A method and device for monitoring the argon blowing process in a steel ladle.

Abstract

This application provides a method and device for monitoring the argon blowing process in a steel ladle, comprising: extracting multiple frames of monitoring images from a monitoring video of the argon blowing production site; identifying the ladle area and / or the argon blowing aperture range in each frame of the monitoring image; and determining the corresponding argon blowing monitoring parameters based on the ladle area and / or the argon blowing aperture range in the frame of the monitoring image. In this way, this application automatically identifies the ladle area and / or the argon blowing aperture range based on the monitoring images, thereby determining the monitoring parameters for argon blowing, which can avoid manual parameter measurement, reduce monitoring costs, and improve monitoring accuracy and efficiency.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a monitoring method and device for the argon blowing process in a ladle. Background Technology

[0002] Argon blowing in a ladle is a simple ladle refining method for degassing molten steel and removing non-metallic inclusions. This method is widely used due to its simplicity, inexpensive equipment, and significant refining effect. Traditional argon blowing processes require manual real-time monitoring of the refining status to adjust process parameters based on the monitoring results.

[0003] However, traditional manual monitoring methods are costly, subjective, and inaccurate. In addition, the monitoring personnel face high workloads and work environments that pose certain risks. These factors greatly limit the efficiency of the argon blowing process. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a monitoring method and device for the argon blowing process in a ladle, which can automatically identify the ladle range and / or the argon blowing aperture range based on the monitoring image, thereby determining the monitoring parameters for argon blowing in the ladle, avoiding manual parameter measurement, reducing monitoring costs, and improving monitoring accuracy and efficiency.

[0005] This application provides a method for monitoring the argon blowing process in a steel ladle, the monitoring method comprising:

[0006] Extract multiple frames of monitoring images from the monitoring video of the argon blowing production site in the ladle;

[0007] For each frame of monitoring image, identify the ladle range and / or argon blowing aperture range in that frame of monitoring image;

[0008] Based on the ladle range and / or argon blowing aperture range in the monitoring image frame, determine the ladle argon blowing monitoring parameters corresponding to the monitoring image frame.

[0009] Furthermore, the argon blowing aperture includes a dark argon blowing aperture in the molten steel and a bright argon blowing aperture on the surface of the molten steel; for each frame of monitoring image, the ladle range and / or argon blowing aperture range in that frame of monitoring image are identified, including:

[0010] The monitoring image frame is input into a pre-trained first target detection model to identify and label the ladle area in the monitoring image frame; and / or,

[0011] The monitoring image frame is input into a pre-trained second target detection model to identify and label the range of dark argon-blown apertures in the monitoring image frame.

[0012] Compare the monitoring image frame with multiple adjacent monitoring images of the same frame to determine whether the monitoring image frame corresponds to the argon blowing stage;

[0013] If so, the monitoring image frame is converted to the HSV color space, and the red pixel area in the converted monitoring image frame is marked as the highlight argon aperture range in the monitoring image frame.

[0014] Furthermore, when the ladle argon blowing monitoring parameters include the aperture area, the ladle argon blowing monitoring parameters corresponding to the monitoring image frame are determined based on the argon blowing aperture range in that frame of the monitoring image, including:

[0015] Determine the number of pixels corresponding to the argon blowing aperture range in the monitoring image frame;

[0016] Based on the mapping relationship between pixels and physical areas in the real world, the number of pixels corresponding to the argon-blown aperture range is converted into aperture area.

[0017] Furthermore, when the ladle argon blowing monitoring parameters include the free space height from the molten steel surface to the edge of the ladle, the ladle argon blowing monitoring parameters corresponding to the monitoring image frame are determined based on the ladle range in the monitoring image frame, including:

[0018] Based on the ladle range in the monitoring image frame, an image is extracted from the monitoring image frame and converted to the HSV color space to obtain the ladle image;

[0019] The ladle image is traversed pixel by pixel from top to bottom. Based on the ladle edge position points and the contact position points between the molten steel and the inner edge of the ladle determined by the traversal, the average free space height pixel count in the ladle image is determined.

[0020] Convert the average free space height pixel count to the real-world free space height.

[0021] Furthermore, the step of performing a pixel-by-pixel traversal of the ladle image from top to bottom, and determining the average free space height pixel count in the ladle image based on the ladle edge positions and the contact points between the molten steel and the inner edge of the ladle determined by the traversal, includes:

[0022] During the traversal of each pixel column, the first yellow pixel encountered is marked as the ladle edge position point corresponding to that pixel column, the first red pixel encountered is marked as the contact position point between the molten steel and the inner edge of the ladle corresponding to that pixel column, and that pixel column is determined as a target pixel column.

[0023] The number of pixels between the ladle edge location point and the contact location point in each target pixel column is determined as the number of pixels in the free space height;

[0024] The average free space height pixel count is determined based on the number of free space height pixels in each target pixel column.

[0025] Furthermore, when the ladle argon blowing monitoring parameters include the slag grayscale value, the ladle argon blowing monitoring parameters corresponding to the monitoring image frame are determined based on the ladle range and argon blowing aperture range in the monitoring image frame, including:

[0026] Based on the ladle range in the monitoring image frame, an image is extracted from the monitoring image frame and converted to the HSV color space to obtain the ladle image;

[0027] The ladle image is traversed pixel by pixel in multiple directions, and the accurate ladle image is determined based on the ladle edge position points determined by the traversal.

[0028] The precise ladle image is binarized to extract the molten steel range image from the precise ladle image;

[0029] The argon-blowing aperture range is removed from the molten steel range image and converted to a grayscale image to obtain a slag grayscale image;

[0030] The average grayscale value in the grayscale image of the steel slag is determined as the grayscale value of the steel slag.

[0031] Furthermore, the ladle image is traversed pixel by pixel in multiple directions, and the precise ladle image is determined based on the ladle edge position points determined by the traversal, including:

[0032] Starting from each pixel on the top, bottom, left, and right sides of the ladle image, traverse pixel by pixel towards the center of the ladle image;

[0033] Mark the first yellow pixel encountered as the edge location of the ladle;

[0034] Based on the marked edge locations of the ladle, the precise ladle image is extracted from the ladle image.

[0035] This application embodiment also provides a monitoring device for the ladle argon blowing process, the monitoring device comprising:

[0036] The extraction module is used to extract multiple frames of monitoring images from the monitoring video of the ladle argon blowing production site;

[0037] The identification module is used to identify the ladle range and / or argon blowing aperture range in each frame of the monitoring image.

[0038] The determination module is used to determine the ladle argon blowing monitoring parameters corresponding to the monitoring image frame based on the ladle range and / or argon blowing aperture range in the monitoring image frame.

[0039] This application also provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of a monitoring method for a ladle argon blowing process as described above are performed.

[0040] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of a monitoring method for a ladle argon blowing process as described above.

[0041] The present application provides a method and device for monitoring the argon blowing process in a ladle, which can automatically identify the ladle range and / or the argon blowing aperture range based on the monitoring image, thereby determining the monitoring parameters for argon blowing in the ladle. This can avoid manual parameter measurement, reduce monitoring costs, and improve monitoring accuracy and efficiency.

[0042] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A flowchart of a monitoring method for a ladle argon blowing process provided in an embodiment of this application is shown;

[0045] Figure 2 A schematic diagram of the structure of a monitoring device for a ladle argon blowing process provided in an embodiment of this application is shown;

[0046] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0048] Research has shown that ladle argon blowing is a simple ladle refining method for degassing molten steel and removing non-metallic inclusions. This method is simple, requires inexpensive equipment, and produces significant refining results, thus gaining widespread application. Traditional argon blowing processes require manual real-time monitoring of the refining status to adjust process parameters based on the monitoring results.

[0049] However, traditional manual monitoring methods are costly, subjective, and inaccurate. In addition, the monitoring personnel face high workloads and work environments that pose certain risks. These factors greatly limit the efficiency of the argon blowing process.

[0050] Based on this, embodiments of this application provide a monitoring method and device for the argon blowing process in a steel ladle, so as to avoid manual measurement of parameters, reduce monitoring costs, and improve monitoring accuracy and efficiency.

[0051] Please see Figure 1 , Figure 1 This is a flowchart illustrating a monitoring method for a ladle argon blowing process provided in an embodiment of this application. The monitoring method provided in this embodiment can be applied to a ladle argon blowing monitoring system.

[0052] like Figure 1 As shown, the monitoring method includes:

[0053] S101. Extract multiple frames of monitoring images from the monitoring video of the argon blowing production site in the ladle.

[0054] Here, electronic devices with image acquisition capabilities, such as cameras, can be deployed at the ladle argon blowing production site to collect real-time monitoring video of the production process. Simultaneously, the cameras also have communication capabilities, allowing them to connect with the monitoring system and transmit the acquired video feed.

[0055] In this step, the camera can collect monitoring video data of the ladle argon blowing production site and send it to the monitoring system; the monitoring system acquires the video stream, extracts the monitoring images frame by frame, and performs subsequent monitoring methods on each monitoring image.

[0056] S102. For each frame of monitoring image, identify the ladle range and / or argon blowing aperture range in that frame of monitoring image.

[0057] In this step, for each frame of the monitoring image, YOLO target detection technology can be used to identify the ladle and / or the argon blowing aperture, and to determine its location in the monitoring image.

[0058] In specific implementation, for each frame of monitoring image, the range of steel ladles in that frame of monitoring image is identified, including: inputting the frame of monitoring image into a pre-trained first target detection model to identify and mark the range of steel ladles in that frame of monitoring image.

[0059] The first object detection model can be built based on the YOLOv5 network model and pre-trained using a calibrated ladle recognition training dataset. Existing technologies can be used for model training, and this application does not impose any restrictions. The trained first object detection model can perform inference detection on each frame of the monitoring image to identify and mark the location of the ladle, for example, by marking it on the monitoring image using a rectangular bounding box.

[0060] On the other hand, the argon blowing aperture during the ladle blowing process includes a dark aperture that appears to churn within the molten steel and a relatively calm, bright white aperture on the surface of the molten steel. For each frame of the monitoring image, the range of the argon blowing aperture in that frame is identified, including:

[0061] Step 1: Input the monitoring image frame into the pre-trained second target detection model to identify and mark the range of the dark argon-blown aperture in the monitoring image frame.

[0062] Here, the second object detection model can also be built based on the YOLOv5 network model and pre-trained using a calibrated aperture recognition training dataset. The training method for the model can also use existing techniques, and this application does not impose any restrictions. The trained second object detection model can perform inference detection on each frame of the monitoring image to identify and mark the range of the dark argon-blown aperture, for example, by marking it on the monitoring image using a rectangular box.

[0063] Step 2: Compare the monitoring image frame with multiple adjacent monitoring images of the same frame to determine whether the monitoring image frame corresponds to the argon blowing stage.

[0064] The bright white halo needs to be distinguished from the bright white appearance of the molten steel surface during the non-argon blowing stage, where it is not covered by slag. Therefore, this step uses a dynamic detection method to compare the current monitoring image with multiple adjacent monitoring images in terms of acquisition time to determine whether the current monitoring image corresponds to the argon blowing stage. Specifically, when the comparison determines that the liquid surface is churning, the argon blowing stage is identified, and the bright white area in the monitoring image at this time is the bright white halo formed by the churning of the liquid surface due to argon blowing.

[0065] Step 3: If yes, convert the monitoring image frame to the HSV color space, and mark the red pixel area in the converted monitoring image frame as the highlight argon aperture range in the monitoring image frame.

[0066] In this step, the monitoring image frame is converted to the HSV color space. In the HSV color space, the bright white iris in the original monitoring image will appear red. Therefore, the red pixel area in the converted monitoring image frame is identified as the range of the bright iris in that monitoring image frame.

[0067] Furthermore, if the monitored image frame corresponds to a non-argon blowing stage, it indicates that there is no bright halo in that frame. This method avoids misjudging the range of the bright argon blowing halo, improving recognition accuracy.

[0068] S103. Based on the ladle range and / or argon blowing aperture range in the monitoring image frame, determine the ladle argon blowing monitoring parameters corresponding to the monitoring image frame.

[0069] Here, the ladle argon blowing monitoring parameters can reflect the argon blowing refining state and provide a basis for adjusting the ladle argon blowing process parameters. In the embodiments of this application, the ladle argon blowing monitoring parameters include at least one of the following: aperture area, free space height from the molten steel surface to the edge of the ladle, and slag grayscale value. The ladle argon blowing monitoring parameters can be determined based on the ladle range and / or the argon blowing aperture range, using image processing methods such as HSV color space processing and binarization.

[0070] It should be noted that the selected monitoring parameters for argon blowing in the ladle determine whether it is necessary to determine the ladle area from the monitoring image, the argon blowing aperture area, or both. The implementation process of step S103 will be described in detail below.

[0071] In a first possible implementation, when the ladle argon blowing monitoring parameters include the aperture area, the ladle argon blowing monitoring parameters corresponding to the monitoring image frame are determined based on the argon blowing aperture range in the monitoring image frame, including:

[0072] Determine the number of pixels corresponding to the argon blowing aperture range in the monitoring image frame; based on the mapping relationship between pixels and physical areas in the real world, convert the number of pixels corresponding to the argon blowing aperture range into aperture area.

[0073] Here, after determining the range of the argon-blowing aperture in each frame of the monitoring image, the number of pixels within that range can be statistically calculated to determine the corresponding pixel count. Since there is a mapping relationship between pixels and physical areas in the real world—for example, an image captured from a 1m x 1m physical area has a pixel count of 1024 x 2048—the physical area corresponding to each pixel can be determined, allowing the conversion of the pixel count corresponding to the argon-blowing aperture range into the actual aperture area. Corresponding to the example above, the calculated actual aperture area includes both the actual area of ​​the dark argon-blowing aperture and the actual area of ​​the bright argon-blowing aperture.

[0074] In a second possible implementation, when the ladle argon blowing monitoring parameters include the free space height from the molten steel surface to the edge of the ladle, the ladle argon blowing monitoring parameters corresponding to the monitoring image frame are determined based on the ladle range in the monitoring image frame, including:

[0075] Step 1: Based on the ladle range in the monitoring image frame, extract the image from the monitoring image frame and convert it to the HSV color space to obtain the ladle image.

[0076] Here, in the HSV color space, the portion of the ladle's inner edge not touched by the liquid surface appears yellow, while the highlighted portion where the liquid surface touches the ladle's inner edge appears red. Therefore, in the algorithm for determining the free space height, the ladle range detected in S102 is first extracted and converted to the HSV color space. Experiments showed that, compared to RGB images, the HSV color space can determine more accurate ladle argon blowing monitoring parameters.

[0077] Step 2: Perform a pixel traversal from top to bottom on the ladle image, and determine the average free space height pixels in the ladle image based on the ladle edge position points and the contact position points between the molten steel and the inner edge of the ladle determined by the traversal.

[0078] In this step, since the ladle range detected in S102 is determined by the rectangular box marked by the target detection model, the extracted ladle image inevitably contains pixels that do not belong to the actual ladle range. Therefore, it is necessary to traverse the ladle image pixel by pixel column from top to bottom. Based on the color of each traversed pixel, the ladle edge position point and the contact position point between the molten steel and the inner edge of the ladle can be determined. Then, based on the number of pixels between the ladle edge position point and the contact position point on each pixel column, the average free space height pixel number is determined.

[0079] In practice, step 2 may include:

[0080] During the traversal of each pixel column, the first yellow pixel encountered is marked as the ladle edge position point corresponding to that pixel column, and the first red pixel encountered is marked as the contact position point between the molten steel and the inner edge of the ladle corresponding to that pixel column. This pixel column is then identified as a target pixel column; that is, pixel columns that have not been traversed to the red pixel are removed.

[0081] The number of pixels between the ladle edge position point and the contact position point in each target pixel column is determined as the number of free space height pixels; that is, the number of free space height pixels for each remaining pixel column that meets the requirements is determined.

[0082] The average free space height pixel count is determined based on the number of free space height pixels in each target pixel column; that is, the average free space height pixel count is obtained by averaging the number of free space height pixels in each target pixel column.

[0083] Step 3: Convert the average free space height pixel count to the real-world free space height.

[0084] Similarly, there is a certain mapping relationship between pixels and physical length in the real world, so the number of pixels in the average free space height can be converted into the free space height in the real world.

[0085] In a third possible implementation, when the ladle argon blowing monitoring parameters include the slag grayscale value, the ladle argon blowing monitoring parameters corresponding to the monitoring image frame are determined based on the ladle range and argon blowing aperture range in the monitoring image frame, including:

[0086] Step 1: Based on the ladle range in the monitoring image frame, extract the image from the monitoring image frame and convert it to the HSV color space to obtain the ladle image.

[0087] Here, the monitoring image frame is converted to the HSV color space. In the HSV color space, the inner edge of the ladle is displayed as yellow, and the main body of the molten steel is displayed as red. However, due to the slag covering, some parts of the molten steel surface may also appear as yellow.

[0088] Step 2: Perform a multi-directional pixel-by-pixel traversal on the ladle image, and determine the precise ladle image based on the ladle edge position points determined by the traversal.

[0089] Similarly, since the ladle range detected in S102 is determined by the rectangular box identified by the target detection model, the extracted ladle image inevitably contains pixels that do not belong to the actual ladle range. Therefore, to accurately determine the grayscale value of the steel slag, it is necessary to determine the accurate ladle image.

[0090] In this step, the ladle image is traversed pixel by pixel in multiple directions. The edge position of the ladle can be determined based on the color of each pixel traversed. Then, based on the edge position of the ladle, a precise ladle image is extracted.

[0091] In practice, step 2 may include:

[0092] Starting from each pixel on the top, bottom, left, and right sides of the ladle image, traverse pixel by pixel towards the center of the ladle image; mark the first yellow pixel encountered as the edge position of the ladle; based on the marked edge position, extract the precise ladle image from the ladle image.

[0093] Specifically, the pixels are traversed from the top, bottom, left, and right edges towards the center. When a yellow pixel is encountered, it is stopped and marked as the edge position of the ladle. The precise ladle range is obtained from this, and the precise ladle image is extracted from the ladle image.

[0094] Step 3: Perform binarization processing on the precise ladle image to extract the range image of molten steel from the precise ladle image.

[0095] In experiments conducted in this application embodiment, it was found that although converting the image to the HSV color space can clearly distinguish the ladle area from the non-ladle area, the boundary between the two is unclear, and the red ladle surface often appears discontinuous, thus affecting the accuracy of the ladle area identification. Therefore, this step requires binarization of the precise ladle image. After processing, the steel wall (the part of the ladle's inner edge not touched by the liquid surface) appears black, and the ladle surface appears white, thereby enabling a more accurate and clear distinction of the ladle area within the precise ladle image.

[0096] Step 4: Remove the argon blowing aperture range from the molten steel range image and convert it to a grayscale image to obtain a steel slag grayscale image.

[0097] Step 5: Determine the average gray value in the grayscale image of the steel slag as the grayscale value of the steel slag.

[0098] In steps 3 and 4, the molten steel image can be converted to a grayscale image first, and then the previously marked argon blowing aperture range (including the dark argon blowing aperture in the molten steel and the bright argon blowing aperture on the surface of the molten steel) can be removed; alternatively, the previously marked argon blowing aperture range can be removed first, and then the image can be converted to grayscale. The remaining portion is the slag grayscale image, i.e., the calculation range of the slag grayscale value. The grayscale value of each pixel in the slag grayscale image is traversed and the average value is taken. The average grayscale value is determined as the slag grayscale value, which is used to reflect the slagging status of the molten steel.

[0099] Furthermore, while determining the ladle argon blowing monitoring parameters corresponding to each frame of the monitored image, the monitoring system simultaneously starts an HTTP service to listen for client requests to obtain monitoring parameters. Upon receiving a client's request for monitoring parameters via the port, the system feeds back the ladle argon blowing monitoring parameters corresponding to the latest monitored frame to the client.

[0100] The embodiments of this application have the following beneficial effects:

[0101] (1) Using artificial intelligence image processing technology to identify the ladle range and the argon blowing aperture range can improve the system's identification accuracy; among them, the argon blowing aperture is divided into two categories. When the liquid surface churns during the argon blowing stage, the white high-brightness aperture formed by the argon blowing churn can be detected additionally.

[0102] (2) Use traditional image processing technology to determine various ladle argon blowing monitoring parameters corresponding to the monitoring images, so as to reflect the argon blowing refining status in a timely and accurate manner.

[0103] (3) The monitoring of the argon blowing process in the ladle can be achieved using only common cameras, avoiding the need for customized expensive high-temperature resistant sensors or manual monitoring, which can significantly reduce costs.

[0104] Please see Figure 2 , Figure 2 This is a schematic diagram of a monitoring device for a ladle argon blowing process provided in an embodiment of this application. Figure 2 As shown, the monitoring device 200 includes:

[0105] Extraction module 210 is used to extract multiple frames of monitoring images from the monitoring video of the ladle argon blowing production site;

[0106] The identification module 220 is used to identify the ladle range and / or argon blowing aperture range in each frame of the monitoring image.

[0107] The determination module 230 is used to determine the ladle argon blowing monitoring parameters corresponding to the monitoring image frame based on the ladle range and / or argon blowing aperture range in the monitoring image frame.

[0108] Furthermore, the argon blowing ring includes a dark argon blowing ring in the molten steel and a bright argon blowing ring on the surface of the molten steel; when the identification module 220 is used to identify the ladle range and / or argon blowing ring range in each frame of monitoring image, the identification module 220 is used to:

[0109] The monitoring image frame is input into a pre-trained first target detection model to identify and label the ladle area in the monitoring image frame; and / or,

[0110] The monitoring image frame is input into a pre-trained second target detection model to identify and label the range of dark argon-blown apertures in the monitoring image frame.

[0111] Compare the monitoring image frame with multiple adjacent monitoring images of the same frame to determine whether the monitoring image frame corresponds to the argon blowing stage;

[0112] If so, the monitoring image frame is converted to the HSV color space, and the red pixel area in the converted monitoring image frame is marked as the highlight argon aperture range in the monitoring image frame.

[0113] Furthermore, when the ladle argon blowing monitoring parameters include the aperture area, when the determining module 230 determines the ladle argon blowing monitoring parameters corresponding to the monitoring image frame based on the argon blowing aperture range in the monitoring image frame, the determining module 230 is used to:

[0114] Determine the number of pixels corresponding to the argon blowing aperture range in the monitoring image frame;

[0115] Based on the mapping relationship between pixels and physical areas in the real world, the number of pixels corresponding to the argon-blown aperture range is converted into aperture area.

[0116] Furthermore, when the ladle argon blowing monitoring parameters include the free space height from the molten steel surface to the edge of the ladle, the determining module 230, when used to determine the ladle argon blowing monitoring parameters corresponding to the monitoring image frame based on the ladle range in the monitoring image frame, is used to:

[0117] Based on the ladle range in the monitoring image frame, an image is extracted from the monitoring image frame and converted to the HSV color space to obtain the ladle image;

[0118] The ladle image is traversed pixel by pixel from top to bottom. Based on the ladle edge position points and the contact position points between the molten steel and the inner edge of the ladle determined by the traversal, the average free space height pixel count in the ladle image is determined.

[0119] Convert the average free space height pixel count to the real-world free space height.

[0120] Furthermore, when the determining module 230 performs a pixel-by-pixel traversal of the ladle image from top to bottom, and determines the average free space height pixels in the ladle image based on the ladle edge position points and the contact position points between the molten steel and the inner edge of the ladle determined by the traversal, the determining module 230 is used to:

[0121] During the traversal of each pixel column, the first yellow pixel encountered is marked as the ladle edge position point corresponding to that pixel column, the first red pixel encountered is marked as the contact position point between the molten steel and the inner edge of the ladle corresponding to that pixel column, and that pixel column is determined as a target pixel column.

[0122] The number of pixels between the ladle edge location point and the contact location point in each target pixel column is determined as the number of pixels in the free space height;

[0123] The average free space height pixel count is determined based on the number of free space height pixels in each target pixel column.

[0124] Furthermore, when the ladle argon blowing monitoring parameters include the slag grayscale value, the determining module 230, when determining the ladle argon blowing monitoring parameters corresponding to the monitoring image frame based on the ladle range and argon blowing aperture range in the monitoring image frame, is used to:

[0125] Based on the ladle range in the monitoring image frame, an image is extracted from the monitoring image frame and converted to the HSV color space to obtain the ladle image;

[0126] The ladle image is traversed pixel by pixel in multiple directions, and the accurate ladle image is determined based on the ladle edge position points determined by the traversal.

[0127] The precise ladle image is binarized to extract the molten steel range image from the precise ladle image;

[0128] The argon-blowing aperture range is removed from the molten steel range image and converted to a grayscale image to obtain a slag grayscale image;

[0129] The average grayscale value in the grayscale image of the steel slag is determined as the grayscale value of the steel slag.

[0130] Furthermore, when the determining module 230 performs multi-directional pixel-by-pixel traversal of the ladle image and determines the precise ladle image based on the ladle edge position points determined by the traversal, the determining module 230 is used to:

[0131] Starting from each pixel on the top, bottom, left, and right sides of the ladle image, traverse pixel by pixel towards the center of the ladle image;

[0132] Mark the first yellow pixel encountered as the edge location of the ladle;

[0133] Based on the marked edge locations of the ladle, the precise ladle image is extracted from the ladle image.

[0134] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 As shown, the electronic device 300 includes a processor 310, a memory 320, and a bus 330.

[0135] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 and the memory 320 communicate via the bus 330. When the machine-readable instructions are executed by the processor 310, they can perform the operations described above. Figure 1 The steps of a method for monitoring the argon blowing process in a ladle, as shown in the method embodiment, can be found in the method embodiment for specific implementation details, which will not be repeated here.

[0136] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figure 1 The steps of a method for monitoring the argon blowing process in a ladle, as shown in the method embodiment, can be found in the method embodiment for specific implementation details, which will not be repeated here.

[0137] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0138] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0139] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0140] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0141] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0142] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for monitoring the argon blowing process in a steel ladle, characterized in that, The monitoring method includes: Extract multiple frames of monitoring images from the monitoring video of the argon blowing production site in the ladle; For each frame of monitoring image, identify the ladle range and / or argon blowing aperture range in that frame of monitoring image; Based on the ladle range and / or argon blowing aperture range in the monitoring image frame, determine the ladle argon blowing monitoring parameters corresponding to the monitoring image frame; The argon blowing aperture includes a dark argon blowing aperture in the molten steel and a bright argon blowing aperture on the surface of the molten steel; for each frame of monitoring image, the range of the argon blowing aperture in that frame of monitoring image is identified, including: The monitoring image frame is input into a pre-trained second target detection model to identify and label the range of dark argon-blown apertures in the monitoring image frame. The monitoring image frame is compared with multiple adjacent monitoring images of the same frame. The comparison determines whether the liquid surface is churning and whether the monitoring image frame corresponds to the argon blowing stage. If so, the monitoring image frame is converted to the HSV color space, and the red pixel area in the converted monitoring image frame is marked as the highlight argon aperture range in the monitoring image frame. If not, then it is determined that there is no bright argon-blown aperture in the monitoring image of that frame; When the ladle argon blowing monitoring parameters include the slag grayscale value, the ladle argon blowing monitoring parameters corresponding to the monitoring image frame are determined based on the ladle range and argon blowing aperture range in the monitoring image frame, including: Based on the ladle range in the monitoring image frame, an image is extracted from the monitoring image frame and converted to the HSV color space to obtain the ladle image; The ladle image is traversed pixel by pixel in multiple directions, and the accurate ladle image is determined based on the ladle edge position points determined by the traversal. The precise ladle image is binarized to extract the molten steel range image from the precise ladle image; The argon-blowing aperture range is removed from the molten steel range image and converted to a grayscale image to obtain a slag grayscale image; The average grayscale value in the grayscale image of the steel slag is determined as the grayscale value of the steel slag.

2. The monitoring method according to claim 1, characterized in that, For each frame of the monitoring image, identify the range of the steel ladle in that frame, including: The monitoring image frame is input into a pre-trained first target detection model to identify and mark the range of steel ladles in the monitoring image frame.

3. The monitoring method according to claim 1, characterized in that, When the ladle argon blowing monitoring parameters include the aperture area, the ladle argon blowing monitoring parameters corresponding to the monitoring image frame are determined based on the argon blowing aperture range in that frame, including: Determine the number of pixels corresponding to the argon blowing aperture range in the monitoring image frame; Based on the mapping relationship between pixels and physical areas in the real world, the number of pixels corresponding to the argon-blown aperture range is converted into aperture area.

4. The monitoring method according to claim 1, characterized in that, When the ladle argon blowing monitoring parameters include the free space height from the molten steel surface to the edge of the ladle, the ladle argon blowing monitoring parameters corresponding to the monitoring image frame are determined based on the ladle range in the monitoring image frame, including: Based on the ladle range in the monitoring image frame, an image is extracted from the monitoring image frame and converted to the HSV color space to obtain the ladle image; The ladle image is traversed pixel by pixel from top to bottom. Based on the ladle edge position points and the contact position points between the molten steel and the inner edge of the ladle determined by the traversal, the average free space height pixel count in the ladle image is determined. Convert the average free space height pixel count to the real-world free space height.

5. The monitoring method according to claim 4, characterized in that, The step of performing a pixel-by-pixel traversal of the ladle image from top to bottom, and determining the average free space height pixels in the ladle image based on the ladle edge positions and the contact points between the molten steel and the inner edge of the ladle determined by the traversal, includes: During the traversal of each pixel column, the first yellow pixel encountered is marked as the ladle edge position point corresponding to that pixel column, the first red pixel encountered is marked as the contact position point between the molten steel and the inner edge of the ladle corresponding to that pixel column, and that pixel column is determined as a target pixel column. The number of pixels between the ladle edge location point and the contact location point in each target pixel column is determined as the number of pixels in the free space height; The average free space height pixel count is determined based on the number of free space height pixels in each target pixel column.

6. The monitoring method according to claim 1, characterized in that, Performing a multi-directional pixel-by-pixel traversal on the ladle image, and determining the precise ladle image based on the ladle edge position points determined by the traversal, includes: Starting from each pixel on the top, bottom, left, and right sides of the ladle image, traverse pixel by pixel towards the center of the ladle image; Mark the first yellow pixel encountered as the edge location of the ladle; Based on the marked edge locations of the ladle, the precise ladle image is extracted from the ladle image.

7. A monitoring device for the argon blowing process in a steel ladle, characterized in that, The monitoring device includes: The extraction module is used to extract multiple frames of monitoring images from the monitoring video of the ladle argon blowing production site; The identification module is used to identify the ladle range and / or argon blowing aperture range in each frame of the monitoring image. The determination module is used to determine the ladle argon blowing monitoring parameters corresponding to the monitoring image frame based on the ladle range and / or the argon blowing aperture range in the monitoring image frame. The argon blowing aperture includes a dark argon blowing aperture in the molten steel and a bright argon blowing aperture on the surface of the molten steel; when the identification module identifies the range of the argon blowing aperture in each frame of the monitoring image, the identification module is used for: The monitoring image frame is input into a pre-trained second target detection model to identify and label the range of dark argon-blown apertures in the monitoring image frame. The monitoring image frame is compared with multiple adjacent monitoring images of the same frame. The comparison determines whether the liquid surface is churning and whether the monitoring image frame corresponds to the argon blowing stage. If so, the monitoring image frame is converted to the HSV color space, and the red pixel area in the converted monitoring image frame is marked as the highlight argon aperture range in the monitoring image frame. If not, then it is determined that there is no bright argon-blown aperture in the monitoring image of that frame; When the ladle argon blowing monitoring parameters include the slag grayscale value, the determining module, when used to determine the ladle argon blowing monitoring parameters corresponding to the monitoring image frame based on the ladle range and argon blowing aperture range in the monitoring image frame, is used for: Based on the ladle range in the monitoring image frame, an image is extracted from the monitoring image frame and converted to the HSV color space to obtain the ladle image; The ladle image is traversed pixel by pixel in multiple directions, and the accurate ladle image is determined based on the ladle edge position points determined by the traversal. The precise ladle image is binarized to extract the molten steel range image from the precise ladle image; The argon-blowing aperture range is removed from the molten steel range image and converted to a grayscale image to obtain a slag grayscale image; The average grayscale value in the grayscale image of the steel slag is determined as the grayscale value of the steel slag.

8. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. The machine-readable instructions are executed by the processor to perform the steps of a monitoring method for argon blowing in a ladle as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of a monitoring method for a ladle argon blowing process as described in any one of claims 1 to 6.

Images