CN116449041B - Continuous casting blank sampling system and method - Google Patents
Continuous casting blank sampling system and method Download PDFInfo
- Publication number
- CN116449041B CN116449041B CN202310699036.2A CN202310699036A CN116449041B CN 116449041 B CN116449041 B CN 116449041B CN 202310699036 A CN202310699036 A CN 202310699036A CN 116449041 B CN116449041 B CN 116449041B
- Authority
- CN
- China
- Prior art keywords
- continuous casting
- image
- casting billet
- unit
- grabbing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000009749 continuous casting Methods 0.000 title claims abstract description 196
- 238000005070 sampling Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 62
- 238000012544 monitoring process Methods 0.000 claims abstract description 42
- 238000003384 imaging method Methods 0.000 claims abstract description 39
- 238000005286 illumination Methods 0.000 claims description 14
- 238000012805 post-processing Methods 0.000 claims description 14
- 238000005498 polishing Methods 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000006740 morphological transformation Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000012952 Resampling Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 22
- 230000008569 process Effects 0.000 abstract description 20
- 230000006378 damage Effects 0.000 abstract description 7
- 239000000126 substance Substances 0.000 abstract description 7
- 208000027418 Wounds and injury Diseases 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 208000014674 injury Diseases 0.000 abstract description 4
- 238000007689 inspection Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 4
- 238000005554 pickling Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005266 casting Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000007769 metal material Substances 0.000 description 2
- 238000003801 milling Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
- G01N35/02—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor using a plurality of sample containers moved by a conveyor system past one or more treatment or analysis stations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/02—Devices for withdrawing samples
- G01N1/04—Devices for withdrawing samples in the solid state, e.g. by cutting
-
- 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
- G06T7/70—Determining position or orientation of objects or cameras
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application relates to the technical field of low-power detection technology, in particular to a continuous casting billet sampling system and a continuous casting billet sampling method, comprising the following steps: the device comprises a position monitoring unit, an imaging unit, a grabbing unit and a processing unit; the position monitoring unit is used for monitoring whether the continuous casting billet reaches a sampling position; the imaging unit is used for acquiring a continuous casting billet image when the continuous casting billet is positioned at the sampling position; the grabbing unit is used for grabbing the continuous casting billet positioned at the sampling position to a designated position; the processing unit is used for acquiring the continuous casting billet image fed back by the imaging unit; extracting coordinate information in the continuous casting billet image, generating a grabbing instruction according to the coordinate information, and sending the grabbing instruction to a grabbing unit; the grabbing instruction is used for enabling the grabbing unit to grab the continuous casting billet positioned at the sampling position to a specified position. The system can replace manual operation, can avoid mechanical injury caused by chemical environment and manual operation sampling, and can reduce the time of sampling procedures, shorten the total time consumption of a low-power detection process and improve the efficiency of the detection process through a standard automatic flow.
Description
Technical Field
The application relates to the technical field of low-power detection processes, in particular to a continuous casting billet sampling system and a continuous casting billet sampling method.
Background
Low power detection is a method of examining macroscopic tissues and defects of a metal material and its products by naked eyes or a magnifying glass (20 times or less). The area of the sample for low-power inspection is large, the visual field is wide, the range is wide, the inspection method, the operation technology and the required inspection equipment are simple, and the quality of the material or the product can be reflected more quickly and comprehensively. Thus, the low-power inspection is widely used in factories.
At present, in the low-power detection process, continuous casting billets are manually conveyed to a pickling device to finish milling, pickling and photographing operations, and then the continuous casting billets are periodically transferred to researchers to finish defect judgment.
The whole low-power detection process consumes time, has safety risk, is easy to cause mechanical injury by manual operation, and is damaged to human body by long-term contact chemical experiments.
Disclosure of Invention
In order to solve the problems of time consumption and safety risk caused by manual transportation in the prior low-power detection process, one aspect of the present application provides a continuous casting billet sampling system, which comprises:
the device comprises a position monitoring unit, an imaging unit and a grabbing unit, and a processing unit electrically connected with the position monitoring unit, the imaging unit and the grabbing unit respectively; the position monitoring unit is used for monitoring whether the continuous casting billet reaches a sampling position; the imaging unit is used for acquiring a continuous casting billet image when the continuous casting billet is positioned at the sampling position; the grabbing unit is used for grabbing the continuous casting billet positioned at the sampling position to a designated position;
the processing unit is configured to:
generating a photographing instruction to be sent to an imaging unit in response to an in-place signal fed back by the position monitoring unit;
acquiring a continuous casting billet image fed back by an imaging unit;
extracting coordinate information in the continuous casting billet image, generating a grabbing instruction according to the coordinate information, and sending the grabbing instruction to a grabbing unit; the grabbing instruction is used for enabling the grabbing unit to grab the continuous casting billet positioned at the sampling position to a specified position.
In one possible implementation, the coordinate information includes: the center position of the continuous casting billet, the length of the continuous casting billet, the width of the continuous casting billet, and the angle formed by the edge of the continuous casting billet and the coordinate axis.
In one possible implementation, the processing unit is further configured to:
when extracting coordinate information in a continuous casting billet image, carrying out image preprocessing on the continuous casting billet image, extracting a roi region and establishing a mask image;
separating the foreground and the background of the mask image based on the U2NET network to obtain an image foreground;
and carrying out image post-processing on the image foreground to obtain coordinate information.
In one possible implementation, the processing unit is further configured to:
before performing image post-processing on the image foreground, judging whether the image foreground meets a preset constraint condition, if so, judging that the continuous casting blank is a combined blank, and if not, judging that the continuous casting blank is a non-combined blank;
wherein, the preset constraint condition is: the difference value between the foreground size of the processed image and the foreground size of the processed image accords with a preset difference value range;
when the continuous casting blanks are combined blanks, the combined blanks are separated in the image prospect, and then, each separated continuous casting blank is subjected to independent image post-processing to obtain the coordinate information of each continuous casting blank.
In one possible implementation, the processing unit is further configured to:
when the roi area is extracted and a mask image is established, a preset section is intercepted in the continuous casting billet image to form the roi area;
and establishing a designated shape array based on the roi region, mapping the shape array into an RGB image by utilizing color space transformation, and modifying pixel values of the RGB image to obtain a mask image.
In one possible implementation, the processing unit is further configured to:
performing image post-processing on the image foreground, and converting the image foreground into a binary image when coordinate information is obtained;
performing morphological transformation on the binary image to obtain a simplified image with noise removed;
extracting the outline of the simplified image, calculating the outline area, and screening out the non-target outline;
calculating to obtain a minimum circumscribed rectangle based on the contour area;
and obtaining the coordinate information of the continuous casting blank according to the minimum circumscribed rectangle.
In one possible implementation, the processing unit is further configured to:
before converting the image foreground into a binary image through empirical values, resampling pixels of the image foreground on the image foreground through a difference method, and converting the image size of the image foreground into a preset size.
In one possible implementation, the system further comprises an illumination unit;
the illumination unit is electrically connected with the processing unit, the illumination unit being configured to: and receiving a photographing instruction and polishing the continuous casting blank to amplify the color difference between the continuous casting blank and the sampling position.
In another aspect, the present application provides a continuous casting billet sampling method, and is applied to any one of the continuous casting billet sampling systems, where the method includes the steps of:
when the continuous casting billet reaches the sampling position, polishing and photographing the continuous casting billet to obtain a continuous casting billet image;
processing the continuous casting billet image to obtain coordinate information;
generating a grabbing instruction according to the coordinate information;
and grabbing the continuous casting billet according to the grabbing instruction and sending the continuous casting billet to a designated position.
From the foregoing, it is an aspect of the present application to provide a continuous casting billet sampling system, comprising: the device comprises a position monitoring unit, an imaging unit, a grabbing unit and a processing unit; the position monitoring unit is used for monitoring whether the continuous casting billet reaches a sampling position; the imaging unit is used for acquiring a continuous casting billet image when the continuous casting billet is positioned at the sampling position; the grabbing unit is used for grabbing the continuous casting billet positioned at the sampling position to a designated position; the processing unit is configured to: generating a photographing instruction to be sent to an imaging unit in response to an in-place signal fed back by the position monitoring unit; acquiring a continuous casting billet image fed back by an imaging unit; extracting coordinate information in the continuous casting billet image, generating a grabbing instruction according to the coordinate information, and sending the grabbing instruction to a grabbing unit; the grabbing instruction is used for enabling the grabbing unit to grab the continuous casting billet positioned at the sampling position to a specified position. The application further provides a continuous casting billet sampling method which is applied to the continuous casting billet sampling system, the position monitoring unit, the imaging unit and the vision system are used for guiding the grabbing unit to sample instead of manual operation, so that mechanical damage caused by chemical environment and manual operation sampling can be avoided, the time of sampling procedures can be reduced through a standard automatic flow, the overall time consumption of a low-power detection process is shortened, and the efficiency of the detection process is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the practice of the application and together with the description, serve to explain the principles of the embodiments of the application. It is evident that the drawings in the following description are only some embodiments of the implementation of the present application and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic diagram of a continuous casting billet sampling system according to an exemplary embodiment of the present application;
FIG. 2 is an image of a continuous casting billet according to an exemplary embodiment of the present application;
FIG. 3 is an image of a separated foreground and background shown in an exemplary embodiment of the present application;
FIG. 4 is a schematic diagram of a minimum bounding rectangle shown in an exemplary embodiment of the present application;
FIG. 5 is a schematic diagram of a continuous casting billet sampling system according to another exemplary embodiment of the present application;
fig. 6 is a flowchart illustrating a method of sampling a continuous casting billet according to an exemplary embodiment of the present application.
Description of the reference numerals
1-a position monitoring unit; a 2-imaging unit; 3-a grabbing unit; 4-a processing unit; 5-illumination unit.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the implementations of embodiments of the application.
Low power detection is a method of examining macroscopic tissues and defects of a metal material and its products by naked eyes or a magnifying glass (20 times or less). The area of the sample for low-power inspection is large, the visual field is wide, the range is wide, the inspection method, the operation technology and the required inspection equipment are simple, and the quality of the material or the product can be reflected more quickly and comprehensively. Thus, the low-power inspection is widely used in factories. At present, in the low-power detection process, continuous casting billets are manually conveyed to a pickling device to finish milling, pickling and photographing operations, and then the continuous casting billets are periodically transferred to researchers to finish defect judgment. The whole low-power detection process consumes time, has safety risk, is easy to cause mechanical injury by manual operation, and is damaged to human body by long-term contact chemical experiments.
In order to solve the problems of time consumption and safety risk caused by manual handling in the prior low-power detection process, an embodiment of the present application provides a continuous casting billet sampling system, as shown in fig. 1, fig. 1 is a schematic diagram of a continuous casting billet sampling system according to an exemplary embodiment of the present application, including:
a position monitoring unit 1, an imaging unit 2, a grabbing unit 3, and a processing unit 4 electrically connected with the position monitoring unit 1, the imaging unit 2, and the grabbing unit 3, respectively.
The position monitoring unit 1 is used for monitoring whether the continuous casting billet reaches a sampling position; specifically, in the embodiment of the present application, the position monitoring unit 1 may actually use an industrial personal computer to monitor, and a PLC logic processor is installed on the industrial personal computer to monitor, or whether the continuous casting billet reaches the sampling position is identified by naked eyes, and a signal can be directly input in place on the industrial personal computer by a person to realize the monitoring function of the position monitoring unit.
The imaging unit 2 is used for acquiring a continuous casting billet image when the continuous casting billet is positioned at the sampling position; specifically, referring to fig. 2, fig. 2 is a continuous casting image according to an exemplary embodiment of the present application. In the embodiment of the application, the imaging unit 2 can be a 2D camera, the 2D camera can be used for acquiring an image signal by converting an optical signal into an electrical signal which can be processed by a computer, and in the embodiment of the application, the 2D camera can be used for carrying out two-dimensional set analysis based on edge monitoring, so as to realize the requirements of monitoring, positioning, identification and the like. According to the application, the function of the continuous casting billet image acquired by the imaging unit 2 is realized through the 2D camera, and the acquired casting billet image is a two-dimensional image, so that the position and the contour can be conveniently identified after the processing unit 4 processes, and the requirement of grabbing the continuous casting billet can be more accurately met.
The grabbing unit 3 is used for grabbing the continuous casting billet positioned at the sampling position to a specified position; the grabbing unit 3 is a mechanical arm or any mechanical device with grabbing function such as a robot, and the application is not particularly limited, and the grabbing unit 3 replaces manual operation to carry the continuous casting billet in the application, so that personnel can be prevented from being in a chemical environment for a long time, and the safety risk is reduced.
The processing unit 4 is configured to:
generating a photographing instruction to be sent to the imaging unit 2 in response to an in-place signal fed back by the position monitoring unit 1; acquiring a continuous casting billet image fed back by the imaging unit 2; extracting coordinate information in the continuous casting billet image, generating a grabbing instruction according to the coordinate information, and sending the grabbing instruction to the grabbing unit 3; the gripping instruction is for causing the gripping unit 3 to grip the continuous casting slab located at the sampling position to a specified position.
In the embodiment of the application, the processing unit 4 is an industrial personal computer provided with a U2NET network, and the U2NET network is provided for Salient Object Detetion (SOD), namely a significance target detection task. The salient object detection task is very similar to the semantic segmentation task, but the salient object detection task is a classification task, and the most attractive object or region in the picture is segmented, so that the salient object detection task has only two types of foreground and background.
According to the embodiment of the application, the processing of the continuous casting billet image is performed based on the U2NET, so that a clear standard image contour can be obtained, the obtained coordinate information is accurate, and the capturing unit 3 can capture according to the coordinate information more accurately and rapidly. It should be understood that, in the present application, the processing unit 4 may be disposed on the same industrial personal computer together with the position monitoring unit 1, or the processing unit 4 may be a separate processor with software or a system having the same processing function.
After the processing unit 4 processes the continuous casting billet image to obtain the coordinate information, a grabbing instruction is generated according to the coordinate information, and when the situation can be understood, the grabbing instruction contains the whole content of the coordinate information and the instruction information for controlling the action of the grabbing unit 3. If the grabbing unit 3 is controlled to be close to the sampling position, after grabbing the continuous casting billet, the continuous casting billet is far away from the sampling position and moved to the designated position.
In view of the foregoing, the present application provides a continuous casting billet sampling system, comprising: the device comprises a position monitoring unit, an imaging unit, a grabbing unit and a processing unit; the position monitoring unit is used for monitoring whether the continuous casting billet reaches a sampling position; the imaging unit is used for acquiring a continuous casting billet image when the continuous casting billet is positioned at the sampling position; the grabbing unit is used for grabbing the continuous casting billet positioned at the sampling position to a designated position; the processing unit is configured to: generating a photographing instruction to be sent to an imaging unit in response to an in-place signal fed back by the position monitoring unit; acquiring a continuous casting billet image fed back by an imaging unit; extracting coordinate information in the continuous casting billet image, generating a grabbing instruction according to the coordinate information, and sending the grabbing instruction to a grabbing unit; the grabbing instruction is used for enabling the grabbing unit to grab the continuous casting billet positioned at the sampling position to a specified position. According to the application, the position monitoring unit, the imaging unit and the vision system are used for guiding the grabbing unit to sample instead of manual operation, so that mechanical injury caused by chemical environment and manual operation sampling can be avoided, the time of a sampling procedure can be reduced by a standard automatic flow, the total time consumption of a low-power detection process is shortened, and the efficiency of the detection process is improved.
In some embodiments of the application, the coordinate information includes: the center position of the continuous casting billet, the length of the continuous casting billet, the width of the continuous casting billet, and the angle formed by the edge of the continuous casting billet and the coordinate axis.
Specifically, the continuous casting billet is placed relative to the sampling position, and besides the length and the width of the continuous casting billet, the continuous casting billet also has angular position information. Therefore, when the continuous casting billet image is processed, the image should be applied to a coordinate axis defined by a system in the processing unit 4, if the continuous casting billet is placed in a skew state, angle information formed by the edge of the continuous casting billet and the coordinate axis can be obtained, taking the grabbing unit 3 as an example of a mechanical arm, and when the mechanical arm grabs, the grabbing hand can be rotated according to the angle information formed by the edge of the casting billet and the coordinate axis, so that the grabbing hand is always gradually clamped from the outer shaft of the continuous casting billet, and the situation that the mechanical arm contacts the continuous casting billet prematurely in the grabbing process to damage the continuous casting billet is avoided.
In some embodiments of the application, the processing unit is further configured to:
when extracting coordinate information in the continuous casting billet image, carrying out image preprocessing on the continuous casting billet image, extracting a roi region and establishing a mask image; separating the foreground and the background of the mask image based on a U2NET network to obtain an image foreground; and carrying out image post-processing on the image foreground to obtain the coordinate information.
Referring to fig. 3, fig. 3 is an image of separated foreground and background shown in an exemplary embodiment of the present application; in the embodiment of the application, the shielding effect can be obtained by extracting the roi region and establishing the mask image, and certain regions on the continuous casting billet image are shielded, so that the continuous casting billet image does not participate in the processing or the calculation of processing parameters, the subsequent processing speed is increased, and the processing pressure of the processing unit 4 is reduced. The U2NET network is a two-layer nested U-shaped structure designed for SOD, and does not use a pre-trained backbone in image classification. It can train from scratch to achieve competitive performance. And the new architecture of the U2NET network allows the network to go deep, so that the memory and the calculation cost are not obviously increased on the basis of obtaining high resolution, and the continuous casting billet image extracting prospect based on the U2NET network is clearer and more accurate.
In some embodiments of the application, the processing unit is further configured to:
before carrying out image post-processing on the image foreground, judging whether the image foreground accords with a preset constraint condition, if so, judging that the continuous casting blank is a combined blank, and if not, judging that the continuous casting blank is a non-combined blank.
When the continuous casting blanks are parallel blanks, separating the parallel blanks in the image prospect, and then performing independent image post-processing on each separated continuous casting blank to obtain the coordinate information of each continuous casting blank.
The continuous casting slab of the present application may have more than one slab when placed in the sampling position, and when there are two or more slabs in juxtaposition, this condition is defined as a parallel slab. In the application, whether the continuous casting blank at the sampling position is in the condition of blank merging is judged by applying the preset constraint condition, and the preset constraint condition can be set arbitrarily, for example, the image size of the continuous casting blank after treatment is compared with the image size of the continuous casting blank before treatment, and the continuous casting blank can be judged to be in the condition of blank merging when the preset difference value is reached.
When the continuous casting blanks are combined, in order to ensure that the grabbing unit 3 can grab the single continuous casting blanks in sequence, the combined blanks should be separated and calculated to obtain the coordinate information of each single blank, otherwise, the situation that the continuous casting blanks fall down due to the fact that the grabbing unit 3 grabs two or more continuous casting blanks simultaneously can occur.
Specifically, the above-described operations for separating the blanks in some embodiments of the present application may be implemented by the following codes (the codes are only exemplary):
“def treatment （predictImg,srcimg,mac） :
srcimg original map mac camera number for #predictimg input image (u 2net function result map)
predictImg=predictImg.astype（np.uint8）
predict= cv2.cvtColor （predictImg, cv2.COLOR_GRAY2BGR）
dst_Image=cv2.copyTo（srcimg,predict）
point_xx=0
point_yy=0
xoix=0#1625
xoiy=0#761
Coarse separation by # open operation
kernel = cv2.getStructuringElement （cv2.MORPH_RECT, （109, 19））
thresh_open = cv2.morphologyEx（predictImg, cv2.MORPH_OPEN, kernel）
flag=0
h=0
M=0
angle=0
point_x=0 point_y=0
Finding outline, preliminary screening by constraint of area, length and width "
In some embodiments of the application, the processing unit is further configured to:
when a roi area is extracted and a mask image is established, a preset interval is intercepted from the continuous casting billet image to form the roi area; and establishing a designated shape array based on the roi region, mapping the shape array into an RGB image by utilizing color space transformation, and modifying pixel values of the RGB image to obtain the mask image.
In the embodiment of the present application, roi (region of interest) in the roi refers to the region of interest. In machine vision and image processing, a region to be processed is outlined from a processed image in a box, circle, ellipse, irregular polygon and the like, and is called a region of interest. In the application, the processing unit 4 can adopt machine vision software such as opencv, matlab and the like to obtain the roi region through various operators and functions, and perform the next processing of the image, namely obtaining the mask image.
mask refers to an image mask, i.e. an area or process for controlling image processing by masking the image to be processed (fully or partially) with a selected image, graphic or object. The particular image or object used for overlay is referred to as a mask or template. In optical image processing, the mask may be a film, a filter, or the like. In digital image processing, the mask is a two-dimensional matrix array, and a multi-value image is sometimes used.
In some embodiments of the application, the processing unit is further configured to:
performing image post-processing on the image foreground, and converting the image foreground into a binary image when the coordinate information is obtained; the binary image is obtained by binarizing the image foreground, and the binarization refers to converting the RGB image into the binary image through an empirical value, for example, the pixel value larger than the threshold value is changed to 255, and the pixel value smaller than the threshold value is changed to 0.
Performing morphological transformation on the binary image to obtain a simplified image with noise removed, wherein the principle of morphological transformation is as follows: separating pixels of a target area through sliding convolution operation, wherein the sliding convolution operation comprises corrosion operation and expansion operation, and the corrosion operation is to utilize a convolution kernel to slide and traverse an image so as to obtain a local minimum value; the expansion operation is to adopt convolution operation to obtain local maximum value.
Extracting the outline of the simplified image, calculating the area of the outline, and screening out non-target outlines; calculating to obtain a minimum circumscribed rectangle based on the contour area; and obtaining the coordinate information of the continuous casting billet according to the minimum circumscribed rectangle.
Specifically, the operations of the above-described image post-processing in some embodiments of the present application may be implemented by the following codes (the codes are only exemplary):
“contours, hierarchy = cv2.findContours（thresh_open, cv2.RETR_TREE, cv2.CHAIN_APPRO
for c in contours:
con_area = cv2.contourArea （c）
#print（"con_areal:",con_area）
if （con_area>50000）:
rect = cv2.minAreaRect （c）
if （rect[1][0]>rect[1][l]）:
w=rect[1][1]
h=rect[1][0]
else:
h=rect[1][1]
w=rect[1][0]
#print（"w:",w）
if （w<500）:
box = cv2.boxPoints（rect）
box =np.int0（box）
print（"hl,wl:",h,w,rect[0],rect[2]） point_x=rect [0] [0]
point_y=rect[0][1]
angle=rect [2]
cv2.drawContours（srcimg, c, 0, （255, 255, 0）, 3）
cv2.drawContours（srcimg, [box], 0, （0, 0, 255）, 3）
cv2.drawContours （predict, c, 0, （255, 255, 0）, 3）
the c 2.Drawcontours (prediction, [ box ], 0, (0, 0, 255), 3) vs2=np. Hstack (srcimg, prediction) # horizontal stack
cv2.imwrite（"vsl.jpg",vs2）
else:
flag=l
break
# complex screening, including sobel filtering, open operation, binarization and area screening
if（flag==l）:
img_gray2 = cv2.cvtColor （dst_Image, cv2.COLOR_BGR2GRAY）
x = cv2.Sobel（img_gray2, cv2.CV_16S, 1, 0）
Y = cv2.Sobel（img_gray2, cv2.CV_16S, 0, 1）
# transform data parallel synthesis
Scale_absx=cv2. ConvertScaleabs (x) # format conversion function
Scale_absY = cv2.convertScaleAbs （y）
result=cv2.addweighted (scale_absx, 0.5, scale_absy,0.5, 0) # image blending
#canny = cv2.Canny（img_gray2, 50, 150）
mean2 = cv2.mean （result） [0]
print（"mean2:",mean2）
ret, thresh = cv2.threshold（result, mean2, 255, cv2.THRESH_BINARY）
kernel = cv2.getStructuringElement （cv2.MORPH_RECT, （109, 19））
thresh_open = cv2.morphologyEx（thresh, cv2.MORPH_OPEN, kernel）
contours, hierarchy = cv2.findContours（result, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE）
for c in contours:
con_area = cv2.contourArea （c）
#print（con_area）
if （con_area>50000）:
rect = cv2.minAreaRect（c）
if （rect[1][0]>rect[1][1]）:
w=rect[1] [1]
h=rect[1][0]
else:
h=rect[1][1]
w=rect[1][0]
box = cv2.boxPoints（rect）
#print（box）
#print（type（box））
box =np.int0（box）
print ("h, w:", h, w, rect [0], rect [2 ])# outputs the result length, width
Point_xx=rect [0] [0] # outputs the result center point x
Point_yy=rect [0] [1] # outputs the result center point y
Angle = rect [2] # output result angle
cv2.circle （srcimg, （int （point_xx）,int （point_yy））,25, （0,0,255）,-1）
cv2.drawContours （srcimg, c, 0, （255, 255, 0）, 3）
cv2.drawContours（srcimg, [box], 0,（0, 0, 255）,3）
cv2.drawContours（predict, c, 0, （255, 255, 0）, 3）
cv2.drawContours （predict, [box], 0, （0, 0, 255）, 3）
#cv2.namedWindow（"img2",0）
#cv2.namedWindow（"img3",0）
#cv2.imshow（"img2",img2）
#cv2.imshow（"img3",img3）”
Referring to fig. 4, fig. 4 is a schematic diagram of a minimum bounding rectangle shown in an exemplary embodiment of the present application; the outline of the simplified image is detected in an image connected domain, and edges with connected properties are found in the comparison of target pixels and neighbor pixels thereof by traversing image pixels. The minimum circumscribed rectangle is obtained by traversing one of the contour point sets in the image, respectively finding the maximum value and the minimum value coordinates of x and y in the coordinate axes to determine the initial circumscribed rectangle, obtaining the rectangular area, and rotating the point set through a formula, wherein the rotating center is the rectangular center; after rotation, new coordinates of the maximum value and the minimum value of the x and the y are obtained, the area is solved, and when the minimum area is found, the connection of the coordinates of the maximum value and the minimum value of the x and the y is the minimum circumscribed rectangle.
In some embodiments of the application, the processing unit is further configured to:
and resampling pixels of the image foreground by a difference method on the image foreground before the image foreground is converted into a binary image through an empirical value, and converting the image size of the image foreground into a preset size.
The image size transformation enables continuous casting billet images which are continuously acquired to be uniform standard, the same image processing mode is convenient to carry out, finally acquired coordinate information also has uniform standard, a uniform coordinate axis can be adapted, and the grabbing of the grabbing unit 3 is more efficient.
In some embodiments of the application, the system further comprises an illumination unit 5; referring to fig. 5, fig. 5 is a schematic diagram of a continuous casting billet sampling system according to another exemplary embodiment of the present application. The illumination unit 5 is electrically connected with the processing unit 4, the illumination unit 5 being configured to: and receiving a photographing instruction and polishing the continuous casting blank to amplify the color difference between the continuous casting blank and the sampling position.
The main technology for realizing sampling in the application is image acquisition and image processing, and all information is derived from continuous casting billet images, so that the continuous casting billet images are stably and continuously acquired. The corresponding illumination unit can be selected according to the characteristics of the continuous casting blank and the field environment, and a proper polishing mode is selected through a polishing experiment, so that a good continuous casting blank image is obtained. The contrast of the continuous casting billet image is obvious, the boundary between the target and the background is clear, and the illumination unit 5 can fade the sampling background, so that the sampling background does not interfere with image processing. The method is beneficial to the effect of image processing, overcomes the interference of ambient light and ensures the image stability.
Another aspect of the embodiments of the present application provides a continuous casting billet sampling method, where the method is applied to any one of the continuous casting billet sampling systems described above, and referring to fig. 6, fig. 6 is a flowchart of a continuous casting billet sampling method according to an exemplary embodiment of the present application, and the method includes the steps of:
s100: and when the continuous casting billet reaches a sampling position, polishing and photographing the continuous casting billet to obtain the continuous casting billet image.
When the continuous casting billet reaches the sampling position, the position monitoring unit 1 acquires the position information and sends the position information to the imaging unit 2 and the illumination unit 5, at the moment, the illumination unit 5 shines the continuous casting billet, the imaging unit 2 shoots the continuous casting billet to obtain a continuous casting billet image, and the continuous casting billet image is sent to the processing unit 4.
S200: and processing the continuous casting billet image to obtain coordinate information. The processing unit 4 may process the continuous casting billet image through opencv and U2NET to obtain coordinate information, and in some embodiments of the present application, the method further includes determining whether the continuous casting billet image is a continuous casting billet, and when the continuous casting billet is determined to be a continuous casting billet, the single continuous casting billet should be separated and then separately calculated to obtain the coordinate information.
S300: and generating a grabbing instruction according to the coordinate information.
The processing unit 4 may generate the coordinate information as a grasping instruction, or may generate the coordinate information as a grasping instruction by the PLC logic processor when the processing unit 4 and the position monitoring unit 1 are provided together on the same industrial personal computer on which the PLC logic processor is mounted.
S400: and grabbing the continuous casting blank according to the grabbing instruction and sending the continuous casting blank to a designated position.
After the continuous casting billet is sampled, the imaging unit 2, the grabbing unit 3 and the processing unit 4 are all closed until a next trigger is used for obtaining an in-place signal, namely, the sampling operation of the next round is performed.
From the foregoing, it is an aspect of the present application to provide a continuous casting billet sampling system, comprising: the device comprises a position monitoring unit, an imaging unit, a grabbing unit and a processing unit; the position monitoring unit is used for monitoring whether the continuous casting billet reaches a sampling position; the imaging unit is used for acquiring a continuous casting billet image when the continuous casting billet is positioned at the sampling position; the grabbing unit is used for grabbing the continuous casting billet positioned at the sampling position to a designated position; the processing unit is configured to: generating a photographing instruction to be sent to an imaging unit in response to an in-place signal fed back by the position monitoring unit; acquiring a continuous casting billet image fed back by an imaging unit; extracting coordinate information in the continuous casting billet image, generating a grabbing instruction according to the coordinate information, and sending the grabbing instruction to a grabbing unit; the grabbing instruction is used for enabling the grabbing unit to grab the continuous casting billet positioned at the sampling position to a specified position. The application further provides a continuous casting billet sampling method which is applied to the continuous casting billet sampling system, the position monitoring unit, the imaging unit and the vision system are used for guiding the grabbing unit to sample instead of manual operation, so that mechanical damage caused by chemical environment and manual operation sampling can be avoided, the time of sampling procedures can be reduced through a standard automatic flow, the overall time consumption of a low-power detection process is shortened, and the efficiency of the detection process is improved.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (8)
1. A continuous casting billet sampling system, the system comprising:
the device comprises a position monitoring unit, an imaging unit and a grabbing unit, and a processing unit electrically connected with the position monitoring unit, the imaging unit and the grabbing unit respectively; the position monitoring unit is used for monitoring whether the continuous casting billet reaches a sampling position; the imaging unit is used for acquiring a continuous casting billet image when the continuous casting billet is positioned at the sampling position; the grabbing unit is used for grabbing the continuous casting billet positioned at the sampling position to a specified position;
the processing unit is configured to:
generating a photographing instruction to be sent to the imaging unit in response to an in-place signal fed back by the position monitoring unit;
acquiring a continuous casting billet image fed back by the imaging unit;
performing image preprocessing on the continuous casting billet image, extracting a roi region and establishing a mask image;
separating the foreground and the background of the mask image based on a U2NET network to obtain an image foreground;
performing image post-processing on the image foreground to obtain coordinate information;
generating a grabbing instruction according to the coordinate information and sending the grabbing instruction to the grabbing unit; the grabbing instruction is used for enabling the grabbing unit to grab the continuous casting billet positioned at the sampling position to a specified position.
2. The continuous casting billet sampling system according to claim 1, wherein the coordinate information comprises: the center position of the continuous casting billet, the length of the continuous casting billet, the width of the continuous casting billet, and the angle formed by the edge of the continuous casting billet and the coordinate axis.
3. The continuous casting billet sampling system of claim 1, wherein the processing unit is further configured to:
before carrying out image post-processing on the image foreground, judging whether the image foreground accords with a preset constraint condition, if so, judging that the continuous casting blank is a combined blank, and if not, judging that the continuous casting blank is a non-combined blank;
wherein, the preset constraint condition is: the difference value between the processed image foreground size and the processed image foreground size accords with a preset difference value range;
when the continuous casting blanks are parallel blanks, separating the parallel blanks in the image prospect, and then performing independent image post-processing on each separated continuous casting blank to obtain the coordinate information of each continuous casting blank.
4. The continuous casting billet sampling system of claim 1, wherein the processing unit is further configured to:
when a roi area is extracted and a mask image is established, a preset interval is intercepted from the continuous casting billet image to form the roi area;
and establishing a designated shape array based on the roi region, mapping the shape array into an RGB image by utilizing color space transformation, and modifying pixel values of the RGB image to obtain the mask image.
5. The strand sampling system of any one of claims 1 to 4, wherein the processing unit is further configured to:
performing image post-processing on the image foreground, and converting the image foreground into a binary image when the coordinate information is obtained;
performing morphological transformation on the binary image to obtain a simplified image with noise removed;
extracting the outline of the simplified image, calculating the area of the outline, and screening out non-target outlines;
calculating to obtain a minimum circumscribed rectangle based on the contour area;
and obtaining the coordinate information of the continuous casting billet according to the minimum circumscribed rectangle.
6. The continuous casting billet sampling system of claim 5, wherein the processing unit is further configured to:
and resampling pixels of the image foreground by a difference method on the image foreground before the image foreground is converted into a binary image through an empirical value, and converting the image size of the image foreground into a preset size.
7. The continuous casting billet sampling system according to claim 1, further comprising an illumination unit;
the illumination unit is electrically connected with the processing unit, the illumination unit being configured to: and receiving a photographing instruction and polishing the continuous casting blank to amplify the color difference between the continuous casting blank and the sampling position.
8. A method for sampling a continuous casting billet, characterized in that the method is applied to the continuous casting billet sampling system according to any one of claims 1 to 7, the method steps comprising:
when the continuous casting billet reaches a sampling position, polishing and photographing the continuous casting billet to obtain a continuous casting billet image;
performing image preprocessing on the continuous casting billet image, extracting a roi region and establishing a mask image;
separating the foreground and the background of the mask image based on a U2NET network to obtain an image foreground;
performing image post-processing on the image foreground to obtain coordinate information;
generating a grabbing instruction according to the coordinate information;
and grabbing the continuous casting blank according to the grabbing instruction and sending the continuous casting blank to a designated position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310699036.2A CN116449041B (en) | 2023-06-14 | 2023-06-14 | Continuous casting blank sampling system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310699036.2A CN116449041B (en) | 2023-06-14 | 2023-06-14 | Continuous casting blank sampling system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116449041A CN116449041A (en) | 2023-07-18 |
| CN116449041B true CN116449041B (en) | 2023-09-05 |
Family
ID=87125943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310699036.2A Active CN116449041B (en) | 2023-06-14 | 2023-06-14 | Continuous casting blank sampling system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116449041B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0224542A (en) * | 1988-07-13 | 1990-01-26 | Nippon Steel Corp | Quality evaluating apparatus for cross section of casting piece |
| CN103543161A (en) * | 2013-10-16 | 2014-01-29 | 湖南镭目科技有限公司 | On-line detection method of continuous casting billet surface quality |
| CN106780483A (en) * | 2017-01-09 | 2017-05-31 | 河北科技大学 | Many continuous casting billet end face visual identifying systems and centre coordinate acquiring method |
| CN111844019A (en) * | 2020-06-10 | 2020-10-30 | 安徽鸿程光电有限公司 | Method and device for determining grabbing position of machine, electronic device and storage medium |
| CN113119108A (en) * | 2021-03-15 | 2021-07-16 | 广州大学 | Grabbing method, system and device of two-finger mechanical arm and storage medium |
| CN113963051A (en) * | 2021-09-15 | 2022-01-21 | 国网四川省电力公司 | Target diameter automatic measurement method and system based on visual information and feature extraction |
| CN219115934U (en) * | 2022-11-30 | 2023-06-02 | 福建国芯科瑞智能科技有限公司 | Intelligent device of continuous casting blank label |
| CN116237944A (en) * | 2023-02-27 | 2023-06-09 | 西门子工业自动化产品(成都)有限公司 | Object grabbing method, device, system, electronic equipment and storage medium |
-
2023
- 2023-06-14 CN CN202310699036.2A patent/CN116449041B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0224542A (en) * | 1988-07-13 | 1990-01-26 | Nippon Steel Corp | Quality evaluating apparatus for cross section of casting piece |
| CN103543161A (en) * | 2013-10-16 | 2014-01-29 | 湖南镭目科技有限公司 | On-line detection method of continuous casting billet surface quality |
| CN106780483A (en) * | 2017-01-09 | 2017-05-31 | 河北科技大学 | Many continuous casting billet end face visual identifying systems and centre coordinate acquiring method |
| CN111844019A (en) * | 2020-06-10 | 2020-10-30 | 安徽鸿程光电有限公司 | Method and device for determining grabbing position of machine, electronic device and storage medium |
| CN113119108A (en) * | 2021-03-15 | 2021-07-16 | 广州大学 | Grabbing method, system and device of two-finger mechanical arm and storage medium |
| CN113963051A (en) * | 2021-09-15 | 2022-01-21 | 国网四川省电力公司 | Target diameter automatic measurement method and system based on visual information and feature extraction |
| CN219115934U (en) * | 2022-11-30 | 2023-06-02 | 福建国芯科瑞智能科技有限公司 | Intelligent device of continuous casting blank label |
| CN116237944A (en) * | 2023-02-27 | 2023-06-09 | 西门子工业自动化产品(成都)有限公司 | Object grabbing method, device, system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116449041A (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102257734B1 (en) | Surface defect inspection method and surface defect inspection device | |
| Neogi et al. | Defect detection of steel surfaces with global adaptive percentile thresholding of gradient image | |
| EP3176751A1 (en) | Information processing device, information processing method, computer-readable recording medium, and inspection system | |
| CN112614062B (en) | Colony counting method, colony counting device and computer storage medium | |
| CN110766689A (en) | Method and device for detecting article image defects based on convolutional neural network | |
| Song et al. | Surface defect detection method using saliency linear scanning morphology for silicon steel strip under oil pollution interference | |
| AU2020272936B2 (en) | Methods and systems for crack detection using a fully convolutional network | |
| CN108764345A (en) | A kind of underwater Dam Crack detection method based on part and global clustering | |
| CN109584215A (en) | A kind of online vision detection system of circuit board | |
| CN112270658A (en) | Elevator steel wire rope detection method based on machine vision | |
| CN109166092A (en) | A kind of image defect detection method and system | |
| CN112308843A (en) | Camera overexposure abnormity adjusting method and system for photovoltaic cell panel image acquisition | |
| CN116363122A (en) | Steel weld crack detection method and system based on artificial intelligence | |
| CN116449041B (en) | Continuous casting blank sampling system and method | |
| Dong et al. | A rapid detection method for the surface defects of mosaic ceramic tiles | |
| CN114331961A (en) | Method for defect detection of an object | |
| JP2019200775A (en) | Surface defect inspection device and surface defect inspection method | |
| CN109001213A (en) | A kind of reel-to-reel ultrathin flexible IC exterior substrate detection method | |
| CN108389191A (en) | The detection method in target shadow region in a kind of SAR image | |
| CN117036259A (en) | Metal plate surface defect detection method based on deep learning | |
| CN112184619A (en) | Metal part surface defect detection method based on deep learning | |
| KR101562988B1 (en) | Apparatus and method for detecting surface defects of hot billet | |
| CN106530292A (en) | Strip steel surface defect image rapid identification method based on line scanning camera | |
| CN115661110A (en) | Method for identifying and positioning transparent workpiece | |
| CN114638835A (en) | Sleeper foreign matter detection method based on depth camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |