CN115897073A - Intelligent control method and system for automatic swinging machine - Google Patents
Intelligent control method and system for automatic swinging machine Download PDFInfo
- Publication number
- CN115897073A CN115897073A CN202211427263.1A CN202211427263A CN115897073A CN 115897073 A CN115897073 A CN 115897073A CN 202211427263 A CN202211427263 A CN 202211427263A CN 115897073 A CN115897073 A CN 115897073A
- Authority
- CN
- China
- Prior art keywords
- cloth
- image
- determining
- flat seaming
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Sewing Machines And Sewing (AREA)
Abstract
The invention provides an intelligent control method of an automatic swinging machine, which comprises the following steps: grabbing and feeding the cloth to be subjected to flat seaming and adjusting the placing position; carrying out image recognition on the placed cloth, and determining a corresponding flat seaming process according to a recognition result; and finishing the blanking work after performing flat seaming work on the cloth based on the flat seaming flow. The invention can lead the lower swing machine to automatically carry out material loading and unloading and automatically complete the flat seaming work.
Description
Technical Field
The invention relates to the field of automatic control of AI intelligence, in particular to an intelligent control method and system for an automatic swinging machine.
Background
The lower hem machine is also called as a flat seaming machine, is special sewing equipment, is provided with more than two straight needles and a curved-hook seaming device, the formed flat seaming stitches are flat, the strength and the elasticity of the stitches are good, and the lower hem machine is suitable for sewing collars, edges, hems, flat seams, splicing seams, trimmings and the like of pajamas, underwear, trousers, various sweaters and knitted clothes.
The traditional lower swinging machine adopts a manual feeding mode, the lower swinging machine is started to work after clothes are placed on the front and rear groups of material teeth manually, and the lower swinging machine is manually controlled to stop after the work is finished, so that the manpower resource is wasted in the process, and therefore, an intelligent control method and system for the automatic lower swinging machine, which can finish automatic feeding and discharging and automatic flat seaming, are needed.
Disclosure of Invention
The invention provides an intelligent control method of an automatic lower-swinging machine, which is used for automatically feeding and discharging cloth and automatically finishing flat seaming.
The invention provides an intelligent control method of an automatic swinging machine, which comprises the following steps:
s1, grabbing and feeding cloth to be subjected to flat seaming and adjusting the placing position;
s2, performing image recognition on the placed cloth, and determining a corresponding flat seaming process according to a recognition result;
and S3, finishing the blanking work after performing flat seaming work on the cloth based on the flat seaming process.
Preferably, the grabbing, feeding and adjusting the placing position of the cloth to be flat-seamed comprises:
shooting the cloth on the conveyor belt through a preset first camera to obtain a first image;
analyzing the first image, and determining the pattern type corresponding to the cloth in the first image;
determining a preset grabbing point position corresponding to the style type and a position where flat seaming work is required;
determining a corresponding preset placing mode according to the position of the cloth needing to be subjected to flat seaming;
and grabbing the cloth through the mechanical arm based on the grabbing point position, and placing the cloth on the flat seaming platform based on the placing mode.
Preferably, the analyzing the first image and the determining the type of the pattern corresponding to the cloth in the first image includes:
step 2, determining whether the probability distribution state of pixel values in the first gray level image meets normal distribution, if so, adjusting the lighting equipment to supplement light for the cloth and then acquiring the first image again, and executing the step 1 and the step 2 in a circulating manner;
step 4, for all pixel points in the first gray level image, determining a local maximum gradient value in a plurality of gradient values corresponding to a plurality of pixel points in a preset second range field of each pixel point in the direction of the x axis and the y axis, and constructing a first image contour point set by using the pixel points corresponding to all the local maximum gradient values in the first gray level image;
step 5, determining the gray value mean value of all pixel points in the first image contour point set, presetting a gray value upper threshold value and a gray value lower threshold value according to the gray value mean value, and screening all pixel points in the first image contour point set according to the gray value upper threshold value and the gray value lower threshold value to obtain a second image contour point set;
step 6, determining the distance between any pixel point and other pixel points in the second image contour point set according to the coordinates of each pixel point in the second image contour point set in the first image, and screening out two pixel points with the closest distance as adjacent points of the pixel point and carrying out line connection;
step 7, performing line connection on each pixel point in the second image contour point set to obtain the contour characteristics of the cloth in the first image;
and 8, matching the contour features with samples in a preset pattern type-contour feature comparison library, and determining the pattern type corresponding to the contour feature with the highest matching degree as the pattern type corresponding to the cloth in the first image.
Preferably, the grabbing the cloth through the mechanical arm based on the grabbing point position comprises:
shooting the cloth through a binocular vision camera arranged on a mechanical arm to respectively obtain a first vision image and a second vision image;
analyzing the first visual image and the second visual image respectively, determining first position information of a grabbing point position in the first visual image, and determining second position information of the grabbing point position in the second visual image;
determining a first shooting distance between a first camera and the cloth and a second shooting distance between a second camera and the cloth in the binocular vision camera, and determining a relative position relation of a grabbing point position on the cloth relative to the binocular vision camera according to the first shooting distance, the second shooting distance, a preset relative distance between the first camera and the second camera and a shooting included angle;
and determining the relative position relation between the mechanical arm gripper and the gripping point position according to the relative position relation of the gripping point position on the cloth relative to the binocular vision camera, and automatically controlling the mechanical arm to approach the gripping point position to grip the cloth.
Preferably, the image recognition of the placed cloth, and the determining of the corresponding flat seaming process according to the recognition result includes:
shooting the cloth placed on the workbench through a preset second camera to obtain a second image;
identifying the second image, and determining whether the pattern type corresponding to the cloth is the same as the identification result corresponding to the first image;
if the cloth materials are different, directly controlling the mechanical arm to place the cloth materials into a conveying belt for manual inspection;
if the cloth is the same as the sewing cloth, determining the position needing to be subjected to flat seaming work, determining a preset flat seaming rule corresponding to the type of cloth, and determining a needle falling position of the cloth when the cloth is subjected to lower hem flat seaming according to the flat seaming rule;
analyzing the second image, determining a specific model of a style type corresponding to the cloth according to the size of the cloth in the second image and the shooting distance between the second camera and the cloth, and further determining a flat seaming stroke corresponding to the model;
and determining a flat seaming process according to the needle falling position and the flat seaming stroke of the cloth during the lower hem flat seaming.
Preferably, the finishing of the blanking work after the flat seaming work is performed on the cloth based on the flat seaming flow comprises:
controlling the flat seaming machine head to move to a needle falling position and starting flat seaming work;
moving the cloth and shooting a position image of the cloth in the moving process through a second camera;
identifying the position image, extracting the edge profile of the cloth, and determining an included angle between the edge profile and the scale mark on the flat seaming platform;
and judging whether the included angle meets a preset flat seaming standard or not, and if not, controlling a flat seaming machine head to adjust the angle to compensate and/or adjust the moving angle of the cloth until the flat seaming work is finished.
And grabbing the cloth after the flat seaming operation by using a mechanical arm, and putting the cloth on a preset conveying belt to complete the blanking operation.
Preferably, in the process of carrying out the flat seaming work, the remaining length of real-time detection line book and remind the staff to change specifically includes:
acquiring image information of the coil, and determining the residual radius of the coil in the image;
determining the initial radius of the coil according to preset coil information, determining a radius difference value between the residual radius and the initial radius, and reminding a worker to replace the coil when the radius difference value is lower than a preset difference threshold value;
or presetting rotating fan blades on the coil, and determining the number of rotation turns of the coil by counting the rotating fan blades through a photoelectric sensor and the number of the rotating fan blades through the photoelectric sensor;
and determining the number of residual turns according to the number of rotation turns of the coil and the number of turns of the coil corresponding to the preset number of turns, reminding a worker to replace the coil when the number of residual turns is lower than the preset number of turns threshold, and resetting the number of rotation turns of the coil after the coil is replaced.
Preferably, the state detection of the sewing needle during the flat seaming operation includes:
laser generating devices are respectively arranged above and below the flat seaming platform, wherein the laser generating devices above the flat seaming platform are aligned with the highest needle point position of an upward lifting needle of a sewing needle in the flat seaming process, and the laser generating devices below the flat seaming platform are aligned with the lowest needle point position of a downward supporting needle of the sewing needle in the flat seaming process;
shooting the highest needle point position and the lowest needle point position of the sewing needle through a preset third camera to obtain a third image;
analyzing the third image to determine whether laser flicker points exist in the third image, and if two laser flicker points exist at the same time, determining that the sewing needle is normal;
if the laser flicker point does not exist, the laser generating device is subjected to self-checking to judge whether the laser generating device fails or not, and if the laser generating device does not fail, the sewing needle is determined to break and a worker is reminded to replace the sewing needle.
In order to achieve the above object, an embodiment of the present invention further provides an intelligent control system for an automatic swinging machine, including:
the feeding module is used for grabbing and feeding the cloth to be subjected to flat seaming and adjusting the placing position;
the flow determining module is used for carrying out image recognition on the placed cloth and determining a corresponding flat seaming flow according to a recognition result;
and the flat seaming module is used for finishing the blanking work after carrying out flat seaming work on the cloth based on the flat seaming process.
Preferably, the feeding module comprises:
the first image acquisition unit is used for shooting the cloth on the conveyor belt through a preset first camera to obtain a first image;
the image analysis unit is used for analyzing the first image and determining the pattern type corresponding to the cloth in the first image;
the position determining unit is used for determining a preset grabbing point position corresponding to the style type and a position where flat seaming work is required;
the placing determining unit is used for determining a corresponding preset placing mode according to the position of the cloth needing to be subjected to flat seaming;
and the grabbing control unit is used for grabbing the cloth through the mechanical arm based on the grabbing point position and placing the cloth on the flat seaming platform based on the placing mode.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flowchart illustrating steps of an intelligent control method for an automatic swing-down machine according to an embodiment of the present invention;
FIG. 2 is a flowchart of a step of grabbing, loading and adjusting a placement position of cloth to be flat-seamed in the embodiment of the invention;
fig. 3 is a schematic structural diagram of an intelligent control system of an automatic swinging machine according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The embodiment of the invention provides an intelligent control method of an automatic swinging machine, which comprises the following steps as shown in figure 1:
s1, grabbing and feeding cloth to be subjected to flat seaming and adjusting the placing position;
s2, performing image recognition on the placed cloth, and determining a corresponding flat seaming process according to a recognition result;
and S3, finishing the blanking work after performing flat seaming work on the cloth based on the flat seaming process.
The working principle and the beneficial effects of the technical scheme are as follows: the cloth that needs to be flat-seamed is grabbed and fed through the mechanical arm, the placing position is adjusted, the placed cloth is subjected to image recognition to determine the type, size and model, the corresponding flat-seaming flow and other related information of the cloth, the corresponding flat-seaming flow is determined according to the recognition result, and finally, the cloth is flat-seamed based on the flat-seaming flow and then is discharged. Based on the integrated work flow of mechanical arm recognition grabbing, cloth information recognition, automatic flat seaming flow determination, flat seaming work and discharging, the AI is used for intelligently recognizing and deciding the image, so that the lower hem machine automatically carries out upper and lower cloth and automatically completes flat seaming work, manual operation behaviors are reduced, and the flat seaming work efficiency of the lower hem of the cloth is improved.
In a preferred embodiment, as shown in fig. 2, the step of grabbing, feeding and adjusting the placement position of the cloth to be flat-seamed comprises the following steps:
s11, shooting the cloth on the conveyor belt through a preset first camera to obtain a first image;
s12, analyzing the first image and determining a pattern type corresponding to the cloth in the first image;
s13, determining a preset grabbing point position corresponding to the style type and a position where flat seaming work is required;
s14, determining a corresponding preset placing mode according to the position of the cloth needing to be subjected to flat seaming;
and S15, grabbing the cloth through the mechanical arm based on the grabbing point position, and placing the cloth on the flat seaming platform based on a placing mode.
The working principle and the beneficial effects of the technical scheme are as follows: when the cloth needing to be subjected to flat seaming is grabbed and fed, shooting the cloth on the conveyor belt through a preset first camera to obtain a first image; analyzing the first image, and determining the pattern type corresponding to the cloth in the first image; determining a preset grabbing point position corresponding to the style type and a position where flat seaming work is required; determining a corresponding preset placing mode according to the position of the cloth needing to be subjected to flat seaming; and grabbing the cloth through the mechanical arm based on the grabbing point position, and placing the cloth on the flat seaming platform based on the placing mode. Through the mode, the intelligent identification and grabbing of the cloth on the conveying belt are realized, and the cloth is reasonably placed according to the flat seaming requirement to improve the flat seaming efficiency.
In a preferred embodiment, analyzing the first image and determining the type of the pattern corresponding to the cloth in the first image includes:
step 2, determining whether the probability distribution state of pixel values in the first gray level image meets normal distribution, if so, adjusting the lighting equipment to supplement light for the cloth and then acquiring the first image again, and executing the step 1 and the step 2 in a circulating manner;
step 4, for all pixel points in the first gray image, determining a local maximum gradient value in a plurality of gradient values corresponding to a plurality of pixel points in a preset second range field of each pixel point in the direction of the x axis and the y axis, and constructing a first image contour point set by using the pixel points corresponding to all the local maximum gradient values in the first gray image;
step 5, determining the gray value mean value of all pixel points in the first image contour point set, presetting a gray value upper threshold value and a gray value lower threshold value according to the gray value mean value, and screening all pixel points in the first image contour point set according to the gray value upper threshold value and the gray value lower threshold value to obtain a second image contour point set;
step 6, determining the distance between any pixel point and other pixel points in the second image contour point set according to the coordinates of each pixel point in the second image contour point set in the first image, and screening out two pixel points with the closest distance as adjacent points of the pixel point and carrying out line connection;
step 7, performing line connection on each pixel point in the second image contour point set to obtain the contour characteristics of the cloth in the first image;
and 8, matching the contour features with samples in a preset pattern type-contour feature comparison library, and determining the pattern type corresponding to the contour feature with the highest matching degree as the pattern type corresponding to the cloth in the first image.
The working principle and the beneficial effects of the technical scheme are as follows: obtaining a first gray image by performing gray processing on the first image, using a Gaussian image fuzzy filter to perform smooth filtering on the first gray image to remove image noise so as to reduce the influence of salt-pepper noise on an identification result, determining whether the probability distribution state of pixel values in the first gray image meets normal distribution, if so, determining that the contrast of pixel points in the image is not high enough, performing light supplement on cloth by adjusting lighting equipment to improve the contrast, then obtaining the first image again, and executing the steps in a circulating manner until the probability distribution state of the pixel values in the obtained first gray image does not meet the normal distribution, then presetting a first derivative in a first range in the x-axis and y-axis directions according to each pixel point in the first gray image, thereby obtaining a gradient value and a gradient direction of each pixel point position in the first gray image, and reflecting the contrast condition of the pixel points in the adjacent range in the image through the gradient value; for all pixel points in the first gray image, determining a local maximum gradient value in a plurality of gradient values corresponding to a plurality of pixel points in a second range preset by each pixel point in the direction of the x axis and the y axis, taking the pixel point corresponding to the local maximum gradient value as a representative point of all the pixel points in a range, and taking the representative point as a basic point of the outline of an image object to perform subsequent work, so that all outline characteristic points in the image can be effectively identified, and a first image outline point set is constructed by utilizing the pixel points corresponding to all the local maximum gradient values in the first gray image; determining a gray value mean value of all pixel points in the first image contour point set, presetting a gray value upper threshold value and a gray value lower threshold value according to the gray value mean value, screening all the pixel points in the first image contour point set according to the gray value upper threshold value and the gray value lower threshold value to obtain a second image contour point set, and screening out coarse error points in the first image contour point set by setting the gray value upper threshold value and the gray value lower threshold value to realize the refinement of the image contour; determining the distance between any pixel point and other pixel points in the second image contour point set according to the coordinates of each pixel point in the first image in the second image contour point set, screening out two pixel points with the closest distance as adjacent points of the pixel point and performing line connection, thereby realizing the conversion of the contour from point to line, assigning the pixel points passed by the connection line according to the mean value of the gray values of all the pixel points in the first image contour point set in the connection process, and further refining the image contour; carrying out line connection on each pixel point in the second image contour point set to obtain the contour characteristics of the cloth in the first image; and matching the contour features with samples in a preset pattern type-contour feature comparison library, and determining the pattern type corresponding to the contour features with the highest matching degree as the pattern type corresponding to the cloth in the first image. Therefore, the intelligent processing and recognition of the image are realized, the accuracy of contour recognition in the image is improved, and finally the accurate searching of the pattern type corresponding to the cloth is realized.
In a preferred embodiment, the grabbing the cloth by the mechanical arm based on the grabbing point position comprises:
shooting the cloth through a binocular vision camera arranged on the mechanical arm to respectively obtain a first visual image and a second visual image;
analyzing the first visual image and the second visual image respectively, determining first position information of a grabbing point position in the first visual image, and determining second position information of the grabbing point position in the second visual image;
determining a first shooting distance between a first camera and the cloth and a second shooting distance between a second camera and the cloth in the binocular vision camera, and determining a relative position relation of a grabbing point position on the cloth relative to the binocular vision camera according to the first shooting distance, the second shooting distance, a preset relative distance between the first camera and the second camera and a shooting included angle;
and determining the relative position relation between the mechanical arm gripper and the gripping point position according to the relative position relation of the gripping point position on the cloth relative to the binocular vision camera, and automatically controlling the mechanical arm to approach the gripping point position to grip the cloth.
The working principle and the beneficial effects of the technical scheme are as follows: when the cloth is grabbed through the mechanical arm based on the grabbing point position, the cloth is shot through a binocular vision camera arranged on the mechanical arm to respectively obtain a first vision image and a second vision image, and the position of a specific position on the cloth is positioned through an image by utilizing the accuracy of position identification through binocular vision detection. Respectively analyzing the first visual image and the second visual image, determining first position information of the grabbing point position in the first visual image, and determining second position information of the grabbing point position in the second visual image, wherein the grabbing point positions in the first visual image and the second visual image are different due to different shooting points of the first visual image and the second visual image; determining a first shooting distance between a first camera and the cloth and a second shooting distance between a second camera and the cloth in the binocular vision camera, determining a relative position relation of a grabbing point position on the cloth relative to the binocular vision camera according to the first shooting distance, the second shooting distance, a preset relative distance between the first camera and the second camera and a shooting included angle, so as to unify corresponding grabbing point positions in the first vision image and the second vision image, and determining a relative position relation of the grabbing point position on the cloth relative to the binocular vision camera according to parameters of the binocular vision camera, such as a camera shooting sight included angle, a camera relative position distance, a scaling ratio of the binocular vision camera and the like; and determining the relative position relation between the mechanical arm gripper and the gripping point position according to the relative position relation of the gripping point position on the cloth relative to the binocular vision camera, and automatically controlling the mechanical arm to approach the gripping point position to grip the cloth. The sight has provided the basis to the intelligent control of arm, snatchs the material loading for the automation, and then has improved the degree of automation of production operation.
In a preferred embodiment, the image recognition of the placed cloth, and the determining of the corresponding flat seaming process according to the recognition result comprises:
shooting the cloth placed on the workbench through a preset second camera to obtain a second image;
identifying the second image, and determining whether the pattern type corresponding to the cloth is the same as the identification result corresponding to the first image;
if the cloth materials are different, directly controlling the mechanical arm to place the cloth materials into a conveying belt for manual inspection;
if the two types of the cloth are the same, determining the position needing to be subjected to flat seaming work, determining a preset flat seaming rule corresponding to the style type of the cloth, and determining a needle falling position of the cloth when the cloth is subjected to lower hem flat seaming according to the flat seaming rule;
analyzing the second image, determining a specific model of a style type corresponding to the cloth according to the size of the cloth in the second image and the shooting distance between the second camera and the cloth, and further determining a corresponding flat seaming stroke under the model;
and determining a flat seaming process according to the needle falling position and the flat seaming stroke of the cloth during the lower hem flat seaming.
The working principle and the beneficial effects of the technical scheme are as follows: in the process of determining the flat seaming process, a preset second camera is used for shooting cloth placed on a workbench to obtain a second image, the second image is identified to determine whether the type of the pattern corresponding to the cloth is the same as the identification result corresponding to the first image, so as to further judge whether the mechanical arm is inaccurate in placement position, folded and wrinkled during placement, and the like, when the situation occurs, the subsequent flat seaming work is not facilitated, the flat seaming work is difficult to recover due to flat seaming errors, and when the situation is determined whether the type of the pattern corresponding to the cloth is different from the identification result corresponding to the first image, directly controlling the mechanical arm to place the cloth into a conveyor belt for manual inspection, manually grabbing and loading the cloth and performing flat seaming, if the cloth is identical to the conveyor belt, determining that accurate flat seaming can be performed, determining a preset flat seaming rule corresponding to the type of cloth after determining a position where flat seaming operation is required, wherein the flat seaming rule comprises patterns of flat seaming lines corresponding to the type of cloth in flat seaming operation, selection of three-line, five-line or five-line flat seaming locking, needle drop points, flat seaming line colors and model materials, offset conditions of the lines in the flat seaming process and the like, and determining a needle drop position when the cloth is subjected to lower-hem flat seaming according to the flat seaming rule; analyzing the second image, determining a specific model of a style type corresponding to the cloth according to the size of the cloth in the second image and the shooting distance between the second camera and the cloth, and further determining a corresponding flat seaming stroke under the model, wherein the flat seaming stroke can comprise information such as a flat seaming path, a flat seaming span, flat seaming frequency or speed, and the like. Therefore, the lower hem machine can automatically complete the flat seaming work by determining the corresponding flat seaming process for the type of the cloth pattern.
In a preferred embodiment, the finishing of the blanking work after the flat seaming work is performed on the cloth based on the flat seaming process comprises:
controlling the flat seaming machine head to move to a needle falling position and starting flat seaming work;
moving the cloth and shooting a position image of the cloth in the moving process through a second camera;
identifying the position image, extracting the edge contour of the cloth, and determining the included angle between the edge contour and the scale mark on the flat seaming platform;
judging whether the included angle meets a preset flat seaming standard or not, and if not, controlling a flat seaming machine head to adjust the angle to compensate and/or adjust the moving angle of the cloth until the flat seaming work is finished;
and grabbing the cloth after the flat seaming operation by using a mechanical arm, and putting the cloth on a preset conveying belt to complete the blanking operation.
The working principle and the beneficial effects of the technical scheme are as follows: the flat seaming machine head is controlled to move to a needle falling position and starts to perform flat seaming; shooting a position image of the cloth in the moving process through a second camera in the cloth moving process; identifying the position image, extracting the edge contour of the cloth, and simultaneously determining an included angle between the edge contour and a scale mark drawn on the flat seaming platform; therefore, whether the included angle meets a preset flat seaming standard or not is judged, if not, the cloth is determined to deflect in the moving process, the cloth needs to be corrected in time, the adjustment angle of the flat seaming machine head needs to be controlled to compensate and/or adjust the moving angle of the cloth until the flat seaming work is completed, and the cloth after the flat seaming work is grabbed by the mechanical arm and is placed on a preset conveying belt to complete the blanking work. Therefore, automatic correction of the flat seaming line in the flat seaming process is realized, the error rate in the flat seaming process is reduced, correction is timely performed under the condition of deviation, and material waste caused by error production is prevented.
In a preferred embodiment, during the process of performing the flat seaming operation, the method for detecting the remaining length of the thread roll in real time and reminding workers to replace the thread roll comprises the following specific steps:
acquiring image information of the coil, and determining the residual radius of the coil in the image;
determining the initial radius of the coil according to preset coil information, determining a radius difference value between the residual radius and the initial radius, and reminding a worker to replace the coil when the radius difference value is lower than a preset difference threshold value;
or presetting rotating fan blades on the coil, and determining the number of rotation turns of the coil by counting the rotating fan blades and the number of the rotating fan blades through a photoelectric sensor;
according to the number of turns of the rotation of coil of wire and this coil of wire correspond preset coil of wire number of turns and confirm the surplus number of turns, remind the staff to carry out the coil of wire and change when the surplus number of turns is less than preset number of turns threshold value to the number of turns of the rotation of resetting the coil of wire after the coil of wire is changed.
The working principle and the beneficial effects of the technical scheme are as follows: the method comprises the steps that the remaining length of a coil is detected in real time, and workers are reminded of replacing the coil, so that the production operation efficiency of the lap machine is improved, image information of the coil can be obtained through a camera in the detection process, and the remaining radius of the coil in an image is determined; determining the initial radius of the currently used coil according to preset coil information, determining a radius difference value between the residual radius and the initial radius, and reminding a worker to replace the coil when the radius difference value is lower than a preset difference threshold value; in a further checking process, the length of the remaining tension line can be calculated by determining the length of the coil of wire, the diameter of the wire and the like through the recognition result of the image, and the calculation process is as follows: based on the radius r = i + j θ of the spiral line in the polar coordinate system, wherein i is the initial radius of the spiral line, j is the radius increasing rate, and θ is a preset correction constant, the radius increasing rate can be determined by the diameter of the thread tightening line, and if the diameter of the thread tightening line is S, the radius of the coil increases by S every time the spiral line rotates, so j = S/2 pi. Considering the reel with a drum, the starting radius of the reel i = r 0 + S/4, wherein r 0 Is the radius of the drum, so the radius of the coil is r = r 0 + S/4+S theta/2 pi, so that the length of the tightly-spiral flat seam line in the case of the same surface meets the formula d l ＝rd θ ＝(r 0 +S/4+Sθ/2π)d θ The length L = L [ (r) of the wound thread is obtained by multiplying the integrated length L of the wound thread by the length L of the wound thread 0 +S/4)θ+Sθ 2 /4π]. The number of the rotating turns of the coil can be determined by presetting rotating fan blades on the coil, enabling the rotating fan blades to pass through a photoelectric sensor, counting by the photoelectric sensor and the number of the rotating fan blades; determining the number of residual turns according to the number of rotation turns of the coil and the number of turns of the coil corresponding to the preset number of turns, and when the number of residual turns is lower than the preset number of turnsRemind the staff to carry out the coil of wire and change during the number of turns threshold value to reset the number of turns of coil of wire after the coil of wire is changed, come to calculate the flat-seam line length through the mode that is more cheap and accurate. Realized the monitoring to surplus flat seam line length through above mode, can let the staff know the surplus condition of coil of wire in advance to in time carry out seamless connection change to the coil of wire, improve production efficiency.
In a preferred embodiment, the detecting the state of the sewing needle during the flat seaming process includes:
laser generating devices are respectively arranged above and below the flat seaming platform, wherein the laser generating device above the flat seaming platform is aligned with the highest needle point position of an upward lifting needle of the sewing needle in the flat seaming process, and the laser generating device below the flat seaming platform is aligned with the lowest needle point position of a downward pushing needle of the sewing needle in the flat seaming process;
shooting the highest needle point position and the lowest needle point position of the sewing needle through a preset third camera to obtain a third image;
analyzing the third image to determine whether laser flicker points exist in the third image, and if two laser flicker points exist at the same time, determining that the state of the sewing needle is normal;
if the laser flicker point does not exist, the laser generating device is self-checked to judge whether the laser generating device fails, and if the laser generating device does not fail, the sewing needle is determined to break and workers are reminded to replace the sewing needle.
The working principle and the beneficial effects of the technical scheme are as follows: laser generating devices are respectively arranged above and below the flat seaming platform, wherein the laser generating device above the flat seaming platform is aligned with the highest needle point position of an upward lifting needle of a sewing needle in the flat seaming process, and the laser generating device below the flat seaming platform is aligned with the lowest needle point position of a downward pushing needle of the sewing needle in the flat seaming process; then, shooting the highest needle point position and the lowest needle point position of the sewing needle through a preset third camera to obtain a third image; further analyzing the third image to determine whether the third image has laser flicker points, and if two laser flicker points exist at the same time, determining that the sewing needle is normal; if the laser flicker point does not exist, the laser generating device is self-checked to judge whether the laser generating device fails, and if the laser generating device does not fail, the sewing needle is determined to break and workers are reminded to replace the sewing needle. Therefore, the detection of the working state of the sewing needle is realized, and the efficiency loss caused by the fact that the sewing needle cannot be timely recovered after the bending and breaking condition occurs is prevented.
In order to achieve the above object, an embodiment of the present invention further provides an intelligent control system for an automatic swing-down machine, as shown in fig. 3, including:
the feeding module is used for grabbing and feeding the cloth to be subjected to flat seaming and adjusting the placing position;
the flow determining module is used for carrying out image recognition on the placed cloth and determining a corresponding flat seaming flow according to a recognition result;
and the flat seaming module is used for finishing the blanking work after carrying out flat seaming work on the cloth based on the flat seaming process.
The working principle and the beneficial effects of the technical scheme are as follows: the cloth that needs to be subjected to flat seaming is grabbed and fed and the placing position is adjusted through the feeding module by utilizing a mechanical arm, relevant information such as a style type, a size and a model and a flat seaming line corresponding to the cloth is determined through image recognition of the placed cloth, a corresponding flat seaming flow is determined through the flow determining module according to a recognition result, and finally, the cloth is subjected to flat seaming work through the flat seaming module based on the flat seaming flow and then is subjected to blanking work. Based on the integrated work flow of mechanical arm recognition grabbing, cloth information recognition, automatic flat seaming flow determination, flat seaming work and blanking, the image is intelligently recognized and decided through AI, manual operation behaviors are reduced, and the flat seaming work efficiency of cloth lower hem is improved.
In a preferred embodiment, the feeding module comprises:
the first image acquisition unit is used for shooting the cloth on the conveyor belt through a preset first camera to obtain a first image;
the image analysis unit is used for analyzing the first image and determining the pattern type corresponding to the cloth in the first image;
the position determining unit is used for determining a preset grabbing point position corresponding to the style type and a position where flat seaming work is required;
the placing determining unit is used for determining a corresponding preset placing mode according to the position of the cloth needing to be subjected to flat seaming;
and the grabbing control unit is used for grabbing the cloth through the mechanical arm based on the grabbing point position and placing the cloth on the flat seaming platform based on the placing mode.
The working principle and the beneficial effects of the technical scheme are as follows: the first image acquisition unit shoots the cloth on the conveyor belt through a preset first camera to obtain a first image; the image analysis unit analyzes the first image and determines the pattern type corresponding to the cloth in the first image; the position determining unit determines a preset grabbing point position corresponding to the style type and a position where flat seaming work is required to be carried out; the placement determining unit determines a corresponding preset placement mode according to the position of the cloth needing to be subjected to flat seaming; the grabbing control unit grabs the cloth through the mechanical arm based on the grabbing point position and places the cloth on the flat seaming platform based on the placing mode. Through the mode, the intelligent identification and grabbing of the cloth on the conveyor belt are realized, and the cloth is reasonably placed according to the flat seaming requirement to improve the flat seaming efficiency.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. An intelligent control method for an automatic swinging machine is characterized by comprising the following steps:
grabbing and feeding the cloth to be subjected to flat seaming and adjusting the placing position;
carrying out image recognition on the placed cloth, and determining a corresponding flat seaming process according to a recognition result;
and finishing the blanking work after performing flat seaming work on the cloth based on the flat seaming flow.
2. The intelligent control method of the automatic lower hem machine according to claim 1, wherein the grabbing, feeding and adjusting the placing position of the cloth to be subjected to flat seaming comprises:
shooting the cloth on the conveyor belt through a preset first camera to obtain a first image;
analyzing the first image, and determining the pattern type corresponding to the cloth in the first image;
determining a preset grabbing point position corresponding to the style type and a position where flat seaming work is required;
determining a corresponding preset placing mode according to the position of the cloth needing to be subjected to flat seaming;
and grabbing the cloth through the mechanical arm based on the grabbing point position, and placing the cloth on the flat seaming platform based on the placing mode.
3. The intelligent control method of the automatic swinging machine according to claim 2, wherein the analyzing the first image and the determining the style type corresponding to the cloth in the first image comprises:
step 1, graying the first image to obtain a first grayscale image, and performing smooth filtering on the first grayscale image by using a Gaussian image fuzzy filter to remove image noise;
step 2, determining whether the probability distribution state of pixel values in the first gray level image meets normal distribution, if so, adjusting the lighting equipment to supplement light for the cloth and then acquiring the first image again, and executing the step 1 and the step 2 in a circulating manner;
step 3, until the probability distribution state of the pixel values in the obtained first gray level image does not meet normal distribution, presetting a first derivative in a first range field in the x-axis and y-axis direction according to each pixel point in the first gray level image, and thus obtaining the gradient value and the gradient direction of each pixel point position in the first gray level image;
step 4, for all pixel points in the first gray image, determining a local maximum gradient value in a plurality of gradient values corresponding to a plurality of pixel points in a preset second range field of each pixel point in the direction of the x axis and the y axis, and constructing a first image contour point set by using the pixel points corresponding to all the local maximum gradient values in the first gray image;
step 5, determining the gray value mean value of all pixel points in the first image contour point set, presetting a gray value upper threshold value and a gray value lower threshold value according to the gray value mean value, and screening all pixel points in the first image contour point set according to the gray value upper threshold value and the gray value lower threshold value to obtain a second image contour point set;
step 6, determining the distance between any pixel point and other pixel points in the second image contour point set according to the coordinates of each pixel point in the second image contour point set in the first image, and screening out two pixel points with the closest distance as adjacent points of the pixel point and carrying out line connection;
step 7, performing line connection on each pixel point in the second image contour point set to obtain the contour characteristics of the cloth in the first image;
and 8, matching the contour features with samples in a preset pattern type-contour feature comparison library, and determining the pattern type corresponding to the contour feature with the highest matching degree as the pattern type corresponding to the cloth in the first image.
4. The intelligent control method of the automatic swinging-down machine according to claim 2, wherein the grabbing the cloth by the mechanical arm based on the grabbing point position comprises:
shooting the cloth through a binocular vision camera arranged on the mechanical arm to respectively obtain a first visual image and a second visual image;
analyzing the first visual image and the second visual image respectively, determining first position information of a grabbing point position in the first visual image, and determining second position information of the grabbing point position in the second visual image;
determining a first shooting distance between a first camera and the cloth and a second shooting distance between a second camera and the cloth in the binocular vision cameras, and determining a relative position relation of a grabbing point position on the cloth relative to the binocular vision cameras according to the first shooting distance, the second shooting distance, a preset relative distance between the first camera and the second camera and a shooting included angle;
and determining the relative position relation between the mechanical arm gripper and the gripping point position according to the relative position relation of the gripping point position on the cloth relative to the binocular vision camera, and automatically controlling the mechanical arm to approach the gripping point position to grip the cloth.
5. The intelligent control method of the automatic lower hem machine according to claim 2, wherein the image recognition of the placed cloth and the determination of the corresponding flat seaming process according to the recognition result comprises:
shooting the cloth placed on the workbench through a preset second camera to obtain a second image;
identifying the second image, and determining whether the pattern type corresponding to the cloth is the same as the identification result corresponding to the first image;
if the cloth materials are different, directly controlling the mechanical arm to place the cloth materials into a conveying belt for manual inspection;
if the two types of the cloth are the same, determining the position needing to be subjected to flat seaming work, determining a preset flat seaming rule corresponding to the style type of the cloth, and determining a needle falling position of the cloth when the cloth is subjected to lower hem flat seaming according to the flat seaming rule;
analyzing the second image, determining a specific model of a style type corresponding to the cloth according to the size of the cloth in the second image and the shooting distance between the second camera and the cloth, and further determining a corresponding flat seaming stroke under the model;
and determining a flat seaming process according to the needle falling position and the flat seaming stroke of the cloth during the lower hem flat seaming.
6. The intelligent control method of the automatic lower hem machine according to claim 1, wherein the finishing of the blanking work after the flat seaming work is performed on the cloth based on the flat seaming process comprises:
controlling the flat seaming machine head to move to a needle falling position and starting flat seaming work;
moving the cloth and shooting a position image of the cloth in the moving process through a second camera;
identifying the position image, extracting the edge profile of the cloth, and determining an included angle between the edge profile and the scale mark on the flat seaming platform;
judging whether the included angle meets a preset flat-seaming standard or not, and if not, controlling a flat-seaming machine head to adjust the angle to compensate and/or adjust the moving angle of the cloth until the flat-seaming work is finished;
and gripping the cloth subjected to the flat seaming operation by using a mechanical arm, and putting the cloth on a preset conveying belt to complete the blanking operation.
7. The intelligent control method of the automatic lap machine according to claim 1, wherein during the flat seaming process, the remaining length of the thread roll is detected in real time and the worker is reminded to replace the thread roll, and the method specifically comprises the following steps:
acquiring image information of the coil, and determining the residual radius of the coil in the image;
determining the initial radius of the coil according to preset coil information, determining a radius difference value between the residual radius and the initial radius, and reminding a worker to replace the coil when the radius difference value is lower than a preset difference threshold value;
or presetting rotating fan blades on the coil, and determining the number of rotation turns of the coil by counting the rotating fan blades and the number of the rotating fan blades through a photoelectric sensor;
and determining the number of residual turns according to the number of rotation turns of the coil and the number of turns of the coil corresponding to the preset number of turns, reminding a worker to replace the coil when the number of residual turns is lower than the preset number of turns threshold, and resetting the number of rotation turns of the coil after the coil is replaced.
8. The intelligent control method of the automatic lower hem machine according to claim 1, wherein the detecting of the state of the sewing needle during the flat seaming process comprises:
laser generating devices are respectively arranged above and below the flat seaming platform, wherein the laser generating device above the flat seaming platform is aligned with the highest needle point position of an upward lifting needle of the sewing needle in the flat seaming process, and the laser generating device below the flat seaming platform is aligned with the lowest needle point position of a downward pushing needle of the sewing needle in the flat seaming process;
shooting the highest needle point position and the lowest needle point position of the sewing needle through a preset third camera to obtain a third image;
analyzing the third image to determine whether laser flicker points exist in the third image, and if two laser flicker points exist at the same time, determining that the sewing needle is normal;
if the laser flicker point does not exist, the laser generating device is self-checked to judge whether the laser generating device fails, and if the laser generating device does not fail, the sewing needle is determined to break and workers are reminded to replace the sewing needle.
9. The utility model provides an automatic pendulum machine intelligence control system which characterized in that includes:
the feeding module is used for grabbing and feeding the cloth to be subjected to flat seaming and adjusting the placing position;
the flow determining module is used for carrying out image recognition on the placed cloth and determining a corresponding flat seaming flow according to a recognition result;
and the flat seaming module is used for finishing the blanking work after carrying out flat seaming work on the cloth based on the flat seaming process.
10. The intelligent control system of an automatic downswing machine according to claim 9, wherein the feeding module comprises:
the first image acquisition unit is used for shooting the cloth on the conveyor belt through a preset first camera to obtain a first image;
the image analysis unit is used for analyzing the first image and determining the pattern type corresponding to the cloth in the first image;
the position determining unit is used for determining a preset grabbing point position corresponding to the style type and a position where flat seaming work is required;
the placing determining unit is used for determining a corresponding preset placing mode according to the position of the cloth needing to be subjected to flat seaming;
and the grabbing control unit is used for grabbing the cloth through the mechanical arm based on the grabbing point position and placing the cloth on the flat seaming platform based on the placing mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211427263.1A CN115897073A (en) | 2022-11-15 | 2022-11-15 | Intelligent control method and system for automatic swinging machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211427263.1A CN115897073A (en) | 2022-11-15 | 2022-11-15 | Intelligent control method and system for automatic swinging machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115897073A true CN115897073A (en) | 2023-04-04 |
Family
ID=86474000
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211427263.1A Pending CN115897073A (en) | 2022-11-15 | 2022-11-15 | Intelligent control method and system for automatic swinging machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115897073A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116548696A (en) * | 2023-05-06 | 2023-08-08 | 深圳市长林自动化设备有限公司 | Press fit detection device and detection method thereof |
-
2022
- 2022-11-15 CN CN202211427263.1A patent/CN115897073A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116548696A (en) * | 2023-05-06 | 2023-08-08 | 深圳市长林自动化设备有限公司 | Press fit detection device and detection method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7539339B2 (en) | Part recognition data creation method and apparatus, electronic part mounting apparatus, and recorded medium | |
| CN100354780C (en) | System for cutting shapes preset in a continuous stream of sheet material | |
| CN115897073A (en) | Intelligent control method and system for automatic swinging machine | |
| CN109324056B (en) | Sewing thread trace measuring method based on machine vision | |
| WO2006042014A2 (en) | Pick and place machine with improved component pick up inspection | |
| US20210343002A1 (en) | Online Detection Method of Circular Weft Knitting Stripe Defects Based on Gray Gradient Method | |
| EP1424885B1 (en) | Electronic component mounting apparatus and electronic component mounting method | |
| CN110454182B (en) | Full-face tunnel boring machine tool changing robot visual positioning structure and method | |
| CN101250783A (en) | Device for distinguishing spools on the basis of their yarn content | |
| CN111733496A (en) | Yarn empty bobbin detection device and method | |
| JP2012234488A (en) | Reference mark model template creating method | |
| CN112796036B (en) | Bobbin state detection method | |
| CN113433137A (en) | Textile cloth surface flaw detection device based on YOLO neural network | |
| CN106706656A (en) | Machine vision-based zipper detection device and method | |
| CN106841222A (en) | A kind of image detecting system for automatic cloth inspection | |
| CN110983609A (en) | Yarn joint detection device and using method thereof | |
| CN109385876A (en) | A kind of the intelligent quality management system and its method of woven fabric | |
| CN112784938A (en) | Intelligent counting method for industrial big data-oriented process batch output | |
| EP2493281B1 (en) | Component mounting apparatus | |
| CN208155260U (en) | A kind of vision detection system for bulb lamp stem position detection | |
| CN107144570A (en) | A kind of tufting machine row's yarn error-detecting method based on machine vision | |
| CN108896561B (en) | Textile fabric detection method based on multi-thread machine vision | |
| KR102462591B1 (en) | Sewing line automatic inspection method using vision system | |
| CN110763695A (en) | Automatic cloth inspecting system and method capable of automatically removing Moire patterns | |
| CN113305017B (en) | Comprehensive intelligent detection and sorting method for full-automatic valve element |
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 |