CN113533349A - Intelligent automatic tobacco shred impurity detecting and removing system - Google Patents

Intelligent automatic tobacco shred impurity detecting and removing system Download PDF

Info

Publication number
CN113533349A
CN113533349A CN202110813239.0A CN202110813239A CN113533349A CN 113533349 A CN113533349 A CN 113533349A CN 202110813239 A CN202110813239 A CN 202110813239A CN 113533349 A CN113533349 A CN 113533349A
Authority
CN
China
Prior art keywords
impurity
tobacco
detection
conveyor
raw material
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.)
Pending
Application number
CN202110813239.0A
Other languages
Chinese (zh)
Inventor
吴玉生
李安虎
林开颜
吴军辉
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN202110813239.0A priority Critical patent/CN113533349A/en
Publication of CN113533349A publication Critical patent/CN113533349A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/01Arrangements or apparatus for facilitating the optical investigation

Landscapes

  • Chemical & Material Sciences (AREA)
  • Biochemistry (AREA)
  • Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Immunology (AREA)
  • Analytical Chemistry (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Manufacture Of Tobacco Products (AREA)

Abstract

The invention provides an intelligent automatic detection and removal system for tobacco shred impurities, which is characterized by comprising the following components: the impurity detection module is used for detecting impurities in the tobacco raw materials so as to obtain an impurity detection result through detection, and the impurity detection result comprises impurity position information; and the impurity removing module is used for removing impurities from the tobacco raw materials according to the impurity position information so as to obtain clean tobacco shreds. The impurity detection module detects the tobacco raw materials according to the color characteristics, the shape characteristics, the texture characteristics and the spectral characteristics of the impurities respectively to obtain impurity detection results. The intelligent automatic tobacco shred impurity detecting and removing system can automatically remove the impurities such as metal, stone, hemp ropes, paper sheets, worm cocoons, foams, stem sticks, mildewed tobacco leaves, wet mass tobacco shreds and the like in the tobacco raw materials, improves the impurity removing efficiency, saves the labor cost, and also can improve the efficiency of the subsequent cigarette making process and the quality of cigarettes.

Description

Intelligent automatic tobacco shred impurity detecting and removing system
Technical Field
The invention belongs to the technical field of tobacco processing, and particularly relates to an intelligent automatic detection and removal system and device for cut tobacco impurities.
Background
The tobacco raw materials are generally mixed with impurities such as metal, stone, hemp ropes, paper pieces, worm cocoons, foams, moldy tobacco leaves and the like, and the impurity removal of the tobacco shreds is one of the most important processes for manufacturing modern cigarette products, and has the following main functions: the irreversible damage of heavy impurities such as metal, stones and the like to the automatic equipment in the later period is prevented; the influence of hemp ropes and worm cocoon foreign matters on the quality of the cigarettes is prevented; prevent the light impurities such as foam and moldy tobacco leaves from influencing the taste and being harmful to health.
At present, foreign tobacco foreign matter removal systems mostly adopt a laser scanning or CCD camera shooting mode to obtain detection signals, researches on identifying and removing impurities in tobacco shreds are few, automatic tobacco foreign matter identification and removal equipment of various tobacco enterprises adopts a detection method based on color characteristics, identification accuracy is low, and development of the tobacco industry is severely restricted.
Disclosure of Invention
In order to solve the problems, the invention provides a tobacco shred impurity identification and removal system with high identification efficiency, which adopts the following technical scheme:
the invention provides an intelligent automatic detection and removal system for tobacco shred impurities, which is characterized by comprising the following components: the impurity detection module is used for detecting impurities in the tobacco raw materials so as to obtain an impurity detection result through detection, and the impurity detection result comprises impurity position information; and the impurity removing module removes impurities from the tobacco raw materials according to the position information of the impurities to obtain clean tobacco shreds, wherein the impurity detecting module is provided with a first detecting part, a second detecting part and a third detecting part, the first detecting part detects the tobacco raw materials according to the color characteristics and the shape characteristics of the impurities to obtain a first detecting result, the second detecting part detects the tobacco raw materials according to the texture characteristics of the impurities to obtain a second detecting result, the third detecting part detects the tobacco raw materials according to the spectral characteristics of the impurities to obtain a third detecting result, and the impurity removing module removes the impurities according to the first detecting result, the second detecting result and the third detecting result respectively.
In the system for automatically detecting and removing the impurities in the intelligent cut tobacco provided by the invention, the system also has the following characteristics: the tobacco primary screening module is used for primarily screening original tobacco containing different impurities to obtain tobacco raw materials; and a tobacco flattening transportation module for flattening and transporting the tobacco raw material to the impurity detection module, wherein the tobacco primary screening module is provided with a conveyor for screening and a negative pressure device for screening, the tobacco shred flattening transportation module is provided with a feeding funnel, a blanking device, a conveying mechanism for flattening and a height limiting mechanism, the blanking device is arranged at the outlet of the feeding funnel, the height limiting mechanism is arranged near the conveying mechanism for flattening, the conveyor for screening is used for conveying the original tobacco to the lower part of the negative pressure device for screening, the negative pressure device for screening is used for absorbing the raw material with smaller specific gravity of the original tobacco as the tobacco raw material and conveying the tobacco raw material to the feeding funnel, the blanking device is used for controlling the falling flow of the tobacco raw material, so that the tobacco raw material is uniformly flattened on the conveying mechanism for flattening, the conveying mechanism for flattening is provided with a plurality of conveyors for conveying the tobacco raw material and flows through the first detection part, The second detection part and the third detection part are used for spreading the overlapped tobacco raw materials, so that all the tobacco raw materials are completely spread.
The intelligent automatic tobacco shred impurity detecting and removing system provided by the invention can also be characterized in that the flattening conveying mechanism is provided with at least 4 conveyors which are respectively a first conveyor, a second conveyor, a third conveyor and a fourth conveyor, the first conveyor is positioned below the blanking device, the second conveyor is positioned below the first detection part, the third conveyor is positioned below the second detection part, the fourth conveyor is positioned below the third detection part, the corresponding heights of the first conveyor, the second conveyor, the third conveyor and the fourth conveyor are sequentially reduced, and the corresponding conveying speeds are sequentially accelerated.
The system for intelligently and automatically detecting and eliminating the impurities in the tobacco shreds provided by the invention can also have the characteristics that the first detection part at least comprises a first image acquisition unit and a first detection model detection unit, the second detection part at least comprises a second image acquisition unit and a second detection model detection unit, the third detection part at least comprises a third image acquisition unit and a third detection model detection unit, the first image acquisition unit acquires an RGB image of the tobacco raw material as a first image through a camera arranged above the tobacco raw material, the first detection model detection unit detects the first image through a first impurity detection model trained in advance according to color and shape characteristics so as to obtain a first detection result, the first detection result comprises first impurity position information, and the second image acquisition unit acquires a plurality of RGB images of the tobacco raw material from different angles through a plurality of cameras arranged above the tobacco raw material as a plurality of RGB images of the tobacco raw material from different angles through a plurality of cameras arranged above the tobacco raw material And the third detection model detection unit detects the third image through the pre-trained third impurity detection model according to the spectral characteristics so as to obtain a third detection result, and the third detection result comprises third impurity position information.
The intelligent automatic detection and removal system for the tobacco shred impurities provided by the invention can also have the characteristics that the first detection part, the second detection part and the third detection part are respectively provided with a light shield used for shielding external natural light for the tobacco raw material and a plurality of light sources arranged in the light shield and used for providing visible light for the tobacco raw material.
In the system for automatically detecting and removing the impurities in the intelligent cut tobacco provided by the invention, the system also has the following characteristics: a control module, wherein the impurity removing module is provided with a negative pressure impurity removing device, a mechanical arm and an impurity recovery container, the negative pressure impurity removing device is at least provided with a negative pressure machine and a plurality of negative pressure suction heads, the negative pressure machine provides power for all the negative pressure suction heads, the impurity recovery container is connected with the negative pressure suction heads through a pipeline, the negative pressure suction heads are arranged at one end of the mechanical arm, when the first detection model detection unit obtains first impurity position information, the control module controls the mechanical arm above the second conveyor to move according to the first impurity position information, so that the negative pressure suction heads move to the positions above the impurities corresponding to the first impurity position information, the impurities are sucked out and conveyed into the impurity recovery container through the pipeline, when the second detection model detection unit obtains second impurity position information, the control module controls the mechanical arm above the third conveyor to move according to the second impurity position information, therefore, the negative pressure suction head moves to the position above the impurities corresponding to the second impurity position information, the impurities are sucked out and conveyed to the impurity recovery container through a pipeline, when the third detection model detection unit obtains third impurity position information, the control module controls the mechanical arm above the third conveyor to move according to the third impurity position information, the negative pressure suction head moves to the position above the impurities corresponding to the third impurity position information, the impurities are sucked out and conveyed to the impurity recovery container through the pipeline, and therefore impurity removal is completed.
The intelligent automatic detection and removal system for the tobacco shred impurities, provided by the invention, can also have the characteristics that an image corresponding to a tobacco raw material is an original image, and the detection process of the impurity detection module comprises the following steps: step S1-1, mean value suppression processing is carried out on the original image, so that a mean value image with the number of the remaining non-zero pixels smaller than a preset number threshold value in the original image is obtained; step S1-2, segmenting the image after the mean value to obtain a segmented image; step S1-3, detecting the connected domains of the segmented image so as to obtain each connected domain, and calculating the minimum circumcircle of each connected domain; step S1-4, sequentially judging whether the radius of the minimum circumscribed circle is smaller than a preset radius threshold value; and step S1-5, when the judgment in the step S1-4 is negative, the minimum circumcircle is the foreign matter circumcircle, the substance surrounded by the foreign matter circumcircle is the foreign matter, and the position information of the foreign matter is obtained according to the foreign matter circumcircle.
The intelligent automatic detection and removal system for the tobacco shred impurities, provided by the invention, can also have the characteristics that the segmented images are obtained through an OSTU algorithm.
Action and Effect of the invention
According to the intelligent automatic tobacco shred impurity detecting and removing system, the first detecting part detects the tobacco raw material according to the color characteristics and the shape characteristics of the impurities to obtain the first detecting result, so that the impurity removing module can remove the impurities (such as foam, plastic, metal, stone, paper, moldy tobacco, tobacco stems and the like) with colors or contours obviously different from those of tobacco shreds according to the first detecting result. And the second detection part detects the tobacco raw material according to the texture characteristics of the impurities to obtain a second detection result, so that the impurity removing module can remove the impurities (such as hemp ropes, worm cocoons, stem sticks and the like) with the texture obviously different from that of the cut tobacco according to the second detection result. In addition, the third detection part detects the tobacco raw materials according to the spectral characteristics of the impurities to obtain a third detection result, so that the impurity removing module can remove the impurities (such as leaves, grass leaves and the like) with the spectral characteristics obviously different from those of the cut tobacco according to the third detection result to obtain purer cut tobacco, and the tobacco quality is improved.
The intelligent automatic tobacco shred impurity detecting and removing system can automatically remove the impurities such as metal, stone, hemp ropes, paper sheets, worm cocoons, foams, stem sticks, mildewed tobacco leaves, wet mass tobacco shreds and the like in the tobacco raw materials, improves the impurity removing efficiency, saves the labor cost, and also can improve the efficiency of the subsequent cigarette making process and the quality of cigarettes.
Drawings
FIG. 1 is a block diagram of an intelligent automatic detection and removal system for tobacco impurities according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an intelligent automatic detection and removal system for tobacco impurities according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a connection between a control module and other modules according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a first detecting portion according to an embodiment of the present invention;
FIG. 5 is a flow chart of a detection process of an embodiment of the present invention;
FIG. 6 is a schematic diagram of a process for processing a spectral image according to an embodiment of the present invention; and
fig. 7 is a flow chart of the working process of the intelligent automatic detection and removal system for the impurities in the cut tobacco according to the embodiment of the invention.
Detailed Description
In order to make the technical means, creation features, achievement purposes and effects of the invention easy to understand, the original tobacco containing impurities such as metal, stone, hemp ropes, paper sheets, worm cocoons, foams, stem sticks, moldy tobacco leaves and wet mass tobacco shreds is taken as an example, and the intelligent automatic tobacco shred impurity detecting and removing system is specifically described by combining the embodiment and the attached drawings.
< example >
FIG. 1 is a block diagram of an intelligent automatic detection and removal system for tobacco impurities according to an embodiment of the present invention; fig. 2 is a schematic structural diagram of an intelligent automatic detection and removal system for impurities in tobacco shreds according to an embodiment of the present invention, and a portion enclosed by a dashed line frame b in fig. 2 is a top view of a portion enclosed by a dashed line frame a.
As shown in fig. 1 and 2, an intelligent automatic detection and elimination system 1 for impurities in tobacco shreds comprises a tobacco primary screening module 11, a tobacco flattening and transporting module 12, an impurity detection module 13, an impurity elimination module 14 and a control module 15.
The tobacco preliminary screening module 11 can preliminarily screen original tobacco containing different impurities to obtain a tobacco raw material, and has a conveyor 111 for screening and a negative pressure device 112 for screening.
The tobacco flattening transportation module 12 can flatten and transport the tobacco material to the impurity detection module 13, and has a feeding funnel 121, a material dropping device 122, a flattening transportation mechanism 123, and a height limiting mechanism 124.
The impurity detection module 13 can detect and identify impurities in the tobacco raw material to obtain an impurity detection result, where the impurity detection result includes impurity position information. The impurity detection module 13 includes the impurity detection module 13 having a first detection unit 131, a second detection unit 132, and a third detection unit 133. Each of the first, second, and third detection units 131, 132, and 133 has a light shield 1311 and a plurality of light sources 1312.
The first detector 131 further includes a first image acquiring unit 1313 and a first detection pattern detecting unit 1314, the second detector 132 further includes a second image acquiring unit and a second detection pattern detecting unit, and the third detector 133 further includes a third image acquiring unit and a third detection pattern detecting unit.
The impurity removing module 14 removes impurities from the tobacco raw material according to the impurity position information to obtain clean tobacco shreds, and includes a negative pressure impurity removing device 141, a mechanical arm 142, and an impurity recovery container 143.
The negative pressure impurity removing device 141 at least has a negative pressure machine and a plurality of negative pressure suction heads.
The control module 15 can control the operation of the tobacco primary screening module 11, the tobacco flattening and transporting module 12, the impurity detecting module 13 and the impurity removing module 14, and is provided with a PLC (programmable logic controller), a variable frequency motor, a power supply, an overload protector, a relay, a switch, a stepping motor and the like. The PLC controls the running speed of the belt conveyor, the power of the negative pressure machine, the running state of the mechanical arm 142 and the like by controlling the rotating speeds of the variable frequency motor and the stepping motor. The switch controls the start and stop of the whole system, the power supply provides power for the variable frequency motor, the stepping motor and the like, and the overload protector protects the circuit safety so as to avoid the danger of circuit short circuit or overload.
Fig. 3 is a schematic diagram of connection between a control module and other modules according to an embodiment of the present invention.
As shown in fig. 3, the PLC is respectively connected to the variable frequency motor of the belt conveyer of the transportation mechanism 123 for flattening, the negative pressure machine of the negative pressure impurity removing device 141, and the mechanical arm 142, the change of the variable frequency motor directly affects the speed of the conveyor belt of the belt conveyer, and the rotation of the mechanical arm 142 directly drives the rotation of the suction head.
The negative pressure device for screening 112 is disposed above the conveyor for screening 111 (specifically, at the trailing end of the conveyor for screening 111 in the transport direction), and the thickness of the raw tobacco laid on the conveyor for screening 111 is close to the distance between the negative pressure device for screening 112 and the conveyor for screening 111. The negative pressure screening device 112 may be connected to a plurality of tobacco flattening transport modules 12.
In this embodiment, the negative pressure device 112 for screening has at least a negative pressure machine and a negative pressure suction head, the negative pressure machine provides power, the negative pressure suction head is aligned with the original tobacco for suction, and the negative pressure device 112 for screening is connected to the 2 tobacco flattening transportation modules 12. The screening conveyor 111 is a vibrating conveyor.
When the screening is carried to screening below with negative pressure device 112 with conveyer 111 original tobacco, screening is adsorbed with negative pressure device 112 to original tobacco, stays the impurity that the proportion is great (such as impurity such as heavy metal, stone, stalk bamboo slips, wet group pipe tobacco) on screening is with conveyer 111, adsorbs remaining original tobacco (be tobacco raw materials) to pipe tobacco shakeout transportation module to accomplish preliminary screening.
The loading hopper 121 is connected to the negative pressure device 112 for screening, and the negative pressure device 112 for screening conveys the tobacco material into the loading hopper 121, so that the loading hopper 121 can temporarily store the tobacco material.
The feeder 122 is provided at the outlet of the loading hopper 121 so that the tobacco material is kept at a certain thickness (thickness where all the tobacco material is spread out as completely as possible) while it is dropped to the flattening conveyor 123.
The control module 15 adjusts the blanking speed of the blanking device 122, so that the tobacco raw materials can be uniformly spread on the spreading transportation mechanism 123, and the thickness of the tobacco raw materials is ensured to meet the requirement of subsequent detection and identification.
The flattening transport mechanism 123 has a plurality of belt conveyors for transporting the tobacco material and passes through the impurity detection module 13.
The belt conveyer comprises a frame, a conveying belt, a belt driving roller, a belt driven roller, a tensioning device, a transmission device, a speed reduction motor and the like. The speed reducing motor is used for driving and can realize frequency conversion and speed regulation. The conveying belt can be additionally provided with accessories such as a height limiting mechanism 124, a skirt edge and the like. Limit for height mechanism 124 is used for adjusting material thickness, and the shirt rim is used for protecting the material, prevents the leakage and the waste of material.
In this embodiment, the transport mechanism 123 for flattening has 5 belt conveyors in total, and the first conveyor 1231 is provided below the loading hopper 121, the second conveyor 1232 is provided below the first detection unit 131, the third conveyor 1233 is provided below the second detection unit 132, the fourth conveyor 1234 is provided below the third detection unit 133, and the fifth conveyor 1235 is provided behind the fourth conveyor 1234, and is used for transporting clean tobacco shreds.
The heights of the first conveyor 1231, the second conveyor 1232, the third conveyor 1233, and the fourth conveyor 1234 decrease in sequence, and when the tobacco material rolls from the previous conveyor to the next conveyor, the lower surface material of the previous conveyor can roll to the upper surface of the next conveyor.
In addition, the transmission speeds of the first conveyor 1231, the second conveyor 1232, the third conveyor 1233 and the fourth conveyor 1234 are sequentially increased, so that the adjacent tobacco raw materials can be further separated, stacking and shielding are avoided, and the accuracy of subsequent detection is improved. The above-mentioned transmission speed can be adjusted.
The height limiting mechanism 124 is disposed above the leveling transport mechanism 123, and can level out the tobacco material having a height higher than a predetermined height threshold (i.e., overlapped tobacco material).
Fig. 4 is a schematic structural diagram of a first detecting portion according to an embodiment of the present invention.
As shown in fig. 4, a light shield 1311 is suspended on the transportation mechanism 123 for flattening, and is kept at a predetermined distance from the belt conveyer, so as to shield the tobacco raw material from external natural light, a light source 1312 is disposed in the light shield 1311 and provides visible light for the tobacco raw material, a first image acquisition unit 1313 is disposed above the second transportation machine 1232, the acquired first image is transmitted to a first detection model detection unit 1314 through a network cable, and the first detection model detection unit 1314 is located at a PC end.
The negative pressure machine provides power for all negative pressure suction heads in a negative pressure extraction mode, the impurity recovery container 143 is connected with all negative pressure suction heads through pipelines, and the negative pressure suction heads are arranged at one end of the mechanical arm 142.
The first image acquiring unit 1313 acquires an RGB image of the tobacco raw material as a first image by a camera disposed above the tobacco raw material.
The first detection model detection unit 1314 detects the first image through a first impurity detection model trained in advance according to the color and shape characteristics, thereby obtaining a first detection result, which includes first impurity position information.
The control module 15 controls the mechanical arm 142 above the second conveyor 1232 to move according to the first impurity position information, so that the negative pressure suction head moves to the position above the impurity corresponding to the first impurity position information, the impurity is sucked out and conveyed to the impurity recovery container 143 through a pipeline, and the remaining tobacco raw material is the raw material after primary removal.
The second image acquisition unit acquires a plurality of RGB images of the primarily rejected raw materials from different angles as second images by a plurality of cameras disposed above the tobacco raw materials (i.e., the primarily rejected raw materials).
In this embodiment, the second image obtaining unit obtains, as the second image, a plurality of RGB images of the raw material after the primary removal from different angles by using 3 cameras.
And the second detection model detection unit detects all the second images through a pre-trained second impurity detection model according to the texture characteristics so as to obtain a plurality of second detection results, wherein the second detection results comprise second impurity position information.
The control module 15 controls the mechanical arm 142 above the third conveyor 1233 to move according to the second impurity position information, so that the negative pressure suction head moves to the position above the impurity corresponding to the second impurity position information, the impurity is sucked out and conveyed to the impurity recovery container 143 through a pipeline, and the remaining raw material after primary removal is the raw material after secondary removal.
The third image acquisition unit acquires a spectral image of the tobacco raw material (i.e., the secondarily-removed raw material) as a third image.
And the third detection model detection unit detects the third image through a pre-trained third impurity detection model according to the spectral characteristics so as to obtain a third detection result, wherein the third detection result comprises third impurity position information.
The control module 15 controls the mechanical arm 142 above the third conveyor 1233 to move according to the third impurity position information, so that the negative pressure suction head moves to the position above the impurity corresponding to the third impurity position information, the impurity is sucked out and conveyed to the impurity recovery container 143 through a pipeline, the impurity removal is completed, and the residual raw material after the secondary removal is clean cut tobacco.
In addition, the clean tobacco shreds in the impurity recovery container 143 can be further manually picked to mix the mistakenly-picked tobacco shreds back into the products, or automatically conveyed to the vibrating conveyor 111 to perform secondary impurity identification and elimination, so that the mistaken picking rate is reduced.
FIG. 5 is a flow chart of a detection process of an embodiment of the present invention; fig. 6 is a schematic diagram of a processing procedure of a spectral image according to an embodiment of the present invention.
The images corresponding to the tobacco material in each of the first detection model detection unit 1314, the second detection model detection unit, and the third detection model are all referred to as original images. Meanwhile, the detection process of each detection unit is the same, and as shown in fig. 5 specifically, the method includes the following steps:
in step S1-1, an original image (for example, the spectral image in the detection process of the third detection model detection unit, as shown in fig. 6 (a)) is subjected to a mean suppression process, so as to obtain a mean image (as shown in fig. 6 (b)) in which the number of remaining non-zero pixels in the original image is smaller than a predetermined number threshold.
In step S1-2, the image after the mean value is segmented to obtain a segmented image (as shown in fig. 6 (c)).
Wherein, the segmented image is obtained by an OSTU algorithm.
And step S1-3, detecting the connected domains of the segmented image to obtain each connected domain, and calculating the minimum circumcircle of each connected domain.
And S1-4, sequentially judging whether the radius of the minimum circumscribed circle is smaller than a preset radius threshold, if not, entering S1-5, and if so, re-entering S1-4 to judge the next minimum circumscribed circle.
Step S1-5, the minimum circumscribed circle is an impurity circumscribed circle, the substance surrounded by the impurity circumscribed circle is an impurity, the impurity position information is obtained according to the impurity circumscribed circle (as shown in fig. 6(d), the white circle in fig. 6(d) is the impurity circumscribed circle), and then the end state is entered.
Fig. 7 is a flow chart of the working process of the intelligent automatic detection and removal system for the impurities in the cut tobacco according to the embodiment of the invention.
As shown in fig. 7, the working process of the intelligent automatic tobacco shred impurity detecting and removing system comprises the following steps:
step S2-1, the control module 15 controls the movement of the screening conveyor 111 to convey the original tobacco to the lower part of the screening negative pressure device 112, the screening negative pressure device 112 adsorbs the lighter raw materials in the original tobacco to the feeding hopper 121 as tobacco raw materials, and then the step S2-2 is performed;
step S2-2, the control module 15 controls the operation speed of the material falling device 122, so that the tobacco material in the feeding funnel 121 falls on the first conveyor 1231 according to the preset falling flow rate, and then the height limiting mechanism 124 further flattens the tobacco material with the ultrahigh thickness flattened on the first conveyor 1231, and then the step S2-3 is performed;
step S2-3, the control module 15 controls the first image obtaining unit 1313 to obtain RGB images of the tobacco raw material as a first image through the camera, and then proceeds to step S2-4;
in step S2-4, the control module 15 controls the first detection pattern detecting unit 1314 to detect the first image through the first foreign object detection pattern according to the color and shape characteristics, thereby obtaining a first detection result including position information of the first foreign object, and then proceeds to step S2-5;
step S2-5, the control module 15 controls the mechanical arm 142 located above the second transporter 1232 to move according to the first impurity position information, so that the corresponding negative pressure suction head moves above the impurity, thereby sucking out the impurity and transporting the impurity to the impurity recovery container 143 through the pipeline, and then the process goes to step S2-6;
step S2-6, the control module 15 controls the second image obtaining unit to obtain a plurality of RGB images of different angles of the tobacco material conveyed by the first conveyor 1231 as second images through the camera, and then the process goes to step S2-7;
step S2-7, the control module 15 controls the second detection model detection unit to detect all the second images through the second impurity detection model according to the texture features, so as to obtain a second detection result including the position information of the second impurities, and then the step S2-8 is performed;
step S2-8, the control module 15 controls the mechanical arm 142 located above the third conveyer 1233 to move according to the second impurity position information, so that the corresponding negative pressure suction head moves above the impurity, thereby sucking out and transporting the impurity to the impurity recovery vessel 143 through the pipeline, and then proceeds to step S2-9;
step S2-9, the control module 15 controls the third image obtaining unit to obtain the spectral image of the tobacco material conveyed from the fourth conveyor 1234 as a third image, and then proceeds to step S2-10;
step S2-10, the control module 15 controls the third detection model detection unit to detect the third image through the pre-trained third impurity detection model according to the spectral characteristics, so as to obtain a third detection result including the position information of the third impurity, and then the step S2-11 is performed;
step S2-11, the control module 15 controls the robot arm 142 located above the third conveyer 1233 to move according to the third impurity position information, so that the negative pressure suction head moves above the impurity, sucks out the impurity and conveys the impurity to the impurity recovery vessel 143 through the pipeline, and then proceeds to step S2-12;
at step S2-12, the control module 15 controls the fourth conveyor 1234 to convey the tobacco material as cut tobacco to the fifth conveyor 1235, and then enters an end state.
Examples effects and effects
According to the intelligent automatic tobacco shred impurity detecting and removing system provided by the embodiment, the first detecting part detects the tobacco raw material according to the color characteristic and the shape characteristic of the impurity to obtain a first detecting result, so that the impurity removing module can remove the impurity (such as foam, plastic, metal, stone, paper, mildewed tobacco, tobacco stems and the like) with the color or the outline obviously different from that of tobacco shreds according to the first detecting result. And the second detection part detects the tobacco raw material according to the texture characteristics of the impurities to obtain a second detection result, so that the impurity removing module can remove the impurities (such as hemp ropes, worm cocoons, stem sticks and the like) with the texture obviously different from that of the cut tobacco according to the second detection result. In addition, the third detection part detects the tobacco raw materials according to the spectral characteristics of the impurities to obtain a third detection result, so that the impurity removing module can remove the impurities (such as leaves, grass leaves and the like) with the spectral characteristics obviously different from those of the cut tobacco according to the third detection result to obtain purer cut tobacco, and the tobacco quality is improved.
In the embodiment, the negative pressure device 112 for screening uses the raw material with a lighter specific gravity in the original tobacco as the tobacco raw material, and conveys the tobacco raw material to the feeding hopper 121, so that impurities with a larger specific gravity (such as stones, metal, stems, wet mass cut tobacco, and the like) can be removed, and the primary screening is completed. Also, since the material falling device 122 can control the falling flow rate of the tobacco material, the height limiting mechanism 124 can limit the thickness of the tobacco material spread on the belt conveyor, so that the tobacco material can be completely spread on the belt conveyor, thereby enabling the impurity detecting module 13 to detect all impurities in the tobacco material.
In an embodiment, because the height that first conveyer 1231, second conveyer 1232, third conveyer 1233 and fourth conveyer 1234 correspond reduces in proper order, the transmission speed that corresponds accelerates in proper order, consequently, can realize the upper and lower layer of material and roll with adjacent pipe tobacco separation, avoid piling up and sheltering from of pipe tobacco to the detection of impurity detection module 13 of being convenient for.
In the embodiment, the second image acquisition unit acquires the RGB images of the tobacco raw materials from different angles through the 3 cameras, so that enough texture characteristics of the tobacco raw materials can be acquired, and the second detection model detection unit can detect the impurities with the textures obviously different from those of the cut tobacco.
In the embodiment, since each of the first, second, and third detection parts 131, 132, and 133 further includes a light shield 1311 for shielding natural light from the outside and a light source 1312 for providing visible light, the first, second, and third image acquisition units 1313, 132, and 133 can acquire high-quality images.
In the embodiment, the control module 15 moves the corresponding mechanical arm 142 according to the first impurity position information, the second impurity position information and the third impurity position information, so that the negative pressure suction head moves to the upper side of the corresponding impurity and adsorbs the impurity to the impurity recovery container 143, and therefore, the negative pressure suction head can be accurately positioned above the impurity to complete the removal and recovery of the impurity.
In the embodiment, the negative pressure device 112 for screening is connected with the 2 tobacco flattening and transporting modules 12, so that a large amount of tobacco raw materials are detected and removed in a shunting manner, and the working efficiency of impurity removal is greatly improved.
In the above embodiment, the negative pressure device 112 for screening is connected to 2 tobacco flattening transportation modules 12, in other aspects of the present invention, the negative pressure device 112 for screening may also be connected to 1 or more tobacco flattening transportation modules 12, so as to meet the impurity identification and elimination requirements of production lines with different material flows, and for production lines with large material flows, a plurality of tobacco flattening transportation modules 12 may be configured, thereby improving the detection and elimination efficiency of tobacco raw materials.
In the above embodiment, the detection is performed by the first detection part 131, the second detection part 132 and the third detection part 132, but in other aspects of the present invention, only one or two detection parts may be configured to perform automatic detection and removal of the tobacco impurities according to the requirement of detecting the purity of the material.

Claims (8)

1. The utility model provides an intelligent shredded tobacco impurity automated inspection and rejection system which characterized in that includes:
the impurity detection module is used for detecting impurities in the tobacco raw materials so as to obtain an impurity detection result through detection, and the impurity detection result comprises the position information of the impurities; and
an impurity removing module for removing the impurities from the tobacco raw materials according to the impurity position information to obtain clean tobacco shreds,
wherein the impurity detection module is provided with a first detection part, a second detection part and a third detection part,
the first detection part detects the tobacco raw material according to the color characteristic and the shape characteristic of the impurities so as to obtain a first detection result,
the second detection part detects the tobacco raw material according to the texture characteristics of the impurities so as to obtain a second detection result,
the third detection part detects the tobacco raw material according to the spectral characteristics of the impurities so as to obtain a third detection result,
and the impurity removing module removes the impurities according to the first detection result, the second detection result and the third detection result respectively.
2. The intelligent automatic tobacco shred impurity detecting and removing system according to claim 1, further comprising:
the tobacco primary screening module is used for primarily screening original tobacco containing different impurities to obtain the tobacco raw material; and
a tobacco flattening and transporting module used for flattening the tobacco raw material and transporting the tobacco raw material to the impurity detecting module,
wherein the tobacco primary screening module is provided with a conveyor for screening and a negative pressure device for screening,
the tobacco shred flattening and transporting module is provided with a feeding funnel, a blanking device, a flattening transporting mechanism and a height limiting mechanism,
the blanking device is arranged at the outlet of the feeding funnel, the height limiting mechanism is arranged near the flattening conveying mechanism,
the screening conveyor is used for conveying the original tobacco to the position below the screening negative pressure device,
the negative pressure device for screening absorbs the raw material with smaller specific gravity in the original tobacco as the tobacco raw material and conveys the tobacco raw material to the feeding hopper,
the blanking device is used for controlling the falling flow of the tobacco raw material so as to ensure that the tobacco raw material is uniformly flattened on the flattening conveying mechanism,
the flattening transport mechanism has a plurality of conveyors for transporting the tobacco material and passing through the first detection unit, the second detection unit, and the third detection unit,
the height limiting mechanism is used for spreading out the overlapped tobacco raw materials, so that the tobacco raw materials are completely flattened.
3. The intelligent automatic tobacco shred impurity detecting and removing system according to claim 2, wherein the system comprises:
wherein the flattening conveying mechanism is at least provided with 4 conveyors which are respectively a first conveyor, a second conveyor, a third conveyor and a fourth conveyor,
the first conveyor is positioned below the blanking device, the second conveyor is positioned below the first detection part, the third conveyor is positioned below the second detection part, and the fourth conveyor is positioned below the third detection part,
the heights corresponding to the first conveyor, the second conveyor, the third conveyor and the fourth conveyor are reduced in sequence, and the corresponding transmission speeds are accelerated in sequence.
4. The intelligent automatic tobacco shred impurity detecting and removing system according to claim 3, wherein the system comprises:
wherein the first detection part at least has a first image acquisition unit and a first detection model detection unit,
the second detection unit has at least a second image acquisition unit and a second detection model detection unit,
the third detecting section has at least a third image acquiring unit and a third detection model detecting unit,
the first image acquiring unit acquires an RGB image of the tobacco raw material as a first image by a camera disposed above the tobacco raw material,
the first detection model detection unit detects the first image through a first impurity detection model trained in advance according to the color and shape characteristics so as to obtain a first detection result, wherein the first detection result comprises first impurity position information,
the second image acquiring unit acquires a plurality of RGB images of the tobacco raw material from different angles as second images by a plurality of cameras disposed above the tobacco raw material,
the second detection model detection unit detects all the second images through a second impurity detection model trained in advance according to the texture features so as to obtain a second detection result, wherein the second detection result comprises second impurity position information,
the third image acquisition unit acquires a spectral image of the tobacco raw material as a third image,
and the third detection model detection unit detects the third image through a third impurity detection model trained in advance according to the spectral characteristics so as to obtain a third detection result, wherein the third detection result comprises third impurity position information.
5. The intelligent automatic tobacco shred impurity detecting and removing system according to claim 4, wherein the system comprises:
the first detection part, the second detection part and the third detection part are all provided with a light shield used for shielding the tobacco raw material from external natural light and a plurality of light sources which are arranged in the light shield and used for providing visible light for the tobacco raw material.
6. The intelligent automatic tobacco shred impurity detecting and removing system according to claim 4, further comprising:
a control module for controlling the operation of the electronic device,
wherein the impurity removing module is provided with a negative pressure impurity removing device, a mechanical arm and an impurity recovery container, the negative pressure impurity removing device is at least provided with a negative pressure machine and a plurality of negative pressure suction heads,
the negative pressure machine provides power for all the negative pressure suction heads, the impurity recovery container is connected with the negative pressure suction heads through a pipeline, the negative pressure suction heads are arranged at one end of the mechanical arm,
when the first detection model detection unit obtains the first impurity position information, the control module controls the mechanical arm positioned above the second conveyor to move according to the first impurity position information, so that the negative pressure suction head moves to the position above the impurity corresponding to the first impurity position information, sucks the impurity out of the impurity and conveys the impurity into the impurity recovery container through the pipeline,
when the second detection model detection unit obtains the second impurity position information, the control module controls the mechanical arm above the third conveyor to move according to the second impurity position information, so that the negative pressure suction head moves to the position above the impurity corresponding to the second impurity position information, sucks the impurity out of the impurity collection container and conveys the impurity into the impurity collection container through the pipeline,
when the third detection model detection unit obtains the third impurity position information, the control module controls the mechanical arm above the third conveyor to move according to the third impurity position information, so that the negative pressure suction head moves to the position above the impurity corresponding to the third impurity position information, the impurity is sucked out and conveyed to the impurity recovery container through the pipeline, and the impurity removal is completed.
7. The intelligent automatic tobacco shred impurity detecting and removing system according to claim 1, wherein the system comprises:
wherein, the image corresponding to the tobacco raw material is an original image,
the detection process of the impurity detection module comprises the following steps:
step S1-1, mean value suppression processing is carried out on the original image, so that a mean value image with the number of the remaining non-zero pixels smaller than a preset number threshold value in the original image is obtained;
step S1-2, segmenting the image after the mean value to obtain an image after segmentation;
step S1-3, detecting connected domains of the segmented image to obtain each connected domain, and calculating the minimum circumcircle of each connected domain;
step S1-4, whether the radius of the minimum circumcircle is smaller than a preset radius threshold value is sequentially judged;
and S1-5, when the judgment in the step S1-4 is negative, the minimum circumscribed circle is an impurity circumscribed circle, the substance surrounded by the impurity circumscribed circle is an impurity, and the impurity position information is obtained according to the impurity circumscribed circle.
8. The intelligent automatic tobacco shred impurity detecting and removing system according to claim 7, wherein the system comprises:
and obtaining the segmented image through an OSTU algorithm.
CN202110813239.0A 2021-07-19 2021-07-19 Intelligent automatic tobacco shred impurity detecting and removing system Pending CN113533349A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110813239.0A CN113533349A (en) 2021-07-19 2021-07-19 Intelligent automatic tobacco shred impurity detecting and removing system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110813239.0A CN113533349A (en) 2021-07-19 2021-07-19 Intelligent automatic tobacco shred impurity detecting and removing system

Publications (1)

Publication Number Publication Date
CN113533349A true CN113533349A (en) 2021-10-22

Family

ID=78100166

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110813239.0A Pending CN113533349A (en) 2021-07-19 2021-07-19 Intelligent automatic tobacco shred impurity detecting and removing system

Country Status (1)

Country Link
CN (1) CN113533349A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114088639A (en) * 2021-10-27 2022-02-25 江苏大学 Pulse spectrum online imaging detection method and device for low-chromaticity-difference plastic foreign matters of tobacco shreds
CN115039905A (en) * 2022-06-21 2022-09-13 云南中烟工业有限责任公司 Method for removing stems in finished cut tobacco based on fusion of flexible winnowing and image recognition

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000028544A (en) * 1998-07-08 2000-01-28 Japan Tobacco Inc Near-infrared ray type foreign material inspection device
CN103211292A (en) * 2013-03-20 2013-07-24 湖南中烟工业有限责任公司 Equipment and method for sectional fine sorting of tobacco sheets
CN103801514A (en) * 2014-01-25 2014-05-21 湖南中烟工业有限责任公司 Device and method for automatically selecting tobacco leaves for producing cut tobacco
CN104655652A (en) * 2013-11-25 2015-05-27 王健 Machine vision-based tobacco impurity sorting and rejecting system
CN107296297A (en) * 2016-07-01 2017-10-27 廖鲁昕 A kind of tobacco impurities identification, eliminating system and method based on exciting light
CN107824456A (en) * 2017-11-24 2018-03-23 云南省烟草烟叶公司 A kind of beating and double roasting tobacco product debris detection means and method
CN112189877A (en) * 2020-10-13 2021-01-08 燕山大学 On-line detection method for tobacco shred impurities in tobacco production line
CN112730445A (en) * 2021-01-19 2021-04-30 红云红河烟草(集团)有限责任公司 Tobacco shred sundry visual image detection system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000028544A (en) * 1998-07-08 2000-01-28 Japan Tobacco Inc Near-infrared ray type foreign material inspection device
CN103211292A (en) * 2013-03-20 2013-07-24 湖南中烟工业有限责任公司 Equipment and method for sectional fine sorting of tobacco sheets
CN104655652A (en) * 2013-11-25 2015-05-27 王健 Machine vision-based tobacco impurity sorting and rejecting system
CN103801514A (en) * 2014-01-25 2014-05-21 湖南中烟工业有限责任公司 Device and method for automatically selecting tobacco leaves for producing cut tobacco
CN107296297A (en) * 2016-07-01 2017-10-27 廖鲁昕 A kind of tobacco impurities identification, eliminating system and method based on exciting light
CN107824456A (en) * 2017-11-24 2018-03-23 云南省烟草烟叶公司 A kind of beating and double roasting tobacco product debris detection means and method
CN112189877A (en) * 2020-10-13 2021-01-08 燕山大学 On-line detection method for tobacco shred impurities in tobacco production line
CN112730445A (en) * 2021-01-19 2021-04-30 红云红河烟草(集团)有限责任公司 Tobacco shred sundry visual image detection system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114088639A (en) * 2021-10-27 2022-02-25 江苏大学 Pulse spectrum online imaging detection method and device for low-chromaticity-difference plastic foreign matters of tobacco shreds
CN114088639B (en) * 2021-10-27 2023-11-10 江苏大学 Pulse spectrum online imaging detection method and device for low-chroma-difference plastic foreign matters in cut tobacco
CN115039905A (en) * 2022-06-21 2022-09-13 云南中烟工业有限责任公司 Method for removing stems in finished cut tobacco based on fusion of flexible winnowing and image recognition

Similar Documents

Publication Publication Date Title
CN113533349A (en) Intelligent automatic tobacco shred impurity detecting and removing system
US9486008B2 (en) System for topping and tailing lettuce heads using a camera-guided servo-controlled water knife
CN106124520A (en) A kind of full-automatic loading and unloading and the device of vision-based detection
CN103008249A (en) Mushroom grader based on computer vision technology
CN109374635A (en) A kind of mask defect detecting device and method
CN211100241U (en) A removing devices for flaw visual detection
CN104062298A (en) Device and method for automatically monitoring impurity rate of grains in grain tank of combine harvester based on image processing
CN112067617A (en) Automatic detection equipment and detection method for quality of finished product cigarette
CN204107867U (en) A kind of bottle cap defect detecting device
CN107594606A (en) A kind of beating and double roasting station-service lift piece cigarette on-line period detection means and method
CN202385685U (en) Tea color sorting machine
CN107350173A (en) A kind of Chinese chestnut automatic sorting device and method for sorting
CN208000278U (en) The smoke box appearance delection device recycled for smoke box
CN208972665U (en) A kind of quick-fried pearl filter stick detection device for eliminating and receiver
CN212328944U (en) Machine vision combines goods sorting facilities of laser and system thereof
CN205284974U (en) Online smoked sheet automatic separation device of air -sweeping type
CN208361506U (en) Carton production line automatic counting feeding-distribution device
CN210098270U (en) Green plum sorting equipment
CN208728059U (en) Flat bar intelligent vision separation system
CN210059036U (en) Online detection and elimination equipment for quick-frozen green soybean defective products
CN206095923U (en) Spectrum shaker video cabinet mirror head, automatic device that sweeps of reflector panel
CN117225735B (en) Board grading visual inspection conveying equipment and method thereof
CN219295803U (en) Short angle bead collection device
CN110170449B (en) Intelligent cleaning production line and cleaning method for traditional Chinese medicine decoction pieces
CN214622370U (en) Emulsion pump cover defect detecting machine based on machine vision detection technology

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