CN115281365A - Sundry detection system and sundry detection method - Google Patents
Sundry detection system and sundry detection method Download PDFInfo
- Publication number
- CN115281365A CN115281365A CN202210922167.8A CN202210922167A CN115281365A CN 115281365 A CN115281365 A CN 115281365A CN 202210922167 A CN202210922167 A CN 202210922167A CN 115281365 A CN115281365 A CN 115281365A
- Authority
- CN
- China
- Prior art keywords
- tobacco
- adjacent
- debris
- cut tobacco
- stages
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 61
- 241000208125 Nicotiana Species 0.000 claims abstract description 165
- 235000002637 Nicotiana tabacum Nutrition 0.000 claims abstract description 165
- 239000012535 impurity Substances 0.000 claims abstract description 64
- 238000000034 method Methods 0.000 claims description 12
- 239000000463 material Substances 0.000 claims description 10
- 238000013473 artificial intelligence Methods 0.000 claims description 9
- 239000000779 smoke Substances 0.000 claims description 9
- 239000011521 glass Substances 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 description 10
- 235000019504 cigarettes Nutrition 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 229920001971 elastomer Polymers 0.000 description 3
- 230000002349 favourable effect Effects 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 239000004033 plastic Substances 0.000 description 3
- 229920003023 plastic Polymers 0.000 description 3
- 239000005060 rubber Substances 0.000 description 3
- 239000004677 Nylon Substances 0.000 description 2
- 208000003464 asthenopia Diseases 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010924 continuous production Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000001035 drying Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000007667 floating Methods 0.000 description 2
- 239000006260 foam Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 229920001778 nylon Polymers 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 239000000945 filler Substances 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24B—MANUFACTURE OR PREPARATION OF TOBACCO FOR SMOKING OR CHEWING; TOBACCO; SNUFF
- A24B3/00—Preparing tobacco in the factory
- A24B3/16—Classifying or aligning leaves
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24B—MANUFACTURE OR PREPARATION OF TOBACCO FOR SMOKING OR CHEWING; TOBACCO; SNUFF
- A24B3/00—Preparing tobacco in the factory
- A24B3/18—Other treatment of leaves, e.g. puffing, crimpling, cleaning
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The present disclosure relates to a foreign matter detection system and a foreign matter detection method for detecting foreign matters in tobacco shreds, the foreign matter detection system comprising: the cut tobacco conveying mechanism comprises a plurality of stages of conveying devices (1), wherein cut tobacco (2) is conveyed between two adjacent stages of conveying devices (1) in the plurality of stages of conveying devices (1), and the end parts of the adjacent ends of at least part of the two adjacent stages of conveying devices (1) in the plurality of stages of conveying devices (1) have height difference; an image pickup device (3) disposed adjacent to a region between adjacent two stages of the multi-stage conveying devices (1); a processor (4) in signal connection with the image acquisition device (3) configured to: and when the cut tobacco (2) falls to the lower conveying device (1) from the higher conveying device (1) in the two adjacent conveying devices (1), the image acquisition device (3) acquires cut tobacco images and identifies impurities (5) in the cut tobacco (2) according to the cut tobacco images.
Description
Technical Field
The disclosure relates to the technical field of tobacco shred impurity removal, in particular to a impurity detection system and a impurity detection method.
Background
Various non-vegetable impurities such as rubber, plastic, nylon, foam and the like are often found in the cut tobacco shred production process. If the sundries are drawn into the cigarettes, the peculiar smell can be released when the consumers ignite the cigarettes, and therefore poor taste is brought, and the sundries in the tobacco shreds are controlled to be an important link in the cigarette production process.
Disclosure of Invention
The inventor finds that in the related technology, the cut tobacco and impurities after cutting the tobacco into shreds are only about 1mm × 5mm, the visual identification difficulty is high, the impurity selection is mainly completed manually, the labor cost required for selecting and screening the fine impurities in the cut tobacco is high, and the identification and removal effect and efficiency are not high; the field working environment is not good, the dust is heavy and the noise is large, the batch continuous production time is long, the working content is boring, the visual fatigue of operators is easy to generate, and the impurity picking effect after the cut tobacco sections are cut is influenced.
In view of this, the embodiments of the present disclosure provide a foreign matter detection system and a foreign matter detection method, which are helpful for improving the accuracy of detecting foreign matters in tobacco shreds.
In one aspect of the present disclosure, there is provided a foreign matter detection system for detecting foreign matters in tobacco shreds, including:
the tobacco shred conveying mechanism comprises a multi-stage conveying device, tobacco shreds are conveyed between two adjacent stages of conveying devices in the multi-stage conveying device, and height difference exists between the end parts of the adjacent ends of at least part of the two adjacent stages of conveying devices in the multi-stage conveying device;
the image acquisition device is arranged adjacent to the area between two adjacent stages of conveying devices in the multi-stage conveying devices;
a processor in signal connection with the image acquisition device configured to:
when the cut tobacco falls to a lower conveying device in a higher conveying device in two adjacent conveying devices, the image acquisition device acquires cut tobacco images and identifies impurities in the cut tobacco according to the cut tobacco images.
In some embodiments, the tobacco filler has a density of ρ kg/m 3 The thickness of the end of the higher conveying device in the two adjacent conveying devices when the end is thrown out is tm, the width of the higher conveying device in the two adjacent conveying devices is wm, and the conveying speed is vm/s;
wherein the content of the first and second substances,
k satisfies: k =1 to 3kg/s.
In some embodiments, the conveying speed v of the higher conveyor of two adjacent stages satisfies: v =0.5 to 2, and the width w satisfies: w =0.5 to 1.
In some embodiments, the product w x v of the width and the conveying speed of the higher conveyor of two adjacent stages satisfies: w × v =0.727.
In some embodiments, the conveying speed v of the higher conveyor of two adjacent stages satisfies: v =1, the width w satisfies: w =0.727.
In some embodiments, the height difference of the end portions of the adjacent ends of the adjacent two stages of conveyors is Hcm, and the height difference H satisfies: h =15 to 20.
In some embodiments, the height difference H between the ends of adjacent ends of two adjacent stages of conveyors satisfies: h =18.
In some embodiments, the processor is further configured to: and enabling the image acquisition device to acquire the tobacco shred image at least comprising the tobacco shred which is at the highest point in the falling process between the two adjacent stages of conveying devices.
In some embodiments, the image capture device comprises a camera having a light receiving area that at least partially coincides with an area between adjacent stages of the conveyor.
In some embodiments, the image capture device further comprises a light source disposed around an area between adjacent stages of the conveyor.
In some embodiments, the number of light sources is two, and a centerline of the optical axis of the camera passes through a range between the two light sources.
In some embodiments, the light source comprises a linear light source disposed parallel to the width direction of the conveyor.
In some embodiments, the image capture device further comprises a housing, the ends of the adjacent ends of adjacent two-stage conveyors, the camera and the light source being disposed within the housing.
In some embodiments, the outer wall of the enclosure comprises glass.
In some embodiments, the processor is configured to:
sundries in the tobacco shred images are identified by establishing and training a non-tobacco sundry artificial intelligent model.
In some embodiments, the artificial intelligence model of non-smoke inclusions includes color and/or shape characteristics of the cut tobacco and inclusions.
In some embodiments, the debris detection system further comprises:
the alarm device is in signal connection with the processor;
wherein the processor is configured to:
when the sundries are identified, the alarm device gives an alarm.
In some embodiments, the debris detection system further comprises:
the rejecting device is in signal connection with the processor;
wherein the processor is configured to:
and when the sundries are identified, the removing device removes the sundries.
In another aspect of the present disclosure, a method for detecting impurities based on any one of the above impurity detection systems is provided, including:
acquiring a cut tobacco image when cut tobacco falls to the starting end of a lower conveying device from the tail end of a higher conveying device in two adjacent stages of conveying devices through an image acquisition device;
and identifying impurities in the tobacco shreds according to the tobacco shred images.
In some embodiments, the operation of acquiring the cut tobacco image specifically includes:
and acquiring a cut tobacco image at least comprising the highest point of the cut tobacco in the falling process between the two adjacent stages of conveying devices through an image acquisition device.
In some embodiments, the operation of identifying the impurities in the cut tobacco image specifically includes:
calling a non-smoke impurity artificial intelligent model;
classifying the tobacco shreds and impurities in the tobacco shred images;
and outputting a classification result, and determining impurities in the tobacco shreds.
In some embodiments, the debris detection method further comprises:
and extracting the topological structure of the tobacco shred image.
In some embodiments, the debris detection method further comprises:
and adjusting parameters of the artificial intelligent model of the non-smoke impurities according to the recognition result.
In some embodiments, the debris detection method further comprises:
when the sundries are identified, the alarm device gives an alarm.
In some embodiments, the debris detection method further comprises:
and when the sundries are identified, the sundries are removed through a removing device.
Therefore, according to the embodiment of the disclosure, by arranging the adjacent two-stage conveying devices with the height difference, when the cut tobacco falls to the head end of the lower conveying device from the tail end of the higher conveying device, the cut tobacco is in a floating and scattering state and becomes looser, the image of the cut tobacco with smaller thickness and density at the moment is collected, and the image of the cut tobacco is visually identified, so that the detection and identification efficiency and accuracy of impurities in the cut tobacco are favorably improved, the purity of the cut tobacco is effectively improved, and the product quality of the cut tobacco in the whole batch is ensured. In addition, the times of manual impurity picking can be reduced, the water dispersion and the crushing amount of the cut tobacco are reduced, and the risk of more impurities mixed due to repeated impurity picking is reduced.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure may be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:
FIG. 1 is a schematic block diagram of some embodiments of a debris detection system according to the present disclosure;
FIG. 2 is a side view of some embodiments of a debris detection system according to the present disclosure;
FIG. 3 is a connection diagram of some embodiments of a debris detection system according to the present disclosure;
FIG. 4 is a schematic block diagram of further embodiments of debris detection systems according to the present disclosure;
FIG. 5 is a partial schematic view of some embodiments of a debris detection system according to the present disclosure;
fig. 6 is a flow chart of some embodiments of a debris detection method according to the present disclosure.
It should be understood that the dimensions of the various parts shown in the figures are not drawn to scale. Further, the same or similar reference numerals denote the same or similar components.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is in no way intended to limit the disclosure, its application, or uses. The present disclosure may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that: the relative arrangement of parts and steps, the composition of materials, numerical expressions and numerical values set forth in these embodiments are to be construed as merely illustrative, and not as limitative, unless specifically stated otherwise.
The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element preceding the word covers the element listed after the word, and does not exclude the possibility that other elements are also covered. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
In the present disclosure, when a specific device is described as being located between a first device and a second device, there may or may not be intervening devices between the specific device and the first device or the second device. When a particular device is described as being coupled to other devices, that particular device may be directly coupled to the other devices without intervening devices or may be directly coupled to the other devices with intervening devices.
All terms (including technical or scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs unless specifically defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
The existing impurity removing equipment in a workshop comprises a blade impurity remover, a metal detector before shredding, a winnowing device after drying cut tobacco and the like, wherein the removing rate of the blade impurity remover is about 85 percent, the wire metal detector only acts on metal objects, and the winnowing device after drying cut tobacco cannot remove light objects such as plastics or rubber, so that the condition that non-tobacco impurities 5 are mixed into the cut tobacco 2 still exists.
In the related technology, the impurity picking after the tobacco shred sections are shredded is mainly completed manually, high labor cost is required for selecting and screening the fine impurities 5 in the tobacco shreds 2, and the effect and efficiency of identifying and rejecting are not high. Due to poor working environment, heavy dust and large noise, long batch continuous production time and dull working content, visual fatigue of operators is easily caused, and the impurity picking efficiency and precision of shredded tobacco leaf segments are influenced. In addition, different from traditional blade segment impurity removal equipment and technology, shredded tobacco shred 2 and sundries 5 are only about 1mm × 5mm generally, the visual identification granularity is very small, the tobacco shred 2 material layer above the vibration groove is thick after shredding, the thickness is about 6-10cm, the related identification technology can only effectively identify the sundries 5 on the surface of the tobacco shred 2, the sundries 5 in the tobacco shred 2 material layer cannot be effectively detected, and the sundries 5 omission risk is caused to a certain degree.
In view of this, referring to fig. 1 to 3, an embodiment of the present disclosure provides a foreign matter detection system for detecting foreign matters 5 in tobacco shreds 2, including: tobacco shred conveying mechanism, image acquisition device 3 and processor 4. The cut tobacco conveying mechanism comprises a multi-stage conveying device 1, wherein the conveying device 1 comprises but is not limited to a vibrating conveyor vibrating at a high speed, and cut tobacco 2 can be uniformly spread when the tail end throws out. The direction of the arrow in fig. 2 is the conveying direction of the conveyor 1, the longitudinal direction of the conveyor is parallel to the conveying direction of the conveyor 1, and the width direction of the conveyor 1 is perpendicular to the conveying direction. The cut tobacco 2 is conveyed between the adjacent two-stage conveyors 1 in the multi-stage conveyor 1 after being output from the tobacco cutter 8, and a height difference exists between end portions of adjacent ends of at least some of the adjacent two-stage conveyors 1 in the multi-stage conveyor 1, as shown by H in fig. 2.
In this embodiment, have adjacent two-stage conveyer 1 of difference in height through the setting, so that pipe tobacco 2 falls to lower conveyer 1's head end from higher conveyer 1's end when, thereby pipe tobacco 2 is in and floats the form of scattering and become more loose, gather thickness this moment, the less image of pipe tobacco 2 of density, and carry out visual identification to the pipe tobacco image, can effectively avoid lou examining debris 5, be favorable to improving detection identification efficiency and the accuracy of debris 5 in pipe tobacco 2, thereby effectively improve pipe tobacco 2's purity, guarantee whole batch pipe tobacco 2's product quality. In addition, the times of manual impurity picking can be reduced, the water dispersion and the crushing amount of the tobacco shreds 2 can be reduced, and the risk of more impurities 5 mixed due to repeated impurity picking can be reduced.
In some embodiments, tobacco shred 2 has a density of ρ kg/m 3 ρ includes, but is not limited to 191.11, the thickness of the shredded tobacco 2 when the end of the higher conveyor 1 in the adjacent two-stage conveyor 1 is thrown is t m, the width of the higher conveyor 1 in the adjacent two-stage conveyor 1 is wm, the conveying speed is v m/s,
k satisfies: k = 1-3 kg/s, and k includes but is not limited to 1.39, and its value may vary according to the flow rate of tobacco 2.
In this embodiment, when the thickness of the cut tobacco 2 thrown out by the higher conveying device 1 is fixed, the width of the conveying device 1 is inversely proportional to the conveying speed, and the width and the speed of the conveying device 1 can be adjusted according to the above formula relationship, so that the cut tobacco 2 is spread to the target thickness, and the identification precision of the sundries 5 is improved.
In some embodiments, the conveying speed v of the conveyor 1 higher in the adjacent two stages of conveyors 1 satisfies: v =0.5 to 2, and the width w satisfies: w =0.5 to 1. In this embodiment, the width and the conveying speed of the conveying device 1 can be adjusted according to the actual production situation, so that the tobacco shreds 2 are distributed more loosely when being thrown up, the missing detection of the impurities 5 is avoided, and the ideal identification precision of the impurities 5 is realized.
In some embodiments, the product w × v of the width and the conveying speed of the higher conveyor 1 of two adjacent stages of conveyors 1 satisfies: w × v =0.727. In this embodiment, the width and the transfer of the higher transfer device 1 can be performedThe product of the speeds is 0.727m/s 2 So that the thickness of the tobacco shreds 2 during throwing can reach 1cm, thereby realizing the optimal thickness of the material layer.
In some embodiments, the conveying speed v of the conveyor 1 higher in the adjacent two stages of conveyors 1 satisfies: v =1, the width w satisfies: w =0.727. In this embodiment, the belt width may be set to 0.727m so that the conveyor 1 reaches the optimum conveying speed of 1m/s, and the total width of the conveyor 1 may be 1m by subtracting the belt widths on both sides of the conveyor 1.
Referring to fig. 2, in some embodiments, the height difference of the end portions of the adjacent ends of the adjacent two stages of conveyors 1 is H cm, and the height difference H satisfies: h =15 to 20. In this embodiment, the height difference between the end portions of the adjacent ends of the two adjacent stages of conveying devices 1 may be set within a range of 15 to 20cm, so that the thrown tobacco shreds 2 can be collected by the image collecting device 3, thereby ensuring high identification accuracy of the impurities 5.
In some embodiments, the height difference H of the end portions of the adjacent ends of the adjacent two stages of conveyors 1 satisfies: h =18. In this embodiment, when the height difference between the end portions of the adjacent ends of the two adjacent stages of conveying devices 1 takes a value of 18cm, the acquisition area of the image acquisition device 3 can fully cover a possible falling trajectory of the cut tobacco 2 when the cut tobacco falls freely between the end portions of the adjacent ends of the two adjacent stages of conveying devices 1, and the accuracy and reliability of identifying the impurities 5 can be improved.
In some embodiments, the processor 4 is further configured to: and enabling the image acquisition device 3 to acquire the tobacco shred image at least comprising the tobacco shred 2 at the highest point in the falling process between the two adjacent stages of conveying devices 1. In this embodiment, through gathering the image when pipe tobacco 2 is in the peak from higher conveyer 1 throwing material to the lower conveyer 1 of next stage in-process of pipe tobacco 2, material layer thickness at this moment is minimum to each object composition can not shelter from each other in the pipe tobacco image of gathering, avoids lou examining debris 5, and the discernment analysis of being convenient for is in order to improve the discernment precision to debris 5 in pipe tobacco 2.
Referring to fig. 2, 4 and 5, in some embodiments, the image capturing device 3 includes a camera 31, and a light receiving area a of the camera 31 is shown as a in fig. 5, and at least partially coincides with an area between two adjacent stages of the conveyor 1. In this embodiment, the camera 31 includes but is not limited to a CCD line scan camera, takes 4 images per second, has a resolution of 2K, a test precision of 0.4mm/pix, has a light receiving area with a width greater than that of the conveyor 1 and can be 800mm, and collects images of the cut tobacco 2 when it is thrown out in real time.
Referring to fig. 2, 4 and 5, in some embodiments, the image capture device 3 further includes a light source 32 disposed around the area between adjacent stages of the conveyor 1. In this embodiment, the light source 32 includes, but is not limited to, an LED light source, and the operating voltage is 24VDC, so as to uniformly illuminate the light receiving area of the camera 31, and facilitate the camera 31 to collect a clear cut tobacco image, so as to improve the accuracy of identifying the sundries 5.
Referring to fig. 5, in some embodiments, the number of light sources 32 is two, and the centerline of the optical axis of the camera 31 passes through the range between the two light sources 32, including but not limited to passing through the midpoint of the line connecting the two light sources 32. In this embodiment, two light sources 32 may be symmetrically disposed on two sides of the camera 31, respectively, to improve the imaging quality of the image capturing device 3.
Referring to fig. 4, in some embodiments, the light source 32 includes a linear light source 32, and the linear light source 32 has an elongated shape, and a length direction thereof is disposed parallel to a width direction of the conveyor 1. In this embodiment, linear light source 32 parallel to the width direction of conveyor 1 may be used to uniformly cover the area where tobacco shred 2 passes, thereby improving the recognition accuracy.
Referring to fig. 2, 4 and 5, in some embodiments, the image capturing device 3 further includes a housing 33, and the end of the adjacent two-stage conveyor 1, the camera 31 and the light source 32 are disposed inside the housing 33. The camera 31 may be provided on a frame at a side of the housing 33, and the light source 33 may be connected between both sides of the housing 33.
In this embodiment, the end portions of the adjacent ends of the two adjacent stages of conveying devices 1, the camera 31 and the light source 32 are arranged inside the cover body 33, so that the influence of light change of the environment on the detection equipment is avoided, the camera 31 and the light source 32 are effectively protected from being polluted, the quality of the acquired tobacco shred images is guaranteed, and the equipment is convenient to clean.
In some embodiments, the outer wall of enclosure 33 comprises glass. In this embodiment, set up the outer wall of the cover body 33 into glass, avoid sheltering from the collection area of the camera 3 to be favorable to operating personnel to observe the monitoring facilities behavior.
In some embodiments, the processor 4 is configured to identify the clutter 5 in the shredded tobacco image by building and training a non-smoke clutter artificial intelligence model. In the embodiment, the artificial intelligence model is established and trained based on the characteristics of the tobacco shred 2 and the sundries 5 such as color and shape, the tobacco shred 2 and the non-tobacco shred sundries 5 are accurately distinguished through real-time image recognition and analysis of the artificial intelligence model, and the classification result is output in real time.
In some embodiments, the non-smoke impurity artificial intelligence model includes color and/or shape characteristics of shredded tobacco 2 and impurities 5. In the embodiment, the tobacco shred 2 and the samples of the common impurities 5 are collected, the artificial intelligent models of the impurities 5 and the tobacco shred 2 are combined based on the characteristics of the shapes and the colors of lines, edges, angles and the like in the images of the tobacco shred 2 and the impurities 5, and the parameters of the models can be adjusted and optimized in real time according to the recognition result and the accuracy of the impurities 5 so as to improve the recognition precision and the recognition efficiency.
Referring to fig. 3 and 4, in some embodiments, the debris detection system further includes an alarm device 6 in signal communication with the processor 4, the processor 4 being configured to cause the alarm device 6 to issue an alarm when a debris 5 is identified. In this embodiment, if processor 4 identifies that foreign matter 5 is present in shredded tobacco 2, alarm device 6 is caused to alarm, and alarm device 6 includes, but is not limited to, emitting an alarm signal in the form of sound and/or light.
Referring to fig. 3, in some embodiments, the debris detection system further comprises a rejecting device 7, the rejecting device 7 including, but not limited to, a flip-type rejecting mechanism disposed on the conveyor 1 and in signal communication with the processor 4, the processor 4 being configured to cause the rejecting device 7 to reject the debris 5 when the debris 5 is identified. In this embodiment, the processor 4 may further cause the removing device 7 to remove the sundries 5 after recognizing the sundries 5, or stop the conveying device 1, so as to manually remove the sundries 5.
Referring to fig. 6, in another aspect of the embodiment of the present disclosure, a method for detecting impurities based on any one of the above-mentioned impurity detection systems is provided, including: steps S1 to S2.
In step S1, an image of the cut tobacco 2 is acquired by the image acquiring device 3 when the end of the higher conveyor 1 falls to the beginning of the lower conveyor 1 in the adjacent two stages of conveyors 1.
In step S2, the foreign matter 5 in the tobacco 2 is identified based on the tobacco image.
In this embodiment, through gathering the image that pipe tobacco 2 fell to lower conveyer 1's head end from higher conveyer 1's end, because pipe tobacco 2 and debris 5 are in the form of floating the separation this moment, the thickness of material is less can not shelter from each other, is favorable to improving the detection recognition efficiency and the accuracy of debris 5 in pipe tobacco 2 to effectively improve pipe tobacco 2's purity, guarantee the product quality of whole batch pipe tobacco 2.
In some embodiments, the operation of acquiring the cut tobacco image specifically includes: and the image acquisition device 3 acquires a cut tobacco image at least comprising the cut tobacco 2 at the highest point in the falling process between the two adjacent stages of conveying devices 1.
In this embodiment, in the process of throwing the collected tobacco shreds 2 from the higher conveying device 1 to the lower conveying device 1 at the next stage, the images of the tobacco shreds 2 at the highest point are the lowest in thickness of the material layer at the moment, so that the collected tobacco shreds are not shielded by each object in the images, the identification and analysis are facilitated, and the identification precision of impurities 5 in the tobacco shreds 2 is improved.
In some embodiments, identifying the sundries 5 in the cut tobacco image specifically includes: and calling a non-tobacco impurity artificial intelligent model, classifying the tobacco shreds 2 and the impurities 5 in the tobacco shred images, outputting a classification result, and determining the impurities 5 in the tobacco shreds 2.
In this embodiment, the artificial intelligence model may extract features in the tobacco shred image, divide each object in the image into two classification labels of tobacco shred 2 and sundries 5, output the classification result, and obtain the required target precision by continuously optimizing parameters.
In some embodiments, the debris detection method further comprises: and extracting the topological structure of the tobacco shred image. In the embodiment, after the tobacco shred image is collected, the topological structure of the image can be extracted, the tobacco shreds 2 and the sundries 5 are classified based on the topological structure, a network structure can be optimized by adopting a back propagation algorithm, unknown parameters in the network are solved, and effective models of lines, edges, angles, simple shapes, complex shapes and the like of the tobacco shreds 2 and the sundries 5 are established through preprocessing.
In some embodiments, the debris detection method further comprises: and adjusting parameters of the artificial intelligent model of the non-smoke impurities according to the recognition result. In the embodiment, parameters of the artificial intelligent model can be adjusted according to the accuracy of the identified sample in practical application, and when the identification accuracy is smaller than the set accuracy threshold, the parameter values of the artificial intelligent algorithm are adjusted, so that the characteristic values of various impurities 5 are changed, the visual detection resolution accuracy is further improved, the identification accuracy of the impurities 5 in the tobacco shreds 2 in the production process is improved until the false rejection rate of the impurities 5 in the production process is smaller than the set reasonable interval, the identification accuracy of the impurities 5 in the tobacco shreds 2 can be improved, the false rejection rate of the impurities 5 in the tobacco shreds is reduced, and the purity guarantee capability of the tobacco shreds 2 in the production process is improved. In actual production, if the false rejection rate in the production process of two continuous batches tends to increase, the current control parameter value of the artificial intelligence algorithm needs to be adjusted.
Referring to fig. 6, in some embodiments, the debris detection method further includes: steps S3 to S4. In step S3, it is determined whether or not the foreign matter 5 is recognized. In step S4, when the sundries 5 are judged to be present, the alarm device 6 gives an alarm, and the alarm device 6 includes, but is not limited to, sending out an alarm signal in the form of sound and/or light. In this embodiment, when the sundries 5 are found, an alarm signal is sent out to prompt an operator to remove the sundries 5 in time.
Referring to fig. 6, in some embodiments, the debris detection method further includes: and step S5. In step S5, when the foreign matter 5 is recognized, the foreign matter 5 is rejected by the rejection device 7. In this embodiment, when the foreign object 5 is found, the removing device 7 may remove the foreign object 5 or the conveyor 1 may be stopped for manual handling.
Thus, various embodiments of the present disclosure have been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the foregoing examples are for purposes of illustration only and are not intended to limit the scope of the present disclosure. It will be understood by those skilled in the art that various changes may be made in the above embodiments or equivalents may be substituted for elements thereof without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.
Claims (25)
1. A debris detecting system for detecting debris in tobacco shreds is characterized by comprising:
the cut tobacco conveying mechanism comprises a plurality of stages of conveying devices (1), wherein cut tobacco (2) is conveyed between two adjacent stages of conveying devices (1) in the plurality of stages of conveying devices (1), and the end parts of the adjacent ends of at least part of the two adjacent stages of conveying devices (1) in the plurality of stages of conveying devices (1) have height difference;
an image pickup device (3) disposed adjacent to a region between adjacent two stages of the multi-stage conveying devices (1);
a processor (4) in signal connection with the image acquisition device (3) configured to:
and when the cut tobacco (2) falls to the lower conveying device (1) from the higher conveying device (1) in the two adjacent conveying devices (1), enabling the image acquisition device (3) to acquire a cut tobacco image, and identifying the sundries (5) in the cut tobacco (2) according to the cut tobacco image.
2. Impurity detection system according to claim 1, characterized in that the density of the cut tobacco (2) is ρ kg/m 3 The tobacco shreds (2) are arranged at the end of the higher conveying device (1) in the two adjacent stages of conveying devices (1)The thickness of the end throwing-out is tm, the width of the higher conveying device (1) in the two adjacent conveying devices (1) is w m, and the conveying speed is v m/s;
wherein the content of the first and second substances,
k satisfies: k =1 to 3kg/s.
3. A debris detecting system according to claim 2, characterized in that the transport speed v of the higher transport device (1) of said two adjacent stages of transport devices (1) is such that: v =0.5 to 2, and the width w satisfies: w =0.5 to 1.
4. A debris detecting system according to claim 3, characterized in that the product w x v of the width and the transport speed of the higher conveyor (1) of the two adjacent stages of conveyors (1) satisfies: w × v =0.727.
5. A debris detecting system according to claim 4, characterized in that the transport speed v of the higher transport device (1) of said two adjacent stages of transport devices (1) is such that: v =1, the width w satisfies: w =0.727.
6. The debris detection system according to claim 1, wherein the height difference between the end portions of the adjacent ends of the two adjacent stages of conveyors (1) is H cm, and the height difference H satisfies: h =15 to 20.
7. A debris detection system according to claim 6, characterized in that the height difference H between the end portions of the adjacent ends of said two adjacent stages of conveyors (1) satisfies: h =18.
8. A debris detection system according to claim 1, wherein the processor (4) is further configured to:
and enabling the image acquisition device (3) to acquire a cut tobacco image at least comprising the highest point of the cut tobacco (2) in the falling process between the two adjacent stages of conveying devices (1).
9. Debris detection system according to claim 1, characterized in that the image acquisition device (3) comprises a camera (31), the light receiving area of the camera (31) at least partly coinciding with the area between the two adjacent stages of conveyors (1).
10. Debris detection system according to claim 9, characterized in that the image acquisition device (3) further comprises a light source (32) arranged around the area between the two adjacent stages of transport devices (1).
11. Debris detection system according to claim 10, characterized in that the number of light sources (32) is two, and that a median line of the optical axes of the cameras (31) passes through a range between the two light sources (32).
12. Debris detection system according to claim 10, characterized in that the light source (32) comprises a linear light source (32), which linear light source (32) is arranged parallel to the width direction of the conveyor (1).
13. Debris detection system according to claim 10, characterized in that the image acquisition arrangement (3) further comprises a housing (33), the ends of the adjacent two-stage conveyors (1), the camera (31) and the light source (32) being arranged inside the housing (33).
14. The debris detection system according to claim 13, wherein an outer wall of the enclosure (33) comprises glass.
15. Debris detection system according to claim 1, characterized in that the processor (4) is configured to:
and identifying impurities (5) in the tobacco shred images by establishing and training a non-tobacco impurity artificial intelligent model.
16. Debris detection system according to claim 15, characterized in that the artificial intelligence model of non-smoke debris comprises color and/or shape characteristics of the cut tobacco (2) and debris (5).
17. A debris detection system according to claim 1, further comprising:
the alarm device (6) is in signal connection with the processor (4);
wherein the processor (4) is configured to:
when the sundries (5) are identified, the alarm device (6) gives an alarm.
18. The debris detection system of claim 17 further comprising: the rejecting device (7) is in signal connection with the processor (4);
wherein the processor (4) is configured to:
and when the sundries (5) are identified, enabling the rejecting device (7) to reject the sundries (5).
19. A foreign material detection method based on the foreign material detection system according to any one of claims 1 to 18, characterized by comprising:
the image acquisition device (3) is used for acquiring a cut tobacco image of the cut tobacco (2) when the tail end of the higher conveying device (1) in the two adjacent stages of conveying devices (1) falls to the beginning end of the lower conveying device (1);
and identifying sundries (5) in the tobacco shreds (2) according to the tobacco shred images.
20. The impurity detection method according to claim 19, wherein the operation of acquiring the image of the cut tobacco specifically comprises:
and the image acquisition device (3) is used for acquiring a cut tobacco image at least comprising the cut tobacco (2) at the highest point in the falling process between the two adjacent stages of conveying devices (1).
21. The debris detection method according to claim 19, wherein the operation of identifying the debris (5) in the cut tobacco image specifically comprises:
calling a non-smoke impurity artificial intelligent model;
classifying the tobacco shreds (2) and the sundries (5) in the tobacco shred image;
and outputting a classification result, and determining sundries (5) in the tobacco shreds (2).
22. The debris detection method according to claim 21, further comprising:
and extracting the topological structure of the tobacco shred image.
23. The debris detection method according to claim 21, further comprising:
and adjusting parameters of the non-smoke impurity artificial intelligence model according to the recognition result.
24. A debris detection method according to claim 19, further comprising:
when the sundries (5) are identified, the alarm device (6) gives an alarm.
25. The debris detection method according to claim 24, further comprising:
when the sundries (5) are identified, the sundries (5) are removed through a removing device (7).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210922167.8A CN115281365A (en) | 2022-08-02 | 2022-08-02 | Sundry detection system and sundry detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210922167.8A CN115281365A (en) | 2022-08-02 | 2022-08-02 | Sundry detection system and sundry detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115281365A true CN115281365A (en) | 2022-11-04 |
Family
ID=83826680
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210922167.8A Pending CN115281365A (en) | 2022-08-02 | 2022-08-02 | Sundry detection system and sundry detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115281365A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110162666A1 (en) * | 2010-01-07 | 2011-07-07 | Hauni Maschinenbau Ag | Method and device for removing foreign particles from a tobacco stream |
| 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 |
| NL1039764C2 (en) * | 2012-08-17 | 2014-02-18 | J O A Technology Beheer B V | A method of, a control system, a device, a sensor and a computer program product for controlling transport of fibrous material in a transport line of a pneumatic conveying system. |
| CN204400060U (en) * | 2015-01-14 | 2015-06-17 | 平安开诚智能安全装备有限责任公司 | Belt feeder transfer system |
| CN213001298U (en) * | 2020-08-14 | 2021-04-20 | 广西中烟工业有限责任公司 | Tobacco impurity removing device |
| CN215984396U (en) * | 2021-09-23 | 2022-03-08 | 秦皇岛烟草机械有限责任公司 | Cut tobacco shred on-line processing device |
| CN114778561A (en) * | 2022-03-21 | 2022-07-22 | 云南昆船设计研究院有限公司 | Tobacco shred quality tracing method and system based on machine vision |
-
2022
- 2022-08-02 CN CN202210922167.8A patent/CN115281365A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110162666A1 (en) * | 2010-01-07 | 2011-07-07 | Hauni Maschinenbau Ag | Method and device for removing foreign particles from a tobacco stream |
| NL1039764C2 (en) * | 2012-08-17 | 2014-02-18 | J O A Technology Beheer B V | A method of, a control system, a device, a sensor and a computer program product for controlling transport of fibrous material in a transport line of a pneumatic conveying system. |
| 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 |
| CN204400060U (en) * | 2015-01-14 | 2015-06-17 | 平安开诚智能安全装备有限责任公司 | Belt feeder transfer system |
| CN213001298U (en) * | 2020-08-14 | 2021-04-20 | 广西中烟工业有限责任公司 | Tobacco impurity removing device |
| CN215984396U (en) * | 2021-09-23 | 2022-03-08 | 秦皇岛烟草机械有限责任公司 | Cut tobacco shred on-line processing device |
| CN114778561A (en) * | 2022-03-21 | 2022-07-22 | 云南昆船设计研究院有限公司 | Tobacco shred quality tracing method and system based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 郭粉林, 廖光军, 王艺斌: "光学烟叶杂物分选机的原理与结构", 烟草科技, no. 03, 25 March 2002 (2002-03-25), pages 23 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106455594B (en) | Shrimp system of processing and method | |
| CN101907453B (en) | Online measurement method and device of dimensions of massive agricultural products based on machine vision | |
| WO2011115666A2 (en) | Computer vision and machine learning software for grading and sorting plants | |
| CN104781654A (en) | Method and apparatus for handling harvested root crops | |
| CN102339385A (en) | Combined light perspective based visual recognition detection method of stems and stem ratios in leaves | |
| US8511226B2 (en) | Pepper de-stemming methods and apparatus | |
| US20080289515A1 (en) | Pepper de-stemming | |
| CN105806751A (en) | On-line monitoring system and method for crushing of cereals in grain tank of combine harvester | |
| US20220379348A1 (en) | Sorting device for agricultural products and corresponding method | |
| FR2818668A1 (en) | DEVICE ON A SPINNING PREPARATION MACHINE FOR THE ANALYSIS OF SEPARATE WASTE | |
| CN114778561A (en) | Tobacco shred quality tracing method and system based on machine vision | |
| CN202385685U (en) | Tea color sorting machine | |
| CN105319166A (en) | Real-time soybean detection instrument | |
| CN115128033A (en) | Tobacco leaf detection method, device and system and storage medium | |
| CN115281365A (en) | Sundry detection system and sundry detection method | |
| PL149988B1 (en) | Apparatus for distinguishing foreign matter in an agricultural crop ingathering machine | |
| CN112730417B (en) | Online detection device for appearance quality of wheat | |
| CN114062366A (en) | Tobacco shred production wind-selection stem-removing quality on-line detection method and system | |
| US20200046010A1 (en) | Pepper de-stemming methods and apparatus | |
| JP2013074797A (en) | Crop harvester | |
| CN215493192U (en) | Online detection device for cut tobacco structure of tobacco shred production line | |
| CN111307805A (en) | Threshing quality detection device and method based on visual feature fusion | |
| CN213001298U (en) | Tobacco impurity removing device | |
| CN215218257U (en) | Automatic stem drawing and separating device | |
| CN113125231A (en) | Automatic stem drawing and separating device and method |
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 |