CN113538393A - Bar and wire stock blank bending detection method, device and equipment and readable storage medium - Google Patents
Bar and wire stock blank bending detection method, device and equipment and readable storage medium Download PDFInfo
- Publication number
- CN113538393A CN113538393A CN202110843908.9A CN202110843908A CN113538393A CN 113538393 A CN113538393 A CN 113538393A CN 202110843908 A CN202110843908 A CN 202110843908A CN 113538393 A CN113538393 A CN 113538393A
- Authority
- CN
- China
- Prior art keywords
- image
- blank
- bending
- gray
- area
- 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
- 238000005452 bending Methods 0.000 title claims abstract description 73
- 238000001514 detection method Methods 0.000 title claims abstract description 53
- 239000000463 material Substances 0.000 claims abstract description 40
- 238000000034 method Methods 0.000 claims abstract description 28
- 239000002994 raw material Substances 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims description 45
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012937 correction Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000003708 edge detection Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 18
- 238000004519 manufacturing process Methods 0.000 description 13
- 229910000831 Steel Inorganic materials 0.000 description 8
- 235000020061 kirsch Nutrition 0.000 description 8
- 239000010959 steel Substances 0.000 description 8
- 238000010438 heat treatment Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000011179 visual inspection Methods 0.000 description 3
- 241001292396 Cirrhitidae Species 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 102100040428 Chitobiosyldiphosphodolichol beta-mannosyltransferase Human genes 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 101150086005 gob-1 gene Proteins 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
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
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30116—Casting
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a method, a device and equipment for detecting bending of a raw material blank of a rod and a wire and a readable storage medium, wherein the method for detecting bending of the raw material blank of the rod and the wire comprises the following steps: collecting images of blanks before the blanks are put into a furnace; extracting a portion of the parison displayed in the image; and detecting the bending degree of the extracted material blank part. The bending detection device solves the technical problem that the bending of the blank cannot be effectively detected before the blank enters the furnace.
Description
Technical Field
The invention belongs to the technical field of rod and wire production, and particularly relates to a rod and wire raw material blank bending detection method, device and equipment and a readable storage medium.
Background
At the present stage, a raw material billet of a rod wire is usually a square billet, the side length of the cross section of the raw material billet is usually 150mm to 300mm, the length of the raw material billet is about 10 meters, and in the production process, the raw material billet (wherein the raw material billet is divided into a hot-conveying billet and a cold-conveying billet, the body of the hot-conveying billet is red, and the body of the cold-conveying billet is gray) needs to pass through a section of conveying roller way and then enter a heating furnace for heating. The bending of individual raw material blanks in the conveying process can be caused by various reasons, so that the steel blanks are difficult to smoothly discharge from the furnace after being heated in the furnace, the production rhythm is influenced, and even equipment can be damaged.
In order to avoid the situation, most of bar production lines are manually checked by operators beside the production lines, and when the bending of the raw material blank is found, the manual control equipment is used for removing the material blank. However, this method has the following disadvantages:
firstly, the working strength of an operator is very high and the operator is influenced by noise for a long time;
secondly, the accuracy of visual inspection of an operator is reduced due to long-time field work;
thirdly, the raw material blank is long and the visual inspection precision is limited;
fourthly, automatic closed-loop control cannot be realized, and the production efficiency is reduced;
and fifthly, the method is not in accordance with the expected target of people reduction and efficiency improvement at the present stage.
Aiming at the problem that the bending of the blank can not be effectively detected before the blank enters the furnace in the related technology, an effective solution is not provided at present.
Therefore, the inventor provides a bending detection method, a device, equipment and a readable storage medium for a bar and wire stock blank by virtue of experience and practice of related industries for many years, so as to overcome the defects in the prior art.
Disclosure of Invention
The invention aims to provide a method, a device and equipment for detecting bending of a raw material blank of a rod wire and a wire rod and a readable storage medium.
The purpose of the invention can be realized by adopting the following technical scheme:
the invention provides a bending detection method of a bar and wire stock blank, which comprises the following steps:
collecting images of blanks before the blanks are put into a furnace;
extracting a portion of the parison displayed in the image;
and detecting the bending degree of the extracted material blank part.
In a preferred embodiment of the present invention, between the capturing of the image of the preform before the preform is introduced into the furnace and the extracting of the portion of the preform displayed in the image, the method further comprises:
identifying in the image an area in which the portion of the preform is present;
and carrying out distortion correction on the image.
In a preferred embodiment of the present invention, the marking of the region of the image where the preform portion appears includes: four end points are marked in the image, and a quadrangle formed by sequentially connecting the end points covers the blank part displayed in the image.
In a preferred embodiment of the present invention, the performing the distortion correction on the image includes: and carrying out distortion correction on the image by adopting a calibration plate.
In a preferred embodiment of the present invention, when the slab is a hot-fed slab, the extracting of the portion of the slab displayed in the image includes:
extracting a gray value of a red channel in the image to obtain a first gray image;
performing contrast enhancement processing on the first gray-scale image to obtain a first gray-scale enhanced image;
performing binarization processing on the first gray level enhanced image to obtain a binarized image;
selecting an image area where the preform part is located in the binarized image;
and selecting the coordinates of all pixel points of the blank part on the far-end edge in the image area.
In a preferred embodiment of the present invention, the selecting an image region in which the material base portion is located in the binarized image includes:
traversing all image areas in the binary image, and calculating the area of each image area;
comparing the area of each image area with a preset judgment value respectively;
and if the area of the image area is larger than the preset judgment value, judging that the image area is the image area where the preform part is located.
In a preferred embodiment of the present invention, when the slab is a cold-fed billet, the extracting the portion of the slab displayed in the image includes:
extracting the gray value of a blue channel in the image to obtain a second gray image;
performing edge detection processing on the second gray level image to obtain a second gray level enhanced image;
performing binarization processing on the second gray-scale enhanced image to obtain a contour line image;
and selecting the coordinates of all pixel points of the blank part on the far-end edge in the contour line image.
In a preferred embodiment of the present invention, the detecting of the bending degree of the extracted preform portion includes:
performing linear fitting on the coordinates of all the selected pixel points to obtain a fitting linear line;
respectively calculating the distance between the coordinates of all the pixel points and the fitting straight line so as to obtain the coordinates of the pixel point farthest from the fitting straight line and the maximum distance between the pixel point and the fitting straight line;
comparing the maximum distance between the pixel point and the fitting straight line with a preset threshold value;
and if the maximum distance between the pixel point and the fitting straight line is greater than a preset threshold value, judging that the blank is bent.
The invention provides a bar and wire stock blank bending detection device, which comprises:
the image acquisition unit is used for acquiring images of the blanks before the blanks enter the furnace;
a preform extracting unit for extracting a preform portion displayed in the image;
and the bending detection unit is used for detecting the bending degree of the extracted material blank part.
In a preferred embodiment of the invention, the image acquisition unit is an industrial camera, and the industrial camera is arranged above the side of the conveying roller way to acquire the images of the blanks on the conveying roller way before the blanks are put into the furnace.
In a preferred embodiment of the present invention, the bar wire blank bending detection apparatus further comprises:
a first image preprocessing unit for marking a region in the image where the preform portion appears;
and the second image preprocessing unit is used for carrying out distortion correction on the image.
The invention provides computer equipment which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the bar and wire stock blank bending detection method.
The present invention provides a computer-readable storage medium storing a computer program for executing the above-described bar wire stock blank bending detection method.
From the above, the method, the device, the equipment and the readable storage medium for detecting the bending of the raw material blank of the bar wire material have the characteristics and advantages that: in the rod and wire production process, the blank is before getting into the heating furnace, gather the image before the blank goes into the furnace to draw the blank part that shows in the image, later detect the crookedness of the blank part in the image of drawing again, thereby can reject the blank that the degree of curvature is too big, form the closed-loop control to the crooked detection of blank, not only can effectively improve the rate of accuracy and the production efficiency that detect, greatly reduced operative employee's intensity of labour moreover, provide the technological means for realizing rod and wire unmanned automatic production.
Drawings
The drawings are only for purposes of illustrating and explaining the present invention and are not to be construed as limiting the scope of the present invention.
Wherein:
FIG. 1: is one of the flow charts of the bending detection method of the bar wire stock blank.
FIG. 2: the second flow chart of the bending detection method of the bar wire stock blank is shown in the invention.
FIG. 3: is a third flow chart of the bending detection method of the bar and wire stock blank.
FIG. 4: the method is a fourth flow chart of the bending detection method of the bar and wire stock blank.
FIG. 5: is the fifth flow chart of the bending detection method of the bar and wire stock blank.
FIG. 6: is the sixth flow chart of the bending detection method of the bar and wire stock blank.
FIG. 7: is an arrangement position diagram of an industrial camera in the bending detection method of the bar and wire stock blank.
FIG. 8: is a structural schematic diagram of the international chessboard pattern calibration plate in the bar and wire stock blank bending detection method.
FIG. 9: the invention is a structural schematic diagram of a dot matrix chart calibration plate realized in the rod and wire stock blank bending detection method.
FIG. 10: is one of the structural block diagrams of the bar wire stock blank bending detection device.
FIG. 11: the second structural block diagram of the rod and wire material blank bending detection device is shown in the invention.
FIG. 12: the third structural block diagram of the rod and wire stock blank bending detection device is shown.
FIG. 13: the fourth structural block diagram of the rod and wire stock blank bending detection device is provided.
FIG. 14: the present invention provides a fifth structural block diagram of a bar and wire material blank bending detection device.
FIG. 15: is a network structure schematic diagram of the bar and wire stock blank bending detection device.
FIG. 16: is a data flow diagram of the bar wire stock bending detection device of the invention.
The reference numbers in the invention are:
1. a material blank; 2. An industrial camera;
3. a rollgang; 4. Heating furnace;
5. an image processing server; 6. A PLC controller;
7. a switch; 10. An image acquisition unit;
20. a first image preprocessing unit; 30. A second image preprocessing unit;
40. a preform extraction unit; 401. A first extraction module;
402. a contrast enhancement module; 403. A first binarization processing module;
404. an image selection module; 4041. An area calculation module;
4042. a first comparison module; 4043. A first judgment module;
405. a first coordinate selection module; 406. A second extraction module;
407. an edge detection module; 408. A second binarization processing module;
409. a second coordinate selection module; 50. A camber detection unit;
501. a straight line fitting module; 502. A distance calculation module;
503. a second comparison module; 504. And a second judgment module.
Detailed Description
In order to more clearly understand the technical features, objects, and effects of the present invention, embodiments of the present invention will now be described with reference to the accompanying drawings.
Implementation mode one
As shown in fig. 1 and 2, the present invention provides a bending detection method of a bar and wire material blank, including the steps of:
step S101: collecting images of the blanks 1 before entering the furnace;
specifically, as shown in fig. 7, a rollgang 3 is arranged upstream of a heating furnace 4 on site, an industrial camera 2 is arranged laterally above the rollgang 3, and before the slabs 1 enter the heating furnace 4, images are acquired by the industrial camera 2 (wherein the images contain the rollgang 3 and the slabs 1 on the rollgang 3), so that the image acquisition of the slabs 1 before entering the furnace is completed.
Step S102: marking the area of the blank part in the image;
in an alternative embodiment of the present invention, step S102 requires the creation of ROI (region of interest) regions to filter out unnecessary image regions (i.e., regions of the image that do not contain the blob 1) as much as possible.
Further, in order to facilitate the analysis of the acquired image, it is first necessary to identify a fixed region in the image where the material blank 1 appears, which is called a region of interest (ROI). The specific method is to mark four end points in the collected image, and the coordinates are (x) respectively1，y1)、(x2，y2)、(x3，y3)、(x4，y4) The quadrangle formed by the four end points being connected in sequence is to be able toThe portion of the preform shown in the image is overlaid (i.e., the entire preform in the image is overlaid by the quadrilateral). In the subsequent steps, the image is processed only in the quadrilateral area, so that unnecessary noise information such as other equipment, background and the like in the image can be filtered, and the analysis efficiency of the image is improved.
Step S103: carrying out distortion correction on the image;
specifically, when the industrial camera 2 collects an image, the image acquired by the industrial camera 2 may be distorted (for example, a rectangular object in practice may be distorted into a trapezoid in the image, or a straight line may be distorted into a curve, etc.) due to different characteristics of the lens and shooting angles, and an imaging problem of the industrial camera 2 may have a great influence on a final detection result, so that distortion correction needs to be performed on the collected image.
Further, a calibration plate may be used to correct distortion of the image. As shown in fig. 8 and 9, the calibration plate may be, but not limited to, a checkerboard calibration plate or a solid dot matrix calibration plate. In addition, image processing software such as OpenCV, Halcon and the like can provide the image distortion correction operator, and the image distortion correction processing can be carried out by directly calling the corresponding image distortion correction operator in the implementation process.
Step S104: extracting a portion of the preform displayed in the image;
the extraction of the preform portion, that is, the finding of the edge position of the preform 1 in the image, can be classified into two cases according to the difference of the preform 1: the first medium blank 1 is a hot-delivery steel blank, namely the temperature of the blank 1 is high, so that the body of the blank is red; in the second type, the billet 1 is a cold-fed billet, i.e. the billet 1 itself is at room temperature and its body is gray.
In the first case, when the material billet 1 is a hot-rolled steel billet, as shown in fig. 3, the step S104 includes:
step S1041: extracting the gray value of a red channel in the image to obtain a first gray image Img _ red;
the body of the hot-fed steel billet is red, one color picture (namely, the collected image) comprises three color channels of R (red channel), G (green channel) and B (blue channel), and the gray value of the billet area on the red channel in the image is higher, so that only the gray value of the red channel in the image is selected, and the corresponding area of the red channel is used for generating a first gray image Img _ red.
Step S1042: performing contrast enhancement processing on the first gray level image Img _ red to obtain a first gray level enhanced image Img _ enhanced;
specifically, in the process of performing contrast enhancement processing on the first grayscale image Img _ red, the calculation formula that can be used is Gnew＝GoldX a + N, wherein GoldIs the original gray value of the image, GnewFor the gray-level value after image enhancement, a and N are parameters (self-adjustable), which can be set as a being 3 and N being-400, if Gnew<0, then Gnew0; if G isnew>255, then Gnew255. And obtaining a first gray-scale enhanced image Img _ enhanced after the processing.
Step S1043: performing binarization processing on the first gray level enhanced image Img _ enhanced to obtain a binarized image Img _ twovalue;
specifically, binarization processing is performed on the first gray-scale enhanced image Img _ enhanced by a threshold segmentation algorithm. If G ≦ 125 (which may be adjusted for practical reasons), then G ≦ 0; if G >125, G is 255; where G is the gray value of the image. After the processing, a binary image Img _ twovalaue is obtained. On the binary image Img _ twovalue, a plurality of image regions (regions) may be included, but only one image region corresponds to the preform body, and other image regions are background noise.
Step S1044: selecting an image area where a blank taking part is located in the binary image Img _ twovalue;
further, as shown in fig. 4, step S1044 includes:
step S10441: traversing all image areas in the binary image Img _ twovalaue, and automatically calculating the area S of each image area through a computerO；
Step S10442: each image areaArea S of domainORespectively comparing the two values with a preset judgment value sigma (generally sigma can be automatically adjusted according to the actual condition, and the value can be 300 in the invention);
step S10443: if the area S of the image areaOGreater than a preset decision value sigma (i.e., S)OAnd > sigma), the image area is judged to be the image area where the part of the preform is located (the connected area of the part of the preform in the image is the largest).
Step S1045: selecting the material blank part in the image area, wherein the material blank part is positioned at the far end edge (namely, as shown in figure 7, one end of the two ends of the blank 1, which is far away from the industrial camera 2, is the far end of the blank part, and one end of the blank part, which is close to the industrial camera 2, is the near end of the blank part, and the far end edge of the blank part is clearer than the near end edge when being observed from the image, so that the far end edge is selected for processing)n，Yn)。
In the second case, when the material billet 1 is a cold-fed steel billet, as shown in fig. 5, the step S104 includes:
step S1046: extracting the gray value of a blue channel in the image to obtain a second gray image Img _ blue;
the body of the cold-fed steel billet is gray, the gray value of a blue channel in the image is selected through field test, and a second gray image Img _ blue is produced in the corresponding area of the blue channel, so that the edges of the billet area and other background areas in the image are clearer.
Step S1047: performing edge detection processing on the second gray level image Img _ blue to obtain a second gray level enhanced image Img _ kirsch;
specifically, edge detection is performed on the second gray scale image Img _ blue by using a standard kirsch operator, so that a second gray scale enhanced image Img _ kirsch can be obtained, and the edge of the preform part has a higher gray value on the second gray scale enhanced image Img _ kirsch.
Step S1048: performing binarization processing on the second gray level enhanced image Img _ kirsch to obtain a contour line image Img _ edge;
specifically, binarization processing is performed on the second gray-scale enhanced image Img _ kirsch through a threshold segmentation algorithm. If G ≦ 240 (which may be adjusted for real world conditions), then G ≦ 0; if G >240, G is 255; where G is the gray value of the image. After processing, a contour image Img _ edge is obtained. The outline of the material mat 1 is displayed on the outline image Img _ edge.
Step S1049: selecting coordinates (X) of all pixel points of the material taking blank part on the far end edge in the contour line image Img _ edgen，Yn)。
Step S105: the curvature of the extracted preform portion is detected.
In an alternative embodiment of the present invention, as shown in fig. 6, step S105 includes:
step S1051: coordinates (X) of all pixel points of the selected blank part on the far end edgen，Yn) Performing straight line fitting to obtain a fitting straight line L;
specifically, the coordinates (X) of all the pixel points of the preform portion located on the distal edge can be determined by the least squares methodn，Yn) Performing straight line fitting; the least square method fitting straight line can adopt general operators of image processing libraries such as OpenCV, Halcon and the like, and the method can directly call corresponding operators in the implementation process.
Step S1052: respectively calculating the coordinates (X) of all pixel pointsn，Yn) The distance from the fitting straight line L to obtain the coordinates (x, y) of a pixel point farthest from the fitting straight line L and the maximum distance d between the farthest pixel point and the fitting straight line L;
step S1053: comparing the maximum distance d between the farthest pixel point (x, y) and the fitting straight line L with a preset threshold value delta;
step S1054: and if the maximum distance d between the farthest pixel point (x, y) and the fitting straight line L is larger than a preset threshold value delta, judging that the blank 1 is bent.
Specifically, the maximum distance d is the pixel distance of the maximum bending point of the blank part in the image from the blank part at the far edge, the larger the value of d is, the higher the bending degree of the blank 1 is represented, and if d > δ (δ is a reference value and can be set by a user), the blank 1 is judged to be bent. The selection of the delta value needs to be set according to the actual situation on site, if the maximum bending distance of the blank 1 tolerable on site is D, the delta value can be D/r, and r is the scale of the acquired image and the actual environment.
The method for detecting the bending of the raw material blank of the bar and wire material has the characteristics and advantages that:
according to the method for detecting the bending of the raw material blank of the bar and wire, in the production process of the bar and wire, before the material blank 1 enters the heating furnace 4, an image of the material blank 1 before entering the furnace is collected through the industrial camera 2, the part of the material blank displayed in the image is extracted, and then the bending degree of the part of the material blank in the extracted image is detected, so that the material blank 1 with the overlarge bending degree can be removed, and closed-loop control of bending detection of the material blank is formed.
Second embodiment
As shown in fig. 10, the present invention provides a rod and wire material blank bending detection apparatus including an image pickup unit 10, a first image preprocessing unit 20, a second image preprocessing unit 30, a blank extracting unit 40, and a camber detecting unit 50.
The image acquisition unit 10 is used for acquiring images of the blanks 1 before entering the furnace; the image capturing unit 10 may be, but is not limited to, an industrial camera 2, and the industrial camera 2 is disposed above and on the side of the rollgang 3 to capture an image of the slab 1 positioned on the rollgang 3 by the industrial camera 2 before the slab 1 is charged into the furnace.
A first image preprocessing unit 20 for marking a region where the preform portion appears in the image; in order to facilitate the analysis of the acquired image, it is first necessary to identify in the image a fixed region of the material blank 1, called region of interest (ROI). The specific method is to mark four end points in the collected image, and the coordinates are (x) respectively1，y1)、(x2，y2)、(x3，y3)、(x4，y4) Formed by connecting these four end points in sequenceThe quadrilateral shape is such that it covers the portion of the preform shown in the image (i.e., the entire preform in the image is covered by the quadrilateral shape). In the subsequent steps, the image is processed only in the quadrilateral area, so that unnecessary noise information such as other equipment, background and the like in the image can be filtered, and the analysis efficiency of the image is improved.
A second image preprocessing unit 30 for performing distortion correction on the image;
further, a calibration board may be used to perform distortion correction on the image. The calibration plate can be, but is not limited to, a checkerboard calibration plate or a solid dot matrix calibration plate.
A bank extracting unit 40 for extracting a portion of the bank displayed in the image;
when the slab 1 is a hot-fed slab, as shown in fig. 11, the slab extracting unit 40 includes a first extracting module 401, a contrast enhancing module 402, a first binarization processing module 403, an image selecting module 404, and a first coordinate selecting module 405.
The first extraction module 401 is configured to extract a grayscale value of a red channel in an image to obtain a first grayscale image Img _ red;
the contrast enhancement module 402 is configured to perform contrast enhancement processing on the first grayscale image Img _ red to obtain a first grayscale enhanced image Img _ enhanced;
the first binarization processing module 403 is configured to perform binarization processing on the first grayscale enhanced image Img _ enhanced to obtain a binarization image Img _ twovalaue;
the image selecting module 404 is configured to select an image area where a material blank part is located in the binarized image Img _ twovalue;
further, as shown in fig. 12, the image selecting module 404 includes an area calculating module 4041, a first comparing module 4042, and a first determining module 4043.
The area calculation module 4041 is configured to traverse all image regions in the binarized image Img _ twovalaue, and automatically calculate an area S of each image region by using a computerO；
Wherein, the first comparing module 4042 is used for comparing the area S of each image regionORespectively comparing the two values with a preset judgment value sigma;
wherein, the first determining module 4043 is configured to determine the area S of the image regionOThe judgment more than the preset is more than the fixed value sigma (namely S)OAnd > sigma), the image area is judged to be the image area where the blank part is located.
When the gob 1 is a cold-fed billet, as shown in fig. 13, the gob extracting unit 40 includes a second extracting module 406, an edge detecting module 407, a second binarization processing module 408, and a second coordinate selecting module 409.
The second extracting module 406 is configured to extract a grayscale value of a blue channel in the image to obtain a second grayscale image Img _ blue;
the edge detection module 407 is configured to perform edge detection processing on the second gray scale image Img _ blue to obtain a second gray scale enhanced image Img _ kirsch;
the second binarization processing module 408 is configured to perform binarization processing on the second grayscale enhanced image Img _ kirsch to obtain a contour line image Img _ edge;
wherein, the second coordinate selecting module 409 is configured to select coordinates (X) of all pixel points of the material-taking blank part located on the far-end edge in the contour line image Img _ edgen，Yn)。
And a bending degree detection unit 50 for detecting the bending degree of the extracted preform portion.
Further, as shown in fig. 14, the curvature detecting unit 50 includes a straight line fitting module 501, a distance calculating module 502, a second comparing module 503, and a second judging module 504.
Wherein, the straight line fitting module 501 is used for selecting coordinates (X) of all pixel points of the preform part on the far-end edgen，Yn) Performing straight line fitting to obtain a fitting straight line L;
wherein, the distance calculating module 502 is used for calculating the coordinates (X) of all the pixel points respectivelyn，Yn) The distance from the fitting straight line L to obtain the coordinate of the pixel point farthest from the fitting straight line L(x, y) and the maximum distance d between the farthest pixel point and the fitted straight line L;
the second comparing module 503 is configured to compare a maximum distance d between the farthest pixel point (x, y) and the fitting straight line L with a preset threshold δ;
the second determining module 504 is configured to determine whether the material blank 1 is bent, and if the maximum distance d between the farthest pixel point (x, y) and the fitting straight line L is greater than a preset threshold δ, determine that the material blank 1 is bent.
In an alternative embodiment of the present invention, as shown in fig. 15 and 16, the rod and wire blank bending detection apparatus further includes an image processing server 5, a switch 7, and a PLC controller 6, and the industrial camera 2 and the image processing server 5 are connected to the PLC controller 6 through the switch 7, respectively. After the PLC 6 detects that the material blank 1 passes through the field, the PLC 6 sends a trigger signal to the image processing server 5, the type of the material blank 1 (whether the material blank 1 is a hot-conveying steel blank or a cold-conveying steel blank) is sent to the image processing server 5, the image processing server 5 sends a request signal to the industrial camera 2 to control the industrial camera 2 to collect images, the industrial camera 2 returns collected image information to the image processing server 5, the image processing server 5 detects the bending degree of the material blank 1 through the rod and wire material blank bending detection method, sends a detection result to the PLC 6, and the PLC 6 sends an operation signal so that an operator can reject the material blank 1 with the overlarge bending degree.
The bending detection device for the raw material blank of the bar and wire material has the characteristics and advantages that:
this crooked detection device of excellent wire rod raw material blank, in excellent wire rod production process, whether blank 1 need detect before going into the stove and take place to bend, but lack effectual detection means, can't form closed-loop control, accomplish through artifical visual inspection's mode at present mostly. Aiming at the problem, the invention adopts an image processing device, and the actual curvature of the blank 1 is detected by collecting and processing the image of the blank 1 in the conveying process, thereby effectively improving the detection accuracy and the working efficiency and providing a technical means for realizing unmanned automatic production.
Third embodiment
The invention provides a computer device which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the bar and wire stock blank bending detection method.
In particular, the computer device may be a computer terminal, a server or a similar computing device.
Embodiment IV
The present invention provides a computer-readable storage medium storing a computer program for executing the above-described bar wire stock blank bending detection method.
In particular, computer-readable storage media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable storage medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only an exemplary embodiment of the present invention, and is not intended to limit the scope of the present invention. Any equivalent changes and modifications that can be made by one skilled in the art without departing from the spirit and principles of the invention should fall within the protection scope of the invention.
Claims (13)
1. A bending detection method for a rod and wire stock blank is characterized by comprising the following steps:
collecting images of blanks before the blanks are put into a furnace;
extracting a portion of the parison displayed in the image;
and detecting the bending degree of the extracted material blank part.
2. The method of detecting bending of a log blank according to claim 1, wherein between said capturing an image of the blank before it enters the furnace and said extracting a portion of the blank displayed in the image, further comprising:
identifying in the image an area in which the portion of the preform is present;
and carrying out distortion correction on the image.
3. The rod wire blank bending detection method according to claim 2, wherein the marking of the region where the blank portion appears in the image includes: four end points are marked in the image, and a quadrangle formed by sequentially connecting the end points covers the blank part displayed in the image.
4. The method of detecting bending of a rod wire stock blank according to claim 2, wherein the performing distortion correction on the image includes: and carrying out distortion correction on the image by adopting a calibration plate.
5. The method of detecting bending of a rod wire blank according to claim 1, wherein the extracting of the portion of the blank displayed in the image when the blank is a hot-fed billet comprises:
extracting a gray value of a red channel in the image to obtain a first gray image;
performing contrast enhancement processing on the first gray-scale image to obtain a first gray-scale enhanced image;
performing binarization processing on the first gray level enhanced image to obtain a binarized image;
selecting an image area where the preform part is located in the binarized image;
and selecting the coordinates of all pixel points of the blank part on the far-end edge in the image area.
6. The method for detecting bending of a preform for a rod wire material according to claim 5, wherein said selecting an image region in which the preform portion is located in the binarized image comprises:
traversing all image areas in the binary image, and calculating the area of each image area;
comparing the area of each image area with a preset judgment value respectively;
and if the area of the image area is larger than the preset judgment value, judging that the image area is the image area where the preform part is located.
7. The rod wire blank bending detection method according to claim 1, wherein the extracting of the portion of the blank displayed in the image when the blank is a cold billet comprises:
extracting the gray value of a blue channel in the image to obtain a second gray image;
performing edge detection processing on the second gray level image to obtain a second gray level enhanced image;
performing binarization processing on the second gray-scale enhanced image to obtain a contour line image;
and selecting the coordinates of all pixel points of the blank part on the far-end edge in the contour line image.
8. The bar wire blank bending detection method according to claim 5, 6 or 7, wherein the detecting of the bending degree of the extracted blank portion comprises:
performing linear fitting on the coordinates of all the selected pixel points to obtain a fitting linear line;
respectively calculating the distance between the coordinates of all the pixel points and the fitting straight line so as to obtain the coordinates of the pixel point farthest from the fitting straight line and the maximum distance between the pixel point and the fitting straight line;
comparing the maximum distance between the pixel point and the fitting straight line with a preset threshold value;
and if the maximum distance between the pixel point and the fitting straight line is greater than a preset threshold value, judging that the blank is bent.
9. The utility model provides a crooked detection device of bar wire raw material base which characterized in that includes:
the image acquisition unit is used for acquiring images of the blanks before the blanks enter the furnace;
a preform extracting unit for extracting a preform portion displayed in the image;
and the bending detection unit is used for detecting the bending degree of the extracted material blank part.
10. The bending detection device of a bar wire material blank according to claim 9, further comprising:
a first image preprocessing unit for marking a region in the image where the preform portion appears;
and the second image preprocessing unit is used for carrying out distortion correction on the image.
11. The rod wire blank bending detection apparatus according to claim 9, wherein the image acquisition unit is an industrial camera disposed laterally above a roller conveyor to acquire images of the blanks positioned on the roller conveyor before the blanks are charged into the furnace.
12. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the bar wire stock blank bend detection method of any one of claims 1 to 8.
13. A computer-readable storage medium storing a computer program for executing the bar wire stock blank bending detection method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110843908.9A CN113538393A (en) | 2021-07-26 | 2021-07-26 | Bar and wire stock blank bending detection method, device and equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110843908.9A CN113538393A (en) | 2021-07-26 | 2021-07-26 | Bar and wire stock blank bending detection method, device and equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113538393A true CN113538393A (en) | 2021-10-22 |
Family
ID=78089036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110843908.9A Pending CN113538393A (en) | 2021-07-26 | 2021-07-26 | Bar and wire stock blank bending detection method, device and equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113538393A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114013961A (en) * | 2021-11-26 | 2022-02-08 | 陕西龙门钢铁有限责任公司 | Control method for automatic conveying of steel billets |
| CN115235548A (en) * | 2022-08-08 | 2022-10-25 | 北京京诚瑞达电气工程技术有限公司 | On-line measurement method and system for tolerance of bar |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108332713A (en) * | 2018-01-16 | 2018-07-27 | 安徽慧视金瞳科技有限公司 | A kind of inclined detection method of insulator pin |
| CN110189344A (en) * | 2019-04-24 | 2019-08-30 | 河海大学常州校区 | A kind of line segment extraction method in power knife switch image |
| CN112132135A (en) * | 2020-08-27 | 2020-12-25 | 南京南瑞信息通信科技有限公司 | Power grid transmission line detection method based on image processing and storage medium |
| CN112348815A (en) * | 2021-01-07 | 2021-02-09 | 新东方教育科技集团有限公司 | Image processing method, image processing apparatus, and non-transitory storage medium |
| US20210150257A1 (en) * | 2019-06-21 | 2021-05-20 | Chengdu Boe Optoelectronics Technology Co., Ltd. | Method and apparatus for evaluating image acquisition accuracy, electronic device and storage medium |
-
2021
- 2021-07-26 CN CN202110843908.9A patent/CN113538393A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108332713A (en) * | 2018-01-16 | 2018-07-27 | 安徽慧视金瞳科技有限公司 | A kind of inclined detection method of insulator pin |
| CN110189344A (en) * | 2019-04-24 | 2019-08-30 | 河海大学常州校区 | A kind of line segment extraction method in power knife switch image |
| US20210150257A1 (en) * | 2019-06-21 | 2021-05-20 | Chengdu Boe Optoelectronics Technology Co., Ltd. | Method and apparatus for evaluating image acquisition accuracy, electronic device and storage medium |
| CN112132135A (en) * | 2020-08-27 | 2020-12-25 | 南京南瑞信息通信科技有限公司 | Power grid transmission line detection method based on image processing and storage medium |
| CN112348815A (en) * | 2021-01-07 | 2021-02-09 | 新东方教育科技集团有限公司 | Image processing method, image processing apparatus, and non-transitory storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 丁曙光;张正刘;: "基于机器视觉的柴油机曲轴轴线弯曲检测", 组合机床与自动化加工技术, no. 10 * |
| 杜媛: "基于自适应分割与直线拟合的芯片连接器针脚缺陷检测算法", 《系统仿真技术》, vol. 12, no. 3, pages 212 - 217 * |
| 梁志芳 等: "《计算机在材料加工中的应用》", 31 March 2012, 媒炭工业出版社, pages: 26 - 34 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114013961A (en) * | 2021-11-26 | 2022-02-08 | 陕西龙门钢铁有限责任公司 | Control method for automatic conveying of steel billets |
| CN115235548A (en) * | 2022-08-08 | 2022-10-25 | 北京京诚瑞达电气工程技术有限公司 | On-line measurement method and system for tolerance of bar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110261410A (en) | A kind of detection device and method of glass lens defect | |
| CN112712512A (en) | Hot-rolled strip steel scab defect detection method and system based on artificial intelligence | |
| JP6620477B2 (en) | Method and program for detecting cracks in concrete | |
| CN113538393A (en) | Bar and wire stock blank bending detection method, device and equipment and readable storage medium | |
| JP5175528B2 (en) | Tunnel lining crack inspection system | |
| CN107490582B (en) | Assembly line workpiece detection system | |
| CN108921819B (en) | Cloth inspecting device and method based on machine vision | |
| JP2012202858A (en) | Closure crack detection method of concrete surface | |
| CN112304954A (en) | Part surface defect detection method based on line laser scanning and machine vision | |
| WO2021000948A1 (en) | Counterweight weight detection method and system, and acquisition method and system, and crane | |
| CN113196040A (en) | Surface defect detection method, surface defect detection device, steel product manufacturing method, steel product quality management method, steel product manufacturing facility, surface defect determination model generation method, and surface defect determination model | |
| CN112258444A (en) | Elevator steel wire rope detection method | |
| CN107679479A (en) | A kind of objective full-filling recognition methods based on morphological image process | |
| CN113155839A (en) | Steel plate outer surface defect online detection method based on machine vision | |
| CN113034480A (en) | Blast furnace damage analysis method based on artificial intelligence and image processing | |
| CN115272336A (en) | Metal part defect accurate detection method based on gradient vector | |
| CN117091953A (en) | Automatic measuring method, computer equipment, system and storage medium for sample deformation | |
| CN114359251A (en) | Automatic identification method for concrete surface damage | |
| KR101328266B1 (en) | Apparatus for detecting surface crack of hot slab | |
| KR101562988B1 (en) | Apparatus and method for detecting surface defects of hot billet | |
| CN101131733A (en) | Self-adapting objective locating method | |
| JP3724720B2 (en) | Warpage shape measuring method and apparatus | |
| CN115205317B (en) | Bridge monitoring photoelectric target image light spot center point extraction method | |
| CN116681664A (en) | Detection method and device for operation of stamping equipment | |
| CN112991251B (en) | Method, device and equipment for detecting surface defects |
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 |