CN212664239U - Coal dressing system based on artificial intelligence image recognition - Google Patents

Abstract

The utility model discloses a coal dressing system based on artificial intelligence image recognition, is provided with a chute with the lower part of the cross section close to a V shape, and coal falls on the initial section of the chute from the top, slides to the tail end of the chute and is automatically arranged in a line; in the process that the coal material moves along the sliding groove, firstly, a spray gun is used for purging coal ash and coal slime on the coal material to enable the coal ash and the coal slime to be exposed out of the surface of an internal solid, then, before the coal material reaches the tail end, a camera device shoots in real time and sends shot images to a control module, the control module recognizes the coal gangue or coal blocks in real time through an artificial intelligence image recognition technology, and controls a gangue removing mechanism to act to remove the coal gangue from the coal blocks. The utility model has high sorting accuracy of the waste rock, simple equipment, wide processing grain size and large processing capacity, and can replace most of manpower; and the device is simple and easy to maintain, is convenient to deploy underground, screens out the gangue and leaves the gangue underground before the coal material is lifted out of the well, and can effectively reduce the output of the gangue.

Description

Coal dressing system based on artificial intelligence image recognition

Technical Field

The utility model belongs to the technical field of coal mining, concretely relates to coal dressing system based on artificial intelligence image recognition.

Background

For a long time, the mining amount of Chinese coal resources is high and reaches billions of tons every year, and more than 5000 coal mines in large and small coal mines exist in China. In recent years, the degree of automation of coal mining mechanization is continuously improved, but the separation of coal gangue is always difficult. The existence of the waste rock increases the ash content in the coal material on one hand, reduces the quality of the raw coal, and on the other hand, in each link of subsequent production and transportation, the damage such as excessive abrasion, even chain clamping shutdown and the like can be brought to the operation of equipment. Therefore, after the raw coal is lifted into the well, the first step is to separate and pick up gangue in the coal material and retain the coal, namely coal dressing.

The traditional main coal preparation process is based on the difference of basic physical properties of coal blocks and gangue, such as different densities, different surface hydrophilic and hydrophobic properties and the like, and can be basically divided into a water washing method and a dry cleaning method. The washing process is a method for separating coal blocks and gangue by using a large amount of water through equipment such as a flotation machine, a jigging machine, a dense medium cyclone and the like according to different performances of the coal blocks and the gangue in water. However, many coal resources are stored in arid water-deficient areas, and water shortage has become a limiting factor for local coal resource development and processing. In addition, young coal is easily slimed when meeting water, and in a severe cold area, washing with water also causes various problems such as freezing of products. The dry cleaning process is a technology for separating coal blocks and gangue according to different specific gravities of the coal blocks and the gangue by manufacturing strong air convection, namely a winnowing process, and comprises modes of crushing separation, air medium cyclone, composite dry separation and the like. However, the particles which can be processed by the method are extremely narrow, and only materials which are smaller than 80 mm can be processed; the separation precision is very low, the gangue discharge rate of air separation is generally 80-90%, the coal carrying rate in the gangue is more than 5%, and the coal carrying rate is generally 6-8%; the influence of water is large, when the water content of raw coal is large, the air holes of the bed surface can be blocked, normal air supply is damaged, the separation effect is deteriorated, or even the separation cannot be carried out, so that the external water is generally required to be less than 7%; and when the content of the gangue is increased, the probability of gangue mixing is correspondingly increased. The power consumption of the winnowing equipment is very high, and the installed power of a winnowing machine for processing 240 tons of raw coal per hour is 650 kilowatts, namely, the winnowing machine needs to consume 2.5-3 degrees of electricity for carrying out the separation on each ton of raw coal on average. Moreover, because the degree of automation is low, the experience and responsibility of the operator have a great influence on the sorting effect.

With the development of artificial intelligence technology in recent years, some artificial intelligence coal separation technologies are developed, for example, X-ray transmission imaging is adopted to distinguish coal blocks from gangue. This technique is not only costly, but also has major safety issues and is relatively complex.

Accordingly, the prior art is subject to further improvements and enhancements.

Disclosure of Invention

In view of the above-mentioned defect of prior art, the utility model aims to provide a coal dressing system based on artificial intelligence image recognition to solve prior art's coal dressing technology, need artifical discernment and pick up, and the technical defect of extravagant resource and energy, and simpler than other intelligent coal dressing equipment's structure, easy to maintain easily deploys in the pit.

The utility model discloses a coal dressing system based on artificial intelligence image recognition, include: the cross section of the downstream of the sliding chute along the sliding direction is in a shape close to a V; the coal falls on the initial section of the chute and slides along the chute to the tail end of the chute; each sliding chute is provided with at least one spray gun which is arranged above each sliding chute and used for spraying and washing the coal; the system comprises at least one camera device, a control module and a display module, wherein the camera device is right opposite to and used for shooting the moving coal in real time, and transmitting a shot image to the control module, and the control module is used for identifying gangue and coal blocks through an artificial intelligent visual image identification technology of deep learning; the gangue removing mechanism acts after receiving the identification result sent by the control module and removes the identified gangue; the identification result comprises an identified gangue position; the approximate V-shaped part is in a shape that the middle is sunken and the two side walls are upwards unfolded, and comprises a V-shaped part or a U-shaped part which is placed right at the right position or an arc with an upward opening.

Preferably, the sliding curve of the chute is a straight line inclined downwards or a steepest descent line, and the steepest descent line is suitable for receiving the coal falling vertically at the initial section.

Preferably, the initial section of the sliding curve is in a downward-curved parabolic shape for receiving coal thrown off from the conveyor belt. The specific curve is determined by the speed and fall of the conveyor belt according to the parabolic motion curve.

Preferably, the gangue removing mechanism comprises a striking rod or a hammer arranged below the tail end, and the striking rod or the hammer acts under the control of the control module to strike the identified gangue and change the falling route of the gangue.

Or preferably, the gangue removing mechanism comprises at least one movable manipulator arranged above the chute, and the manipulator is controlled by the control module and can move to the chute to grab gangue.

Preferably, the coal feeder further comprises a vibration module, wherein the vibration module is used for vibrating the chute to help the coal material slide to the tail end.

Preferably, the system further comprises a chute state monitoring and identifying system, wherein the chute state monitoring and identifying system shoots an image of the chute and transmits the image to the control module; the control module identifies the state of the chute through an artificial intelligence visual image identification technology, including whether the chute is blocked, whether the coal supply is interrupted, whether the chute has too large coal, and whether the chute is gangue which needs to be thrown away.

More preferably, the device further comprises a dredging mechanism of the chute, when the chute is monitored to be blocked, the dredging mechanism is used for dredging the chute, and an alarm is given when the chute cannot be dredged.

Further preferably, the dredging mechanism further comprises an oversize coal processing device for processing the oversize coal when the oversize coal cannot fall into the chute, including picking or crushing.

Preferably, the control module comprises an image illumination enhancement algorithm and is used for enhancing the incoming digital illumination of the shot image, helping the artificial intelligence visual analysis to improve the identification accuracy and being beneficial to improving the accuracy of the artificial intelligence image identification under the dim condition, particularly under the underground working condition.

Preferably, the control module comprises an image defogging algorithm and is used for digitally processing the shot image, defogging, haze removal and dust removal, so that the accuracy of artificial intelligence image recognition is improved in the high environment of air dust, particularly under the underground working condition.

Preferably, the coal screening device further comprises a vibrating coal screen for screening out coal materials smaller than a set size before entering the chute and not entering the chute.

In a better embodiment, the initial section of the chute is provided with a group of perforated screens with the aperture smaller than the set size for screening out the coal material smaller than the set size.

Preferably, the fluid ejected by the spray gun is high-pressure air.

More preferably, the high-pressure air is also added with water mist for reducing dust in the air and enabling the surface of the coal material to be moderately wet so as to increase the visual identification degree.

Preferably, the dust collector also comprises a ventilation system used for reducing the concentration of dust in the air and increasing the definition of images shot by the camera device.

Preferably, the spray gun is opposite to the front and the back of the injection point of the chute, and the upper part of the chute is closed or semi-closed for preventing coal from splashing.

Preferably, the lens of the camera device is provided with a cleaning device for cleaning the lens to increase the definition of the image taken by the camera device.

More preferably, the cleaning device is a blade with a blade portion attached to the lens and is matched with a cleaning liquid spray head.

More preferably, the chutes are of different sizes and sizes respectively for receiving coal in different size ranges.

Further preferably, a plurality of the sliding chutes are arranged side by side downwards, a coal discharging plate crosses each of the initial sections from above the sliding chutes, and the side surfaces of the coal discharging plate in the width direction incline to each of the initial sections; the coal material slides to each initial section from the side surface in the process of sliding forward along the coal outlet plate, slides to the tail end along each sliding groove and then falls; at least one striking rod or hammer is arranged below each end.

Still further preferably, the coal outlet plate is provided with a conveyor belt for conveying the coal across the respective chutes, the coal sliding sideways to the respective starting sections during the conveying.

In a better embodiment, a plurality of sliding grooves are arranged side by side to form a lower sliding surface, and the coal discharging plate is arranged above the initial section of the lower sliding surface; and at least one manipulator is further arranged and can move to each position of the lower sliding surface to pick up the gangue.

The utility model discloses a coal dressing system's operating method based on artificial intelligence image recognition, including the step:

a. the coal material slides downwards in the chute;

b. the spray gun sprays and flushes the coal material;

c. the camera device shoots the washed coal material in real time;

d. the camera device transmits the shot image to the control module in real time;

e. after identifying the gangue or the coal blocks, the control module sends an identification result to a gangue removing mechanism;

f. and the gangue removing mechanism removes the gangue from the coal blocks according to the action of the recognition result.

The utility model discloses a coal dressing system based on artificial intelligence image recognition is provided with at least one spout, the spout is close to the V font along the transversal surface of direction of sliding, and the coal charge falls in the initial section of spout from the top to slide to the end of spout, and the automation is arranged in a line, does benefit to the work efficiency and the accuracy of each process such as follow-up shooting, discernment, letter sorting; in the process that the coal material moves along the sliding chute, firstly, a spray gun is used for washing coal ash and coal slime on the sprayed coal material to expose the surface of the internal solid, so that the accuracy of artificial intelligent visual identification is improved; and before reaching the tail end, shooting in real time by the camera device and sending the shot image to the control module, identifying the current coal material as gangue or coal blocks in real time by the control module through an artificial intelligent image identification technology, controlling the action of a gangue removing mechanism, and removing the gangue from the coal blocks. The utility model has high sorting accuracy for the gangue, simple equipment, wide processing grain size and large processing capacity, and can replace most of manpower; the device is simple and easy to maintain, is convenient to deploy underground, screens out the gangue and leaves the gangue underground before the coal material is lifted out of the well, and can effectively reduce the output of the gangue.

The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings, so as to fully understand the objects, the features and the effects of the present invention.

Drawings

FIG. 1 is a structural diagram of a single channel of a coal preparation system based on artificial intelligence image recognition of the present invention;

FIG. 2 is a structural diagram of a side-by-side channel of the coal preparation system based on artificial intelligence image recognition of the present invention;

FIG. 3 is a structural diagram of a lower sliding surface of the coal preparation system based on artificial intelligence image recognition of the present invention;

FIG. 4 is a block diagram of a control module of the coal preparation system based on artificial intelligence image recognition according to the present invention;

fig. 5 is a flow chart of the working method of the coal preparation system based on artificial intelligence image recognition of the present invention.

In the figure, 105, a coal inlet, 106, a coal outlet plate, 110, a starting section, 111, a chute, 115, a porous screen, 120, a tail end, 200, gangue, 250, a coal block, 300, a camera, 400, a spray gun, 500, a control module, 600, a mechanical arm, 650, a striking rod or a hammer.

Detailed Description

The utility model provides a coal dressing system based on artificial intelligence image recognition, for making the utility model discloses a purpose, technical scheme and effect are clearer, make clear and definite, and it is right that the following reference drawing does further detailed description. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The utility model provides a pair of coal dressing system based on artificial intelligence image recognition, the basic structure is as shown in figure 1, include: at least one chute 111 for transporting the coal, the downstream portion of said chute 111, in a cross section perpendicular to the sliding direction, being approximately V-shaped, i.e. having a depressed central bottom, and two side walls extending upwards, the upper portions of the two side walls being separated from each other, and the bottom portions of the two side walls merging with each other, forming a central depression in the bottom, i.e. in a cross section perpendicular to the sliding direction, being configured as a cross section close to V-shape, such as a right-side V-shape or U-shape or an upwardly open circular arc, or similar other shapes with intermediate depression, the two side walls extending upwards. And preferably, the coal material is V-shaped, so that the smaller coal material falls on the lower layer, and the larger coal material is clamped on the upper layer, so that the coal material on the coal material can more easily form a single-row advancing.

The top of the chute 111 may be closed or semi-closed. The chute 111 may use the gravity component to guide the coal material thereon to slide down, or make the coal material slide down by means of an external stress. Specifically, the chute 111 includes a starting section 110 with a higher horizontal position and an end 120 with a lower horizontal position, and the coal material slides down from the starting section 110 to the end 120 under the action of gravity on the chute 111. The shape of the sliding groove 111 along the sliding direction, i.e. the shape along the length direction, is preferably the steepest descending line or straight line between the starting section 110 and the end section 120. And in a preferred embodiment, the angle of inclination of the chute 111 is adjustable, but is typically adjusted and fixed during installation. When the coal slide device is installed, the inclined angle can be adjusted, and the downward sliding speed of the coal on the coal slide device can be adjusted. Specifically, when the inclination angle is too small, the throughput of the coal decreases, and the sliding may even stop; when the gradient is too large, the coal material rolling phenomenon can occur. Both of these cases should be avoided.

The coal material, including the coal block 250 and the gangue 200, is just mined out especially underground, and is only subjected to crushing treatment at most. The technical scheme of the utility model for the coal charge is in on the spout 111, to the terminal 120 in-process that slides, gangue 200 wherein just is discerned and is followed by autosegregation from coal cinder 250.

In one embodiment, as shown in FIG. 1, the initial section 110 of the chute 111 is aligned with a coal inlet 105 from below, and coal is fed into the initial section 110 from the coal inlet 105. Or in another embodiment, the starting section 110 is provided with a parabolic shape for receiving the coal material conveyed by a conveyor belt, and the parabolic shape can match with the original moving curve of the coal material when the coal material is thrown out by the conveyor belt, so that the abrasion of the coal material on the surface of the starting section 110 can be reduced. The coal block falling on the sliding chute 111 is then driven by gravity or other external force to move on the sliding chute 111 toward the other end, i.e. the end 120, i.e. the moving direction shown by the arrow a in fig. 1. Before reaching the tip 120, the gangue 200 and coal 250 in the coal charge will be identified and subsequently separated. The recognition is mainly completed through an artificial intelligence real-time image recognition technology of deep learning.

Alternatively, in a preferred embodiment, to help the coal material move from the starting section 110 to the ending section 120, a vibration module may be further provided, and the vibration module vibrates the chute 111 and the coal material thereon to further reduce the friction force of the coal material sliding.

In operation, when coal falls on the chute 111, because the downstream portion of the chute 111 has a cross section close to a V shape, the coal naturally converges at the bottom of the chute 111 as a single row, i.e. each solid coal block advances in a single row, as shown in fig. 1, in the chute 111, so that only the maximum solid coal block, i.e. the gangue 200 or the coal block 250, simultaneously exists in a cross section of the downstream portion of the chute 111, which is conveniently photographed by the camera 300 disposed above the end 120 of the chute 111, the camera 300 then transmits the photographed image to a control mechanism 500, and the control mechanism 500 judges the coal located on the end 120 by an artificial intelligence visual image recognition technology of deep learning, judging whether the gangue 200 is the coal block 250 or not, and controlling the corresponding gangue removing mechanism to act according to the judgment result to remove the gangue 200 from the coal block 250.

Considering that the surface of the coal material may be contaminated with substances that hinder the identification, such as coal ash and coal slurry, and affect the accuracy of the identification of the coal material, or even make an erroneous judgment, and cause unnecessary economic loss, a spray gun 400 is disposed above the chute 111, facing the coal material, and the spray gun 400 sprays fluid, preferably compressed air, at a certain pressure to flush the coal material, i.e., in a spraying direction indicated by an arrow b in fig. 1. The lance 400 is disposed above the chute 111 and closer to the starter section 110. And the shooting point of the camera 300 is located downstream of the spray point of the spray gun 400 on the chute 111. That is, each coal briquette is sprayed by the spray gun 400 and then photographed by the camera 300.

The spraying direction of the spray gun 400 is preferably perpendicular to the sliding chute 111, and the upper part of the sliding chute, which is opposite to the front and rear positions of the spraying point of the sliding chute 111, of the spray gun 400 is closed or semi-closed so as to avoid blowing off coal. More preferably, a plurality of the lances 400 may be used simultaneously for injection and may be re-injected when the coal is tumbled in a rolling manner.

Preferably, a certain amount of water mist is added to the compressed air ejected from the spray gun 400. Thereby reach the dust fall effect, can make the image shoot more clearly. The water mist has the other function of slightly wetting the surface of the coal material, which can also increase the visual discrimination of the coal material, so that the accuracy of image recognition can be improved.

Specifically, a camera 300 is arranged above the chute 111 to shoot coal images in real time, a shooting point of the camera 300 falls in the chute 111 and is conveyed in a single direction, that is, in a shooting direction indicated by an arrow c in fig. 1, the shot images are sent to a control module 500 along an arrow d in fig. 1, the control module 500 identifies the coal in the coal images one by one through an artificial intelligent visual image identification technology of deep learning, and at least judges in real time whether the coal is located at the tail end 120, that is, the coal at the shooting point of the camera 300 on the conveyor belt 100 is the gangue 200 or the coal 250.

The image capturing device 300 may be provided for each sliding groove 111; alternatively, one image pickup device 300 is used to simultaneously pick up the coal materials on the ends of the plurality of chutes 111, and a distinguishing module is added to the software program of the control mechanism 500 to identify and judge the coal materials on the ends on the picked-up image one by one.

In a better implementation, considering that the coal material may block the chute 111 due to being too large or too wet, the camera module and the control module can be used to judge the traveling speed of the coal material, and whether the interruption of the coal material occurs or not, if the interruption is found, the dredging device can be controlled to dredge the chute 111, and an acoustic/optical alarm can be given when needed.

Alternatively, a second camera may be added to the initial segment 110 for detecting the status of the initial segment 110, including the initial segment 110 being blocked or the coal supply being interrupted or the coal being too large. When the coal supply is detected to be abnormal, an acoustic/optical prompt is sent out, and a manager is called to perform manual intervention, such as picking up excessive gangue; or sending a command to operate an automatic blockage removing mechanism to pick up large coal blocks and dredge the chute 111. The large coal material picked up may be sent to a coal separator with a higher specification, or the large coal material may be identified as gangue on site and directly thrown away.

Because the coal material smaller than the set size is easy to generate dust during operation, which affects the subsequent shooting and identification processing, in a preferred embodiment, the artificial intelligent coal preparation system further comprises a coal material screening system, and the undersized coal material is screened before entering the chute 111. For example, a vibrating coal screen is arranged to screen out the coal with too small volume. Or, to increase the integration level of the device, the coal screening system may be further integrated on the chute 111, specifically: a set of perforated screens 115 with a smaller diameter than a predetermined size are arranged on the initial section 110, and when the coal slides through the area where the perforated screens 115 are arranged, the undersized coal falls out of the screen holes. At this time, if a vibration module for vibrating the sliding chute 111 is further provided, the screening effect is better.

After the control module identifies the current coal on the end 120, the identification result is sent to a gangue dumping mechanism, i.e., the direction indicated by the arrow e in fig. 1.

The specific implementation manner of the gangue dumping mechanism can be that as shown in fig. 1, at least one manipulator 600 is arranged above the chute 111 and before the tail end 120, the manipulator 600 is controlled by the control module 500, moves to the position above each identified gangue 200, quickly descends into the chute 111, catches and extracts each gangue 200, then ascends to leave, and discards the gangue 200 elsewhere. The specific construction and control of the manipulator 600 is conventional in the art and is not described herein.

In a second embodiment, the reject mechanism may also be provided as a hammer bar or hammer 650 below the tip 120. When the control module 500 identifies the gangue 200 on the tip 120, the striking rod or hammer 650 is driven to strike or kick off the gangue 200 dropping from the tip 120, changing its dropping course and dropping point, and thereby separating the gangue 200 from the coal block 250.

In view of the accuracy of the time-based control of the reject mechanism, the striking rod or hammer 650 should be located as close as possible to the tip 120, and the control module sends the identification to the striking rod or hammer 650 each time the gangue 200 on the tip 120 is identified, to minimize possible coal movement due to time delays that may cause the identified and struck coal to be not the same.

In a preferred embodiment, a ventilation system is further included to reduce the concentration of powder in the air in the path of the image captured by the camera 300. Meanwhile, considering that soot or other dust in the air may adhere to the lens of the camera device 300 and directly affect the shooting clarity, in a preferred embodiment, a lens cleaning device is further disposed at the lens of the camera device 300, and the cleaning device may be implemented by referring to a common automobile wiper principle, for example, the cleaning device is a wiper blade whose blade portion is attached to the lens and is matched with a cleaning liquid nozzle.

The utility model provides an image recognition algorithm, for the general image recognition algorithm of prior art can.

In view of the need to process coal in large quantities simultaneously, in a preferred embodiment, as shown in fig. 2, a plurality of chutes 111 are positioned side by side with each of the start sections 110 aligned in unison, and above the start sections 110, a coal outlet plate 106 is provided that spans all of the start sections 110, such as a conveyor belt that transports the coal across each chute 111. The side surfaces of the coal outlet plate 106 along the width direction are inclined to each initial section 110; therefore, the coal material will dispersedly slide down to each initial segment 110 from the side surface in the process of sliding along the coal outlet plate 106, and slide down to the tail end 120 along each sliding groove 111 and then fall down; and at least one striking rod or hammer 650 is provided under each end 120. At this time, a plurality of image capturing devices 300 may be provided to cover part of the sliding chute 111, or one image capturing device 300 may be provided to cover all the sliding chutes 111 from below the initial segment 110, capture the coal sliding thereon, and send the captured coal to the control module 500 for recognition and send the recognition result to the striking rod or hammer 650, so as to control the starting action to strike and fly the gangue 200.

Alternatively, as shown in fig. 3, a plurality of the sliding grooves 111 arranged side by side may be combined and simplified into an inclined lower sliding surface. Similarly, a coal plate 106 is arranged above each initial section 110, the coal material slides down along the sliding surface, is shot by the camera device 300 in the sliding process, sends shot images to the control module 500, identifies the gangue 200 therein, and controls a gangue removal mechanism to remove the gangue 200. At this time, the gangue dumping mechanism is preferably a manipulator 600, and the manipulator 600 may move to all positions of the lower sliding surface to pick up the gangue 200. Of course, it is also possible to provide a striking rod or hammer 650 at the same time below said end 120.

The utility model discloses a control module 500's basic function is as shown in FIG. 4, control module 500 can discern most of gangues 200 mixed in the coal charge through the study training of degree of depth learning image recognition module. During operation, the control module 500 sends the recognition result to a gangue removal mechanism, and executes gangue removal operation to separate the gangue 200 from the coal block 250. Moreover, the control module 500 may further include a state detecting and dredging module for the sliding chute 111, and an illumination-enhancing haze-removing and dust-removing module for digitally enhancing the image quality of the shot image, using, for example, a dark channel algorithm or an artificial intelligence haze-removing algorithm, which are common in the prior art.

And, consider recognition efficiency, the utility model discloses a coal dressing system based on artificial intelligence image recognition can also set up many spout 111 discerns simultaneously and selects separately the operation. Each sliding chute 111 is at least correspondingly provided with a spray gun 400 and a gangue removing mechanism; the image capturing device 300 may be configured to independently locate each chute 111, or may be shared among a plurality of chutes 111, and simultaneously capture the coal located at the end 120 of each chute 111.

The utility model discloses a coal dressing system based on artificial intelligence image recognition because simple structure, can dispose in the pit, can remove most waste rock 200 before the coal charge goes out of the well, stays in the pit, can not pile up into the mountain like this subaerial, and it is troublesome to bring the subsequent processing.

The utility model discloses a working method based on artificial intelligence image recognition system, its flow chart is shown as figure 5, including following step:

a. the coal material slides downwards in the chute 111;

b. the lance 400 injects and flushes the coal charge;

c. the camera device 300 shoots the washed coal material in real time;

d. the camera 300 transmits the photographed image to the control module 500 in real time;

e. after identifying the gangue 200 or the coal block 250, the control module 500 sends an identification result to a gangue removal mechanism;

f. and the gangue removing mechanism removes the gangue 200 from the coal block 250 according to the action of the identification result.

Also, in a preferred implementation, the control module 500 issues an alarm to prompt a human operator to intervene when a coal blockage condition occurs or when the chute 111 is empty.

To sum up, the utility model discloses a coal dressing system based on artificial intelligence image recognition is provided with at least one spout 111, spout 111 is along the cross-section of the direction of sliding and is nearly V font, and the coal charge falls in the initial section 110 of spout 111 from the top to slide to the end 120 of spout 111, and the automation is arranged in a line, does benefit to the work efficiency and the accuracy of each process such as follow-up shooting, discernment, letter sorting; in the process that the coal material moves along the sliding chute 111, firstly, the spray gun 400 is used for washing and washing coal ash and coal slime on the coal material to expose the surface of the internal solid, so that the accuracy of artificial intelligent visual identification is improved; before reaching the tail end 120, the camera device 300 shoots in real time and sends the shot images to the control module 500, and the control module 500 recognizes that the current coal is the gangue 200 or the coal block 250 in real time through an artificial intelligence image recognition technology, controls the action of a gangue removing mechanism and removes the gangue 200 from the coal block 250. The utility model has high sorting accuracy for the gangue, simple equipment, wide processing grain size and large processing capacity, and can replace most of manpower; the device is simple and easy to maintain, is convenient to deploy underground, screens out the gangue and leaves the gangue underground before the coal material is lifted out of the well, and can effectively reduce the output of the gangue.

The foregoing has described in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be devised by those skilled in the art in light of the teachings of the present invention without undue experimentation. Therefore, the technical solutions that can be obtained by a person skilled in the art through logic analysis, reasoning or limited experiments based on the prior art according to the concepts of the present invention should be within the scope of protection defined by the claims.

Claims (9)

1. A coal dressing system based on artificial intelligence image recognition is characterized by comprising:

the cross section of the downstream of the sliding chute along the sliding direction is in a shape close to a V; the coal falls on the initial section of the chute and slides along the chute to the tail end of the chute;

the spray gun is arranged above each sliding chute and used for spraying and washing the coal;

the system comprises at least one camera device, a control module and a display module, wherein the camera device is right opposite to and used for shooting the moving coal in real time, and transmitting a shot image to the control module, and the control module is used for identifying gangue and coal blocks through an artificial intelligent visual image identification technology of deep learning;

the gangue removing mechanism acts after receiving the identification result sent by the control module and removes the identified gangue;

the identification result comprises an identified gangue position;

the approximate V-shaped part is in a shape that the middle is sunken and the two side walls are upwards unfolded, and comprises a V-shaped part or a U-shaped part which is placed right at the right position or an arc with an upward opening.

2. The coal preparation system of claim 1, wherein the sliding curve of the chute is a downward sloping straight line or a parabola or a steepest descent line.

3. The coal preparation system according to claim 1, wherein the gangue removal mechanism comprises a striking rod or hammer arranged below the tail end, and the striking rod or hammer acts under the control of the control module to strike the identified gangue and change the falling route of the gangue.

4. The coal preparation system of claim 1, wherein the gangue removal mechanism comprises at least one movable manipulator disposed above the terminal end, the manipulator being controlled by the control module to be movable into the chute to grasp gangue.

5. The coal preparation system of claim 1, further comprising a vibration module for vibrating said chute to assist said coal in sliding toward said distal end.

6. The coal preparation system of claim 1, wherein the lance emits high pressure air to which water mist is also added.

7. The coal preparation system of claim 1, wherein the lance faces upstream and/or downstream of the injection point of the chute, and the chute is closed or semi-closed above to prevent coal from splashing.

8. The coal preparation system according to claim 1, wherein the lens of the camera device is provided with a cleaning device for cleaning the lens.

9. The coal preparation system according to claim 1, wherein a plurality of said chutes are arranged side by side in a downward direction, a coal outlet plate is arranged across each of said initial sections from above in a longitudinal direction, and a side surface of said coal outlet plate in a width direction is inclined toward each of said initial sections; the coal material slides to each initial section from the side surface in the process of sliding forward along the coal outlet plate, slides to the tail end along each sliding groove and then falls; at least one striking rod or hammer is arranged below each end.

Images