CN113252682B - Method for improving accuracy of surface quality detection system for identifying strip steel surface defects - Google Patents
Method for improving accuracy of surface quality detection system for identifying strip steel surface defects Download PDFInfo
- Publication number
- CN113252682B CN113252682B CN202110405306.5A CN202110405306A CN113252682B CN 113252682 B CN113252682 B CN 113252682B CN 202110405306 A CN202110405306 A CN 202110405306A CN 113252682 B CN113252682 B CN 113252682B
- Authority
- CN
- China
- Prior art keywords
- defect
- defects
- parameter
- detection system
- parameters
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention particularly relates to a method for improving the accuracy of a surface quality detection system for identifying strip steel surface defects, which belongs to the technical field of steel production and comprises the following steps: presetting parameters of a surface quality detection system, wherein the parameters comprise: the fuzzy processing parameters are determined according to different steel grades, and when the steel grade is GA material, the fuzzy processing parameters are (0.2-0.4) × (0.2-0.3) mm; when the steel grade is a GI material, the hazing parameter is (0.6-0.8) × (0.3-0.4) mm; the method comprises the following steps that a surface quality detection system with preset parameters is adopted to identify the defects of the strip steel, so that the accuracy of identifying the defects of the surface of the strip steel by the surface quality detection system is improved; parameters are set according to the characteristics of the surfaces of different steel types, so that the condition that a plurality of strip steel textures are detected due to the fact that the upper limit and the lower limit are simply reduced is avoided.
Description
Technical Field
The invention belongs to the technical field of steel production, and particularly relates to a method for improving the accuracy of a surface quality detection system for identifying surface defects of strip steel.
Background
With the improvement of the use requirements of users and the aggravation of the steel homogenization competition, the surface quality of the strip steel becomes an important basis for measuring the quality of steel products and the product competitiveness.
The traditional surface quality detection is carried out by adopting a manual visual spot inspection and a frequency flash detection method, and the method has three main defects: 1. the sampling inspection rate is low, the surface detection can be only carried out when the strip steel is at a low speed, and the quality condition of the surface of the strip steel cannot be truly and reliably reflected by 100 percent; 2. the real-time performance is poor, and the high-speed production rhythm of a production line cannot be met; 3. the consistency is lacked, the detection result is easily influenced by subjective judgment of detection personnel, and the consistency and the scientificity of detection are lacked. In addition, the method has the disadvantages that small defects such as dark spots are difficult to detect and harm is caused to detection personnel. The traditional manual detection cannot obtain satisfactory detection results.
Kangnai vision (Cognex) is an online surface quality detection system, can be used in a plurality of fields such as steel, papermaking, chemical industry and the like, and realizes the detection of the surface defects of products. However, in different fields and even different production lines, the conditions are different, and personalized setting and configuration are required to be performed by combining the characteristics of the production line, the product characteristics and the user requirements, so that automatic detection of both quality and efficiency is realized, the labor intensity is greatly reduced, and the production efficiency is improved.
Disclosure of Invention
In view of the above, the present invention has been made to provide a method for improving the accuracy of a surface quality inspection system for identifying surface defects of a strip steel, which overcomes or at least partially solves the above-mentioned problems.
The embodiment of the invention provides a method for improving the accuracy of a surface quality detection system for identifying the surface defects of strip steel, which comprises the following steps:
presetting parameters of a surface quality detection system, wherein the parameters comprise: the fuzzy processing parameters are determined according to different steel grades, and when the steel grade is a GA material, the fuzzy processing parameters are (0.2-0.4) × (0.2-0.3) mm; when the steel grade is a GI material, the blurring treatment parameter is (0.6-0.8) × (0.3-0.4) mm;
and defect recognition is carried out on the strip steel by adopting a surface quality detection system with preset parameters so as to improve the accuracy of the surface quality detection system in recognizing the surface defects of the strip steel.
Optionally, the parameters further include: pseudo defect filtering parameters including a pseudo defect distance from the head of the steel strip filtering distance parameter, a pseudo defect filtering area parameter and a pseudo defect filtering strength parameter, wherein the pseudo defect distance from the head of the steel strip filtering distance parameter is less than 2 meters, and the pseudo defect filtering area parameter is less than 0.5mm 2 And the pseudo defect filtration strength parameter is 0-20.
Optionally, the parameters include: a defect retention range parameter, a defect identification sensitivity parameter, a defect image merging parameter, a small defect filtering range parameter, and an edge defect filtering range parameter.
Optionally, the defect retention range parameter is an image retention range outside the defect, which is 25 × 25 to 32 × 32.
Optionally, the defect identification sensitivity parameter is 55-65.
Optionally, the defect image merging parameters include an in-box-area parameter and an out-box-area parameter, the in-box-area parameter is 1 × 1-3 × 3, and the out-box-area parameter is not merged.
Optionally, the small defect filtering range parameter includes a small defect filtering area parameter, and the small defect filtering area parameter is less than 0.3-0.4mm 2 。
Optionally, the edge defect filtering range parameter includes a distance parameter from the edge and a gray value parameter, the distance parameter from the edge is less than 5-6mm, and the gray value parameter is 20-230.
Optionally, the method further includes:
presetting surface defect types of a surface quality detection system, wherein the surface defect types comprise linear defects, scab defects and covering slag defects;
and identifying the defects of the strip steel by adopting a surface quality detection system with preset surface defect types.
Optionally, the defect identification of the strip steel by using the surface quality detection system after the preset surface defect type specifically includes:
when the distance between the defect and the head is more than 20m, the distance between the defect and the nearest edge is more than 15mm; the height of the defect is 100-500mm, and the width of the defect is less than 2.5mm; the gray scale of the defect is that SV1 brightness is more than 20%, SV1 darkness is more than 20%, and SV1% is more than 50%; judging the defect as a linear defect;
when the distance between the defect and the head is more than 5m, the distance between the defect and the nearest edge is more than 5mm; the length-width ratio of the defect is more than 2, and the width of the defect is less than 50mm; the gray scale of the defect is SV1 with the strongest darkness less than 80; judging the scar defect;
when the distance between the defect and the head is more than 5m, the distance between the defect and the nearest edge is more than 5mm; the length-width ratio of the defect is more than 5, and the width of the defect is 2-5mm; the gray scale of the defect is SV1 with the minimum darkness less than 45, SV1% is more than 50%; the mold flux defect is judged.
One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:
the method for improving the accuracy of the surface quality detection system for identifying the surface defects of the strip steel provided by the embodiment of the invention comprises the following steps: presetting parameters of a surface quality detection system, wherein the parameters comprise: the fuzzy processing parameters are determined according to different steel grades, and when the steel grade is a GA material, the fuzzy processing parameters are (0.2-0.4) × (0.2-0.3) mm; when the steel grade is a GI material, the hazing parameter is (0.6-0.8) × (0.3-0.4) mm; the method comprises the steps that a surface quality detection system with preset parameters is adopted to identify the defects of the strip steel, so that the accuracy of identifying the surface defects of the strip steel by the surface quality detection system is improved; the application finds in the course of the invention: the surface generally has heavier textures, the detection precision can be greatly interfered, and the influence on the judgment accuracy is larger if a defect picture shot by a hardware system is directly judged, so that fine defects are detected by adopting image fuzzy processing, but the defects are difficult to detect as the colors of the defects are closer to the colors of strip steel.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a flow chart of a method provided by an embodiment of the present invention;
FIG. 2 is a diagram showing the result of detection of an artificial defect of a strip steel before optimization, provided by embodiment 1 of the present invention;
FIG. 3 is a diagram showing the result of the optimized detection of the artificial defects of the strip steel provided in embodiment 1 of the present invention;
FIG. 4 is a graph of noise levels at and near the location of a defect prior to optimization as provided in example 2 of the present invention;
FIG. 5 is a graph of the noise level at the optimized defect and nearby locations provided in example 2 of the present invention.
Detailed Description
The present invention will be described in detail below with reference to specific embodiments and examples, and the advantages and various effects of the present invention will be more clearly apparent therefrom. It will be understood by those skilled in the art that these specific embodiments and examples are for the purpose of illustrating the invention and are not to be construed as limiting the invention.
Throughout the specification, unless otherwise specifically noted, terms used herein should be understood as having meanings as commonly used in the art. Accordingly, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. If there is a conflict, the present specification will control.
Unless otherwise specifically stated, various raw materials, reagents, instruments, equipment and the like used in the present invention are commercially available or can be prepared by existing methods.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
in the invention process, the applicant finds that when the surface defect of the cold-rolled steel is detected by adopting a Cognex surface quality detection system, the method for improving the accuracy of the surface defect comprises the following steps:
1. defect detection rate and effect
The first step of realizing accurate judgment of the defects is to detect and present the defects participating in the judgment in a clear form as much as possible, and simultaneously avoid detecting the defects not needing to participate in the judgment so as to improve the running efficiency and the detection precision of the equipment. And 5, locking five key influence aspects by combining the surface quality requirements of the cold-rolled strip steel.
(1) And the defect retention range is reasonably controlled, the shot peripheral image part of the defect is selectively retained, the defect is easily missed to be judged when the range is too large, and the defect is easily mistakenly judged when the range is too small. In combination with the applicable conditions of the cold-rolled steel strip, the image storage range except for the defects needs to be set to be 25 × 25-32 × 32 in the repeat-grain parameters;
(2) And reasonably controlling the defect identification sensitivity. Sensitivity reflects the accuracy of defect identification, and high sensitivity allows identification of finer defects, but also more false defects. The sensitivity needs to be set to be 55-65 in the recipe-thresholds in combination with the applicable conditions of the cold-rolled strip steel;
(3) And reasonably controlling the image merging parameters. One typical characteristic of the surface defects of the cold-rolled steel strip is that part of the defects exist intermittently, and the conventional mode of a surface inspection instrument is a separate treatment, but the mode cannot truly reflect the sizes and the shapes of the defects, so that specific defects need to be combined. Combining the applicable conditions of the cold-rolled steel strip, controlling the merging range of the internal defects of the box area to be 1 to 3 in the recipe-dsfect parameters, and setting the merging range between the images outside the box area not to be merged;
(4) And reasonably controlling the filtering range of the small defects. The defects detected by the conventional mode of the meter detector are that a part of small defects can not influence the product quality, and on the contrary, the detection precision and efficiency can be influenced by too many defects. Therefore, it is necessary to reasonably control the small defect filtering range, so as to ensure both sufficient precision and accuracy and efficiency. The applicable conditions of the cold-rolled strip steel are combined, and the small defect filtration range needs to be controlled to be within<0.3-0.4mm 2 ；
(5) And reasonably controlling the filtration range of the edge defects. The cold-rolled strip steel runs on the roller way, a large number of false defects often appear at the overlapping transition position of the edge part of the strip steel and the roller way, and reasonable filtration is required. And combining the application conditions of the patent, wherein the locking control range is that the distance between the defect and the edge part is less than 5-6mm, and the gray value is 20-230.
2. Effects of Defect noise treatment
The customer has higher requirements for the surface quality of the cold-rolled steel sheet, and needs to have higher detection precision, but simultaneously because the surface of the cold-rolled steel sheet generally has heavier textures, the detection precision can be greatly interfered, and the influence on the judgment accuracy is larger if a defect picture shot by a hardware system is directly judged, so that the defect noise processing step must be carried out in the process of detecting and judging the defects on the surface of the cold-rolled steel sheet, and two key influence aspects are locked simultaneously:
(1) And optimizing fuzzy processing parameters. The image blurring processing is to detect fine defects, and if the defects are relatively close to the strip steel color, the defects are difficult to detect, and if the upper limit and the lower limit are simply reduced, a plurality of strip steel textures are detected. Combining the surface characteristics of different steel grades to finally determine that the GA material fuzzy parameter is controlled at (0.2-0.4) × (0.2-0.3) mm, and the GI material fuzzy processing parameter is controlled at (0.6-0.8) × (0.3-0.4) mm; the GA material is an alloyed galvanized material, and the GI material is a hot-dip galvanized material.
(2) And optimizing the filtering rule of the false defects at the head of the strip steel. Due to the particularity of the cold-rolled strip steel, a non-finished area exists at a certain distance from the head of the cold-rolled strip steel, a defect filtering rule needs to be set independently, specific pseudo defects need to be filtered, and meanwhile enough real defects are reserved. And (3) filtering the defects within 2 meters from the head by combining the applicable conditions of the patent, wherein the filtering area is less than 0.5mm2, and the strength is within the range of 0-20.
3. Effects of typical defects
Among the defects on the surface of the cold-rolled steel strip, the defect of dark color of the strip is the most common defect, and the defects are generally called inclusion defects. However, the actual causes of such defects are complex, and although the morphological features are very close, the defects are slightly different, so that the method of "inclusion" is not favorable for preparing and judging the causes of the defects, and further is not favorable for optimizing the production line process. The patent combines production practice to propose to subdivide the defects into three types of linear defects, scabs and covering slag, and provides judgment parameters of the three types of typical surface defects:
linear defects: the position is defined as a distance from the head of >20 meters and a distance from the nearest edge of >15mm; the dimensions are defined as height 100-500mm, width <2.5mm; the gray scale was defined as SV1 brightness >20%, SV1 darkness >20%, SV1% >50%.
Scabbing defect: the position is limited to the nearest edge distance being more than 5mm, and the head distance being more than 5 m; aspect ratio is limited to aspect ratio >2, width <50mm; the grayscale feature is limited to SV1 with the strongest darkness <80.
Defects of the mold flux: the position is defined as >5 meters from the head and >5mm from the nearest edge; the size is limited to 2-5mm; the length to width ratio is defined as >5; the gray scale is defined as SV1 minimum darkness <45,sv1% by >50%.
The method for improving the accuracy of identifying the surface defects of the cold-rolled steel strip according to the present application will be described in detail with reference to examples, comparative examples and experimental data.
Experimental example 1
Artificially respectively making two black lines in the whole width direction on the upper and lower surfaces of a steel coil at the inlet of a production line, respectively making 3 small black dots and 3 vertical thin lines, and reversely checking whether the defects are detected after passing through a meter inspection instrument.
Before the parameters for improving the defect detection rate are set, only one camera on the driving side of the upper surface and two cameras on the working side of the lower surface in the meter detection instrument detect defects, the remaining 62.5 percent of the cameras do not detect the defects, and the result is shown in fig. 2, wherein the left side in the figure is the detection result of the upper surface, and the right side in the figure is the detection result of the lower surface.
According to the method for improving the defect detection rate provided by the embodiment, the defect retention range is enlarged, the defect identification sensitivity is controlled, the image merging parameters are controlled, the small defect filtering range is controlled, and the edge defect filtering range is controlled. And then verifying again that the artificially manufactured defects on the upper surface and the lower surface can be completely detected after passing through the meter detector, and the result is shown in fig. 3, wherein the left side in the figure is the detection result of the upper surface, and the right side in the figure is the detection result of the lower surface.
By adopting the method provided by the embodiment of the application to detect the cold-rolled strip steel, the detection rate of the defects can be greatly improved.
Experimental example 2
The defects and the noise conditions at the peripheral positions detected by adopting a conventional mode are shown in figure 4 by taking a cold-rolled plate GA material as an example; it can be seen that the defect sites are very noisy.
By adopting the method for improving defect noise processing provided by the embodiment, after processing by methods such as optimizing fuzzy processing parameters and optimizing pseudo-defect filtering rules, the conditions of defects and nearby noise are shown in fig. 5; and the noise reduction at the position of the visible defect is obvious.
The method provided by the embodiment of the application is adopted to detect the cold-rolled strip steel, so that the noise of the defect position can be effectively reduced.
Experimental example 3
The method is adopted to detect the inclusion defect of the cold-rolled strip steel.
The traditional 'inclusion' defects are further subdivided into three types of linear defects, scabs and covering slag, a typical gallery of the three types of defects is constructed, the typical gallery is shot in advance and recorded into a detection system, and judgment parameters of the three types of typical surface defects are given.
The results are shown in the following table:
as can be seen from the table, the conventional "inclusion" defect identification accuracy is only 53% and the total defect identification accuracy is only 85% before optimization. After the inclusion is subdivided into three types of linear defects, scabs and covering slag, the identification accuracy of the three types of defects reaches 91-94%, and the total defect identification accuracy is improved to 93%.
One or more technical solutions in the embodiments of the present invention at least have the following technical effects or advantages:
(1) The method provided by the embodiment of the invention can detect the defects which need to participate in the judgment as much as possible and present the defects in a clear form, and simultaneously avoid detecting the defects which do not need to participate in the judgment, thereby greatly improving the operation efficiency and the detection precision of the equipment;
(2) The method provided by the embodiment of the invention solves the problem that the detection precision is greatly interfered because the surface of the cold-rolled steel sheet generally has heavier textures;
(3) The method provided by the embodiment of the invention subdivides the defects which are commonly called as inclusion into three types, namely linear defects, scabbing defects and covering slag defects, is favorable for accurately judging the reasons of the defects and further optimizes the production line process.
Finally, it should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (3)
1. A method for improving the accuracy of a surface quality detection system for identifying the surface defects of strip steel is characterized by comprising the following steps:
presetting parameters of a surface quality detection system, wherein the parameters comprise: the method comprises the following steps of determining fuzzy processing parameters according to different steel grades, wherein the fuzzy processing parameters are (0.2-0.4) × (0.2-0.3) mm when the steel grade is a GA material; when the steel grade is a GI material, the hazing parameter is (0.6-0.8) × (0.3-0.4) mm; the pseudo-defect filtering parameters comprise a pseudo-defect distance steel strip head filtering distance parameter, a pseudo-defect filtering area parameter and a pseudo-defect filtering strength parameter, the pseudo-defect distance steel strip head filtering distance parameter is less than 2 meters, and the pseudo-defect filtering area parameter is less than 0.5mm 2 The pseudo defect filtration strength parameter is 0-20; the defect reserving range parameter is an image saving range of 25-32 for the image except the defect; the defect identification sensitivity parameter is 55-65; the defect image merging parameters comprise box area internal parameters and box area external parameters, the box area internal parameters are 1 x 1-3 x 3, and the box area external parameters are not merged; the small defect filtration range parameter comprises a small defect filtration area parameter, and the small defect filtration area parameter is less than 0.3-0.4mm 2 The edge defect filtering range parameters comprise a distance parameter from the edge and a gray value parameter, wherein the distance parameter from the edge is less than 5-6mmThe gray value parameter is 20-230;
and defect recognition is carried out on the strip steel by adopting a surface quality detection system with preset parameters so as to improve the accuracy of the surface quality detection system in recognizing the surface defects of the strip steel.
2. The method for improving the accuracy of identifying surface defects of a strip steel by a surface quality inspection system according to claim 1, further comprising:
presetting surface defect types of a surface quality detection system, wherein the surface defect types comprise linear defects, scab defects and covering slag defects;
and identifying the defects of the strip steel by adopting a surface quality detection system with preset surface defect types.
3. The method for improving the accuracy of the surface quality detection system for identifying the surface defects of the strip steel according to claim 2, wherein the step of identifying the defects of the strip steel by using the surface quality detection system with the preset surface defect type specifically comprises the following steps:
when the distance between the defect and the head is more than 20m, the distance between the defect and the nearest edge is more than 15mm; the height of the defect is 100-500mm, and the width of the defect is less than 2.5mm; the gray scale of the defect is that SV1 brightness is more than 20%, SV1 darkness is more than 20%, and SV1% is more than 50%; judging the defect as a linear defect;
when the distance between the defect and the head is more than 5m, the distance between the defect and the nearest edge is more than 5mm; the length-width ratio of the defect is more than 2, and the width of the defect is less than 50mm; the gray scale of the defect is SV1 with the strongest darkness less than 80; judging the scar defect;
when the distance between the defect and the head is more than 5m, the distance between the defect and the nearest edge is more than 5mm; the length-width ratio of the defect is more than 5, and the width of the defect is 2-5mm; the gray scale of the defect is SV1 with minimum darkness less than 45, SV1% is more than 50%; the mold flux defect is judged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110405306.5A CN113252682B (en) | 2021-04-15 | 2021-04-15 | Method for improving accuracy of surface quality detection system for identifying strip steel surface defects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110405306.5A CN113252682B (en) | 2021-04-15 | 2021-04-15 | Method for improving accuracy of surface quality detection system for identifying strip steel surface defects |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113252682A CN113252682A (en) | 2021-08-13 |
| CN113252682B true CN113252682B (en) | 2022-12-16 |
Family
ID=77220786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110405306.5A Active CN113252682B (en) | 2021-04-15 | 2021-04-15 | Method for improving accuracy of surface quality detection system for identifying strip steel surface defects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113252682B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004038885A (en) * | 2002-07-08 | 2004-02-05 | Adoin Kenkyusho:Kk | Image feature learning type defect detection method, defect detection device and defect detection program |
| CN101408521A (en) * | 2007-07-06 | 2009-04-15 | 卡姆特有限公司 | Method for increasing defect |
| CN103134807A (en) * | 2011-08-19 | 2013-06-05 | 康耐视公司 | System and method for identifying defects in a material |
| CN104914111A (en) * | 2015-05-18 | 2015-09-16 | 北京华检智研软件技术有限责任公司 | Strip steel surface defect on-line intelligent identification and detection system and detection method |
| WO2020067262A1 (en) * | 2018-09-28 | 2020-04-02 | Ｊｆｅスチール株式会社 | Method and device for detecting defect in surface of metal sheet, and method for manufacturing plated steel sheet |
| CN112598621A (en) * | 2020-11-27 | 2021-04-02 | 攀钢集团西昌钢钒有限公司 | Intelligent determination method for surface quality of cold-rolled strip steel |
-
2021
- 2021-04-15 CN CN202110405306.5A patent/CN113252682B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004038885A (en) * | 2002-07-08 | 2004-02-05 | Adoin Kenkyusho:Kk | Image feature learning type defect detection method, defect detection device and defect detection program |
| CN101408521A (en) * | 2007-07-06 | 2009-04-15 | 卡姆特有限公司 | Method for increasing defect |
| CN103134807A (en) * | 2011-08-19 | 2013-06-05 | 康耐视公司 | System and method for identifying defects in a material |
| CN104914111A (en) * | 2015-05-18 | 2015-09-16 | 北京华检智研软件技术有限责任公司 | Strip steel surface defect on-line intelligent identification and detection system and detection method |
| WO2020067262A1 (en) * | 2018-09-28 | 2020-04-02 | Ｊｆｅスチール株式会社 | Method and device for detecting defect in surface of metal sheet, and method for manufacturing plated steel sheet |
| CN112598621A (en) * | 2020-11-27 | 2021-04-02 | 攀钢集团西昌钢钒有限公司 | Intelligent determination method for surface quality of cold-rolled strip steel |
Non-Patent Citations (3)
| Title |
|---|
| 基于Gabor小波和加权马氏距离的带钢表面缺陷检测;陈海永等;《电子测量与仪器学报》;20160515;第30卷(第05期);全文 * |
| 带钢视觉检测系统的研究现状及展望;杨水山等;《冶金自动化》;20080325;第32卷(第02期);全文 * |
| 康耐视产品在埋弧焊焊缝跟踪系统中的应用;孙吉等;《焊管》;20091128;第32卷(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113252682A (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6117398B1 (en) | Steel plate surface defect inspection apparatus and surface defect inspection method | |
| US6779159B2 (en) | Defect inspection method and defect inspection apparatus | |
| US10041888B2 (en) | Surface defect inspecting device and method for hot-dip coated steel sheets | |
| CN114529549A (en) | Cloth defect labeling method and system based on machine vision | |
| CN116758061A (en) | Casting surface defect detection method based on computer vision | |
| CN108896278A (en) | A kind of optical filter silk-screen defect inspection method, device and terminal device | |
| CN114758185B (en) | Injection molding parameter control method and system based on gray level chromatic aberration | |
| CN110288618B (en) | Multi-target segmentation method for uneven-illumination image | |
| CN115330772A (en) | Online welding spot quality detection method | |
| CN115330758A (en) | Welding quality detection method based on denoising processing | |
| CN115100200A (en) | Optical fiber defect detection method and system based on optical means | |
| CN113610850A (en) | Decorative paper texture abnormity detection method based on image processing | |
| CN114581376A (en) | Automatic sorting method and system for textile silkworm cocoons based on image recognition | |
| CN113252682B (en) | Method for improving accuracy of surface quality detection system for identifying strip steel surface defects | |
| SE528526C2 (en) | Method and apparatus for optical evaluation of a paper surface | |
| CN108445008A (en) | A kind of detection method of steel strip surface defect | |
| CN116993742B (en) | Nickel alloy rolling defect detection method based on machine vision | |
| CN111126371B (en) | Coarse pointer dial reading method based on image processing | |
| CN115861304A (en) | Method and system for detecting steel strip-shaped structure based on image processing | |
| CN114998354A (en) | Steel belt roll mark detection method based on graph filtering | |
| JP2021189238A (en) | Belt inspection system and belt inspection program | |
| EP0475454A2 (en) | Defect inspection system | |
| JP2004151006A (en) | Quality control method of hot dip zinced steel plate, and quality control device of hot dip zinced steel plate | |
| CN115290661B (en) | Rubber ring defect identification method based on computer vision | |
| CN115797353B (en) | Intelligent detection system and method for quality of cold-rolled strip steel |
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 |