CN118417184B - Intelligent textile automatic sorting system based on machine vision - Google Patents
Intelligent textile automatic sorting system based on machine vision Download PDFInfo
- Publication number
- CN118417184B CN118417184B CN202410842758.3A CN202410842758A CN118417184B CN 118417184 B CN118417184 B CN 118417184B CN 202410842758 A CN202410842758 A CN 202410842758A CN 118417184 B CN118417184 B CN 118417184B
- Authority
- CN
- China
- Prior art keywords
- textile
- textiles
- image
- flaw
- stain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000004753 textile Substances 0.000 title claims abstract description 176
- 230000007547 defect Effects 0.000 claims abstract description 39
- 238000013441 quality evaluation Methods 0.000 claims abstract description 12
- 230000005856 abnormality Effects 0.000 claims description 29
- 230000011664 signaling Effects 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 26
- 238000001514 detection method Methods 0.000 claims description 23
- 230000002159 abnormal effect Effects 0.000 claims description 20
- 238000005452 bending Methods 0.000 claims description 19
- 238000012423 maintenance Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 13
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000002950 deficient Effects 0.000 claims description 6
- 230000001960 triggered effect Effects 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000010191 image analysis Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 10
- 238000003908 quality control method Methods 0.000 abstract description 2
- 239000004744 fabric Substances 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000001965 increasing effect Effects 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention discloses an intelligent textile automatic sorting system based on machine vision, which reduces manual input errors and quickens sorting speed by automatically identifying textile labels, collects image information of textiles and analyzes the image information when sorting the textiles to a corresponding target workshop, comprehensively evaluates stains, defects and sutures to generate flaw estimation values, provides comprehensive data support for quality control of the textiles, improves accuracy of quality evaluation, further generates bar codes comprising flaw grade information according to the flaw estimation values of the corresponding textiles, attaches the bar codes to the corresponding textiles, and continues to convey the bar codes after the attachment is finished until the bar codes are conveyed to the corresponding target workshop of the textiles, thereby solving the problem that the quality of the textiles cannot be evaluated based on quality requirements of the textiles in the prior art, and packages and sends evaluation results and the textiles to the corresponding sorting target workshop.
Description
Technical Field
The invention relates to the technical field of textile sorting, in particular to an intelligent automatic textile sorting system based on machine vision.
Background
With the rapid development of industrial automation, the demand for automated sorting in textile manufacturing is increasing. The traditional manual sorting mode is low in efficiency, is easy to make mistakes, cannot meet the requirement of mass production, and therefore needs to replace manual work to finish the production requirement through automatic sorting.
The existing automatic textile sorting system has the following defects in the practical application process:
During the sorting process of the textiles, the quality of the production of the textiles cannot be evaluated based on the quality requirements of the textiles, the evaluation results and the textiles are packaged and sent to corresponding sorting target workshops, the intelligent degree is low, meanwhile, the quality evaluation task amount is heavy through manpower, and goods are easy to accumulate.
For this reason, put forward an intelligent fabrics automatic sorting system based on machine vision.
Disclosure of Invention
In view of the above, the present invention provides an intelligent automatic sorting system for textiles based on machine vision, so as to solve the problems set forth in the background art.
The aim of the invention can be achieved by the following technical scheme: an intelligent textile automatic sorting system based on machine vision, comprising:
And the classification decision module: the method comprises the steps of moving textiles along with a conveyor belt, scanning and identifying RFID tags on each textile when the textiles pass through an RFID reading area, analyzing information in the RFID tags of each textile after identification, determining a target workshop of each textile, and transferring the corresponding textile from a main conveyor belt to a branch conveyor belt of the target workshop according to determined target workshop control execution equipment;
And an image analysis module: in the conveying process of each textile through the corresponding branch conveyor belt, the image acquisition equipment is arranged through each branch conveyor belt; collecting image information of each textile, preprocessing and analyzing each group of image information, extracting color and pattern information matched with a label from each group of image information analysis results, respectively carrying out matching verification on color verification information and pattern information of the corresponding textile and color and pattern information in the label, and transmitting the image information of the corresponding textile to a quality evaluation module if the verification is passed;
the quality evaluation module: receiving and analyzing the image information of the corresponding textile to obtain a flaw estimation Defal of the corresponding textile; generating a bar code comprising flaw grade information based on the flaw estimation Defal of the corresponding textile, attaching the bar code to the corresponding textile, and continuing to convey the corresponding textile after the attachment is completed until the corresponding textile is conveyed to a target workshop of the corresponding textile;
An abnormality detection module: the sorting process is monitored in real time, the specific type of the abnormality is identified through a self-checking mechanism when the abnormality occurs, a maintenance signaling corresponding to the specific type of the abnormality is triggered after the identification is completed, and corresponding steps are executed.
In some embodiments, image information corresponding to the textile is received and analyzed, specifically:
Firstly, enhancing an image, separating a stain area in the image from a background after enhancing, classifying according to characteristics of the stain area, including oil stain characteristics, ink characteristics and dye permeation characteristics, and setting a weight coefficient corresponding to the oil stain characteristics, the ink characteristics and the dye permeation characteristics respectively; counting the pixel number of each spot area in the image, and converting based on the resolution of the image to obtain each group of spot areas of the corresponding textile; accumulating the stain areas with the oil stain characteristics as the oil stain areas of the corresponding textiles; accumulating the stain areas of the ink features to be used as the ink areas of corresponding textiles; accumulating the stain areas of the dye permeation characteristics as the permeation areas of the corresponding textiles; extracting weight coefficients of all the characteristics, multiplying the oil stain area, the ink area and the permeation area by the corresponding weight coefficients respectively, and then summing to obtain a stain estimated value TR of the corresponding textile;
Thinning a defect area in the image, separating the defect area in the image from the background by using threshold segmentation after thinning is finished, and classifying according to the characteristics of the defect area, wherein the characteristics comprise small hole characteristics and tearing characteristics; setting a weight coefficient corresponding to the small hole characteristic and the tearing characteristic respectively; counting the pixel number of each defective area in the image, and converting based on the resolution of the image to obtain each group of defective areas of the corresponding textile; accumulating the defect areas of the small hole characteristics to be used as the small hole areas of the corresponding textiles; accumulating the defect areas of the tearing characteristics to be used as the tearing areas of the corresponding textiles; and extracting weight coefficients of all the characteristics, multiplying the aperture area and the tearing area by the corresponding weight coefficients respectively, and then summing to obtain defect estimated values TE of the corresponding textiles.
In some embodiments, a flaw estimate Defal is obtained for the corresponding textile, specifically:
Recognizing the edge of a suture in the image, and acquiring a straight line segment in the image after recognition is completed, wherein the straight line segment is the suture of the corresponding textile; tracking the detected straight line segment after the straight line segment is obtained, and identifying the abnormality in the straight line segment in the process of analyzing the path and the continuity of the straight line segment, wherein the abnormality comprises bending and wire breakage; calculating the bending length and the broken line length of each straight line segment in the image, and accumulating the bending length and the broken line length of each group to obtain the bending total length and the broken line total length of the corresponding textile; setting a weight coefficient corresponding to the bending and the broken wire respectively; multiplying the bending total length and the breaking total length of the corresponding textile with the corresponding weight coefficients respectively, and then summing to obtain a stitch estimated value TC of the corresponding textile;
Obtaining a target workshop to which a corresponding textile belongs, and setting maximum allowable values of textile stain estimated values TR, defect estimated values TE and seam estimated values TC of different target workshops; substituting the estimated stain TR, estimated defect TE and estimated seam TC of the corresponding textile into a formula Performing weighted calculation to obtain flaw estimation Defal of the corresponding textile; wherein the method comprises the steps of、AndMaximum allowable values of the stain estimate TR, the defect estimate TE, and the stitch estimate TC are respectively represented;、 And The impact weight factors for the stain estimate TR, defect estimate TE, and stitch estimate TC, respectively.
In some embodiments, the specific process of deriving the flaw grade based on the flaw estimate Defal for the corresponding textile is:
Presetting reference thresholds of flaw estimation Defal of different target workshops, further calculating a difference value between the two values as a flaw exceeding value of the corresponding textile if the flaw estimation Defal of the corresponding textile is larger than the corresponding preset reference threshold, presetting each group of value ranges of the flaw exceeding value, and setting each group of value ranges to correspond to a flaw grade respectively; and matching the flaw exceeding value of the corresponding textile with each preset group of value ranges to obtain the flaw grade of the corresponding textile.
In some embodiments, the maintenance signaling corresponding to the specific type of the anomaly is triggered, and the corresponding steps are executed, specifically:
extracting a fault detection point of an abnormal specific type, drawing a circle by taking the fault detection point as a circle center and setting a distance as a radius, and screening maintainers in the circle range as to-be-selected solution personnel of maintenance signaling;
Sending a position feedback signaling to the mobile terminal of each to-be-selected person, after each to-be-selected person confirms the position feedback signaling, obtaining the specific position of each to-be-selected person, calculating the distance from each to-be-selected person to the fault detection point based on the specific position of each to-be-selected person, and marking the distance as Jr;
further acquiring the historical solution times of each to-be-selected person, extracting the solution time length used by each abnormal solution from the historical solution times of each to-be-selected person, marking the historical solution times of each to-be-selected person as Je, and taking the average value of the solution time length of each group of each to-be-selected person as the solution time length Jf of each to-be-selected person.
In some embodiments, the maintenance signaling corresponding to the abnormal specific type is triggered, and the corresponding steps are executed, further:
Numbering the specific types of the anomalies, wherein the numbering is denoted by i, wherein i=1, 2 or p, wherein p is the total number of the specific types of the anomalies; setting the distance Jr, the historical solution times Je and the influence weight factors of the solution equal time JF corresponding to different abnormal specific types, and respectively marking the distance Jr, the historical solution times Je and the influence weight factors of the solution equal time JF corresponding to the abnormal specific types as 、And；
Abnormal specific type based on current trigger maintenance signaling is based on formulaWeighting calculation is carried out, and a preferable position value wefgh of each to-be-selected solution person in the circle range is obtained; sorting from large to small based on the size of the preferable position value wefgh of each to-be-selected person, selecting the to-be-selected person with the maximum preferable position value wefgh as the processing person for triggering the maintenance signaling at the time, and adding one to the historical solution times of the processing person; and sending the specific type of the current abnormality and the corresponding fault detection point to the mobile terminal of the processing personnel.
In some embodiments, the anomaly detection module is further configured to monitor and analyze defect exceeding values of textiles on each of the branch conveyor belts in real time, preset a threshold number of defect exceeding values of textiles on each of the branch conveyor belts, and trigger a production optimization signaling to a mobile terminal of a manager if the number of defect exceeding values of textiles on a corresponding branch conveyor belt reaches the preset threshold number in a certain sorting operation process.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, the textile labels are automatically identified, the manual input errors are reduced, the sorting speed is increased, meanwhile, when the textiles are sorted to the corresponding target workshops, the image information of the textiles is collected and analyzed, comprehensive evaluation is carried out on stains, defects and seams, flaw evaluation is generated, comprehensive data support is provided for quality control of the textiles, accuracy of quality evaluation is improved, a bar code comprising flaw grade information is further generated according to the flaw evaluation of the corresponding textiles, the bar code is attached to the corresponding textiles, and the bar code is continuously conveyed until conveyed to the target workshops of the corresponding textiles after the attachment is completed, so that the problem that the quality of production of the textiles cannot be evaluated based on the quality requirements of the textiles in the prior art is solved, and an evaluation result and the textiles are packaged and sent to the corresponding sorting target workshops;
according to the invention, the sorting process is monitored in real time, and the abnormality is rapidly identified and responded when the abnormality occurs, and the abnormality is solved by selecting the person with the largest optimal position value through a series of steps, so that the abnormality processing efficiency is improved.
Drawings
Further details, features and advantages of the application are disclosed in the following description of exemplary embodiments with reference to the following drawings, in which:
fig. 1 is a functional block diagram of the present invention.
Detailed Description
Several embodiments of the present application will be described in more detail below with reference to the accompanying drawings in order to enable those skilled in the art to practice the application. The present application may be embodied in many different forms and objects and should not be limited to the embodiments set forth herein. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art. The examples do not limit the application.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and/or the present specification and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Referring to fig. 1, an intelligent textile automatic sorting system based on machine vision includes a classification decision module, an image analysis module, a quality evaluation module and an anomaly detection module;
the classification decision-making module is used for moving the textiles along with the conveyor belt, scanning and identifying the RFID tags on each textile by the RFID reader when the textiles pass through the RFID reading area, analyzing information in the RFID tags of each textile after the identification, determining a target workshop of each textile, and transferring the corresponding textiles from the main conveyor belt to a branch conveyor belt of the target workshop according to the determined target workshop control execution equipment; an implement such as a robotic arm or an actuation valve; label information includes, but is not limited to, number, material, type, color, etc.;
If the RFID tag cannot read or display information errors, the corresponding textile is directly conveyed to an abnormal processing workshop, and operators in the workshop check the textile and manually sort or correct tag information.
The image analysis module is used for acquiring images through image acquisition equipment arranged on each branch conveyor belt in the conveying process of each textile through the corresponding branch conveyor belt; image acquisition devices such as high resolution industrial cameras; collecting image information of each piece of textile, preprocessing each group of image information, analyzing, and extracting color and pattern information matched with the label from each group of image information analysis results; extracting color and pattern features from the preprocessed image by using an image processing technique; the color verification information and the pattern information of the corresponding textiles are respectively matched with the color information and the pattern information in the labels, if the color verification information and the pattern information pass the verification, the image information of the corresponding textiles is sent to a quality evaluation module, and otherwise, the corresponding textiles are conveyed to an abnormal processing workshop; preprocessing including but not limited to graying, filtering, edge detection, etc.;
it is noted that, assuming that the RFID tag of a piece of textile indicates that it should have a stripe pattern of alternating red and white, the industrial camera captures its image as the textile passes through the branch conveyor. Firstly, red and white stripes are identified in an image, then whether the arrangement and the width of the stripes are consistent with the label description is verified, and if the verification is passed, the image information of the corresponding textile is sent to a quality evaluation module; if the verification fails, the corresponding textile is automatically transported to an exception handling shop.
The quality evaluation module receives and analyzes the image information of the corresponding textile to obtain a flaw estimation Defal of the corresponding textile; generating a bar code comprising flaw grade information based on the flaw estimation Defal of the corresponding textile, attaching the bar code to the corresponding textile, and continuing to convey the corresponding textile after the attachment is completed until the corresponding textile is conveyed to a target workshop of the corresponding textile;
The corresponding flaw estimation Defal for the textile is obtained, specifically:
S1: firstly, enhancing an image; such as filters to highlight the edges of stains and spots; separating a stain area in the image from the background by using a threshold segmentation technology after enhancement, and classifying according to the characteristics of the stain area, wherein the stain area comprises oil stain characteristics, ink characteristics and dye penetration characteristics; setting a weight coefficient corresponding to the oil stain characteristic, the ink characteristic and the dye penetration characteristic respectively; presetting according to specific characteristics by technicians, and adjusting later;
counting the pixel number of each spot area in the image, and converting based on the resolution of the image to obtain each group of spot areas of the corresponding textile;
accumulating the stain areas with the oil stain characteristics as the oil stain areas of the corresponding textiles;
Accumulating the stain areas of the ink features to be used as the ink areas of corresponding textiles;
accumulating the stain areas of the dye permeation characteristics as the permeation areas of the corresponding textiles;
extracting weight coefficients of all the characteristics, multiplying the oil stain area, the ink area and the permeation area by the corresponding weight coefficients respectively, and then summing to obtain a stain estimated value TR of the corresponding textile;
S2: refining the defect area in the image by using morphological operation; such as expansion, erosion, open operation, and closed operation; to remove small noise and fill small holes; separating a defect area in the image from the background by using threshold segmentation after finishing refinement, and classifying according to the characteristics of the defect area, wherein the characteristics comprise small hole characteristics and tearing characteristics; setting a weight coefficient corresponding to the small hole characteristic and the tearing characteristic respectively;
counting the pixel number of each defective area in the image, and converting based on the resolution of the image to obtain each group of defective areas of the corresponding textile;
Accumulating the defect areas of the small hole characteristics to be used as the small hole areas of the corresponding textiles;
Accumulating the defect areas of the tearing characteristics to be used as the tearing areas of the corresponding textiles;
Extracting weight coefficients of all the characteristics, multiplying the aperture area and the tearing area by the corresponding weight coefficients respectively, and then summing to obtain defect estimated values TE of the corresponding textiles;
S3: identifying the edge of a suture in the image by using a Canny edge detector, and obtaining a straight line segment in the image by applying Hough transformation after the identification is completed, wherein the straight line segment is the suture of the corresponding textile; tracking the detected straight line segment after the straight line segment is obtained, and identifying the abnormality in the straight line segment in the process of analyzing the path and the continuity of the straight line segment, wherein the abnormality comprises bending and wire breakage; the bending is identified by comparing the difference between the actual path of the straight line segment and the fitted straight line;
Calculating the bending length and the broken line length of each straight line segment in the image, and accumulating the bending length and the broken line length of each group to obtain the bending total length and the broken line total length of the corresponding textile;
Setting a weight coefficient corresponding to the bending and the broken wire respectively; multiplying the bending total length and the breaking total length of the corresponding textile with the corresponding weight coefficients respectively, and then summing to obtain a stitch estimated value TC of the corresponding textile;
S4: obtaining a target workshop to which a corresponding textile belongs, and setting maximum allowable values of textile stain estimated values TR, defect estimated values TE and seam estimated values TC of different target workshops; setting by technicians according to the application scenes and the types of textiles in different target workshops;
Substituting the estimated stain TR, estimated defect TE and estimated seam TC of the corresponding textile into a formula Performing weighted calculation to obtain flaw estimation Defal of the corresponding textile; wherein the method comprises the steps of、AndMaximum allowable values of the stain estimate TR, the defect estimate TE, and the stitch estimate TC are respectively represented;、 And The impact weight factors of the stain evaluation TR, the defect evaluation TE and the stitch evaluation TC are respectively set to 1.205, 1.218 and 1.209;
S5: presetting reference thresholds of flaw estimation Defal of different target workshops, further calculating a difference value between the two values as a flaw exceeding value of the corresponding textile if the flaw estimation Defal of the corresponding textile is larger than the corresponding preset reference threshold, presetting each group of value ranges of the flaw exceeding value, and setting each group of value ranges to correspond to a flaw grade respectively; matching the flaw exceeding value of the corresponding textile with each preset group of value ranges to obtain the flaw grade of the corresponding textile; the larger the flaw exceeding value is, the higher the flaw grade correspondingly matched is;
in addition, the quality evaluation is realized while the textile sorting is realized, the labor cost is saved, the possible errors in manual sorting and quality inspection are reduced, the quality of the textile is evaluated on the whole based on the calculated flaw evaluation value, and the data reference is provided for the adjustment of the subsequent textile production process.
The abnormality detection module is used for monitoring the sorting process in real time and identifying the specific type of the abnormality through a self-checking mechanism when the abnormality occurs; specific types of anomalies include, but are not limited to, tag read failure, image acquisition failure, classification errors, or actuator failure; triggering a maintenance signaling corresponding to the abnormal specific type after the identification is completed, and executing corresponding steps;
Triggering a maintenance signaling corresponding to the specific type of the abnormality, and executing corresponding steps, wherein the specific steps are as follows:
Extracting fault detection points of abnormal specific types; for example, if the image acquisition fails, the image acquisition equipment is used as a fault detection point, if the tag reading fails, the RFID reader is used as a fault detection point, the specific fault detection point is set by a technician, and the subsequent adjustment can be performed according to the actual application situation; drawing a circle by taking the fault detection point as a circle center and setting the distance as a radius, and screening maintenance personnel in the circle range as maintenance signaling to be selected;
Sending a position feedback signaling to the mobile terminal of each to-be-selected person, after each to-be-selected person confirms the position feedback signaling, obtaining the specific position of each to-be-selected person, calculating the distance from each to-be-selected person to the fault detection point based on the specific position of each to-be-selected person, and marking the distance as Jr;
Further acquiring the historical solution times of each to-be-selected person, and extracting the solution time length used by each abnormal solution from each historical solution time of each to-be-selected person; the solution time length starts to count from the time when the solution personnel reaches the fault detection point, and the counting is finished after the abnormal solution is finished;
Marking the historical solution times of each to-be-selected person as Je; taking the average value of the solution time of each group of each to-be-selected solution person as the solution time JF of each to-be-selected solution person;
numbering the specific types of the anomalies, wherein the numbering is denoted by i, wherein i=1, 2 or p, wherein p is the total number of the specific types of the anomalies;
Setting different distance Jr, historical solution times Je and influence weight factors of solution equal time JF corresponding to different abnormal specific types, and respectively marking the distance Jr, the historical solution times Je and the influence weight factors of solution equal time JF corresponding to the abnormal specific types as 、And；
Abnormal specific type based on current trigger maintenance signaling is based on formulaWeighting calculation is carried out, and a preferable position value wefgh of each to-be-selected solution person in the circle range is obtained;、 And Performing specific value taking based on the specific type of the current abnormality;
Sorting from large to small based on the size of the preferable position value wefgh of each to-be-selected person, selecting the to-be-selected person with the maximum preferable position value wefgh as the processing person for triggering the maintenance signaling at the time, and adding one to the historical solution times of the processing person;
the specific type of the current abnormality and the corresponding fault detection point are sent to the mobile terminal of the processor;
It should be noted that, different influencing weight factors are set according to different anomaly types, so that different maintenance scenes can be flexibly adapted, for example, if a tag is read out and fails, the tag is relatively easy to solve, the weight of a priority distance is higher, the problem of anomaly is serious due to the fact that an actuating mechanism is failed, people with higher experience and efficiency are required to process, and the weight of the average time and the historical solution times is higher.
In summary, the monitoring of the sorting process is realized, the sorting process is rapidly identified and responded when the abnormality occurs, and the abnormality is solved by selecting the person with the largest optimal position value wefgh through a series of steps, so that the processing efficiency is improved.
The abnormality detection module is also used for monitoring and analyzing flaw excess values of textiles on each branch conveyor belt in real time, presetting the threshold number of the flaw excess values of the textiles on each branch conveyor belt, and triggering production optimization signaling to a mobile terminal of a manager if the number of the flaw excess values of the textiles on the corresponding branch conveyor belt reaches the preset threshold number in a certain sorting operation process;
It should be noted that, the above-mentioned flaw excess value through real-time supervision and analysis fabrics on each branch conveyer belt to preset corresponding threshold value quantity, when reaching preset threshold value quantity, represent that the quantity of flaw fabrics is more, then correspondingly trigger production optimization signaling and remind the administrator to adjust and optimize the problem that exists to the production line of fabrics, further improved intelligent degree.
The above formulas are all obtained by collecting a large amount of data for software simulation, and a formula close to the true value is selected, and the influencing weight factors and specific coefficient values in the formulas are set by a person skilled in the art according to actual conditions, and can be adjusted and modified later.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (4)
1. Intelligent textile automatic sorting system based on machine vision, characterized by comprising:
And the classification decision module: the method comprises the steps of moving textiles along with a conveyor belt, scanning and identifying RFID tags on each textile when the textiles pass through an RFID reading area, analyzing information in the RFID tags of each textile after identification, determining a target workshop of each textile, and transferring the corresponding textile from a main conveyor belt to a branch conveyor belt of the target workshop according to determined target workshop control execution equipment;
And an image analysis module: in the conveying process of each textile through the corresponding branch conveyor belt, the image acquisition equipment is arranged through each branch conveyor belt; collecting image information of each textile, preprocessing and analyzing each group of image information, extracting color and pattern information matched with a label from each group of image information analysis results, respectively carrying out matching verification on color verification information and pattern information of the corresponding textile and color and pattern information in the label, and transmitting the image information of the corresponding textile to a quality evaluation module if the verification is passed;
the quality evaluation module: receiving and analyzing the image information of the corresponding textile to obtain a flaw estimation Defal of the corresponding textile; generating a bar code comprising flaw grade information based on the flaw estimation Defal of the corresponding textile, attaching the bar code to the corresponding textile, and continuing to convey the corresponding textile after the attachment is completed until the corresponding textile is conveyed to a target workshop of the corresponding textile;
The method comprises the following steps:
Firstly, enhancing an image, separating a stain area in the image from a background after enhancing, classifying according to characteristics of the stain area, including oil stain characteristics, ink characteristics and dye permeation characteristics, and setting a weight coefficient corresponding to the oil stain characteristics, the ink characteristics and the dye permeation characteristics respectively; counting the pixel number of each spot area in the image, and converting based on the resolution of the image to obtain each group of spot areas of the corresponding textile; accumulating the stain areas with the oil stain characteristics as the oil stain areas of the corresponding textiles; accumulating the stain areas of the ink features to be used as the ink areas of corresponding textiles; accumulating the stain areas of the dye permeation characteristics as the permeation areas of the corresponding textiles; extracting weight coefficients of all the characteristics, multiplying the oil stain area, the ink area and the permeation area by the corresponding weight coefficients respectively, and then summing to obtain a stain estimated value TR of the corresponding textile;
thinning a defect area in the image, separating the defect area in the image from the background by using threshold segmentation after thinning is finished, and classifying according to the characteristics of the defect area, wherein the characteristics comprise small hole characteristics and tearing characteristics; setting a weight coefficient corresponding to the small hole characteristic and the tearing characteristic respectively; counting the pixel number of each defective area in the image, and converting based on the resolution of the image to obtain each group of defective areas of the corresponding textile; accumulating the defect areas of the small hole characteristics to be used as the small hole areas of the corresponding textiles; accumulating the defect areas of the tearing characteristics to be used as the tearing areas of the corresponding textiles; extracting weight coefficients of all the characteristics, multiplying the aperture area and the tearing area by the corresponding weight coefficients respectively, and then summing to obtain defect estimated values TE of the corresponding textiles;
Recognizing the edge of a suture in the image, and acquiring a straight line segment in the image after recognition is completed, wherein the straight line segment is the suture of the corresponding textile; tracking the detected straight line segment after the straight line segment is obtained, and identifying the abnormality in the straight line segment in the process of analyzing the path and the continuity of the straight line segment, wherein the abnormality comprises bending and wire breakage; calculating the bending length and the broken line length of each straight line segment in the image, and accumulating the bending length and the broken line length of each group to obtain the bending total length and the broken line total length of the corresponding textile; setting a weight coefficient corresponding to the bending and the broken wire respectively; multiplying the bending total length and the breaking total length of the corresponding textile with the corresponding weight coefficients respectively, and then summing to obtain a stitch estimated value TC of the corresponding textile;
Obtaining a target workshop to which a corresponding textile belongs, and setting maximum allowable values of textile stain estimated values TR, defect estimated values TE and seam estimated values TC of different target workshops; substituting the estimated stain TR, estimated defect TE and estimated seam TC of the corresponding textile into a formula Performing weighted calculation to obtain flaw estimation Defal of the corresponding textile; wherein TR Allow for 、TE Allow for and TC Allow for represent maximum allowable values of the stain estimate TR, the defect estimate TE, and the stitch estimate TC, respectively; α1, α2, and α3 are the impact weight factors of the stain estimate TR, defect estimate TE, and stitch estimate TC, respectively;
presetting reference thresholds of flaw estimation Defal of different target workshops, further calculating a difference value between the two values as a flaw exceeding value of the corresponding textile if the flaw estimation Defal of the corresponding textile is larger than the corresponding preset reference threshold, presetting each group of value ranges of the flaw exceeding value, and setting each group of value ranges to correspond to a flaw grade respectively; matching the flaw exceeding value of the corresponding textile with each preset group of value ranges to obtain the flaw grade of the corresponding textile;
An abnormality detection module: the sorting process is monitored in real time, the specific type of the abnormality is identified through a self-checking mechanism when the abnormality occurs, a maintenance signaling corresponding to the specific type of the abnormality is triggered after the identification is completed, and corresponding steps are executed.
2. The automatic sorting system for intelligent textiles based on machine vision according to claim 1, characterized in that the maintenance signaling corresponding to the specific type of anomaly is triggered and the corresponding steps are performed, in particular:
extracting a fault detection point of an abnormal specific type, drawing a circle by taking the fault detection point as a circle center and setting a distance as a radius, and screening maintainers in the circle range as to-be-selected solution personnel of maintenance signaling;
Sending a position feedback signaling to the mobile terminal of each to-be-selected person, after each to-be-selected person confirms the position feedback signaling, obtaining the specific position of each to-be-selected person, calculating the distance from each to-be-selected person to the fault detection point based on the specific position of each to-be-selected person, and marking the distance as Jr;
further acquiring the historical solution times of each to-be-selected person, extracting the solution time length used by each abnormal solution from the historical solution times of each to-be-selected person, marking the historical solution times of each to-be-selected person as Je, and taking the average value of the solution time length of each group of each to-be-selected person as the solution time length Jf of each to-be-selected person.
3. The automatic sorting system for intelligent textiles based on machine vision according to claim 2, wherein the maintenance signaling corresponding to the specific type of anomaly is triggered and the corresponding steps are performed, further:
Numbering the specific types of the anomalies, wherein the numbering is denoted by i, wherein i=1, 2 or p, wherein p is the total number of the specific types of the anomalies; setting the distance Jr, the historical solution times Je and the influence weight factors of the solution time JF corresponding to different abnormal specific types, and marking the distance Jr, the historical solution times Je and the influence weight factors of the solution time JF corresponding to the abnormal specific types as eta i, mu i and lambda i respectively;
Abnormal specific type based on current trigger maintenance signaling is based on formula Weighting calculation is carried out, and a preferable position value wefgh of each to-be-selected solution person in the circle range is obtained; sorting from large to small based on the size of the preferable position value wefgh of each to-be-selected person, selecting the to-be-selected person with the maximum preferable position value wefgh as the processing person for triggering the maintenance signaling at the time, and adding one to the historical solution times of the processing person; and sending the specific type of the current abnormality and the corresponding fault detection point to the mobile terminal of the processing personnel.
4. The automatic sorting system for intelligent textiles based on machine vision according to claim 1, wherein the anomaly detection module is further configured to monitor and analyze defect exceeding values of textiles on each of the branch conveyor belts in real time, preset a threshold number of defect exceeding values of textiles on each of the branch conveyor belts, and trigger a production optimization signaling to a mobile terminal of a manager if the number of defect exceeding values of textiles on a corresponding branch conveyor belt reaches the preset threshold number in a certain sorting operation process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410842758.3A CN118417184B (en) | 2024-06-27 | 2024-06-27 | Intelligent textile automatic sorting system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410842758.3A CN118417184B (en) | 2024-06-27 | 2024-06-27 | Intelligent textile automatic sorting system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118417184A CN118417184A (en) | 2024-08-02 |
| CN118417184B true CN118417184B (en) | 2024-11-01 |
Family
ID=92324989
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410842758.3A Active CN118417184B (en) | 2024-06-27 | 2024-06-27 | Intelligent textile automatic sorting system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118417184B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372696A (en) * | 2016-11-08 | 2017-02-01 | 苏州巨细信息科技有限公司 | Fabric inspection and defect data statistical system |
| CN113344913A (en) * | 2021-07-06 | 2021-09-03 | 常州宏大智能装备产业发展研究院有限公司 | Fabric flaw detection method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE69515646T2 (en) * | 1995-05-10 | 2000-08-17 | Legler Industria Tessile S.P.A., Ponte San Pietro | Method and device for detecting defects in textile webs and the like |
| CN114549522B (en) * | 2022-04-24 | 2022-06-24 | 启东新朋莱纺织科技有限公司 | Textile quality detection method based on target detection |
| CN115980322B (en) * | 2023-02-09 | 2023-07-04 | 百福工业缝纫机（张家港）有限公司 | Intelligent detection method and system for fabric flaws |
| CN117115147B (en) * | 2023-10-19 | 2024-01-26 | 山东华盛创新纺织科技有限公司 | Textile detection method and system based on machine vision |
| CN118154605B (en) * | 2024-05-11 | 2024-08-02 | 江西智成飞桨科技有限公司 | Textile AI flaw detection method, system and equipment |
-
2024
- 2024-06-27 CN CN202410842758.3A patent/CN118417184B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372696A (en) * | 2016-11-08 | 2017-02-01 | 苏州巨细信息科技有限公司 | Fabric inspection and defect data statistical system |
| CN113344913A (en) * | 2021-07-06 | 2021-09-03 | 常州宏大智能装备产业发展研究院有限公司 | Fabric flaw detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118417184A (en) | 2024-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102036127B1 (en) | Apparel production monitoring system using image recognition | |
| CN109550712A (en) | A kind of chemical fiber wire tailfiber open defect detection system and method | |
| CN108109137A (en) | The Machine Vision Inspecting System and method of vehicle part | |
| CN110216080A (en) | Quality monitoring system of PCB processing production line based on image contrast | |
| CN105044122A (en) | Copper part surface defect visual inspection system and inspection method based on semi-supervised learning model | |
| JP5168215B2 (en) | Appearance inspection device | |
| CN103207186A (en) | Identification method for defect detection of automatic cloth inspecting machine and system thereof | |
| CN112985515B (en) | Method and system for detecting assembly qualification of product fastener and storage medium | |
| CN113111903A (en) | Intelligent production line monitoring system and monitoring method | |
| CN111591715A (en) | Belt longitudinal tearing detection method and device | |
| CN115239711B (en) | Online operation abnormity identification system of sewing equipment | |
| CN112150439A (en) | Automatic sorting equipment and sorting method for injection molding parts | |
| CN116309277A (en) | Steel detection method and system based on deep learning | |
| CN116188459B (en) | Line laser rapid identification method and system for belt tearing detection | |
| CN118417184B (en) | Intelligent textile automatic sorting system based on machine vision | |
| KR102666787B1 (en) | Method, apparatus and program for inspecting defect | |
| Szkilnyk et al. | Vision based fault detection of automated assembly equipment | |
| Mursalin et al. | FABRIC DEFECT INSPECTION SYSTEM USING NEURAL NETWORK AND MICROCONTROLLER. | |
| CN113927217A (en) | Intelligent welding system | |
| CN117862068A (en) | Defective product sorting program verification method, device and storage medium | |
| CN115672778A (en) | Intelligent visual recognition system | |
| CN117094609A (en) | Intelligent management system for aluminum profile production quality based on machine vision | |
| CN118475812A (en) | Tray inspection system and related method | |
| US20230237636A1 (en) | Vision inspection system for defect detection | |
| KR20230168640A (en) | Apparatus and method for inspecting tool status and cut products in plastic working using artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |