Method for detecting defects in the sinkers of an automatic knitting machine, and corresponding system and computer program

Abstract

Method, system and computer program for detecting defects in the sinkers of an automatic knitting machine comprising needles and sinkers, wherein: a digital camera captures digital image frames of a group of working sinkers; an automatic image recognition is carried out to determine a pattern jointly defined by the sinkers; at least one parameter is automatically derived from the pattern; a deviation of said parameter from a predetermined reference is automatically calculated; and in function of said deviation, the presence of a defect in the group of sinkers is automatically determined.

Description

[0001] METHOD FOR DETECTING DEFECTS IN THE SINKERS OF AN AUTOMATIC KNITTING MACHINE, AND CORRESPONDING SYSTEM AND COMPUTER PROGRAM

[0002] DESCRIPTION

[0003] Field of the invention

[0004] The invention is comprised in the field of automatic knitting machines.

[0005] The invention more specifically relates to a method for detecting defects in the sinkers of an automatic knitting machine of the type comprising a plurality of yarn feeders, a plurality of movable needles and a plurality of movable sinkers shaped as thin plates and arranged between said needles, each of said needles being adapted to subsequently catch and free a yarn provided by one of said yarn feeders when said needle is moved, and each of said sinkers being adapted to subsequently hold and free a loop of a stitch of yarn when said sinker is moved, said knitting machine further comprising an actuating device for automatically moving said needles and said sinkers according to a preestablished pattern for manufacturing a knitted fabric from the yarns provided by said yarn feeders by a cooperation between said needles and said sinkers.

[0006] The invention also relates to a system for detecting defects in the sinkers of an automatic knitting machine of this type, and a corresponding computer program to carry out the method.

[0007] Prior art

[0008] Automatic knitting machines are commonly used for manufacturing knitted fabrics at industrial scale. These machines are designed to work intensively. They have a high number of components, including a high number of needles and sinkers as well as the mechanics to move them, which must work in a very precise manner to knit each stitch without defects. The machine is usually equipped with sensors and monitored by a human knitter who can stop the process if something goes wrong. Both the machine components and the produced knitted fabric can be monitored. When the machine is stopped because a defect has been detected in the knitted fabric, there is a high cost associated to the interruption because the human knitter must check the knitted fabric, discard the section with defects, fix the problem and restart the machine. Therefore, it is of great importance to early detect the signs of defects in machine components which can cause defects in the fabric.

[0009] Defects in the sinkers are one of the causes of defects in the fabric. The sinkers are continuously moved in reciprocating movement and, to form the stitch, they come into contact with the yarn that is under tension. This interaction of the sinkers with the yarn progressively causes wear and misalignment of the sinkers that can cause defects in the fabric. A sinker can also break or be deformed or displaced due to interaction with the yarn or with the mechanisms that move the sinkers.

[0010] It is known and common to carry out an inspection of the sinkers with the knitting machine stopped. To do this, a few sinkers are disassembled and their thickness is measured in the areas in contact with the yarn, in order to determine if they have suffered excessive wear. When an excessive wear is observed, all sinkers of the knitting machine are replaced. This method is adequate to prevent defects in the fabric caused by sinker wear. However, it has the drawback that it requires planned machine stops, which must be done well in advance of a wear limit as to prevent defects in the fabric. Furthermore, this method does not allow detecting a defect in a single sinker caused by a problem other than progressive wear. Therefore, this method does not allow preventing defects in the fabric caused by a single faulty sinker.

[0011] Description of the invention

[0012] The purpose of this invention is to provide a method for detecting defects in the sinkers of an automatic knitting machine of the type indicated above in the chapter “Field of the invention”, which can be easily implemented at low cost without modifying the knitting machine and allowing an immediate, automatic reliable detection of different sort of defects in the sinkers.

[0013] This is achieved by means of a method for detecting defects in the sinkers of an automatic knitting machine of this type, characterized in that a digital camera is arranged to capture digital image frames of a group of the sinkers while said automatic knitting machine is working manufacturing the knitted fabric, the sinkers being adjacent to each other in said group; and in that said method comprises the following steps: [a] obtaining from said digital camera image frames containing at least portions of the sinkers of said group while said automatic knitting machine is working manufacturing said knitted fabric;

[0014] [b] performing an automatic image recognition in said image frame to determine at least one pattern jointly defined by at least portions of the sinkers of said group;

[0015] [c] automatically deriving from said pattern at least one parameter related to the presence, the position or the shape of said sinkers or portions of said sinkers in said group;

[0016] [d] automatically calculating a deviation of said at least one parameter from a predetermined reference;

[0017] [e] in function of said deviation, automatically determining the presence of a defect in said group of sinkers.

[0018] As will be seen below in the detailed description of the embodiments, the method according to the invention can be easily implemented by simply installing a digital camera and using a software to carry out an automatic image recognition and determination of a defect in a sinker. Installing a camera in a position for capturing proper digital image frames of the group of sinkers while the automatic knitting machine is working is generally not a problem. The camera can be attached to the knitting machine or an external frame.

[0019] It must be noted that the method according to the invention is not based on the recognition of the shape or dimensions of an individual sinker, but on recognising a pattern which is jointly defined by at least portions of the sinkers of the group, contained in an image frame taken by the digital camera while the knitting machine is working. There is no need to analyse the sinkers individually. This provides a fast and robust process for immediately detecting a variety of defects in the sinkers. The method allows a highly reliable detection of a defect in the sinkers because the pattern can be simple, and the deviation easily determined. In addition, the method can be easily adapted to a variety of knitting machines, equipped with different types of sinkers and needles. Adapting the method to a particular machine can be done by software, by initially selecting the pattern and the parameter from an image frame delivered by the digital camera while the machine is working and when all the sinkers are known to be without defects, and by setting a predetermined reference for said parameter from said image frame. An important aspect of the invention is that it allows detecting not only defects in the sinkers that cause a faulty stitch in the fabric that is being manufactured by the knitting machine, but also defects in the sinkers before they cause such faulty stitch in the fabric. For instance, a slight deviation in the nib of a sinker, or an initial wear in some parts of the sinker due to friction with the yarn, are defects that do not initially cause a faulty stitch, but which can be detected by the method according to the invention before they become critical and they cause a defect in the yarn. The invention thus makes it possible to carry out preventive maintenance in an efficient manner by replacing the sinkers that are identified as being likely to cause defects in the yarn. In function of the type of defect observed for a single sinker, it can be enough to replace only this sinker or to check its assembly. The invention also allows determining a degree of severity of a defect and issuing a corresponding warning signal. A first type of warning signal indicates that the knitting machine must be stopped immediately because a critical defect has been detected in one of the sinkers, which should be causing a faulty stitch. Another type of warning signal indicates that the knitting machine should be stopped as soon as possible, and a sinker should be inspected and eventually replaced, because a slight defect has been detected in the sinker, that can cause soon a faulty stitch. When a type of defect related to wearing is detected in a significant number of sinkers, a warning can be prompted indicating that all the sinkers should be replaced as soon as possible.

[0020] In preferred embodiments, the pattern determined in step [b] comprises a plurality of spots in the image frame, each of said spots corresponding to a reflexion of light in a portion of a sinker of the group. This provides a particularly fast and easy way for determining the pattern and also for determining the parameter, the predetermined reference and the deviation, since a set of spots is easily recognizable by software. This solution is particularly suitable for the sinkers of a knitting machine, because said sinkers are usually metallic, with a surface that reflects light well, and have various curved parts that can generate a spot of reflected light in the image frame. In addition, the method according to this solution can be easily transferred from one knitting machine to another with just a few adjustments, because even if the shape of the sinkers is not the same, the pattern of a group of spots created by equivalent parts of the sinkers can be very similar. Another advantage of this solution is that it makes it easier to identify which sinker has a defect.

[0021] The term “spot” used in the present document must be interpreted according to its usual meaning: a small area visibly different, as in color or finish, from the surrounding area. The spot may have any shape: it is not necessarily a circular dot. For instance, it can have an oblong shape.

[0022] Preferably, the parameter automatically derived from the pattern in step [c] comprises at least one of the group consisting of the number spots in said pattern, the shape of the spots, the area of the spots, the position of the spots in the image frame and a relative distance between two of the spots. This allows to determine in a simple and effective manner a significant deviation in the parameter and therefore a defect in one of the sinkers. For instance, when the parameter is the number of spots in the pattern, missing one of these spots is easily recognisable and is a clear indication of a defect in the corresponding sinker.

[0023] Preferably, each of the spots corresponds to a reflexion of light in at least one curved edge of each of the sinkers. These spots are particularly well defined and separated from each other.

[0024] Preferably, the curved edge of the sinker, in which a reflexion of light occurs which corresponds to the spot, is chosen to be an edge of said sinker comprising a nib and a throat adapted to subsequently hold and free a loop of a stitch of yarn when said sinker is moved. This is one of the portions of the sinker that suffers the most wear due to friction with the yarn, and in which a defect is more likely to appear with use. An excessive wear on this portion alters the shape, position or existence of the spot and therefore it is easily detected.

[0025] Preferably, the curved edge of the sinker, in which a reflexion of light occurs which corresponds to the spot, is chosen to be a curved end portion of the nib. This is a portion of the sinker which is in contact with yarn, and which creates a well-defined spot when the light reflects on it. In addition, when the defect is a tilt or a bending of the sinker with respect to a vertical direction, this is the portion of the sinker that varies its position at the most, causing a significant change in the shape, position or existence of the corresponding spot will allows to better detect this defect.

[0026] Preferably, the curved edge of the sinker, in which a reflexion of light occurs which corresponds to the spot, is chosen to be a curved end portion of said sinker, currently known as “knock- over edge”, adapted to support the fabric as it is being knitted. This is also a portion of the sinker which creates a well-defined spot when the light reflects on it. In addition, when the defect is a tilt or a bending of the sinker with respect to a horizontal direction, this is the portion of the sinker that varies its position at the most, causing a significant change in the shape, position or existence of the corresponding spot will allows to better detect this defect.

[0027] Preferably, before step [b], the image frames obtained in step [a] are transformed to monochrome images, therefore making the process of automatic recognition faster. This is an important advantage, since it solves the problem of how the complete quickly enough the process of recognizing the pattern in the portions of sinkers contained in an image frame, before the next image frame is generated. Transforming the images to monochrome ones implies losing an important part of the information contained in said images, but this does not deteriorate the robustness of the method because it is not necessary to know the exact shape of the spots.

[0028] Preferably, a controlled lighting is focused on said group of sinkers, so that the light reflexion that creates the spots does not depend on the ambient light present in the place where the machine is located.

[0029] Preferably, the number of sinkers, of which at least a portion is contained in the image frames, is comprised between 2 and 50, preferably between 2 and 30, more preferably between 5 and 15. These ranges are optimum for determining the pattern, the parameter and the predetermined reference.

[0030] Preferably, whenever in step [e] the presence of a defect is automatically detected in the group of sinkers, a sinker in which said defect is present is automatically identified in function of the parameter that has been automatically derived in step [c]. This allows to fix the problem by directly replacing the defective sinker. It also allows to deduce which portion of the knitted fabric is likely to have a defect due to the defective sinker, so that the knitted fabric can be inspected in a more effective manner.

[0031] Although the method according to the invention can be applied to a variety of automatic knitting machines, in preferred embodiments the automatic knitting machine is a circular knitting machine in which the needles and the sinkers are arranged in a rotating cylinder which make said needles and said sinkers to travel along a circumference which is coaxial with said rotating cylinder. The digital camera is statically arranged, so that it does not rotate with the rotating cylinder, and the digital image frames include a portion of said circumference. In these applications, the method according to the invention is particularly advantageous. It is easy to install the digital camera and it is also easy to obtain a stationary pattern in the image frames. The digital camera can be installed on the inner side of the rotating cylinder or on the outer side thereof, depending on the structure of the automatic knitting machine. For most of the current knitting machines, the digital camera is preferably installed on the inner side of the rotating cylinder. The invention also comprises a corresponding system for detecting defects in the sinkers of an automatic knitting machine, comprising an automatic knitting machine with a plurality of yarn feeders, a plurality of movable needles and a plurality of movable sinkers shaped as thin plates and arranged between said needles, each of said needles being adapted to subsequently catch and free a yarn provided by one of said yarn feeders when said needle is moved, and each of said sinkers being adapted to subsequently hold and free a loop of a stitch of yarn when said sinker is moved, said knitting machine further comprising an actuating device for automatically moving said needles and said sinkers according to a preestablished pattern for manufacturing a knitted fabric from the yarns provided by said yarn feeders by a cooperation between said needles and said sinkers ; characterized in that it further comprises: a digital camera arranged to capture digital image frames of a group of said sinkers while said automatic knitting machine is working manufacturing said knitted fabric, the sinkers being adjacent to each other in said group; a processor connected to said digital camera; a computer program comprising instructions which, when executed by said processor, cause said processor to carry out the following steps:

[0032] [a] obtaining from said digital camera image frames containing at least portions of the sinkers of said group while said automatic knitting machine is working manufacturing said knitted fabric;

[0033] [b] performing an automatic image recognition in said image frame to determine at least one pattern jointly defined by at least portions of the sinkers of said group;

[0034] [c] automatically deriving from said pattern at least one parameter related to the presence, the position or the shape of said sinkers or portions of said sinkers in said group;

[0035] [d] automatically calculating a deviation of said at least one parameter from a predetermined reference;

[0036] [e] in function of said deviation, automatically determining the presence of a defect in said group of sinkers.

[0037] The system optionally has the structural features according to the preferred embodiments discussed above for the method, and the computer program optionally comprises instructions to carry out the steps of the method according to said preferred embodiments. The invention also comprises the computer program defined above in the description of the system.

[0038] The invention also comprises other features concerning details illustrated in the detailed description of embodiments of the invention and in the attached drawings.

[0039] Brief description of the drawings

[0040] The advantages and features of the invention can be seen from the following description in which, with a non-limiting character with respect to the scope of the main claim, preferred embodiments are described in reference to the drawings.

[0041] Fig. 1 is a schematic view of a first embodiment of a system according to the invention. The automatic knitting machine is circular, of the kind with one set of vertical needles and one set of sinkers.

[0042] Fig. 2 is a view of the upper part of a needle, with the latch in open position.

[0043] Fig. 3 is a view of the same upper part of the needle, with the latch in closed position.

[0044] Fig. 4 is a lateral view of a sinker.

[0045] Fig. 5 is a photographic image of a group of working needles and sinkers in the automatic knitting machine, of which the digital camera obtains image frames.

[0046] Fig. 6A is a schematic view of a processed image frame of the group of sinkers, which shows the spots that are used to determine the pattern and the presence of defects in the sinkers. All the sinkers are without defects.

[0047] Fig. 6B is a processed monochrome image frame corresponding to schematic view of Fig. 6A.

[0048] Fig. 7A is a view equivalent to Fig. 6A, but in which a first type of defect is observed: a significant wear on the top edge of the sinkers, in an intermediate area between the throat and the curved end portion of the sinker. Fig. 7B is a processed monochrome image frame corresponding to schematic view of Fig. 7 A.

[0049] Fig. 8A is a view equivalent to Fig. 6A, but in which a second type of defect is observed in one of the sinkers: a significant change on the curbed end portion of the nib.

[0050] Fig. 8B is a processed monochrome image frame corresponding to schematic view of Fig. 8A.

[0051] Fig. 9A is a view equivalent to Fig. 6A, but in which a third type of defect is observed in one of the sinkers: a significant displacement of the nib.

[0052] Fig. 9B is a processed monochrome image frame corresponding to schematic view of Fig. 9A.

[0053] Fig. 10A is a view equivalent to Fig. 6A, but in which a fourth type of defect is observed in one of the sinkers: the nib is broken.

[0054] Fig. 10B is a processed monochrome image frame corresponding to schematic view of Fig. 10A.

[0055] Fig. 11 A is a view equivalent to Fig. 6A, but in which a fifth type of defect is observed in one of the sinkers: a significant displacement of the curved end portion of the sinker.

[0056] Fig. 11 B is a processed monochrome image frame corresponding to schematic view of Fig. 11 A.

[0057] Fig. 12A is a view equivalent to Fig. 6A, but in which a sixth type of defect is observed in one of the sinkers: a significant displacement of the whole sinker.

[0058] Fig. 12B is a processed monochrome image frame corresponding to schematic view of Fig. 12A.

[0059] Fig. 13 is a block diagram of the main steps of the method according to the invention.

[0060] Detailed description of embodiments of the invention Figs. 1-12 refer to an embodiment of a system and a method according to the invention. In this embodiment, the automatic knitting machine 1 is a circular knitting machine of the type having a set of vertical needles 3 and a set of sinkers 16 for manufacturing a single jersey knit tubular fabric 17.

[0061] Fig. 1 is a schematic view of the system, in which the knitting machine 1 is represented in a schematic sectional view. The system comprises the automatic knitting machine 1 , a digital camera 4, a controlled lighting 13 and a computer system including a processor 15 which is connected to the digital camera 4. A software, including an automatic image recognition algorithm, is executed by the processor 15.

[0062] The automatic knitting machine 1 comprises a plurality of yarn feeders 2, a plurality of movable needles 3 and a plurality of movable sinkers 16 shaped as thin plates and arranged between the needles 3. Each of the needles is adapted to subsequently catch and free a yarn provided by one of the yarn feeders 2 when said needle 3 is subsequently moved in vertical direction. Each of the sinkers 16 is adapted to subsequently hold and free a loop of a stitch of yarn when said sinker 16 is subsequently moved in horizontal direction. The knitting machine 1 further comprises an actuating device for automatically moving the needles 3 and the sinkers 16 according to a preestablished pattern for manufacturing a knitted fabric 17 from the yarns 7 provided by the yarn feeders 2 by a cooperation between said needles 3 and said sinkers 16.

[0063] More concretely, the automatic kitting machine 1 used in the tests described below for an exemplary embodiment is a single jersey circular knitting machine, model of CANMARTEX- JUMBERCA brand, with 1728 needles, diameter of 30 inches, and an 18 gauge (number of needles per inch). The needles 3 and the sinkers 16 are arranged in a rotating cylinder 14, so that they travel along a circumference which is coaxial with the rotating cylinder 14. The needles 3 and the sinkers 16 interact with cams which are statically arranged in a dial around the rotating cylinder 14, and which make each needle 3 to move vertically up and down, and each sinker 15 to move horizontally forward and backward, forming stitches while the cylinder 14 rotates continuously. The rotating cylinder 14, actuated by a motor, and the static cams are the actuating device referred to above for automatically moving the needles 3 and the sinkers 16. Since the cams are static, each needle 3 and each sinker 16 travelling along the circumference has a unique position at each point of said circumference. The sinkers 16 are arranged between the needles 3 and move horizontally to control the movement of the fabric as the machine knits. More concretely, the function of the sinkers 16 is to hold the old loop of stitch at a lower level on the needle 3 stem than the new loop of the stitch being formed, and to prevent the old loop from being lifted by the needle 3 as it rises to clear the loop from its hook. In addition, the sinkers 16 support the fabric as it is produced and slides down over a curved end portion of the sinkers 16.

[0064] Fig. 5 is a is a photographic image of a group of working needles 3 and sinkers 16 in the automatic knitting machine 1 , of which the digital camera 4 obtains image frames. In this image, the sinkers 16 are the parallel thin plates, the top of the needles 3 are visible at half height in the image, and the knitted fabric 17 as it is being produced is seen in the upper part of the image. The needles 3 are all identical. The sinkers 16 are also all identical. The needles 3 are latch needles as schematically shown in Figs. 2 and 3. Each needle 3 has a free top end forming a hook 9 and a pivoting latch 10 which is pushed by the yarn of the knit loop as the needle 3 moves up and down, so that the latch 10 subsequently closes and open the hook 9. The hook 9 is adapted to subsequently catch and free a yarn when the needle 3 is moved. Figs. 2 and 3 respectively show the needle 3 with the latch 10 in an open and a closed position. The sinkers 16 are thin plates. As shown is the lateral view of Fig. 4, the upper edge 18 of the sinker 16 has several curved portions, defining different functional portions of the sinker 16. From left to right in Fig. 4, the upper edge 18 of the sinker defines a butt 22, which is the part of the sinker 16 that cooperates with the static cams of the dial to move the sinker 16, a nib 19 with a curbed end portion and a throat 20 under said nib 19, which holds and frees an old loop of a stitch of yarn when the sinker 16 is horizontally moved, and a curved end portion 21 of the sinker, currently known as “knock-over edge”, which supports the knitted fabric 17 that slides down over said curved end portion 21 . Between the nib 19 and the curved end portion 21 there is an intermediate area 23, currently known as “knock-over paltform”, which is a portion of the sinker 16 that wears out particularly because it laterally impacts with a yarn when the sinkers 16 move along the circumferential path. It must be noted that the invention is not limited to sinkers shaped as shown in Fig. 4. The invention can also be applied to other sinkers with a great variety of shapes.

[0065] The operation of this type of circular knitting machine with needles and sinkers, as well as the movements of the needles and the sinkers to form the knit loops, are not described in greater detail here since they are well known to those skilled in the art.

[0066] The digital camera 4 is statically arranged, so that it does not rotate with the rotating cylinder 14. It is arranged to capture digital image frames 5 of a portion of the circumference along which the needles 3 and the sinkers 16 travel, while the automatic knitting machine 1 is working manufacturing the knitted fabric 17. Image frames 5 captured by the digital camera 4 include a group 6 of sinkers 16 adjacent to each other. The lighting 13 is a lamp statically arranged so that the light it emits focuses on the group 6 of needles 3. The relative position of the lamp with respect to the digital camera 4 and the intensity of the light emitted by said lamp are adjusted so that a suitable reflexion of light on the sinkers 16, allowing to identify a pattern in processed image frames 5 as will be discussed below. In the exemplary embodiment depicted in the figures, the digital camera 4 and the lighting 13 are fixed to a static support (not shown in the figures), on an inner side with respect to a virtual cylinder that axially extends the rotating cylinder 14. This position of the digital camera 4 and the lighting 13 is suitable in most of circular knitting machines, in which the left portion of the sinker 16 (referring to Fig. 4) comprising the butt 22 is usually covered by structural parts of the die that make difficult to see the right portion on the sinker 16 containing the nib 19, the throat 20 and the curved end portion 21. In addition, the spots created by light reflection on this right portion are better defined when the digital camera 4 and the lighting 13 are arranged in said position. However, in other embodiments, the digital camera 4 and / or the lighting 13 can be arranged in different positions. For instance, they can be fixed to a static support on an outer side with respect to said virtual cylinder.

[0067] The digital camera 4 used in the tests described below is a video digital camera model TIS- DMK-33UX264 commercialized by the German firm The Imaging Source Europe GmbH. It is equipped with a Sony IMX264 sensor and has a 2448x2048 pixels resolution and a 35 PFS (frames per second) (FPS) video capture. The sensor operates with a Global Shutter CMOS image capture method, allowing to collect all the data at the same time without a lag due to the shutter.

[0068] The method according to the invention comprises the following main steps:

[0069] [a] obtaining from the digital camera 4 image frames 5 containing at least portions of the sinkers 16 of the group 6 while the automatic knitting machine 1 is working manufacturing the knitted fabric;

[0070] [b] performing an automatic image recognition in said image frame 5 to determine at least one pattern jointly defined by at least portions of the sinkers 16 of said group 6;

[0071] [c] automatically deriving from said pattern at least one parameter related to the presence, the position or the shape of the sinkers 16 or portions of said sinkers 16 in said group 6; [d] automatically calculating a deviation of said at least one parameter from a predetermined reference;

[0072] [e] in function of said deviation, automatically determining the presence of a defect in said group 6 of sinkers 16.

[0073] The group of working needles 3 and sinkers 16 in the automatic knitting machine 1 , of which the digital camera 4 obtains image frames, is shown in Fig. 5. Figs. 6A to 12A are schematic, idealized figures of the image frames 5 during these steps. Figs. 6B to 12B are real processed monochrome image frames corresponding to schematic views of Figs. 6A to 12A.

[0074] The image frames 5 contain eight sinkers 16 in total, although only five of them form the pattern as will be discussed below. In Figs. 6A and 6B, all the sinkers are known to be without defects. Before step [b], the image frame obtained in step [a] is processed: it is oversaturated and transformed to monochrome. This processed image frame 5 is schematically shown in Fig. 6A. A real processed image frame 5 is shown in Fig. 6B.

[0075] In an initial step, in which the automatic knitting machine 1 is working and all the sinkers 16 are known to be without defects, a processed image 5 like the one schematically shown in Fig. 6A is analysed. From this initial analysis, the pattern, as well as the one or several parameters discussed above are chosen, and the corresponding predetermined references are set. These pattern, parameters and predetermined refences are introduced as settings in the software.

[0076] A pattern, which allows to identify defects in the sinkers 16, is identified in Fig. 6A. This pattern is formed by a plurality of spots 8, each of them corresponding to a reflexion of the light emitted by the lighting 13 on a portion of the sinkers 3 of the group 6. In the exemplary embodiment shown in the figures, the patter is formed by two lines of spots 8. In the upper line of spots 8 in Fig. 6A, each spot 8 corresponds to a reflexion of light in the curved end portion 21 of the upper edge 18 of each sinker 16. In the lower line of spots 8 in Fig. 6A, each spot 8 corresponds to a reflexion of light in the curved end portion of the nib 19 of each sinker 16. The pattern is formed by five consecutive spots 8, in each of the upper line and the lower line of spots 8. There are five couples of spots 8, each comprising one spot 8 in the upper line and one spot 8 in the lower line. Each couple of spots 8 corresponds to one sinker 16. What is monitored, through these five couples of spots 8, is the nib 19, the curved end portion 21 and the intermediate area 23 of a group of five adjacent sinkers 16. At least one parameter is chosen in the pattern, and a predetermined reference is set for said parameter from Fig. 6A in which all the sinkers 16 are free of defects. The parameter can be, for instance, one or several from the following:

[0077] The total number of spots 8 and / or the number of spots 8 in each of the upper and the lower line. The predetermined reference is the value 10 for the total number of spots 8 and the value 5 in each line (there must be five spots 8 in the upper line and five spots 8 in the lower line).

[0078] The shape of spots 8. The predetermined reference is an elongated shape for the spots 8 in the supper line, with a vertically oriented major direction, and a substantially circular shape for the spots 8 of the lower line.

[0079] The area of the spots 8. The predetermined reference is the area of the spots 8 measured in Fig. 6A.

[0080] The position of the spots 8. The predetermined reference is the X-Y position of a central point of the spot 8 in Fig. 6A.

[0081] - A relative distance between two spots 8, for instance the relative distance between each pair of consecutive spots 8 along each of the upper line and the lower line, and / or the relative distance between each couple of spots 8 corresponding to the same sinker 16. The predetermined reference is a relative distance between spots 8 measured in Fig. 6A.

[0082] The steps [a] to [e] of the method are carried out by the software for subsequent image frames 5 obtained from the digital camera 4 while the automatic knitting machine 1 is working manufacturing a knitted fabric. Steps [b] and [c] are carried out by an image recognition algorithm included in the software. The image frames 5 are taken at a suitable time rate, which is adjusted in function of the rotational speed of the rotating cylinder 14 and the gauge, so that in each image frame 5 all the sinkers 16 are at the same position. The time rate for taking the image frames 5 is also adjusted so that each sinker 16 of the knitting machine 1 is contained in at least one of the image frames 5 and present in at least one of the first or the second pattern.

[0083] Figs. 7A and 7B are respectively equivalent to Figs. 6A and 6B, but in this case a first type of defect is observed: a significant wear on the top edge 18 of most the sinkers 16, in the intermediate area 23 between the throat 20 and the curved end portion 21. The defect is detected because an additional line of spots 8 has appeared between the upper line and the lower line. This is due to a change in the reflexion of light on the intermediate area 23 caused by wearing. This is automatically recognised by the software which carries out steps [a]-[e], and which automatically determines the presence of a defect in the group 6 of sinkers 16 in step [e]. For instance, if the parameters chosen in the initial step comprise the total number and the position of the spots 8, in step [d] the deviation consists in that the total number of spots 8 is 15 instead of 10, and in that five additional spots 8 are aligned along an intermediate line between the upper line and the lower line. On the other hand, the nature of the deviation allows to deduce the nature and the importance of the defect. The presence of additional spots 8 in an intermediate line indicates that a significant level of wear has been reached in the intermediate area 23 of most of the sinkers 16. The software prompts a message indicating that the sinkers 16 should be replaced as soon as possible.

[0084] Figs. 8A and 8B are respectively equivalent to Figs. 6A and 6B, but in this case a second type of defect is observed in one of the sinkers 16: a significant change on the end curved surface of the nib 19 of one of the sinkers 16. The defect is detected because the area of the corresponding spot 8 has significantly changed. This is due to a change in the reflexion of light on the nib 19, which can be caused by wearing or by the presence of dirt. This is automatically recognised by the software which carries out steps [a]-[e], and which automatically determines the presence of a defect in the group 6 of sinkers 16 in step [e]. For instance, if the parameters chosen in the initial step comprise the area of the spots 8, in step [d] the deviation consists in that the area of the second spot 8 from the right in the lower line has significantly changed. In this example, the area taken as a parameter is the total area of the sum of white pixels forming the spot 8. What can be seen in Fig. 8B is a lower brightness of the spot 8, which implies a lower area as defined above. The software prompts an alarm indicating that the corresponding sinker 16 must be inspected as soon as possible and indicating the number of the faulty sinker 16. The number of the sinker 16 refers to the position of said sinker 16 in the knitting machine. It is calculated by the software from the position on the sinker 16 in the image frame 5 (in this case, the second from the right) and from a counting of the sinkers 16 passing through the image frame 5. It is also possible to automatically calculate and indicate the area of the knitted fabric which could be affected by the faulty sinker 16.

[0085] Figs. 9A and 9B are respectively equivalent to Figs. 6A and 6B, but in this case a third type of defect is observed in one of the sinkers 16: a significant displacement of the nib 19 of one of the sinkers 16. The defect is detected because position of the corresponding spot 8 has significantly changed. The cause is that the nib 19 has bent, or else the sinker 16 has been tilted with respect to a vertical direction. This is automatically recognised by the software which carries out steps [a]-[e], and which automatically determines the presence of a defect in the group 6 of sinkers 16 in step [e]. For instance, if the parameters chosen in the initial step comprise the position of the spots 8, in step [d] the deviation consists in that the position of the fourth spot 8 from the right in the lower line has significantly changed. The software prompts an alarm causing an immediate stop of the knitting machine and indicating the number of the sinker 16 having a critical defect and, optionally, the area of the knitted fabric that probably has a defect due to the faulty sinker 16. The number of the faulty sinker 16 and the affected area of the fabric are automatically calculated by the software as indicated above for the second type of defect.

[0086] Figs. 10A and 10B are respectively equivalent to Figs. 6A and 6B, but in this case a fourth type of defect is observed in one of the sinkers 16: the nib 19 of one of the sinkers 16 is broken. The defect is detected because a spot 8 is missing in the lower line. This is automatically recognised by the software which carries out steps [a]-[e], and which automatically determines the presence of a defect in the group 6 of sinkers 16 in step [e]. For instance, if the parameters chosen in the initial step comprise the number of spots 8 and the position of the spots 8, in step [d] the deviation consists in that the number of spots 8 in the lower line is 4 instead of 5, and the position of the fourth spot 8 from the right in the lower line is lost. The software prompts an alarm which immediately stops the machine and gives an information on the faulty sinker 16 and the affected area of the fabric as described above for the third type of defect.

[0087] Figs. 11 A and 11 B are respectively equivalent to Figs. 6A and 6B, but in this case a fifth type of defect is observed in one of the sinkers 16: a significant displacement of the curved end portion 21 of one of the sinkers 16. The cause is that the sinker 16 has been tilted with respect to a horizontal direction. The defect is detected because the position of a spot 8 has significantly changed in the upper line. This is automatically recognised by the software which carries out steps [a]-[e], and which automatically determines the presence of a defect in the group 6 of sinkers 16 in step [e]. For instance, if the parameters chosen in the initial step comprise the position of the spots 8, in step [d] the deviation consists in that the position of the fifth spot 8 from the right in the upper line has significantly changed. The software prompts an alarm which immediately stops the machine and gives an information on the faulty sinker 16 and the affected area of the fabric as described above for the third type of defect. Figs. 12A and 12B are respectively equivalent to Figs. 6A and 6B, but in this case a sixth type of defect is observed in one of the sinkers 16: a significant displacement of one of the sinkers 16 as a whole. The cause is a defect related to the sinker housing. The defect is detected because the position of both the spot 8 of the lower line and the corresponding spot 8 of the upper line have significantly changed. This is automatically recognised by the software which carries out steps [a]-[e], and which automatically determines the presence of a defect in the group 6 of sinkers 16 in step [e]. For instance, if the parameters chosen in the initial step comprise the position of the spots 8, in step [d] the deviation consists in that the position of the two fourth spots 8 from the right has significantly changed. The software prompts an alarm which immediately stops the machine and gives an information on the faulty sinker 16 and the affected area of the fabric as described above for the third type of defect.

[0088] The system and the method according to the invention as described above for an exemplary embodiment can automatically detect at least the following defects in the sinkers 16:

[0089] The presence of dirt or a significant wear on the top surface of the nib or in the intermediate area between the throat and the curved end portion of the sinker; a significant bent of the nib or a significant tilt of the sinker with respect to a vertical direction; a broken nib; a significant tilt of the sinker with respect to a horizontal direction; a problem with the housing of the sinker, causing a wrong position of the whole sinker.

[0090] Each of these defects is automatically recognised because it causes a change in the reflexion of light on the sinkers, which in turn causes a change in the pattern which is recognised by an image recognition software. As discussed above, the system and the method according to the invention allow to automatically recognize whether the defect is critical (a faulty sinker which is very likely causing a defect in the knitted fabric) or non-critical (a defect in a sinker which is probably not yet causing a defect in the knitted fabric but that requires the identified sinker to be inspected as soon as possible). The invention is not limited to large diameter circular knitting machines as described above for two exemplary embodiments, producing weft knitted tubular fabric in continuous lengths of constant width, but also applies to other kind of automatic knitting machines with needles and sinkers like, for instance and in a non-limiting manner, small diameter circular weft knitting machines.

Claims

CLAIMS1 Computer-implemented method for detecting defects in the sinkers of an automatic knitting machine (1), said automatic knitting machine (1) comprising a plurality of yarn feeders (2), a plurality of movable needles (3) and a plurality of movable sinkers (16) shaped as thin plates and arranged between said needles (3), each of said needles (3) being adapted to subsequently catch and free a yarn provided by one of said yarn feeders (2) when said needle (3) is moved, and each of said sinkers (16) being adapted to subsequently hold and free a loop of a stitch of yarn when said sinker (16) is moved, said knitting machine (1) further comprising an actuating device for automatically moving said needles (3) and said sinkers (16) according to a preestablished pattern for manufacturing a knitted fabric from the yarns provided by said yarn feeders (2) by a cooperation between said needles (3) and said sinkers (16); characterized in that a digital camera (4) is arranged to capture digital image frames (5) of a group (6) of said sinkers (16) while said automatic knitting machine (1) is working manufacturing said knitted fabric, the sinkers (16) being adjacent to each other in said group (6); and in that said method comprises the following steps carried out by a processor:[a] obtaining from said digital camera (4) image frames (5) containing at least portions of the sinkers (16) of said group (6) while said automatic knitting machine (1) is working manufacturing said knitted fabric;[b] performing an automatic image recognition in said image frame (5) to determine at least one pattern jointly defined by at least portions of the sinkers (16) of said group (6);[c] automatically deriving from said pattern at least one parameter related to the presence, the position or the shape of said sinkers (16) or portions of said sinkers (16) in said group (6);[d] automatically calculating a deviation of said at least one parameter from a predetermined reference;[e] in function of said deviation, automatically determining the presence of a defect in said group (6) of sinkers (16).2.- Computer-implemented method according to claim 1 , wherein said pattern determined in step [b] comprises a plurality of spots (8) in said image frame (5), each of said spots (8) corresponding to a reflexion of light in a portion of a sinker (16) of said group (6).3.- Computer-implemented method according to claim 2, wherein said parameter automatically derived from said pattern in step [c] comprises at least one of the group consisting of the number of said spots (8) in said pattern, the shape of said spots (8), the area of said spots (8), the position of said spots (8) in said image frame (5) and a relative distance between two of said spots (8).4.- Computer-implemented method according to any of claims 2 to 3, wherein each of said spots (8) corresponds to a reflexion of light in at least one curved edge (18) of each of said sinkers (16).5.- Computer-implemented method according to claim 4, wherein said curved edge (18) of the sinker (16), in which a reflexion of light occurs which corresponds to said spot (8), is chosen to be an edge of said sinker (16) comprising a nib (19) and a throat (20) adapted to subsequently hold and free a loop of a stitch of yarn when said sinker (16) is moved.6.- Computer-implemented method according to claim 5, wherein said curved edge (18) of the sinker (16), in which a reflexion of light occurs which corresponds to said spot (8), is chosen to be a curved end portion of said nib (19).7.- Computer-implemented method according to any of claims 4 to 6, wherein said curved edge (18) of the sinker (16), in which a reflexion of light occurs which corresponds to said spot (8), is chosen to be a curved end portion (21) of said sinker (16) adapted to support the fabric as it is being knitted.8.- Computer-implemented method according to any of claims 1 to 7, wherein, before step [b], said image frames (6) obtained in step [a] are transformed to monochrome images.9.- Computer-implemented method according to any of claims 1 to 8, wherein a controlled lighting (13) is focused on said group (6) of sinkers (16).10.- Computer-implemented method according to any of claims 1 to 9, wherein, when in step [e] the presence of a defect is automatically detected in said group (6) of sinkers (16), a sinker (16) in which said defect is present is automatically identified in function of said parameter that has been automatically derived in step [c].11.- Computer-implemented method according to any of claims 1 to 10, wherein said automatic knitting machine (1) is a circular knitting machine in which said needles (3) and said sinkers (16) are arranged in a rotating cylinder (14) which make said needles (3) and said sinkers (16) to travel along a circumference which is coaxial with said rotating cylinder (14), and wherein said digital camera (4) is statically arranged, so that it does not rotate with said rotating cylinder (14), and said digital image frames (5) include a portion of said circumference.

12. System for detecting defects in the sinkers of an automatic knitting machine (1), comprising an automatic knitting machine (1) with a plurality of yarn feeders (2), a plurality of movable needles (3) and a plurality of movable sinkers (16) shaped as thin plates and arranged between said needles (3), each of said needles (3) being adapted to subsequently catch and free a yarn provided by one of said yarn feeders (2) when said needle (3) is moved, and each of said sinkers (16) being adapted to subsequently hold and free a loop of a stitch of yarn when said sinker (16) is moved, said knitting machine (1) further comprising an actuating device for automatically moving said needles (3) and said sinkers (16) according to a preestablished pattern for manufacturing a knitted fabric from the yarns provided by said yarn feeders (2) by a cooperation between said needles (3) and said sinkers (16); characterized in that it further comprises: a digital camera (4) arranged to capture digital image frames (5) of a group (6) of said sinkers (16) while said automatic knitting machine (1) is working manufacturing said knitted fabric, the sinkers (16) being adjacent to each other in said group (6); a processor (14) connected to said digital camera (4); a computer program comprising instructions which, when executed by said processor (14), cause said processor (14) to carry out the following steps:[a] obtaining from said digital camera (4) image frames (5) containing at least portions of the sinkers (16) of said group (6) while said automatic knitting machine (1) is working manufacturing said knitted fabric;[b] performing an automatic image recognition in said image frame (5) to determine at least one pattern jointly defined by at least portions of the sinkers (16) of said group (6);[c] automatically deriving from said pattern at least one parameter related to the presence, the position or the shape of said sinkers (16) or portions of said sinkers (16) in said group (6);[d] automatically calculating a deviation of said at least one parameter from a predetermined reference;[e] in function of said deviation, automatically determining the presence of a defect in said group (6) of sinkers (16).

13. System according to claim 12, wherein said instructions of the computer program are adapted so that said pattern determined in step [b] comprises a plurality of spots (8) in said image frame (5), each of said spots (8) corresponding to a reflexion of light in a portion of a sinker (16) of said group (6).14.- System according to claim 13, wherein said instructions of the computer program are adapted so that said parameter automatically derived from said pattern in step [c] comprises at least one of the group consisting of the number of said spots (8) in said pattern, the shape of said spots (8), the area of said spots (8), the position of said spots (8) in said image frame (5) and a relative distance between two of said spots (8).15.- System according to any of claims 13 to 14, wherein said instructions of the computer program are adapted so that each of said spots (8) corresponds to a reflexion of light in at least one curved edge (18) of each of said sinkers (16).16.- System according to claim 15, wherein said instructions of the computer program are adapted so that said curved edge (18) of the sinker (16), in which a reflexion of light occurs which corresponds to said spot (8), is chosen to be an edge of said sinker (16) comprising a nib (19) and a throat (20) adapted to subsequently hold and free a loop of a stitch of yarn when said sinker (16) is moved.17.- System according to claim 16, wherein said instructions of the computer program are adapted so that said curved edge (18) of the sinker (16), in which a reflexion of light occurs which corresponds to said spot (8), is chosen to be a curved end portion of said nib (19).18.- System according to any of claims 15 to 17, wherein said instructions of the computer program are adapted so that said curved edge (18) of the sinker (16), in which a reflexion of light occurs which corresponds to said spot (8), is chosen to be a curved end portion (21) of said sinker (16) adapted to support the fabric as it is being knitted.19.- System according to any of claims 12 to 18, wherein said instructions of the computer program are adapted so that, before step [b], said image frames (6) obtained in step [a] are transformed to monochrome images.20.- System according to any of claims 12 to 19, comprising a controlled lighting (13) focused on said group (6) of sinkers (16).21.- System according to any of claims 12 to 20, wherein said instructions of the computer program are adapted so that, when in step [e] the presence of a defect is automatically detected in said group (6) of sinkers (16), a sinker (16) in which said defect is present is automatically identified in function of said parameter that has been automatically derived in step [c],22.- System according to any of claims 12 to 21 , wherein said automatic knitting machine (1) is a circular knitting machine in which said needles (3) and said sinkers (16) are arranged in a rotating cylinder (14) which make said needles (3) and said sinkers (16) to travel along a circumference which is coaxial with said rotating cylinder (14), and wherein said digital camera (4) is statically arranged, so that it does not rotate with said rotating cylinder (14), and said digital image frames (5) include a portion of said circumference.

23. Computer program for detecting defects in the sinkers of an automatic knitting machine (1), said computer program comprising instructions which, when executed by a processor (15), cause said processor (15) to carry out the following steps:[a] obtaining from a digital camera (4) image frames (5) containing at least portions of the sinkers of a group (6) of sinkers (16) of an automatic knitting machine (1), wherein said image frames have been taken by said digital camera (4) while said automatic knitting machine (1) is working manufacturing a knitted fabric;[b] performing an automatic image recognition in said image frame (5) to determine at least one pattern jointly defined by at least portions of the sinkers (16) of said group (6);[c] automatically deriving from said pattern at least one parameter related to the presence, the position or the shape of said sinkers (16) or portions of said sinkers (16) in said group (6);[d] automatically calculating a deviation of said at least one parameter from a predetermined reference;[e] in function of said deviation, automatically determining the presence of a defect in said group (6) of sinkers (16).

Images