CN115205299A - Intelligent plate rolling machine fault identification method based on machine vision - Google Patents

Intelligent plate rolling machine fault identification method based on machine vision Download PDF

Info

Publication number
CN115205299A
CN115205299A CN202211134482.0A CN202211134482A CN115205299A CN 115205299 A CN115205299 A CN 115205299A CN 202211134482 A CN202211134482 A CN 202211134482A CN 115205299 A CN115205299 A CN 115205299A
Authority
CN
China
Prior art keywords
point
points
plate
edge
pixel
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
Application number
CN202211134482.0A
Other languages
Chinese (zh)
Inventor
缪屹东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Dongchen Machinery Technology Co ltd
Original Assignee
Jiangsu Dongchen Machinery Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Dongchen Machinery Technology Co ltd filed Critical Jiangsu Dongchen Machinery Technology Co ltd
Priority to CN202211134482.0A priority Critical patent/CN115205299A/en
Publication of CN115205299A publication Critical patent/CN115205299A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the technical field of pattern recognition, in particular to an intelligent plate rolling machine fault recognition method based on machine vision. The method uses image acquisition equipment to acquire images of the plate after the plate bending machine processes the plate. And determining the circle center and radius range of the Hough circle detection according to the scene, and then detecting whether a circumference exists through Hough circle transformation. And judging whether the plate bending machine fails or not according to the Hough circle detection result. The method uses a Hough circle detection method to judge the state of the plate processed by the plate bending machine so as to judge whether the plate bending machine has a fault, in the traditional Hough circle detection algorithm, each point in an image needs to be taken as a center point, the length of the image is taken as a radius, traversal is performed once and once, the calculation cost is very high, the range of the center point and the radius is determined by analyzing a scene, the Hough circle detection range is reduced, and the calculation efficiency is improved.

Description

Intelligent plate rolling machine fault identification method based on machine vision
Technical Field
The invention relates to the technical field of pattern recognition, in particular to an intelligent plate rolling machine fault recognition method based on machine vision.
Background
The plate bending machine is a device for bending and forming a plate by using a working roll, can be used for forming parts with different shapes, such as a cylindrical part, a conical part and the like, and is very important processing equipment. The principle is that the working roll is moved by external force such as hydraulic pressure, mechanical force and the like, so that the plate is bent or rolled and formed. Along with the rapid development of economic construction in China, the demand on the plate bending machine is higher and higher, and the technical requirements are higher and higher, when the plate bending machine breaks down when bending a plate, for example, the plate bending force or angle is incorrect, the plate is not changed into a closed circle or edges and corners exist around the plate, so that whether the plate bending machine breaks down or not can be judged according to the state of the plate after being bent.
The existing judging method can identify a circular area in a cross section image of a plate processed by a plate rolling machine through a machine vision method, and judge whether a fault occurs or not through parameters of the circular area. However, the existing method is only applicable and determined in the case that a circle exists in the image, and if it is not determined whether the image includes the circle, the method is not accurate.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an intelligent plate rolling machine fault identification method based on machine vision, and the adopted technical scheme is as follows:
the invention provides a plate rolling machine fault intelligent identification method based on machine vision, which comprises the following steps:
obtaining a cross section image of the plate processed by the plate bending machine; obtaining edge information of the cross-section image to obtain an edge image; the edge image comprises an inner edge and an outer edge of the plate;
respectively determining four first representative points of the inner edge and four second representative points of the outer edge according to the maximum minimum abscissa and the maximum minimum ordinate of the edge point on the inner edge and the outer edge; the first representative point forms a first rectangular area, and the second representative point forms a second rectangular area;
determining the thickness of the plate according to the sizes of the first rectangular area and the second rectangular area; taking each pixel point in the second rectangular area as an initial central point, and rounding by taking the thickness of the plate as a radius to obtain a test circle; taking each pixel point in the second rectangular area as a starting point, making a ray along the directions of the starting point and one edge point, if the ray comprises two pixel points, regarding the ray as a test ray, and respectively obtaining a first distance and a second distance from the starting point to the two pixel points on the test ray; obtaining the distance difference between the first distance and the second distance, obtaining the similarity of the distance difference and the plate thickness, and obtaining the position fluctuation factor of the pixel point corresponding to the starting point according to all the similarities corresponding to the starting point of the test ray;
if no edge point exists in the test circle, the pixel point corresponding to the initial circle center point is the first circle center point to be selected; obtaining circle center confidence according to the position fluctuation factor of the first circle center point to be selected; screening out a second circle center point to be selected according to the circle center confidence coefficient; and determining two radiuses of a second circle center point to be selected according to the first representative point and the second representative point, rounding to obtain a reference circle, screening out detection circles according to the number of edge points on the reference circle, and if no detection circle exists, indicating that the plate bending machine fails.
Further, the first representative point constituting a first rectangular area includes:
selecting 4 pixel points with the largest and smallest horizontal coordinates and the largest and smallest vertical coordinates from the coordinates of all edge points, making two pixel points with the largest and smallest horizontal coordinates into horizontal straight lines passing through the two points according to the coordinates of the four pixel points, and making two pixel points with the largest and smallest vertical coordinates into vertical straight lines passing through the two points, wherein the four straight lines form a first rectangular area.
Further, the method of obtaining the second representative point includes:
respectively making a vertical straight line for the pixel points with the maximum abscissa and the minimum abscissa, extracting two pixel points closest to the two points in the crossed points of the vertical straight line and the edge points, making a horizontal straight line for the two pixel points with the maximum ordinate and the minimum ordinate, and extracting the two pixel points closest to the two points in the horizontal straight line to obtain a second representative point.
Further, the determining the thickness of the plate material according to the sizes of the first rectangular area and the second rectangular area comprises:
Figure 934539DEST_PATH_IMAGE001
wherein, the first and the second end of the pipe are connected with each other,
Figure 285886DEST_PATH_IMAGE002
the thickness of the plate is the thickness of the plate,
Figure 599888DEST_PATH_IMAGE003
is the length and width of the first rectangular area,
Figure 480119DEST_PATH_IMAGE004
is the length and width of the second rectangular area.
Further, the obtaining a distance difference between the first distance and the second distance, and obtaining similarity between the distance difference and the plate thickness, and the obtaining the position fluctuation factor of the pixel point corresponding to the starting point according to all similarities corresponding to the starting point of the test ray includes:
Figure 652474DEST_PATH_IMAGE005
wherein, the first and the second end of the pipe are connected with each other,
Figure 745195DEST_PATH_IMAGE006
is as follows
Figure 421027DEST_PATH_IMAGE007
The position of the individual starting points is subject to fluctuations,
Figure 3318DEST_PATH_IMAGE008
is as follows
Figure 161505DEST_PATH_IMAGE007
The position coordinates of the individual starting points,
Figure 854654DEST_PATH_IMAGE009
is a first
Figure 650572DEST_PATH_IMAGE010
The coordinates of the pixel points on the test ray that are closest to the starting point,
Figure 403764DEST_PATH_IMAGE011
is a first
Figure 19553DEST_PATH_IMAGE010
The coordinates of the pixel point on the test ray that is the second closest to the starting point,
Figure 781973DEST_PATH_IMAGE012
is as follows
Figure 432397DEST_PATH_IMAGE007
The number of test rays corresponding to each starting point,
Figure 356491DEST_PATH_IMAGE013
is the thickness of the plate.
Further, the obtaining of the circle center confidence according to the position fluctuation factor of the first circle center point to be selected includes:
Figure 990735DEST_PATH_IMAGE014
wherein, the first and the second end of the pipe are connected with each other,
Figure 524222DEST_PATH_IMAGE015
is a first
Figure 29153DEST_PATH_IMAGE007
The confidence of the circle center of each pixel point,
Figure 124148DEST_PATH_IMAGE006
is a first
Figure 714529DEST_PATH_IMAGE007
The position fluctuation factor of each pixel point is determined,
Figure 553172DEST_PATH_IMAGE016
are natural constants.
The invention has the following beneficial effects:
the embodiment of the invention uses a Hough circle detection method to judge the state of the plate processed by the plate bending machine to judge whether the plate bending machine has a fault, in the traditional Hough circle detection algorithm, each point in an image needs to be taken as a center point, the length of the image is taken as a radius, traversal is performed once and once, and the calculation cost is very high.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a plate bending machine fault intelligent identification method based on machine vision according to an embodiment of the present invention.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined object, the following detailed description will be given to a method for intelligently identifying a fault of a plate rolling machine based on machine vision according to the present invention, with reference to the accompanying drawings and preferred embodiments, and specific implementation manners, structures, features and effects thereof. In the following description, the different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the intelligent plate bending machine fault identification method based on machine vision in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for intelligently identifying a fault of a plate bending machine based on machine vision according to an embodiment of the present invention is shown, where the method includes:
step S1: obtaining a cross section image of the plate processed by the plate bending machine; obtaining edge information of the cross-section image to obtain an edge image; the edge image comprises an inner edge and an outer edge of the plate.
The plate bending machine is a machine for bending a plate into a cylindrical object, the plate is conveyed to a material presenting area through a conveying channel after being bent, and an image acquisition device is used for acquiring a cross section image of the plate after being processed. In the embodiment of the invention, in order to facilitate the operation of subsequent images, graying is applied to the cross-section image to obtain the grayscale image of the processed plate.
In the embodiment of the invention, the plate rolling machine is used for rolling the plate to obtain the cylindrical plate, the acquired image is the image of the cross section of the plate, if the plate rolling machine fails, a rolling roller of the plate rolling machine cannot move according to the direction of a preset angle, so that the treated plate possibly cannot form a cylinder or the surface of the plate is not smooth, a gap is formed on the circular circumference of the cross section in the image in the cross section image, the problems of no bonding, straight line on the circumference, plate rolling angle change and the like exist.
Based on the above problems, the embodiment of the present invention adopts hough circle transformation to determine whether the above situation occurs by detecting a circular edge, and before using hough circle transformation, a gray scale image is first converted into an edge image by edge detection.
After the edge points are obtained by edge detection, each edge pixel point under the rectangular coordinate system can be placed on a circle formed by a plurality of center points and radiuses, so that each edge pixel point can correspond to a three-dimensional curve formed by the radiuses and the center points, a threshold value is set, and when the intersection number of the curves is larger than the threshold value, a circle is considered.
However, in the case where only a circle is present in the image, if it is not possible to determine whether the image contains a circle, the method is not accurate. This is improved by embodiments of the present invention, and the scene according to embodiments of the present invention determines the location of the center point and the size of the radius.
Step S2: respectively determining four first representative points of the inner edge and four second representative points of the outer edge according to the maximum minimum abscissa and the maximum minimum ordinate of the upper edge point of the inner edge and the outer edge; the first representative point constitutes a first rectangular region and the second representative point constitutes a second rectangular region.
Because of the thickness of the sheet material, there are outer and inner edges in the edge image. Determining four first representative points of the inner edge and four second representative points of the outer edge according to the maximum minimum abscissa and the maximum minimum ordinate of the upper edge point of the inner edge and the outer edge respectively, specifically including:
according to the coordinates of the four pixel points, the two pixel points with the largest horizontal coordinate and the smallest horizontal coordinate are used as horizontal straight lines of the two points, the two pixel points with the largest vertical coordinate and the smallest vertical coordinate are used as vertical straight lines of the two points, the four straight lines form a rectangular area, the pixel point of the center of the circle is fixed in the interior of all the edge points, and therefore the center of the circle is fixed in the first rectangular area.
The abscissa and the ordinate in the embodiment of the present invention refer to the number of rows and columns in the image, i.e., position information of the image. For example, the (1, 1) coordinate indicates the first row and the first column, and the (n, 1) coordinate indicates the nth row and the 1 st column.
Because the cylindrical shape in the embodiment of the invention has thickness, the 4 pixel points found in the steps move inwards to form another edge point, so that for the pixel point with the maximum abscissa and the minimum abscissa, a vertical straight line is respectively made for the two points, two pixel points closest to the two points are extracted from the crossed points of the vertical straight line and the edge points, and then, similarly, two pixel points with the maximum ordinate and the minimum ordinate are made for the horizontal straight line of the two points, and the two pixel points closest to the two points are also extracted from the horizontal straight line, so that new 4 pixel points are obtained, and the four pixel points also obtain a rectangular area in the mode, wherein the rectangular area is smaller than the last one, the rectangular area is regarded as a second rectangular area, and the center of a circle is also in the area.
The approximate area of the center of the circle, namely the second rectangular area, is obtained through the steps. And then, calculating the confidence of each pixel point in the region.
And step S3: determining the thickness of the plate according to the sizes of the first rectangular area and the second rectangular area; taking each pixel point in the second rectangular area as an initial center point, and taking the thickness of the plate as a radius to make a circle to obtain a test circle; taking each pixel point in the second rectangular area as a starting point, making a ray along the directions of the starting point and one edge point, if the ray comprises two pixel points, regarding the ray as a test ray, and respectively obtaining a first distance and a second distance from the starting point to the two pixel points on the test ray; and obtaining the distance difference between the first distance and the second distance, obtaining the similarity between the distance difference and the plate thickness, and obtaining the position fluctuation factor of the pixel point corresponding to the starting point according to all the similarities corresponding to the starting point of the test ray.
Let the length and width of the first rectangular region respectively be
Figure 443767DEST_PATH_IMAGE017
. The length and width of the second rectangular region are respectively
Figure 709664DEST_PATH_IMAGE018
And subtracting the length and the width corresponding to the two and dividing by 2 to obtain the thickness of the plate, and calculating as follows:
Figure 787341DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 164096DEST_PATH_IMAGE002
the thickness of the plate is the thickness of the plate,
Figure 407733DEST_PATH_IMAGE003
is the length and width of the first rectangular area,
Figure 844531DEST_PATH_IMAGE004
is the length and width of the second rectangular area.
And taking each pixel point in the second rectangular area as an initial center point, and taking the thickness of the plate as the radius to make a circle to obtain a test circle. Firstly, in a second rectangular region, all pixel points in the region are given a range, and because a center point cannot be around an edge point, each pixel point in the region is taken as the center of a circle,
Figure 409504DEST_PATH_IMAGE002
a circle is obtained for the radius, and the edge separation degree of the point is judged according to whether the edge point exists in the circle or not.
Figure 589950DEST_PATH_IMAGE019
Wherein
Figure 52809DEST_PATH_IMAGE020
Indicating the edge separation degree of the v-th pixel point if
Figure 660508DEST_PATH_IMAGE021
Then it indicates a low degree of phase separation, if
Figure 447198DEST_PATH_IMAGE022
Then a high degree of phase separation is indicated.
Taking each pixel point in the second rectangular area as a starting point, making a ray along the directions of the starting point and one edge point, if the ray comprises two pixel points, regarding the ray as a test ray, and respectively obtaining a first distance and a second distance from the starting point to the two pixel points on the test ray; obtaining a distance difference between the first distance and the second distance, obtaining similarity of the distance difference and the plate thickness, and obtaining a position fluctuation factor of a pixel point corresponding to the starting point according to all similarities corresponding to the starting point of the test ray, specifically comprising:
Figure 431335DEST_PATH_IMAGE023
wherein the content of the first and second substances,
Figure 885450DEST_PATH_IMAGE006
is as follows
Figure 664050DEST_PATH_IMAGE007
The position of the individual starting points is subject to fluctuations,
Figure 938037DEST_PATH_IMAGE008
is as follows
Figure 958820DEST_PATH_IMAGE007
The position coordinates of the individual starting points,
Figure 533021DEST_PATH_IMAGE009
is as follows
Figure 482522DEST_PATH_IMAGE010
The coordinates of the pixel points on the test ray that are closest to the starting point,
Figure 509384DEST_PATH_IMAGE011
is a first
Figure 569744DEST_PATH_IMAGE010
The coordinates of the pixel point on the test ray that is the second closest to the starting point,
Figure 264031DEST_PATH_IMAGE012
is as follows
Figure 148548DEST_PATH_IMAGE007
The number of test rays corresponding to each starting point,
Figure 397126DEST_PATH_IMAGE013
is the thickness of the plate.
And step S4: if no edge point exists in the test circle, the pixel point corresponding to the initial circle center point is the first circle center point to be selected; obtaining circle center confidence according to the position fluctuation factor of the first circle center point to be selected; screening out a second circle center point to be selected according to the circle center confidence coefficient; and determining two radiuses of a second circle center point to be selected according to the first representative point and the second representative point, performing Hough circle detection to obtain a reference circle, screening out detection circles according to the number of edge points on the reference circle, and if no detection circle exists, indicating that the plate bending machine fails.
Namely, selection
Figure 261177DEST_PATH_IMAGE020
The method includes the following steps that a point 1 serves as a first central point to be selected, and circle center confidence is obtained according to position fluctuation factors of the first central point to be selected, and the method specifically includes the following steps:
Figure 809970DEST_PATH_IMAGE014
wherein, the first and the second end of the pipe are connected with each other,
Figure 605669DEST_PATH_IMAGE015
is as follows
Figure 341544DEST_PATH_IMAGE007
The confidence of the center of a circle of each pixel point,
Figure 9285DEST_PATH_IMAGE006
is a first
Figure 147006DEST_PATH_IMAGE007
The position fluctuation factor of each pixel point is determined,
Figure 874790DEST_PATH_IMAGE016
are natural constants.
In the formula
Figure 97961DEST_PATH_IMAGE024
In order to have a final result falling within the interval 0-1, the molecules have a minimum of 1, a maximum of e, and the moreThe higher the confidence of the large.
Figure 303815DEST_PATH_IMAGE015
For representing the confidence of the circle center, the value range of the curve of the value is 0-1, the larger the value is, the better the confidence of the circle center is, for the scheme, the selection is made
Figure 296041DEST_PATH_IMAGE025
The pixel point of (2) is taken as the range of the circle center, namely the group committee second to-be-selected circle center point with the circle center confidence coefficient larger than 0.6.
And after a second circle center point to be selected is obtained, obtaining the radius of Hough circle detection, obtaining a point in a second rectangular region through a diagonal line, selecting the length from the point to the longest line in 4 diagonal lines as the maximum radius of Hough circle detection, and taking u as the minimum radius, thereby obtaining the range of the circle center point and the range of the radius of Hough circle transformation, and obtaining a plurality of reference circles.
And screening out detection circles according to the number of edge points on the reference circle, and setting a threshold value to be 80%, namely, when 80% of pixel points on the circumference are edge points, the circumference is considered as the detected reference circle.
If two circles are obtained after image detection, the plate bending machine is not considered to have a fault, and in addition, the plate bending machine is considered to have a fault, so that the curled plate cannot keep a good round shape and is an unqualified product.
In summary, in the embodiment of the present invention, the image acquisition device is used to acquire the image of the plate bending machine after the plate is processed. And determining the circle center and the radius range of the Hough circle detection according to the scene, and then detecting whether a circumference exists through Hough circle transformation. And judging whether the plate rolling machine fails or not according to the Hough circle detection result. The embodiment of the invention uses a Hough circle detection method to judge the state of the plate processed by the plate bending machine so as to judge whether the plate bending machine fails, in the traditional Hough circle detection algorithm, each point in an image needs to be taken as a center point, the image length is taken as a radius, traversal is performed once, and the calculation cost is very high.
It should be noted that: the sequence of the above embodiments of the present invention is only for description, and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (6)

1. A veneer reeling machine fault intelligent identification method based on machine vision is characterized by comprising the following steps:
obtaining a cross section image of the plate processed by the plate bending machine; obtaining edge information of the cross-section image to obtain an edge image; the edge image comprises an inner edge and an outer edge of the plate;
respectively determining four first representative points of the inner edge and four second representative points of the outer edge according to the maximum minimum abscissa and the maximum minimum ordinate of the edge point on the inner edge and the outer edge; the first representative point forms a first rectangular area, and the second representative point forms a second rectangular area;
determining the thickness of the plate according to the sizes of the first rectangular area and the second rectangular area; taking each pixel point in the second rectangular area as an initial center point, and taking the thickness of the plate as a radius to make a circle to obtain a test circle; taking each pixel point in the second rectangular area as a starting point, making a ray along the directions of the starting point and one edge point, if the ray comprises two pixel points, regarding the ray as a test ray, and respectively obtaining a first distance and a second distance from the starting point to the two pixel points on the test ray; obtaining the distance difference between the first distance and the second distance, obtaining the similarity of the distance difference and the plate thickness, and obtaining the position fluctuation factor of the pixel point corresponding to the starting point according to all the similarities corresponding to the starting point of the test ray;
if no edge point exists in the test circle, the pixel point corresponding to the initial circle center point is the first circle center point to be selected; obtaining circle center confidence according to the position fluctuation factor of the first circle center point to be selected; screening out a second circle center point to be selected according to the circle center confidence coefficient; and determining two radiuses of a second circle center point to be selected according to the first representative point and the second representative point, performing Hough circle detection to obtain reference circles, screening out detection circles according to the number of edge points on the reference circles, and judging whether the plate bending machine fails or not according to the number of the detection circles.
2. The intelligent machine vision-based veneer reeling machine fault identification method according to claim 1, wherein the first representative point forming a first rectangular area comprises:
selecting 4 pixel points with the largest and smallest abscissa and the largest and smallest ordinate from the coordinates of all the edge points, making two pixel points with the largest and smallest abscissa as horizontal straight lines passing through the two points according to the coordinates of the four pixel points, and making two pixel points with the largest and smallest ordinate as vertical straight lines passing through the two points, wherein the four straight lines form a first rectangular area.
3. The intelligent machine vision-based veneer reeling machine fault identification method according to claim 2, wherein the method for obtaining the second representative point comprises the following steps:
respectively making a vertical straight line for the pixel points with the maximum abscissa and the minimum abscissa, extracting two closest pixel points from the two points in the intersection points of the vertical straight line and the edge points, making a horizontal straight line for the two pixel points with the maximum ordinate and the minimum ordinate, and extracting the two closest pixel points from the two points in the horizontal straight line to obtain a second representative point.
4. The intelligent machine vision-based veneer reeling machine fault identification method of claim 1, wherein the determining of the thickness of the plate according to the sizes of the first rectangular area and the second rectangular area comprises:
Figure 197567DEST_PATH_IMAGE001
wherein, the first and the second end of the pipe are connected with each other,
Figure 172477DEST_PATH_IMAGE002
the thickness of the plate is the thickness of the plate,
Figure 60798DEST_PATH_IMAGE003
is the length and width of the first rectangular area,
Figure 412145DEST_PATH_IMAGE004
the length and width of the second rectangular area.
5. The method of claim 1, wherein the obtaining of the distance difference between the first distance and the second distance and the similarity between the distance difference and the plate thickness according to the intelligent identification method for the plate bending machine fault based on the machine vision comprises:
Figure 436733DEST_PATH_IMAGE005
wherein, the first and the second end of the pipe are connected with each other,
Figure 612237DEST_PATH_IMAGE006
is a first
Figure 519013DEST_PATH_IMAGE007
The position of the individual starting points is subject to fluctuations,
Figure 408472DEST_PATH_IMAGE008
is as follows
Figure 818725DEST_PATH_IMAGE007
The position coordinates of the individual starting points,
Figure 604278DEST_PATH_IMAGE009
is a first
Figure 263929DEST_PATH_IMAGE010
The coordinates of the pixel points on the test ray that are closest to the starting point,
Figure 924456DEST_PATH_IMAGE011
is as follows
Figure 126898DEST_PATH_IMAGE010
The coordinates of the pixel point on the test ray which is the second closest to the starting point,
Figure 880090DEST_PATH_IMAGE012
is as follows
Figure 230300DEST_PATH_IMAGE007
The number of test rays corresponding to each starting point,
Figure 219816DEST_PATH_IMAGE013
is the thickness of the plate.
6. The intelligent veneer reeling machine fault identification method based on the machine vision is characterized in that the obtaining of the circle center confidence coefficient according to the position fluctuation factor of the first to-be-selected circle center point comprises the following steps:
Figure 870241DEST_PATH_IMAGE014
wherein the content of the first and second substances,
Figure 528755DEST_PATH_IMAGE015
is a first
Figure 694157DEST_PATH_IMAGE007
The confidence of the circle center of each pixel point,
Figure 729109DEST_PATH_IMAGE006
is a first
Figure 499619DEST_PATH_IMAGE007
The position fluctuation factor of each pixel point is determined,
Figure 63456DEST_PATH_IMAGE016
is a natural constant.
CN202211134482.0A 2022-09-19 2022-09-19 Intelligent plate rolling machine fault identification method based on machine vision Pending CN115205299A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211134482.0A CN115205299A (en) 2022-09-19 2022-09-19 Intelligent plate rolling machine fault identification method based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211134482.0A CN115205299A (en) 2022-09-19 2022-09-19 Intelligent plate rolling machine fault identification method based on machine vision

Publications (1)

Publication Number Publication Date
CN115205299A true CN115205299A (en) 2022-10-18

Family

ID=83573693

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211134482.0A Pending CN115205299A (en) 2022-09-19 2022-09-19 Intelligent plate rolling machine fault identification method based on machine vision

Country Status (1)

Country Link
CN (1) CN115205299A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050105827A1 (en) * 2003-09-09 2005-05-19 Fuji Photo Film Co., Ltd. Method and apparatus for detecting positions of center points of circular patterns
CN101699217A (en) * 2009-11-03 2010-04-28 武汉大学 Method used for detecting concentric circle of industrial part
CN109816675A (en) * 2018-12-28 2019-05-28 歌尔股份有限公司 Detection method, detection device and the storage medium of object
CN113689415A (en) * 2021-08-30 2021-11-23 安徽工业大学 Steel pipe wall thickness online detection method based on machine vision

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050105827A1 (en) * 2003-09-09 2005-05-19 Fuji Photo Film Co., Ltd. Method and apparatus for detecting positions of center points of circular patterns
CN101699217A (en) * 2009-11-03 2010-04-28 武汉大学 Method used for detecting concentric circle of industrial part
CN109816675A (en) * 2018-12-28 2019-05-28 歌尔股份有限公司 Detection method, detection device and the storage medium of object
CN113689415A (en) * 2021-08-30 2021-11-23 安徽工业大学 Steel pipe wall thickness online detection method based on machine vision

Similar Documents

Publication Publication Date Title
Louloudis et al. A block-based Hough transform mapping for text line detection in handwritten documents
CN115861291B (en) Chip circuit board production defect detection method based on machine vision
CN116611748B (en) Titanium alloy furniture production quality monitoring system
CN116977358B (en) Visual auxiliary detection method for corrugated paper production quality
CN102004916B (en) Image characteristic extraction system and method
CN112508090A (en) External package defect detection method
CN105654097A (en) Method for detecting quadrangular marker in image
CN111768407B (en) Defect detection algorithm based on quick positioning
CN106815830B (en) Image defect detection method
CN115311267B (en) Method for detecting abnormity of check fabric
CN110852315A (en) Method and device for quickly identifying annular characters
CN115049651B (en) Metal plate stamping abnormity detection method
CN116542972A (en) Wall plate surface defect rapid detection method based on artificial intelligence
CN113112470A (en) Cold rolling process steel bending detection and analysis method based on artificial intelligence
CN111461010B (en) Power equipment identification efficiency optimization method based on template tracking
CN111652846B (en) Semiconductor defect identification method based on characteristic pyramid convolution neural network
CN115170567A (en) Method for detecting defects of waterproof steel plate for ship
CN116309577A (en) Intelligent detection method and system for high-strength conveyor belt materials
CN115937651A (en) Cylindrical roller surface detection method and system based on improved yolov5s network model
CN115661143A (en) Rapid detection system for MiniLED wafer defects
CN107545217B (en) Fingerprint matching method, fingerprint matching device and fingerprint identification chip
CN115205299A (en) Intelligent plate rolling machine fault identification method based on machine vision
CN114581446B (en) Battery core abnormity detection method and system of laminated battery
CN115018792A (en) Deep-drawing part wrinkling detection method based on computer vision technology
CN113689381B (en) Corrugated pipe inner wall flaw detection model and detection method

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