CN117915791A - Assembly device and assembly method for producing a multi-component smoking article - Google Patents
Assembly device and assembly method for producing a multi-component smoking article Download PDFInfo
- Publication number
- CN117915791A CN117915791A CN202280061344.6A CN202280061344A CN117915791A CN 117915791 A CN117915791 A CN 117915791A CN 202280061344 A CN202280061344 A CN 202280061344A CN 117915791 A CN117915791 A CN 117915791A
- Authority
- CN
- China
- Prior art keywords
- rod
- rod segment
- inspection
- segment
- pair
- 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
- 230000000391 smoking effect Effects 0.000 title claims abstract description 120
- 238000004519 manufacturing process Methods 0.000 title claims description 8
- 238000007689 inspection Methods 0.000 claims abstract description 120
- 238000000926 separation method Methods 0.000 claims abstract description 19
- 238000005520 cutting process Methods 0.000 claims abstract description 8
- 239000004615 ingredient Substances 0.000 claims abstract description 7
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 60
- 238000010801 machine learning Methods 0.000 claims description 39
- 230000003287 optical effect Effects 0.000 claims description 12
- 230000007547 defect Effects 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 8
- 125000006850 spacer group Chemical group 0.000 claims description 5
- 238000010168 coupling process Methods 0.000 claims description 4
- 238000005859 coupling reaction Methods 0.000 claims description 4
- 230000008878 coupling Effects 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 239000005022 packaging material Substances 0.000 claims 2
- 239000000463 material Substances 0.000 abstract description 17
- 239000013256 coordination polymer Substances 0.000 description 14
- 238000013528 artificial neural network Methods 0.000 description 10
- 239000000945 filler Substances 0.000 description 10
- 239000011265 semifinished product Substances 0.000 description 8
- 230000002950 deficient Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000004026 adhesive bonding Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 235000019504 cigarettes Nutrition 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000009849 deactivation Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24C—MACHINES FOR MAKING CIGARS OR CIGARETTES
- A24C5/00—Making cigarettes; Making tipping materials for, or attaching filters or mouthpieces to, cigars or cigarettes
- A24C5/32—Separating, ordering, counting or examining cigarettes; Regulating the feeding of tobacco according to rod or cigarette condition
- A24C5/34—Examining cigarettes or the rod, e.g. for regulating the feeding of tobacco; Removing defective cigarettes
- A24C5/3412—Examining cigarettes or the rod, e.g. for regulating the feeding of tobacco; Removing defective cigarettes by means of light, radiation or electrostatic fields
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24D—CIGARS; CIGARETTES; TOBACCO SMOKE FILTERS; MOUTHPIECES FOR CIGARS OR CIGARETTES; MANUFACTURE OF TOBACCO SMOKE FILTERS OR MOUTHPIECES
- A24D3/00—Tobacco smoke filters, e.g. filter-tips, filtering inserts; Filters specially adapted for simulated smoking devices; Mouthpieces for cigars or cigarettes
- A24D3/02—Manufacture of tobacco smoke filters
- A24D3/0295—Process control means
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
- Absorbent Articles And Supports Therefor (AREA)
- Manufacturing Of Cigar And Cigarette Tobacco (AREA)
Abstract
An assembling apparatus (1) for producing multi-component smoking articles, each smoking article comprising a first rod segment (SP 1) and a second rod segment (SP 2) having respective central Axes (AC), the first rod segment being obtained from a rod (B3) and being provided with a flavouring ingredient, the assembling apparatus comprising: -a combining unit (10) for forming a group of rod segments (GS 1, GS 2), wherein the first and second rod segments are axially aligned and abutting end-to-end, and configured to couple a respective second rod segment (SP 2) to an end of each rod (B3), and in a separation station (103T) the rods are separated into a pair of portions (B3', B3 ") by cutting the rods transversely, forming a corresponding pair of rod segment groups (GS 1, GS 2); a wrapping unit (14) for wrapping the sheet of wrapping material around each group of rod segments (GS 1, GS 2); and an inspection system (12) including a first inspection stage (121) located upstream of the separation stage (103T) in the conveying direction and configured to axially observe the ends of the rods, and a second inspection stage (13) located downstream of the separation stage (103T) to axially observe the free ends of the first rod segments (SP 1) in each rod segment group (GS 1, GS 2).
Description
Technical Field
The present invention relates to a method and system for inspecting smoking articles.
Background
In the field of smoking articles, such as cigarettes and heating non-combustion (HNB) devices, quality inspection of individual articles is required. Indeed, automatic machines for manufacturing smoking articles sometimes produce defective smoking articles. In particular, there are smoking articles comprising a body placed in a wrapper, wherein the body must be in a predetermined position; in this case, the defect may be caused by incorrect positioning of the object. For example, some cigarettes have a filter comprising an object with a cross-section in the form of a curved object, as described in patent document WO2020128827A1 in the name of the present inventors, wherein the object is marked 2 in the figures. In another example, the HNB device comprises an object having a circular cross-section, as described in patent document WO2012016795A1, wherein the object is marked 6 in the drawing.
Against this background, an automatic machine for manufacturing smoking articles may be provided with an inspection system known in the prior art (for example from patent document EP3520631A1 in the name of the present inventors). Examples of methods for inspecting smoking articles are described in the following prior art documents: WO2018185722A1, CN111972700A, EP3476228A1, ITBO20080755A1 and EP3067823A1. Furthermore, with respect to assembly apparatuses for producing smoking articles, the prior art provides, for example, the solutions described in documents DE102014203158A1 and EP0653170 A1.
However, there remains a need for a system that is particularly efficient, reliable and fast in performing an inspection of a smoking article. In particular, it is desirable that such a system be capable of reliable quality inspection during processing during production.
Disclosure of Invention
It is an object of the present invention to provide a method and system for inspecting smoking articles that overcomes the above-mentioned disadvantages of the prior art.
The above object is fully achieved by the method and system according to the invention characterized in the appended claims.
According to one aspect of the disclosure, the disclosure provides a method for inspecting a smoking article. Each smoking article comprises an elongate tubular wrapper extending along a longitudinal axis, a filler material wrapped in the wrapper, and an elongate body embedded in the filler material at a predetermined location.
The method comprises the step of capturing an image of the smoking article or a part thereof. The image is viewed along an optical path oriented along the longitudinal axis.
The method includes the step of delivering the image to a machine learning model. The machine learning model is trained to identify subjects in the image. This step is performed by the processor.
This enables the machine to check (at least) for the presence of a body within the filler material.
Preferably, the machine learning model is trained to generate positioning data for each image. The positioning data indicates the position of the body relative to the tubular wrapper. The positioning data represents a planar geometry defining an object represented in the image. In this way, in addition to checking for the presence of a body within the filling material, its position relative to the wrapper can be identified.
The method includes the steps of processing, by a processor, positioning data based on reference data representing a predetermined position of a subject; for example, the processing includes a step of comparing, by the processor, the positioning data with reference data representing a predetermined position of the subject.
Thus, the processor may check whether the subject is effectively positioned at an acceptable position relative to the predetermined position. For example, the processor may access a deviation value that identifies a maximum deviation value between the subject position determined from the positioning data and the predetermined position.
In one embodiment, the machine learning model includes a deep neural network. In one embodiment, the neural network is a convolutional neural network.
The neural network may include one or more filtering stages (FILTERING STAGE) of a maximum pooling type.
The machine learning model is trained by the step of delivering a plurality of example images. For each image, a machine learning model is trained by the step of conveying positioning target data representative of a planar geometry defining an object represented in the image.
These examples include a plurality of first images of a semi-finished smoking article with a correctly positioned object. In one embodiment, these examples include a plurality of second images of a semi-finished smoking article having an object that is incorrectly positioned according to the selection of the predetermined locating defect.
The method comprises the step of determining, by the control unit, a positive or negative recognition result identifying the object in the image. The identifying step is performed by a machine learning model. If the result of the identification is negative, the method comprises a step of generating information for rejecting the smoking article, which is performed by the control unit. If the identification is affirmative, the method comprises the step of starting to compare the positioning data with reference data representing a predetermined position of the subject. Next, the method includes generating information for rejecting or approving the smoking article in response to the comparison. This allows firstly the rejection of articles without a body and secondly the rejection of articles with incorrect body position in the presence of a body.
In one embodiment, the method includes the step of optically inspecting the wrapper for each image captured. The method includes the step of generating wrapper data representing the results of inspecting the wrapper.
The method includes the step of comparing the wrapper data with reference wrapper data representing a predetermined specification of the wrapper. The method includes the step of generating (i) information for culling or (ii) information to proceed with the conveying step in response to (i) a negative result or (ii) a positive result of the comparing step, respectively.
Thus, the method comprises a full inspection of the smoking article, the full inspection further comprising inspecting the wrapper.
According to one aspect, the method is a method for inspecting smoking articles one by one. In other words, the method includes capturing an image of each individual smoking article. Preferably, the method comprises the step of positioning individual smoking articles in an inspection zone aimed at by the inspection device so as to capture an image thereof. In one embodiment of the method, the inspection area is illuminated with a constant illumination parameter to allow the smoking article to be illuminated uniformly. Furthermore, the illumination parameters of the examination region are the same as those used to capture the plurality of example images. In one embodiment of the method, the smoking article is positioned in the inspection region in the same orientation relative to the inspection device. Moreover, smoking articles framed in the multiple example images have the same orientation as smoking articles inspected during the production process.
The uniformity of illumination and positioning between the captured image and the example image greatly improves the reliability of inspection by machine learning models. This is not possible if the inspection is not performed separately but in groups, wherein each smoking article has its own position relative to the inspection device.
In one embodiment, the inspection device is synchronized with a conveyor that conveys the smoking articles (or semi-finished products or components forming part of the smoking articles) into and out of the inspection zone. Preferably, the smoking articles (or semi-finished products or components used to form the smoking articles) are transported one after the other in an orderly manner; preferably, they are transferred into the inspection station such that their orientation is predetermined and known to the system. This improves inspection accuracy and facilitates training of machine learning models to identify defects or to perform quality control. Furthermore, for each smoking article to be inspected, the control unit knows the inspection result. The control unit is thus able to control the rejecting device to reject individual defective smoking articles.
Notably, singulating (singulate) the smoking articles also facilitates the rejection operation. Indeed, in the case of a grouped inspection of smoking articles, it is not only more difficult to identify a single defective smoking article, but it is also more complex to reject it, because: (i) It must be singulated retrospectively or (ii) multiple smoking articles have to be rejected due to the presence of a single defective article.
In at least one example embodiment, the smoking article or a portion thereof is moved individually as a single article along a predetermined path within an apparatus for producing smoking articles (which in one example is an assembly apparatus, but which may be a different type of apparatus in terms of this aspect of the disclosure and other aspects regarding inspection systems and image processing modes). At least one inspection station (e.g., a first inspection station or a first inspection station and a second inspection station) is positioned along a predetermined path. The inspection station includes at least one illuminator and one camera. Preferably, also as described above), the smoking articles or parts thereof are moved one after the other along a predetermined path; preferably, the smoking articles or parts thereof are also moved along the predetermined path in such a way that they have a predetermined orientation (orientation of the optical path relative to the camera known to the system; e.g. they are oriented so that they are aligned with the camera) in the inspection station.
In one example, in the step of capturing an image, each smoking article or portion thereof moving along a predetermined path is individually observed and photographed (i.e., as an object of image capture); in this way, each image is associated with a single smoking article or a portion thereof.
With respect to the machine learning model, it should be noted that it is preferably trained by delivering thereto a plurality of example images, each of which relates to a single smoking article or a portion thereof. Furthermore, the machine learning model may also be trained by delivering target data to it (in which case learning is supervised); alternatively, the target data is not delivered thereto (in this case, learning is unsupervised).
In one example, the machine readable instructions contained in the non-transitory data store cause the processor to, for each smoking article or a portion thereof in the stream:
capturing, by at least one inspection station (e.g. by a first inspection station and a second inspection station), a plurality of images of the smoking article or a portion thereof viewed along a path having a predetermined orientation;
-delivering the plurality of images to a machine learning model.
The machine learning model is trained to identify predetermined defect categories for the smoking article or a portion thereof. In one example, a class of defects relates to the absence or location of a body located in the smoking article (at a predetermined location). However, the machine learning model may be trained to identify other types of defects, such as, purely by way of example, the presence of stains or impurities or shapes that differ from a predetermined (reference) shape of the smoking article or a portion thereof.
According to an aspect of the present disclosure, the present disclosure provides a computer program comprising instructions for performing the steps of the method described in the present disclosure when executed by a processor.
According to one aspect of the present disclosure, there is provided an inspection system for inspecting a smoking article comprising an elongate tubular wrapper extending along a longitudinal axis, a filler material wrapped in the wrapper, and an elongate body embedded in the filler material at a predetermined location. The system includes a processor and a non-transitory data storage device including machine-readable instructions. The machine readable instructions tell the processor to capture an image of the smoking article or a portion thereof viewed along an optical path oriented along the longitudinal axis. Machine-readable instructions tell the processor to deliver the image to a machine-learned model that is machine-trained to identify subjects in the image.
The non-transitory data storage device also includes instructions that tell the processor to process the images to generate, for each image, positioning data representing a planar geometry defining a subject represented in the image.
The non-transitory data storage device further includes instructions that tell the processor to compare the positioning data with reference data representing a predetermined location of the subject.
These instructions tell the processor to determine a positive or negative result of identifying the object in the image that is performed by the machine learning model. If the result of the identification is negative, the instructions tell the processor to generate information for rejecting the smoking article. If the identification is affirmative, the instructions tell the processor to compare the positioning data with reference data representing a predetermined location of the subject and generate information for rejecting or approving the smoking article in response to the comparison.
In one embodiment, the machine learning model includes a deep neural network. The deep neural network may be a convolutional deep neural network. The deep neural network may include one or more filtering stages of a maximally pooled type.
According to one aspect of the present disclosure, there is provided an apparatus for continuously and cyclically producing smoking articles, wherein each smoking article comprises an elongate tubular wrapper extending along a longitudinal axis, a filler material wrapped in the wrapper, and an elongate body embedded in the filler material at a predetermined location. The apparatus comprises inspection means according to any one of the features described in this disclosure.
According to an aspect of the present disclosure, there is provided a method for inspecting smoking articles, wherein each smoking article comprises a body placed at a predetermined location inside the smoking article. The method is applicable in the case of operations performed by an apparatus that produces smoking articles in a continuous cycle through a series of stations from an initial station to a final station.
The method includes the step of capturing an image of the machine-generated semi-finished product at an intermediate processing station between an initial processing station and a final processing station.
The method includes the step of delivering the image to a machine learning model trained to identify a subject in the image, performed by a control unit.
According to one aspect of the present disclosure, there is provided an assembly apparatus for producing a multi-component smoking article. Each smoking article comprises a plurality of rod segments defining a respective central axis. The plurality of stick segments comprises a first stick segment and a second stick segment, the first stick segment being provided with a flavouring ingredient.
The assembly device comprises a combination unit. The combination unit is configured to form rod segment groups, each rod segment group comprising at least a first rod segment and a second rod segment. The first and second rod segments are axially aligned with each other. The first rod segment and the second rod segment are abutted end-to-end.
The groups of rod segments advance perpendicularly to their central axes. The first rod segment is obtained from rods, each rod having a first end and a second end spaced apart along a rod axis.
The combination unit is configured to couple the respective second rod segment to the first and second ends of the rod. The combining unit is configured to divide the rod into a pair of sections by cutting the rod transverse to the rod axis in the separation station, thereby forming a corresponding pair of rod segment groups. Each rod segment set includes a respective rod portion and a respective second rod segment.
The assembly device comprises a packaging unit. The wrapping unit is configured to receive a series of rod segment groups conveyed in a conveying direction from the combining unit, to convey the rod segment groups perpendicular to a central axis of the rod segment groups, and to wrap a sheet of wrapping material on each rod segment group.
The assembly apparatus includes an inspection system.
The inspection system includes a first inspection station. The first inspection station is located upstream of the separation station in the conveying direction. The first inspection station is configured to axially view the first end and the second end of each rod.
The inspection system includes a second inspection station. The second inspection station is located downstream of the separation station in the conveying direction. The second inspection station is configured to axially view the free ends of the respective first rod segments of each of the pair of rod segment sets.
In one embodiment, the assembly device comprises a spacer table which is interposed between the separating table and the second inspection table with respect to the conveying direction. The spacer is configured to axially space the rod segment sets of the pair of rod segment sets.
The assembly apparatus is configured to transport a rod segment set of a pair of rod segment sets perpendicular to the rod axis between the separation stage and the spacer stage.
The second inspection station includes a central camera axially interposed between the rod segment sets of the pair of rod segment sets. In one embodiment, the second inspection station includes another central camera interposed axially between the rod segment sets of the pair of rod segment sets.
In one embodiment, the second inspection station comprises a right-side inspection unit comprising a central camera facing to the right with respect to the conveying direction for viewing the free end of one of the pair of rod segment groups.
In one embodiment, the second inspection station comprises a left inspection unit comprising a further central camera facing to the left with respect to the conveying direction for viewing the free end of the other of the above-mentioned pair of rod segment groups.
In a preferred embodiment, the right and left inspection units are offset in the conveying direction.
Preferably, the first inspection station is provided with a pair of cameras.
In one embodiment, the cameras of the pair of cameras have respective optical paths oriented in opposite converging directions. Further, according to an aspect of the present disclosure, the second pair of cameras have respective optical paths aligned but oriented in opposite converging directions.
The assembly device comprises a control unit. The control unit is connected to the first inspection station and the second inspection station to drive them. The control unit is provided with a processor and a non-transitory data storage device comprising machine readable instructions that instruct the processor to capture a plurality of images of the smoking article or a portion thereof viewed along an optical path oriented along the longitudinal axis by the first inspection station and the second inspection station. It should be noted that the smoking article comprises a body placed at a predetermined position inside the smoking article.
The control unit is provided with a processor and a non-transitory data storage device including machine readable instructions telling the processor to deliver a plurality of images to a machine learning model trained to identify a subject in the images.
According to one aspect, the present disclosure provides an apparatus for producing smoking articles (preferably multi-component articles), each smoking article comprising a component that is inspectable by optical means in at least one inspection station of the apparatus and that is hidden from the optical means when the smoking article is completed. In other words, the present disclosure relates to those apparatuses in which smoking articles are obtained by progressive processes that define inspectable semi-finished products that cannot be inspected with optical instruments when the smoking article is completed.
These devices include inspection systems. The inspection system is located in an inspection station of the apparatus, which corresponds to the inspected semifinished product.
The apparatus includes a first processing station configured to form an inspectable semi-finished product from the processing component. The apparatus comprises a second processing station configured to form smoking articles from the inspected semifinished product.
The inspection station is interposed between the first and second treatment stations along a transport path of the smoking articles in the apparatus.
Advantageously, the device comprises a control unit. The control unit is connected to the inspection system to drive it. The control unit is provided with a processor and a non-transitory data storage device comprising machine readable instructions.
The control unit is programmed to receive a plurality of images of the inspectable semi-finished product or a portion thereof captured by the inspection system. For example, the image is captured along an optical path that is preferably oriented along the longitudinal axis of the smoking article. For example only, the inspection system captures an image of a subject located at a predetermined location in the smoking article. However, the inspection system may be configured to identify other aspects of the smoking article that are otherwise not visible at completion, such as whether dirt or stain is present on the surface prior to being wrapped, or the length of one rod segment prior to being glued to another rod segment.
The control unit is programmed to deliver the plurality of images to the machine learning model.
For example, but not necessarily, the machine learning model is trained to identify a subject within the smoking article in the image. For example, in other embodiments, it may identify whether dirt or stain is present on the surface prior to being wrapped, or the length of one rod segment prior to being glued to another rod segment.
According to one aspect, the present disclosure provides an assembly method for producing multi-component smoking articles, wherein each smoking article comprises a plurality of rod segments defining a respective central axis, and wherein the plurality of rod segments comprises a first rod segment and a second rod segment, the first rod segment being provided with a flavouring ingredient.
The method comprises the step of conveying a stream of sticks, each stick having a flavouring ingredient and being elongate along a stick axis from a first end to a second end, in a conveying direction transverse to the stick axis, performed by the combined unit.
The method includes the step of coupling respective second rod segments to the first and second ends of the rod.
The method comprises the following steps performed in the separation station by means of a combining unit: the rod is divided into a pair of sections by cutting the rod transverse to the rod axis, thereby forming a corresponding pair of rod segment sets.
Each rod segment set includes a respective rod portion defining a respective first rod segment and a respective second rod segment axially aligned along a central axis and abutting end-to-end.
The method comprises the step of transporting the group of rod segments through the wrapping unit perpendicular to the central axis of the group of rod segments.
The method includes the step of transporting the set of rod segments perpendicular to a central axis of the set of rod segments.
The method includes the step of wrapping the group of rod segments in a sheet of wrapping material by a wrapping system.
The method comprises a first step of observing the first end and the second end of each rod in a first inspection station located upstream of the separation station in the conveying direction.
The method comprises a second step of observing the free end of the respective first rod segment of each rod segment group of the pair in a second inspection station located downstream of the separation station in the conveying direction.
In one embodiment, the method further comprises the step of spacing the rod segment sets of the pair of rod segment sets in the axial direction after the separating step and before the second observing step.
According to one aspect of the present disclosure, during the spacing step, the rod segment sets of a pair of rod segment sets are also transported transverse to their axes.
In one embodiment of the method, the coupling step precedes the decoupling step.
In one embodiment, the second observation step comprises the following sub-steps in sequence:
-observing the free end of one of the pair of rod segment sets by means of a central camera;
-transporting the groups of rod segments in a transport direction;
-observing the free end of the other rod segment set of the pair of rod segment sets by means of the other central camera.
In one embodiment, a smoking article comprises a body disposed at a predetermined location inside the smoking article. The method further includes the step of delivering images captured in the first and second exam tables to a machine learning model trained to identify the subject in each image.
Drawings
These and other features will become more apparent from the following description of a preferred embodiment illustrated by way of non-limiting example in the accompanying drawings, in which:
Figure 1 shows a schematic side view of an apparatus for continuously and cyclically producing smoking articles;
fig. 2 shows a schematic top view of the device of fig. 1;
Figure 3 schematically illustrates a method for inspecting a smoking article;
Figure 4 schematically shows a cross-section of a smoking article comprising a filler material and a body CP.
Detailed Description
Referring to the drawings, reference numeral 1 denotes an assembly apparatus for producing a multi-component smoking article. Each smoking article comprises a plurality of rod segments SP defining a respective central axis. The plurality of stick segments comprises a first stick segment SP1 and a second stick segment SP2, the first stick segment SP1 being provided with a flavouring ingredient. The smoking article further comprises an outer wrapper IC.
The device 1 comprises a combination unit 10. The combination unit is configured to form rod segment groups GS, each rod segment group GS comprising at least a first rod segment SP1 and a second rod segment SP2 axially aligned and abutting end to end. In the combined unit, the rod segment groups GS advance perpendicularly to their central axis AC.
In particular, the device 1 comprises a splitting unit 11 configured to form a plurality of first and second rod segments SP1, SP2 from respective rods, which first and second rod segments SP1, SP2 are then paired to define respective rod segment groups.
In particular, in one embodiment, the second rod segment SP2 includes a first portion SP2' and a second portion SP2".
The dividing unit 11 comprises a first separating element 111, which first separating element 111 is configured to divide the first rod into corresponding rods B1, which rods B1 define a first portion SP2' of the second segment SP2 and have a predetermined length along the respective central axis AC.
The partitioning unit 11 comprises a second separating element 112, which second separating element 112 is configured to separate the second rod into corresponding rods B2, which rods B2 define the second portions SP2 "of the second rod segments SP2 and have a predetermined length along the respective central axis AC.
The partitioning unit 11 comprises a third separating element 113, which third separating element 113 is configured to separate a third rod into corresponding rods B3, which rods B3 define the first rod segments SP1 and have a predetermined length along the respective central axis AC. It should be noted that the third stick B3 is a stick containing a flavoured filling material MTA. In addition, the first stick segment SP1 should ideally comprise a body CP embedded in a flavoured filler material.
The apparatus 1 comprises an inspection system 12, the inspection system 12 being configured to capture inspection data to be processed to derive information about the smoking article.
The inspection system comprises a first inspection station 121, which first inspection station 121 is configured to capture inspection data relating to a rod B3 defining a first rod segment SP 1. In particular, rods B3 each comprise a first end B31 and a second end B32. The first inspection station 121 includes a first pair of cameras 122, each camera 122 configured to capture a corresponding image of the first end B31 and the second end B32 of the rod B3.
In the first inspection station, a first pair of cameras 122 capture image data 122' representing an image of a first end B31 of rod B3 and an image of a second end B32 of rod B3.
The apparatus 1 comprises a control unit 2, which control unit 2 comprises a processor and is configured to control the apparatus 1 and to process data received from an inspection system 12.
The control unit 2 is configured to recognize whether the main body CP is present in the wand B3. In addition, in one embodiment, the control unit 2 is further configured to check whether the body CP is in the correct position with respect to the filling material MTA of the rod B3.
The step of identifying the subject CP is performed by delivering image data captured by the first inspection stage 121 through the first pair of cameras 122 to the machine learning model MA. The machine learning model MA is trained to identify the subject CP in the image. The identification step is described in more detail below.
We then note that in this step, the apparatus has a plurality of first bars B1 and a plurality of second bars B2 that together define a second bar segment SP2, and a plurality of third bars B3 that define the first bar segment SP 1.
At this time, the combining unit 10 starts to operate to combine the three kinds of bars B1, B2, B3. The combination unit is configured to convey the bars B1, B2 and B3 along a conveying direction DA perpendicular to the central axis AC of the bars B1, B2, B3.
The combined unit comprises a first station 101. The first station 101 comprises a respective first cutting station 101T configured to cut the rod B1 in a direction perpendicular to the central axis AC (that is to say, in the conveying direction DA) to form a first segment B1' and a second segment B1". The first stage 101 further comprises a first separator 101S, which first separator 101S is configured to space apart the first segment B1' and the second segment B1 "along a spacing direction DD, which spacing direction DD is perpendicular to the conveying direction DA and parallel to the central axis of the rod B1 (has been separated). Separating the two segments is necessary to allow the insertion of a rod B2 of the plurality of second rods B2 at an intermediate position between the first segment B1' and the second segment B1 "along the spacing direction DD.
The combined unit 10 then comprises a second station 102 in which a second rod B2 of the plurality of second rods B2 is placed at an intermediate position between the first segment B1' and the second segment B1 "in the spacing direction DD.
The second station 102 comprises a first gluing device 102I configured to connect a first end of the rod B2 to a corresponding end of a first segment B1' of the rod B1 and to connect a second end of the rod B2 to a corresponding end of a second segment B1″ of the rod B1.
The second station comprises a second cutting element 102T configured to divide the second rod B2 into a corresponding first segment B2' and a second segment B2", the first segment B2' being connected to the first segment B1' of the first rod B1 to define a first rod segment SP1 of a smoking article, the second segment B2" being connected to the second segment B1 "of the first rod B1 to define a further second rod segment SP2 of a further smoking article.
The second station 102 comprises a second separator 102S configured to separate a second rod segment SP2 from another second rod segment SP 2.
The combined unit 10 comprises a third station 103 in which third station 103 a third rod B3 of the plurality of third rods B3 is placed at an intermediate position between a second rod segment (formed by the first segment B1 'of the first rod B1 and the first segment B2' of the second rod B ") and another second rod segment (formed by the second segment B1" of the first rod B1 and the second segment B2 ") in the spacing direction DD.
The third station 103 comprises a second gluing device 103I configured to connect the first end of the rod B3 to a corresponding end of the second rod segment SP2, i.e. to the end of the first segment B2' of the second rod B2. The second gluing device 103I is configured to connect the second end of the rod B3 to a corresponding end of another second rod segment SP2, i.e. to the end of the second segment B2 "of the second rod B2.
The third station 103 comprises a third cutting element 103T configured to divide the third rod B3 into a corresponding first segment B3 'and a second segment B3", the first segment B3' being connected to the first segment B2 'of the second rod B2 to define a first rod segment group GS1 (defined by a first rod segment SP1 (defined by the first segment B3' of the third rod B3) and a second rod segment SP 2), the second segment B3" being connected to the second segment B2 "of the second rod B2 to define a second rod segment group GS2 (defined by another second rod segment SP2 and the first rod segment SP1, the first rod segment SP1 being defined by the second segment B3" of the third rod B3).
The third stage 103 comprises a third separator 103S configured to separate the first and second rod segment groups GS1, GS2 along the spacing direction DD.
Thus, after the third station, in the combined unit 10 there are two rod segment groups spaced apart from each other in the spacing direction DD, which are then wrapped to form two smoking articles. In this station, both end portions of the first and second rod segment groups GS1 and GS2 have not been checked for the presence of the body CP in the filler material MTA.
Thus, the device 1 considers further checks to check whether the subject CP is present.
Thus, the apparatus 1 comprises a second inspection station 13 configured to capture image data representing images of the outer ends of the first rod segments SP1 of the first rod segment group GS1 and the outer ends of the first rod segments SP1 of the second rod segment group GS 2.
In particular, the second inspection station 13 is configured to inspect whether the main body CP extends to the outer end of the first rod segment SP1 of the first rod segment group GS1 and to the outer end of the first rod segment SP1 of the second rod segment group GS 2.
In one embodiment, the second inspection station 13 includes a second pair of cameras 131, including a right side camera 131A and a left side camera 131B. In one embodiment, the right camera 131A is spaced apart from the left camera 131B along the conveying direction DA. Further, the cameras 131A, 131B of the second pair of cameras 131 are configured to capture image data of the outer end of the first rod segment SP1 of the first rod segment group GS1 and the outer end of the first rod segment SP1 of the second rod segment group GS2, respectively.
In other embodiments, two cameras of the pair of cameras 131 are arranged at the same position in the conveying direction DA and are viewed in opposite directions.
It should therefore be noted that in the preferred embodiment, the cameras of the first pair of cameras are facing respectively capturing images of the two opposite ends of the third rod B3, while the cameras of the second pair of cameras 131 are facing in opposite directions to capture images of the free ends of the first rod segment SP1 of the first rod segment group GS1 and the first rod segment SP1 of the second rod segment group GS 2.
In one embodiment, the second pair of cameras 131 is located above the conveyor and faces in a direction oriented outwardly from the conveyor. In other words, the second pair of cameras 131 is located between the first rod segment group GS1 and the second rod segment group GS2 along the spacing direction DD. This allows framing (frames) the areas of the smoking article that face each other and are therefore not visible from the side of the conveyor of the smoking article.
The apparatus 1 comprises a wrapping device 14 configured to wrap the first and second groups of rod segments GS1, GS2.
At the end of the second inspection station 13, the first and second groups of rod segments GS1, GS2 are processed by a wrapping device 14, which wrapping device 14 wraps each of them to define a respective smoking article.
In one embodiment, the apparatus comprises a third inspection station 15 configured to control wrapping of the smoking article. In particular, the third inspection station 15 comprises a camera configured to capture images of the wrapper IC on the smoking article. These images are sent to the control unit 2, which control unit 2 is configured to process them and to compare them with a reference image to check whether the wrapper IC meets a predetermined quality criterion.
In one embodiment, the device 1 comprises a deactivation device 18 configured to deactivate smoking articles or rods B3 that do not meet specified quality requirements.
In particular, the control unit 2 is connected to the deactivation device 18 to send a driving signal representing information about whether to deactivate the smoking article or rod B3. The drive signal is generated by the control unit based on information received from the first inspection station 121 and/or the second inspection station 13 and/or the third inspection station 15.
The inspection method implemented by the apparatus 1 and the combining unit of the present disclosure is described in detail below.
The method includes the step of capturing an image IMM of the smoking article or a portion thereof (i.e. rod B3). The image is viewed along an optical path oriented along a longitudinal axis L parallel to and coincident with the central axis AC.
The method comprises the step of delivering the image IMM to a machine learning model MA. The machine learning model MA is trained to identify the subject CP in the image. This step is performed by the processor of the control unit 2.
The machine learning model MA is trained to generate positioning data 201 for each image. The positioning data 201 indicates the position of the body CP relative to the tubular wrapper. The positioning data 201 represent a planar geometry defining an object represented in the image IMM. In this way, in addition to checking whether the bulk CP is present inside the filling material MTA, its position relative to the wrapper can be identified.
The method comprises a step FCN performed by the processor of comparing the positioning data 201 with reference data 201' representing a predetermined position of the subject CP. The machine learning model MA includes reference data 201', the reference data 201' determining its operation in the recognition step (i.e., the machine learning model MA defines a recognition algorithm based on the reference data 201 '). The reference data 201' is automatically derived by the machine learning model MA from a plurality of training examples (which include corresponding positioning data vectors associated with respective target values) in a learning step. Preferably, the training examples include a plurality of example images and corresponding target values.
In one embodiment, the machine learning model MA includes a deep neural network. In one embodiment, the neural network is a convolutional neural network.
The neural network may include one or more filtering stages of a maximally pooled type.
The machine learning model MA is trained by the step of delivering a plurality of example images. For each image, a machine learning model is trained by the step of conveying positioning target data representative of a planar geometry defining an object represented in the image.
These examples include a plurality of first images IM1 of a semi-finished smoking article with correctly positioned objects. In one embodiment, these examples include a plurality of second images IM2 of a semi-finished smoking article having an object that is incorrectly positioned according to the selection of the predetermined locating defect.
The method comprises a step FDT of determining a positive or negative recognition result for recognizing an object in the image, which is performed by the control unit 2. The recognition is performed by the machine learning model MA. If the recognition result 202' is negative, the method comprises a step FGN of generating information 203 for rejecting smoking articles, which is performed by the control unit 2. If the recognition result 202 "is affirmative, the method comprises a step FCN of the step of starting to compare the positioning data with reference data representing a predetermined position of the subject CP, performed by the control unit 2. Next, the method includes generating information 203 for rejecting or approving the smoking article in response to the comparing step FCN.
Claims (17)
1. An assembly apparatus (1) for producing multi-component smoking articles, each smoking article comprising a plurality of rod segments defining a respective central Axis (AC), the plurality of rod segments comprising a first rod segment (SP 1) and a second rod segment (SP 2), the first rod segment (SP 1) being provided with a flavouring ingredient, the assembly apparatus (1) comprising:
-a combining unit (10) configured to form rod segment groups (GS 1, GS 2), wherein each rod segment group comprises at least the first rod segment (SP 1) and the second rod segment (SP 2) axially aligned and abutting end-to-end, wherein the rod segment groups (GS 1, GS 2) are transported perpendicular to their central Axis (AC), and wherein the first rod segment (SP 1) is obtained from rod (B3), each rod (B3) having a first end (B31) and a second end (B32) spaced apart along a rod Axis (AC), the combining unit (10) being configured to couple the first end and the second end of the rod (B3) to the respective second rod segment (SP 2), and to divide the rod into a pair of parts (B3 ', B3 ") by cutting the rod transverse to the rod Axis (AC) during a separation station (103T), thereby forming a respective pair of rod segment groups (GS 1, GS 2), each rod segment group (GS 1', GS 2) comprising a respective second segment (B1 ', GS 2"), and a respective second segment (B1 ', GS2 ');
-a packaging unit (14) configured to receive from the combining unit (10) a series of rod segment groups (GS 1, GS 2) conveyed in a conveying direction, to convey the rod segment groups (GS 1, GS 2) perpendicular to a central Axis (AC) of the rod segment groups (GS 1, GS 2) and to wrap a sheet of packaging material on each rod segment group (GS 1, GS 2);
-an inspection system (12) comprising:
-a first inspection station (121) located upstream of the separation station (103T) in the conveying direction and configured to axially observe the first end (B31) and the second end (B32) of each rod;
-a second inspection station (13) downstream of the separation station (103T) in the conveying direction and configured to axially observe the free end of the respective first rod segment (SP 1) of each of the pair of rod segment groups (GS 1, GS 2).
2. Assembly device (1) according to claim 1, comprising a spacer table (103S), the spacer table (103S) being interposed between the separation table (103T) and the second inspection table (13) with respect to the conveying direction and being configured to axially space apart a group of rod segments of the pair of groups of rod segments (GS 1, GS 2).
3. Assembly device (1) according to claim 2, configured to convey a group of rod segments of the pair of rod segment groups (GS 1, GS 2) perpendicular to the rod Axis (AC) between the separation station (103T) and the spacing station (103S).
4. An assembling apparatus (1) according to claim 3, wherein said second inspection station (13) comprises a central camera (131) interposed axially between the rod segment sets of said pair of rod segment sets (GS 1, GS 2).
5. Assembly device (1) according to claim 4, wherein the second inspection station (13) comprises a further central camera (131), the further central camera (131) being axially interposed between the rod segment sets of the pair of rod segment sets (GS 1, GS 2).
6. Assembly device (1) according to claim 5, wherein the second inspection station (13) comprises:
-a right inspection unit (131A) comprising the central camera facing to the right with respect to the conveying direction to view the free end of one of the pair of rod segment groups (GS 1, GS 2);
a left inspection unit (131B) comprising said further central camera facing to the left with respect to said conveying direction for observing the free end of the other rod segment group of said pair of rod segment groups (GS 1, GS 2),
Wherein the right inspection unit (131A) and the left inspection unit (131B) are offset in the conveying direction and define a second pair of cameras (131).
7. Assembly device (1) according to any one of the preceding claims 1 to 6, wherein the first inspection station (121) is provided with a first pair of cameras (122).
8. Assembly device (1) according to claim 7, wherein the cameras of the first pair of cameras (122) have respective light paths oriented in opposite converging directions, and wherein the second pair of cameras (131) have respective light paths aligned but oriented in opposite converging directions.
9. Assembly device (1) according to any one of the preceding claims 1 to 8, comprising a control unit (2), the control unit (2) being connected to the first inspection station (121) and the second inspection station (13) to drive them, the control unit (2) being provided with a processor and a non-transitory data storage device comprising machine readable instructions informing the processor to:
-capturing, by means of the first inspection station (121) and the second inspection station (13), a plurality of images of the smoking article or a portion thereof, viewed along an optical path oriented along a longitudinal axis (L), the smoking article comprising a body (CP) located at a predetermined position inside the smoking article;
-delivering the plurality of Images (IMM) to a machine learning Model (MA) trained to identify the subject (CP) in the Images (IMM).
10. Assembly device (1) according to any one of the preceding claims 1 to 9, comprising a conveyor configured to generate a flow of smoking articles or parts thereof moving along the predetermined path, and a control unit (2) connected to the first inspection station (121) and the second inspection station (13) to drive them, the control unit (2) being provided with a processor and with non-transitory data storage comprising machine-readable instructions telling the processor for each smoking article or part thereof:
-capturing, by means of the first inspection station (121) and the second inspection station (13), a plurality of images of the smoking article or a portion thereof observed along a path having a predetermined orientation;
-delivering the plurality of Images (IMM) to a machine learning Model (MA), the machine learning Model (MA) being trained to identify a predetermined defect class of the smoking article or a part thereof.
11. An assembly method for producing multi-component smoking articles, each smoking article comprising a plurality of rod segments defining a respective central Axis (AC), the plurality of rod segments comprising a first rod segment (SP 1) and a second rod segment (SP 2), the first rod segment (SP 1) being provided with a flavouring ingredient, the method comprising the steps of:
a) By means of the combined unit (10),
-Conveying a stream of bars (B3) in a direction transverse to a bar Axis (AC), each bar (B3) having a flavouring composition and being elongated along the bar Axis (AC) from a first end (B31) to a second end (B32);
-coupling a respective second rod segment (SP 2) to the first end (B31) and the second end (B32) of the rod;
-in a separation station (103T), dividing the rod (B3) into a pair of portions (B3 ', B3 ") by cutting the rod (B3) transversely to the rod Axis (AC), thereby forming a corresponding pair of rod segment groups (GS 1, GS 2), each comprising a respective rod portion (B3', B3"), defining a respective first rod segment (SP 1) and a respective second rod segment (SP 2) axially aligned along a central axis and abutting end-to-end;
-transporting the group of rod segments (GS 1, GS 2) perpendicular to a central Axis (AC) of the group of rod segments (GS 1, GS 2);
b) Through the packaging unit (14),
-Transporting the group of rod segments (GS 1, GS 2) perpendicular to a central Axis (AC) of the group of rod segments (GS 1, GS 2);
-wrapping said group of rod segments (GS 1, GS 2) in a sheet of packaging material;
c) By means of an inspection system (12),
-A first step of observing the first end (B31) and the second end (B32) of each rod (B3) in a first inspection station (121) located upstream of the separation station (103T) in the conveying direction;
-a second step of observing the free end of the respective first rod segment (SP 1) of each rod segment group of the pair of rod segment groups (GS 1, GS 2) in a second inspection station (13) downstream of the separation station (103T) in the conveying direction.
12. The method according to claim 11, further comprising the step of spacing rod segment sets of the pair of rod segment sets (GS 1, GS 2) in an axial direction (DD) after the separation station (103T) and before the second inspection station (13).
13. A method according to claim 12, wherein during the step of spacing, the groups of rod segments of the pair of groups of rod segments (GS 1, GS 2) are also transported transversely to their axes.
14. The method of any one of claims 11 to 13, wherein the coupling step precedes the decoupling step.
15. Method according to any one of claims 11 to 14, wherein the second inspection station (13) comprises the following sub-steps in sequence:
-observing the free end of one of the pair of rod segment groups (GS 1, GS 2) by means of a central camera (131A);
-conveying the groups of rod segments (GS 1, GS 2) in the conveying direction;
-observing the free end of the other rod segment group of the pair of rod segment groups (GS 1, GS 2) by means of a further central camera (131B).
16. The method according to any one of claims 11 to 15, wherein the smoking article comprises a body (CP) located at a predetermined position in the smoking article, the method further comprising the step of delivering Images (IMM) captured by the first inspection station (121) and the second inspection station (13) to a machine learning Model (MA) trained to identify the body (CP) in the Images (IMM).
17. A method according to any one of claims 11 to 16, comprising, for each smoking article or part thereof: a step of generating an ordered flow of smoking articles or parts thereof moving one after the other along a predetermined path,
A step of transferring the Images (IMM) captured by the first inspection stage (121) and the second inspection stage (13) to a machine learning Model (MA), the first inspection stage (121) and the second inspection stage (13) being positioned along a predetermined path,
Wherein the machine learning Model (MA) is trained to identify predetermined defect categories for the smoking article or a portion thereof.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| IT102021000023954 | 2021-09-17 | ||
| IT102021000023954A IT202100023954A1 (en) | 2021-09-17 | 2021-09-17 | Assembly apparatus and assembly method for producing multi-component smoking articles. |
| PCT/IB2022/058703 WO2023042113A2 (en) | 2021-09-17 | 2022-09-15 | Assembling apparatus and assembling method for producing multicomponent smoking articles |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117915791A true CN117915791A (en) | 2024-04-19 |
Family
ID=78771040
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202280061344.6A Pending CN117915791A (en) | 2021-09-17 | 2022-09-15 | Assembly device and assembly method for producing a multi-component smoking article |
Country Status (5)
| Country | Link |
|---|---|
| EP (1) | EP4351365A2 (en) |
| KR (1) | KR20240054384A (en) |
| CN (1) | CN117915791A (en) |
| IT (1) | IT202100023954A1 (en) |
| WO (1) | WO2023042113A2 (en) |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07135951A (en) * | 1993-11-16 | 1995-05-30 | Japan Tobacco Inc | Device for inspecting foot surface of filter cigarette |
| IT1393013B1 (en) * | 2008-12-18 | 2012-04-11 | Gd Spa | METHOD FOR SETTING UP AND MANAGEMENT OF THE CONTROL DEVICE IN A MACHINE FOR THE PRODUCTION OF SMOKE ITEMS. |
| GB201013072D0 (en) | 2010-08-04 | 2010-09-15 | British American Tobacco Co | Smoking article |
| CN104636707B (en) * | 2013-11-07 | 2018-03-23 | 同方威视技术股份有限公司 | The method of automatic detection cigarette |
| DE102014203158B4 (en) * | 2014-02-21 | 2016-01-14 | Hauni Maschinenbau Ag | Optical inspection of rod-shaped articles of the tobacco processing industry |
| EP3606361B1 (en) * | 2017-04-07 | 2021-06-16 | International Tobacco Machinery Poland SP. Z O.O. | Apparatus and method for rejection of defective rod-like articles from a mass flow of rod-like articles of the tobacco industry |
| EP3476228B1 (en) * | 2017-10-25 | 2020-07-22 | International Tobacco Machinery Poland Sp. z o.o. | Method and apparatus for filling transport containers with rod-like articles of tabacco industry |
| IT201800002250A1 (en) | 2018-01-31 | 2019-07-31 | Gd Spa | Method and apparatus for the inspection of the ends of rod-shaped pieces of the tobacco industry |
| IT201800020083A1 (en) | 2018-12-18 | 2020-06-18 | Gd Spa | MACHINE FOR THE MAKING OF TUBULAR SLICES FOR THE TOBACCO INDUSTRY |
| CN111972700B (en) * | 2019-05-22 | 2023-04-25 | 上海烟草集团有限责任公司 | Cigarette appearance detection method and device, equipment, system and medium thereof |
-
2021
- 2021-09-17 IT IT102021000023954A patent/IT202100023954A1/en unknown
-
2022
- 2022-09-15 KR KR1020247011918A patent/KR20240054384A/en unknown
- 2022-09-15 WO PCT/IB2022/058703 patent/WO2023042113A2/en active Application Filing
- 2022-09-15 EP EP22785793.5A patent/EP4351365A2/en active Pending
- 2022-09-15 CN CN202280061344.6A patent/CN117915791A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| KR20240054384A (en) | 2024-04-25 |
| WO2023042113A2 (en) | 2023-03-23 |
| EP4351365A2 (en) | 2024-04-17 |
| IT202100023954A1 (en) | 2023-03-17 |
| WO2023042113A3 (en) | 2023-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2768734B1 (en) | Cigarette package coding system and associated method | |
| CN106880078B (en) | For manufacturing the method and system of bar-type article | |
| EP2550876B1 (en) | Method and device for filter inspection | |
| CN102328822B (en) | Method for examining sortation of goods | |
| US20150117982A1 (en) | Method and device for removing at least one book block from and/or supplying at least one book block to a conveying section of a book production line | |
| EP3606361B1 (en) | Apparatus and method for rejection of defective rod-like articles from a mass flow of rod-like articles of the tobacco industry | |
| WO2012117499A1 (en) | Inspection system of filter rod | |
| CN117915791A (en) | Assembly device and assembly method for producing a multi-component smoking article | |
| US20060130858A1 (en) | Module for a machine and method for perforating rod-shaped articles of the tobacco industry | |
| CN117956910A (en) | Method and system for inspecting smoking articles | |
| JP6412034B2 (en) | Inspection equipment | |
| CN110234240B (en) | Method and system for producing multi-segment articles of the tobacco industry | |
| JP2006262900A (en) | Method and apparatus for checking product quality of tobacco product in production line | |
| US9221080B2 (en) | Method for inspection and sorting of pistachios | |
| KR101750533B1 (en) | Apparatus For Classifying Agricultural Product | |
| US11752524B2 (en) | Method for recovering a posteriori information about the operation of a plant for automatic classification and sorting of fruit | |
| JP2014113061A (en) | Inspection system and inspection method for cigarette filter | |
| DE4200546A1 (en) | Automatic sortation system for e.g. polyethylene terepthalate bottles - includes feeding through inspection device where faults generate corresp. signals and affected bottles are removed at suitable stations | |
| DK180419B1 (en) | System for cutting and trimming meat cuts | |
| CN115452737A (en) | Tobacco bale mildew tobacco leaf online detection and elimination method, platform and readable storage medium | |
| CN111295103A (en) | Unit and method for inspecting groups of portions of tobacco industry articles | |
| CN112754068A (en) | Feeding device for feeding tobacco industry segments | |
| JP2005040792A (en) | Bottle inspection system | |
| CN116161374A (en) | Method for synchronizing indexes during production of gloves or condoms | |
| CN116871200A (en) | Automatic detection and repair method for PCBA product |
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 |