CN112697803A - Plate strip steel surface defect detection method and device based on machine vision - Google Patents
Plate strip steel surface defect detection method and device based on machine vision Download PDFInfo
- Publication number
- CN112697803A CN112697803A CN202011489920.6A CN202011489920A CN112697803A CN 112697803 A CN112697803 A CN 112697803A CN 202011489920 A CN202011489920 A CN 202011489920A CN 112697803 A CN112697803 A CN 112697803A
- Authority
- CN
- China
- Prior art keywords
- strip steel
- image
- gray
- plate strip
- detected
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 119
- 239000010959 steel Substances 0.000 title claims abstract description 119
- 230000007547 defect Effects 0.000 title claims abstract description 107
- 238000001514 detection method Methods 0.000 title claims description 20
- 238000005554 pickling Methods 0.000 claims abstract description 27
- 238000005096 rolling process Methods 0.000 claims abstract description 26
- 238000004519 manufacturing process Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 13
- 239000013074 reference sample Substances 0.000 claims abstract description 13
- 230000002950 deficient Effects 0.000 claims description 18
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 14
- 239000011229 interlayer Substances 0.000 claims description 9
- 238000003825 pressing Methods 0.000 claims description 8
- 229910052742 iron Inorganic materials 0.000 claims description 7
- 230000001788 irregular Effects 0.000 claims description 6
- 239000002253 acid Substances 0.000 claims description 5
- 238000005520 cutting process Methods 0.000 claims description 5
- 238000005406 washing Methods 0.000 claims description 4
- 239000000839 emulsion Substances 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000006748 scratching Methods 0.000 claims description 3
- 230000002393 scratching effect Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 8
- 101100117236 Drosophila melanogaster speck gene Proteins 0.000 description 5
- 239000004816 latex Substances 0.000 description 5
- 229920000126 latex Polymers 0.000 description 5
- UQSXHKLRYXJYBZ-UHFFFAOYSA-N Iron oxide Chemical compound [Fe]=O UQSXHKLRYXJYBZ-UHFFFAOYSA-N 0.000 description 4
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 2
- 229910052782 aluminium Inorganic materials 0.000 description 2
- 238000005336 cracking Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000007373 indentation Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 239000010410 layer Substances 0.000 description 2
- 238000009966 trimming Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a method and a device for detecting surface defects of plate strip steel based on machine vision, the method firstly establishes a reference sample database according to the gray characteristic quantity of plate strip steel images without defects and with different defect types, then obtaining an original image of the plate strip steel on the pickling cold continuous rolling production line when the plate strip steel runs to a shooting area as an image to be detected, extracting gray characteristic quantity after gray processing and image enhancement processing are sequentially carried out on the image to be detected, comparing the gray characteristic quantity corresponding to each image to be detected with the gray characteristic quantity in a reference sample database, determining whether the plate strip steel part corresponding to the image to be detected has defects or not, if a defect determines a specific type of defect, and its location, the apparatus has a guide rail mounted therein, the camera and the light source can be moved left and right, and the defects at different stations can be detected simultaneously by the camera and the light source which are respectively arranged at the rolling section and the pickling section of the production line.
Description
Technical Field
The invention relates to the technical field of intelligent detection, in particular to a method and a device for detecting surface defects of plate strip steel based on machine vision.
Background
With the rapid development of economy in China, people have more and more demands on plate and strip steel, the production of the plate and strip steel is rapidly developed in recent years, and the plate and strip steel is used as one of important products in the steel industry and has been applied to various high-precision fields such as industrial production and manufacturing, aerospace and the like. Therefore, the surface quality of the strip steel has high requirements, and the defect detection of the surface of the strip steel is usually required.
The current detection of the surface defects of the plate strip steel is usually carried out by manual naked eyes, but as the working time is prolonged, people can generate visual fatigue, and in addition, the environment, the light, the shooting angle and the like can influence the result. Especially, when the plate and strip steel is in rapid operation, the defects on the surface of the plate and strip steel are more difficult to judge by people. Compared with machine vision detection, the machine does not generate fatigue due to overlong time, and meets the requirement of the existing batch production. However, the existing detection system cannot adapt to the change of defects, such as two similar surface defects, and the system cannot accurately identify the defect type. In addition, external factors such as shooting angle, light intensity and the like also influence the surface defect detection of the plate strip steel. Therefore, a detection method capable of accurately, efficiently and in real time is required to be provided for the surface detection of the plate strip steel.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a plate strip steel surface defect detection method based on machine vision, which comprises the following steps:
step 1: establishing a reference sample database according to the gray characteristic quantity of the plate strip steel images without defects and with different defect types;
step 2: acquiring an original image of the plate strip steel on the pickling cold continuous rolling production line when the plate strip steel runs to a shooting area as an image to be detected;
and step 3: carrying out gray level processing on each image to be detected to obtain a gray level image of the plate strip steel;
and 4, step 4: carrying out image enhancement processing on the gray level image by using a self-adaptive filtering algorithm;
and 5: uniformly dividing each gray level image subjected to enhancement processing into N independent units;
step 6: calculating the gray value of each unit, and drawing a gray level histogram of each gray level image;
and 7: extracting the gray characteristic quantity of each gray histogram;
and 8: comparing the gray characteristic quantity corresponding to each image to be detected with the gray characteristic quantity in the reference sample database to determine whether the plate strip steel part corresponding to the image to be detected is defective or not, and determining a specific defect type if the plate strip steel part is defective;
and step 9: determining the distance L of a defect part relative to one end of the plate strip steel by using a formula (1) according to the shooting time t of an image to be detected and the running speed v of the pickling cold continuous rolling production line;
L＝v(t-t0) (1)
in the formula, t0The starting time of one end of the plate strip steel entering the production line is shown.
The reference sample in step 1 includes: gray scale characteristic quantity D of non-defective plate strip steel image0(x0,y0,z0) Gray scale feature D of the image of the strip steel of the ith defect typei(xi,yi,zi) 1,2,..., n; the defect types include: acid-starving, acid-washing, spot stopping, roller mark supporting of a straightening machine, scratching, emulsion spot residue, transverse crack, longitudinal crack, crazing, irregular surface interlayer, belt-shaped surface interlayer, iron scale pressing, powdery iron scale pressing and edge burr cutting; wherein x0、y0、z0Respectively representing the mean value, variance and entropy value of gray scale in the gray scale characteristic quantity of the image of the strip steel without the defect platei,yi,ziRespectively representing the gray mean, the variance and the entropy in the gray characteristic quantity of the plate strip steel image of the ith defect type, wherein n represents the number of the types of the defects.
The step 8 comprises the following steps:
step 8.1: judging whether the plate band steel part corresponding to the jth image to be detected has defects, if so, judging the gray characteristic quantity of the jth image to be detected
Each parameter of
And is
And is
Judging that the strip steel part corresponding to the jth image to be detected is not defective, otherwise, judging that the strip steel part is defective, and continuing to execute the step 8.2, wherein delta0Representing a gray scale feature quantity D0(x0,y0,z0) The offset of each of the parameters in (a),
respectively represent the jth waiting sheetDetecting a gray mean value, a variance and an entropy value in the gray characteristic quantity of the image;
step 8.2: judging the specific defect type of the defective strip steel, if the jth image to be detected has the gray characteristic quantity
Each parameter of
Or
Or
And judging that the strip steel part corresponding to the jth image to be detected is the ith defect type.
A detection device for detecting the surface defects of plate strip steel based on machine vision comprises a camera, a light source and a computer, wherein the camera is arranged at a position which is a certain height away from the upper part and the lower part of the plate strip steel and can move along the axial direction of the plate strip steel, the light source is arranged at one side of the camera, the camera is electrically connected with the computer, the image of the plate strip steel running on an acid pickling cold continuous rolling production line is collected in real time through the camera, and the image is transmitted to the computer for detecting and judging the defects.
Further, in order to simultaneously detect the defects of the plate strip steel running on the pickling cold continuous rolling production line in the rolling section and the pickling section, a camera and a light source which are matched with each other need to be respectively installed in the rolling section and the pickling section of the production line.
The invention has the beneficial effects that:
the invention provides a method and a device for detecting the surface defects of plate strip steel based on machine vision, which are characterized in that the method and the device are used for collecting the surface defect pictures of the plate strip steel in advance and establishing a reference sample database according to various obtained gray characteristic quantities; extracting gray characteristic quantity after the obtained image to be detected is subjected to image enhancement processing, and determining whether a fault exists, a specific fault type and a fault position by comparing the gray characteristic quantity with a reference sample; the device can be installed at different positions of a production line according to actual conditions and is used for detecting defects at different stations in the production process. And the device can be used for detecting different types of plate strip steel by collecting reference samples of different types of plate strip steel, and can also be arranged on production lines of different plate strip steels to be used for collecting defect samples of the plate strip steel.
Drawings
FIG. 1 is a flow chart of a method for detecting surface defects of a strip steel based on machine vision in the invention;
FIG. 2 is a schematic view of a detection apparatus for detecting surface defects of a strip steel by using a machine vision-based method according to the present invention;
FIG. 3 is a schematic view of the installation position of the detection device in the pickling cold continuous rolling production line;
FIG. 4 is a processing diagram of scratch defects in the present invention, wherein (a) shows a gray distribution histogram of a strip image of a plate with scratch defects, (b) shows a gray graph with scratch defects, and (c) shows a gray graph of the plate strip after the scratch image is enhanced;
FIG. 5 is a view showing the processing of the under-pickled defects in the present invention, wherein (a) shows an image of a strip with the under-pickled defects, (b) shows a gray-scale image of an image of a strip with the under-pickled defects, and (c) shows a gray-scale image of the strip after the image of the strip is enhanced;
FIG. 6 is a diagram showing various plate strip defects actually photographed at the pickling stage in the present invention, wherein (a) shows a plate strip image having an over-pickling defect, wherein (b) shows a plate strip image having a parking spot defect, wherein (c) shows a plate strip image having a leveler backup roll mark defect, and wherein (d) shows a plate strip image having a trimming burr defect;
FIG. 7 is a diagram showing the processing of the latex speck residual defect in the present invention, wherein (a) shows the gray distribution histogram of the strip steel image with latex speck residual defect, (b) shows the gray graph of the strip steel residual defect with latex speck, and (c) shows the gray graph of the strip steel latex speck after image enhancement;
fig. 8 is a diagram of various plate strip defects actually photographed at a rolling stage in the present invention, in which (a) shows a plate strip image with an irregular surface interlayer defect, in which (b) shows a plate strip image with a band-shaped surface interlayer defect, in which (c) shows a plate strip image with a scale indentation defect, in which (d) shows a plate strip image with a powdery scale indentation defect, (e) shows a plate strip image with a longitudinal crack defect, in which (f) shows a plate strip image with a transverse crack defect, and (g) shows a plate strip image with a crack defect.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
As shown in fig. 1, a method for detecting surface defects of a plate strip steel based on machine vision includes the following steps:
step 1: establishing a reference sample database according to the gray characteristic quantity of the plate strip steel images without defects and with different defect types, wherein the reference sample comprises: gray scale characteristic quantity D of non-defective plate strip steel image0(x0,y0,z0) Gray scale feature D of the image of the strip steel of the ith defect typei(xi,yi,zi) 1,2,..., n; the defect types include: acid-starving, acid-washing, spot stopping, roller mark supporting of a straightening machine, scratching, emulsion spot residue, transverse crack, longitudinal crack, crazing, irregular surface interlayer, belt-shaped surface interlayer, iron scale pressing, powdery iron scale pressing and edge burr cutting; wherein x0、y0、z0Respectively representing the mean value, variance and entropy value of gray scale in the gray scale characteristic quantity of the image of the strip steel without the defect platei,yi,ziRespectively representing the gray mean, the variance and the entropy in the gray characteristic quantity of the plate strip steel image of the ith defect type, wherein n represents the number of the types of the defects.
Step 2: acquiring an original image of the plate strip steel on the pickling cold continuous rolling production line when the plate strip steel runs to a shooting area as an image to be detected;
and step 3: carrying out gray level processing on each image to be detected to obtain a gray level image of the plate strip steel;
and 4, step 4: carrying out image enhancement processing on the gray level image by using a self-adaptive filtering algorithm;
and 5: uniformly dividing each gray level image subjected to enhancement processing into N independent units;
step 6: calculating the gray value of each unit, and drawing a gray level histogram of each gray level image; among them, the processing diagram of scratch defects is shown in FIG. 4, the processing diagram of under-acid defects is shown in FIG. 5, and the processing diagram of latex speck residual defects is shown in FIG. 7.
And 7: extracting the gray characteristic quantity of each gray histogram;
and 8: comparing the gray characteristic quantity corresponding to each image to be detected with the gray characteristic quantity in the reference sample database, determining whether the strip steel part corresponding to the image to be detected is defective or not, and determining a specific defect type if the defect is determined, wherein the method comprises the following steps:
step 8.1: judging whether the plate band steel part corresponding to the jth image to be detected has defects, if so, judging the gray characteristic quantity of the jth image to be detected
Each parameter of
And is
And is
Judging that the strip steel part corresponding to the jth image to be detected is not defective, otherwise, judging that the strip steel part is defective, and continuing to execute the step 8.2, wherein delta0Representing a gray scale feature quantity D0(x0,y0,z0) The offset of each of the parameters in (a),
respectively representing the gray level mean value, the variance and the entropy value in the gray level characteristic quantity of the jth image to be detected;
step 8.2: judging the specific defect type of the defective plate strip steel, and if the jth sheet is to be detectedGray scale feature quantity of image
Each parameter of
Or
Or
And judging that the strip steel part corresponding to the jth image to be detected is the ith defect type.
And step 9: determining the distance L of a defect part relative to one end of the plate strip steel by using a formula (1) according to the shooting time t of an image to be detected and the running speed v of the pickling cold continuous rolling production line;
L＝v(t-t0) (1)
in the formula, t0The starting time of one end of the plate strip steel entering the production line is shown.
The detection device for the detection method of the surface defects of the plate strip steel based on machine vision comprises a camera, a light source and a computer, wherein the camera is arranged at a position which is a certain height away from the upper part and the lower part of the plate strip steel and can move along the axial direction of the plate strip steel, the light source is arranged at one side of the camera, the camera is electrically connected with the computer, the image of the plate strip steel running on an acid pickling cold continuous rolling production line is collected in real time through the camera, and the image is transmitted to the computer for defect detection and judgment.
As shown in fig. 2, the specific structure of the present embodiment includes: the device comprises a CCD camera 1 (the model is MV-GED501M-T), a light source 6, a computer, a first horizontal beam 7, a first vertical beam 3, a second horizontal beam 4, a second vertical beam 2, a first horizontal guide rail 8 and a second horizontal guide rail 5, wherein the first horizontal beam 7 is respectively arranged on the first vertical beam 3 at a certain height from the upper part and the lower part of a plate strip steel 9, the first horizontal guide rail 8 is arranged on the first horizontal beam 7, and the CCD camera 1 is uniformly arranged on the first horizontal guide rail 8; a horizontal beam II 4 is respectively arranged on the vertical beam II 2 at a certain height from the upper part and the lower part of the plate band steel 9, a horizontal guide rail II 5 is arranged on the horizontal beam II 4, a light source 6 is uniformly arranged on the horizontal guide rail II 5, a CCD camera 1 is electrically connected with a computer, an original image of the plate band steel 9 acquired by the CCD camera 1 is transmitted to the computer for defect detection and judgment, in order to simultaneously detect the defects of the plate strip steel 9 running on the pickling cold continuous rolling production line in the rolling section and the pickling section, a device assembled by a matched camera and a light source is required to be respectively arranged in the rolling section and the pickling section of the production line, the schematic diagram of the installation position is shown in figure 3, the images of the plate strip steel at the rolling section and the pickling section are collected at the same time and transmitted to a computer, and (4) detecting various defects generated after the strip steel is subjected to different processing procedures by comparing with the reference samples stored in the database.
In order to facilitate the adjustment of the shooting visual field, the light source and the camera need to move along the axial direction of the plate strip steel (namely move left and right), the device adopts a guide rail design, the cross beam adopts 6060 heavy aluminum profiles, and the connection mode is angle aluminum connection.
In order to improve the shooting quality of the image, camera parameters need to be set first before shooting, and the shooting angle needs to be adjusted, various defects of the acid-washing section obtained by actual shooting are shown in fig. 6, and the characteristics of each defect are expressed as follows:
acid pickling: the surface of the steel strip is rougher than that of the steel plate after normal pickling, the color is not silvery white, but is dark black or brownish black, and the gray value of the large-area point-shaped steel strip on the surface of the steel plate is higher;
parking spot: the parking spots are large spots formed by chemical substances stuck on the surface of the steel strip when the pickling line is parked, and can be distributed at any position of the steel strip;
supporting a roll mark by a straightening roll: regular light and dark stripes along the rolling direction of the steel plate are generally invisible without hand feeling and seriously have hand feeling, are longitudinally distributed along the plate strip, and are brightly distributed when a gray level image is transversely seen;
trimming burrs and edges: the cutting edges of the circle shears are dull or have gaps, or the gaps and the overlapping amount of the cutting edges are not adjusted, burrs appear after the circle shears are cut, and after the binarization processing of the image edge gray level image, the light and shade at the pixel points are alternated;
the various defects of the rolled section obtained by actual shooting are shown in fig. 8, and the characteristics of each defect are expressed as follows:
irregular surface tape layer: the thin layer on the surface of the plate strip steel is folded, the defects are always grey white, and the sizes and the shapes of the defects are different and are irregularly distributed on the surface of the plate strip steel;
band-shaped surface interlayer: the inclusions on the surface of the plate strip steel are irregularly distributed along the rolling direction in a linear or strip shape and sometimes gradually disappear in a point or tongue shape;
pressing iron scale: the scale is a defect that the scale is pressed into the surface of the strip steel, is usually distributed on the whole or part of the upper surface and the lower surface of the strip steel irregularly in a small spot shape, a fish scale shape, a strip shape and a block shape, and is often accompanied with a rough pockmarked surface;
pressing powdery iron oxide scales: the powdery iron oxide scale is pressed into the surface of the plate strip steel, is mainly generated on the upper surface of the plate strip steel and is distributed irregularly, and can also be generated on the lower surface;
longitudinal splitting: discontinuous cracks on the surface of the rolled piece along the rolling direction have different lengths and depths, the rolled piece is fractured due to serious longitudinal cracks, and a gray scale image shows longitudinal bright stripes;
transverse splitting: irregular cracks on the surface of the rolled piece, which are vertical to the rolling direction, are sometimes M-shaped or Z-shaped, the rolled piece is fractured due to serious transverse cracking, and a gray scale image is represented as a transverse bright stripe;
cracking: a discontinuous crack on the surface of a rolled piece is outwards diverged in a lightning shape by taking a certain point as a center, the affected area is generally oval according to the extension and the width, and the gray scale image shows that transverse and longitudinal stripes are converged and diverged.
Claims (5)
1. A method for detecting surface defects of plate strip steel based on machine vision is characterized by comprising the following steps:
step 1: establishing a reference sample database according to the gray characteristic quantity of the plate strip steel images without defects and with different defect types;
step 2: acquiring an original image of the plate strip steel on the pickling cold continuous rolling production line when the plate strip steel runs to a shooting area as an image to be detected;
and step 3: carrying out gray level processing on each image to be detected to obtain a gray level image of the plate strip steel;
and 4, step 4: carrying out image enhancement processing on the gray level image by using a self-adaptive filtering algorithm;
and 5: uniformly dividing each gray level image subjected to enhancement processing into N independent units;
step 6: calculating the gray value of each unit, and drawing a gray level histogram of each gray level image;
and 7: extracting the gray characteristic quantity of each gray histogram;
and 8: comparing the gray characteristic quantity corresponding to each image to be detected with the gray characteristic quantity in the reference sample database to determine whether the plate strip steel part corresponding to the image to be detected is defective or not, and determining a specific defect type if the plate strip steel part is defective;
and step 9: determining the distance L of a defect part relative to one end of the plate strip steel by using a formula (1) according to the shooting time t of an image to be detected and the running speed v of the pickling cold continuous rolling production line;
L＝v(t-t0) (1)
in the formula, t0The starting time of one end of the plate strip steel entering the production line is shown.
2. The method for detecting the surface defects of the plate strip steel based on the machine vision is characterized in that the reference sample in the step 1 comprises the following steps: gray scale characteristic quantity D of non-defective plate strip steel image0(x0,y0,z0) Gray scale feature D of the image of the strip steel of the ith defect typei(xi,yi,zi) 1,2,..., n; the defect types include: acid-starving, acid-washing, spot stopping, roller mark supporting of a straightening machine, scratching, emulsion spot residue, transverse crack, longitudinal crack, crazing, irregular surface interlayer, belt-shaped surface interlayer, iron scale pressing, powdery iron scale pressing and edge burr cutting; wherein x0、y0、z0Respectively represents the gray mean value, the variance and the entropy value in the gray characteristic quantity of the image of the non-defective strip steel,xi,yi,zirespectively representing the gray mean, the variance and the entropy in the gray characteristic quantity of the plate strip steel image of the ith defect type, wherein n represents the number of the types of the defects.
3. The method for detecting the surface defects of the plate strip steel based on the machine vision is characterized in that the step 8 comprises the following steps:
step 8.1: judging whether the plate band steel part corresponding to the jth image to be detected has defects, if so, judging the gray characteristic quantity of the jth image to be detected
Each parameter of
And is
And is
Judging that the strip steel part corresponding to the jth image to be detected is not defective, otherwise, judging that the strip steel part is defective, and continuing to execute the step 8.2, wherein delta0Representing a gray scale feature quantity D0(x0,y0,z0) The offset of each of the parameters in (a),
respectively representing the gray level mean value, the variance and the entropy value in the gray level characteristic quantity of the jth image to be detected;
step 8.2: judging the specific defect type of the defective strip steel, if the jth image to be detected has the gray characteristic quantity
Each parameter of
Or
Or
And judging that the strip steel part corresponding to the jth image to be detected is the ith defect type.
4. The detection device is characterized by comprising a camera, a light source and a computer, wherein the camera is arranged at a position which is a certain height away from the upper part and the lower part of the strip steel and can move along the axial direction of the strip steel, the light source is arranged at one side of the camera, the camera is electrically connected with the computer, the strip steel image running on an acid pickling cold continuous rolling production line is collected in real time through the camera, and the image is transmitted to the computer for defect detection and judgment.
5. The inspection apparatus of claim 4, wherein in order to simultaneously inspect the defects of the strip steel running on the pickling line in the rolling and pickling sections, a camera and a light source are respectively installed in the rolling and pickling sections.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011489920.6A CN112697803A (en) | 2020-12-16 | 2020-12-16 | Plate strip steel surface defect detection method and device based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011489920.6A CN112697803A (en) | 2020-12-16 | 2020-12-16 | Plate strip steel surface defect detection method and device based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112697803A true CN112697803A (en) | 2021-04-23 |
Family
ID=75508569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011489920.6A Pending CN112697803A (en) | 2020-12-16 | 2020-12-16 | Plate strip steel surface defect detection method and device based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112697803A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113740350A (en) * | 2021-09-01 | 2021-12-03 | 常州大学 | Strip steel surface image acquisition device for defect identification and use method thereof |
| CN114264786A (en) * | 2021-11-29 | 2022-04-01 | 马鞍山钢铁股份有限公司 | Casting blank quality evaluation method and system based on continuous casting tundish submerged nozzle nodule and nodule |
| CN114723751A (en) * | 2022-06-07 | 2022-07-08 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Unsupervised strip steel surface defect online detection method |
| CN114742788A (en) * | 2022-04-01 | 2022-07-12 | 南通高精数科机械有限公司 | Copper bar defect detection method and system based on machine vision |
| CN114965935A (en) * | 2022-05-17 | 2022-08-30 | 马鞍山钢铁股份有限公司 | Strip steel quality judgment method and system based on customer requirements |
| CN116288381A (en) * | 2023-03-16 | 2023-06-23 | 山东钢铁集团日照有限公司 | Closed-loop control method for realizing stable pickling quality by automatically adjusting hydrochloric acid process parameters |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1900701A (en) * | 2006-07-19 | 2007-01-24 | 北京科技大学 | Online detecting method and device for hot rolling strip surface fault based on laser line light source |
| WO2007062563A1 (en) * | 2005-12-01 | 2007-06-07 | Bohai Shipbuilding Industry Co., Ltd. | On-line automatic inspection method for detecting surface flaws of steel during the pretreatment of the ship steel |
| CN102095731A (en) * | 2010-12-02 | 2011-06-15 | 山东轻工业学院 | System and method for recognizing different defect types in paper defect visual detection |
| CN104568956A (en) * | 2013-10-12 | 2015-04-29 | 上海掌迪自动化科技有限公司 | Machine vision based detection method for strip steel surface defects |
| CN106596575A (en) * | 2016-12-15 | 2017-04-26 | 南通维新自动化科技有限公司 | Wood plate surface defect detection device |
| CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
| CN109030503A (en) * | 2018-07-11 | 2018-12-18 | 无锡赛默斐视科技有限公司 | The online surface defects detection system of strip and its detection method |
| CN109886932A (en) * | 2019-01-25 | 2019-06-14 | 中国计量大学 | Gear ring of wheel speed sensor detection method of surface flaw based on SVM |
| CN110026449A (en) * | 2019-04-29 | 2019-07-19 | 沈阳建筑大学 | A kind of on-line measurement system and method based on machine vision |
| CN111968098A (en) * | 2020-08-24 | 2020-11-20 | 广东工业大学 | Strip steel surface defect detection method, device and equipment |
-
2020
- 2020-12-16 CN CN202011489920.6A patent/CN112697803A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007062563A1 (en) * | 2005-12-01 | 2007-06-07 | Bohai Shipbuilding Industry Co., Ltd. | On-line automatic inspection method for detecting surface flaws of steel during the pretreatment of the ship steel |
| CN1900701A (en) * | 2006-07-19 | 2007-01-24 | 北京科技大学 | Online detecting method and device for hot rolling strip surface fault based on laser line light source |
| CN102095731A (en) * | 2010-12-02 | 2011-06-15 | 山东轻工业学院 | System and method for recognizing different defect types in paper defect visual detection |
| CN104568956A (en) * | 2013-10-12 | 2015-04-29 | 上海掌迪自动化科技有限公司 | Machine vision based detection method for strip steel surface defects |
| CN106596575A (en) * | 2016-12-15 | 2017-04-26 | 南通维新自动化科技有限公司 | Wood plate surface defect detection device |
| CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
| CN109030503A (en) * | 2018-07-11 | 2018-12-18 | 无锡赛默斐视科技有限公司 | The online surface defects detection system of strip and its detection method |
| CN109886932A (en) * | 2019-01-25 | 2019-06-14 | 中国计量大学 | Gear ring of wheel speed sensor detection method of surface flaw based on SVM |
| CN110026449A (en) * | 2019-04-29 | 2019-07-19 | 沈阳建筑大学 | A kind of on-line measurement system and method based on machine vision |
| CN111968098A (en) * | 2020-08-24 | 2020-11-20 | 广东工业大学 | Strip steel surface defect detection method, device and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 穆晓芳 等: "数字图像处理技术", 煤炭工业出版社, pages: 417 - 420 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113740350A (en) * | 2021-09-01 | 2021-12-03 | 常州大学 | Strip steel surface image acquisition device for defect identification and use method thereof |
| CN114264786A (en) * | 2021-11-29 | 2022-04-01 | 马鞍山钢铁股份有限公司 | Casting blank quality evaluation method and system based on continuous casting tundish submerged nozzle nodule and nodule |
| CN114264786B (en) * | 2021-11-29 | 2024-01-12 | 马鞍山钢铁股份有限公司 | Casting blank quality evaluation method and system based on continuous casting tundish immersion nozzle falling-off nodulation |
| CN114742788A (en) * | 2022-04-01 | 2022-07-12 | 南通高精数科机械有限公司 | Copper bar defect detection method and system based on machine vision |
| CN114965935A (en) * | 2022-05-17 | 2022-08-30 | 马鞍山钢铁股份有限公司 | Strip steel quality judgment method and system based on customer requirements |
| CN114723751A (en) * | 2022-06-07 | 2022-07-08 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Unsupervised strip steel surface defect online detection method |
| CN114723751B (en) * | 2022-06-07 | 2022-09-23 | 中国空气动力研究与发展中心设备设计与测试技术研究所 | Unsupervised strip steel surface defect online detection method |
| CN116288381A (en) * | 2023-03-16 | 2023-06-23 | 山东钢铁集团日照有限公司 | Closed-loop control method for realizing stable pickling quality by automatically adjusting hydrochloric acid process parameters |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112697803A (en) | Plate strip steel surface defect detection method and device based on machine vision | |
| CN109682839B (en) | Online detection method for surface defects of metal arc-shaped workpiece | |
| CN104101600B (en) | Cross Section of CC Billet testing of small cracks method | |
| Choi et al. | Detection of pinholes in steel slabs using Gabor filter combination and morphological features | |
| CA2685095C (en) | Method for detecting and classifying surface defects on continuously cast slabs | |
| CN107967681B (en) | Elevator compensation chain impact defect detection method based on machine vision | |
| CN109115800B (en) | Method for rapidly detecting burrs of product and accurately measuring length | |
| CN115375686B (en) | Glass edge flaw detection method based on image processing | |
| CN101995412B (en) | Robust glass scratch defect detection method and device thereof | |
| WO2021185010A1 (en) | Roller surface defect identification method and apparatus for roller press | |
| CN115690387A (en) | Alloy surface detection system based on image recognition | |
| CN105184792B (en) | A kind of saw blade wear extent On-line Measuring Method | |
| CN114897908B (en) | Machine vision-based method and system for analyzing defects of selective laser powder spreading sintering surface | |
| CN113034442B (en) | Hot rolled strip steel surface quality grading method based on defect distribution map | |
| CN111062939B (en) | Method for rapidly screening quality of strip steel surface and automatically extracting defect characteristics | |
| Tang et al. | Surface inspection system of steel strip based on machine vision | |
| US6232617B1 (en) | Apparatus for detecting surface defects on running metal strip | |
| CN107677677B (en) | Quantitative characterization method for segregation degree of continuous casting billet | |
| CN117333727A (en) | Conveyer belt wearing and tearing area discernment analysis system based on visual image processing technique | |
| CN114383522B (en) | Method for measuring surface gap and surface difference of workpiece with reflective difference | |
| CN115980063A (en) | Workpiece surface flaw detection method and device | |
| CN113547281A (en) | Method for repairing surface cracks of leveling roller and performing nondestructive testing | |
| CN109064417B (en) | Subway tunnel image processing method and device | |
| CN113092486B (en) | Method suitable for detecting water ripples on surface of high-gloss surface product | |
| CN115931878A (en) | Workpiece surface flaw detection method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210423 |
|
| RJ01 | Rejection of invention patent application after publication |