CN113787007B - Intelligent dry separator execution precision intelligent real-time detection method, electronic equipment and storage medium - Google Patents

Intelligent dry separator execution precision intelligent real-time detection method, electronic equipment and storage medium Download PDF

Info

Publication number
CN113787007B
CN113787007B CN202111135921.5A CN202111135921A CN113787007B CN 113787007 B CN113787007 B CN 113787007B CN 202111135921 A CN202111135921 A CN 202111135921A CN 113787007 B CN113787007 B CN 113787007B
Authority
CN
China
Prior art keywords
separated
particle
dry separator
particles
effective
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111135921.5A
Other languages
Chinese (zh)
Other versions
CN113787007A (en
Inventor
王铁刚
张锐
李恭利
杜彦楠
闫治海
梁景强
高思华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inner Mongolia Dayan Mining Group Co ltd
Original Assignee
Inner Mongolia Dayan Mining Group Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Inner Mongolia Dayan Mining Group Co ltd filed Critical Inner Mongolia Dayan Mining Group Co ltd
Priority to CN202111135921.5A priority Critical patent/CN113787007B/en
Publication of CN113787007A publication Critical patent/CN113787007A/en
Application granted granted Critical
Publication of CN113787007B publication Critical patent/CN113787007B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/34—Sorting according to other particular properties
    • B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
    • B07C5/3425—Sorting according to other particular properties according to optical properties, e.g. colour of granular material, e.g. ore particles, grain
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/36—Sorting apparatus characterised by the means used for distribution
    • B07C5/361—Processing or control devices therefor, e.g. escort memory
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/36—Sorting apparatus characterised by the means used for distribution
    • B07C5/363—Sorting apparatus characterised by the means used for distribution by means of air

Landscapes

  • Sorting Of Articles (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses an intelligent real-time detection method for execution precision of an intelligent dry separator, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring the particle area variation trend of particles to be separated at the position of a nozzle of the dry separator when the dry separator performs blowing; and if the change trend of the particle area accords with a preset change condition, judging that no fault exists, otherwise, judging that a fault occurs, and executing fault alarm operation. According to the invention, whether the execution of the injection is normal or not is judged through the area change trend of the particle image, so that whether the execution mechanism can effectively inject or not is detected in real time in the sorting process, faults are detected in real time, and the sorting effect is prevented from being deteriorated.

Description

Intelligent real-time detection method for execution precision of intelligent dry separator, electronic equipment and storage medium
Technical Field
The invention relates to the technical field related to intelligent dry separators, in particular to an intelligent real-time detection method, electronic equipment, a system and a storage medium for execution precision of an intelligent dry separator.
Background
The intelligent dry separation machine adopts intelligent photoelectric separation identification, and after particles to be separated are detected, blowing information is transmitted to a control center, and then blowing is executed through a high-speed electromagnetic valve to complete separation, and a schematic diagram is shown in figure 1. The X-ray source 2' and the ray receiving device 3' in the sorting chamber 1' perform photoelectric sorting and identification on particles entering the sorting chamber 1' from the classifying screen 4', after the particles to be separated are detected, blowing information is transmitted to the control center, and then the air compressor 5' is controlled by the high-speed electromagnetic valve to perform blowing, so that clean coal falls into the clean coal belt 6', gangue and the like fall into the gangue belt 7', sorting is completed, and dust is collected by the dust collection device 8 '.
Wherein normal switch and the jetting precision of solenoid valve are the prerequisite of high quality separation, and current intelligent dry separation machine often accomplishes the debugging of jetting precision before equipment operation, detects whether the solenoid valve breaks down before equipment operation simultaneously, and then guarantees that equipment can normal operating.
However, the existing method for detecting or judging whether the actuator is normal is generally shutdown for maintenance. Therefore, the existing mode can only carry out preparatory treatment when the equipment stops running, cannot detect in real time in the running process of the equipment, cannot find out the faults of the electromagnetic valve and the execution precision deviation in time, and can only further analyze the reasons through the deterioration of the product sorting effect to influence the whole sorting effect.
Disclosure of Invention
Therefore, it is necessary to provide an intelligent dry separator execution precision real-time detection method, an electronic device, and a storage medium, for solving the technical problem that the fault cannot be detected in real time during the operation of the dry separator in the prior art.
The invention provides an intelligent real-time detection method for execution precision of an intelligent dry separator, which comprises the following steps:
acquiring the particle area variation trend of particles to be separated at the nozzle position of the dry separator when the dry separator performs blowing;
and if the change trend of the particle area meets the preset change condition, judging that no fault exists, otherwise, judging that a fault occurs, and executing fault alarm operation.
Further, when the dry separator performs blowing, acquiring a particle area variation trend of particles to be separated at a nozzle position of the dry separator specifically includes:
responding to the detection of a particle event to be separated by the dry separator, and acquiring continuous effective pictures of the nozzle position of the dry separator when the dry separator performs a blowing operation;
carrying out image recognition on a plurality of continuous effective pictures to obtain the outline of the particles to be separated corresponding to the particles to be separated in the effective pictures;
calculating the area of the particles to be separated in each effective picture according to the outline of the particles to be separated;
and determining the variation trend of the area of the particles to be separated in the continuous effective pictures as the variation trend of the area of the particles.
Furthermore, the acquiring multiple continuous effective pictures of the nozzle position in response to the detection of the particle event to be separated by the dry separator specifically includes:
and responding to the event that the dry separator detects the particles to be separated, and acquiring a first picture from the beginning of the blowing operation executed by the dry separator to an Nth picture after the blowing operation is finished as a plurality of continuous effective pictures, wherein N is a positive integer.
Furthermore, the acquiring continuous multiple effective pictures of the nozzle position of the dry separator when the dry separator performs the blowing operation in response to the dry separator detecting the event of the particles to be separated specifically includes:
continuously shooting the nozzle position of the dry separator at a fixed frequency from a separation chamber of the dry separator to the nozzle position of the dry separator at a preset angle to obtain a picture library comprising a plurality of continuous pictures;
and responding to the detection of the dry separator to-be-separated particle event, and acquiring continuous multiple pictures as effective pictures when the dry separator performs the blowing operation from the picture library.
Furthermore, the image recognition of the continuous multiple effective pictures to obtain the contour of the particles to be separated corresponding to the particles to be separated in the effective pictures specifically includes:
acquiring positioning information of particles to be separated by photoelectric separation identification equipment when a dry separator executes blowing operation;
and acquiring the outline of the particles to be separated corresponding to the particles to be separated in each effective picture through image identification according to the positioning information.
Still further, the obtaining of the contour of the particles to be separated corresponding to the particles to be separated in each effective picture through image recognition according to the positioning information specifically includes:
determining a blowing execution device for executing blowing operation in a plurality of blowing devices, wherein nozzles of the plurality of blowing devices are arranged along the width direction of a conveyor belt, the positioning information is the nozzle image positions of the nozzles of the blowing execution device in effective pictures, and in each effective picture, a straight line passing through the nozzle image positions and extending along the conveying direction of the conveyor belt is used as a reference line;
carrying out image recognition on each effective picture to obtain one or more particle outlines to be screened;
and for each effective picture, selecting the particle contour to be screened closest to the reference line from the particle contours to be screened included in the effective picture as the particle contour to be separated corresponding to the particle to be separated and the effective picture.
Still further, the selecting a contour of the particle to be screened, which is closest to the reference line, from contours of the particle to be screened included in the effective picture as a contour of the particle to be separated corresponding to the particle to be separated and the effective picture specifically includes:
if the effective picture is an effective picture between the occurrence of the blowing operation and the completion of the blowing operation, selecting a particle contour to be screened which is closest to the reference line from particle contours to be screened included in the effective picture as a particle contour to be separated corresponding to the effective picture and the particles to be separated;
and if the effective picture is the effective picture after the blowing operation is performed, selecting the outline of the particle to be screened which is separated from the position of the nozzle image or is positioned at the position of the nozzle image in the transmission direction of the transmission belt, and taking the outline of the particle to be screened which is closest to the reference line as the outline of the particle to be separated corresponding to the effective picture and the particle to be separated.
And further:
the change conditions are as follows: changing along with time, changing the change rate of the particle area from a negative number to a positive number, and then changing the change rate of the particle area from the positive number to the negative number; or alternatively
The change conditions are as follows: over time, the particle area changes from gradually decreasing to gradually increasing, and then from gradually increasing to gradually decreasing.
The present invention provides an electronic device including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to at least one of the processors; wherein the content of the first and second substances,
the memory stores instructions executable by at least one of the processors to enable the at least one of the processors to perform the intelligent dry separator execution precision intelligent real-time detection method as described above.
The invention provides a storage medium which stores computer instructions for executing all the steps of the intelligent dry separator execution precision intelligent real-time detection method when a computer executes the computer instructions.
According to the invention, whether the jetting is normally executed is judged according to the area change trend of the particle image, so that whether the actuating mechanism can effectively jet is detected in real time in the sorting process, faults are detected in real time, and the sorting effect is prevented from being deteriorated.
Drawings
FIG. 1 is a schematic diagram of a conventional intelligent dry separator;
FIG. 2 is a flow chart of the operation of the intelligent dry separator execution precision intelligent real-time detection method of the present invention;
FIG. 3 is a system schematic diagram of a detection system of the intelligent dry separator of one embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for performing intelligent real-time detection of the execution accuracy of the intelligent dry separator according to an embodiment of the present invention;
FIG. 5 is a schematic view of particle profile positioning according to an example of the present invention;
FIG. 6 is a schematic representation of the variation of the cross-sectional area of the particles at different stages;
FIG. 7 is a diagram showing a comparison of the variation trend curves of the areas of the particles to be separated in the normal state and the fault state;
fig. 8 is a schematic diagram of a hardware structure of an electronic device according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples.
Example one
Fig. 2 is a flowchart illustrating a method for intelligently detecting the execution precision of the intelligent dry separator in real time according to the present invention, which includes:
step S201, acquiring a particle area variation trend of particles to be separated at a nozzle position of a dry separator when the dry separator performs blowing;
and S202, if the change trend of the particle area meets the preset change condition, judging that no fault exists, otherwise, judging that a fault occurs, and executing fault alarm operation.
Specifically, as shown in fig. 3, the detection system of the intelligent dry separator according to an embodiment of the present invention includes an X-ray source 2 and a ray receiving device 3 located in a separation chamber 1, an air compressor 5, an identification camera 9, and a controller (not shown in the figure), the X-ray source 2 and the ray receiving device 3 perform photoelectric separation and identification on particles entering the separation chamber 1 from a classifying screen 4, after detecting the particles to be separated, blowing information is transmitted to a control center, and then the air compressor 5 is controlled by a high-speed solenoid valve to perform blowing, so that clean coal falls into a clean coal belt 6, and gangue falls into a gangue belt 7 to complete separation, and dust is collected by a dust collection device 8. When the X-ray source 2 detects particles to be separated, the relevant blowing information is sent to the execution solenoid valve, the solenoid valve controls the air compressor 5 to execute blowing, and the blowing information is also sent to the controller, which triggers step S201, for example, the recognition camera 9 or other shooting device shoots the nozzle position 51 of the air compressor 5, and sends the shooting data to the controller, and the execution state of the solenoid valve is detected in real time. The execution state of the solenoid valve is judged by the particle area variation tendency of the particles to be separated at the nozzle position 51. The nozzle position is the position of the nozzle of the blowing device. By executing step S202, it is determined whether the particle area variation trend meets the preset variation condition, and if the particle area variation trend does not meet the preset variation condition, it is determined that a fault occurs, and a corresponding fault warning operation is executed. The fault alarm operation can be to record the fault, analyze the fault, or perform an audible and visual alarm operation. And the fault alarm operation is also recorded when the fault is judged to be sent, and when the frequency of judging the fault exceeds a preset threshold value, corresponding acousto-optic alarm operation is triggered.
According to the invention, whether the execution of the injection is normal or not is judged through the area change trend of the particle image, so that whether the execution mechanism can effectively inject or not is detected in real time in the sorting process, faults are detected in real time, and the sorting effect is prevented from being deteriorated.
Example two
Fig. 4 is a flowchart illustrating a method for performing intelligent real-time detection on the execution precision of the intelligent dry separator according to an embodiment of the present invention, including:
step S401, responding to the fact that the dry separator detects a particle event to be separated, and acquiring continuous multiple effective pictures of the position of a nozzle of the dry separator when the dry separator executes blowing operation;
in one embodiment, the acquiring, in response to the detection of the to-be-separated particle event by the dry separator, a plurality of consecutive effective pictures of the nozzle position specifically includes:
and responding to the detection of a particle event to be separated by the dry separator, and acquiring a first picture from the beginning of the blowing operation executed by the dry separator to an Nth picture after the blowing operation is finished as a plurality of continuous effective pictures, wherein N is a positive integer.
In one embodiment, in response to the dry separator detecting a particle event to be separated, acquiring multiple continuous effective pictures of a nozzle position of the dry separator when the dry separator performs a blowing operation specifically includes:
continuously shooting the nozzle position of the dry separator at a fixed frequency from a separation chamber of the dry separator to the nozzle position of the dry separator at a preset angle to obtain a picture library comprising a plurality of continuous pictures;
and responding to the detection of the dry separator to-be-separated particle event, and acquiring continuous multiple pictures as effective pictures when the dry separator performs the blowing operation from the picture library.
S402, carrying out image recognition on a plurality of continuous effective pictures to obtain the contour of the particles to be separated corresponding to the particles to be separated in the effective pictures;
in one embodiment, the image recognition of the continuous multiple effective pictures to obtain the contour of the particle to be separated corresponding to the particle to be separated in the effective pictures specifically includes:
acquiring positioning information of particles to be separated by photoelectric separation identification equipment when a dry separator executes blowing operation;
and acquiring the outline of the particles to be separated corresponding to the particles to be separated in each effective picture through image identification according to the positioning information.
In one embodiment, the obtaining, according to the positioning information and through image recognition, a contour of a particle to be separated corresponding to the particle to be separated in each effective picture specifically includes:
determining a blowing execution device for executing blowing operation in a plurality of blowing devices, wherein nozzles of the plurality of blowing devices are arranged along the width direction of a conveyor belt, the positioning information is the nozzle image positions of the nozzles of the blowing execution device in effective pictures, and in each effective picture, a straight line passing through the nozzle image positions and extending along the conveying direction of the conveyor belt is used as a reference line;
carrying out image recognition on each effective picture to obtain one or more particle outlines to be screened;
and for each effective picture, selecting the outline of the particles to be screened closest to the reference line from the outlines of the particles to be screened included in the effective picture as the outline of the particles to be separated corresponding to the effective picture and the particles to be separated.
In one embodiment, the selecting, from the outlines of the particles to be screened included in the effective picture, an outline of the particles to be screened closest to the reference line as an outline of the particles to be separated corresponding to the effective picture and the particles to be separated specifically includes:
if the effective picture is an effective picture between the occurrence of the blowing operation and the completion of the blowing operation, selecting a particle contour to be screened, which is closest to the reference line, from particle contours to be screened, which are included in the effective picture, as a particle contour to be separated, which corresponds to the effective picture and the particle to be separated;
and if the effective picture is the effective picture after the blowing operation is performed, selecting the outline of the particle to be screened which is separated from the position of the nozzle image or is positioned at the position of the nozzle image in the transmission direction of the transmission belt, and taking the outline of the particle to be screened which is closest to the reference line as the outline of the particle to be separated corresponding to the effective picture and the particle to be separated.
Step S403, calculating the area of the particles to be separated in each effective picture according to the contour of the particles to be separated.
Step S404, determining a variation trend of the area of the particles to be separated in the consecutive effective pictures as a variation trend of the area of the particles.
And S405, if the particle area variation trend meets a preset variation condition, judging that no fault exists, otherwise, judging that a fault occurs, and executing a fault alarm operation.
In one embodiment, the changing condition is: changing along with time, changing the change rate of the particle area from a negative number to a positive number, and then changing the change rate of the particle area from the positive number to the negative number; or alternatively
The change conditions are as follows: over time, the particle area changes from gradually decreasing to gradually increasing, and then from gradually increasing to gradually decreasing.
Specifically, in order to detect the state of the solenoid valve and the blowing accuracy in real time, the present embodiment employs an additional camera to detect the opening and closing of the solenoid valve and the particle blowing accuracy in real time by using images, and the structure of the additional camera is shown in fig. 3. Including X ray source 2 and ray receiving arrangement 3 that are located sorting chamber 1, air compressor machine 5, discernment camera 9, and controller (not shown in the figure), X ray source 2 and ray receiving arrangement 3 carry out the photoelectricity to the granule that gets into sorting chamber 1 from classifying screen 4 and select separately the discernment, detect and wait to separate the granule after, transmit jetting information to control center, and then control air compressor machine 5 through high-speed solenoid valve and carry out the jetting, make the cleaned coal fall into cleaned coal belt 6, waste rock etc. falls into waste rock belt 7, accomplish the sorting, and by the dust collecting equipment 8 dust absorption. When the X-ray source 2 detects particles to be separated, the relevant blowing information is sent to the execution solenoid valve, the solenoid valve controls the air compressor 5 to execute blowing, and the blowing information is also sent to the controller, so as to trigger step S401, for example, the recognition camera 9 or other shooting device shoots the nozzle position 51 of the air compressor 5, and sends the shooting data to the controller, and the execution state of the solenoid valve is detected in real time according to the picture.
The recognition camera 9 is placed on top of the sorting chamber 1, preferably illuminating the nozzle position 51 (i.e. the solenoid valve position) at an angle of 60 °, and capturing images at a fixed frequency. Specifically, the camera always takes pictures at a constant frequency to constitute a total stock, and each time a specific particle is identified, a corresponding picture is extracted for the specific particle to perform a targeted analysis, so as to complete individual judgment of each particle. Since the X-ray source 2 sends the event of detecting the particles to be separated to the controller when detecting the particles to be separated, and the air compressor 5 performs the blowing operation at the preset time after detecting the particle event to be separated, the preset time after detecting the particle event to be separated is the blowing time. For example, the blowing time is the starting blowing time of the electromagnetic valve corresponding to the particles to be judged. And selecting the first picture from which the blowing operation starts to the Nth picture after the blowing is finished as a plurality of continuous effective pictures according to the blowing time. For example, the 1 st photograph from the beginning of blowing to the 10 th photograph from the end of blowing is selected as the effective picture. The specific value of N can be selected according to actual needs.
Then triggering step S402, sending the effective picture with the execution information to the information processing center of the controller for image recognition processing. Finally, step S403 to step S405 are executed, and whether or not the electromagnetic valve performs high-precision blowing is determined by identifying the cross-sectional area.
In the determination process, in step S402, a plurality of particle profiles are selected through image recognition, and then the particle profile to be separated corresponding to the particle to be separated in each effective picture is determined according to the positioning information of the photoelectric selection recognition device.
Specifically, the photoelectric sorting and identifying device, such as the X-ray source 2 and the ray receiving device 3, can determine whether the particles on the conveying belt are particles to be separated, such as gangue. At the same time, the position of the particles to be separated on the conveyor belt can be obtained. Therefore, the photoelectric selection identification device informs the control center, and when the particles to be separated reach the blowing position, the corresponding blowing device is controlled to perform blowing operation, so that the particles to be separated are blown out and fall into the gangue belt 7. At the nozzle position 51, a plurality of blowing devices are arranged along the width direction of the conveyor belt, when a plurality of parallel particles reach the nozzle position 51, the control center of the dry separation machine opens the electromagnetic valve of the blowing device below the particles to be separated, and the particles to be separated are blown out from the plurality of parallel particles and fall into the gangue belt 7. The blowing device performing the blowing operation is the blowing performing device. The control center of the dry separator selects the blowing device and can be realized by adopting the existing particle recognition mode of the dry separator.
Since the position of the blowing devices is fixed, the nozzle position of each blowing device is fixed in the position in the effective picture taken by the recognition camera 9. In the case of a plurality of blowing devices, since the nozzles of the blowing devices are arranged in the width direction of the conveyor belt, the recognition camera 9 photographs all the nozzles. As shown in fig. 5, as an example of the present invention, the nozzle image positions of the nozzle positions of the three blowing devices in the effective picture 51 are the nozzle image position 52, the nozzle image position 53, and the nozzle image position 54, respectively. Wherein the nozzle image position 53 is the nozzle image position of the nozzle of the blowing device in the active picture 51. A straight line extending in the conveying direction of the conveying belt through the nozzle image position 53 is taken as a reference line 55. A plurality of particle outlines to be screened can be identified from each effective picture through an image identification technology. As shown in fig. 5, as an example of the present invention, the effective picture 51 identifies a contour 56 of a particle to be screened, a contour 57 of a particle to be screened, and a contour 58 of a particle to be screened. The contour 57 of the particle to be screened closest to the reference line 55 is selected as the contour of the particle to be separated corresponding to the particle to be separated. The selection can be carried out according to the distance from the center of the outline of the particle to be screened to the reference line, and the outline of the particle to be screened with the shortest distance from the center to the reference line is selected as the outline of the particle to be separated.
More specifically, if the effective picture is an effective picture between the occurrence of the blowing operation and the completion of the blowing operation, selecting a particle profile to be screened, which is closest to the reference line, from the particle profiles to be screened, included in the effective picture, as a particle profile to be separated, corresponding to the particle to be separated, of the effective picture.
And finally, if the effective picture is the effective picture after the blowing operation is executed, the particles to be separated integrally leave the nozzle position at the moment, so that the particle contour to be screened, which is closest to the reference line, in the particle contour to be screened, which leaves the nozzle image position or is positioned at the nozzle image position in the conveying direction of the conveying belt is selected as the particle contour to be separated, corresponding to the particles to be separated, of the effective picture. For example, in the captured effective photograph, the particle profile moves from top to bottom, and when the particle profile is located below the nozzle image position, the particle profile leaves the nozzle image position in the conveying direction of the conveyor belt.
The particle profile to be separated corresponding to the particle to be separated is determined in the above manner, and then step S403 is performed to calculate the particle area of the particle profile to be separated as the particle area to be separated. And step S404 is executed to draw an area curve for the areas of the particles to be separated in the continuous multiple pictures, so as to obtain the change trend of the areas of the particles. And finally, step S405 is executed to compare the particle area variation trend with preset variation conditions, and whether the switch of the electromagnetic valve and the particle blowing precision meet the requirements or not is judged, so that whether the dry separator fails or not is determined.
In the case of normal blowing, taking square particles as an example, as shown in fig. 6, the whole blowing process can be divided into five stages according to the relative positions of the particles and the nozzle, including: a pre-blowing phase 61, a head-up phase 62, a flush phase 63, a tail-tipping phase 64, and a tip-over phase 65. The cross-sectional area detected by the pictures should exhibit a tendency to decrease, increase and decrease during the pre-blowing phase 61, the head-up phase 62, the level phase 63, and the tail-tilting phase 64, while the cross-sectional area repeats between increasing and decreasing during the flip phase 65. When the electromagnetic valve breaks down or the blowing precision is in problem, the particles are not influenced by gas and continue to do parabolic motion, and the area is not changed greatly and is slightly reduced. Therefore, if the variation trend of the area of the particles to be separated is not in accordance with the expectation, the analysis system sends out the alarm information of the fault in the execution stage. In the image analysis link, the accuracy of analysis can be improved by drawing an area curve and detecting the change rate of the derivative of the curve. As shown in fig. 7, the abscissa is the number of pictures (i.e., time) collected in time series, and the unit is sheet; the ordinate is the area, where the unit of the ordinate is square meters. The blown particles do not contain a flip phase area change. As can be seen from fig. 7, the area trend curve 71 of the particles to be separated in the normal state includes a first decreasing stage 711, an increasing stage 712, and a second decreasing stage 713. The curve 72 of the trend of the area of the particles to be separated in the fault state has no change and only slightly decreases.
Therefore, a curve change rate mode can be adopted, namely the change trend of the particle area is expressed by the change rate of the particle area, and the change condition is defined as that: over time, the rate of change of particle area changes from negative to positive and then from positive to negative. The rate of change of the particle area is negative, i.e., the particle area gradually decreases, and the rate of change of the particle area is positive, i.e., the particle area gradually increases.
Similarly, the area change can be directly judged, and the change condition is defined as: over time, the particle area changes from gradually decreasing to gradually increasing, and then from gradually increasing to gradually decreasing.
In comparison, the values of the curves may be appropriately filtered, for example, a plurality of curves whose change rates are positive may be regarded as a change from a negative value to a positive value. The change rate of the curve is considered to change from a positive value to a negative value until a plurality of consecutive curve change rates are negative values. Or the curve change rate exceeds a certain threshold value to start comparison, so that misjudgment caused by small-range fluctuation of data is avoided.
In this embodiment, the inversion state of the blowing particles (material flow) is determined by an image, and whether the blowing device blows normally or not is determined according to the variation trend of the particle area. The detection effect precision of this embodiment is higher, and whether the effective jetting of actuating mechanism can be detected in real time in the sorting process, real-time detection trouble avoids selecting separately the effect variation.
EXAMPLE III
Fig. 8 is a schematic diagram of a hardware structure of an electronic device according to the present invention, which includes:
at least one processor 801; and the number of the first and second groups,
a memory 802 communicatively coupled to at least one of the processors 801; wherein the content of the first and second substances,
the memory 802 stores instructions executable by at least one of the processors to enable the at least one of the processors to perform the intelligent dry separator accuracy intelligent real-time detection method as described above.
Fig. 8 illustrates an example of a processor 801.
The electronic device is preferably a controller. The electronic device may further include: an input device 803 and a display device 804, the display device 804 may be used for audible and visual alarms.
The processor 801, the memory 802, the input device 803, and the display device 804 may be connected by a bus or other means, and are illustrated as being connected by a bus.
The memory 802 is a non-volatile computer-readable storage medium, and can be used to store a non-volatile software program, a non-volatile computer-executable program, and modules, such as program instructions/modules corresponding to the intelligent dry separator execution precision intelligent real-time detection method in the embodiment of the present application, for example, the method flow shown in fig. 2. The processor 801 executes various functional applications and data processing by running nonvolatile software programs, instructions and modules stored in the memory 802, that is, the intelligent dry separator execution precision intelligent real-time detection method in the above embodiments is realized.
The memory 802 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the intelligent dry separator execution precision intelligent real-time detection method, and the like. Further, the memory 802 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory 802 optionally includes memory located remotely from the processor 801, which may be connected via a network to a device that performs the intelligent dry separator method of performing the precision intelligent real-time detection method. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 803 may receive an input of a user click and generate signal inputs related to user settings and function controls for the intelligent dry separator to perform the precision intelligent real-time detection method. The display device 804 may include a display screen or the like.
When the one or more modules are stored in the memory 802, the intelligent dry separator in any of the above-described method embodiments performs the precision intelligent real-time detection method when executed by the one or more processors 801.
According to the invention, whether the execution of the injection is normal or not is judged through the area change trend of the particle image, so that whether the execution mechanism can effectively inject or not is detected in real time in the sorting process, faults are detected in real time, and the sorting effect is prevented from being deteriorated.
An embodiment of the present invention provides a storage medium, which stores computer instructions for executing all the steps of the intelligent dry separator execution precision intelligent real-time detection method as described above when a computer executes the computer instructions.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is specific and detailed, but not to be understood as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (9)

1. An intelligent real-time detection method for execution precision of an intelligent dry separator is characterized by comprising the following steps:
acquiring the particle area variation trend of particles to be separated at the position of a nozzle of the dry separator when the dry separator performs blowing;
if the change trend of the particle area meets the preset change condition, judging that no fault exists, otherwise, judging that a fault occurs, and executing fault alarm operation;
when obtaining dry separator and carrying out jetting, the granule area variation tendency of the granule of waiting to separate of dry separator's nozzle position specifically includes:
responding to the detection of a particle event to be separated by the dry separator, and acquiring continuous effective pictures of the nozzle position of the dry separator when the dry separator performs a blowing operation;
carrying out image recognition on a plurality of continuous effective pictures to obtain the outlines of the particles to be separated corresponding to the particles to be separated in the effective pictures;
calculating the area of the particles to be separated in each effective picture according to the outline of the particles to be separated;
and determining the variation trend of the area of the particles to be separated in the continuous effective pictures as the variation trend of the area of the particles.
2. The intelligent real-time detection method for execution precision of the intelligent dry separator according to claim 1, wherein the acquiring of the continuous multiple effective pictures of the nozzle position in response to the detection of the particle event to be separated by the dry separator specifically comprises:
and responding to the detection of a particle event to be separated by the dry separator, and acquiring a first picture from the beginning of the blowing operation executed by the dry separator to an Nth picture after the blowing operation is finished as a plurality of continuous effective pictures, wherein N is a positive integer.
3. The intelligent real-time detection method for execution precision of the intelligent dry separator according to claim 1, wherein the step of acquiring continuous multiple effective pictures of the position of the nozzle of the dry separator when the dry separator executes a blowing operation in response to the dry separator detecting a particle event to be separated specifically comprises the steps of:
continuously shooting the nozzle position of the dry separator at a fixed frequency from a separation chamber of the dry separator to the nozzle position of the dry separator at a preset angle to obtain a picture library comprising a plurality of continuous pictures;
and responding to the detection of the event of the particles to be separated by the dry separator, and acquiring continuous multiple pictures of the dry separator during the blowing operation as effective pictures from the picture library.
4. The intelligent real-time detection method for execution precision of the intelligent dry separator according to claim 2, wherein the image recognition is performed on a plurality of continuous effective pictures to obtain the outline of the particles to be separated corresponding to the particles to be separated in the effective pictures, and specifically comprises:
acquiring positioning information of particles to be separated by photoelectric separation identification equipment when a dry separator executes blowing operation;
and acquiring the outline of the particles to be separated corresponding to the particles to be separated in each effective picture through image recognition according to the positioning information.
5. The intelligent dry separator execution precision intelligent real-time detection method according to claim 4, wherein the step of obtaining the contour of the particles to be separated corresponding to the particles to be separated in each effective picture through image recognition according to the positioning information specifically comprises the steps of:
determining a blowing execution device for executing blowing operation in a plurality of blowing devices, wherein nozzles of the plurality of blowing devices are arranged along the width direction of a conveyor belt, the positioning information is the nozzle image positions of the nozzles of the blowing execution device in effective pictures, and in each effective picture, a straight line passing through the nozzle image positions and extending along the conveying direction of the conveyor belt is used as a reference line;
carrying out image recognition on each effective picture to obtain one or more particle outlines to be screened;
and for each effective picture, selecting the outline of the particles to be screened closest to the reference line from the outlines of the particles to be screened included in the effective picture as the outline of the particles to be separated corresponding to the effective picture and the particles to be separated.
6. The intelligent dry separator execution precision intelligent real-time detection method according to claim 5, wherein the selecting a particle contour to be screened closest to the reference line from particle contours to be screened included in the effective picture as a particle contour to be separated corresponding to the particle to be separated and the effective picture specifically comprises:
if the effective picture is an effective picture between the occurrence of the blowing operation and the completion of the blowing operation, selecting a particle contour to be screened which is closest to the reference line from particle contours to be screened included in the effective picture as a particle contour to be separated corresponding to the effective picture and the particles to be separated;
and if the effective picture is the effective picture after the blowing operation is performed, selecting the outline of the particle to be screened which is separated from the position of the nozzle image or is positioned at the position of the nozzle image in the transmission direction of the transmission belt, and taking the outline of the particle to be screened which is closest to the reference line as the outline of the particle to be separated corresponding to the effective picture and the particle to be separated.
7. The intelligent dry separator execution precision intelligent real-time detection method according to any one of claims 1 to 6, characterized in that:
the change conditions are as follows: changing along with time, changing the change rate of the particle area from a negative number to a positive number, and then changing the change rate of the particle area from the positive number to the negative number; or alternatively
The change conditions are as follows: over time, the particle area changes from gradually decreasing to gradually increasing, and then from gradually increasing to gradually decreasing.
8. An electronic device, comprising:
at least one processor; and (c) a second step of,
a memory communicatively coupled to at least one of the processors; wherein the content of the first and second substances,
the memory stores instructions executable by at least one of the processors to enable the at least one of the processors to perform the intelligent dry separator execution precision intelligent real-time detection method of any one of claims 1 to 7.
9. A storage medium storing computer instructions for performing all the steps of the intelligent dry sorting machine performing the precision intelligent real-time detection method according to any one of claims 1-7 when the computer executes the computer instructions.
CN202111135921.5A 2021-09-27 2021-09-27 Intelligent dry separator execution precision intelligent real-time detection method, electronic equipment and storage medium Active CN113787007B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111135921.5A CN113787007B (en) 2021-09-27 2021-09-27 Intelligent dry separator execution precision intelligent real-time detection method, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111135921.5A CN113787007B (en) 2021-09-27 2021-09-27 Intelligent dry separator execution precision intelligent real-time detection method, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113787007A CN113787007A (en) 2021-12-14
CN113787007B true CN113787007B (en) 2023-03-31

Family

ID=79184566

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111135921.5A Active CN113787007B (en) 2021-09-27 2021-09-27 Intelligent dry separator execution precision intelligent real-time detection method, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113787007B (en)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102489453A (en) * 2011-11-24 2012-06-13 天津吉亚牧业集团有限公司 Matrix nozzle actuating mechanism of color sorter
CN105499154A (en) * 2016-01-05 2016-04-20 天津美腾科技有限公司 Telligent dry separator (TDS)
CN110077111B (en) * 2018-05-30 2020-07-10 广东聚华印刷显示技术有限公司 Method, device and system for correcting ink jet printing head
JP7309427B2 (en) * 2019-04-15 2023-07-18 キヤノン株式会社 Inkjet recording device, recording method, and program
CN110293762B (en) * 2019-06-20 2021-02-26 森大（深圳）技术有限公司 Method and device for dynamically detecting abnormal nozzle in printing process and storage medium

Also Published As

Publication number Publication date
CN113787007A (en) 2021-12-14

Similar Documents

Publication Publication Date Title
JP5569799B2 (en) Color sorter
CN102639259B (en) Inspection apparatus and method using pattern recognition
CN111242108B (en) Belt transfer point coal blockage identification method based on target detection
US20140247347A1 (en) Methods and Apparatus for Video Based Process Monitoring and Control
CN101509766B (en) On-line detecting method for spring end plane angle by machine vision system
TWI616388B (en) Conveying object identification control system and conveying device
US20220379348A1 (en) Sorting device for agricultural products and corresponding method
EP2454029B1 (en) Sorting apparatus and method using a graphical user interface
CN114140684A (en) Method, device and equipment for detecting coal blockage and coal leakage and storage medium
JP5859845B2 (en) Threading plate abnormality detection device
CN113297885A (en) Belt conveyor surface state detection method and device based on convolutional neural network
CN113787007B (en) Intelligent dry separator execution precision intelligent real-time detection method, electronic equipment and storage medium
CN114101095B (en) Control method of sorting equipment and sorting equipment
ES2658388B1 (en) RECOGNITION OF COINS AND COLLECTION FROM A FLOW OF MATERIAL
JP2020185118A5 (en)
JP6715282B2 (en) Quality monitoring system
CN107516310B (en) Mask vision stain inspection and waste discharge method
CN108663004B (en) Method and device for detecting abnormal thickness of paper money
EP4129566A1 (en) Information processing device and machine tool
CN109516067B (en) Part detection system and detection method
US20230070533A1 (en) Method for cleaning blinding particles in crushers
WO2012004550A1 (en) Dual sensitivity browser for sorting machines
CN105618385A (en) Screw detecting machine
JP7343186B2 (en) Conveyed object detection processing system and conveyance device
TWI834046B (en) Conveyor system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant