangue separation in coal preparation plants, which can effectively reduce the labor intensity of workers and improve the working environment, which is of great significance to the safe and efficient production of the coal preparation process.

The core technology of coal gangue separation is coal rock identification technology, and there are many existing coal rock identification methods, such as radar detection, vibration detection method, electromagnetic wave detection method, etc. However, various identification methods are relatively easy to receive interference from the external environment, and have complex structures, difficult operation ports, difficult deployment, and poor device adaptability.

There is a need for a new coal rock identification method or device that improves or even solves the problems existing in the prior art.

SUMMARY OF THE INVENTION

In order to solve the technical problems existing in the prior art, the present invention provides a coal gangue sorting system and method based on video analysis, the near-infrared light source is not easily disturbed by the external environment, the light source is stable, and the video analysis method improves the identification and selection of coal and rock. Accuracy and safety, the automatic coal gangue sorting system reduces the consumption of manpower and material resources in the coal gangue sorting process.

In order to achieve the above object, the present invention proposes a coal gangue sorting system based on video analysis. The coal gangue sorting system mainly includes a central processing unit, a camera, a near-infrared light source, a camera and a sorting control unit.

The central processing unit includes a control module, a near-infrared light source control module, a prediction module, a video processing module, and a communication module;

The control module controls and connects the near-infrared light source control module, and is used for controlling the near-infrared light source to adjust the angle of the fan surface of the light source;

The control module controls the connection of the camera, and is used to trigger the camera to collect the signal of the sample video;

The control module is connected to the control video processing module, and is used to control the sample video collected by the camera to be sent to the video processing module for block division and coordinate positioning;

The control module is connected to the control prediction module, and is used for the control prediction module to retrieve the sample video from the video processing module for prediction and identification, and transmit the identification result to the sorting control unit through the communication module.

The sorting control unit includes an air blowing device and a mechanical arm; the sorting control unit is connected to the communication module, and is used for transmitting the identification result to the mechanical arm and the air blowing device to sort the coal gangue.

Further, according to the coal gangue sorting system of the present invention, the central processing unit is located in the first metal shell, installed next to the mechanical arm directly above the belt conveyor, and the near-infrared light source and the camera are located in the second metal shell. , installed on the back side of the discharge port just above the belt conveyor, the center of the side of the second metal shell facing the coal gangue object has a perspective window with a size of 10 × 20cm, and the optical axis of the camera is aligned with the center of the perspective window.

Further, according to the coal gangue sorting system of the present invention, the near-infrared light source is a single light source placed next to the camera, the bottom surface of the cone light source is perpendicular to the optical axis of the camera, and the angle of the light source fan is controlled by the processing unit to provide suitable samples for the sample. angle of the light source.

Further, according to the coal gangue sorting system of the present invention, the sorting control unit is located in the third metal shell, and is connected to control the mechanical arm and the air blowing device, and the mechanical arm and the air blowing device are located before the coal gangue conveying line. , the prediction module transmits the prediction results to the beginning and sorting control unit, and sorts the identified coal gangue.

Further, according to the coal gangue sorting system of the present invention, the prediction module adopts a DSP chip.

The beneficial effects achieved by the present invention:

The coal gangue separation system has simple structure, high recognition rate and strong adaptability, can realize real-time recognition and information transmission, ensure the timeliness and accuracy of coal gangue separation, improve coal gangue separation efficiency, and protect personnel. safety and cost savings.

Description of drawings

Fig. 1 is the structural representation of the coal gangue sorting system based on video analysis provided by the present invention;

2 is a schematic structural diagram of each module and other units of the central processing unit provided by the present invention;

FIG. 3 is a schematic structural diagram of a near-infrared light source and a camera provided by the present invention.

Fig. 4 is the working process diagram of the coal gangue sorting system based on video analysis provided by the present invention;

Reference numerals in the drawings in the description include:

1- Feeding trough, 2- Alignment device, 3- Second metal shell, 4- First metal shell, 5- Third metal shell, 6- Robot arm, 7- Air blowing device, 8- Coal transport trough, 9 - gangue trough, 10-belt conveyor, 11-near infrared light source, 12-camera, 13-radiator, 14-connector, 15-perspective window.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments.

In the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "upper", "lower", "left", "right", "upper end", "lower end", etc. are based on those shown in the accompanying drawings. The orientation or positional relationship is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. The terms "one", "two" are used for descriptive purposes only and should not be construed to indicate or imply relative importance.

Unless otherwise expressly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it may be a mechanical connection or an electrical connection, or the internal communication between two components, or a direct connection. , and may also be indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific situations.

In order to solve the problems existing in the prior art, as shown in FIGS. 1 to 4 , the present invention provides a coal gangue sorting system based on video analysis, which improves the safety, accuracy and stability of coal gangue sorting.

As shown in Figure 1, the video analysis-based coal gangue sorting system includes a feeding trough 1, which is connected to an alignment device 2 and is arranged at one end of the belt conveyor 10 to align the materials to avoid When the overlapping phenomenon occurs, the belt conveyor 10 is sequentially provided with a second metal shell 3, a first metal shell 4, a third metal shell 5, a mechanical arm 6, an air blowing device 7, a coal transport trough 8, and a gangue transport trough 9 from left to right. .

As shown in FIG. 1 , the video analysis-based coal gangue sorting system includes a central processing unit, a camera 12, a near-infrared light source 11 and a sorting control unit. The central processing unit is installed in the first metal shell and installed next to the sorting control unit.

As shown in Figure 2, the near-infrared light source and the camera are arranged in the second metal shell, which is installed on the back side of the discharge port directly above the belt conveyor. The center of the side of the second metal shell facing the coal gangue object has a size of 10 The perspective window of ×20cm, the optical axis of the camera is aligned with the center of the perspective window. The second metal shell is provided with a radiator 13 , a terminal 14 and a see-through window 15 .

The near-infrared light source is a single light source placed next to the camera, the bottom surface of the cone light source is perpendicular to the optical axis of the camera, and the angle of the light source sector is controlled by the processing unit to provide a suitable light source angle for the sample and a good light source environment for the camera. The video is clearer.

The camera adopts a CMOS imaging sensor and has functions of automatic exposure control, gamma correction, background compensation, automatic gain control, etc., and is used for collecting coal gangue video images.

As shown in FIG. 3 , the central processing unit is located in the first metal shell, and includes a control module, a near-infrared light source control module, a video processing module, a prediction module, and a communication module;

The control module adopts a RAM processor whose central processing unit is Cortex-R5 core, and the output terminal is controlled to be connected to a near-infrared light source control module, a camera, a video processing module and a coal rock identification module for controlling the operation of the entire coal rock identification device;

The control module adopts control to connect the near-infrared light source control module for controlling the near-infrared light source to adjust the angle of the fan surface of the light source;

The control module controls and connects the camera, and is used to trigger the camera to collect the signal of the sample video, and the communication port connected with the control input end of the camera imaging sensor is realized by the I ² C bus port;

The control module is connected to the control video processing module, and is used to control the sample video collected by the camera to be sent to the video processing module for block division and coordinate positioning. The data input end is connected to the camera data output port, and the storage video processing module data The output port is connected to the data input port of the prediction module, and is used to control the sample video collected by the camera to be sent to the video processing module for block division and coordinate positioning, and the communication port connected to the data output end of the camera imaging sensor is realized by the MIPI port;

The control module is connected to the control prediction module, which is used for the control prediction module to call the sample video in the video processing module for prediction and identification, and transmit the identification result to the sorting control unit through the communication module. The prediction module adopts the TMS320C6000 series of TI Company. DSP chip, the signal input end is connected to the video processing module and the output end is connected to the communication module;

The output end of the communication module is connected to the sorting control unit, and the prediction result processed by the prediction module is transmitted to the sorting control unit through the communication module. The sorting control unit is connected to the control air blowing device and the mechanical arm.

The sorting control unit is used for adjusting and controlling the air blowing device and the mechanical arm according to the predicted result, so as to sort the coal gangue.

The coal gangue sorting method based on video analysis is shown in Figure 4:

1. When the device is started, the feeding device transports the materials to the belt conveyor, and the alignment device performs alignment and tiling to prevent the stacking of materials; at the same time, the coal gangue sorting system is activated to initialize the parameters of the camera and the near-infrared light source.

2. The video processing module is connected to the control camera to shoot the coal gangue sample, which is used to control the sample video collected by the camera to be sent to the video processing module for block division and coordinate positioning.

3. The video processing module transmits the video to the prediction module to process and identify the video, and obtain the prediction result.

4. The prediction result is transmitted to the sorting control unit by the communication module, and the mechanical arm and the air blowing device sort the coal gangue according to the prediction result, which improves the sorting efficiency and saves labor costs.

The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection of the present invention. within the range.

Claims (6)

1. The coal gangue sorting system based on video analysis is characterized in that: it includes a feeding trough, which is connected to the whole column device, and is arranged at one end of the belt conveyor, and the belt conveyor is sequentially provided with a second metal shell from left to right, A metal shell, a third metal shell, a mechanical arm, an air blowing device, a coal trough, and a gangue trough; Also includes central processing unit, near-infrared light source, camera and sorting control unit: The central processing unit includes a control module, a near-infrared light source control module, a video processing module, a prediction module, and a communication module; The control module controls and connects the near-infrared light source control module, and is used for controlling the near-infrared light source to adjust the angle of the fan surface of the light source; The control module controls the connection of the camera, and is used to trigger the camera to collect the signal of the video sample; The control module is connected to the control video processing module, and is used to control the sample video collected by the camera to be sent to the video processing module for block division and coordinate positioning; The control module is connected to the control prediction module, and is used for the control prediction module to call the sample video in the video processing module for prediction and identification, and transmit the identification result to the sorting control unit through the communication module; The sorting control unit includes an air blowing device and a mechanical arm; the sorting control unit is connected to the communication module, and is used for transmitting the identification result to the mechanical arm and the air blowing device to sort the coal gangue. 2. The coal gangue sorting system based on video analysis according to claim 1, wherein the near-infrared light source is a single light source placed beside the camera, the bottom surface of the cone light source is perpendicular to the optical axis of the camera, and the angle of the light source fan surface It is controlled by the processing unit to provide a suitable light source angle for the sample. 3. The coal gangue sorting system based on video analysis according to claim 1, wherein the central processing unit is located in the first metal shell, and is installed next to the mechanical arm directly above the belt conveyor, and the light source and the The camera is located in the second metal shell and is installed directly above the belt conveyor, 0.8m away from the air blowing port. The first metal shell facing the belt conveyor has a perspective window with a size of 10 × 20cm in the center. The optical axis of the camera is opposite. The center of the quasi-perspective window. 4. The coal gangue sorting system based on video analysis according to claim 1, wherein the sorting control unit is located in the third metal shell, and is connected to control a mechanical arm and an air blowing device. The air blowing device is located before the coal gangue conveying line, and the prediction module transmits the prediction results to the beginning of the period and the sorting control unit, and sorts the identified coal gangue. 5 . The coal gangue sorting system based on video analysis according to claim 1 , wherein the prediction module adopts a DSP chip. 6 . 6. the coal gangue sorting method based on video analysis, is characterized in that, comprises the following steps: S1. When the device is started, the feeding device transports the material to the belt conveyor, and the alignment device performs alignment and tiling to prevent the stacking of materials; at the same time, the coal gangue sorting system is activated to initialize the camera and the parameters of the near-infrared light source; S2. The video processing module is connected to the control camera to shoot the coal gangue sample, which is used to control the sample video collected by the camera to be sent to the video processing module for block division and coordinate positioning; S3. The video processing module transmits the video to the prediction module to process and identify the video, and obtain a prediction result; S4. The prediction result is transmitted to the sorting control unit by the communication module, and the mechanical arm and the air blowing device sort the coal gangue according to the prediction result, so as to improve the sorting efficiency and save labor costs.

Images