A method for slag overflow identification of a converter mouth and related equipment

Abstract

The application discloses a converter mouth overflow slag identification method and related equipment, relates to the technical field of industrial intelligentization and metallurgical process monitoring, and the target heat of the converter includes multiple overflow slag identification time periods with time sequence. For the overflow slag identification time periods, the method comprises the following steps: acquiring multiple overflow slag monitoring images with time sequence of the converter mouth and operation parameters in the converter smelting process; processing the multiple overflow slag monitoring images to obtain multiple overflow slag characteristic values; in the case that the operation parameters are not within the preset parameter range, determining the motion direction according to the position change of the target object in each overflow slag monitoring image; identifying whether the converter mouth overflows slag according to the motion direction, if the converter mouth overflows slag, recording the overflow slag characteristic value, if the converter mouth does not overflow slag, reassigning the overflow slag characteristic value as the target characteristic value, constructing an overflow slag characteristic value change curve based on the overflow slag characteristic values of each overflow slag identification time period, and performing flame filtering processing on the curve to obtain the overflow slag identification condition.

Description

Technical Field

[0001] This application relates to the fields of industrial intelligence and metallurgical process monitoring technology, and in particular to a method and related equipment for identifying overflow slag at the converter furnace mouth. Background Technology

[0002] Currently, converter blowing is a crucial step in the steel production process, decisively impacting steel quality and production efficiency. During converter blowing, slag-steel splashing at the converter mouth is a relatively frequent occurrence. The negative impacts of this splashing problem are significant. On the one hand, a large amount of iron is lost due to splashing, increasing production costs and reducing the economic efficiency of steel production. On the other hand, the splashed high-temperature molten slag can cause serious damage to surrounding equipment, shortening its lifespan, increasing maintenance costs and downtime, and affecting production continuity. More importantly, splashing poses a significant threat to the personal safety of workers; even slight negligence can lead to serious accidents. Steel companies primarily rely on operators closely observing the converter mouth to determine if splashing has occurred and then adjusting process operations accordingly.

[0003] However, this traditional detection method has certain limitations. During converter smelting, flames frequently erupt from the furnace opening. The flames and splashed slag at the furnace opening are visually very similar, not only in brightness but also in location. This situation greatly interferes with slag overflow detection based on image recognition technology. Image recognition technology, as a modern detection method, was originally intended to quickly and accurately determine whether splashing has occurred by analyzing images of the converter furnace opening, providing operators with timely decision-making support. However, due to the confusion between the characteristics of the flames and splashed slag, image recognition systems struggle to accurately distinguish between the two, leading to a significant decrease in the accuracy of slag overflow detection. Inaccurate slag overflow detection results may cause operators to miss the optimal time for process adjustments, making it impossible to respond to splashing problems in a timely and effective manner, further exacerbating iron loss, equipment damage, and safety hazards. Summary of the Invention

[0004] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0005] In a first aspect, embodiments of this application provide a method for identifying slag overflow at the taphole of a converter. The target furnace cycle of the converter includes multiple slag overflow identification time periods with a temporal sequence. For each of the slag overflow identification time periods, the method includes: Acquire multiple slag overflow monitoring images of the converter furnace mouth with a time sequence, as well as the operating parameters during the converter smelting process; Multiple overflow monitoring images are processed to obtain multiple overflow feature values; When the operating parameters are not within the preset parameter range, the movement direction of the target object is determined based on the position change of the target object in each of the overflow monitoring images. The preset parameter range is the range of operating parameters of the converter when the fire risk value of the converter mouth is greater than or equal to the preset risk value. The target object includes flames and / or liquid slag. Based on the direction of movement of the target object, it is determined whether the converter furnace mouth is overflowing with slag. If slag overflow exists, the slag overflow characteristic value is recorded. If slag overflow does not exist, the slag overflow characteristic value is reassigned as the target characteristic value. Based on the slag overflow characteristic value of each slag overflow identification period, a slag overflow characteristic value change curve is constructed, and the slag overflow characteristic value change curve is subjected to flame filtering to obtain the slag overflow identification status of the target furnace.

[0006] In one embodiment of the present invention, the step of identifying whether the converter opening is overflowing with slag based on the direction of movement of the target object includes: When the target object moves downwards, the overflow slag identification indicates that overflow slag exists; If the target object moves in an upward or both upward and downward direction, the overflow condition is determined to be no overflow.

[0007] In one embodiment of the present invention, the step of processing the overflow monitoring image to obtain overflow feature values ​​includes: The overflow monitoring image is divided into regions of interest, and the regions of interest are defined as the liquid slag flow areas. The region of interest is identified and segmented to obtain the overflow area and the background area; The ratio of the area of ​​the overflow region to the area of ​​the point of interest region is used as the overflow feature value.

[0008] In one embodiment of the present invention, the step of processing the overflow monitoring image to obtain the overflow feature value includes: If the operating parameters are within the preset parameter range, the overflow characteristic value is cleared to zero, thus ending this overflow identification step.

[0009] In one embodiment of the present invention, the step of determining the direction of movement of the target object based on the positional changes of the target object in each of the overflow monitoring images includes: The overflow monitoring images are binarized to obtain bright areas and background areas; Edge detection is performed on each of the bright areas and edge contour information is extracted to obtain contour coordinates. The overflow monitoring image corresponds one-to-one with the contour coordinates, and the abscissa of each contour coordinate is a preset abscissa value. The direction of motion of the target object is determined based on the changes in the ordinate of each contour coordinate.

[0010] In one embodiment of the present invention, the step of determining the direction of movement of the target object based on the positional changes of the target object in each of the overflow monitoring images includes: For each frame of the image, the overflow monitoring image is preprocessed based on Gaussian blur to obtain a preprocessed image, and key points are detected in the preprocessed image based on an image feature detection algorithm. Multiple key points are matched to obtain multiple matching points, and the direction of the line connecting each matching point is used as the direction of movement of the target object.

[0011] In one embodiment of the present invention, the step of constructing a slag overflow feature value change curve based on the slag overflow feature values ​​of each of the slag overflow identification time periods, and performing flame filtering on the slag overflow feature value change curve to obtain the slag overflow identification status of the target furnace includes: Obtain the overflow characteristic values ​​for each of the overflow identification time periods; Based on the overflow characteristic values ​​of each overflow identification period, an overflow characteristic value change curve is constructed; The overflow slag characteristic value change curve is subjected to flame filtering to obtain the target overflow slag characteristic value change curve; The overflow identification status of the target furnace is obtained based on the characteristic value change curve of the target overflow characteristic value change curve.

[0012] Secondly, this application proposes a slag overflow identification system for converter furnace openings, the system comprising: an image processing module, a trajectory tracking module, and a curve drawing and processing module; The image processing module is configured to: acquire multiple slag overflow monitoring images of the converter furnace opening with a time sequence and the operating parameters of the converter smelting process; process the multiple slag overflow monitoring images to obtain multiple slag overflow feature values; The trajectory tracking module is configured to: determine the direction of movement of the target object based on the position change of the target object in each of the overflow monitoring images when the operating parameters are not within the preset parameter range; the preset parameter range is the range of operating parameters of the converter when the fire risk value of the converter mouth is greater than or equal to the preset risk value. The curve plotting and processing module is configured to: identify whether the converter furnace opening is overflowing with slag based on the direction of movement of the target object; if slag overflow exists, record the slag overflow feature value; if slag overflow does not exist, reassign the slag overflow feature value to the target feature value; construct the slag overflow feature value change curve based on the slag overflow feature value of each slag overflow identification period; and perform flame filtering on the slag overflow feature value change curve to obtain the slag overflow identification status of the target furnace.

[0013] Thirdly, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of a converter mouth slag identification method as described in any of the first aspects above.

[0014] Fourthly, this application also proposes a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the steps of the method for identifying overflow slag at the converter mouth according to any one of the first aspects.

[0015] In summary, the converter slag overflow identification method of this application determines the movement direction of the target object based on the positional changes of the target object in various slag overflow monitoring images when the operating parameters are not within the preset parameter range. The target object includes flames and / or liquid slag. The method identifies whether the converter slag overflows based on the movement direction of the target object, thereby eliminating conventional operating factors. It also improves the accuracy of identifying slag overflow in the converter smelting process by utilizing the different movement trajectories and durations of flames and liquid slag. This method can quickly and accurately obtain quantitative information on slag overflow, thereby promoting the efficient and stable operation of the converter.

[0016] The method for identifying slag overflow at the converter mouth proposed in this application, along with other advantages, objectives, and features of this application, will be partly apparent from the following description and partly understood by those skilled in the art through study and practice of this application. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a flowchart illustrating a method for identifying overflow slag at the converter furnace opening, as provided in an embodiment of this application. Figure 2 A schematic diagram of a slag overflow identification system at the converter furnace mouth provided in this application embodiment; Figure 3 This is a schematic diagram of an electronic device for identifying overflow slag at the converter furnace mouth, provided as an embodiment of this application. Detailed Implementation

[0018] To better understand the technical solutions provided in the embodiments of this specification, the technical solutions of the embodiments of this specification will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0019] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The term "two or more" includes two or more cases.

[0020] Please see Figure 1 This is a flowchart illustrating a method for identifying overflow slag at the converter furnace opening, provided in an embodiment of this application. The target furnace cycle includes multiple overflow identification time periods with a temporal sequence. For each overflow identification time period, the method includes: S110. Acquire multiple slag overflow monitoring images of the converter furnace mouth with a time sequence, as well as the operating parameters of the converter smelting process. For example, the start of converter smelting is identified based on converter operation signals. After converter smelting begins, monitoring images of slag overflow at the converter mouth are acquired. During each slag overflow identification period of converter smelting, monitoring images of slag overflow at the converter mouth are continuously acquired using cameras and other equipment. These images include portions of the fume hood and furnace cap areas. These slag overflow monitoring images are arranged chronologically to reflect the state of the furnace mouth at different times. Simultaneously, operating parameters during the converter smelting process are collected, such as fume hood height, oxygen lance height, oxygen flow rate, fume hood inlet pressure, blower flow rate, scrap steel addition time, and feeding valve opening time. These operating parameters can be obtained from the converter's automated control system.

[0021] The slag overflow monitoring images visually display the furnace opening, while the operating parameters reflect the internal operating status and physical conditions of the converter. Combining the two provides a rich and comprehensive data foundation for accurate subsequent judgment of slag overflow, avoiding misjudgments caused by relying on a single information source.

[0022] S120. Process the multiple overflow monitoring images to obtain multiple overflow feature values; For example, the acquired overflow monitoring images are divided and segmented to obtain multiple overflow feature values. Through image segmentation and feature value calculation, the overflow information in the image is quantified into specific numerical values, allowing the overflow situation to be presented in a measurable way. This helps to accurately assess and compare the degree of overflow in subsequent processes, providing clear quantitative indicators for overflow identification.

[0023] S130. When the operating parameters are not within the preset parameter range, the movement direction of the target object is determined according to the position change of the target object in each of the overflow monitoring images. The preset parameter range is the range of operating parameters of the converter when the fire risk value of the converter furnace mouth is greater than or equal to the preset risk value. The target object includes flames and / or liquid slag. For example, the preset parameter range refers to the range of converter operating parameters corresponding to a converter mouth fire risk value greater than or equal to a preset risk value. When the operating parameters are not within this preset range, it indicates that the possibility of a fire at the furnace mouth is low, and the movement direction of the target object, i.e., the flame and / or liquid slag, can be determined. Specifically, the positional changes of the target object in various slag overflow monitoring images are identified using the background difference method or feature point method to determine the movement direction of the target object.

[0024] By setting preset parameter ranges, misjudgments that might be caused by furnace opening fires due to routine smelting operations were eliminated. Based on this, determining the direction of movement of the target material further distinguishes the different movement characteristics of flames and molten slag, providing more crucial information for accurately identifying overflowing slag.

[0025] S140. Identify whether the converter furnace opening is overflowing with slag based on the direction of movement of the target object. If slag overflow exists, record the slag overflow feature value. If there is no slag overflow, reassign the slag overflow feature value to the target feature value. Construct a slag overflow feature value change curve based on the slag overflow feature value of each slag overflow identification period, and perform flame filtering on the slag overflow feature value change curve to obtain the slag overflow identification status of the target furnace.

[0026] For example, since slag overflow typically manifests as a downward dripping motion, while the movement direction of a flame is more complex, the direction of movement of the target object can be used to identify whether slag is overflowing at the converter furnace opening. Determining the direction of movement effectively reduces false detections. If slag overflow is detected, the corresponding slag overflow characteristic value is recorded for subsequent analysis of the degree and frequency of slag overflow. If no slag overflow is detected, the slag overflow characteristic value is reassigned to the target characteristic value, which is typically 0, to eliminate potential false detections.

[0027] Clearly defined rules for judging slag overflow make the slag overflow identification process more standardized and accurate. Recording slag overflow characteristic values ​​can provide data support for quality control and safety management in the converter smelting process, and help analyze the patterns and causes of slag overflow. Resetting the slag overflow characteristic values ​​to zero in non-slag overflow situations ensures the accuracy of subsequent analysis data and avoids interference from false detection data.

[0028] In summary, the converter slag overflow identification method proposed in this application determines the movement direction of the target object based on its position change in various slag overflow monitoring images when the operating parameters are not within the preset parameter range. The target object includes flames and / or liquid slag. The method identifies whether the converter mouth is overflowing based on the movement direction of the target object, thereby eliminating conventional operating factors. It also improves the accuracy of identifying slag overflow during the converter smelting process by utilizing the different movement trajectories and durations of flames and liquid slag. This method can quickly and accurately obtain quantitative information on slag overflow, thereby promoting the efficient and stable operation of the converter.

[0029] In some examples, the step of identifying whether slag overflows from the converter opening based on the direction of movement of the target object includes: When the target object moves downwards, the overflow slag identification indicates that overflow slag exists; If the target object moves in an upward or both upward and downward direction, the overflow condition is determined to be no overflow.

[0030] For example, in the converter smelting process, slag overflow and flame movement have different physical characteristics and manifestations. Due to its own gravity, slag typically drips downwards from the furnace opening when overflow occurs. However, the flame, influenced by complex airflow and chemical reactions within the furnace, exhibits a more complex movement direction, potentially erupting upwards or fluctuating up and down. Based on this difference, determining the direction of movement of the target object allows for a more accurate distinction between genuine slag overflow and other phenomena.

[0031] Therefore, after setting the number of consecutive frames and obtaining the movement direction of the target object in the consecutive frame images, if the movement direction of the target object is downward, it indicates that it is liquid slag splashing and dripping; if the movement direction is upward or both upward and downward, it indicates that it is flame expansion or contraction, and the overflow slag feature value within the consecutive frame range is cleared to zero. The number of consecutive frames should not be too large, and should be determined according to the camera frame rate and the frequency of image acquisition, generally 2-5 frames.

[0032] This motion direction-based judgment rule fully considers the different motion characteristics of liquid slag and flame, avoiding potential misjudgments that may occur when relying solely on image features such as color and brightness for slag overflow identification. Because flame and liquid slag have some similar features in images and are easily confused, the key information of motion direction allows for more accurate differentiation, significantly improving the accuracy of slag overflow identification.

[0033] In some examples, the step of processing the overflow monitoring image to obtain overflow feature values ​​includes: The overflow monitoring image is divided into regions of interest, and the regions of interest are defined as the liquid slag flow areas. The region of interest is identified and segmented to obtain the overflow area and the background area; The ratio of the area of ​​the overflow region to the area of ​​the point of interest region is used as the overflow feature value.

[0034] For example, firstly, the overflow monitoring image is segmented into Regions of Interest (ROIs), identifying the area of ​​slag flow below the furnace opening as the ROI, as this ROI is the key area for overflow. Then, the ROI is segmented to separate the slag area from the background. Finally, overflow feature values ​​are calculated based on the segmentation results, using the formula: Overflow Feature Value = Overflow Area / ROI Area * 100%. Through precise image region segmentation, overflow features are quantified into area ratios, providing objective and accurate feature data for subsequent overflow judgment and improving the accuracy of overflow identification.

[0035] In some examples, the steps following the processing of the overflow monitoring image to obtain overflow feature values ​​include: If the operating parameters are within the preset parameter range, the overflow characteristic value is cleared to zero, thus ending this overflow identification step.

[0036] For example, after obtaining the slag overflow characteristic value, the first step is to monitor and judge the current converter operating parameters to see if they are within the preset parameter range. When it is determined that the operating parameters are within the preset parameter range, it is considered that there is no risk of slag overflow in the converter. At this time, even if the previously calculated slag overflow characteristic value is not zero, it is likely a misjudgment caused by non-slag overflow factors such as image noise or flame flickering. To ensure the accuracy of the data and the reliability of subsequent analysis, the slag overflow characteristic value is reset to zero. For example, at the end of smelting, changes in parameters such as oxygen lance height, oxygen flow rate, and blower flow rate can cause an imbalance in gas pressure inside and outside the furnace mouth, which can easily lead to furnace mouth flameout. When this stage occurs, the falsely detected slag overflow characteristic value is cleared to zero to eliminate the interference of flameout.

[0037] After resetting the slag overflow characteristic value to zero, the current slag overflow identification step ends. This means that if the converter is operating normally, further analysis and judgment of the slag overflow situation at this stage is temporarily unnecessary. The system can shift its focus to other monitoring and control aspects, or wait for the next monitoring cycle to restart the slag overflow identification process. This avoids unnecessary calculations and analysis, improving system operating efficiency. It effectively eliminates interference caused by routine operations in the smelting process, such as furnace mouth flames, avoiding false detections and improving the accuracy of slag overflow identification.

[0038] In some examples, the step of determining the direction of movement of the target object based on its positional changes in each of the overflow monitoring images includes: The overflow monitoring images are binarized to obtain bright areas and background areas; Edge detection is performed on each of the bright areas and edge contour information is extracted to obtain contour coordinates. The overflow monitoring image corresponds one-to-one with the contour coordinates, and the abscissa of each contour coordinate is a preset abscissa value. The direction of motion of the target object is determined based on the changes in the ordinate of each contour coordinate.

[0039] For example, binarization segmentation is a simple and effective image segmentation method. In overflow monitoring images, flames and slag are usually brighter than the background. Therefore, binarizing each overflow monitoring image can yield bright and background regions. Edges are areas in the image where grayscale values ​​change abruptly, representing the boundaries of the target object. Using an edge detection algorithm to process the binarized bright regions can identify the edges of the target object. These edges constitute the outline of the target object. After obtaining the outline of the target object, the coordinate information of each point on the outline is extracted. These coordinates represent the outline coordinates of the target object. Based on a preset abscissa value, the abscissas of each outline coordinate are filtered, retaining the outline coordinates with the preset abscissa value. Each overflow monitoring image corresponds to a specific set of outline coordinates, allowing analysis of the target object's movement based on changes in the outline coordinates of different images.

[0040] In a Cartesian coordinate system, changes in the ordinate reflect changes in the vertical position of the target object. If the ordinate gradually increases, it indicates the target object is moving downwards; if it gradually decreases, it indicates upwards; if it both increases and decreases, it indicates the target object is moving in both directions. Therefore, the direction of movement of the target object can be determined based on the changes in the ordinate of each contour coordinate. That is, multiple contour coordinates with fixed abscissas are selected; finally, the changes in the ordinates of contour points with the same abscissa during consecutive frames are statistically analyzed to determine the direction of movement. This method of determining the direction of movement based on background difference has a relatively simple algorithm, low computational load, and can quickly determine the direction of movement of the target object while maintaining a certain level of accuracy, thus improving the real-time performance of spillage identification.

[0041] In some examples, the step of determining the direction of movement of the target object based on its positional changes in each of the overflow monitoring images includes: For each frame of the image, the overflow monitoring image is preprocessed based on Gaussian blur to obtain a preprocessed image, and key points are detected in the preprocessed image based on an image feature detection algorithm. Multiple key points are matched to obtain multiple matching points, and the direction of the line connecting each matching point is used as the direction of movement of the target object.

[0042] For example, for each frame of the overflow monitoring image, the image is first preprocessed to obtain a preprocessed image. Specifically, Gaussian blur is used to remove noise, but other denoising and smoothing methods can also be used depending on the image characteristics. Next, keypoint detection is performed using image feature detection algorithms, such as SIFT (Scale-Invariant Feature Transform), to detect keypoints in the preprocessed image and calculate their feature descriptors. In different frames of the overflow monitoring image, keypoints of the same target object have similar feature descriptors. By comparing the feature descriptors of keypoints in different images, keypoint pairs with similar features are found; these keypoint pairs are the matching points. For example, a keypoint detected in the first frame and a keypoint detected in the second frame have high similarity in their feature descriptors and can be matched. Subsequently, feature keypoint matching is performed to obtain multiple matching points, and the direction of the line connecting these matching points is determined. Finally, the direction of the line connecting each matching point in consecutive frames is used as the target object's motion direction. The feature-point-based method can more accurately capture the features and motion information of the target object, and is particularly suitable for motion direction detection in complex scenes, improving the accuracy and robustness of motion direction determination.

[0043] In some examples, the step of constructing a slag overflow feature value change curve based on the slag overflow feature values ​​of each of the slag overflow identification periods, and performing flame filtering on the slag overflow feature value change curve to obtain the slag overflow identification status of the target furnace includes: Obtain the overflow characteristic values ​​for each of the overflow identification time periods; Based on the overflow characteristic values ​​of each overflow identification period, an overflow characteristic value change curve is constructed; The overflow slag characteristic value change curve is subjected to flame filtering to obtain the target overflow slag characteristic value change curve; The overflow identification status of the target furnace is obtained based on the characteristic value change curve of the target overflow characteristic value change curve.

[0044] For example, based on the converter operation signal, the completion of converter smelting is identified. The acquisition of converter slag overflow monitoring images and the recording of slag overflow characteristic value curves are stopped. The slag overflow characteristic value change curve for this smelting process is obtained. Specifically: the slag overflow characteristic values ​​for each slag overflow identification period are obtained. Using the slag overflow identification period as the horizontal axis (usually representing time) and the slag overflow characteristic values ​​as the vertical axis, the corresponding slag overflow characteristic values ​​for each period are plotted on a coordinate system. Then, these points are connected sequentially with line segments to obtain the slag overflow characteristic value change curve.

[0045] Flame filtering was applied to the slag overflow characteristic value curve of this furnace to obtain the target slag overflow characteristic value variation curve. The flame filtering was based on wavelet transform, which decomposed the slag overflow characteristic value variation curve into detail coefficients at different scales. Thresholding was then used to remove short-timescale, i.e., high-frequency detail coefficients, thus eliminating false detections caused by short-lived flames.

[0046] Based on the peak value changes in the characteristic value variation curve of the target slag overflow characteristic value for the target furnace, the number of slag overflows during the smelting process of the target furnace, the state of each slag overflow, the start and end times of each slag overflow, the maximum slag overflow characteristic value for each overflow, and the integral value of each slag overflow period are statistically recorded to obtain the slag overflow identification status of the target furnace. The slag overflow information of the furnace is saved, awaiting the start of the next furnace.

[0047] By constructing and processing the slag overflow characteristic value change curve, the slag overflow situation of the entire furnace can be reflected comprehensively and intuitively. Flame filtering further improves the accuracy of slag overflow identification results, providing strong support for quality control and safety management in the converter smelting process.

[0048] like Figure 2 As shown, this application proposes a slag overflow identification system for converter furnace openings. The system includes: an image processing module 21, a trajectory tracking module 22, and a curve drawing and processing module 23. The image processing module 21 is configured to: acquire multiple slag overflow monitoring images of the converter furnace opening with a time sequence and the operating parameters of the converter smelting process; process the multiple slag overflow monitoring images to obtain multiple slag overflow feature values; The trajectory tracking module 22 is configured to: determine the direction of movement of the target object based on the position change of the target object in each of the overflow monitoring images when the operating parameters are not within the preset parameter range; the preset parameter range is the range of operating parameters of the converter when the fire risk value of the converter mouth is greater than or equal to the preset risk value. The curve plotting and processing module 23 is configured to: identify whether the converter furnace mouth overflows with slag based on the direction of movement of the target object; if slag overflow exists, record the slag overflow feature value; if slag overflow does not exist, reassign the slag overflow feature value to the target feature value; construct the slag overflow feature value change curve based on the slag overflow feature value of each slag overflow identification period; and perform flame filtering processing on the slag overflow feature value change curve to obtain the slag overflow identification status of the target furnace.

[0049] The effects of applying the aforementioned method in the above system can be found in the description of the aforementioned method embodiments, and will not be repeated here.

[0050] like Figure 3As shown, this application embodiment also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of any of the above-mentioned methods for identifying overflow slag at the converter furnace mouth.

[0051] Since the electronic device described in this embodiment is the device used to implement the slag overflow identification device at the converter mouth in the embodiment of this application, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in the embodiment of this application. Therefore, how the electronic device implements the method in the embodiment of this application will not be described in detail here. Any device used by those skilled in the art to implement the method in the embodiment of this application is within the scope of protection of this application.

[0052] In practical implementation, when the computer program 311 is executed by the processor, it can achieve the following: Figure 1 Any of the corresponding implementation methods in the embodiments.

[0053] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0054] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0055] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0056] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0057] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0058] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to execute the LDPC decoding method of a solid-state drive controller.

[0059] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0060] Those skilled in the art will clearly 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.

[0061] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0062] 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.

[0063] Furthermore, 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0064] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a 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 all or part 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 of 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.

[0065] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications 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.

[0066] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this specification.

[0067] Obviously, those skilled in the art can make various modifications and variations to this specification without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims and their equivalents, this specification is also intended to include such modifications and variations.

Claims

1. A method for slag overflow recognition of a converter mouth, characterized in that, The target furnace cycle of the converter includes multiple slag overflow identification periods with a temporal sequence. For each slag overflow identification period, the method includes: Acquire multiple slag overflow monitoring images of the converter furnace mouth with a time sequence, as well as the operating parameters during the converter smelting process; Multiple overflow monitoring images are processed to obtain multiple overflow feature values; When the operating parameters are not within the preset parameter range, the movement direction of the target object is determined based on the position change of the target object in each of the overflow monitoring images. The preset parameter range is the range of operating parameters of the converter when the fire risk value of the converter mouth is greater than or equal to the preset risk value. The target object includes flames and / or liquid slag. The converter opening is identified as overflowing slag based on the direction of movement of the target object. If overflowing slag is present, the overflowing slag characteristic value is recorded. If overflowing slag is not present, the overflowing slag characteristic value is reassigned to the target characteristic value. An overflowing slag characteristic value change curve is constructed based on the overflowing slag characteristic values ​​of each overflowing slag identification period. The overflowing slag characteristic value change curve is then subjected to flame filtering to obtain the overflowing slag identification status of the target furnace. The target characteristic value is 0. The overflowing slag identification status is obtained by statistically recording the number of overflowing slags, the status of each overflowing slag, the start and end times of each overflowing slag, the maximum overflowing slag characteristic value, and the integral value of each overflowing slag period during the smelting process of the target furnace based on the peak value change of the characteristic value in the target overflowing slag characteristic value change curve of the target furnace. The step of identifying whether slag overflows from the converter opening based on the direction of movement of the target object includes: When the target object moves downwards, the overflow slag identification indicates that overflow slag exists; When the target object moves in an upward or both upward and downward direction, the overflow condition is identified as no overflow. The step of determining the direction of movement of the target object based on its position change in each of the overflow monitoring images includes: The overflow monitoring images are binarized to obtain bright areas and background areas; Edge detection is performed on each of the bright areas and edge contour information is extracted to obtain contour coordinates. The overflow monitoring image corresponds one-to-one with the contour coordinates, and the abscissa of each contour coordinate is a preset abscissa value. The direction of motion of the target object is determined based on the changes in the ordinate of each contour coordinate. Alternatively, the step of determining the direction of movement of the target object based on its positional changes in each of the overflow monitoring images includes: For each frame of the image, the overflow monitoring image is preprocessed based on Gaussian blur to obtain a preprocessed image, and key points are detected in the preprocessed image based on an image feature detection algorithm. Multiple key points are matched to obtain multiple matching points, and the direction of the line connecting each matching point is used as the direction of movement of the target object.

2. The method for identifying overflow slag at the converter mouth according to claim 1, characterized in that, The step of processing the overflow monitoring image to obtain the overflow feature value includes: The overflow monitoring image is divided into regions of interest, and the regions of interest are defined as the liquid slag flow areas. The region of interest is identified and segmented to obtain the overflow area and the background area; The ratio of the area of ​​the overflow region to the area of ​​the point of interest region is used as the overflow feature value.

3. The method for identifying overflow slag at the converter mouth according to claim 1, characterized in that, The steps following the processing of the overflow monitoring image to obtain overflow feature values ​​include: If the operating parameters are within the preset parameter range, the overflow slag characteristic value is cleared to zero, thus ending this overflow slag identification step.

4. The method for identifying overflow slag at the converter mouth according to claim 1, characterized in that, The step of constructing a slag overflow feature value change curve based on the slag overflow feature values ​​of each of the slag overflow identification time periods, and performing flame filtering on the slag overflow feature value change curve to obtain the slag overflow identification status of the target furnace includes: Obtain the overflow characteristic values ​​for each of the overflow identification time periods; Based on the overflow characteristic values ​​of each overflow identification period, an overflow characteristic value change curve is constructed; The overflow slag characteristic value change curve is subjected to flame filtering to obtain the target overflow slag characteristic value change curve; The overflow identification status of the target furnace is obtained based on the characteristic value change curve of the target overflow characteristic value change curve.

5. A slag overflow identification system for a converter furnace mouth, characterized in that, The system includes: an image processing module, a trajectory tracking module, and a curve drawing and processing module; The image processing module is configured to: acquire multiple slag overflow monitoring images of the converter furnace opening with a time sequence and the operating parameters of the converter smelting process; process the multiple slag overflow monitoring images to obtain multiple slag overflow feature values; The trajectory tracking module is configured to: determine the direction of movement of the target object based on the position change of the target object in each of the overflow monitoring images when the operating parameters are not within the preset parameter range; the preset parameter range is the range of operating parameters of the converter when the fire risk value of the converter mouth is greater than or equal to the preset risk value. The curve plotting and processing module is configured to: identify whether the converter furnace opening is overflowing with slag based on the movement direction of the target object; if slag overflow exists, record the slag overflow characteristic value; if slag overflow does not exist, reassign the slag overflow characteristic value to the target characteristic value; construct a slag overflow characteristic value change curve based on the slag overflow characteristic values ​​of each slag overflow identification period; and perform flame filtering on the slag overflow characteristic value change curve to obtain the slag overflow identification status of the target furnace. The target characteristic value is 0, and the slag overflow identification status is obtained by statistically recording the number of slag overflows during the smelting process of the target furnace, the slag overflow status of each overflow, the start and end times of each overflow, the maximum slag overflow characteristic value of each overflow, and the integral value of each overflow period, based on the peak value change of the characteristic value in the target slag overflow characteristic value change curve of the target furnace. The target furnace includes multiple slag overflow identification periods with a temporal sequence. The step of identifying whether the converter furnace opening is overflowing with slag based on the movement direction of the target object includes: if the movement direction of the target object is downward, the slag overflow identification status is that slag overflow exists; in the... When the target object's movement direction is upward or both upward and downward, the overflow slag identification condition is that there is no overflow slag. The step of determining the target object's movement direction based on the position change of the target object in each of the overflow slag monitoring images includes: performing binarization segmentation on each of the overflow slag monitoring images to obtain bright areas and background areas; performing edge detection on each of the bright areas and extracting edge contour information to obtain contour coordinates, wherein each overflow slag monitoring image corresponds one-to-one with the contour coordinates, and the horizontal coordinate of each contour coordinate is a preset horizontal coordinate value; determining the target object's movement direction based on the change of the vertical coordinate of each contour coordinate; or, the step of determining the target object's movement direction based on the position change of the target object in each of the overflow slag monitoring images includes: for each frame of image, performing preprocessing on the overflow slag monitoring image based on Gaussian blur to obtain a preprocessed image, performing key point detection on the preprocessed image based on an image feature detection algorithm; matching multiple key points to obtain multiple matching points, and using the direction of the line connecting each matching point as the target object's movement direction.

6. An electronic device, comprising: The memory and processor are characterized in that the processor is used to execute a computer program stored in the memory to implement the steps of a converter mouth slag identification method as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the slag overflow identification method at the converter mouth as described in any one of claims 1-4.

Images