CN113866183B - Fault detection method and device for strip steel surface detector - Google Patents
Fault detection method and device for strip steel surface detector Download PDFInfo
- Publication number
- CN113866183B CN113866183B CN202111077980.1A CN202111077980A CN113866183B CN 113866183 B CN113866183 B CN 113866183B CN 202111077980 A CN202111077980 A CN 202111077980A CN 113866183 B CN113866183 B CN 113866183B
- Authority
- CN
- China
- Prior art keywords
- edge
- strip steel
- gray
- area
- cameras
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 157
- 239000010959 steel Substances 0.000 title claims abstract description 157
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 50
- 230000008569 process Effects 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 6
- 238000013459 approach Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 12
- 230000008901 benefit Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 241001270131 Agaricus moelleri Species 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000003889 chemical engineering Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- 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
- G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
-
- 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
- G01N2021/8887—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
Abstract
The application relates to the technical field of strip steel detection, in particular to a fault detection method and device of a strip steel surface detector, wherein the method comprises the following steps: obtaining an edge image of the strip steel from an edge camera; the edge cameras are determined from N cameras according to the width of the strip steel, and the N cameras are arranged at positions corresponding to the strip steel; determining a designated area in the edge image in the edge searching process of the edge image; wherein the specified area is determined according to a strip steel area and a non-strip steel area on the edge image; obtaining the angle deviation of the side camera according to the designated area; and if the angle deviation is not in the set angle range, determining that the angle deviation fault exists in the side camera. The method can rapidly and efficiently analyze the angle deviation fault of the detector, improve the detection efficiency of the detector and ensure the working stability of the detector.
Description
Technical Field
The application relates to the technical field of strip steel detection, in particular to a fault detection method and device of a strip steel surface detector.
Background
Strip steel is one of the main product forms of the steel industry, and has become an indispensable raw material in the industries of automobiles, mechanical manufacturing, chemical engineering, aerospace, shipbuilding and the like. In the aspect of quality inspection of the surface of the strip steel, the detector for detecting the surface of the strip steel has an irreplaceable function due to the high production speed of the production line. The quality of the strip steel surface is confirmed by field quality inspectors by means of a detector, defects on the strip steel surface are recorded, and the detector can increase the evaluation quantity due to excessive detection. Moreover, along with the vibration, the strip steel impact, the artificial collision and other factors of related equipment, the camera or the light source of the detector can slightly deviate in the angle direction, and the on-site quality inspection post can not quickly identify the fault of the detector, so that the defect imaging abnormality can be caused or the detection omission can occur, and the problem of low fault detection efficiency of the detector is caused.
Disclosure of Invention
The embodiment of the application solves the technical problem of low fault detection efficiency of the strip steel surface detector in the prior art by providing the fault detection method and the fault detection device of the strip steel surface detector, and achieves the technical effects of rapidly and efficiently analyzing the angle deviation fault of the detector, improving the detection efficiency of the detector and ensuring the working stability of the detector.
In a first aspect, an embodiment of the present application provides a fault detection method for a strip steel surface detector, including:
obtaining an edge image of the strip steel from an edge camera; the edge cameras are determined from N cameras according to the width of the strip steel, and the N cameras are arranged at positions corresponding to the strip steel;
determining a designated area in the edge image in the edge searching process of the edge image; wherein the specified area is determined according to a strip steel area and a non-strip steel area on the edge image;
obtaining the angle deviation of the side camera according to the designated area;
and if the angle deviation is not in the set angle range, determining that the angle deviation fault exists in the side camera.
Preferably, the edge finding process for the edge image includes:
and carrying out edge searching processing on the edge image, wherein the edge searching processing comprises at least one of transverse edge searching processing and longitudinal edge searching processing.
Preferably, the performing the lateral edge finding process on the edge image includes:
obtaining the current gray level of the current position in the process of carrying out line-by-line edge searching on the edge image with a set step length and a set frequency;
if the deviation between the current gray level and the historical gray level is larger than a first set gray level threshold value, determining a strip steel edge according to the current gray level and the historical gray level; wherein, the historical gray scale is the gray scale of the position at the last moment;
and obtaining the strip steel area and the non-strip steel area according to the strip steel edge.
Preferably, the performing the longitudinal edge finding processing on the edge image includes:
in the process of carrying out column-by-column edge searching on the edge image by taking pixels as units, obtaining the pixel position of each pixel in each column of pixels;
if the deviation between the pixel position of a certain pixel in a certain column of pixels and the average pixel position of the rest pixels in the column of pixels is greater than a position deviation threshold value, removing the pixel;
after removing the pixels, acquiring a first gray average value and a second gray average value; the first gray average value is the gray average value of a certain column of pixels, and the second gray average value is the gray average value of a column of pixels adjacent to the column of pixels;
if the deviation between the first gray average value and the second gray average value is larger than a second set gray threshold value, determining a strip steel edge according to the first gray average value and the second gray average value;
and obtaining the strip steel area and the non-strip steel area according to the strip steel edge.
Preferably, the determining the designated area according to the strip steel area and the non-strip steel area on the edge image includes:
and screening the designated area from the non-strip steel area, wherein the designated area is positioned close to the strip steel area.
Preferably, the obtaining the angular deviation of the edge camera according to the specified area includes:
obtaining the gray scale of the designated area according to the designated area;
and obtaining the angle deviation according to the gray scale of the designated area.
Preferably, the determining the edge camera from the N cameras according to the width of the strip steel includes:
obtaining the edge parameters according to the width of the strip steel, the total shooting range of the N cameras and the shooting range of each camera in the N cameras; wherein N is an integer greater than 2;
and determining a camera corresponding to the side parameter from the N cameras according to the side parameter, and determining the camera as the side camera.
Based on the same inventive concept, the present application also provides a fault detection device of a strip steel surface detector, including:
the first obtaining module is used for obtaining an edge image of the strip steel from the edge camera; the edge cameras are determined from N cameras according to the width of the strip steel, and the N cameras are arranged at positions corresponding to the strip steel;
the first determining module is used for determining a designated area in the edge image in the edge searching process of the edge image; wherein the specified area is determined according to a strip steel area and a non-strip steel area on the edge image;
the second obtaining module is used for obtaining the angle deviation of the side camera according to the designated area;
and the second determining module is used for determining that the angle deviation fault exists in the side camera if the angle deviation is not in the set angle range.
Based on the same inventive concept, in a third aspect, the present application provides a computer device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the fault detection method of the strip steel surface detector when executing the program.
Based on the same inventive concept, in a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements the steps of the fault detection method of the strip steel surface detector.
One or more technical solutions in the embodiments of the present application at least have the following technical effects or advantages:
in the embodiment of the application, an edge camera is determined from N cameras according to the width of the strip steel, and then an edge image is obtained through the edge camera. The method can quickly and efficiently determine the edge camera and obtain the accurate edge image. Then, edge finding processing is performed on the edge image. In the edge finding process, a designated area of the edge image is determined. Then, the angular deviation of the edge camera is obtained from the specified area. And finally, judging the angle deviation. If the angle deviation is not in the set angle range, determining that the angle deviation fault exists in the side camera. If the angle deviation is within the set angle range, determining that the side camera has no angle deviation fault. The fault detection method can rapidly and efficiently analyze the angle deviation fault of the detector, improve the detection efficiency of the detector and ensure the working stability of the detector. Therefore, the technical problem of low fault detection efficiency of the strip steel surface detector is solved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also throughout the drawings, like reference numerals are used to designate like parts. In the drawings:
FIG. 1 is a schematic flow chart showing the steps of a fault detection method of a strip steel surface detector in an embodiment of the application;
FIG. 2 is a schematic block diagram showing the arrangement of the detector in the embodiment of the present application;
FIG. 3 is a schematic diagram showing the arrangement of the strip steel and the camera in the embodiment of the application;
FIG. 4 is a schematic diagram of a transverse edge finding process in an embodiment of the application;
fig. 5 is a schematic structural diagram illustrating removal of abnormal pixels in the longitudinal edge finding process according to an embodiment of the present application;
FIG. 6 shows a schematic block diagram of a fault detection device of a strip steel surface detector in an embodiment of the application;
fig. 7 shows a schematic structural diagram of a computer device in an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example 1
A first embodiment of the present application provides a fault detection method for a strip surface detector, as shown in fig. 1, which is performed for a detector 201 for detecting the surface of a strip 202. After the strip 202 is manufactured or after a certain process step in rolling, the surface of the strip 202 needs to be inspected by using a detector 201. The detector 201 is arranged as shown in fig. 2. The detector 201 is disposed above the upper surface of the strip steel 202, below the lower surface of the strip steel 202, or above the upper surface of the strip steel 202 and below the lower surface of the strip steel 202, and the specific location of the detector 201 is not limited herein.
The following describes in detail the specific implementation steps of the fault detection method of the strip steel surface detector provided in this embodiment with reference to fig. 1:
first, step S101 is performed to obtain an edge image of the strip steel from an edge camera; the edge cameras are determined from N cameras according to the width of the strip steel, and the N cameras are arranged at positions corresponding to the strip steel.
Specifically, a row of cameras are arranged at positions corresponding to the surface of the strip steel, the row of cameras generally comprises at least two cameras, and the row of cameras are uniformly and symmetrically distributed by taking a central axis in the running direction of the strip steel as a central line. The angle at which each camera in a row photographs the strip is different. As shown in fig. 3, the arrow in fig. 3 represents the running direction of the strip, the broken line represents the central axis of the strip, and a row of cameras is disposed above the upper surface of the strip, and the row of cameras has four cameras, which are respectively denoted as a1, a2, a3 and a4. The four cameras are uniformly and symmetrically distributed by taking the central axis in the running direction of the strip steel as the central line, a1 and a4 are symmetrically distributed by the central line, and a2 and a3 are symmetrically distributed by the central line.
The cameras for shooting the edge images of the strip steel are different according to the widths of the strip steel. For example, as shown in fig. 3, if the strip width is too small, it is possible that the cameras a2 and a3 take an image of the edge of the strip. Then, it is necessary to determine a camera capable of capturing an edge image of the current strip from among cameras capturing the surface of the strip, that is, determine an edge camera, and further acquire the edge image.
The determination of the edge camera process is: obtaining edge parameters according to the width of the strip steel, the total shooting range of N cameras and the shooting range of each camera in the N cameras; n cameras are arranged at positions corresponding to the surfaces of the strip steel, and N is an integer greater than 2. According to the side parameters, a camera corresponding to the side parameters is determined from the N cameras, and is determined as a side camera.
Specifically, the side parameter B is obtained according to the formula (1).
B＝(C-W)/(2×D) (1)；
Wherein W is the width of the strip steel; c is the total shooting range of N cameras, namely the coverage area covered by the whole shooting of N cameras; d is the shooting range of a single camera.
When B is less than 1, the two outermost cameras in the N cameras are edge cameras;
when B is more than or equal to 1 and less than 2, the second two cameras in the row from the outermost two cameras in the N cameras are edge cameras;
when B is more than or equal to 2 and less than 3, the third two cameras in the row from the outermost two cameras in the N cameras are edge cameras; and so on.
For example, assume that a total of 10 cameras are disposed above the upper surface of the strip, and that the 10 cameras are uniformly and symmetrically distributed about the central axis of the strip in the running direction. And, these 10 cameras are sequentially denoted as W1, W2, W3, W4, W5, W6, W7, W8, W9, and W10 from left to right. When the obtained side parameter B < 1, W1 and W10 are side cameras. When B is more than or equal to 1 and less than 2, W2 and W9 are edge cameras. When B is more than or equal to 2 and less than 3, W3 and W8 are edge cameras. And so on.
After the edge camera is determined, the edge camera shoots the edge image of the strip steel, so that the edge image is obtained.
It should be noted that, since there are unstable regions or defective regions within 10 meters of the head and within 10 meters of the tail of the strip, the edge image captured by the edge camera is a captured edge image within a region from 10 meters outside the head to 10 meters outside the tail of the strip.
In this embodiment, the edge camera is determined according to the width of the strip steel, the total photographing range of the N cameras, and the photographing range of each of the N cameras. And the determined edge camera shoots to obtain an edge image of the strip steel, so that the characteristic of intelligently identifying the edge camera is reflected, the obtained edge image is reliable and accurate, and a basic guarantee is provided for detecting faults of the detector.
Step S102 is executed, and a designated area in the edge image is determined in the edge searching process of the edge image; the appointed area is determined according to the strip steel area and the non-strip steel area on the edge image.
Specifically, edge finding processing is performed on the edge image, namely, a strip steel edge is found in the edge image, wherein the edge finding processing comprises at least one of transverse edge finding processing and longitudinal edge finding processing. That is, the side image may be processed by a lateral edge finding process, or processed by a longitudinal edge finding process, or processed by a lateral edge finding process and then processed by a longitudinal edge finding process, which is not limited herein. The strip steel edge found through the transverse edge finding processing and the longitudinal edge finding processing has more accurate position and better effect compared with the strip steel edge found through the single-mode edge finding processing.
The process of carrying out transverse edge finding processing on the edge image comprises the following steps: and obtaining the current gray level of the current position in the process of carrying out line-by-line edge searching on the side image with the set step length and the set frequency. The setting step length is usually 3mm, and can be set according to actual requirements. The set frequency is a progressive frequency, usually 1mm, and can be set according to actual requirements. If the deviation between the current gray level and the historical gray level is larger than a first set gray level threshold value, determining the strip steel edge according to the current gray level and the historical gray level; the historical gray is the gray of the previous position, and the first set gray threshold is usually 20, or may be set according to the actual requirement. And obtaining a strip steel area and a non-strip steel area according to the strip steel edge.
Specifically, the side image is divided into P lines, with the upper left point of the side image as the origin or the upper right point of the side image as the origin. Wherein P is an integer not less than ten. And searching strip steel edges line by line in the left-to-right or right-to-left direction on the edge image from the original point with set step length and set frequency. In the process of searching the strip steel edge, the current gray level of the current position is obtained.
For example, as shown in fig. 4, a long dashed line on the edge image indicates a row, a thickened frame is a set step, a plurality of thickened frames are drawn to indicate positions where the set steps at different times are located, and a middle vertical line is a strip edge. The side image is divided into 50 lines, and the upper left point of the side image is used as the origin. From the origin, the strip edges are searched row by row with a set step length of 3mm, a set frequency of 1mm and a left-to-right direction. Taking the first row as an example, calculating the gray within 3mm from the origin at the last moment in the left-to-right direction; currently, 3mm step length at the previous moment is progressively increased by 1mm in the left-to-right direction, and gray scale within 3mm at the moment is calculated; at the next moment, the current step length of 3mm is increased by 1mm in the left-to-right direction, and the gray scale within 3mm at the next moment is calculated.
After the current gray level of the current position is obtained, the current gray level and the historical gray level need to be judged, wherein the historical gray level represents the gray level of the position at the last moment. When the deviation between the current gray level and the historical gray level is larger than a first set gray level threshold 20, selecting the position corresponding to the gray level with larger gray level value from the current gray level and the historical gray level as a strip steel edge, namely determining the position corresponding to the current gray level as the strip steel edge if the gray level value of the current gray level is larger than the gray level value of the historical gray level, and determining the position corresponding to the historical gray level as the strip steel edge if the gray level value of the current gray level is smaller than the gray level value of the historical gray level; or averaging the position corresponding to the current gray level and the position corresponding to the historical gray level, wherein the position corresponding to the average value is the strip steel edge.
The principle of determining the strip steel edge is as follows: the colors of the areas outside the strip steel are consistent, the areas are usually pure black areas with gray scales of 0-5, the gray scales of the strip steel areas are usually more than 120, and the gray scales are very different or have great deviation.
After the strip edges are determined, the strip areas and the non-strip areas can be distinguished according to the gray scales of different positions. For example, if the gray level of the A1 position is 1, the A1 position is in the non-strip region. If the gray level of the A2 position is 130, the A2 position is in the strip area.
In the embodiment, the strip steel edge is quickly found through the transverse edge finding process, and the method has the advantages of high precision, reliable and quick result and practicality, so that the detection efficiency of the detector is improved, and the detection stability is ensured.
The process of carrying out longitudinal edge finding processing on the edge image comprises the following steps: in the edge finding process on the side image column by column in pixel units, the pixel position of each pixel in each column of pixels is obtained. And if the deviation between the pixel position of a certain pixel in a certain column of pixels and the average pixel position of the rest pixels in the column of pixels is greater than a position deviation threshold value, removing the pixel. The deviation threshold is usually 2mm, and can be set according to actual requirements.
After removing the pixels, acquiring a first gray average value and a second gray average value; the first gray average value is the gray average value of a certain column of pixels, and the second gray average value is the gray average value of a column of pixels adjacent to the column of pixels. If the deviation of the first gray average value and the second gray average value is larger than the second set gray threshold value, determining the strip steel edge according to the first gray average value and the second gray average value. The second set gray threshold is usually 20, and may be set according to actual requirements. And obtaining a strip steel area and a non-strip steel area according to the strip steel edge.
Specifically, the edge image is divided into a plurality of pixels, and the pixels are arranged in a regular array, so that the pixel position of each pixel in each array of pixels is obtained. When the deviation of the pixel position of a certain pixel in a certain column of pixels and the average pixel position of the rest pixels in the column of pixels is larger than the position deviation threshold value, the pixel is removed, and the pixel is an abnormal pixel point. As shown in fig. 5, the small black dots in the graph are pixels, and the pixels are selected, and the deviation between the positions of the selected pixels and the average pixel positions of the rest pixels in the column of pixels is greater than the position deviation threshold, so that the pixels need to be removed.
After the abnormal pixel point is removed, the gray average value of each column of pixels is required to be calculated, and then the gray average value of two adjacent columns of pixels is judged. The average gray level of a certain column of pixels is referred to as a first average gray level, and the average gray level of a column of pixels adjacent to the column of pixels is referred to as a second average gray level. When the deviation between the first gray average value and the second gray average value is greater than a second set gray threshold value 20, selecting a row of pixels corresponding to the gray average value with larger numerical value from the first gray average value and the second gray average value as strip steel edges, namely determining a row of pixels corresponding to the first gray average value as strip steel edges if the first gray average value is greater than the second gray average value, and determining a row of pixels corresponding to the second gray average value as strip steel edges if the first gray average value is less than the second gray average value; or the position of a row of pixels corresponding to the first gray level average value is averaged with the position of a row of pixels corresponding to the second gray level average value, and the position corresponding to the average value is the strip steel edge.
After the strip edges are determined, the strip areas and the non-strip areas can be distinguished according to the gray average values of pixels in different columns. It should be noted that the principle of determining the edges of the strip steel is consistent with the principle of determining the edges of the strip steel in the transverse edge searching process.
In the embodiment, the strip steel edge is quickly found through longitudinal edge finding processing, so that the method has the advantages of high precision, reliable and quick result and practicality, the detection efficiency of the detector is improved, and the detection stability is guaranteed. Of course, the strip steel edge found by combining the transverse edge finding treatment with the longitudinal edge finding treatment has higher precision and reliability, and the detection efficiency of the detector is improved at any time.
After the strip edges, the strip areas and the non-strip areas are determined, the designated areas need to be screened from the non-strip areas, wherein the positions of the designated areas are close to the strip areas.
Specifically, the specified area may be set to a size first, then extracted from the non-strip area, and the size is set according to actual requirements. Or selecting the area with excellent presentation degree and stable effect from the non-strip steel area as the appointed area. To avoid interference from other factors in the non-strip area, such as interference from imaging by other equipment such as rollers, buttons or motors in the process, it is desirable to have the selected designated area located close to the strip area.
Then, step S103 is performed to obtain the angular deviation of the edge camera from the specified area.
Specifically, after the specified region is obtained, the gradation of the specified region, that is, the average gradation value of the specified region is obtained from the specified region. The angular deviation is obtained according to the gray scale of the designated area.
The gray scale of the designated area is according to the formula (2), and the angle deviation J can be obtained.
H＝a+b×J (2)；
Wherein H is the average gray value of the appointed area; a is a basic gray value, which represents the average gray value of a non-strip steel area when no deviation exists; b is the deviation slope. The basic gray values of the non-strip steel areas may also be different due to the different equipment of different production lines, so a and b may fluctuate within a certain range.
The principle of obtaining the angular deviation is: the gray scale of the non-strip area in the captured edge image increases due to the increased angular deviation of the edge camera. As the angular deviation increases progressively, the average gray value will approach the average gray value of the strip (typically 120) and will not continue to expand. In view of the fact that in the practical application field, the angle deviation of the camera is 30 degrees, the human eyes can observe the angle deviation very easily. Therefore, the failure detection method of the present embodiment counts only the deviation within 30 degrees. And the deviation within 0-30 degrees, the relation between the average gray value and the deviation angle is a relatively obvious linear relation, namely the formula (2).
In this embodiment, the angle deviation is obtained according to the average gray value of the designated area, and is obtained based on a reasonable principle, so that the obtained angle deviation is accurate and reliable, the angle deviation fault of the detector can be rapidly and efficiently analyzed, the detection efficiency of the detector is improved, and the working stability of the detector is ensured.
Finally, step S104 is executed, and if the angle deviation is not within the set angle range, it is determined that the edge camera has an angle deviation fault.
Specifically, if the angle deviation is not within the set angle range, it is determined that the edge camera has an angle deviation fault. The set angle range is set according to actual requirements. The reason for the angular deviation fault of the side camera may be that the side camera has a problem or that the photographing angle of the side camera has a deviation. If there is an angular deviation in each of the cameras in the row above the upper surface of the strip, it may be a problem with the light source of the detector.
If the angle deviation is within the set angle range, determining that the side camera has no angle deviation fault.
One or more technical solutions in the embodiments of the present application at least have the following technical effects or advantages:
in this embodiment, an edge camera is determined from the N cameras according to the width of the strip steel, and then an edge image is obtained by the edge camera. The method can quickly and efficiently determine the edge camera and obtain the accurate edge image. Then, edge finding processing is performed on the edge image. In the edge finding process, a designated area of the edge image is determined. Then, the angular deviation of the edge camera is obtained from the specified area. And finally, judging the angle deviation. If the angle deviation is not in the set angle range, determining that the angle deviation fault exists in the side camera. If the angle deviation is within the set angle range, determining that the side camera has no angle deviation fault. The fault detection method can rapidly and efficiently analyze the angle deviation fault of the detector, improve the detection efficiency of the detector and ensure the working stability of the detector. Therefore, the technical problem of low fault detection efficiency of the strip steel surface detector is solved.
Example two
Based on the same inventive concept, the second embodiment of the present application further provides a fault detection device of a strip steel surface detector, as shown in fig. 6, including:
a first obtaining module 301, configured to obtain an edge image of the strip steel from an edge camera; the edge cameras are determined from N cameras according to the width of the strip steel, and the N cameras are arranged at positions corresponding to the strip steel;
a first determining module 302, configured to determine a specified region in the edge image during edge searching processing on the edge image; wherein the specified area is determined according to a strip steel area and a non-strip steel area on the edge image;
a second obtaining module 303, configured to obtain an angular deviation of the edge camera according to the specified area;
and the second determining module 304 is configured to determine that the edge camera has an angle deviation fault if the angle deviation is not within a set angle range.
As an optional embodiment, the first determining module 302, configured to perform edge finding processing on the edge image, includes:
and carrying out edge searching processing on the edge image, wherein the edge searching processing comprises at least one of transverse edge searching processing and longitudinal edge searching processing.
As an optional embodiment, the performing the lateral edge finding processing on the edge image includes:
obtaining the current gray level of the current position in the process of carrying out line-by-line edge searching on the edge image with a set step length and a set frequency;
if the deviation between the current gray level and the historical gray level is larger than a first set gray level threshold value, determining a strip steel edge according to the current gray level and the historical gray level; wherein, the historical gray scale is the gray scale of the position at the last moment;
and obtaining the strip steel area and the non-strip steel area according to the strip steel edge.
As an optional embodiment, the performing the longitudinal edge finding processing on the edge image includes:
in the process of carrying out column-by-column edge searching on the edge image by taking pixels as units, obtaining the pixel position of each pixel in each column of pixels;
if the deviation between the pixel position of a certain pixel in a certain column of pixels and the average pixel position of the rest pixels in the column of pixels is greater than a position deviation threshold value, removing the pixel;
after removing the pixels, acquiring a first gray average value and a second gray average value; the first gray average value is the gray average value of a certain column of pixels, and the second gray average value is the gray average value of a column of pixels adjacent to the column of pixels;
if the deviation between the first gray average value and the second gray average value is larger than a second set gray threshold value, determining a strip steel edge according to the first gray average value and the second gray average value;
and obtaining the strip steel area and the non-strip steel area according to the strip steel edge.
As an alternative embodiment, the determining the designated area according to the strip area and the non-strip area on the edge image includes:
and screening the designated area from the non-strip steel area, wherein the designated area is positioned close to the strip steel area.
As an optional embodiment, the second obtaining module 303, configured to obtain, according to the specified area, an angular deviation of the edge camera, includes:
obtaining the gray scale of the designated area according to the designated area;
and obtaining the angle deviation according to the gray scale of the designated area.
As an alternative embodiment, the first obtaining module 301, configured to determine the edge camera from the N cameras according to the width of the strip, includes:
obtaining the edge parameters according to the width of the strip steel, the total shooting range of the N cameras and the shooting range of each camera in the N cameras; wherein N is an integer greater than 2;
determining a camera corresponding to the edge parameter from the N cameras according to the edge parameter, and determining the camera as the edge camera
Since the fault detection device of the strip steel surface detector described in this embodiment is a device for implementing the fault detection method of the strip steel surface detector in the first embodiment of the present application, based on the fault detection method of the strip steel surface detector described in the first embodiment of the present application, a person skilled in the art can understand the specific implementation of the fault detection device of the strip steel surface detector of this embodiment and various modifications thereof, so how to implement the fault detection device of the strip steel surface detector in the first embodiment of the present application will not be described in detail herein. The device used by those skilled in the art to implement the fault detection method of the medium-steel surface detector according to the first embodiment of the present application is within the scope of the present application.
Example III
Based on the same inventive concept, the third embodiment of the present application further provides a computer device, as shown in fig. 7, including a memory 404, a processor 402, and a computer program stored in the memory 404 and capable of running on the processor 402, where the processor 402 implements the steps of any one of the above fault detection methods of the strip surface detector when executing the program.
Where in FIG. 7 a bus architecture (represented by bus 400), bus 400 may comprise any number of interconnected buses and bridges, with bus 400 linking together various circuits, including one or more processors, represented by processor 402, and memory, represented by memory 404. Bus 400 may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., as are well known in the art and, therefore, will not be described further herein. Bus interface 406 provides an interface between bus 400 and receiver 401 and transmitter 403. The receiver 401 and the transmitter 403 may be the same element, i.e. a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 402 is responsible for managing the bus 400 and general processing, while the memory 404 may be used to store data used by the processor 402 in performing operations.
Example IV
Based on the same inventive concept, the fourth embodiment of the present application further provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any one of the fault detection methods of the strip steel surface detector according to the previous embodiment.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application 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. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (9)
1. The fault detection method of the strip steel surface detector is characterized by comprising the following steps of:
obtaining an edge image of the strip steel from an edge camera; the edge cameras are determined from N cameras according to the width of the strip steel, and the N cameras are arranged at positions corresponding to the strip steel;
determining a designated area in the edge image in the edge searching process of the edge image; wherein the specified area is determined according to a strip steel area and a non-strip steel area on the edge image;
obtaining the angle deviation of the side camera according to the designated area; calculating the angle deviation of the side camera according to the formula h=a+b×j, wherein H is an average gray value of the designated area, a is a basic gray value, b is a deviation slope, and J is the angle deviation of the side camera; when the angle deviation is gradually increased, the average gray value of the designated area gradually approaches to the average gray value of the strip steel;
and if the angle deviation is not in the set angle range, determining that the angle deviation fault exists in the side camera.
2. The method of claim 1, wherein said edge finding processing of said edge image comprises:
and carrying out edge searching processing on the edge image, wherein the edge searching processing comprises at least one of transverse edge searching processing and longitudinal edge searching processing.
3. The method of claim 2, wherein said performing said lateral edge finding process on said edge image comprises:
obtaining the current gray level of the current position in the process of carrying out line-by-line edge searching on the edge image with a set step length and a set frequency;
if the deviation between the current gray level and the historical gray level is larger than a first set gray level threshold value, determining a strip steel edge according to the current gray level and the historical gray level; wherein, the historical gray scale is the gray scale of the position at the last moment;
and obtaining the strip steel area and the non-strip steel area according to the strip steel edge.
4. The method of claim 2, wherein said performing said longitudinal edge finding process on said edge image comprises:
in the process of carrying out column-by-column edge searching on the edge image by taking pixels as units, obtaining the pixel position of each pixel in each column of pixels;
if the deviation between the pixel position of a certain pixel in a certain column of pixels and the average pixel position of the rest pixels in the column of pixels is greater than a position deviation threshold value, removing the pixel;
after removing the pixels, acquiring a first gray average value and a second gray average value; the first gray average value is the gray average value of a certain column of pixels, and the second gray average value is the gray average value of a column of pixels adjacent to the column of pixels;
if the deviation between the first gray average value and the second gray average value is larger than a second set gray threshold value, determining a strip steel edge according to the first gray average value and the second gray average value;
and obtaining the strip steel area and the non-strip steel area according to the strip steel edge.
5. The method of claim 1, wherein said determining the designated area from the strip and non-strip areas on the edge image comprises:
and screening the designated area from the non-strip steel area, wherein the designated area is positioned close to the strip steel area.
6. The method of claim 1, wherein said determining said edge camera from N cameras based on the width of the strip comprises:
obtaining the edge parameters according to the width of the strip steel, the total shooting range of the N cameras and the shooting range of each camera in the N cameras; wherein N is an integer greater than 2;
and determining a camera corresponding to the side parameter from the N cameras according to the side parameter, and determining the camera as the side camera.
7. A fault detection device for a strip steel surface detector, comprising:
the first obtaining module is used for obtaining an edge image of the strip steel from the edge camera; the edge cameras are determined from N cameras according to the width of the strip steel, and the N cameras are arranged at positions corresponding to the strip steel;
the first determining module is used for determining a designated area in the edge image in the edge searching process of the edge image; wherein the specified area is determined according to a strip steel area and a non-strip steel area on the edge image;
the second obtaining module is used for obtaining the angle deviation of the side camera according to the designated area; calculating the angle deviation of the side camera according to the formula h=a+b×j, wherein H is an average gray value of the designated area, a is a basic gray value, b is a deviation slope, and J is the angle deviation of the side camera; when the angle deviation is gradually increased, the average gray value of the designated area gradually approaches to the average gray value of the strip steel;
and the second determining module is used for determining that the angle deviation fault exists in the side camera if the angle deviation is not in the set angle range.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method steps of any of claims 1-6 when the program is executed.
9. A computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor realizes the method steps of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111077980.1A CN113866183B (en) | 2021-09-15 | 2021-09-15 | Fault detection method and device for strip steel surface detector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111077980.1A CN113866183B (en) | 2021-09-15 | 2021-09-15 | Fault detection method and device for strip steel surface detector |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113866183A CN113866183A (en) | 2021-12-31 |
| CN113866183B true CN113866183B (en) | 2023-11-14 |
Family
ID=78995877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111077980.1A Active CN113866183B (en) | 2021-09-15 | 2021-09-15 | Fault detection method and device for strip steel surface detector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113866183B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009008502A (en) * | 2007-06-27 | 2009-01-15 | Omron Corp | Data registering method for surface state inspection and surface state inspection device |
| JP2010112846A (en) * | 2008-11-07 | 2010-05-20 | Jfe Steel Corp | Method and apparatus for adjusting surface inspecting device |
| CN102319743A (en) * | 2011-05-24 | 2012-01-18 | 重庆大学 | Band steel deflection and floating quantity laser scanning detection method and deflection correction system |
| CN103357672A (en) * | 2012-03-30 | 2013-10-23 | 鞍钢股份有限公司 | Online strip steel boundary detection method |
| CN103834796A (en) * | 2012-11-23 | 2014-06-04 | 宝山钢铁股份有限公司 | Method for online recognition of deviation of strip steel in furnace |
| CN104985002A (en) * | 2015-05-27 | 2015-10-21 | 北京首钢股份有限公司 | Hot rolled strip steel edge defect alarm method and apparatus |
| CN105414206A (en) * | 2014-09-19 | 2016-03-23 | 鞍钢股份有限公司 | On-line rapid positioning method for cold-rolling strip steel edge |
| CN106546598A (en) * | 2016-10-28 | 2017-03-29 | 鞍钢未来钢铁研究院 | Belt steel surface detecting system light source self-adaptation control method |
| JP2017211200A (en) * | 2016-05-23 | 2017-11-30 | 株式会社デンソー | Camera calibrating device, and camera calibrating method |
| CN108364311A (en) * | 2018-01-29 | 2018-08-03 | 深圳市亿图视觉自动化技术有限公司 | A kind of metal parts automatic positioning method and terminal device |
| CN112150455A (en) * | 2020-09-30 | 2020-12-29 | 王海 | Method and system for judging visual angle deviation of photovoltaic camera based on artificial intelligence |
| CN112801966A (en) * | 2021-01-21 | 2021-05-14 | 北京科技大学设计研究院有限公司 | Online detection method for hot-rolled strip steel deviation |
-
2021
- 2021-09-15 CN CN202111077980.1A patent/CN113866183B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009008502A (en) * | 2007-06-27 | 2009-01-15 | Omron Corp | Data registering method for surface state inspection and surface state inspection device |
| JP2010112846A (en) * | 2008-11-07 | 2010-05-20 | Jfe Steel Corp | Method and apparatus for adjusting surface inspecting device |
| CN102319743A (en) * | 2011-05-24 | 2012-01-18 | 重庆大学 | Band steel deflection and floating quantity laser scanning detection method and deflection correction system |
| CN103357672A (en) * | 2012-03-30 | 2013-10-23 | 鞍钢股份有限公司 | Online strip steel boundary detection method |
| CN103834796A (en) * | 2012-11-23 | 2014-06-04 | 宝山钢铁股份有限公司 | Method for online recognition of deviation of strip steel in furnace |
| CN105414206A (en) * | 2014-09-19 | 2016-03-23 | 鞍钢股份有限公司 | On-line rapid positioning method for cold-rolling strip steel edge |
| CN104985002A (en) * | 2015-05-27 | 2015-10-21 | 北京首钢股份有限公司 | Hot rolled strip steel edge defect alarm method and apparatus |
| JP2017211200A (en) * | 2016-05-23 | 2017-11-30 | 株式会社デンソー | Camera calibrating device, and camera calibrating method |
| CN106546598A (en) * | 2016-10-28 | 2017-03-29 | 鞍钢未来钢铁研究院 | Belt steel surface detecting system light source self-adaptation control method |
| CN108364311A (en) * | 2018-01-29 | 2018-08-03 | 深圳市亿图视觉自动化技术有限公司 | A kind of metal parts automatic positioning method and terminal device |
| CN112150455A (en) * | 2020-09-30 | 2020-12-29 | 王海 | Method and system for judging visual angle deviation of photovoltaic camera based on artificial intelligence |
| CN112801966A (en) * | 2021-01-21 | 2021-05-14 | 北京科技大学设计研究院有限公司 | Online detection method for hot-rolled strip steel deviation |
Non-Patent Citations (2)
| Title |
|---|
| How atmospheric haze affects the efficiency of wide-angle airborne television cameras when ground objects are being observed;Ovsyannikov etc;optical technology;第84卷(第3期);1-6 * |
| 基于图像处理的带钢表面缺陷检测改进算法的研究;孙光民;刘鹏;李子博;;软件工程(第04期);1-4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113866183A (en) | 2021-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10699400B2 (en) | Image processing apparatus, image processing method, and storage medium | |
| KR100744212B1 (en) | Method and system for detecting defects on a printed circuit board | |
| KR102301437B1 (en) | Vision inspection apparatus and method of detecting mura thereof | |
| CN113838038B (en) | Carbon fiber cloth cover defect detection method and device, electronic equipment and storage medium | |
| US11928805B2 (en) | Information processing apparatus, information processing method, and storage medium for defect inspection and detection | |
| CN113284154B (en) | Steel coil end face image segmentation method and device and electronic equipment | |
| CN115953373B (en) | Glass defect detection method, device, electronic equipment and storage medium | |
| JP5440162B2 (en) | White spot detection device, image forming apparatus, and white spot detection program | |
| CN113362238A (en) | Test image processing method and device, electronic equipment and storage medium | |
| CN115535525A (en) | Conveyor belt longitudinal tearing detection system and method based on image matching | |
| CN113866183B (en) | Fault detection method and device for strip steel surface detector | |
| Hashmi et al. | Computer-vision based visual inspection and crack detection of railroad tracks | |
| CN115861315B (en) | Defect detection method and device | |
| JP6007552B2 (en) | Tire X-ray inspection determination method | |
| CN113256607B (en) | Defect detection method and device | |
| CN110634124A (en) | Method and equipment for area detection | |
| JP4346379B2 (en) | Defect inspection method | |
| CN104935837B (en) | For optical imagery pointing device and the image processing method of optical video equipment | |
| US11120541B2 (en) | Determination device and determining method thereof | |
| EP1453299A3 (en) | Image processing method and apparatus for recovering from reading faults | |
| JP2023047003A (en) | Machine learning system, learning data collection method and learning data collection program | |
| JP6173088B2 (en) | Inspection device, inspection method, program, and recording medium | |
| WO2015159352A1 (en) | Web inspection device, web inspection method, and web inspection program | |
| JPH06103968B2 (en) | Image processor for overhead line inspection | |
| JP2008116380A (en) | Defect detection method, defect detector, and defect detection program |
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 |