CN113281341A - Detection optimization method of double-sensor surface quality detection system of hot-dip galvanized strip steel - Google Patents
Detection optimization method of double-sensor surface quality detection system of hot-dip galvanized strip steel Download PDFInfo
- Publication number
- CN113281341A CN113281341A CN202110419699.5A CN202110419699A CN113281341A CN 113281341 A CN113281341 A CN 113281341A CN 202110419699 A CN202110419699 A CN 202110419699A CN 113281341 A CN113281341 A CN 113281341A
- Authority
- CN
- China
- Prior art keywords
- detection
- linear array
- value
- light source
- array system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G01N21/8806—Specially adapted optical and illumination features
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8835—Adjustable illumination, e.g. software adjustable screen
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/06—Illumination; Optics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/06—Illumination; Optics
- G01N2201/062—LED's
Landscapes
- 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)
- Coating With Molten Metal (AREA)
Abstract
A detection optimization method of a dual-sensor surface quality detection system of hot-dip galvanized strip steel comprises the following steps: pre-dividing all varieties of hot-dip galvanized strip steel into a plurality of linear array system detection groups and planar array system detection groups; setting different parameters for each detection group; observing the actual image gray value and the actual light source power value of each detection group; when the actual image gray values and the actual light source power values of all varieties in the detection group are in the set range, the parameter setting of the detection group is reasonable; otherwise, adjusting the corresponding camera gain value, when the section reaches the set upper limit or lower limit, part of varieties are not in the set range, and after adjusting the corresponding camera aperture, the corresponding camera aperture is adjusted until the varieties reach the set range; solidifying the camera aperture value and the camera gain value as production operation parameters; and after the parameters of all the detection groups are optimized, curing the results of all the linear array system detection groups and the linear array system detection groups. The invention ensures that the LED light source has longer service life.
Description
Technical Field
The invention relates to a detection group of a hot-dip galvanized strip steel double-sensor surface detection system. In particular to a detection optimization method of a dual-sensor surface quality detection system of hot-dip galvanized strip steel.
Background
With the continuous upgrading of products in the manufacturing industry of China, the requirements of each manufacturing industry on cold-rolled hot zinc steel plates are continuously increased, higher and higher requirements are provided for the surface quality of the cold-rolled hot zinc steel plates, and particularly, in the field of automobile manufacturing, each manufacturer provides very strict requirements for the surface quality of an automobile outer plate. Therefore, hot galvanizing strip steel production enterprises need to do strip steel surface detection work while optimizing the production process so as to ensure that qualified products are provided.
In the continuous production process of hot-dip galvanized steel strips, surface quality detection is usually carried out by adopting methods such as manual visual sampling detection, frequency flash detection and the like. However, the problems of high running speed of the strip steel, various surface defects, small defects exceeding the resolution of human eyes and the like exist, so that the manual method can only reliably detect a large number of obvious defects, and the condition of missing detection is easy to occur on more tiny and accidental defects, thereby not only being beneficial to improving the production process, but also causing the flow of unqualified products to customers, causing economic loss and influencing the reputation of enterprises.
With the rapid development of the CCD imaging technology and the image recognition technology and the continuous progress of the artificial intelligence algorithm, the strip steel surface detection system based on the machine vision technology is rapidly developed and is adopted by more and more steel production to assist the detection of the strip steel surface quality, and a very ideal effect is obtained. The surface quality detection system consists of a sensor system and detection and classification software. The sensor system comprises a light source, a camera, an electrical cabinet, a detection server, a debugging terminal and a detection terminal, and the most advanced technology at present is to simultaneously apply the light source of the linear array camera and the light source of the area array camera. The linear array light source and the area array light source have respective characteristics, and can have different identification capabilities for defects with different strip steel texture structures and different characteristics. The area array light source has good universality, the detection rate of two-dimensional color difference defects with large gray value difference can exceed 90%, but the detection rate of three-dimensional defects is low; the linear array light source can detect the three-dimensional defects more than 90%, but has poor effect on detecting the color difference defects. Therefore, the linear array light source and the area array light source are integrated into the same set of surface quality detection system, so that the inspection function can be more comprehensively realized, and the defect detection rate is improved.
The light source of the linear array camera is a parallel white LED light source, the light source of the area array camera is an invisible infrared LED light source, and the service life of the LED light source can reach about 10 years under the optimal condition. The power value of the light source of the surface detection system can be automatically adjusted along with the color shading degree of the upper surface and the lower surface of the strip steel, so that the image has reasonable and stable gray value. However, due to the difference between the types and specifications of hot-dip galvanized steel strips, the degree of surface color shading is greatly different, if detection groups are not distinguished, the same camera software and hardware parameters are adopted, and the automatic adjustment function of the light source is only relied on, all types are difficult to ensure to have stable image gray values, and if the surface color of the steel strips is too dark, the LED light source can be caused to work under high power or even full power for a long time, and the service life of the LED light source can be greatly shortened. Therefore, all hot-dip galvanized steel strip varieties are divided into a plurality of linear array system detection groups and a plurality of linear array system detection groups according to different surface color darkness degrees, quality requirements and light source types, different camera software and hardware parameters are set for the linear array system detection groups, the stability of the gray value of an output image of the system can be better ensured, and the service life of the LED light source can be well prolonged.
Disclosure of Invention
The invention aims to solve the technical problem of providing an optimization method capable of ensuring that a hot-dip galvanized strip steel double-sensor surface detection system can output excellent and stable image gray values and an LED light source reaches an ideal service life.
The technical scheme adopted by the invention is as follows: a method for optimizing classification groups of a surface defect detection system based on an area array light source comprises the following steps:
1) pre-dividing all continuous annealing plates with different brands into a plurality of classification groups according to the surface color difference state and the total brightness of the continuous annealing plates;
2) setting parameters of different classification groups in sequence, wherein the parameters comprise a defect image target gray value range, a target light source power value range, a gain value range of each mesa array light source camera and an aperture value of each mesa array light source camera;
3) respectively observing the actual gray value and the actual light source power value of the defect image shot by the surface defect detection system aiming at each mark in each classification group;
4) judging whether the actual gray value and the actual light source power value of the defect image of each grade in each classification group are within the range of the target gray value and the target light source power value of the defect image set in the step 2);
when the actual gray values and the actual light source power values of the defect images of all the marks in the classification group are within the set range, the parameter setting of the classification group is reasonable, and the step 7) is carried out;
when the actual gray values of the defect images of all the marks in the classification group are within the set range, the actual light source power values of part of the marks are within the set range, and the actual light source power values of part of the marks are not within the set range, entering the step 5);
when the actual gray values of the defect images of the partial marks in the classification group are within the set range and the actual gray values of the defect images of the partial marks are not within the set range, entering the step 6);
5) adjusting the gain value of an area array light source camera in the surface defect detection system until the actual gray values and the actual light source power values of defect images of all brands in the classification group reach the set range, entering the step 7), adjusting the aperture of the area array light source camera when the gain value of the area array light source camera of a certain table is adjusted to the set upper limit or lower limit and the actual light source power values of part brands are not in the set range, and then returning to the step 3);
6) for the marks with the actual gray value of the defect image smaller than the set lower limit of the target gray value of the defect image, increasing the gain value of the corresponding area array light source camera in the surface defect detection system to improve the actual gray value of the defect image until the actual gray value and the actual light source power value of the defect image of all marks in the classification group reach the set range; when the gain value of the area array light source camera is increased to the upper limit and the actual gray value of the defect image still does not reach the set range, increasing the aperture value of the area array light source camera and returning to the step 3); for the marks with the actual gray value of the defect image larger than the target gray value upper limit of the defect image, reducing the actual gray value of the defect image by reducing the corresponding area array light source camera gain value in the surface defect detection system until the actual gray value of the defect image and the actual light source power value of all marks in the classification group reach the set range; when the gain value of the area array light source camera is reduced to the lower limit, the actual gray value of the defect image still does not reach the set range, the aperture value of the area array light source camera is reduced, and the step 3 is returned;
7) solidifying the aperture value and the gain value of each table array light source camera of the classification group and taking the aperture value and the gain value as production operation parameters;
8) and after the parameters of all classification groups are optimized, curing the classification result.
The detection optimization method of the dual-sensor surface quality detection system of the hot-dip galvanized strip steel has the advantages that the cold-dip galvanized strip steel is divided into 6 linear array system detection groups and 6 planar array system detection groups according to the gray level and quality requirements of the upper surface and the lower surface of each variety of the hot-dip galvanized strip steel and the difference of the light source types of the dual-sensor surface quality detection systems. The method can ensure that the image shot by the double-sensor surface quality detection system has excellent and stable image gray value, and can ensure that the power of the light source works within a reasonable range, thereby being beneficial to the detection of the double-sensor surface quality detection system on the surface defects of the hot-dip galvanized strip steel, and effectively ensuring that the LED light source has longer service life.
Drawings
FIG. 1 is a detection grouping method of the detection optimization method of the dual-sensor surface quality detection system of the hot-dip galvanized strip steel of the invention;
FIG. 2 is a flow chart of a detection optimization method of the dual-sensor surface quality detection system for hot-dip galvanized steel strip according to the invention;
FIG. 3 is a diagram showing the detection effect of the "area array S4S 3" detection group and the "line array S4S 3" detection group on the same warping defect;
FIG. 4 is a diagram showing the detection effect of the area array HQ detection group and the line array HQ detection group on the same scratch defect.
Detailed Description
The following describes in detail a detection optimization method of the dual-sensor surface quality detection system for hot-dip galvanized steel strip according to the present invention with reference to the following embodiments and accompanying drawings.
As shown in fig. 1 and 2, the detection optimization method of the dual-sensor surface quality detection system for hot-dip galvanized strip steel of the invention is characterized by comprising the following steps:
1) pre-dividing all varieties into a plurality of linear array system detection groups and a plurality of linear array system detection groups according to the gray degree and the quality requirements of the upper and lower surfaces of the hot-dip galvanized strip steel and the difference of the light source types of the double-sensor surface quality detection system;
the method is characterized in that all varieties are pre-divided into a plurality of linear array system detection groups and a planar array system detection group, hot-dip galvanized strip steel is pre-divided into six detection groups, and the detection groups are divided into the following detection groups according to the gray level of surface color and the quality requirements from high to low in sequence: thick plates, DP steel, HQ, S5, S4S3, S3A; each detection group is divided into a linear array system detection group and an area array system detection group according to different light source types; the decision priority of each detection group is: HQ > S5 > DP > plank > S4S3 > S3A.
2) Setting different parameters including the range of image target gray value, the range of target light source power value, the range of camera gain value and the camera aperture value for each linear array system detection group and each linear array system detection group respectively;
the camera aperture values corresponding to the linear array system detection group and the planar array system detection group are both F5.6, and the camera gain value setting ranges corresponding to the linear array system detection group and the planar array system detection group are both 128-1024; the range of target gray values of images of the linear array system detection group is 90-110%, the range of target gray values of images of the area array system detection group is 70-90%, and the power value range of the target light source is 65-85%.
3) Respectively observing the actual image gray value and the actual light source power value of the linear array system detection group and the linear array system detection group shot by the double-sensor surface quality detection system for each variety;
4) judging whether the actual image gray value and the actual light source power value of each variety in the linear array system detection group and the linear array system detection group are within the range set in the step 2);
when the actual image gray values and the actual light source power values of all the varieties in the linear array system detection group and the planar array system detection group are within the set range, the parameter setting of the linear array system detection group and the planar array system detection group is reasonable, and the step 7 is carried out);
when the actual image gray values of all varieties in the linear array system detection group or the area array system detection group are in the set range, the actual light source power values of part of varieties are in the set range, and the actual light source power values of part of varieties are not in the set range, entering the step 5);
when the gray values of the actual images of part of varieties in the linear array system detection group or the area array system detection group are within the set range, and the gray values of the actual images of part of varieties are not within the set range, entering the step 6);
5) adjusting the camera gain value of a linear array detection system or an area array detection system corresponding to an image in a double-sensor surface quality detection system of the hot-dip galvanized strip steel until the actual image gray values and the actual light source power values of all varieties in a linear array system detection group and an area array system detection group reach a set range, entering a step 7), and returning to the step 4 after adjusting the camera aperture of the linear array detection system or the area array detection system when the camera gain value of the linear array detection system or the area array detection system is adjusted to a set upper limit or a set lower limit and the actual light source power values of part of varieties are not in the set range; wherein the content of the first and second substances,
when the actual light source power value of a certain image in the linear array system detection group or the area array system detection group is less than 65%, the actual light source power value is increased to reach a set range by reducing the corresponding camera gain value, and when the corresponding camera gain value is reduced to the lower limit value 128, the actual light source power value is still less than 65%, the camera aperture value of the corresponding camera is reduced to f8, so that the actual image gray values and the actual light source power values of all kinds of images in the linear array system detection group or the area array system detection group reach the set range.
When the actual light source power value of a certain image in the linear array system detection group or the area array system detection group is larger than 85%, the actual light source power value is reduced to reach a set range by increasing the corresponding camera gain value, and when the camera gain value of the corresponding camera is increased to 1024, the actual light source power value is still larger than 85%, the camera aperture value of the camera is increased to f4, so that the actual image gray values and the actual light source power values of all kinds of images in the linear array system detection group or the area array system detection group reach the set range.
6) For varieties smaller than the lower limit of the image target gray value, increasing the camera gain value of a linear array detection system or an area array detection system in a double-sensor surface quality detection system of the hot-dip galvanized strip steel to improve the actual image gray value until the actual image gray values and the actual light source power values of all varieties in the linear array system detection group and the area array system detection group reach the set range; when the gain value of the camera of the linear array detection system or the area array detection system corresponding to the image is increased to the upper limit and the actual image gray value still does not reach the set range, increasing the camera aperture value of the linear array detection system or the area array detection system, and returning to the step 4); for steel grades larger than the upper limit of the image target gray value, reducing the actual image gray value by adjusting the camera gain value of a corresponding linear array detection system or area array detection system in a double-sensor surface quality detection system of the hot-dip galvanized strip steel until the actual image gray values and the actual light source power values of all varieties in the linear array system detection group and the area array system detection group reach the set range; when the gain value of the camera of the corresponding linear array detection system or area array detection system is reduced to the lower limit, and the actual image gray value still does not reach the set range, reducing the aperture value of the camera of the linear array detection system or area array detection system, and returning to the step 4);
7) solidifying the camera aperture value and the camera gain value corresponding to the linear array system detection group or the area array system detection group and taking the camera aperture value and the camera gain value as production operation parameters;
8) and after the parameters of all the linear array system detection sets and the parameters of all the linear array system detection sets are optimized, the results of all the linear array system detection sets and all the linear array system detection sets are solidified.
Examples are given below:
example 1
The method for optimizing the parameters of an area array S4S3 detection group and a linear array S4S3 detection group in the detection optimization method of the hot-dip galvanized strip steel double-sensor surface quality detection system comprises the following steps:
1) setting the aperture values of 1# -20 # cameras corresponding to the detection group of the area array S4S3 to be F5.6, and setting the gain values of the cameras to be [600, 600, 600, 600, 600, 600, 600, 600, 600, 600, 600] respectively; setting the aperture value of the camera from 1# to 20# corresponding to the detection group of the linear array S4S3 to F5.6, and preliminarily setting the gain values of the camera to [300, 300, 300, 300, 300, 300 ];
2) continuously observing the actual image gray value and the actual light source power value corresponding to each variety in an area array S4S3 shot by a double-sensor surface quality detection system of the hot-dip galvanized strip steel, judging whether the actual image gray value of each variety is within a set range of 90-110, and simultaneously judging whether the actual light source power value of each variety is within a set range of 65-85%; continuously observing the actual image gray value and the actual light source power value corresponding to each variety in a linear array S4S3 shot by a double-sensor surface quality detection system of the hot-dip galvanized strip steel, judging whether the actual image gray value of each variety is within the set range of 70-90, and simultaneously judging whether the actual light source power value of each variety is within the set range of 65-85%;
3) through observation of images of all varieties in the "area array S4S 3", the actual image gray-scale values of some varieties are higher than the upper limit 110. Continuously observing whether the actual image gray value and the actual light source power value of each variety are in the set range or not by adjusting the gain value of a camera corresponding to a corresponding image in a double-sensor surface quality detection system of the hot-dip galvanized strip steel, and if not, continuously adjusting in the above manner until the actual image gray value and the actual light source power value of each variety are in the set range; by observing the images of all varieties in the "line S4S 3", the gray values of the actual images of a part of varieties in the "line S4S 3" are higher than the upper limit 90. Continuously observing whether the actual image gray value and the actual light source power value of each variety are in the set range or not by adjusting the gain value of a camera corresponding to the image in the double-sensor surface quality detection system of the hot-dip galvanized strip steel, and if not, continuously adjusting in the manner until the actual image gray value and the actual light source power value of each variety are in the set range;
4) when the aperture value of the camera 1# -20 # corresponding to the area array S4S3 is F5.6, and the gain values are respectively set to [411, 409, 422, 425, 437, 430, 428, 426, 420, 416, 418, 419, 422, 421, 427, 433, 428, 427, 419, 415], the actual image gray values of all varieties in the area array S4S3 are within the set range of 90-110, and the actual light source power values are within the set range of 65-85%; when the aperture value of the 1# -6 # camera corresponding to the "line S4S 3" is F5.6, and the gain values are respectively set as [198, 213, 220, 218, 209, 196], the actual image gray-scale values of all the varieties in the "line S4S 3" are all within the set range of 70-90, and the actual light source power values are all within the set range of 65-85%.
5) The "area array S4S 3" detection group parameters are saved, and the corresponding 1# -20 # camera aperture values F5.6 are saved, the gain values being [411, 409, 422, 425, 437, 430, 428, 426, 420, 416, 418, 419, 422, 421, 427, 433, 428, 427, 419, 415], respectively. And saving the detection group parameters of the linear array S4S3, and saving corresponding aperture values F5.6 of the 1# -6 # camera, wherein the gain values are [198, 213, 220, 218, 209 and 196], respectively.
The detection effect graphs of the area array S4S3 detection group and the line array S4S3 detection group on the same warping defect are shown in FIG. 3.
Example 2
Aiming at the parameter optimization of an area array DP detection group and a linear array DP detection group in the detection optimization method of the hot-dip galvanized strip steel double-sensor surface quality detection system, the method comprises the following steps:
1) setting the aperture value of a camera from 1# to 20# corresponding to the detection group of the area array DP to F5.6, and setting the gain value of the camera to [400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400, 400] respectively; simultaneously preliminarily setting the aperture value of a 1# -6 # camera corresponding to the linear array DP detection group to be F5.6, and preliminarily setting the gain value of the camera to be [200, 200, 200, 200, 200, 200] respectively;
2) continuously observing the actual image gray value and the actual light source power value corresponding to each variety image in the 'area array DP' shot by a double-sensor surface quality detection system of the hot-dip galvanized strip steel, judging whether the actual image gray value of each variety is within the set range of 90-110, and simultaneously judging whether the actual light source power value of each variety is within the set range of 65-85%; continuously observing the actual image gray value and the actual light source power value corresponding to each variety in the linear array DP shot by a double-sensor surface quality detection system of the hot-dip galvanized strip steel, judging whether the actual image gray value of each variety is within the set range of 70-90, and simultaneously judging whether the actual light source power value of each variety image is within the set range of 65% -85%;
3) by observing the images of all varieties in the area array DP, the gray values of the actual images of all varieties in the area array DP are within the set range, and the actual light source power value of part of varieties is higher than the set upper limit of the light source power value by 85 percent. Continuously observing whether the gray value of the actual image of each variety and the power value of the actual light source are in the set range or not by adjusting the gain value of the camera corresponding to the corresponding image in the double-sensor surface quality detection system of the hot-dip galvanized strip steel, and if not, continuously adjusting in the above way until the gray value of the actual image of each variety and the power value of the actual light source are in the set range; by observing the images of all varieties in the linear array DP, the gray values of the actual images of all varieties in the linear array DP are within the set range, and the power value of the actual light source of part of varieties is higher than the set upper limit of the power value of the light source by 85%. Continuously observing whether the gray value of the actual image of each variety and the power value of the actual light source are in the set range or not by adjusting the gain value of the camera corresponding to the corresponding image in the double-sensor surface quality detection system of the hot-dip galvanized strip steel, and if not, continuously adjusting in the above way until the gray value of the actual image of each variety and the power value of the actual light source are in the set range;
4) when the aperture value of the 1# -20 # camera corresponding to the area array DP is F5.6, the gain value is respectively set as [588, 591, 596, 603, 609, 618, 626, 633, 639, 636, 638, 636, 629, 624, 618, 614, 606, 600, 593, 587], "the actual image gray values of all varieties in the area array DP" are all within the set range of 90-110, and the actual light source power is all within the set range of 65-85%; when the aperture value of the 1# -6 # camera corresponding to the linear array DP is F5.6, the gain values are respectively set to [677, 698, 696, 689, 676, 669], the actual image gray values of all varieties in the linear array DP are all within the set range of 70-90, and the actual light source power is all within the set range of 65% -85%.
5) The "area array DP" detection group parameters are saved, and corresponding 1# -20 # camera aperture values F5.6 are saved, and the gain values are [588, 591, 596, 603, 609, 618, 626, 633, 639, 636, 638, 636, 629, 624, 618, 614, 606, 600, 593, 587], respectively. And saving the linear array DP detection group parameters, and saving corresponding aperture values F5.6 of the 1# -6 # camera, wherein the gain values are [677, 698, 696, 689, 676, 669], respectively.
The detection effect graphs of the area array HQ detection group and the linear array HQ detection group for the same scratch defect are shown in FIG. 4.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (6)
1. A detection optimization method of a dual-sensor surface quality detection system of hot-dip galvanized strip steel is characterized by comprising the following steps:
1) pre-dividing all varieties into a plurality of linear array system detection groups and a plurality of linear array system detection groups according to the gray degree and the quality requirements of the upper and lower surfaces of the hot-dip galvanized strip steel and the difference of the light source types of the double-sensor surface quality detection system;
2) setting different parameters including the range of image target gray value, the range of target light source power value, the range of camera gain value and the camera aperture value for each linear array system detection group and each linear array system detection group respectively;
3) respectively observing the actual image gray value and the actual light source power value of the linear array system detection group and the linear array system detection group shot by the double-sensor surface quality detection system for each variety;
4) judging whether the actual image gray value and the actual light source power value of each variety in the linear array system detection group and the linear array system detection group are within the range set in the step 2);
when the actual image gray values and the actual light source power values of all the varieties in the linear array system detection group and the planar array system detection group are within the set range, the parameter setting of the linear array system detection group and the planar array system detection group is reasonable, and the step 7 is carried out);
when the actual image gray values of all varieties in the linear array system detection group or the area array system detection group are in the set range, the actual light source power values of part of varieties are in the set range, and the actual light source power values of part of varieties are not in the set range, entering the step 5);
when the gray values of the actual images of part of varieties in the linear array system detection group or the area array system detection group are within the set range, and the gray values of the actual images of part of varieties are not within the set range, entering the step 6);
5) adjusting the camera gain value of a linear array detection system or an area array detection system corresponding to an image in a double-sensor surface quality detection system of the hot-dip galvanized strip steel until the actual image gray values and the actual light source power values of all varieties in a linear array system detection group and an area array system detection group reach a set range, entering a step 7), and returning to the step 4 after adjusting the camera aperture of the linear array detection system or the area array detection system when the camera gain value of the linear array detection system or the area array detection system is adjusted to a set upper limit or a set lower limit and the actual light source power values of part of varieties are not in the set range;
6) for varieties smaller than the lower limit of the image target gray value, increasing the camera gain value of a linear array detection system or an area array detection system in a double-sensor surface quality detection system of the hot-dip galvanized strip steel to improve the actual image gray value until the actual image gray values and the actual light source power values of all varieties in the linear array system detection group and the area array system detection group reach the set range; when the gain value of the camera of the linear array detection system or the area array detection system corresponding to the image is increased to the upper limit and the actual image gray value still does not reach the set range, increasing the camera aperture value of the linear array detection system or the area array detection system, and returning to the step 4); for steel grades larger than the upper limit of the image target gray value, reducing the actual image gray value by adjusting the camera gain value of a corresponding linear array detection system or area array detection system in a double-sensor surface quality detection system of the hot-dip galvanized strip steel until the actual image gray values and the actual light source power values of all varieties in the linear array system detection group and the area array system detection group reach the set range; when the gain value of the camera of the corresponding linear array detection system or area array detection system is reduced to the lower limit, and the actual image gray value still does not reach the set range, reducing the aperture value of the camera of the linear array detection system or area array detection system, and returning to the step 4);
7) solidifying the camera aperture value and the camera gain value corresponding to the linear array system detection group or the area array system detection group and taking the camera aperture value and the camera gain value as production operation parameters;
8) and after the parameters of all the linear array system detection sets and the parameters of all the linear array system detection sets are optimized, the results of all the linear array system detection sets and all the linear array system detection sets are solidified.
2. The detection optimization method of the dual-sensor surface quality detection system of the hot-dip galvanized strip steel according to claim 1, characterized in that, the pre-division of all varieties into a plurality of linear array system detection groups and planar array system detection groups in step 1) is to pre-divide the hot-dip galvanized strip steel into six detection groups, and the detection groups are divided into the following detection groups according to the gray level of the surface color and the quality requirements from high to low in sequence: thick plates, DP steel, HQ, S5, S4S3, S3A; each detection group is divided into a linear array system detection group and an area array system detection group according to different light source types; the decision priority of each detection group is: HQ > S5 > DP > plank > S4S3 > S3A.
3. The detection optimization method for the dual-sensor surface quality detection system of the hot-dip galvanized strip steel according to claim 1, characterized in that the camera aperture values of the step 2) corresponding to the linear array system detection group and the planar array system detection group are both F5.6, and the camera gain values of the corresponding linear array system detection group and the planar array system detection group are both set within a range of 128-1024.
4. The detection optimization method of the dual-sensor surface quality detection system for hot-dip galvanized steel strips according to claim 1, characterized in that the target gray-scale value range of the images of the linear array system detection group in the step 2) is 90-110, the target gray-scale value range of the images of the area array system detection group is 70-90, and the power value ranges of the target light sources are 65-85%.
5. The detection optimization method for the dual-sensor surface quality detection system of the hot-dip galvanized steel strip according to claim 1, characterized in that in step 5), when the actual light source power value of a certain image in the linear array system detection group or the area array system detection group is less than 65%, the actual light source power value is increased to reach the set range by reducing the corresponding camera gain value, and when the corresponding camera gain value is reduced to the lower limit value of 128, the actual light source power value is still less than 65%, the camera aperture value of the corresponding camera is reduced to f8, so that the actual image gray values and the actual light source power values of all kinds of images in the linear array system detection group or the area array system detection group reach the set range.
6. The detection optimization method for the dual-sensor surface quality detection system of the hot-dip galvanized steel strip according to claim 1, characterized in that in step 5), when the actual light source power value of a certain image in the linear array system detection group or the area array system detection group is greater than 85%, the actual light source power value is reduced to reach the set range by increasing the corresponding camera gain value, and when the camera gain value of the corresponding camera is increased to the upper limit value of 1024, the actual light source power value is still greater than 85%, the camera aperture value of the camera is increased to f4, so that the actual image gray values and the actual light source power values of all kinds of images in the linear array system detection group or the area array system detection group reach the set range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110419699.5A CN113281341A (en) | 2021-04-19 | 2021-04-19 | Detection optimization method of double-sensor surface quality detection system of hot-dip galvanized strip steel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110419699.5A CN113281341A (en) | 2021-04-19 | 2021-04-19 | Detection optimization method of double-sensor surface quality detection system of hot-dip galvanized strip steel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113281341A true CN113281341A (en) | 2021-08-20 |
Family
ID=77276948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110419699.5A Pending CN113281341A (en) | 2021-04-19 | 2021-04-19 | Detection optimization method of double-sensor surface quality detection system of hot-dip galvanized strip steel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113281341A (en) |
Citations (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1076101A (en) * | 1993-05-04 | 1993-09-15 | 刘长兴 | The method and the device thereof that are used for the diagnostic transmission equipment equalization imaging |
| CN1076102A (en) * | 1993-05-04 | 1993-09-15 | 刘长兴 | The method and the device thereof that are used for reproducing imaging parameters of diagnostic transmission equipment |
| WO1994024927A1 (en) * | 1993-05-04 | 1994-11-10 | Tam, Paul, Y. | Method and apparatus for examining tissue by transillumination using near infrared light |
| CN1149718A (en) * | 1995-10-27 | 1997-05-14 | 日本钢管株式会社 | Method for detecting surface defects and apparatus thereof |
| WO1997037336A1 (en) * | 1996-03-29 | 1997-10-09 | Commonwealth Scientific And Industrial Research Organisation | An aircraft detection system |
| CN1573283A (en) * | 2003-06-09 | 2005-02-02 | 株式会社三丰 | Image measuring method and image measuring device |
| CN102724404A (en) * | 2012-06-08 | 2012-10-10 | 北京大恒图像视觉有限公司 | All weather exposure gaining automatic regulation method and system |
| CN102822738A (en) * | 2010-03-22 | 2012-12-12 | 伊斯曼柯达公司 | Digital camera with underwater capture mode |
| JP2012247278A (en) * | 2011-05-27 | 2012-12-13 | National Printing Bureau | Watermark position checking method |
| CN104583710A (en) * | 2012-12-14 | 2015-04-29 | Gii采集有限责任公司,以总检测有限责任公司的名义营业 | High-speed 3-d method and system for optically measuring a geometric dimension of manufactured parts |
| CN204556517U (en) * | 2015-05-11 | 2015-08-12 | 沈阳准则精密技术有限公司 | Hot rolled sheet metal surface quality on-line detecting device |
| CN104915716A (en) * | 2014-03-14 | 2015-09-16 | 宝山钢铁股份有限公司 | Method of uniformly optimizing illuminating LED array light source for strip steel surface detection |
| CN105657282A (en) * | 2014-11-11 | 2016-06-08 | 宁波舜宇光电信息有限公司 | Visual identification method capable of initiatively optimizing image brightness |
| US20160203593A1 (en) * | 2013-09-10 | 2016-07-14 | Thyssenkrupp Steel Europe Ag | Method and device for testing an inspection system for detecting surface defects |
| CN106341626A (en) * | 2016-09-14 | 2017-01-18 | 北京空间机电研究所 | Dynamic-scope automatic adjusting method of glimmering linear array based on electron multiplication |
| CN106657801A (en) * | 2016-10-26 | 2017-05-10 | 浙江大华技术股份有限公司 | Video information acquiring method and apparatus |
| CN107532887A (en) * | 2015-05-13 | 2018-01-02 | 新日铁住金株式会社 | Shape inspection method, shape inspection apparatus and program |
| CN107635103A (en) * | 2015-08-11 | 2018-01-26 | 广东欧珀移动通信有限公司 | A kind of image processing method and mobile terminal and medium product |
| CN107786785A (en) * | 2016-08-29 | 2018-03-09 | 华为技术有限公司 | Photo-irradiation treatment method and device |
| JP2018059903A (en) * | 2016-10-07 | 2018-04-12 | サムソン エレクトロ−メカニックス カンパニーリミテッド． | Exterior appearance inspection device, and optical system automatic calibration method of the same |
| CN108088845A (en) * | 2017-12-07 | 2018-05-29 | 武汉精测电子集团股份有限公司 | A kind of image-forming correction method and device retained based on Weak Information |
| CN108234889A (en) * | 2018-03-19 | 2018-06-29 | 浙江国自机器人技术有限公司 | A kind of method, apparatus and storage medium for adjusting Image Acquisition brightness |
| CN108489989A (en) * | 2018-03-28 | 2018-09-04 | 苏州巨能图像检测技术有限公司 | The two-sided appearance detecting instrument of photovoltaic module based on the detection of polyphaser joining image-forming |
| CN109900720A (en) * | 2019-03-22 | 2019-06-18 | 武汉艾维视智能技术有限公司 | It is a kind of to adapt to different web plate optical detection light-source brightness automatic adjusting methods and system |
| CN109959452A (en) * | 2019-04-02 | 2019-07-02 | 浙江大学 | A kind of underwater fluorescence spectrum imager of pull-type and imaging method |
| CN110376210A (en) * | 2019-08-02 | 2019-10-25 | 山东齐昊新型彩铝有限公司 | New colorful aluminium surface defect on-line detecting system |
| CN110637227A (en) * | 2017-03-29 | 2019-12-31 | 深圳配天智能技术研究院有限公司 | Detection parameter determining method and detection device |
| WO2020183958A1 (en) * | 2019-03-08 | 2020-09-17 | Ｊｆｅスチール株式会社 | Chemically converted film inspection method, chemically converted film inspection device, surface-treated steel sheet manufacturing method, surface-treated steel sheet quality management method, and surface-treated steel sheet manufacturing equipment |
| CN111879790A (en) * | 2020-07-28 | 2020-11-03 | 唐山钢铁集团有限责任公司 | Method for detecting surface defects of aluminum-silicon-plated product |
| CN112098415A (en) * | 2020-08-06 | 2020-12-18 | 杭州电子科技大学 | Nondestructive testing method for quality of waxberries |
-
2021
- 2021-04-19 CN CN202110419699.5A patent/CN113281341A/en active Pending
Patent Citations (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1076102A (en) * | 1993-05-04 | 1993-09-15 | 刘长兴 | The method and the device thereof that are used for reproducing imaging parameters of diagnostic transmission equipment |
| WO1994024927A1 (en) * | 1993-05-04 | 1994-11-10 | Tam, Paul, Y. | Method and apparatus for examining tissue by transillumination using near infrared light |
| CN1076101A (en) * | 1993-05-04 | 1993-09-15 | 刘长兴 | The method and the device thereof that are used for the diagnostic transmission equipment equalization imaging |
| CN1149718A (en) * | 1995-10-27 | 1997-05-14 | 日本钢管株式会社 | Method for detecting surface defects and apparatus thereof |
| WO1997037336A1 (en) * | 1996-03-29 | 1997-10-09 | Commonwealth Scientific And Industrial Research Organisation | An aircraft detection system |
| CN1573283A (en) * | 2003-06-09 | 2005-02-02 | 株式会社三丰 | Image measuring method and image measuring device |
| CN102822738A (en) * | 2010-03-22 | 2012-12-12 | 伊斯曼柯达公司 | Digital camera with underwater capture mode |
| JP2012247278A (en) * | 2011-05-27 | 2012-12-13 | National Printing Bureau | Watermark position checking method |
| CN102724404A (en) * | 2012-06-08 | 2012-10-10 | 北京大恒图像视觉有限公司 | All weather exposure gaining automatic regulation method and system |
| CN104583710A (en) * | 2012-12-14 | 2015-04-29 | Gii采集有限责任公司,以总检测有限责任公司的名义营业 | High-speed 3-d method and system for optically measuring a geometric dimension of manufactured parts |
| US20160203593A1 (en) * | 2013-09-10 | 2016-07-14 | Thyssenkrupp Steel Europe Ag | Method and device for testing an inspection system for detecting surface defects |
| CN104915716A (en) * | 2014-03-14 | 2015-09-16 | 宝山钢铁股份有限公司 | Method of uniformly optimizing illuminating LED array light source for strip steel surface detection |
| CN105657282A (en) * | 2014-11-11 | 2016-06-08 | 宁波舜宇光电信息有限公司 | Visual identification method capable of initiatively optimizing image brightness |
| CN204556517U (en) * | 2015-05-11 | 2015-08-12 | 沈阳准则精密技术有限公司 | Hot rolled sheet metal surface quality on-line detecting device |
| CN107532887A (en) * | 2015-05-13 | 2018-01-02 | 新日铁住金株式会社 | Shape inspection method, shape inspection apparatus and program |
| CN107635103A (en) * | 2015-08-11 | 2018-01-26 | 广东欧珀移动通信有限公司 | A kind of image processing method and mobile terminal and medium product |
| CN107786785A (en) * | 2016-08-29 | 2018-03-09 | 华为技术有限公司 | Photo-irradiation treatment method and device |
| CN106341626A (en) * | 2016-09-14 | 2017-01-18 | 北京空间机电研究所 | Dynamic-scope automatic adjusting method of glimmering linear array based on electron multiplication |
| JP2018059903A (en) * | 2016-10-07 | 2018-04-12 | サムソン エレクトロ−メカニックス カンパニーリミテッド． | Exterior appearance inspection device, and optical system automatic calibration method of the same |
| CN106657801A (en) * | 2016-10-26 | 2017-05-10 | 浙江大华技术股份有限公司 | Video information acquiring method and apparatus |
| CN110637227A (en) * | 2017-03-29 | 2019-12-31 | 深圳配天智能技术研究院有限公司 | Detection parameter determining method and detection device |
| CN108088845A (en) * | 2017-12-07 | 2018-05-29 | 武汉精测电子集团股份有限公司 | A kind of image-forming correction method and device retained based on Weak Information |
| CN108234889A (en) * | 2018-03-19 | 2018-06-29 | 浙江国自机器人技术有限公司 | A kind of method, apparatus and storage medium for adjusting Image Acquisition brightness |
| CN108489989A (en) * | 2018-03-28 | 2018-09-04 | 苏州巨能图像检测技术有限公司 | The two-sided appearance detecting instrument of photovoltaic module based on the detection of polyphaser joining image-forming |
| WO2020183958A1 (en) * | 2019-03-08 | 2020-09-17 | Ｊｆｅスチール株式会社 | Chemically converted film inspection method, chemically converted film inspection device, surface-treated steel sheet manufacturing method, surface-treated steel sheet quality management method, and surface-treated steel sheet manufacturing equipment |
| CN109900720A (en) * | 2019-03-22 | 2019-06-18 | 武汉艾维视智能技术有限公司 | It is a kind of to adapt to different web plate optical detection light-source brightness automatic adjusting methods and system |
| CN109959452A (en) * | 2019-04-02 | 2019-07-02 | 浙江大学 | A kind of underwater fluorescence spectrum imager of pull-type and imaging method |
| CN110376210A (en) * | 2019-08-02 | 2019-10-25 | 山东齐昊新型彩铝有限公司 | New colorful aluminium surface defect on-line detecting system |
| CN111879790A (en) * | 2020-07-28 | 2020-11-03 | 唐山钢铁集团有限责任公司 | Method for detecting surface defects of aluminum-silicon-plated product |
| CN112098415A (en) * | 2020-08-06 | 2020-12-18 | 杭州电子科技大学 | Nondestructive testing method for quality of waxberries |
Non-Patent Citations (1)
| Title |
|---|
| 杨水山: "冷轧带钢表面缺陷机器视觉自动检测技术研究", 《中国优秀博硕士学位论文全文数据库信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103063167B (en) | A kind of method of automatic decision laser cleaning effect | |
| CN105046700B (en) | Fruit surface defect detection method and system based on gamma correction and color classification | |
| TW201702586A (en) | Optical film defect detection method and system thereof | |
| CA2681817A1 (en) | Lumber inspection method, device and program | |
| CN108596909A (en) | Hollow cylinder Surface Flaw Detection system and method | |
| CN106709529B (en) | Visual detection method for photovoltaic cell color difference classification | |
| CN109461156B (en) | Threaded sealing plug assembly detection method based on vision | |
| CN111665251A (en) | Visual detection method for surface defects | |
| CN115456652B (en) | Precise injection molding defective product tracing method based on artificial intelligence | |
| CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
| CN111766245B (en) | Button cell negative electrode shell defect detection method based on machine vision | |
| CN115424008A (en) | Method and system for detecting light modulation and focusing of laser projector production line | |
| CN113808104A (en) | Block-based metal surface defect detection method and system | |
| CN116908093B (en) | Flaw identification system for goods | |
| CN113281341A (en) | Detection optimization method of double-sensor surface quality detection system of hot-dip galvanized strip steel | |
| CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
| CN110516725B (en) | Machine vision-based wood board stripe spacing and color detection method | |
| CN108416790A (en) | A kind of detection method for workpiece breakage rate | |
| CN108989608B (en) | Road surface image gray level correction method based on linear array camera | |
| CN113125346A (en) | Surface defect detection system classification group optimization method based on area array light source | |
| Singh et al. | Detection of defects in glass sheet using cs c based segmentation method | |
| CN113706467A (en) | Method for detecting low-contrast foreign matter and poor heterochrosis of glass | |
| CN115222735A (en) | Metal mold quality detection method based on pockmark defects | |
| CN109272462A (en) | Suitable for the image automatic correcting method of metal works identification, equipment and storage equipment | |
| CN108764252B (en) | Machine vision-based front and back recognition method for decorative alloy sheet |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210820 |