WO2022101714A1 - Apparatus and method for continuous detection of defects in a yarn in a spinning machine - Google Patents

Apparatus and method for continuous detection of defects in a yarn in a spinning machine Download PDF

Info

Publication number
WO2022101714A1
WO2022101714A1 PCT/IB2021/059569 IB2021059569W WO2022101714A1 WO 2022101714 A1 WO2022101714 A1 WO 2022101714A1 IB 2021059569 W IB2021059569 W IB 2021059569W WO 2022101714 A1 WO2022101714 A1 WO 2022101714A1
Authority
WO
WIPO (PCT)
Prior art keywords
defects
images
spinning machine
roving
processing
Prior art date
Application number
PCT/IB2021/059569
Other languages
French (fr)
Inventor
Matteo GIAVARINI
Rosario Assenza
Renato GHILARDI
Luca BRESCIANINI
Noman HALEEM
Matteo BUSTREO
Alessio DEL BUE
Original Assignee
MARZOLI MACHINES TEXTILE S.r.l.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by MARZOLI MACHINES TEXTILE S.r.l. filed Critical MARZOLI MACHINES TEXTILE S.r.l.
Priority to JP2023528682A priority Critical patent/JP2023552680A/en
Priority to DE112021005995.5T priority patent/DE112021005995T5/en
Priority to CN202180076738.4A priority patent/CN116507908A/en
Publication of WO2022101714A1 publication Critical patent/WO2022101714A1/en

Links

Classifications

    • D—TEXTILES; PAPER
    • D01—NATURAL OR MAN-MADE THREADS OR FIBRES; SPINNING
    • D01H—SPINNING OR TWISTING
    • D01H13/00—Other common constructional features, details or accessories
    • D01H13/32—Counting, measuring, recording or registering devices
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
    • G01N21/8915—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined non-woven textile material
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/36—Textiles
    • G01N33/365—Textiles filiform textiles, e.g. yarns
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models

Definitions

  • This invention is in the field of textile fiber processing, and in particular in the field of instruments and methods for detecting defects in the products of spinning preparation processes .
  • obj ects of the present invention a method and an apparatus for detecting tangles or knots , usually referred to as “neps , " in the yarn produced in a ringspinning machine .
  • a spinning machine is capable of processing bobbins of roving to obtain spools of yarn, after having drawn and twisted the roving .
  • the spinning machine consists of a frame extending along a longitudinal axis and supporting a creel from which the bobbins of roving are hung, a drawing device supported by the frame , consisting of a set of coupled cylinders having a longitudinal extension, between which the roving to be drawn passes , and a rail carrying the spindles , in a row along the longitudinal axis , rotating about its vertical axis , from which the drawn and twisted yarn is wound .
  • a first method provides for analyzing in the laboratory a sample consisting of the yarn of some spools removed from the spinning machine , generally by means of capacitive sensors capable of detecting the variation of mass along the yarn, thus defining the type and frequency of tangles ; this method is generally reliable , but does not allow for intervening on the processing parameters to improve the quality of the yarn, nor for understanding the causes of defects found, because it is performed after finishing the production of the yarn .
  • the USTER® Tester 5-S 800 manufactured and marketed by Uster Technologies AG, is often used .
  • a second method involves the use of detection modules , based on capacitive or optical sensors , arranged at the spindles for winding the yarn, equipped with blades capable of physically eliminating tangles from the yarn . Even in this case , it is not possible to trace the causes that generated the defect and intervene accordingly .
  • Other methodologies are applied in the yarn winding phase , a process that takes place downstream of the spinning machines ; for example , the Uster® Quantum 3 tester, based on capacitive sensors , produced and marketed by Uster Technologies AG, and the YarnMaster Prisma tester, based on optical sensors , produced and marketed by Loepfe Brothers Ltd, are widely used .
  • a first obj ect of this invention is to detect defects in a yarn in a spinning machine , in order to modi fy the processing parameters of the spinning machine or other upstream machines or maintenance procedures , so as to obtain a better quality yarn .
  • Fig . 1 shows a spinning machine provided with a detection apparatus according to this invention
  • FIG. 1 is a diagram of the spinning machine in Fig . 1 ;
  • - Fig . 3a and 3b show positive images of original neps with corresponding pixel profile ;
  • Fig . 4 shows a set of positive images of synthetic neps .
  • 1 collectively denotes a spinning machine of a spinning line for obtaining spools of yarn from bobbins of roving, having extension along a longitudinal axis X .
  • the spinning machine 1 comprises a frame 2 for supporting components , made in one or more parts arranged side by side , and a creel 4 supported by the frame 2 .
  • the creel 4 comprises vertical posts 6 and a plurality of longitudinal cross members 8 , supported by the posts 6 at a predetermined elevation .
  • the crossbars 8 are intended to support a plurality of hanging bobbins of roving B .
  • the spinning machine 1 comprises a drawing device 10 , supported by the frame 2 .
  • the drawing device 10 comprises a plurality of lower drawing cylinders 12a- 12d, typically three or four in number, which are motori zed, and extend longitudinally, made in one piece or from multiple , structurally distinct , side-by-side and aligned segments .
  • the drawing device 10 further comprises a plurality of pressure arms 14 arranged side by side longitudinally .
  • Each pressure arm carries upper idle pressure rollers 16 .
  • the pressure rollers 16 form drawing pairs , through which the roving passes , which is drawn by the peripheral velocity of each drawing pair, increasing from upstream to downstream .
  • the spinning machine 1 further comprises a winding device 17 arranged below the drawing device 10 , immediately downstream of the first drawing cyl inder 12a .
  • the winding device 17 comprises a yarn guide assembly 18 , comprising a support 20 connected to the frame 2 , and a plurality of yarn guides 22 , supported by the support 20 and arranged side by s ide longitudinally .
  • the winding device 17 further comprises a rail 23 , located below the yarn guide assembly 18 , i . e . , downstream of the yarn guides 22 .
  • the rail 23 is supported by the frame 2 and is vertically translatable with reciprocating motion .
  • the winding device 17 further comprises a plurality of spindles 24 arranged side by side longitudinally along the rail 23 , each rotatable about a respective vertical axis .
  • the roving wound in a predefined bobbin B travels a first path segment to pass into the drawing device 10 , from which it comes out drawn; the drawn roving R travels a second path segment S2 between the drawing device and a respective spindle 24 , passing through a respective yarn guide 22 .
  • the yarn obtained from the drawing and twisting of the roving is wound onto a tube fitted onto the spindle to form a spool of yarn .
  • a detection region 50 is defined, between the drawing device 10 and the winding device 17 , crossed by the second path segment S2 of the drawn roving R .
  • the drawn roving passing through the detection region 50 is subj ected to a process for defect detection, and in particular for the detection of tangles or knots , generally referred to as "neps . "
  • the detection process comprises an acquisition step during which images of at least one segment R* of the roving R in transit through the detection region 50 are acquired .
  • the spinning machine 1 comprises acquisition means 60 , e . g . , digital , e . g . , compri sing a video camera, adapted to acquire images I of at least one segment R* of the roving R in transit through the detection region 50 .
  • the spinning machine 1 comprises illumination means 62 adapted to illuminate , for example by means of a warm or cold light , or, in a variant embodiment , by infrared rays , at least one zone of the detection region 50 comprising the segment R* of the roving R .
  • the detection proces s further comprises a step of processing the images I acquired by said acquisition means 60 , carried out by processing means 70 .
  • Said processing means 70 are configured to detect neps by means of an adaptive or machine learning detection algorithm, in particular of the Haar-cascade type , preferably based on the Viola-Jones method .
  • an adaptive or machine learning detection algorithm in particular of the Haar-cascade type , preferably based on the Viola-Jones method .
  • the latter is illustrated in the paper “Rapid obj ect detection using a boosted cascade of simple features , " presented at the Conference on Computer Vision and Pattern Recognition ( 2001 ) by Paul Viola and Michael Jones , whose teaching on the implementation of the algorithm is expressly incorporated here .
  • the learning of the detection algorithm is based on a set of positive images Ip, i . e . , images in which the segment R* of drawn roving R has neps , and a set of negative images In, in which the segment R* of drawn roving R does not have neps.
  • the positive images Ip of the positive image set are determined by means of processing a pixel profile for each image, wherein said pixel profile is obtained by adding the bright pixels on each row of the image and selecting as positive images those for which at least one peak of the pixel profile exceeds a threshold value, e.g. determined by means of a mean value and a standard deviation (Fig. 3a and 3b) .
  • a threshold value e.g. determined by means of a mean value and a standard deviation
  • the positive images are subjected to a further selection, eliminating the images in which the peak is given by single frayed hairs; said further selection is performed by means of an additional selection algorithm or manually.
  • positive images Ip are digitally constructed and consist of images of semi-circles or semi-ellipses, preferably vertical (Fig. 4) , e.g., differing from each other in the length of the minor axis and the major axis.
  • positive images Ip comprise positive images with original neps and positive images with synthetic neps , i . e . , combining the aforesaid two embodiments .
  • said processing means are configured to detect neps using an adaptive or machine learning detection algorithm of the Convolutional Neural Networks ( CNN) and/or Recurrent Neural Networks (RNN) type .
  • CNN Convolutional Neural Networks
  • RNN Recurrent Neural Networks
  • the acquisition means 60 continuously acquire images I of a segment R* of the roving R .
  • Said images I are processed by the processing means 70 to detect the frequency of the neps and preferably their shape , thus classi fying them by type , by means of the machine learning detection algorithm, in particular of the Haar-cascade type preferably based on the Viola- Jones method or by means of Convolutional Neural Networks ( CNN) and/or Recurrent Neural Networks (RNN) .
  • the machine learning detection algorithm in particular of the Haar-cascade type preferably based on the Viola- Jones method or by means of Convolutional Neural Networks ( CNN) and/or Recurrent Neural Networks (RNN) .
  • CNN Convolutional Neural Networks
  • RNN Recurrent Neural Networks
  • the processing parameters of the spinning machine such as twisting of the yarn, drawing and/or pre-drawing of the roving, type , and weight of the ring, the hardness of the axle rubbers , cylinder gauge , pressure on the axles , and production speed are adj usted in order to improve roving quality, or the parameters are adj usted for the processes performed upstream of the spinning machine , such as twisting, drawing and/or predrawing, hardness of the axle rubbers , cylinder gauge , pressure on the axles , production speed in a roving frame , production speed and drawing assembly gauge in a drawing frame , percentage of rej ects , number of strokes and drawing unit gauge in a combing machine , production speed, nep and trash removal in a
  • this invention ensures good reliability of results , as it allows industrially acceptable discernment between maj or defects and other minor irregularities .
  • the image processing according to the invention is very fast and enables continuous detection of defects and rapid action to improve production .

Abstract

An apparatus for detecting defects in a drawn roving (R) being processed in a spinning machine comprises acquisition means (60), and processing means (70) for digitally processing acquired images (I) and detecting defects by means of a machine learning detection algorithm.

Description

"APPARATUS AND METHOD FOR CONTINUOUS DETECTION OF DEFECTS IN A YARN IN A SPINNING MACHINE" DESCRIPTION
[0001] This invention is in the field of textile fiber processing, and in particular in the field of instruments and methods for detecting defects in the products of spinning preparation processes . In particular, are obj ects of the present invention a method and an apparatus for detecting tangles or knots , usually referred to as "neps , " in the yarn produced in a ringspinning machine .
[0002] As is well known, a spinning machine is capable of processing bobbins of roving to obtain spools of yarn, after having drawn and twisted the roving .
[0003] To this end, the spinning machine consists of a frame extending along a longitudinal axis and supporting a creel from which the bobbins of roving are hung, a drawing device supported by the frame , consisting of a set of coupled cylinders having a longitudinal extension, between which the roving to be drawn passes , and a rail carrying the spindles , in a row along the longitudinal axis , rotating about its vertical axis , from which the drawn and twisted yarn is wound .
[0004] It is well known how imperfections in the yarn cause unpleasant ef fects in the appearance of the fabric, especially in the case of colored fabrics . For this reason, there is a strong need in the industry to monitor the extent and frequency of imperfections , and in particular fiber tangles .
[0005] To date , there are two industrial methodologies for detecting defects in yarn .
[0006] A first method provides for analyzing in the laboratory a sample consisting of the yarn of some spools removed from the spinning machine , generally by means of capacitive sensors capable of detecting the variation of mass along the yarn, thus defining the type and frequency of tangles ; this method is generally reliable , but does not allow for intervening on the processing parameters to improve the quality of the yarn, nor for understanding the causes of defects found, because it is performed after finishing the production of the yarn . For example, the USTER® Tester 5-S 800 , manufactured and marketed by Uster Technologies AG, is often used .
[0007] A second method involves the use of detection modules , based on capacitive or optical sensors , arranged at the spindles for winding the yarn, equipped with blades capable of physically eliminating tangles from the yarn . Even in this case , it is not possible to trace the causes that generated the defect and intervene accordingly . [0008] Other methodologies are applied in the yarn winding phase , a process that takes place downstream of the spinning machines ; for example , the Uster® Quantum 3 tester, based on capacitive sensors , produced and marketed by Uster Technologies AG, and the YarnMaster Prisma tester, based on optical sensors , produced and marketed by Loepfe Brothers Ltd, are widely used .
[0009] A first obj ect of this invention, moreover, is to detect defects in a yarn in a spinning machine , in order to modi fy the processing parameters of the spinning machine or other upstream machines or maintenance procedures , so as to obtain a better quality yarn .
[0010] The aforesaid methodologies are not suitable for this obj ect , partly because they use capacitive or optical sensors that require a regular yarn feed .
[0011] Between the drawing device and the winding device of the spinning machine , however, the yarn undergoes strong oscillations , due to the winding and twisting actions that take place downstream .
[0012] Some studies also involve the use of image acquisition via a video camera, and then processing of the images in order to detect tangles . For example , some methodologies are described in the following articles :
- Li Z , Pan R and Gao W . Formation of digital yarn black board using sequence images . Textile Research Journal . 2016; 86: 593-603;
- Eldessouki M, Ibrahim S and Militky J. A dynamic and robust image processing based method for measuring the yarn diameter and its variation. Textile Research Journal. 2014; 84: 1948-60;
- Ling C, Lianying Z, Li C and Xuanli Z. Digital image processing of cotton yarn seriplane. 2010 International Conference on Computer and Information Application. 2010, p. 274-7;
- Li Z, Xiong N, Wang J, Pan R, Gao W and Zhang N. An intelligent computer method for automatic mosaic of sequential slub yarn images based on image processing. Textile Research Journal. 2018; 88: 2854-66;
Carvalho V, Soares F and Vasconcelos R. Artificial intelligence and image processing based techniques: A tool for yarns parameterization and fabrics prediction. 2009 IEEE Conference on Emerging Technologies & Factory Automation. 2009, p. 1-4.
[0013] However, these methods are not suitable for the intended industrial purposes since they involve the use of a pre-tensioned yarn with a regular feed.
[0014] Finally, some solutions are illustrated, for example, in patent documents CN-A-111235709, CN-A- 109389583, CN-A- 105386174 , DEI 02018111648A1 ,
W02019130209A3, JP2018178282A, and DE 102016121662A1. [0015] Furthermore , the solutions known today are also unsatis factory in terms of the reliability of the results . In ef fect , often some slight irregularities of the fibers , such as a slight enlargement of the fibers in one region, are mistakenly identi fied as tangling or another defect .
[0016] It is the obj ect of this invention to provide a method and apparatus for detecting defects in a yarn being processed in a spinning machine , which satis fies the requirements of the industry and overcomes the drawbacks discussed above with reference to the prior art .
[0017] This obj ect is achieved by a method according to claim 1 and an apparatus according to claim 17 . The claims dependent thereon identi fy additional advantageous embodiments of the invention .
[0018] The features and advantages of the method and the apparatus according to this invention will be apparent from the description below, given by way of non-limiting example in accordance with the figures in the attached drawings , wherein :
Fig . 1 shows a spinning machine provided with a detection apparatus according to this invention ;
- Fig . 2 is a diagram of the spinning machine in Fig . 1 ;
- Fig . 3a and 3b show positive images of original neps with corresponding pixel profile ;
Fig . 4 shows a set of positive images of synthetic neps .
[0019] For descriptive clarity, reference will be made below to a method and apparatus for detecting neps ; however, it is understood that the invention is applicable to defect detection in general .
[0020] With reference to the attached figures , 1 collectively denotes a spinning machine of a spinning line for obtaining spools of yarn from bobbins of roving, having extension along a longitudinal axis X .
[0021] The spinning machine 1 comprises a frame 2 for supporting components , made in one or more parts arranged side by side , and a creel 4 supported by the frame 2 .
[0022] The creel 4 comprises vertical posts 6 and a plurality of longitudinal cross members 8 , supported by the posts 6 at a predetermined elevation . The crossbars 8 are intended to support a plurality of hanging bobbins of roving B .
[0023] Below the crossbars 8 , i . e . , downstream of the bobbins B, the spinning machine 1 comprises a drawing device 10 , supported by the frame 2 .
[0024] The drawing device 10 comprises a plurality of lower drawing cylinders 12a- 12d, typically three or four in number, which are motori zed, and extend longitudinally, made in one piece or from multiple , structurally distinct , side-by-side and aligned segments .
[0025] The drawing device 10 further comprises a plurality of pressure arms 14 arranged side by side longitudinally . Each pressure arm carries upper idle pressure rollers 16 . [0026] Coupling with the pressure cylinders 12a- 12d, the pressure rollers 16 form drawing pairs , through which the roving passes , which is drawn by the peripheral velocity of each drawing pair, increasing from upstream to downstream .
[0027] The spinning machine 1 further comprises a winding device 17 arranged below the drawing device 10 , immediately downstream of the first drawing cyl inder 12a . [0028] The winding device 17 comprises a yarn guide assembly 18 , comprising a support 20 connected to the frame 2 , and a plurality of yarn guides 22 , supported by the support 20 and arranged side by s ide longitudinally . [0029] The winding device 17 further comprises a rail 23 , located below the yarn guide assembly 18 , i . e . , downstream of the yarn guides 22 . The rail 23 is supported by the frame 2 and is vertically translatable with reciprocating motion .
[0030] The winding device 17 further comprises a plurality of spindles 24 arranged side by side longitudinally along the rail 23 , each rotatable about a respective vertical axis .
[0031] In normal operation of the spinning machine 1 , the roving wound in a predefined bobbin B travels a first path segment to pass into the drawing device 10 , from which it comes out drawn; the drawn roving R travels a second path segment S2 between the drawing device and a respective spindle 24 , passing through a respective yarn guide 22 . The yarn obtained from the drawing and twisting of the roving is wound onto a tube fitted onto the spindle to form a spool of yarn .
[0032] According to this invention, a detection region 50 is defined, between the drawing device 10 and the winding device 17 , crossed by the second path segment S2 of the drawn roving R .
[0033] The drawn roving passing through the detection region 50 is subj ected to a process for defect detection, and in particular for the detection of tangles or knots , generally referred to as "neps . "
[0034] The detection process comprises an acquisition step during which images of at least one segment R* of the roving R in transit through the detection region 50 are acquired .
[0035] For this purpose , the spinning machine 1 comprises acquisition means 60 , e . g . , digital , e . g . , compri sing a video camera, adapted to acquire images I of at least one segment R* of the roving R in transit through the detection region 50 .
[0036] Preferably, moreover, the spinning machine 1 comprises illumination means 62 adapted to illuminate , for example by means of a warm or cold light , or, in a variant embodiment , by infrared rays , at least one zone of the detection region 50 comprising the segment R* of the roving R .
[0037] The detection proces s further comprises a step of processing the images I acquired by said acquisition means 60 , carried out by processing means 70 .
[0038] Said processing means 70 are configured to detect neps by means of an adaptive or machine learning detection algorithm, in particular of the Haar-cascade type , preferably based on the Viola-Jones method . The latter is illustrated in the paper "Rapid obj ect detection using a boosted cascade of simple features , " presented at the Conference on Computer Vision and Pattern Recognition ( 2001 ) by Paul Viola and Michael Jones , whose teaching on the implementation of the algorithm is expressly incorporated here .
[0039] The learning of the detection algorithm is based on a set of positive images Ip, i . e . , images in which the segment R* of drawn roving R has neps , and a set of negative images In, in which the segment R* of drawn roving R does not have neps.
[0040] According to a first embodiment (referred to as "with original neps") , starting from images of a drawn roving for learning, e.g., acquired during normal use of a predefined spinning machine, and therefore depicting segments with neps and segments without neps, the positive images Ip of the positive image set are determined by means of processing a pixel profile for each image, wherein said pixel profile is obtained by adding the bright pixels on each row of the image and selecting as positive images those for which at least one peak of the pixel profile exceeds a threshold value, e.g. determined by means of a mean value and a standard deviation (Fig. 3a and 3b) .
[0041] Preferably, moreover, the positive images are subjected to a further selection, eliminating the images in which the peak is given by single frayed hairs; said further selection is performed by means of an additional selection algorithm or manually.
[0042] According to a further embodiment (termed "with synthetic neps") , positive images Ip are digitally constructed and consist of images of semi-circles or semi-ellipses, preferably vertical (Fig. 4) , e.g., differing from each other in the length of the minor axis and the major axis. [0043] According to a still further embodiment ( termed "hybrid" ) , positive images Ip comprise positive images with original neps and positive images with synthetic neps , i . e . , combining the aforesaid two embodiments .
[0044] According to a further embodiment of the invention, said processing means are configured to detect neps using an adaptive or machine learning detection algorithm of the Convolutional Neural Networks ( CNN) and/or Recurrent Neural Networks (RNN) type .
[0045] In the normal operation of the spinning machine , while the roving R is in transit through the detection area 50 , the acquisition means 60 continuously acquire images I of a segment R* of the roving R .
[0046] Said images I are processed by the processing means 70 to detect the frequency of the neps and preferably their shape , thus classi fying them by type , by means of the machine learning detection algorithm, in particular of the Haar-cascade type preferably based on the Viola- Jones method or by means of Convolutional Neural Networks ( CNN) and/or Recurrent Neural Networks (RNN) .
[0047] On the basis of these findings , as part of a method for managing the spinning machine or a spinning line comprising the spinning machine and machines upstream thereof , such as cards , combers , drawing frames and roving frames , the processing parameters of the spinning machine , such as twisting of the yarn, drawing and/or pre-drawing of the roving, type , and weight of the ring, the hardness of the axle rubbers , cylinder gauge , pressure on the axles , and production speed are adj usted in order to improve roving quality, or the parameters are adj usted for the processes performed upstream of the spinning machine , such as twisting, drawing and/or predrawing, hardness of the axle rubbers , cylinder gauge , pressure on the axles , production speed in a roving frame , production speed and drawing assembly gauge in a drawing frame , percentage of rej ects , number of strokes and drawing unit gauge in a combing machine , production speed, nep and trash removal in a card and in a blow room line , or maintenance work is carried out on the spinning machine or on the machines upstream thereo f .
[0048] Innovatively, the apparatus and method for detecting defects in a spinning machine according to this invention meet the needs of the industry and overcome the aforesaid drawbacks .
[0049] Indeed, since the detection is carried out continuously on the roving being processed in the spinning machine , it is possible to intervene to modi fy the processing parameters on the spinning machine or on the machines upstream or to intervene with maintenance interventions in order to improve the quality of the yarn .
[0050] Moreover, advantageously, this invention ensures good reliability of results , as it allows industrially acceptable discernment between maj or defects and other minor irregularities .
[0051] Furthermore , the tests carried out have shown a good correspondence between the readings obtained by means of the apparatus of this invention and the tests based on the testers normally used today as mentioned in the introduction .
[0052] Advantageously, moreover, the image processing according to the invention is very fast and enables continuous detection of defects and rapid action to improve production .
[0053] It is clear that a person skilled in the art , in order to satis fy contingent needs , may make modi fications to the method and the apparatus described above , said modi fications all being contained within the scope of protection as defined in the following claims .

Claims

1. A method for detecting defects in a drawn roving (R) being processed in a spinning machine, comprising the step of acquiring images (I) of the drawn roving (R) in transit in a segment (Sr) of a path (S2) and the step of digitally processing said images (I) to detect said defects, wherein the image processing step (I) involves detecting defects using a machine learning detection algorithm, wherein the learning of the detection algorithm is based on a set of positive images (Ip) in which a depicted roving segment has defects, and a set of negative images (In) in which a depicted roving segment does not have said defects.
2. A method according to claim 1, wherein the processing step provides the step of detecting the frequency of the defects along the roving (R) .
3. A method according to claim 1 or 2, wherein the processing step provides the step of detecting the type of defects.
4. A method according to any of the preceding claims, wherein, starting from images of a drawn roving for learning having segments with defects and segments without defects, the positive images (Ip) are determined by processing a pixel profile for each image, wherein said pixel profile is obtained by adding bright pixels on each row of the image and selecting those for which at least one peak of the pixel profile exceeds a threshold value as positive images.
5. A method according to claim 4, wherein said threshold value is determined by means of an average value of the profile and a standard deviation.
6. A method according to claim 4 or 5, wherein said learning images of the roving are acquired during the normal use of a predefined spinning machine.
7. A method according to any one of claims 4 to 6, wherein the positive images are subjected to a further selection by eliminating the images in which the peak is given by individual pulled hairs.
8. A method according to claim 7, wherein said further selection is performed by means of a further selection algorithm.
9. A method according to claim 7, wherein said further selection is performed manually.
10. A method according to any of the preceding claims, wherein the positive images (Ip) are digitally built and formed by images of preferably vertical semi-circles or semi-ellipses, for example different from one another in length of the minor axis and of the major axis.
11. A method according to any of claims 1 to 9, wherein
- a part of the positive images (Ip) is obtained by means 16 of a machine learning detection algorithm; and a remaining part of the positive images ( Ip ) is obtained by means of digital construction .
12 . A method according to any of the preceding claims , wherein the detection algorithm is of the Haar-cascade type .
13. A method according to claim 12 , wherein the detection algorithm of the Haar-cascade type is based on the Viola- Jones method .
14 . A method according to any of claims 1 to 11 , wherein the algorithm is of the Convolutional Neural Networks ( CNN) and/or Recurrent Neural Networks (RNN) type .
15 . A method for managing a spinning machine ( 1 ) of a spinning line , comprising :
- a method for detecting defects in a drawn roving (R) according to any of the preceding claims , and
- a successive step of varying processing parameters of the spinning machine or performing maintenance operations on said spinning machine .
16. A method for managing a spinning line comprising a spinning machine ( 1 ) and machines for textile processing upstream of the spinning machine , comprising
- a method for detecting defects on the spinning machine ( 1 ) according to any of claims 1 to 14 , and
- a successive step of varying processing parameters of 17 at least one of said machines upstream of the spinning machine or performing maintenance operations on at least one of said machines upstream of the spinning machine.
17. An apparatus for detecting defects in a drawn roving (R) being processed in a spinning machine, comprising:
- acquisition means (60) adapted to acquire images (I) of the drawn roving (R) from a detection area (50) located between a drawing device (10) and a winding device (17) of the spinning machine, said detection area (50) being crossed by a segment (Sr) of a path (S2) of the roving (R) ; processing means (70) operatively connected to the acquisition means for digitally processing said images (I) and detecting the defects; said processing means (70) being configured to detect the defects by means of a machine learning detection algorithm, wherein the learning of the detection algorithm is based on a set of positive images (Ip) in which a represented segment of roving has defects, and a set of negative images (In) , in which a represented segment of drawn roving does not have said defects.
PCT/IB2021/059569 2020-11-16 2021-10-18 Apparatus and method for continuous detection of defects in a yarn in a spinning machine WO2022101714A1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2023528682A JP2023552680A (en) 2020-11-16 2021-10-18 Apparatus and method for continuously detecting yarn defects in a spinning machine
DE112021005995.5T DE112021005995T5 (en) 2020-11-16 2021-10-18 Device and method for the continuous detection of defects in a yarn in a spinning machine
CN202180076738.4A CN116507908A (en) 2020-11-16 2021-10-18 Device and method for continuously detecting yarn defects in spinning machine

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IT102020000027360 2020-11-16
IT102020000027360A IT202000027360A1 (en) 2020-11-16 2020-11-16 APPARATUS AND METHOD FOR THE CONTINUOUS DETECTION OF DEFECTS IN A THREAD IN A SPINNING MACHINE

Publications (1)

Publication Number Publication Date
WO2022101714A1 true WO2022101714A1 (en) 2022-05-19

Family

ID=74592407

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2021/059569 WO2022101714A1 (en) 2020-11-16 2021-10-18 Apparatus and method for continuous detection of defects in a yarn in a spinning machine

Country Status (5)

Country Link
JP (1) JP2023552680A (en)
CN (1) CN116507908A (en)
DE (1) DE112021005995T5 (en)
IT (1) IT202000027360A1 (en)
WO (1) WO2022101714A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102022114910A1 (en) 2022-06-14 2023-12-14 Deutsches Zentrum für Luft- und Raumfahrt e.V. Method, device and computer program for detecting defects and method and device for depositing fiber material
DE102022207070A1 (en) 2022-07-11 2024-01-11 Robert Bosch Gesellschaft mit beschränkter Haftung Method for detecting anomalies on a surface of an object

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1621872A2 (en) * 2003-01-08 2006-02-01 Premier Evolvics PVT. Ltd. Measuring and testing continuous elongated textile material
CN105386174A (en) * 2015-12-03 2016-03-09 江南大学 Siro spinning broken-strand detection device based on image technology and detection algorithm
CN109389583A (en) * 2018-09-17 2019-02-26 东华大学 A kind of coil quality intelligent sort management method and its realization device
CN111235709A (en) * 2020-03-18 2020-06-05 东华大学 Online detection system for spun yarn evenness of ring spinning based on machine vision

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102016121662A1 (en) 2016-11-11 2018-05-17 Saurer Germany Gmbh & Co. Kg Method and device for assessing the quality of a longitudinally moved strand-like material
JP2018178282A (en) 2017-04-06 2018-11-15 村田機械株式会社 Yarn defect display device and yarn processing device
CN111670358A (en) 2017-12-26 2020-09-15 彼得·佩纳 Device and method for monitoring yarn quality
DE102018111648A1 (en) 2018-05-15 2019-11-21 Saurer Spinning Solutions Gmbh & Co. Kg Yarn sensor for optically detecting a yarn moved in its longitudinal direction

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1621872A2 (en) * 2003-01-08 2006-02-01 Premier Evolvics PVT. Ltd. Measuring and testing continuous elongated textile material
CN105386174A (en) * 2015-12-03 2016-03-09 江南大学 Siro spinning broken-strand detection device based on image technology and detection algorithm
CN109389583A (en) * 2018-09-17 2019-02-26 东华大学 A kind of coil quality intelligent sort management method and its realization device
CN111235709A (en) * 2020-03-18 2020-06-05 东华大学 Online detection system for spun yarn evenness of ring spinning based on machine vision

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
VIOLA PAUL ET AL: "ACCEPTED CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION 2001 Rapid Object Detection using a Boosted Cascade of Simple Features", 14 December 2001 (2001-12-14), XP055823865, Retrieved from the Internet <URL:https://www.cs.cmu.edu/~efros/courses/LBMV07/Papers/viola-cvpr-01.pdf> [retrieved on 20210713] *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102022114910A1 (en) 2022-06-14 2023-12-14 Deutsches Zentrum für Luft- und Raumfahrt e.V. Method, device and computer program for detecting defects and method and device for depositing fiber material
DE102022207070A1 (en) 2022-07-11 2024-01-11 Robert Bosch Gesellschaft mit beschränkter Haftung Method for detecting anomalies on a surface of an object

Also Published As

Publication number Publication date
DE112021005995T5 (en) 2023-09-07
CN116507908A (en) 2023-07-28
IT202000027360A1 (en) 2022-05-16
JP2023552680A (en) 2023-12-19

Similar Documents

Publication Publication Date Title
WO2022101714A1 (en) Apparatus and method for continuous detection of defects in a yarn in a spinning machine
CN1080334C (en) Process and device for monitoring quality of yarns
US11319649B2 (en) Ring spinning system and method for operating
US6798506B2 (en) Method and device for detecting impurities in a longitudinally moving thread-like product
US6380548B1 (en) Method and device for detecting foreign matter in longitudinally traveling yarn
EP3293295B1 (en) Measurement system for a machine that processes a continuous strand like textile material
JPH07172699A (en) Device to check wound quality of thread package and application of said device on winder or fine spinning machine
WO2016194484A1 (en) Yarn winding system, automatic winder, spinning frame and yarn winding method
EP3293595A1 (en) An integrated system and method for online monitoring and offline testing in a textile unit
EP0479984B1 (en) Textile on-line sampling inspection
EP1057907A1 (en) Spinning mill processing control systems and methods
CN108285062A (en) Yarn information acquisition device, Yarn winding machine and textile machine system
WO2021223784A1 (en) A method for detecting structural defects of fasciated yarn comprising a core from parallel fibers which is bound together by wrapper fibers and wild fibers, a device for performing the method, a computer program for the device and a computer readable medium with the computer program
CN114761631A (en) Optimizing fiber manufacturing process for foreign fibers
EP3587632A1 (en) Abnormality detection method, fiber processing system, spinning machine, and abnormality detection program
US6349530B1 (en) Process and apparatus for controlling cops of ring spun yarn dependent on a yarn hairiness
CN1214139C (en) Method and device for conducting quality control of textile strips
EP3587636A1 (en) Periodic unevenness detecting method, textile processing system, spinning machine, and periodic unevenness detecting program
Celik et al. An Innovative Solution for Abrage Fault Detection on Yarn Bobbin and Fabric Surface
CN204803458U (en) Take fine machine of branch of automatic monitoring device
Jansen Image-Based Condition Monitoring of Air-Jet Spinning Machines with Artificial Neural Networks
CN117405699A (en) Production method of non-foreign fiber yarn
US4909027A (en) Multi-spindle textile machine monitoring process and apparatus
JPH11350338A (en) Sensing of nap of wound yarn, and sensor therefor
JP2003064550A (en) Method of evaluation for convergence state of yarns, and evaluating apparatus for the same

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21799338

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023528682

Country of ref document: JP

Ref document number: 202180076738.4

Country of ref document: CN

122 Ep: pct application non-entry in european phase

Ref document number: 21799338

Country of ref document: EP

Kind code of ref document: A1