Image processing method for identifying soft argon blowing pattern area of steel ladle

Abstract

The invention provides an image processing method for identifying a soft blowing argon pattern area of a steel ladle, which relates to the field of image processing, and comprises the following steps: collecting an argon pattern image of a slag surface of the steel ladle; preprocessing: carrying out edge detection on the image; an optimal edge oval shape is fitted; determining an action area of an argon port; carrying out dynamic region segmentation on the exposed molten iron and the steel slag; identifying effective argon flower areas of the two branches; and the argon flow of the two branches is adjusted. According to the method, the argon flow of each branch is accurately regulated and controlled according to the identified argon pattern size of each branch, so that the identified argon pattern size of each branch reaches the set size, the stability and consistency of the soft blowing process can be remarkably improved, the production requirements are better met, and the production effect is improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to an image processing method for identifying the area of ​​soft argon blowing in a ladle. Background Art

[0002] The ladle bottom argon blowing technology is mainly used in the steel smelting process. This technology blows argon into the bottom of the ladle to form argon flowers, thereby promoting full contact between liquid metal and gas, achieving the purpose of stirring molten steel, removing impurities, temperature control, and improving metal quality. In order to improve the argon stirring efficiency, most steel mills use double argon port ladles. The two argon ports are arranged at a certain angle at the bottom of the ladle, allowing argon to be blown into the molten steel through different channels at the same time to form argon flowers. Argon flowers refer to the bubbles and gas flow phenomenon formed by the interaction of bottom-blown argon and liquid metal. As the molten steel surges, the steel slag originally on the liquid surface is blown away or dispersed, so that the molten steel exposed to the surging liquid surface is the argon flower. It can be understood that the larger the bottom blowing argon flow rate, the larger the area of ​​the argon flower. The process of ladle argon blowing is usually divided into three stages according to the argon blowing intensity: strong blowing, medium blowing, and soft blowing. This grading method helps to improve production efficiency and reduce costs.

[0003] Generally, the argon blowing flow rate is large during the strong blowing and medium blowing stages, and the argon flowers blown out of the two branches of the molten steel surface will blend together, making it difficult to distinguish the argon flower areas produced by each argon port to accurately control the flow rates of the two branches. In the soft blowing stage, the argon blowing flow rate is small, and the argon flower areas blown out of the two argon ports can usually be clearly distinguished. In addition, the soft blowing stage is crucial to the overall effect of argon blowing in the ladle, which not only affects the chemical composition and physical properties of the molten steel, but is also directly related to the quality of the final product. Therefore, in actual operation, accurately controlling the size of the argon flowers in the soft blowing stage is an important part of improving the efficiency of steel production.

[0004] As metallurgical processes become increasingly complex, the requirements for argon flow control are becoming increasingly stringent. Traditional methods usually use fixed flow or operators to visually monitor the liquid level to control the flow, which cannot flexibly respond to the needs under different working conditions and is difficult to standardize operations. It is difficult to distinguish the argon flower areas generated by each argon port to accurately control the flow of the two branches.

[0005] Among the existing technologies for regulating the flow rate of soft-blowing argon gas through images, most methods lack independent regulation of the flow rate of argon gas in a single branch, and usually only rely on the brightness of the overall image or the argon flower area identified in the entire ladle to adjust the overall flow rate. This control method may not meet the actual process requirements, because in the soft-blowing process, the size of the argon flowers blown out of the two branches needs to meet the process standards to achieve the best effect. Although the Chinese patent with publication number CN114943743A proposes to divide the image into two parts and regard the areas identified in the two parts of the image as the argon flowers blown out corresponding to the two branches, this simple one-size-fits-all segmentation method that does not fully consider the position of the argon port and the diffusion characteristics of the argon flowers on the liquid surface is likely to cause the argon flower part of a branch to be incorrectly divided into another part, thereby causing inaccurate flow control.

[0006] Secondly, current technology generally regards all exposed molten steel on the ladle liquid surface as an effective argon flower area. However, in the soft blowing stage, in fact, only the tumbling exposed molten steel blown out near the argon port is an effective argon flower area, and the exposed molten steel due to molten steel shaking or slag surface cracking cannot effectively feedback the size of the argon blowing flow rate. Mistaking these non-effective areas for argon flowers will lead to inaccurate flow control, thereby affecting the degassing effect and the final molten steel quality. Summary of the invention

[0007] The present application is made in view of the above-mentioned problems, and its purpose is to provide an image processing method for identifying the area of ​​argon flower in ladle soft blowing. By considering the specific position of the argon port, the effective argon flower area of ​​each branch can be identified more accurately, avoiding the errors caused by a one-size-fits-all approach, and can effectively reduce the misidentification of molten steel exposed due to liquid surface swaying or slag surface cracking as argon flower, thereby improving the accuracy of the recognition result. The argon flow rate of each branch can be accurately controlled by the size of the argon flower identified in each branch, so that the size of the argon flower identified in each branch reaches the set size, which can significantly improve the stability and consistency of the soft blowing process, better meet production requirements, and improve production effects.

[0008] Specifically, the first aspect of the present application provides an image processing method for identifying the area of ​​soft argon blowing in a ladle, comprising the following steps: Step 1: Collect the argon flower image on the ladle slag surface; Ladle slag surface refers to the slag layer formed on the surface of molten steel during the steelmaking process. Steel slag is a by-product generated by the reaction of lime and other solvents added to remove impurities (such as silicon, oxygen, carbon, phosphorus, sulfur, etc.) in molten steel during the steelmaking process. It usually floats on the surface of molten steel to form a slag layer.

[0009] Argon flower images on the ladle slag surface refer to the bubbles and fluctuations formed on the slag surface due to the stirring effect of argon gas during the argon blowing process at the bottom of the ladle. These argon flower images can be captured by camera equipment and used to analyze the dynamic changes of the molten steel and slag layer in the ladle.

[0010] Step 2: Preprocess and detect edges of the acquired images; The edge detection algorithm is used to perform edge detection on the image to extract the edge information of the ladle.

[0011] Step 3: Based on the edge information of the ladle, an optimal edge ellipse shape is fitted by fitting technology; Get the center point coordinates of the edge ellipse shape ( , ), semi-major axis length a, semi-minor axis length b and tilt angle ; Step 4: Determine the position of the argon port on the image according to the ladle number, and determine the effective area of ​​the argon port according to the image; Step 5: Calculate the grayscale average of all pixels within the ladle ellipse outline , and set the segmentation threshold range and grayscale average range based on the grayscale average value to perform dynamic area segmentation; It is necessary to set the minimum and maximum values ​​of the segmentation threshold, the minimum and maximum values ​​of the grayscale average, and perform dynamic area segmentation of exposed molten iron and slag.

[0012] Step 6: Perform threshold segmentation on the image based on the segmentation threshold to obtain a binary image, extract the effective contour information of the exposed molten steel area, and identify the effective argon flower areas of the two branches respectively in combination with the geometric position of the argon port and the diffusion characteristics of the argon flower on the liquid surface, and calculate the corresponding argon flower diameter; Step 7: Adjust the argon flow rate of the current branch according to the difference between the argon flower diameter of the current branch and the set soft blowing argon flower diameter.

[0013] The stop time of the argon flow is adjusted so that the calculated argon flower diameters of the two branches meet the process requirements.

[0014] Furthermore, the step 2 specifically includes: performing grayscale processing on the image, using a Sobel operator or a Canny operator to perform edge detection on the preprocessed image, and extracting edge information of the ladle.

[0015] The Sobel operator detects edges by calculating the gradient of the image in the horizontal and vertical directions. It uses a 3x3 convolution kernel to perform differential operations on the image in the x and y directions respectively, and then takes the square root of the sum of the squares of the two results to obtain an edge intensity image.

[0016] The Canny operator is a multi-stage edge detection algorithm that includes Gaussian filtering, gradient calculation, non-maximum suppression, double threshold detection, and edge connection. It can detect edges in images more accurately, reduce the impact of noise, and provide clear edge contours.

[0017] If the edge detection speed is high and the image noise is low, the Sobel operator can be selected as a fast edge detection method. If higher edge detection accuracy and robustness are required, the Canny operator is used.

[0018] Furthermore, in the step three, the fitting process is specifically performed by using the least squares method for fitting.

[0019] The least squares method has important application value in image edge fitting, and can effectively extract geometric features and optimize the fitting effect.

[0020] Furthermore, the step 4 specifically includes: The ladle number is identified through the image, and the position of the argon port center in the image is determined according to the argon port distribution position of the corresponding ladle. A circle with a radius of 1 / 3 of the ladle radius is drawn with the argon port center as the effective area of ​​​​the argon port.

[0021] Furthermore, the dynamic region segmentation specifically includes: (1) When When the grayscale average value is less than or equal to the minimum value set: ; (2) When Greater than the minimum grayscale average value And less than the set maximum grayscale average value hour: ; (3) When Greater than or equal to the maximum grayscale average value set hour: ; in: is the segmentation threshold; is the minimum value of segmentation threshold; is the grayscale average of all pixels within the elliptical outline of the ladle; is the minimum grayscale average value; is the maximum grayscale average value; is the maximum value of the segmentation threshold.

[0022] Furthermore, the image is segmented based on the segmentation threshold to obtain a binary image, and effective contour information of the exposed molten steel area is extracted, specifically including: The image is segmented according to the segmentation threshold, and finally a binary image is obtained. The contour features of all exposed molten steel areas in the binary image are extracted, and the contour areas with a contour area smaller than the set minimum contour area are removed. The number of valid contours is N, and the area of ​​the i-th contour is .

[0023] Furthermore, the effective argon flower areas of the two branches are identified respectively in combination with the geometric position of the argon port and the diffusion characteristics of the argon flower on the liquid surface, specifically including: Step 2.1: Calculate the area of ​​all valid contours in the argon port area of ​​each branch, then calculate the ratio of the area of ​​each valid contour in the branch area to the total area of ​​this contour, and then calculate the ratio of the area of ​​each valid contour in the branch area to the total area of ​​the corresponding branch area. The formula is as follows: ; ; ; ; in: is the ratio of the area of ​​the i-th valid contour located in the branch 1 region to the total area of ​​this contour; is the area of ​​the i-th valid contour located in the branch 1 region; is the area of ​​the i-th effective contour; is the ratio of the area of ​​the i-th valid contour located in the branch 2 region to the total area of ​​this contour; is the area of ​​the i-th valid contour located in the branch 2 region; is the ratio of the area of ​​the i-th effective contour located in the branch 1 region to the total area of ​​the branch 1 region; is the ratio of the area of ​​the i-th effective contour located in the branch 2 region to the total area of ​​the branch 2 region; is the total area of ​​branch 1; is the total area of ​​branch 2; Step 2.2: Set the weight W and calculate the probability score of each valid contour being a valid argon flower blown out by two branches. The formula is as follows: ; ; in: is the probability score that the i-th valid profile is a valid argon flower blown out by branch 1; is the weight; is the ratio of the area of ​​the i-th valid contour located in the branch 1 region to the total area of ​​this contour; is the ratio of the area of ​​the i-th effective contour located in the branch 1 region to the total area of ​​the branch 1 region; is the probability score that the i-th valid profile is a valid argon flower blown out by branch 2; is the ratio of the area of ​​the i-th valid contour located in the branch 2 region to the total area of ​​this contour; is the ratio of the area of ​​the i-th effective contour located in the branch 2 region to the total area of ​​the branch 2 region; Step 2.3: Find the index of the contour with the highest probability score in the two branches, denoted as , , determine whether the highest score in the branch is greater than the set minimum score If it is greater than the set minimum score, the corresponding index is added to the valid argon flower area index list of the corresponding branch; Step 2.4: After identifying the most likely valid argon flower contour in each branch, further determine whether the contours around it also belong to the valid argon flower area; Step 2.5: For the case where the same index number appears in the valid argon flower index list of two branches at the same time, further determine whether the profiles corresponding to these indexes belong to branch 1 or branch 2; Step 2.6: Calculate the sum of the areas of all the contours corresponding to the indexes in the effective argon flower area index list of the two branches respectively, calculate the argon flower ratio of the two branches and convert the argon flower ratio into the equivalent diameter of the argon flower on the slag surface.

[0024] Furthermore, the step 2.4 specifically includes: If the valid argon flower index list of the current branch is not empty, calculate the centroid coordinates of the corresponding contour according to the unique index in the list, take the centroid as the center of the circle, and use the diagonal length of the minimum circumscribed rectangle of the contour to determine the radius of the circle, thereby drawing a circular area; For all other valid contours, check whether their center of gravity is within the above circular area and confirm whether their probability score of valid argon flower is higher than the preset minimum threshold. If the above two conditions are met at the same time, it is judged as a valid contour, and the indexes of these valid contours are added to the valid argon flower area index list of the corresponding branch.

[0025] Furthermore, the step 2.5 specifically includes: The Euclidean distance between the centroid of the contour corresponding to each overlapping index and the center coordinates of the argon ports of branch 1 and branch 2 is calculated in turn; If the distance between the centroid of a certain contour and the center of the argon outlet of branch 1 is smaller than the distance between the centroid of a certain contour and the center of the argon outlet of branch 2, the contour is judged to belong to branch 1 and is deleted from the index list of branch 2. On the contrary, if it is closer to the argon port center of branch 2, the contour is determined to belong to branch 2 and is deleted from the index list of branch 1.

[0026] Furthermore, the calculation of the argon flower ratio of the two branches and converting the argon flower ratio into an equivalent diameter of the argon flower on the slag surface specifically includes: Calculate the sum of the areas of all the index-corresponding contours in the effective argon flower area index list of the two branches respectively. Divide these two areas by the total area of ​​the ladle contour to get the argon flower ratio of the two branches. Then convert the argon flower ratio into the equivalent diameter of the argon flower on the slag surface. The formula is as follows: ; ; in: is the equivalent diameter of the argon flower on the slag surface in branch 1; is the actual diameter of the ladle; is the argon flower ratio of branch 1; is the equivalent diameter of the argon flower on the slag surface in branch 2; is the argon flower ratio of branch 2.

[0027] Since the argon blowing process requirements generally limit the actual diameter of the argon flower, for example, the diameters of the argon flowers in the two branches during the soft blowing stage are required to be within 100mm-200mm, it is more reasonable to convert the argon flower ratio into the equivalent diameter of the argon flower on the slag surface to control the argon flow rate.

[0028] In the second aspect, the present application also provides a computing device, which has the function of implementing the method described in the first aspect above. The beneficial effects can be found in the description of the first aspect, which will not be repeated here. The function can be implemented by hardware, or by executing the corresponding software implementation through hardware. The hardware or software includes one or more modules corresponding to the above functions. In one possible design, the structure of the device includes an acquisition module, a training module, and optionally, a construction module. These modules can implement the function of the training node in the method example of the first aspect above. Please refer to the detailed description in the method example for details, which will not be repeated here.

[0029] In the third aspect, the present application also provides a computing device, which is used to implement the functions of the method described in the first aspect above. The beneficial effects can be found in the description of the first aspect and will not be repeated here. The structure of the computing device includes a processor and a memory, and the memory is used to store instructions and / or data. The memory is coupled to the processor, and when the processor executes the program instructions stored in the memory, the function of the training node in the example of the first aspect above can be implemented. The structure of the computing device also includes a communication interface for communicating with other devices.

[0030] In a fourth aspect, the present application also provides a computer-readable storage medium, in which instructions are stored, and when the computer-readable storage medium is run on a computer, the computer executes the method in the above-mentioned first aspect and various possible designs of the first aspect.

[0031] In a fifth aspect, the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method in the above-mentioned first aspect and various possible designs of the first aspect.

[0032] In a sixth aspect, the present application also provides a computing chip, which is connected to a memory, and the chip is used to read and execute a software program stored in the memory, and to execute the methods in the above-mentioned first aspect and various possible implementation methods of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present drawings or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present drawings. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0034] Figure 1 is a flow chart of the steps of the present invention; Figure 2 This is a schematic diagram of the argon action area according to an embodiment of the present invention; The purpose, features and advantages of this figure will be further described in conjunction with the embodiments with reference to the accompanying drawings. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0036] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0037] Unless otherwise specified, all embodiments and optional embodiments of the present application can be combined with each other to form a new technical solution.

[0038] Unless otherwise specified, all technical features and optional technical features of this application can be combined with each other to form a new technical solution.

[0039] If there is no special explanation, all steps of the present application can be performed sequentially or randomly, preferably sequentially. For example, the method includes steps (a) and (b), which means that the method may include steps (a) and (b) performed sequentially, or may include steps (b) and (a) performed sequentially. For example, the method may further include step (c), which means that step (c) may be added to the method in any order. For example, the method may include steps (a), (b) and (c), or may include steps (a), (c) and (b), or may include steps (c), (a) and (b), etc.

[0040] If there is no special explanation, the "include" and "comprising" mentioned in this application are open-ended or closed-ended. For example, the "include" and "comprising" may mean that other components not listed may also be included or only the listed components may be included or only the listed components may be included.

[0041] If not specifically stated, in this application, the term "or" is inclusive. For example, the phrase "A or B" means "A, B, or both A and B". More specifically, any of the following conditions satisfies the condition "A or B": A is true (or exists) and B is false (or does not exist); A is false (or does not exist) and B is true (or exists); or both A and B are true (or exist).

[0042] In order to better understand the solutions of the embodiments of the present application, some relevant terms and concepts that may be involved in the embodiments of the present application are first introduced below.

[0043] (1) Ladle is a container used to hold and transport molten steel during the steelmaking process. During the steelmaking process, the ladle is often used for secondary refining of molten steel, for example, stirring by blowing argon gas from the bottom to even out the composition and temperature of the molten steel and to promote the floating and removal of inclusions.

[0044] (2) Soft blowing is a steelmaking operation mode, which usually refers to the introduction of a small flow of oxygen into the molten pool during the converter steelmaking process to effectively control the molten pool temperature, generally controlled at 1650-1750°C. In the soft blowing mode, a layer of slag is covered on the surface of the molten pool, which is beneficial to the desulfurization and dephosphorization of the molten steel.

[0045] (3) Argon bloom refers to the phenomenon of bubbles and gas flow formed by the interaction between the bottom-blown argon gas and the liquid metal. As the molten steel surges, the slag originally on the liquid surface is blown away or dispersed, and the molten steel exposed on the surging liquid surface is the argon bloom.

[0046] In this embodiment, Figure 1 As shown, an image processing method for identifying the soft argon blowing area of ​​a ladle comprises the following steps: Step 1: Collect the argon flower image on the ladle slag surface; Ladle slag surface refers to the slag layer formed on the surface of molten steel during the steelmaking process. Steel slag is a by-product generated by the reaction of lime and other solvents added to remove impurities (such as silicon, oxygen, carbon, phosphorus, sulfur, etc.) in molten steel during the steelmaking process. It usually floats on the surface of molten steel to form a slag layer.

[0047] Argon flower images on the ladle slag surface refer to the bubbles and fluctuations formed on the slag surface due to the stirring effect of argon gas during the argon blowing process at the bottom of the ladle. These argon flower images can be captured by camera equipment and used to analyze the dynamic changes of the molten steel and slag layer in the ladle.

[0048] The image is taken by a camera installed above the ladle to reflect the state of the ladle liquid level and the distribution of slag and argon flowers.

[0049] Step 2: Preprocess and detect edges of the acquired images; The edge detection algorithm is used to perform edge detection on the image to extract the edge information of the ladle.

[0050] Step 3: Based on the edge information of the ladle, an optimal edge ellipse shape is fitted by fitting technology; Get the center point coordinates of the edge ellipse shape ( , ), semi-major axis length a, semi-minor axis length b and tilt angle ; Step 4: Determine the position of the argon port on the image according to the ladle number, and determine the effective area of ​​the argon port according to the image; Step 5: Calculate the grayscale average of all pixels within the ladle ellipse outline , and set the segmentation threshold range and grayscale average range based on the grayscale average value to perform dynamic area segmentation; It is necessary to set the minimum and maximum values ​​of the segmentation threshold, the minimum and maximum values ​​of the grayscale average, and perform dynamic area segmentation of exposed molten iron and slag.

[0051] Step 6: Perform threshold segmentation on the image based on the segmentation threshold to obtain a binary image, extract the effective contour information of the exposed molten steel area, and identify the effective argon flower areas of the two branches respectively in combination with the geometric position of the argon port and the diffusion characteristics of the argon flower on the liquid surface, and calculate the corresponding argon flower diameter; Step 7: Adjust the argon flow rate of the current branch according to the difference between the argon flower diameter of the current branch and the set soft blowing argon flower diameter.

[0052] The stop time of the argon flow is adjusted so that the calculated argon flower diameters of the two branches meet the process requirements.

[0053] Furthermore, the step 2 specifically includes: performing grayscale processing on the image, using a Sobel operator or a Canny operator to perform edge detection on the preprocessed image, and extracting edge information of the ladle.

[0054] The Sobel operator detects edges by calculating the gradient of the image in the horizontal and vertical directions. It uses a 3x3 convolution kernel to perform differential operations on the image in the x and y directions respectively, and then takes the square root of the sum of the squares of the two results to obtain an edge intensity image.

[0055] The Canny operator is a multi-stage edge detection algorithm that includes Gaussian filtering, gradient calculation, non-maximum suppression, double threshold detection, and edge connection. It can detect edges in images more accurately, reduce the impact of noise, and provide clear edge contours.

[0056] If the edge detection speed is high and the image noise is low, the Sobel operator can be selected as a fast edge detection method. If higher edge detection accuracy and robustness are required, the Canny operator is used.

[0057] Furthermore, in step three, the fitting process is specifically performed by using the least squares method.

[0058] The least squares method has important application value in image edge fitting, and can effectively extract geometric features and optimize the fitting effect.

[0059] Furthermore, step four specifically includes: The ladle number is identified through the image, and the position of the argon port center in the image is determined according to the argon port distribution position of the corresponding ladle. A circle with a radius of 1 / 3 of the ladle radius is drawn with the argon port center as the effective area of ​​​​the argon port.

[0060] like Figure 2 As shown, the ladle mouth contour is obtained by step 2, and two argon ports are distributed on both sides of the ladle at an angle of 120°. The distance from the center of the ladle is 2 / 3 of the radius of the ladle. Therefore, the position of the argon port center on the image can be determined, namely, the branch 1 argon port and the branch 2 argon port in the figure, a is the semi-major axis length of the elliptical ladle contour, and b is the semi-minor axis length of the elliptical ladle contour.

[0061] Furthermore, dynamic region segmentation specifically includes: (1) When When the grayscale average value is less than or equal to the minimum value set: ; (2) When Greater than the minimum grayscale average value And less than the set maximum grayscale average value hour: ; (3) When Greater than or equal to the maximum grayscale average value set hour: ; Dynamically determining the segmentation threshold can ensure more accurate regional segmentation under different argon blowing intensities and liquid surface slag conditions, providing an accurate basis for subsequent analysis.

[0062] Furthermore, based on the segmentation threshold, the image is segmented to obtain a binary image, and effective contour information of the exposed molten steel area is extracted, specifically including: The image is segmented according to the segmentation threshold, and finally a binary image is obtained. The contour features of all exposed molten steel areas in the binary image are extracted, and the contour areas with a contour area smaller than the set minimum contour area are removed. The number of valid contours is N, and the area of ​​the i-th contour is .

[0063] Furthermore, the effective argon flower areas of the two branches are identified respectively in combination with the geometric position of the argon port and the diffusion characteristics of the argon flower on the liquid surface, specifically including: Step 2.1: Calculate the area of ​​all valid contours in the argon port area of ​​each branch, then calculate the ratio of the area of ​​each valid contour in the branch area to the total area of ​​this contour, and then calculate the ratio of the area of ​​each valid contour in the branch area to the total area of ​​the corresponding branch area. The formula is as follows: ; ; ; ; Step 2.2: Set the weight W and calculate the probability score of each valid contour being a valid argon flower blown out by two branches. The formula is as follows: ; ; Step 2.3: Find the index of the contour with the highest probability score in the two branches, denoted as , , determine whether the highest score in the branch is greater than the set minimum score If it is greater than the set minimum score, the corresponding index is added to the valid argon flower area index list of the corresponding branch; Step 2.4: After identifying the most likely valid argon flower contour in each branch, further determine whether the contours around it also belong to the valid argon flower area; Step 2.5: For the case where the same index number appears in the valid argon flower index list of two branches at the same time, further determine whether the profiles corresponding to these indexes belong to branch 1 or branch 2; Step 2.6: Calculate the sum of the areas of all the contours corresponding to the indexes in the effective argon flower area index list of the two branches respectively, calculate the argon flower ratio of the two branches and convert the argon flower ratio into the equivalent diameter of the argon flower on the slag surface.

[0064] Furthermore, step 2.4 specifically includes: If the valid argon flower index list of the current branch is not empty, calculate the centroid coordinates of the corresponding contour according to the unique index in the list, take the centroid as the center of the circle, and use the diagonal length of the minimum circumscribed rectangle of the contour to determine the radius of the circle, thereby drawing a circular area; For all other valid contours, check whether their center of gravity is within the above circular area and confirm whether their probability score of valid argon flower is higher than the preset minimum threshold. If the above two conditions are met at the same time, it is judged as a valid contour, and the indexes of these valid contours are added to the valid argon flower area index list of the corresponding branch.

[0065] Furthermore, step 2.5 specifically includes: The Euclidean distance between the centroid of the contour corresponding to each overlapping index and the center coordinates of the argon ports of branch 1 and branch 2 is calculated in turn; If the distance between the centroid of a certain contour and the center of the argon outlet of branch 1 is smaller than the distance between the centroid of a certain contour and the center of the argon outlet of branch 2, the contour is judged to belong to branch 1 and is deleted from the index list of branch 2. On the contrary, if it is closer to the argon port center of branch 2, the contour is determined to belong to branch 2 and is deleted from the index list of branch 1.

[0066] Furthermore, the argon flower ratios of the two branches are calculated and converted into the equivalent diameter of the argon flower on the slag surface, specifically including: Calculate the sum of the areas of all the index-corresponding contours in the effective argon flower area index list of the two branches respectively. Divide these two areas by the total area of ​​the ladle contour to get the argon flower ratio of the two branches. Then convert the argon flower ratio into the equivalent diameter of the argon flower on the slag surface. The formula is as follows: ; ; Since the argon blowing process requirements generally limit the actual diameter of the argon flower, for example, the diameters of the argon flowers in the two branches during the soft blowing stage are required to be within 100mm-200mm, it is more reasonable to convert the argon flower ratio into the equivalent diameter of the argon flower on the slag surface to control the argon flow rate.

[0067] It should be noted that the present application is not limited to the above-mentioned embodiments. The above-mentioned embodiments are only examples, and the embodiments having the same structure as the technical idea and exerting the same effect within the scope of the technical solution of the present application are all included in the technical scope of the present application. In addition, without departing from the scope of the main purpose of the present application, various modifications that can be thought of by those skilled in the art to the embodiments and other methods of combining some of the constituent elements in the embodiments are also included in the scope of the present application.

Claims

1. An image processing method for identifying the area of ​​soft argon blowing in a ladle, characterized in that: The following steps are involved: Step 1: Collect the argon flower image on the ladle slag surface; Step 2: Preprocess and detect edges of the acquired images; Step 3: Fitting an optimal edge ellipse shape based on the edge information of the ladle; Step 4: Determine the position of the argon port on the image according to the ladle number, and determine the effective area of ​​the argon port according to the image; Step 5: Based on the grayscale average of all pixels within the ladle ellipse outline Set the segmentation threshold range and grayscale average range to perform dynamic area segmentation; Step 6: Perform threshold segmentation on the image based on the segmentation threshold to obtain a binary image, identify the effective argon flower areas of the two branches respectively based on the argon port position and the diffusion characteristics of the argon flower on the liquid surface, and calculate the corresponding argon flower diameters; Step 7: Adjust the argon flow rate of the current branch according to the difference between the argon flower diameter of the current branch and the set argon flower diameter.

2. The image processing method for identifying the soft argon blowing area of ​​a ladle according to claim 1, characterized in that: The step 2 specifically includes: performing grayscale processing on the image, using a Sobel operator or a Canny operator to perform edge detection on the pre-processed image, and extracting edge information of the ladle.

3. The image processing method for identifying the soft argon blowing area of ​​a ladle according to claim 1, characterized in that: In the step three, the fitting process is specifically to adopt the least squares method for fitting.

4. The image processing method for identifying the soft argon blowing area of ​​a ladle according to claim 1, characterized in that: The step 4 specifically includes: The ladle number is identified through the image, and the position of the argon port center in the image is determined according to the argon port distribution position of the corresponding ladle. A circle with a radius of 1 / 3 of the ladle radius is drawn with the argon port center as the effective area of ​​​​the argon port.

5. The image processing method for identifying the soft argon blowing area of ​​a ladle according to claim 1, characterized in that: The dynamic region segmentation specifically includes: (1) When When the grayscale average value is less than or equal to the minimum value set: ； (2) When Greater than the minimum grayscale average value And less than the set maximum grayscale average value hour: ； (3) When Greater than or equal to the maximum grayscale average value set hour: ； in: is the segmentation threshold; is the minimum value of segmentation threshold; is the grayscale average of all pixels within the elliptical outline of the ladle; is the minimum grayscale average value; is the maximum grayscale average value; is the maximum value of the segmentation threshold.

6. The image processing method for identifying the soft argon blowing area of ​​a ladle according to claim 1, characterized in that: The step of performing threshold segmentation on the image based on the segmentation threshold to obtain a binary image and extracting effective contour information of the exposed molten steel area specifically includes: The image is segmented according to the segmentation threshold, and finally a binary image is obtained. The contour features of all exposed molten steel areas in the binary image are extracted, and the contour areas with a contour area smaller than the set minimum contour area are removed. The number of valid contours is N, and the area of ​​the i-th contour is .

7. The image processing method for identifying the soft argon blowing area of ​​a ladle according to claim 1, characterized in that: The method of identifying the effective argon flower areas of the two branches respectively in combination with the geometric position of the argon port and the diffusion characteristics of the argon flower on the liquid surface specifically includes: Step 2.1: Calculate the area of ​​all valid contours located in the argon port area of ​​each branch, then calculate the ratio of the area of ​​each valid contour located in the branch area to the total area of ​​the contour, and then calculate the ratio of the area of ​​each valid contour located in the branch area to the total area of ​​the corresponding branch area; Step 2.2: Set the weight W and calculate the probability score of each valid contour being a valid argon flower blown out by the two branches; Step 2.3: Find the index of the contour with the highest probability score in the two branches, denoted as , , determine whether the highest score in the branch is greater than the set minimum score If it is greater than the set minimum score, the corresponding index is added to the valid argon flower area index list of the corresponding branch; Step 2.4: After identifying the most likely valid argon flower contour in each branch, further determine whether the contours around it also belong to the valid argon flower area; Step 2.5: For the case where the same index number appears in the valid argon flower index list of two branches at the same time, further determine whether the profiles corresponding to these indexes belong to the first branch or the second branch; Step 2.6: Calculate the sum of the areas of all the contours corresponding to the indexes in the effective argon flower area index list of the two branches respectively, calculate the argon flower ratio of the two branches and convert the argon flower ratio into the equivalent diameter of the argon flower on the slag surface.

8. The image processing method for identifying the soft argon blowing area of ​​a ladle according to claim 7, characterized in that: The step 2.4 specifically includes: If the valid argon flower index list of the current branch is not empty, calculate the centroid coordinates of the corresponding contour according to the unique index in the list, take the centroid as the center of the circle, and use the diagonal length of the minimum circumscribed rectangle of the contour to determine the radius of the circle, thereby drawing a circular area; For all other valid contours, check whether their center of gravity is within the above circular area and confirm whether their probability score of valid argon flower is higher than the preset minimum threshold. If the above two conditions are met at the same time, it is judged as a valid contour, and the indexes of these valid contours are added to the valid argon flower area index list of the corresponding branch.

9. The image processing method for identifying the soft argon blowing area of ​​a ladle according to claim 7, characterized in that: The step 2.5 specifically includes: The Euclidean distance between the centroid of the contour corresponding to each overlapping index and the center coordinates of the argon ports of branch 1 and branch 2 is calculated in turn; If the distance between the centroid of a certain contour and the center of the argon outlet of branch 1 is smaller than the distance between the centroid of a certain contour and the center of the argon outlet of branch 2, the contour is judged to belong to branch 1 and is deleted from the index list of branch 2. On the contrary, if it is closer to the center of the argon port of branch 2, the contour is determined to belong to branch 2 and is deleted from the index list of branch 1.

10. The image processing method for identifying the soft argon blowing area of ​​a ladle according to claim 7, characterized in that: The calculating of the argon flower ratio of the two branches and converting the argon flower ratio into an equivalent diameter of the argon flower on the slag surface specifically includes: Calculate the sum of the areas of all index-corresponding contours in the effective argon flower area index list of the two branches respectively, divide these two areas by the total area of ​​the ladle contour to get the argon flower ratio of the two branches, and then convert the argon flower ratio into the equivalent diameter of the argon flower on the slag surface.

Images