Inspection system for yarn bobbins and method for inspecting yarn bobbins - Patents.com

Abstract

An inspection system for yarn bobbins is provided. A system should be provided that allows for improved automation of yarn bobbin inspection. The system comprises an image capture device (5) for capturing images of the yarn bobbin (12), a database (3) in which a first data set relating to at least a first type of defect is stored, the first data set being generated by using a sample of yarn bobbins (12) having the first type of defect, and an application (4) for determining whether the yarn bobbin (12) inspected using the image capture device (5) has the first type of defect. Further, a method for inspecting yarn bobbins and assigning different types of defects to the yarn bobbins is provided.

Description

[Technical field]

[0001] The present invention relates to an inspection system for yarn bobbins capable of inspecting the yarn bobbins for defects. Additionally, a respective method for inspecting such yarn bobbins is provided. [Background technology]

[0002] To date, in the industrial process of yarn production, yarn bobbins are inspected by human eyes to look for the presence of certain defects or faults on the yarn bobbin. If such defects or faults are present, the respective bobbin is marked or removed from the bobbin that is to be sent to the customer. However, several techniques have been disclosed in the scientific literature that allow the inspection to be performed by physical measurements, in particular by image inspection systems. Such prior art techniques are described, for example, in the scientific articles Automatic Bobbin Inspection System, J. Baumgartinger, R. Konig, Lenzinger Berichte, 82 (2003) 70-75, and An Innovative Solution for Abrage Fault Detection on Yarn Bobbin and Fabric Surface, HICElik, E. Gultekin, LCDDulger, HISunbul, H.Kani in ICENS, 5 th This was reported at the International Conference on Engineering and Natural Science, June 12-16, 2019 in Prague.

[0003] In the latter paper, a visual inspection system for a generic prototype machine is described that uses an illumination section and a camera. The illumination section shines light of a certain temperature on the surface of the yarn bobbin, making so-called wear defects (defects caused by wear) more visible. These defects are, for example, on the surface of the yarn bobbin and are caused by wear. It is shown that by modifying the brightness and adjusting the image processing of the acquired images, the respective wear defects (wear defects) can be made more visible.

[0004] The scientific paper Automatic Bobbin Inspection System (J. Baumgartinger & R. Konig, 2003) describes the different commonly known defects of yarn bobbins in terms of geometrical shape, macrostructural defects and microstructural defects. In particular, it is described how the detection of broken filaments can be performed. A CCD camera records a laser beam reflected at the surfaces of the yarn bobbin while the yarn bobbin is rotated and analyzed, and if the reflected beam meets certain conditions, it is determined that a broken filament is located at the respective surface. These surfaces are the end surfaces of the bobbin in the longitudinal direction of the bobbin. This system requires a lot of effort to set the respective boundary conditions etc. in order to detect broken filaments. Summary of the Invention [Problem to be solved by the invention]

[0005] In view of the above prior art documents, the inventors have now found that it is possible to apply a new approach and use a system operating on artificial intelligence and / or deep learning to determine whether a particular defect is present in a yarn bobbin. [Means for solving the problem]

[0006] With this in mind, an inspection system is provided having the features defined in claim 1. In a first step, a sample of yarn bobbins having a particular type of defect (or fault) is used to acquire an image of each yarn bobbin via an image acquisition device. From the acquired images data is obtained that is stored in a database.

[0007] Thus, a number of yarn bobbins having each type of defect are used to populate a first data set in a database. Then, when additional yarn bobbins are evaluated later in the industrial process, it can be automatically determined or derived whether a particular type of defect is present. It can then be determined whether this type of defect is present.

[0008] That is, the application determines whether the respective data acquired by the image acquisition device corresponds or substantially corresponds to the data in the first data set. In this case, it is determined that a first defect is present. In order to have a valid first data set in the database, it is beneficial to generate said data set using samples of yarn bobbins having this particular type of defect, called a "first type of defect", where this first type of defect is provided in different areas respectively or has different aspects. Since the various aspects of the first type of defect are extensive in the respective different samples, the respective first data set can be better used to identify whether the first defect is included in the yarn bobbin undergoing inspection during production.

[0009] The inspection system may include an image capture device for capturing an image of the yarn bobbin, the image data being compared in the application to a first data set stored in a database to determine if the yarn bobbin inspected using the image capture device has a first type of defect.

[0010] According to a further development, a second data set corresponding to a second type of defect is stored in the database. This second data set can also be set by using a sample of yarn bobbins having this second type of defect. The aspects described above for the generation of the first data set can also be applied to the generation of the second data set.

[0011] Beneficially, the sample yarn bobbins used to establish the respective first and second data sets have only the respective first and / or second defects.

[0012] The first and second data sets do not have to be provided in different sections of the database, but can all be stored together in one section of the database. Each data associated with the first and second data sets may have a respective identifier that assigns it to a first or second type of defect. Samples having both types of defects may also be used to populate the data sets. This data may have identifiers that correspond to the first and second types of defects.

[0013] Thus, the system is also able to determine whether the defect in the yarn bobbin being inspected is a second type of defect.

[0014] Each yarn bobbin having the first and / or second type of defect can be removed from the batch of bobbins shipped to the customer. Each bobbin having a defect can be sorted to form a batch of yarn bobbins having the first type of defect, a batch of yarn bobbins having the second type of defect, and a batch of yarn bobbins having both types of defects.

[0015] Each batch can be placed on a different pallet, etc. Each type of defect can be an elastane free defect, a damaged bobbin defect, a wear defect, a color defect, or a diameter defect.

[0016] An elastane-free defect is to be understood as follows: Some yarns, for example those used in the production of denim, may have a certain elasticity. To ensure this elasticity, at least one elastic filament may be provided in the yarn to adjust the respective properties. Further filaments with inelasticity may be provided, which may be twisted together during ring spinning to form a core. This core may be encapsulated by a cover layer comprising staple fibres, for example natural fibres. However, during the spinning (particularly ring spinning) process, the elastic filaments contained in the core may break, and thus there may be areas in the core where no elastic filaments are provided. These areas are called elastane-free areas. An elastane-free defect is therefore a defect in which there are areas along the yarn where there are areas in the elastane-containing yarn where no elastane is provided. This elastane is not limited to materials corresponding to the trademark "Elastane" but may be provided by any elastic filament, such as Lycra. The inventors have found for the first time that it is possible to detect such elastane-free defects using a specific image acquisition device and artificial intelligence.

[0017] A damaged bobbin defect is a defect related to damage to the bobbin itself. The term bobbin, as opposed to the term yarn bobbin, is used in this application only for the central shaft on which the yarn is wound. Thus, the yarn bobbin includes the yarn wound on the bobbin. In the following, as long as the term bobbin is used, it means the shaft on which the yarn is wound. In the following, when the term yarn bobbin is used, it means the complete arrangement including the yarn wound on the bobbin.

[0018] Each bobbin may be broken or otherwise damaged, which may be seen, for example, when an image acquisition system is focused on the leading longitudinal face of the yarn bobbin.

[0019] Wear defects are defects resulting from wear of the yarn and bobbin during handling. A color defect is a defect in the color of the yarn. In certain production processes, the yarn may be colored. The respective results should correspond to a standardized color code. It may be the case that the color code is painted on the inside of the bobbin, for example via a sticker. The respective system may obtain the respective color code and determine whether the detected color of the yarn matches the color code. This may ensure that the respective color ordered by the customer is fulfilled for the respective yarn bobbin.

[0020] A diameter defect is a defect in the diameter of a yarn bobbin. Each batch of bobbins typically has a predetermined diameter, e.g., a diameter ordered by a customer. Therefore, an inspection system is used to determine diameter defects in order to control each yarn bobbin that is packaged and shipped to a customer.

[0021] Any of the respective defects, alone or in any combination, may be determined by the same inspection system.

[0022] This means that in addition to elastane free defects, damaged bobbin defects and / or wear defects and / or color defects and / or diameter defects can be detected.

[0023] For each defect, a different data set is generated using the sample yarn bobbin and the data sets are stored in a database.

[0024] From the database it is determined which of the stored data corresponds to the data of the acquired image, thereby making a respective assignment of the different defects.

[0025] The application is configured to determine a type of defect in a yarn bobbin inspected using the image capture device.

[0026] The inventors have further noted that it is advantageous for the application to have a defect assignment module and additionally a defect marker module, whereby a type of defect in the yarn bobbin inspected by means of the image acquisition device is assigned to each yarn bobbin, and whereby data is generated for providing a marker that can be superimposed on the image of the yarn bobbin acquired by the image acquisition device.

[0027] With such an arrangement, the human operator operating the inspection system can better identify each defect and where it is located on each bobbin.

[0028] Beneficially, the marker is defined by a collection of pixels, the size and shape of which corresponds to the area of ​​the defect.

[0029] Different types of defects may be assigned to different colors used for the markers. For example, the color of a pixel indicating an elastane free defect may be red, the color of a pixel indicating a damaged bobbin defect may be green, the color of a pixel indicating a wear defect may be blue, and the color of a pixel indicating a diameter defect may be yellow. The respective markers may be superimposed on the respective image of the respective yarn bobbin acquired with the image acquisition device, and this superimposed image can be visualized on the display. Then, each person operating the system can see the display to which the respective defect is assigned. To make it even easier for the operator to determine where the defect is located, it is beneficial that on the display an image of the yarn bobbin (without the superimposed marker) is shown next to an image of the yarn bobbin (with the superimposed marker), both images being of the same size (magnification). The location of the defect is better visible than in an image without the marker.

[0030] Although the transport of each of the yarn bobbins through the systems is not separated, it has been considered beneficial for each system to comprise a bobbin holder mounted on a rail, which can be moved along the rail through an inspection zone (the zone in which image acquisition is performed).

[0031] From the batch of bobbins to be inspected, each yarn bobbin may be placed into a respective bobbin holder, either manually by a user (operator) or automatically by a robot. Through the bobbin holder, the yarn bobbins move through an inspection zone. The yarn bobbins can then be removed from the yarn holder, either manually by a human or automatically by a robot, and automatically assigned to a pallet on which the respective defective bobbins are stored and / or to a pallet on which the non-defective bobbins are stored.

[0032] The allocation may be done automatically or by respective light systems having red or green lights. Green lights correspond to yarn bobbins without defects so that an operator can allocate the yarn bobbins to a package of yarn bobbins to be sent to a customer. Red lights correspond to yarns with defects. Different light types can also be used to allocate yarn bobbins to different defect types.

[0033] According to a further development, the yarn bobbin holder is adapted to rotate the yarn bobbin along an axis that is perpendicular to the bobbin central axis and that may also be perpendicular to the rail extension direction. Each yarn bobbin advantageously moves along the rail along its longitudinal direction. However, in the inspection zone, it is advantageous to rotate each yarn bobbin by 90° so that the respective axial direction of the bobbin is perpendicular to the rail extension direction.

[0034] In such an arrangement, each image capture device is typically mounted on a different side of a longitudinal rail to better inspect each longitudinal end face of the bobbin. A rotation of the yarn bobbin may also be performed during image capture to capture images at different areas of the yarn bobbin.

[0035] Each bobbin holder may be constructed as a ring with a fixed area in which the yarn bobbins may be placed. The yarn bobbins should be placed such that relative movement of the yarn bobbins is prevented. This may be a circumferential movement or a translational movement of the yarn bobbins. It is beneficial that both circumferential and translational relative movements are prevented.

[0036] The fixing area may be defined by two parallel rods extending in the direction of the ring central axis of the ring defining the bobbin holder. The two parallel rods may have a gap between them that holds the bobbin at its outer circumferential surface. Such a configuration makes it easy to place yarn bobbins of different diameters in the same holder.

[0037] Each ring of the bobbin holders may have a rotating hinge attached to the rail via a movable element. In certain inspection systems, it may be beneficial for a plurality of such bobbin holders to be arranged one after the other along the rail, and it may be advantageous for the bobbin holders to be adapted to move together along the rail. That means that each of the respective bobbin holders may be connected to an adjacent bobbin holder by a chain or cable or other coupling, which means that as the chain or cable or other coupling is drawn along the respective rail, the bobbin holders move a predetermined distance from each other through the system.

[0038] It is further advantageous for the system to include a darkroom having two openings through which the rails extend from the inlet and outlet. The image acquisition device may be provided within the darkroom. When such a darkroom is used, ambient light is prevented from interfering with image acquisition and generating artifacts.

[0039] However, the use of such a darkroom is not necessary, particularly if the image acquisition device does not operate in the visible spectrum, but rather in the infrared or x-ray spectrum.

[0040] Each image acquisition device advantageously comprises an illumination section for illuminating an area of ​​the yarn bobbin for defect detection and a camera device for acquiring an image of the area, via which the respective area can be illuminated and via which the illuminated area can be photographed.

[0041] Additionally, the system may include an image processing and conditioning module. Through the image processing and conditioning module, each acquired image can be filtered, which may provide better data quality in which it is easier to detect each type of defect.

[0042] It has been shown that for each different type of defect it is beneficial that a different image acquisition device is used, since different image acquisition conditions may be favorable for different types of defects. On the one hand, different filtering can be applied for the different types of defects by means of an image processing and conditioning module. On the other hand and / or additionally, the respective camera devices used are sensitive to different wavelengths and / or the respective illumination sections irradiate radiation having different wavelengths and / or having different wavelength ranges and / or color temperatures.

[0043] In particular, the illumination section operates at a particular wavelength or color temperature depending on the defect type being detected.

[0044] Depending on the defect type being detected, different filters may be used in the image processing and conditioning module.

[0045] Each image capture device used may be one or more of the following: an image capture device for elastane free defects, an image capture device for damaged bobbin defects, an image capture device for wear defects, an image capture device for color defects, and an image capture device for diameter defects.

[0046] Each of the defect types has already been described in the previous sections. The difference between each of the image capture devices may be that they operate at different wavelengths and / or different color temperatures, and / or each camera device may have different sensitivities.

[0047] In particular, in an image acquisition device for elastane-free defects, it has been found to be advantageous for the illumination section to have a ring shape and for the camera device to be arranged in a central region of the ring, the ring-shaped illumination section being mounted such that each beam is directed to each longitudinal end face of the yarn bobbin, and the central axis of each of the rings of the illumination section may thus be arranged perpendicular to the extension direction of the rail.

[0048] In particular, it has been found to be advantageous for two image acquisition devices for elastane-free defect detection to be arranged on opposite sides of the rail, with the advantage that both image acquisition devices are centrally aligned with respect to each other, said aligned centres being perpendicular to the extension direction of the rail.

[0049] Furthermore, it has been considered beneficial to provide at least one further image acquisition device upstream and downstream of the image acquisition device for elastane-free defects. Such an image acquisition device may be an image acquisition device for wear defects, color defects, diameter defects, etc.

[0050] The system may further be configured such that yarn bobbins fed into the system are automatically classified according to the defect type detected.

[0051] The system may further be configured such that the data acquired during defect detection is periodically stored in a database after a human (operator) has confirmed that the actual detected defect corresponds to the defect type assigned to the yarn bobbin by the system.

[0052] For this reason, it is beneficial to have a display unit and markers on the overlaid images, so that each person operating the inspection system can instantly feed and input more data (wider data set) into the database to have a better assignment to the defect type.

[0053] Typically, the system is configured such that the defect assignment to the different types of defects is done by artificial intelligence, and / or the system is specifically configured to operate using deep learning.

[0054] In addition to the aforementioned inspection system, a method is provided for inspecting yarn bobbins and assigning different types of defects thereto. The method uses an application and a database for the defect assignment. Each of the aforementioned aspects described with respect to the system may also be provided for the respective inspection method.

[0055] The method may be an automated method carried out on a computer. Additionally, computer readable applications may be provided that perform the respective bobbin inspections and / or automatically control the respective systems.

[0056] In the following, some embodiments of the invention will be described with reference to the drawings. [Brief description of the drawings]

[0057] [Figure 1] FIG. 1 is a schematic diagram of a portion of a system including an inspection zone located within a darkroom. [Diagram 2] FIG. 1 is a detailed view of the layout of the inspection zones in the darkroom. [Figure 3a] FIG. 13 shows different images in which elastane-free defects have been detected and the respective images have markers superimposed (right side of the figure). [Figure 3b] FIG. 13 shows different images in which elastane-free defects have been detected and the respective images have markers superimposed (right side of the figure). [Figure 3c] FIG. 13 shows different images in which elastane-free defects have been detected and the respective images have markers superimposed (right side of the figure). [Figure 3d] FIG. 13 shows different images in which elastane-free defects have been detected and the respective images have markers superimposed (right side of the figure). [Figure 4a] 1 is a diagram of an image generated by wear defect detection, in which on the right side of the figure, wear defect areas are assigned by markers to the areas on the longitudinal end sides of the respective yarn bobbins. [Figure 4b] 1 is a diagram of an image generated by wear defect detection, in which on the right side of the figure, wear defect areas are assigned by markers to the areas on the longitudinal end sides of the respective yarn bobbins. [Figure 5a] The damaged bobbin defect and markers are shown superimposed on the acquired image on the right side of the figure. [Figure 5b] The damaged bobbin defect and markers are shown superimposed on the acquired image on the right side of the figure. [Figure 5c] The damaged bobbin defect and markers are shown superimposed on the acquired image on the right side of the figure. [Figure 6] FIG. 1 is a schematic diagram illustrating the overall configuration of a system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0058] On the right side of FIG. 6, a computer 1 and a display 2 are shown. The computer 1 may have a database 3 stored in a storage area and an application 4 running on this computer. An image acquisition device 5 is connected to the computer 1, allowing data to be exchanged between the image acquisition device 5 and the computer 1. Via an interface, data can be entered into the respective database 3. This is shown diagrammatically by the "Data Entry" box in FIG. 6. The image acquisition device 5 and / or the bobbin selection means for selecting the respective yarn bobbin after defect determination and / or the transport of the yarn bobbin 12 along the rail 8, which will be described later, can be controlled by a control module in the computer 1. Said control module may also be integrated in the application 4. However, in FIG. 6, the control module is shown as a separate and independent module in the computer 1.

[0059] On the left side of Fig. 6, a schematic arrangement of a darkroom 6 is shown with an image capture device 5 mounted in a specific case. A rail 8 extends from an entrance opening 9 of the darkroom 6 to an exit opening 10 of the darkroom 6 (e.g. also Fig. 1).

[0060] The yarn bobbins 12 to be evaluated are first placed on a holder 11, not shown in said figures (but identified with reference number 11 in figures 1 and 2). The holder 11 is mounted on rails 8. The yarn bobbins 12 mounted on the holder 11 are then moved along the rails 8 to an inspection area in the darkroom 6. In the inspection area, the image acquisition device 5 acquires an image of the respective bobbin. In certain cases, it may be advantageous for images to be acquired from the respective end faces, sectioning the yarn bobbins in their longitudinal direction. The end faces have the reference number 13 in figure 6. However, the inspection is not limited to the respective end faces, but can also be performed at the respective circumferential faces. Also, inspection of the interior of the yarn bobbins 12 can be performed when the respective image acquisition device operates at a wavelength or wavelength range that penetrates the yarn bobbins.

[0061] In the particular case, however, each image acquisition device comprises a camera arrangement 14 and an illumination section 15. Via the illumination section 15, radiation having a particular wavelength or comprising waves of a particular wavelength band or having a particular color temperature is illuminated onto each yarn bobbin 12.

[0062] By means of a respective camera device 14, an image of the illuminated yarn bobbin 12 is taken. The respective image data is transferred to the computer 1. In a respective image processing and conditioning module 16, which may be part of the computer 1, respective filtering rules may be applied depending on the respective defects detected. The respective filtered data is fed to the application 4. In the application 4, it is determined which of a number of defect types the yarn bobbin 12 under evaluation is to be given. After the respective bobbin inspection, the yarn bobbins 12 are moved out of the darkroom 6 through the exit opening 10, the yarn bobbins 12 can be selected, and the respective yarn bobbins 12 that are free of defects or free of significant defects can be assigned to respective batches of yarn bobbins to be shipped to customers.

[0063] Each image capture device 5 may have wear detection functionality, broken bobbin detection functionality, color detection functionality, diameter detection functionality and elastane free zone detection functionality. Using each functionality, each defect may be detected.

[0064] In the particular case shown in Figure 6, the respective functions are shown as alternatives or may exist simultaneously for one image acquisition device 5 shown therein. The respective functions may be provided within one image acquisition device, but separate image acquisition devices may also be provided, each with a camera device 14 and a respective illumination section 15. In each of the respective image acquisition devices, the respective camera device and illumination section may have a different specific configuration with respect to the illuminated wavelength or wavelength range or sensitivity, as will be explained in the following sections.

[0065] However, image capture device 5 generates image data that is provided to application 4 .

[0066] In the application 4, the respective data is compared with a data set stored in a database 3. This database 3 is set up by feeding the database 3 with data for each type of defect. To do so, in a first step of starting the respective inspection system, a yarn bobbin 12 with the respective type of defect is inspected in the system and the respective data is assigned to the specific defect type. To do so, the data may have an identifier that identifies the specific defect. This feeding of yarn bobbins with different types of defects may be done for different defects. For example, 10 to 100 yarn bobbins with elastane free defects are fed into the system and the respective data derived with the image acquisition device are fed into the database.

[0067] Also, 10 to 100 yarn bobbins with broken bobbin defects are used to generate the bobbin defect data in the database. The same can be done with sample bobbins with wear defects, bobbins with different specific diameters, and bobbins with specific colors.

[0068] This training of the database and the addition of further data to the database may be done periodically after a specified period or number of inspected yarn bobbins, or simultaneously during the inspection of each yarn bobbin being evaluated. To do so, it is necessary to match each identified defect (identified by the system) and see if it corresponds to each defect that should have been identified.

[0069] This can be done by a human. This can be done after each yarn bobbin leaves the exit opening 10 and each human (operator) looks at the defect and decides whether the defect corresponds to a specific defect identified by the system, in which case the respective data is provided to the database as data corresponding to this type of defect.

[0070] This assignment may also be made with the aid of a display device when a human is looking at the display device. A color marking or at least a marking may be provided that is superimposed on the acquired image to help the operator to assign whether each detected defect corresponds to a respective defect actually present on the respective yarn bobbin.

[0071] The image acquired can be any image, even an X-ray image allowing to inspect not only the surface of the yarn bobbin but also its interior. However, each marker may be generated by a number of pixels corresponding to the area in which the defect is detected.

[0072] Thus, by comparing the image without pixels with the image with pixels when the images are placed next to each other on the screen, the operator can ascertain whether the detected defect corresponds to the defect type expected to be detected, in which case the respective data can be assigned in a database as an identifier characterizing said defect type.

[0073] This allows each database 3 and application 4 to be trained.

[0074] Application 4 is an application with artificial knowledge, which searches a database for similarities between the acquired images and images with specific defects. In order to have a good database, it is beneficial to have sample yarn bobbins with very different aspects of defect location, defect spread or defect size for specific defects, such as elastane free. Thus, the differences between the aspects of a specific type of defect have a strong variation. Thus, a more reliable assignment of the acquired images of the bobbin to be evaluated can be more easily obtained. The wider the diversity of the aspects of a specific defect (for example the diversity of elastane free defects), the higher the reliability of the data generated and its suitability used in the application.

[0075] Figure 1 shows an example of the configuration of the left side of the system shown in Figure 6. Figure 1 shows a darkroom 6 surrounding an inspection area. Each rail 8 extends from an entrance opening 9 to an exit opening 10. Each opening may have a respective opening area from 22 that is 150% larger than a respective yarn bobbin cross-sectional area perpendicular to its longitudinal axis. This reduced size of the opening prevents excess light from entering the inspection area.

[0076] The rail 8 can also be seen in FIG. 2. A ring 17 corresponding to the bobbin holder 11 is hung thereon. On the underside of the ring 17 opposite to the side provided with the rotation hinge 19, two parallel extending rods 18 are provided with a gap 20 between them. In the gap 20, the respective outer circumferential surface of each yarn bobbin 12 can be fixed. This makes it possible to prevent the bobbin from moving in a translational manner. However, the yarn bobbin itself may still be rotated about its central axis.

[0077] Each ring 17 is attached via a rotating hinge 19 to a movable element provided on the underside of the rail 8, which is not visible in the figure, and each ring can rotate as shown in the sequence of Figures 1 and 2.

[0078] That is, when each yarn bobbin 12 enters the darkroom 6, the bobbin direction (axial direction) coincides with the longitudinal direction of the rail. In the inspection area, the bobbins may be rotated (e.g. automatically by a control module) in certain cases by about 90° to inspect the front and rear end faces of each yarn bobbin 12. However, the rotation of the yarn bobbins may also be performed during image acquisition in the inspection area.

[0079] In the particular configuration shown in Figures 1 and 2, elements with references 23a, 23b correspond to illumination sections of image capture devices for identifying elastane defects on the yarn bobbin. Elements with references 24a, 24b correspond to camera devices of said respective image capture devices for determining elastane defects. Each camera device 24a, 24b is provided in a central area along the central axis of the illumination section 23a, 23b. The illumination section is defined by a ring that illuminates a respective area of ​​the yarn bobbin with a particular wavelength or wavelength band or light temperature.

[0080] The respective illumination wavelengths and / or the respective sensitivity and camera devices are selected for their good ability to detect elastane-free defects. In this particular case, for elastane-free defects, two image processing and image acquisition devices are provided on either side of each yarn bobbin 12, flanking the rail 8.

[0081] In the particular case of this embodiment downstream of this image acquisition device for elastane-free defect detection, an image acquisition device for abrasion detection and an image acquisition device for color defect detection are provided. The image acquisition device for color defect detection has the reference 5b. The image acquisition device for abrasion defect detection has the reference 5c. Each device comprises a respective illumination section and a camera section. In particular, the respective illumination for abrasion detection is plate-shaped and a camera is provided which looks at the end face of the respective yarn bobbin through a hole in the plate, whereby a plane wave illumination is provided.

[0082] The illumination section for color defect detection has a bell-like shape so that the illumination beams illuminate the sample at different angles. In the case of the image acquisition device for color defect detection, the respective camera devices 14 are also held in concentric circles.

[0083] After each measurement has been performed and each holder 11 has moved through the inspection zone, each holder 11 is rotated back to its original orientation and then each holder 11 moves out of the system through the exit opening 10.

[0084] At this point, the yarn bobbin is removed from the holder and bobbin selection is performed automatically, for example as indicated by the arrow between the computer and the box "BOBBIN SELECTION MEANS" in Figure 6. This automatic selection can also be controlled by the control module.

[0085] In each of Figures 3, 4 and 5 it is shown how the respective data can be processed in the application 4 so that the respective markers are generated. To do so, the application 4 comprises, in addition to the defect assignment module 25, a defect marker module 26.

[0086] In the defect assignment module 25, the respective defect assignment is performed via a respective matching of the acquired image data with data in the database 3 via artificial intelligence. Via a respective defect marker module 26, a marker is generated, which in this case may be a specific group of pixels corresponding to the area where the respective defect was detected.

[0087] The markers are superimposed on the images, and display 2 can show (as shown in Figures 3a, 3b, 3c and 3d) the respective images without the markers and the corresponding areas of the image with the markers (the left image in Figures 3-5 is the image without the marker, and the right image in each is an image with the marker superimposed in the same position as the image without the marker, and at the same magnification as the image without the marker). Thus, when a user looks at display 2, he can see where in each area of ​​the original image each defect was detected and what that defect looks like.

[0088] Each defect shown in Figures 3a-3d corresponds to an elastane-free defect. Elastane-free defects have certain characteristics that are best seen, for example, in Figure 3c. On the left side of Figure 3c, in the area where the respective marker is shown in the right image, it is shown that the respective yarn does not extend to a circumferential section and has a wave. From this wave shape, it can be inferred that no elastane is provided in the core of said section of yarn, as the yarn hangs loosely and creates a wave-like appearance.

[0089] It has now been shown for the first time by the inventors that specific elastane-free defects can be determined by artificial intelligence and that respective markers can be assigned to them.

[0090] For example, by comparing Figures 3a-3d with Figures 4a and 4b, which show result images obtained by an image acquisition device for wear detection (with and without markers, left and right images in Figure 4), it can be seen that the image acquisition device for acquiring elastane-free defects may have a higher resolution than the image acquisition device for wear defects.

[0091] However, the detection for wear is done in the same way, and in Figure 4a, b the left side shows the respective images without the markers superimposed on the image, and the right side shows the markers superimposed on the image, in this case the markers are red, whereas the markers indicating elastane free defects are yellow.

[0092] Thus, in this case, each defect image is shown separately on each screen, and these images may be superimposed and the defects may be marked in different colors.

[0093] Figures 5a, 5b and 5c show different defects in the bobbin itself. Again, the respective images depicted on the left have markers superimposed, while the images on the right have no markers. In the case of Figure 5a, the bobbin is broken and a dashed line is shown as a marker. In Figure 5b, part of the bobbin is missing.

[0094] In FIG. 5c, no bobbin is provided. If the left side shows the acquired image and the right side shows the image superimposed with the respective marker, both images being shown adjacent to each other on the display 2, and both images being the same size visualized adjacent to each other, the respective user may identify whether the respective defect corresponds to a supposed defect automatically identified by the system, in which case he may assign the respective data to be entered into the database and use the data to improve the database and thus the subsequent defect determination.

[0095] The present invention is not limited to the particular configurations described above, but in its broadest sense can be applied generally to determining defects in yarn bobbins by matching acquired data with data in a pre-stored database for each type of defect.

[0096] In particular, the present invention relates to systems and methods that use artificial intelligence and that use deep learning, which is trained in the process with additional data.

[0097] In certain configurations, each defect can be automatically detected and sorting of the yarn bobbins into different batches can be performed.

[0098] In addition to the specific systems, respective inspection methods and / or applications capable of implementing the respective methods on a computer may also be provided.

[0099] In a particular embodiment, it is described that the respective applications and the database are provided on one computer. It may also be the case that the database is provided remotely from the applications, that the applications are applications executable on a PDA or another remote terminal device, that the applications are applications executable on the Internet. The control of the respective applications may be performed remotely from the respective premises where the respective inspection of the yarn bobbins is performed. The respective activation of the different elements may be performed by wireless communication or alternatively via a local area network.

[0100] Reference List 1. Computer 2. Display 3. Database 4. Application 5. Image acquisition device 5b Image acquisition device for color defect detection 5c Image capture device for detecting wear defects 6 Darkroom 8 Rail 9 Inlet opening 10 Outlet opening 11 Holder 12 Yarn bobbin 13 End face 14 Camera equipment 15 Lighting Section 16 Image processing and adjustment module 17. Ring 18 Rod 19 Rotating hinge 20 Gap 23a, 23b Illumination section of an image capture device for identifying elastane defects on yarn bobbins 24a, 24b Camera device of an image capture device for identifying elastane defects on a yarn bobbin 25 Defect Allocation Module 26 Defect Marker Module

Claims

1. an image capture device (5) for capturing an image of the yarn bobbin (12); a database (3) in which a first data set relating to at least a first type of defect is stored, said first data set being generated by using a sample of yarn bobbins (12) having said first type of defect; an application (4) for determining whether the yarn bobbin (12) inspected using the image acquisition device (5) has the first type of defect; 1. An inspection system for a yarn bobbin comprising:

2. 2. The inspection system according to claim 1, characterized in that the inspection system is configured such that in the database (3) a second data set relating to at least a second type of defect is stored, the second data set being generated by using a sample of yarn bobbins (12) having this second type of defect.

3. 3. The inspection system according to claim 2, characterized in that the application (4) is configured to determine whether the yarn bobbin (12) inspected by means of the image acquisition device (5) has the first type of defect and / or the second type of defect.

4. An inspection system according to any of claims 1 to 3, characterized in that the types of defects are selected from the group comprising the following: elastane free defects, damaged bobbin defects, wear defects, colour defects, diameter defects.

5. 5. The inspection system according to claim 3 or 4, characterized in that the inspection system is configured such that in the database (3) one or more further data sets are stored, each related to at least one further type of defect, each said data set being generated by using a sample of yarn bobbins (12) having this further type of defect.

6. The inspection system according to any one of claims 2 to 5, characterized in that the application (4) is configured to determine a type of the defect in the yarn bobbin (12) inspected by means of the image acquisition device (5).

7. The application (4) a defect assignment module (25) for assigning the type of the defect of the yarn bobbin (12) inspected using the image acquisition device (5) to the yarn bobbin (12); a defect marker module (26) that generates data to provide a marker that can be superimposed on the image of the yarn bobbin (12) captured by the image capture device (5); The inspection system according to any one of claims 1 to 6, comprising:

8. 8. The inspection system of claim 7, wherein the marker is defined by a collection of pixels, the size and shape of the collection of pixels corresponding to an area of ​​the defect.

9. 9. An inspection system according to claim 7 or 8, characterized in that the system is configured such that for different types of defects different colours are used for the markers.

10. An inspection system according to any one of claims 7 to 9, characterized in that a superimposed image in which the marker is superimposed on the image of each of the yarn bobbins (12) acquired using the image acquisition device (5) is visualized on a display (2).

11. Inspection system according to any of claims 1 to 10, characterized in that the system further comprises a bobbin holder (11) mounted on a rail (8), the bobbin holder (11) being capable of being moved along the rail (8) through an inspection zone, the inspection zone being a zone in which the acquisition of the images is performed.

12. 12. The inspection system according to claim 11, characterized in that the bobbin holder (11) is adapted to rotate the yarn bobbin (12) along an axis that is perpendicular to a bobbin central axis.

13. 13. An inspection system according to claim 11 or 12, characterized in that the bobbin holder (11) is constituted by a ring (17) having a fixing area in which the yarn bobbin (12) can be arranged to prevent relative movement of the yarn bobbin (12) within the bobbin holder (11) in at least one of the circumferential and / or translational directions.

14. 14. The inspection system according to claim 13, characterized in that the fixing area is defined by two parallel extending rods (18) extending in the direction of the ring central axis of the ring (17), said rods having a gap (20) between them for holding the yarn bobbin (12) at its outer circumferential surface.

15. Inspection system according to any one of claims 11 to 14, characterized in that the ring (17) has a rotation hinge (19) attached to the rail (8) via a movable element.

16. Inspection system according to any of claims 11 to 15, characterized in that a plurality of bobbin holders (17) are arranged one after the other along the rail (8).

17. An inspection system according to any of claims 11 to 16, characterized in that the bobbin holder (17) is adapted to move together along the rail (8).

18. An inspection system according to any one of claims 1 to 17, characterized in that the system further comprises a darkroom (6) having two openings (9, 10) through which the rail (8) extends from an entrance to an exit.

19. 19. Inspection system according to claim 18, characterized in that the image acquisition device (5) is arranged in the darkroom (6).

20. 20. The inspection system according to any of the preceding claims, characterized in that the image acquisition device (5) comprises an illumination section (15) for illuminating an area of ​​the yarn bobbin (12) for defect detection, and a camera device (14) for acquiring the image of said area.

21. Inspection system according to any of the preceding claims, characterized in that the system further comprises an image processing and adjustment module (16).

22. Inspection system according to any of the preceding claims, characterized in that the system is configured such that for the determination of the defect different image acquisition devices (5) are used depending on the defect type to be detected.

23. 21. The inspection system of claim 20, characterized in that the illumination section (15) operates at a specific wavelength and / or color temperature depending on the defect type to be detected.

24. 22. The inspection system of claim 21, wherein the image processing and conditioning module (16) is adapted to process and condition the image data with different filters depending on the defect type to be detected.

25. Inspection system according to any of claims 18 to 24, characterized in that at least one of the following image acquisition device types is provided in the darkroom (6): an image acquisition device for elastane free defects, an image acquisition device for damaged bobbin defects, an image acquisition device for wear defects, an image acquisition device for color defects and an image acquisition device for diameter defects.

26. 26. Inspection system according to claim 25, characterized in that the image acquisition device for elastane-free defects comprises an illumination section (15) having a ring shape and a camera device (14) arranged in a central area of ​​said ring.

27. 27. Inspection system according to claim 25 or 26, characterized in that the two image acquisition devices for elastane-free defects are arranged on opposite sides of the rail (8).

28. Inspection system according to any of claims 25 to 27, characterized in that a further image acquisition device is provided upstream or downstream of the image acquisition device for elastane-free defects.

29. An inspection system according to any of the preceding claims, characterized in that the system is configured such that yarn bobbins (12) fed to the system are automatically classified according to the defect type detected.

30. The inspection system of any one of claims 1 to 29, characterized in that the system is configured such that the data acquired during defect detection is periodically stored in the database after a human has confirmed that the detected defect corresponds to the defect type assigned by the system.

31. 30. The inspection system of claim 1, wherein the assignment of defects to different types of defects is performed by artificial intelligence and / or the system is configured to operate using deep learning.

32. A method for inspecting yarn bobbins and assigning different types of defects thereto, said method using an application and a database for defect assignment.

Images