CN115029704A - Intelligent control method and device for stainless steel pickling process - Google Patents
Intelligent control method and device for stainless steel pickling process Download PDFInfo
- Publication number
- CN115029704A CN115029704A CN202210949953.7A CN202210949953A CN115029704A CN 115029704 A CN115029704 A CN 115029704A CN 202210949953 A CN202210949953 A CN 202210949953A CN 115029704 A CN115029704 A CN 115029704A
- Authority
- CN
- China
- Prior art keywords
- image
- gradient
- detected
- value
- oxidation
- 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.)
- Granted
Links
Images
Classifications
-
- C—CHEMISTRY; METALLURGY
- C23—COATING METALLIC MATERIAL; COATING MATERIAL WITH METALLIC MATERIAL; CHEMICAL SURFACE TREATMENT; DIFFUSION TREATMENT OF METALLIC MATERIAL; COATING BY VACUUM EVAPORATION, BY SPUTTERING, BY ION IMPLANTATION OR BY CHEMICAL VAPOUR DEPOSITION, IN GENERAL; INHIBITING CORROSION OF METALLIC MATERIAL OR INCRUSTATION IN GENERAL
- C23G—CLEANING OR DE-GREASING OF METALLIC MATERIAL BY CHEMICAL METHODS OTHER THAN ELECTROLYSIS
- C23G1/00—Cleaning or pickling metallic material with solutions or molten salts
- C23G1/02—Cleaning or pickling metallic material with solutions or molten salts with acid solutions
- C23G1/08—Iron or steel
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- General Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Materials Engineering (AREA)
- Mechanical Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Cleaning And De-Greasing Of Metallic Materials By Chemical Methods (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of methods for identification by using electronic equipment, in particular to an intelligent control method and a device for a stainless steel pickling process, wherein the method comprises the following steps: acquiring an image to be detected and a standard image; obtaining a gradient difference image according to the gradient image corresponding to the image to be detected and the standard image; selecting a target image from the standard image according to the gradient co-occurrence matrix of the image to be detected and the gradient co-occurrence matrix of each gradient difference image; acquiring a reference gray value according to the target image; acquiring a gradient difference value of the image to be detected, and calculating the oxidation degree in the image to be detected according to the gradient difference value and a reference gray value; according to the method, the pickling time of the oxidation area corresponding to the oxidation degree is adjusted according to the oxidation degree, and the pickling time of the areas corresponding to different oxidation degrees is adjusted, so that the pickling effect of the stainless steel surface is improved.
Description
Technical Field
The invention relates to the technical field of intelligent detection of electronic equipment, in particular to an intelligent control method and device for a stainless steel pickling process.
Background
In the processes of heating, rough rolling and finish rolling of the plate blank, the surface of the stainless steel can be oxidized to generate iron scale, and the iron scale can be firmly covered on the surface of the strip steel. During storage, if not stored properly, oxide will also be produced on the surface. According to the use requirements of the surface of the steel, the steel is usually subjected to processes such as cold rolling or hot dipping, but before the cold rolling or hot dipping process, oxides on the surface of the stainless steel must be removed by acid cleaning so as to ensure the quality of the cold rolling and hot dipping.
However, the short pickling time can cause that the oxide skin on the surface of the steel cannot be completely removed, and the defect of insufficient pickling is formed; if the pickling speed is too slow and the corresponding pickling time is too long, the steel surface is over-corroded to form an over-pickling defect. Therefore, speed control of the pickling section is very important.
The existing pickling time control method usually depends on experience values of workers to set unified pickling time, but because the oxidation degrees of different parts of stainless steel in the production, transportation and storage processes are different, only the unified pickling time experience values are used, when pickling is carried out on an area with small oxidation degree on the surface of steel, over-pickling or under-pickling is possibly caused, and the pickling quality of different oxidation areas of the steel can be influenced by using the unified pickling time.
Therefore, it is necessary to provide a method and a device for identifying and processing stainless steel pickling process by electronic equipment to realize intelligent control.
Disclosure of Invention
The invention provides an intelligent control method and device for a stainless steel pickling process, and aims to solve the existing problems.
The intelligent control method for the stainless steel pickling process adopts the following technical scheme: the method comprises the following steps:
acquiring an image to be detected on the surface of the stainless steel and a plurality of standard images qualified in acid washing;
acquiring an image to be detected and a gradient image corresponding to each standard image, and obtaining a plurality of corresponding gradient difference images according to the gradient image of the image to be detected and the gradient image of each standard image;
acquiring a first entropy value of a gradient co-occurrence matrix corresponding to an image to be detected and a second entropy value of a gradient co-occurrence matrix corresponding to each gradient difference image, calculating a difference value between the first entropy value and each second entropy value, acquiring all gradient difference images corresponding to the difference values larger than 0, and marking a standard image corresponding to each gradient difference image corresponding to the difference value larger than 0 as a target image;
acquiring reference gray values according to all target images;
acquiring a gradient difference value of a region corresponding to each pixel point in the image to be detected, and calculating the oxidation degree of a central pixel point corresponding to each region in the image to be detected according to the gradient difference value and a reference gray value;
clustering the oxidation degree of each pixel point in the image to be detected to obtain a plurality of clustering areas, recording the clustering areas as oxidation areas, and adjusting the pickling time of each oxidation area according to the oxidation degree and the pickling solution concentration corresponding to each oxidation area and by combining the corresponding oxidation degree and the corresponding pickling solution concentration in the historical data.
Further, the step of obtaining a plurality of corresponding gradient difference images according to the gradient image of the image to be detected and the gradient image of each standard image includes:
respectively obtaining a gradient image corresponding to an image to be detected and gradient values and gradient directions corresponding to pixel points in the gradient image corresponding to each standard image;
and (3) carrying out difference on the gradient value and the gradient direction corresponding to the image to be detected and the gradient value and the gradient direction corresponding to each standard image to obtain a plurality of gradient difference images.
Further, the step of obtaining the reference gray value according to the entropy of the image to be detected, the entropy of each target image and the average gray value of each target image includes:
acquiring a gray level histogram of each target image after normalization;
determining the average gray value of the target image according to the gray levels in the gray histogram and the proportion of each gray level;
and taking the difference value between the corresponding entropy value of the image to be detected and the corresponding entropy value of each target image as weight, and carrying out weighted calculation on the average gray value of each target image to obtain a reference gray value.
Further, the step of obtaining the gradient difference value of the corresponding region of each pixel point in the image to be detected comprises:
acquiring a sliding window area image by taking each pixel point in the detection image as a central pixel point;
and obtaining the gradient difference value of the region corresponding to the central pixel point according to the gradient vector and the gradient value of each pixel point in each sliding window region image and the gradient vector and the gradient value corresponding to the central pixel point.
Further, the step of calculating the oxidation degree of the central pixel point corresponding to each region in the image to be detected according to the gradient difference value and the reference gray value comprises the following steps:
calculating the oxidation degree of each pixel point in the image to be detected according to the following formula (1):
wherein the content of the first and second substances,
for the first in the image to be detected
The oxidation degree of each central pixel point;
for the first image except the central pixel point in the current sliding window area image
Gradient direction of each pixel point;
for the first image except the central pixel point in the current sliding window area image
Gradient values of the individual pixel points;
for the first in the image to be detected
The gray value of each central pixel point;
is a reference gray value.
Further, the step of clustering the oxidation degree of each pixel point in the image to be detected to obtain a plurality of clustering areas and marking the clustering areas as oxidation areas comprises:
carrying out first clustering on the oxidation degree of each pixel point to obtain a plurality of primary clustering results, wherein each clustering result corresponds to one oxidation degree;
performing secondary clustering on the primary clustering result to obtain a secondary clustering result;
and taking the secondary clustering result as a minimum enclosure frame, wherein each minimum enclosure frame region corresponds to an oxidation region.
Further, the step of adjusting the pickling time of each oxidation area according to the oxidation degree and the pickling solution concentration corresponding to each oxidation area and combining the corresponding oxidation degree and the corresponding pickling solution concentration in the historical data comprises the following steps:
establishing a database according to the same oxidation degree, the same pickling solution concentration and the same oxidation degree of the stainless steel image qualified by pickling in the historical data and the time average value of all pickling times under the same pickling solution concentration;
matching the oxidation degree and the pickling solution concentration corresponding to the oxidation area of the image to be detected with the data in the database to obtain the pickling time average value corresponding to the same oxidation degree and the same pickling solution concentration in the database;
and taking the acid washing time average value as the adjustment value of the acid washing time of each corresponding oxidation area to adjust the acid washing time of the oxidation area.
The invention also discloses an intelligent control device for the stainless steel pickling process, which comprises the following components: the acquisition module is used for acquiring an image to be detected on the surface of the stainless steel and a plurality of standard images qualified in acid washing;
the first image processing module is used for respectively carrying out difference on the gradient image of the image to be detected and the gradient image of each standard image to obtain a plurality of corresponding gradient difference images;
the second image processing module is used for acquiring a first entropy value of a gradient co-occurrence matrix corresponding to an image to be detected and a second entropy value of the gradient co-occurrence matrix corresponding to each gradient difference image, calculating a difference value between the first entropy value and each second entropy value, acquiring all gradient difference images corresponding to the difference values larger than 0, and marking a standard image corresponding to each gradient difference image corresponding to the difference value larger than 0 as a target image;
the first parameter calculation module is used for acquiring the average gray value of each target image and acquiring a reference gray value according to the average gray value of each target image;
the second parameter calculation module is used for acquiring a gradient difference value of a region corresponding to each pixel point in the image to be detected and calculating the oxidation degree of a central pixel point corresponding to each region in the image to be detected according to the gradient difference value and a reference gray value;
the adjusting module is used for clustering the oxidation degree of each pixel point in the image to be detected to obtain a plurality of clustering areas and marking the clustering areas as oxidation areas, and adjusting the pickling time of each oxidation area according to the oxidation degree and the pickling solution concentration corresponding to the oxidation areas
The invention has the beneficial effects that: the invention relates to an intelligent control method and a device for a stainless steel pickling process, which acquire an image to be detected on the surface of a stainless steel material, process the image to be detected to obtain a standard image which is qualified by pickling and is similar to the image to be detected, determine a reference gray value by using the standard image and the image to be detected, determine the corresponding oxidation degree of each oxidation area of the image to be detected according to the reference gray value and the gradient difference value of the image to be detected, adjust the pickling time of each oxidation area according to the corresponding oxidation degree and the concentration of pickling solution of each oxidation area and by combining the corresponding oxidation degree and the concentration of the pickling solution in historical data, realize that the pickling time of different oxidation areas can be adjusted in a self-adaptive manner when the oxidation areas on the surface of the stainless steel are pickled, so that different positions with different oxidation degrees on the surface of the stainless steel can obtain the best pickling effect, the method is applied to the stainless steel pickling process, and intelligent control is realized by identifying and processing through electronic equipment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of the general steps of an embodiment of an intelligent control method for a stainless steel pickling process of the present invention;
fig. 2 is a flowchart of specifically obtaining the target image in step S3 in the embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
An embodiment of the intelligent control method for the stainless steel pickling process of the invention is shown in figure 1, and the method comprises the following steps:
s1, acquiring an image to be detected of the surface of the stainless steel and a plurality of standard images qualified by acid washing; specifically, an RGB camera is used for collecting a photo to be detected of the surface of the stainless steel material to be detected and a plurality of qualified photos of the surface of the stainless steel material which is qualified after acid washing, the photo to be detected is processed through a semantic segmentation technology to obtain an image to be detected which only contains the steel material part, and the semantic segmentation technology is also used for processing a plurality of standard images which are qualified after acid washing to obtain a standard image which only contains the steel material part.
S2, because the color of the steel surface changes after the steel is oxidized and the color depth of the oxides with different oxidation degrees is different, the larger the gray difference between the image to be detected and the standard image is, the larger the oxidation degree is; in addition, due to the influence of illumination factors, when the illumination environments of the standard image and the image to be detected are different, the obtained gray level difference comprises the difference caused by different illumination, in order to avoid the inaccuracy of the detection result, firstly, the gradient image corresponding to the image to be detected and each standard image is obtained, and a plurality of corresponding gradient difference images are obtained according to the gradient image of the image to be detected and the gradient image of each standard image; specifically, a gradient image corresponding to the image to be detected and a gradient value and a gradient direction corresponding to a pixel point in a gradient image corresponding to each standard image are respectively obtained, that is, Sobel gradient detection is performed on the image to be detected and each standard image to obtain a corresponding gradient image, and the gradient value and the gradient direction corresponding to the pixel point in the gradient image; and subtracting the gradient value and the gradient direction corresponding to the image to be detected from the gradient value and the gradient direction corresponding to each standard image to obtain a plurality of gradient difference images.
S3, respectively obtaining an image to be detected and a gradient co-occurrence matrix corresponding to each gradient difference image, specifically, counting the gradient direction of each pixel point in the gradient image corresponding to the image to be detected, obtaining the gradient co-occurrence matrix of all pixels in the gradient image in the 0 ° direction according to each gradient direction in the range of the gradient direction as the direction grade of the gradient co-occurrence matrix, where the gradient co-occurrence matrix is used to represent the number of times that a pixel pair of different pixel points in the image appears in the corresponding gradient direction, normalizing the obtained gradient co-occurrence matrix, calculating the entropy of the gradient co-occurrence matrix, selecting a plurality of target images from a plurality of standard images according to the gradient co-occurrence matrix of the image to be detected and the gradient co-occurrence matrix of each gradient difference image, specifically, as shown in fig. 2, obtaining a first entropy, a second entropy, and a second entropy of the gradient co-occurrence matrix corresponding to the image to be detected, A second entropy value of a gradient co-occurrence matrix corresponding to each gradient difference image; calculating a difference value between the first entropy value and each second entropy value; acquiring all gradient difference images corresponding to the difference value larger than 0; and recording the standard image corresponding to each gradient difference image as a target image.
S4, acquiring a reference gray value according to the entropy of the image to be detected, the entropy of each target image and the average gray value of each target image; specifically, a gray level histogram of each target image after normalization is obtained; determining the average gray value of the target image according to the gray levels in the gray histogram and the proportion of each gray level; and taking the difference value between the corresponding entropy value of the image to be detected and the corresponding entropy value of each target image as weight, and carrying out weighted calculation on the average gray value of each target image to obtain a reference gray value.
S5, obtaining the gradient difference value of each pixel point corresponding region in the image to be detected, because the surface of the stainless steel is oxidized, the surface of the stainless steel can have color change, and two different oxides can be generated according to different environments generated by oxidation: the oxide generated in the humid environment at normal temperature is rust which is reddish brown; the other is the oxide iron sheet generated at high temperature, commonly called as iron scale, which is dark black. Wherein the gray scale value of rust is higher and the gray scale value of iron phosphorus is lower than that of the normal area. Therefore, the degree of oxidation can be judged according to the degree of color change; when the color of the pixel point is black, namely the gray value is smaller than that of the normal area, the possibility that the point is iron-phosphorus oxide is high; when the color of the pixel point is red, namely the gray value is larger than that of the normal area, the possibility that the point is the rust oxide is high; considering that a normal area is smooth and has a low oxidation degree, a bright illumination area exists on the surface of the normal area, and gray scale difference can also be formed, namely, the oxidation degree of each position cannot be correctly judged only according to the gray scale difference, and the illumination area is different from the rust oxidation area in that rust oxides can form rust particles on the surface of stainless steel to damage the smoothness of the surface of the stainless steel, so that the gradient difference value of the surface of steel is increased. Therefore, when the oxidation degree of the pixel points with the gray values larger than the gray value of the normal area is evaluated, the gradient difference values of the pixel points are combined for comprehensive judgment, and the oxidation degree of the central pixel point corresponding to each area in the image to be detected is calculated according to the gradient difference values and the reference gray value; specifically, the step of obtaining the gradient difference value of the corresponding region of each pixel point in the image to be detected comprises: obtaining a sliding window area image by taking each pixel point in the detection image as a central pixel point, and obtaining a gradient difference value of a region corresponding to the central pixel point according to the gradient vector and the gradient value of each pixel point in each sliding window area image and the gradient vector and the gradient value of the pixel point corresponding to the central pixel point; specifically, the step of calculating the oxidation degree of the central pixel point corresponding to each region in the image to be detected according to the gradient difference value and the reference gray value comprises the following steps: calculating the oxidation degree of each pixel point in the image to be detected according to the following formula (1):
wherein the content of the first and second substances,
for the first in the image to be detected
Each central pixel point
The degree of oxidation;
for the first image except the central pixel point in the current sliding window area image
Gradient direction of each pixel point;
for the first image except the central pixel point in the current sliding window area image
Gradient values of the individual pixel points;
for the first in the image to be detected
The gray value of each central pixel point;
is a reference gray value;
is shown as
The difference degree of the gray value of each pixel point relative to the reference gray value under normal conditions
Approaching to 1, when the point is the scale oxide, the gray value corresponding to the pixel point is less than the reference gray value, that is, the gray value is less than the reference gray value
And the larger the value, the more obvious the blackening degree and the larger the oxidation degree; when the point is rust oxide, the gray value corresponding to the pixel point is greater than the reference gray value, namely
And the smaller the value, the greater the degree of oxidation; but since there may be an influence of illumination, and the gray value of the illuminated area is also larger than the reference gray value,
is shown as
The larger the gradient complexity of each pixel point is, the larger the gradient fluctuation of each pixel point relative to the central pixel point in the sliding window area where the pixel point is located is, the more complicated the gradient distribution is, namely, the more uneven the peripheral area of the pixel point is, and the larger the corresponding gradient difference value is.
S6, clustering the oxidation degree of each pixel point in the image to be detected to obtain a plurality of clustering areas, marking as oxidation areas, and adjusting the pickling time of each oxidation area according to the oxidation degree and the pickling solution concentration corresponding to each oxidation area and by combining the oxidation degree and the pickling solution concentration corresponding to the historical data; specifically, the step of clustering the oxidation degree of each pixel point in the image to be detected to obtain a plurality of clustering areas and marking the clustering areas as oxidation areas comprises the following steps: carrying out first clustering on the oxidation degree of each pixel point to obtain a plurality of primary clustering results, wherein each clustering result corresponds to one oxidation degree; performing secondary clustering on the primary clustering result to obtain a secondary clustering result; taking the secondary clustering result as a minimum enclosure frame, wherein each minimum enclosure frame region corresponds to an oxidation region; specifically, the step of adjusting the pickling time of each oxidation area according to the oxidation degree and the pickling solution concentration corresponding to each oxidation area and combining the corresponding oxidation degree and the corresponding pickling solution concentration in the historical data comprises the following steps: establishing a database according to the same oxidation degree, the same pickling solution concentration and the same oxidation degree of the stainless steel image qualified by pickling in the historical data and the time average value of all pickling times under the same pickling solution concentration; matching the oxidation degree and the pickling solution concentration corresponding to the oxidation area of the image to be detected with the data in the database to obtain the pickling time average value corresponding to the same oxidation degree and the same pickling solution concentration in the database; and adjusting the pickling time of the oxidation area by taking the pickling time average value as the adjustment value of the pickling time of each corresponding oxidation area.
The invention also discloses an intelligent control device for the stainless steel pickling process, which comprises the following components: the system comprises an acquisition module, a first image processing module, a second image processing module, a first parameter calculation module, a second parameter calculation module and an adjustment module, wherein the acquisition module selects an RGB camera, the RGB camera acquires a to-be-detected picture of the surface of the stainless steel material to be detected and a plurality of qualified pictures of the surface of the stainless steel material which is qualified by pickling, then the to-be-detected picture is processed by a semantic segmentation technology to obtain an image to be detected which only contains a steel material part, and a plurality of standard images which are qualified by pickling are processed by the same semantic segmentation technology to obtain a standard image which only contains the steel material part; the first image processing module is used for respectively carrying out difference on the gradient image of the image to be detected and the gradient image of each standard image to obtain a plurality of corresponding gradient difference images; the second image processing module is used for acquiring a first entropy value of a gradient co-occurrence matrix corresponding to an image to be detected and a second entropy value of the gradient co-occurrence matrix corresponding to each gradient difference image, calculating a difference value between the first entropy value and each second entropy value, acquiring all gradient difference images corresponding to the difference values larger than 0, and marking a standard image corresponding to each gradient difference image corresponding to the difference value larger than 0 as a target image; the first parameter calculation module is used for acquiring the average gray value of each target image and acquiring a reference gray value according to the average gray value of each target image; the second parameter calculation module is used for acquiring a gradient difference value of a region corresponding to each pixel point in the image to be detected and calculating the oxidation degree of a central pixel point corresponding to each region in the image to be detected according to the gradient difference value and a reference gray value; the adjusting module is used for clustering the oxidation degree of each pixel point in the image to be detected to obtain a plurality of clustering areas, recording the clustering areas as oxidation areas, and adjusting the pickling time of each oxidation area according to the oxidation degree and the pickling solution concentration corresponding to the oxidation areas.
In summary, the present invention provides an intelligent control method and device for stainless steel pickling process, by collecting the image to be measured on the surface of the stainless steel material, then processing the image to be detected to obtain a standard image which is similar to the image to be detected and qualified by pickling, determining a reference gray value by utilizing the standard image and the image to be detected, determining the oxidation degree corresponding to each oxidation area of the image to be detected according to the reference gray value and the gradient difference value of the image to be detected, then, the pickling time of each oxidation area is adjusted according to the corresponding oxidation degree and pickling solution concentration of each oxidation area and the corresponding oxidation degree and pickling solution concentration in historical data, when the oxidation area on the surface of the stainless steel is pickled, the pickling time of different oxidation areas can be adaptively adjusted, so that the optimal pickling effect can be obtained at different positions with different oxidation degrees on the surface of the stainless steel.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (8)
1. An intelligent control method for a stainless steel pickling process is characterized by comprising the following steps:
acquiring an image to be detected on the surface of the stainless steel and a plurality of standard images qualified by acid washing;
acquiring an image to be detected and a gradient image corresponding to each standard image, and obtaining a plurality of corresponding gradient difference images according to the gradient image of the image to be detected and the gradient image of each standard image;
acquiring a first entropy value of a gradient co-occurrence matrix of an image to be detected and a second entropy value of a gradient co-occurrence matrix of each gradient difference image, calculating a difference value between the first entropy value and each second entropy value, acquiring all gradient difference images corresponding to the difference values larger than 0, and marking a standard image corresponding to each gradient difference image corresponding to the difference value larger than 0 as a target image;
acquiring reference gray values according to all target images;
acquiring a gradient difference value of a region corresponding to each pixel point in the image to be detected, and calculating the oxidation degree of a central pixel point corresponding to each region in the image to be detected according to the gradient difference value and a reference gray value;
clustering the oxidation degree of each pixel point in the image to be detected to obtain a plurality of clustering areas, recording the clustering areas as oxidation areas, and adjusting the pickling time of each oxidation area according to the oxidation degree and the pickling solution concentration corresponding to each oxidation area and by combining the corresponding oxidation degree and the corresponding pickling solution concentration in the historical data.
2. The intelligent control method for the stainless steel pickling process as claimed in claim 1, wherein the step of obtaining a plurality of corresponding gradient difference images according to the gradient image of the image to be detected and the gradient image of each standard image comprises:
respectively obtaining a gradient image corresponding to an image to be detected and gradient values and gradient directions corresponding to pixel points in the gradient image corresponding to each standard image;
and subtracting the gradient value and the gradient direction corresponding to the image to be detected from the gradient value and the gradient direction corresponding to each standard image to obtain a plurality of gradient difference images.
3. The intelligent control method for the stainless steel pickling process according to claim 1, wherein the step of obtaining the reference gray value according to all the target images comprises:
acquiring a normalized gray level histogram of each target image;
determining the average gray value of the target image according to the gray levels in the gray histogram and the proportion of each gray level;
and taking the difference value between the corresponding entropy value of the image to be detected and the corresponding entropy value of each target image as weight, and carrying out weighted calculation on the average gray value of each target image to obtain a reference gray value.
4. The intelligent control method for the stainless steel pickling process according to claim 1, wherein the step of obtaining the gradient difference value of the corresponding area of each pixel point in the image to be detected comprises the steps of:
acquiring a sliding window area image by taking each pixel point in the detection image as a central pixel point;
and obtaining the gradient difference value of the region corresponding to the central pixel point according to the gradient vector and the gradient value of each pixel point in each sliding window region image and the gradient vector and the gradient value of the pixel point corresponding to the central pixel point.
5. The intelligent control method for the stainless steel pickling process according to claim 1, wherein the step of calculating the oxidation degree of the central pixel point corresponding to each region in the image to be detected according to the gradient difference value and the reference gray value comprises the following steps:
calculating the oxidation degree of each pixel point in the image to be detected according to the following formula (1):
wherein the content of the first and second substances,
for the first in the image to be detected
The oxidation degree of each central pixel point;
for the current sliding window area within the image
Gradient direction of each pixel point;
for the current sliding window area within the image
Gradient values of the individual pixel points;
for the first in the image to be detected
The gray value of each central pixel point;
is a reference gray value.
6. The intelligent control method for the stainless steel pickling process according to claim 1, wherein the step of clustering the oxidation degree of each pixel point in the image to be detected to obtain a plurality of clustering areas and marking the clustering areas as oxidation areas comprises the following steps:
carrying out first clustering on the oxidation degree of each pixel point to obtain a plurality of primary clustering results, wherein each clustering result corresponds to one oxidation degree;
performing secondary clustering on the primary clustering result to obtain a secondary clustering result;
and taking the secondary clustering result as a minimum enclosure frame, wherein each minimum enclosure frame region corresponds to an oxidation region.
7. The intelligent control method for the stainless steel pickling process according to claim 1, wherein the step of adjusting the pickling time of each oxidation area according to the corresponding oxidation degree and pickling solution concentration of each oxidation area and the corresponding oxidation degree and pickling solution concentration in historical data comprises the following steps:
establishing a database according to the same oxidation degree, the same pickling solution concentration and the same oxidation degree of the stainless steel image qualified by pickling in the historical data and the time average value of all pickling times under the same pickling solution concentration;
matching the oxidation degree and the pickling solution concentration corresponding to the oxidation area of the image to be detected with the data in the database to obtain the pickling time average value corresponding to the same oxidation degree and the same pickling solution concentration in the database;
and taking the acid washing time average value as the adjustment value of the acid washing time of each corresponding oxidation area to adjust the acid washing time of the oxidation area.
8. The intelligent control device for the stainless steel pickling process according to any one of claims 1 to 7, characterized by comprising:
the acquisition module is used for acquiring an image to be detected on the surface of the stainless steel and a plurality of standard images qualified in acid washing;
the first image processing module is used for respectively subtracting the gradient image of the image to be detected and the gradient image of each standard image to obtain a plurality of corresponding gradient difference images;
the second image processing module is used for acquiring a first entropy value of a gradient co-occurrence matrix of an image to be detected and a second entropy value of a gradient co-occurrence matrix of each gradient difference image, calculating a difference value between the first entropy value and each second entropy value, acquiring all gradient difference images corresponding to the difference values larger than 0, and marking a standard image corresponding to each gradient difference image corresponding to the difference value larger than 0 as a target image;
the first parameter calculation module is used for acquiring the average gray value of each target image and acquiring a reference gray value according to the average gray value of each target image;
the second parameter calculation module is used for acquiring a gradient difference value of a region corresponding to each pixel point in the image to be detected and calculating the oxidation degree of a central pixel point corresponding to each region in the image to be detected according to the gradient difference value and a reference gray value;
and the adjusting module is used for clustering the oxidation degree of each pixel point in the image to be detected to obtain a plurality of clustering areas and marking the clustering areas as oxidation areas, and adjusting the pickling time of each oxidation area according to the oxidation degree and the pickling solution concentration corresponding to the oxidation areas.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210949953.7A CN115029704B (en) | 2022-08-09 | 2022-08-09 | Intelligent control method and device for stainless steel pickling process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210949953.7A CN115029704B (en) | 2022-08-09 | 2022-08-09 | Intelligent control method and device for stainless steel pickling process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115029704A true CN115029704A (en) | 2022-09-09 |
| CN115029704B CN115029704B (en) | 2022-12-09 |
Family
ID=83130109
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210949953.7A Active CN115029704B (en) | 2022-08-09 | 2022-08-09 | Intelligent control method and device for stainless steel pickling process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115029704B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116288381A (en) * | 2023-03-16 | 2023-06-23 | 山东钢铁集团日照有限公司 | Closed-loop control method for realizing stable pickling quality by automatically adjusting hydrochloric acid process parameters |
| CN116958139A (en) * | 2023-09-20 | 2023-10-27 | 深圳市盘古环保科技有限公司 | Advanced oxidation intelligent monitoring method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030185420A1 (en) * | 2002-03-29 | 2003-10-02 | Jason Sefcik | Target detection method and system |
| CN102800107A (en) * | 2012-07-06 | 2012-11-28 | 浙江工业大学 | Motion target detection method based on improved minimum cross entropy |
| AU2020102091A4 (en) * | 2019-10-17 | 2020-10-08 | Wuhan University Of Science And Technology | Intelligent steel slag detection method and system based on convolutional neural network |
| AU2020102883A4 (en) * | 2020-10-20 | 2020-12-17 | Zhengzhou Sias University | Apple disease identification method based on the histogram of layered gradient directions in logarithmic frequency domain |
| WO2021068486A1 (en) * | 2019-10-12 | 2021-04-15 | 深圳壹账通智能科技有限公司 | Image recognition-based vision detection method and apparatus, and computer device |
| WO2021238739A1 (en) * | 2020-05-28 | 2021-12-02 | 江苏大学附属医院 | Clustering algorithm-based multi-parameter cumulative calculation method for calcification index of lower limb blood vessels |
| WO2022160452A1 (en) * | 2021-02-01 | 2022-08-04 | 深圳大学 | Optical fiber automatic focus method for laser processing, and automatic focus system |
-
2022
- 2022-08-09 CN CN202210949953.7A patent/CN115029704B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030185420A1 (en) * | 2002-03-29 | 2003-10-02 | Jason Sefcik | Target detection method and system |
| CN102800107A (en) * | 2012-07-06 | 2012-11-28 | 浙江工业大学 | Motion target detection method based on improved minimum cross entropy |
| WO2021068486A1 (en) * | 2019-10-12 | 2021-04-15 | 深圳壹账通智能科技有限公司 | Image recognition-based vision detection method and apparatus, and computer device |
| AU2020102091A4 (en) * | 2019-10-17 | 2020-10-08 | Wuhan University Of Science And Technology | Intelligent steel slag detection method and system based on convolutional neural network |
| WO2021238739A1 (en) * | 2020-05-28 | 2021-12-02 | 江苏大学附属医院 | Clustering algorithm-based multi-parameter cumulative calculation method for calcification index of lower limb blood vessels |
| AU2020102883A4 (en) * | 2020-10-20 | 2020-12-17 | Zhengzhou Sias University | Apple disease identification method based on the histogram of layered gradient directions in logarithmic frequency domain |
| WO2022160452A1 (en) * | 2021-02-01 | 2022-08-04 | 深圳大学 | Optical fiber automatic focus method for laser processing, and automatic focus system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116288381A (en) * | 2023-03-16 | 2023-06-23 | 山东钢铁集团日照有限公司 | Closed-loop control method for realizing stable pickling quality by automatically adjusting hydrochloric acid process parameters |
| CN116958139A (en) * | 2023-09-20 | 2023-10-27 | 深圳市盘古环保科技有限公司 | Advanced oxidation intelligent monitoring method |
| CN116958139B (en) * | 2023-09-20 | 2023-11-21 | 深圳市盘古环保科技有限公司 | Advanced oxidation intelligent monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115029704B (en) | 2022-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115029704B (en) | Intelligent control method and device for stainless steel pickling process | |
| CN116188462B (en) | Noble metal quality detection method and system based on visual identification | |
| CN115841434B (en) | Infrared image enhancement method for gas concentration analysis | |
| CN115018844B (en) | Plastic film quality evaluation method based on artificial intelligence | |
| CN104568986A (en) | Method for automatically detecting printing defects of remote controller panel based on SURF (Speed-Up Robust Feature) algorithm | |
| CN111260788B (en) | Power distribution cabinet switch state identification method based on binocular vision | |
| CN115619793B (en) | Power adapter appearance quality detection method based on computer vision | |
| CN109816645B (en) | Automatic detection method for steel coil loosening | |
| CN115035106B (en) | Strip steel defect intelligent detection method | |
| CN116740058B (en) | Quality detection method for solid state disk matched wafer | |
| CN105488475B (en) | Method for detecting human face in mobile phone | |
| CN115953398B (en) | Defect identification method for strip steel surface | |
| CN116228780B (en) | Silicon wafer defect detection method and system based on computer vision | |
| CN115330645A (en) | Welding image enhancement method | |
| CN115049656A (en) | Method for identifying and classifying defects in silicon steel rolling process | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN117764864B (en) | Nuclear magnetic resonance tumor visual detection method based on image denoising | |
| CN116883412B (en) | Graphene far infrared electric heating equipment fault detection method | |
| CN112668725A (en) | Metal hand basin defect target training method based on improved features | |
| CN116612112A (en) | Visual inspection method for surface defects of bucket | |
| CN117078688B (en) | Surface defect identification method for strong-magnetic neodymium-iron-boron magnet | |
| CN117541582B (en) | IGBT insulation quality detection method for high-frequency converter | |
| CN117437238B (en) | Visual inspection method for surface defects of packaged IC | |
| CN115254674B (en) | Bearing defect sorting method | |
| US20230386023A1 (en) | Method for detecting medical images, electronic device, and storage medium |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230216 Address after: 226000 Heping North Road, Huilong Town, Qidong City, Nantong City, Jiangsu Province (in Qidong Wangsheng Electronic Technology Co., Ltd.) Patentee after: Nantong ketesen New Material Technology Co.,Ltd. Address before: 226000 No. 1, Xinglong Road, Qidong science and technology entrepreneurship Park, Nantong City, Jiangsu Province Patentee before: JIANGSU GUANSEN NEW MATERIAL TECHNOLOGY CO.,LTD. |
|
| TR01 | Transfer of patent right |