Dense medium shallow slot intelligent control system and control method thereof

Through AI visual analysis technology and machine learning algorithms, the fluid force field of heavy-middle grooves is monitored and controlled in real time, and the complexity of suspension density adjustment and accident control problems are solved, and the high accuracy and stability of heavy-middle groove sorting is achieved, improving the improvement of high-quality and stability of heavy-middle groove sorting The intelligence level of coal preparation plants.

CN119016189AActive Publication Date: 2024-11-26YHD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411181454.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-26
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

The existing heavy-interstitial shallow trough sorting process has complicated suspension density adjustment and difficult to effectively control vortex and pan-flowering accidents, resulting in unstable sorting, affecting the yield of refined coal and the coal-carrying rate of gangue.

Method used

Using AI vision analysis technology combined with machine learning algorithms, images are monitored and identified in real time through cameras or sensors, sorting and recognition models are established, horizontal flow and upstream solenoid valves are adjusted, and the fluid force field is changed to achieve accuracy of heavy-interference shallow grooves. control.

Benefits of technology

Improve the stability and accuracy of heavy-interference shallow trough sorting, reduce manual intervention, reduce coal belt rate, improve refined coal output, adapt to coal quality changes and working conditions, and improve the intelligence of coal preparation plants. level.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119016189A_ABST
    Figure CN119016189A_ABST
Patent Text Reader

Abstract

The invention provides an intelligent control method for a dense-medium shallow slot, which comprises the following steps of: acquiring an image sorted by the dense-medium shallow slot based on an AI visual analysis technology, preprocessing, and judging whether an abnormal phenomenon exists or not; extracting features related to the abnormal phenomenon from the preprocessed image; training the extracted features based on a machine learning algorithm, and establishing a sorting recognition and control model; dense medium shallow slot sorting images are collected in real time, a sorting recognition and control model is used for recognition, whether an abnormal phenomenon exists or not and the degree, the position and the influence range of the abnormal phenomenon are obtained, and the opening degree of the horizontal flow high-precision electromagnetic valve and the opening degree of the upward flow high-precision electromagnetic valve are adjusted when the abnormal phenomenon exists. The method can effectively improve the stability and accuracy of the heavy medium shallow slot washing process, is suitable for coal quality change and working condition fluctuation in an industrial field, guides actual production control, and practically improves the intelligent level of a coal preparation plant.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of heavy medium coal preparation production, and specifically but not limited to, to a heavy medium shallow tank intelligent control system and a control method thereof. Background Art

[0002] In recent years, the coal preparation industry has entered a wave of intelligent construction. Due to the poor endowment of coal resources, variable coal quality, and large amount of coal to be selected in my country, the sorting process of coal preparation plants in my country is complex and diverse compared with that in foreign countries. In my country, the vast majority of thermal coal preparation plants are based on the heavy medium shallow trough sorting process. It is particularly important to achieve clean and efficient use of coal through the intelligent transformation of the heavy medium shallow trough. At present, most scientific research institutions and many scholars mostly study the control of heavy medium over heavy medium shallow trough sorting, mainly focusing on the use of coal selectivity curves, and realizing automatic control of medium density through the system online intelligent setting of sorting process parameters such as circulating medium density.

[0003] The heavy medium shallow trough sorting process is to separate clean coal from gangue by stratifying the raw coal in the heavy medium suspension according to the different densities. At present, the main methods for intelligent research on heavy medium shallow troughs are mostly based on the ash content of raw coal and clean coal, and the density of the suspension is obtained by the selectivity curve for sorting. However, the adjustment of the suspension density has the disadvantages of large changes and complex processes. At the same time, it is impossible to conduct relevant research and solutions to accidents such as heavy medium blooming and vortexes that are prone to occur during heavy medium shallow trough sorting. Therefore, it is necessary to conduct effective research on multiphase flow in heavy medium shallow troughs, and finally achieve precise control through linkage with intelligent video. With the in-depth development of control engineering and the precise manufacturing of various instruments and meters, the use of intelligent video analysis to adjust the opening of each valve, thereby affecting the flow field of horizontal flow and upward flow, and achieving precise sorting is one of the directions of intelligent development of heavy medium shallow trough sorting technology.

[0004] Therefore, by adjusting the thrust generated by the pumping medium, the fluid force field in the shallow trough can be changed, and then the shallow trough sorting can be fine-tuned, which can better meet the high-precision sorting control of the heavy medium shallow trough, and realize the difficulty of shallow trough sorting valve adjustment through automatic adjustment instead of relying on manual experience; at the same time, it can effectively control accidents such as "vortex" and "floating" that occur in shallow trough sorting; further increase the output of clean coal, reduce the coal carrying rate of gangue, and guide the coal preparation plant to produce under the optimized control strategy that conforms to the actual situation.

[0005] In view of this, it is necessary to provide a new structure or method to solve at least part of the above problems. Summary of the invention

[0006] In response to one or more problems in the prior art, the present invention proposes an intelligent control system for a heavy medium shallow tank and a control method thereof. By establishing a sorting identification and control model to control the solenoid valves on the horizontal flow and ascending flow pipelines, the stability and accuracy of the heavy medium shallow tank washing process are improved, the system adapts to changes in coal quality and fluctuations in operating conditions at industrial sites, guides actual production control, and effectively improves the intelligence level of coal preparation plants.

[0007] The technical solution to achieve the purpose of the present invention is:

[0008] An intelligent control system for a heavy medium shallow tank, comprising a driving device, a monitoring device and a regulating device, wherein:

[0009] A driving device is installed at one end of the trough body, and the driving device is used to drive the scraper to move counterclockwise along the top surface-side surface-bottom surface-side periphery of the trough body; a number of crossbeams for fixing pulleys are arranged above the trough body, and the pulleys are used to limit the movement of the scraper above the liquid surface of the trough body; the scraper is used to discharge the sediment in the trough body from the discharge port, so that the sorted materials enter from the side above the trough body, and the floating materials are affected by the horizontal flow and flow out from the other end above the trough body together with the suspension in the trough; the monitoring device includes a visual analysis device and a fluid flow rate monitoring device, the visual analysis device is installed on the upper side of the trough body, and the fluid flow rate monitoring device is installed in an array on the overflow port of the trough body, the visual analysis device and the fluid flow rate monitoring device are used together to monitor the fluid operation effect in the trough body, and control the regulating device accordingly; the regulating device is installed on the fluid operation pipeline of the trough body, and the regulating device is used to change the fluid state according to the fluid operation effect.

[0010] Furthermore, in the intelligent control system of the heavy medium shallow tank of the present invention, the driving device includes a left motor and a right motor, and the left motor and the right motor are respectively installed on the front side and the rear side of one end of the tank body.

[0011] Furthermore, in the intelligent control system of the heavy medium shallow tank of the present invention, the regulating device includes a horizontal flow electromagnetic control valve and an upward flow electromagnetic control valve, wherein the horizontal flow electromagnetic control valve is installed on the horizontal flow pipeline of the tank body, and the upward flow electromagnetic control valve is installed on the upward flow pipeline of the tank body, both of which are used to regulate and change the fluid state in the tank body.

[0012] Furthermore, in the intelligent control system for the heavy medium shallow tank of the present invention, the horizontal flow electromagnetic control valve and the upward flow electromagnetic control valve are both high-precision electromagnetic valves.

[0013] Furthermore, in the intelligent control system of the heavy medium shallow tank of the present invention, the fluid flow rate monitoring device includes a plurality of flow rate sensors, and the flow rate sensors are evenly distributed on the overflow weir of the tank body to obtain the fluid velocity in the tank body.

[0014] A heavy medium shallow tank intelligent control method, comprising:

[0015] S1. Based on AI visual analysis technology, use a camera or sensor to collect and identify images of heavy-medium shallow trough sorting, and pre-process the collected images, including denoising, contrast enhancement, brightness adjustment, etc., and then judge whether there are abnormal phenomena in the heavy-medium shallow trough sorting machine based on the images, and determine the degree and location of the abnormal phenomena, which include blooming and vortex phenomena;

[0016] S2. Extracting features related to the abnormal phenomenon from the preprocessed image, wherein the features include color, texture, shape, motion, etc.;

[0017] S3, training the extracted features based on machine learning algorithms to establish sorting, identification and control models;

[0018] S4. Collect images of heavy medium shallow tank sorting in real time, use the sorting recognition and control model to identify the images, obtain whether there are abnormal phenomena and their degree, location and impact range, and adjust the opening of the horizontal flow high-precision solenoid valve and the upward flow high-precision solenoid valve when abnormal phenomena exist.

[0019] Furthermore, in the intelligent control method for the heavy medium shallow tank of the present invention, the camera or sensor in S1 collects images of the heavy medium shallow tank sorting from multiple angles and positions.

[0020] Furthermore, in the intelligent control method for the heavy medium shallow tank of the present invention, image processing and machine learning algorithms are used in S1 to identify abnormal phenomena in the heavy medium shallow tank separator.

[0021] Furthermore, in the intelligent control method for the heavy medium shallow tank of the present invention, in S4, the opening of the high-precision solenoid valves of the horizontal flow and the upward flow are controlled to change the distribution of the fluid force field in the heavy medium shallow tank and the horizontal flow and the upward flow of the medium, and the fluid force field in the shallow tank is utilized to realize the orthogonal effects of the horizontal flow and the upward flow on the sedimentation of the material according to the sedimentation changes of materials of different densities and particle sizes in the complex medium flow, thereby realizing the normal sorting of the heavy medium shallow tank.

[0022] Compared with the prior art, the present invention adopts the above technical solution and has the following technical effects:

[0023] 1. The intelligent control system and control method of the heavy medium shallow tank of the present invention are helpful to guide the equipment adjustment of the heavy medium shallow tank in accordance with the actual situation, and truly improve the sorting level of the equipment.

[0024] 2. The intelligent control system and control method of the heavy medium shallow tank of the present invention use cameras or sensors and other equipment based on AI visual analysis technology to monitor abnormal conditions such as blooming and vortices in the tank in real time. By processing and analyzing images or data, it is determined whether there are abnormal phenomena such as blooming and vortices and determine their extent and location.

[0025] 3. The intelligent control system and control method of the heavy medium shallow tank of the present invention introduces the sedimentation changes of materials with different densities and particle sizes in complex medium flows, obtains the orthogonal effects of horizontal flow and upward flow on material sedimentation, can better meet the needs of actual production, and guide production control.

[0026] 4. The intelligent control system and control method of the heavy medium shallow tank of the present invention can use video to monitor the fluid state on the surface of the tank body, control the flow rate by linking the horizontal flow and the upward flow valve of the medium, and realize the refined control of the heavy medium shallow tank sorting system. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are used to provide a further understanding of the present invention and are used together with the description to explain the embodiments of the present invention, but do not constitute a limitation of the present invention. In the accompanying drawings:

[0028] Figure 1 The front view of the intelligent control system of the heavy medium shallow tank of the present invention is shown.

[0029] Figure 2 A top view of the heavy medium shallow tank intelligent control system of the present invention is shown.

[0030] Figure 3 The left side view of the intelligent control system of the heavy medium shallow tank of the present invention is shown.

[0031] Figure 4 A flow chart of the intelligent control method of the heavy medium shallow tank of the present invention is shown.

[0032] Meaning of the accompanying symbols: 1. trough body, 2. left motor, 3. right motor, 4. discharge port, 5. scraper, 6. beam, 7. pulley, 8. visual analysis equipment, 9. fluid flow rate monitoring device, 10. horizontal flow electromagnetic control valve, 11. upflow electromagnetic control valve. DETAILED DESCRIPTION

[0033] In order to further understand the present invention, preferred embodiments of the present invention are described below in conjunction with examples. However, it should be understood that these descriptions are only for further illustrating the features and advantages of the present invention, rather than limiting the claims of the present invention.

[0034] The description in this section is only for typical embodiments, and the present invention is not limited to the scope of the embodiments. The combination of different embodiments, the mutual replacement of some technical features in different embodiments, and the mutual replacement of the same or similar prior art means with some technical features in the embodiments are also within the scope of the description and protection of the present invention.

[0035] According to one aspect of the present invention, a method for intelligently controlling a heavy medium shallow tank comprises the following steps:

[0036] Step 1. Establish AI visual analysis technology and use cameras or sensors to monitor the flooding and vortexes in the tank in real time. By processing and analyzing images or data, it is possible to determine whether there is flooding and vortexes, and to determine their extent and location. With AI visual analysis technology, image processing and machine learning algorithms can be used to identify flooding and vortexes in shallow tank machines.

[0037] Flooding: Flooding refers to the appearance of a large amount of foam and water splashes in the water tank of the shallow tank machine. Flooding may be caused by the following reasons: 1) The water level in the water tank is too high or too low, resulting in unstable water flow speed; 2) A large amount of air enters the water tank, causing the water and air in the water tank to form foam; 3) There is a malfunction in the stirring device or water spraying device in the water tank, resulting in unstable water flow.

[0038] Vortex phenomenon: Vortex refers to the vortex-shaped water flow formed in the water tank of the shallow tank machine. The vortex phenomenon may be caused by the following reasons: 1) The water flow speed in the water tank is too fast, causing the water flow to rotate; 2) There are obstacles in the water tank that hinder the flow of water, causing the water flow to vortex; 3) The stirring device or water spray device in the water tank is not designed reasonably, resulting in unstable water flow.

[0039] Step 2: Data collection.

[0040] Use cameras or sensors to collect images or data in the water tank in real time. Images from multiple angles and positions can be collected to obtain more comprehensive information. Flow rate sensors are evenly distributed on the overflow weir to determine fluid velocity, monitor the stability of the water layer, and identify abnormal flow rates in the water layer.

[0041] Step 3: Image preprocessing.

[0042] The collected images are preprocessed, including denoising, contrast enhancement, brightness adjustment and other operations, to improve image quality and reduce interference.

[0043] Step 4: Feature extraction.

[0044] Extract features related to blooms and vortices from the preprocessed image. These features can include information on color, texture, shape, motion, etc.

[0045] Step 5: Train the model.

[0046] Use machine learning algorithms, such as convolutional neural networks (CNN) or support vector machines (SVM), to train the extracted features. Prepare a set of labeled image data, which contains image samples of blooming and vortex phenomena, so that abnormal conditions such as blooming and vortex can be identified. Use the trained model to identify the images collected in real time. Based on the output of the model, it can be determined whether there is a blooming and vortex phenomenon, and its degree, location, and scope of influence can be further analyzed.

[0047] Step 6: Model verification and optimization.

[0048] Use the validation set to validate the trained model and optimize it based on the validation results. The accuracy and robustness of the model can be improved by adjusting the model parameters, increasing the training samples, etc.

[0049] Step 7. Adjust controls.

[0050] Through the above control process, AI visual analysis technology can realize the automatic identification and monitoring of the flooding and vortex phenomena in the shallow trough machine. Once the flooding and vortex phenomena are identified, the control system can be used to adjust the horizontal liquid flow and the rising liquid flow to control the flow of water, thereby changing the fluid force field in the trough to control the sorting effect and avoid accidents. In the process of heavy medium shallow trough sorting, if the horizontal liquid flow and the rising liquid flow are not adjusted properly, the liquid flow will fluctuate. If the horizontal liquid flow is too large, the material stratification is not sufficient, which affects the sorting effect. If the horizontal liquid flow is too small, the material cannot move forward normally after the shallow trough is added, and it may even vortex in place. It is possible that the material will accumulate and crush the shallow trough, causing an accident. If the rising liquid flow is too large, it will cause flooding in the trough and affect the normal flow of the material, affect the looseness of the material in the shallow trough, and cause the medium density in the shallow trough to be uneven and unstable, thereby affecting the material sorting effect. Through the distribution of fluid force field in the heavy medium shallow trough, the horizontal flow and upward flow of the medium in the shallow trough are changed. By utilizing the fluid force field in the shallow trough, according to the sedimentation changes of materials with different densities and particle sizes in the complex medium flow, the orthogonal effects of horizontal flow and upward flow on material sedimentation are realized, thereby realizing the normal sorting of the heavy medium shallow trough.

[0051] Step 8: On-site debugging to verify the effect.

[0052] The application of AI visual analysis technology can realize the automatic monitoring and control of shallow trough machines and improve the stability and efficiency of the washing process. This technology can improve the stability and efficiency of the washing process, reduce manual intervention, and provide data support for optimizing the design and operating parameters of shallow trough machines. At the same time, through the collection and analysis of a large amount of data, the design and operating parameters of shallow trough machines can also be optimized, further improving the washing effect and reducing energy consumption, and ultimately achieving the goal of heavy medium coal preparation that meets production control requirements.

[0053] The description and application of the present invention here are illustrative, and it is not intended to limit the scope of the present invention to the above-mentioned embodiments. The effects or advantages involved in the specification may not be reflected in the actual experimental examples due to the uncertainty of specific condition parameters or other factors, and the effects or advantages are not used to limit the scope of the invention. The deformation and change of the embodiments disclosed here are possible, and the replacement of the embodiments and the various equivalent parts are well known to those of ordinary skill in the art. It should be clear to those skilled in the art that the present invention can be implemented in other forms, structures, arrangements, proportions, and with other components, materials and parts without departing from the spirit or essential features of the present invention. Other deformations and changes can be made to the embodiments disclosed here without departing from the scope and spirit of the present invention.

Claims

1. An intelligent control system for a heavy medium shallow tank, characterized in that: It includes a driving device, a monitoring device and a regulating device, wherein: A driving device is installed at one end of the tank body (1), and the driving device is used to drive the scraper (5) to move counterclockwise along the top surface-side surface-bottom surface-side periphery of the tank body (1); a plurality of crossbeams (6) for fixing pulleys (7) are arranged above the tank body (1), and the pulleys (7) are used to limit the movement of the scraper (5) above the liquid surface of the tank body (1); the scraper (5) is used to discharge the sediment in the tank body (1) from the discharge port (4), so that the sorted material enters from one side above the tank body (1), and the floating material is affected by the horizontal flow and flows out from the other end above the tank body (1) together with the suspension in the tank; The monitoring device comprises a visual analysis device (8) and a fluid flow rate monitoring device (9), wherein the visual analysis device (8) is installed on one side above the tank body (1), and the fluid flow rate monitoring device (9) is installed in an array on the overflow port of the tank body (1), and the visual analysis device (8) and the fluid flow rate monitoring device (9) are used together to monitor the running effect of the fluid in the tank body (1), and control the regulating device accordingly; The regulating device is installed on the fluid running pipeline of the tank body (1), and the regulating device is used to change the state of the fluid according to the running effect of the fluid.

2. The intelligent control system for heavy medium shallow tank according to claim 1 is characterized in that: The driving device comprises a left motor (2) and a right motor (3), and the left motor (2) and the right motor (3) are respectively mounted on the front side and the rear side of one end of the tank body (1).

3. The intelligent control system for heavy medium shallow tank according to claim 1 is characterized in that: The regulating device comprises a horizontal flow electromagnetic control valve (10) and an upward flow electromagnetic control valve (11), wherein the horizontal flow electromagnetic control valve (10) is installed on the horizontal flow pipeline of the tank body (1), and the upward flow electromagnetic control valve (11) is installed on the upward flow pipeline of the tank body (1), and both are used to regulate and change the state of the fluid in the tank body (1).

4. The intelligent control system for heavy medium shallow tank according to claim 3 is characterized in that: The horizontal flow electromagnetic control valve (10) and the upward flow electromagnetic control valve (11) are both high-precision electromagnetic valves.

5. The intelligent control system for heavy medium shallow tank according to claim 1 is characterized in that: The fluid flow rate monitoring device (9) comprises a plurality of flow rate sensors, which are evenly distributed on the overflow weir of the tank body (1) and are used to obtain the fluid velocity in the tank body (1).

6. A method for intelligent control of a heavy medium shallow tank, characterized in that: include: S1. Based on AI visual analysis technology, use a camera or sensor to collect and identify images of heavy-medium shallow trough sorting, and pre-process the collected images, including denoising, contrast enhancement, brightness adjustment, etc., and then judge whether there are abnormal phenomena in the heavy-medium shallow trough sorting machine based on the images, and determine the degree and location of the abnormal phenomena, which include blooming and vortex phenomena; S2. Extracting features related to the abnormal phenomenon from the preprocessed image, wherein the features include color, texture, shape, motion, etc.; S3, training the extracted features based on machine learning algorithms to establish sorting, identification and control models; S4. Collect images of heavy medium shallow tank sorting in real time, use the sorting recognition and control model to identify the images, obtain whether there are abnormal phenomena and their degree, location and impact range, and adjust the opening of the horizontal flow high-precision solenoid valve and the upward flow high-precision solenoid valve when abnormal phenomena exist.

7. The intelligent control method for a heavy medium shallow tank according to claim 6, characterized in that: The camera or sensor in S1 collects images of the heavy medium shallow trough sorting from multiple angles and positions.

8. The intelligent control method for a heavy medium shallow tank according to claim 6, characterized in that: Image processing and machine learning algorithms are used in S1 to identify anomalies in a heavy medium shallow trough separator.

9. The intelligent control method for a heavy medium shallow tank according to claim 6, characterized in that: In S4, the opening of the high-precision electromagnetic valves for horizontal flow and upward flow is controlled to change the distribution of the fluid force field in the heavy medium shallow tank and the horizontal flow and upward flow of the medium. The fluid force field in the shallow tank is used to achieve the orthogonal effects of the horizontal flow and upward flow on the material sedimentation according to the sedimentation changes of materials with different densities and particle sizes in the complex medium flow, thereby achieving normal sorting in the heavy medium shallow tank.

Citation Information

Patent Citations

  • Material bed and bed pressure cooperative control based fluidized sorting equipment

    CN110433951A

  • System for intelligently adjusting dense medium density of dense medium shallow slot based on machine vision

    CN113908970A

  • Dense medium shallow slot sorting machine and feeding end auxiliary sorting method thereof

    CN118287250A

  • Intelligent shallow slot dense medium gangue pre-discharging system

    CN217491209U

  • Dry-method dense medium fluidized bed-based separator intelligent control method

    WO2021212641A1