Converter dry return prediction method, device, medium and equipment

Abstract

This application discloses a method, apparatus, medium, and equipment for predicting converter slag dryness. The method includes: acquiring multiple first images of consecutive frames around the oxygen lance orifice of the converter; determining whether metal splashing exists around the oxygen lance orifice based on the multiple first images; detecting the volume fraction of carbon monoxide in the flue gas composition of the converter and determining the rising slope of the volume fraction within a preset time period; acquiring a second image around the taphole of the converter and determining the flame length around the taphole based on the second image; and determining, during the middle stage of converter blowing, if metal splashing exists around the oxygen lance orifice, the rising slope of the volume fraction is greater than or equal to a preset rising slope threshold, and the flame length is greater than or equal to a preset length threshold, then the converter is determined to have slag dryness. When the converter is in the middle stage of blowing, the blowing ratio of the oxygen lance is greater than or equal to a first blowing ratio threshold and less than or equal to a second blowing ratio threshold. This application can improve the accuracy of predicting slag dryness.

Description

Technical Field

[0001] This application belongs to the field of converter control technology, and in particular relates to a converter re-drying prediction method, device, medium and equipment. Background Technology

[0002] During the mid-stage of converter blowing, slag re-drying is one of the most common and hazardous abnormal conditions in steelmaking. Once re-drying occurs, additional production time is needed to clean the oxygen lance and slag adhering to the furnace mouth, severely impacting operational efficiency. Therefore, early identification and timely intervention of re-drying are both challenging and crucial aspects of steelmaking process control.

[0003] To detect re-drying in advance, a dual-parameter model of audio and flue gas is commonly used. The signal from this model is processed by the controller and outputs a command to lift the lance or add ore to eliminate the re-drying phenomenon. However, in practical applications, the audio signal is easily interfered with by reflections from adjacent converters, dust removal fans, and plant structures, resulting in a high false alarm rate. Summary of the Invention

[0004] The embodiments of this application provide a method for predicting converter slag drying, which can at least improve the accuracy of predicting slag drying phenomena to a certain extent.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] The first aspect of this application provides a method for predicting converter reflow drying, including: Acquire multiple first images of consecutive frames around the oxygen lance orifice of the converter, and determine whether there is metal spatter around the oxygen lance orifice based on the multiple first images; The volume fraction of carbon monoxide in the flue gas of the converter is detected, and the rate of increase of the volume fraction within a preset time period is determined. A second image of the area around the taphole of the converter is obtained, and the flame length around the taphole is determined based on the second image. During the middle stage of the converter's blowing process, if there is metal splashing around the oxygen lance nozzle, the rising slope of the volume fraction is greater than or equal to a preset rising slope threshold, and the flame length is greater than or equal to a preset length threshold, then it is predicted that the converter is experiencing a drying phenomenon. In the case where the converter is in the middle stage of the blowing process, the blowing ratio of the oxygen lance is greater than or equal to a first blowing ratio threshold and less than or equal to a second blowing ratio threshold.

[0007] Optionally, determining whether there is metal spatter around the oxygen lance orifice based on the plurality of first images includes: Each of the first images is thresholded to obtain a binarized image, and the splash particles are determined based on the binarized image; The splashing speed of the splashing particles is determined based on the positional change between two adjacent frames of the binarized image. If, within multiple consecutive frames of the binarized image, the number of splashed particles is greater than or equal to a preset number threshold, and the splashing speed is greater than or equal to a preset speed threshold, then it is determined that metal splashing exists around the oxygen lance hole.

[0008] Optionally, the step of thresholding each of the first images to obtain a binarized image includes: After performing contrast-limited adaptive histogram equalization on each of the first images, threshold segmentation is performed to obtain the binarized image.

[0009] Optionally, determining the splash particles based on the binarized image includes: Obtain all closed connected regions in the binarized image, and treat each connected region as a candidate splash particle; For each connected component, the area and perimeter of the connected component are obtained, and the roundness of the connected component is determined based on the area and perimeter. If the area of ​​the connected component is greater than or equal to a preset area and the roundness of the connected component is greater than or equal to a preset roundness, then the candidate splash particle is selected as the splash particle.

[0010] Optionally, the preset duration includes a start time and an end time, and determining the rising slope of the volume fraction within the preset duration includes: The first volume fraction of carbon monoxide at the initial time and the second volume fraction at the final time are obtained; The difference between the first volume fraction and the second volume fraction is determined, and the ratio of the difference to the preset duration is used as the rising slope.

[0011] Optionally, determining the flame length around the taphole based on the second image includes: The flame region in the second image is identified, and the maximum vertical pixel length of the flame region is determined. Based on a preset mapping relationship between pixel length and actual length, the actual flame length corresponding to the maximum vertical pixel length is determined, and the actual flame length is used as the flame length around the steel outlet.

[0012] Optionally, after predicting that the converter exhibits a back-drying phenomenon, the method further includes: The severity of the re-drying phenomenon is determined based on the rising slope of the volume fraction and the flame length, wherein the rising slope of the volume fraction and the flame length are positively correlated with the severity of the re-drying phenomenon.

[0013] A second aspect of this application provides a converter re-drying prediction device, comprising: The first determining unit is used to acquire multiple first images of consecutive frames around the oxygen lance hole of the converter, and determine whether there is metal spatter around the oxygen lance hole based on the multiple first images; The second determining unit is used to detect the volume fraction of carbon monoxide in the flue gas composition of the converter and determine the rising slope of the volume fraction within a preset time period. The third determining unit is used to acquire a second image around the tapping hole of the converter and determine the flame length around the tapping hole based on the second image. The fourth determining unit is used to predict that the converter has a back-drying phenomenon if, during the middle stage of the blowing process in the converter, there is metal splashing around the oxygen lance nozzle, the rising slope of the volume fraction is greater than or equal to a preset rising slope threshold, and the flame length is greater than or equal to a preset length threshold. In the case that the converter is in the middle stage of the blowing process, the blowing ratio of the oxygen lance is greater than or equal to a first blowing ratio threshold and less than or equal to a second blowing ratio threshold.

[0014] A third aspect of this application provides a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to perform the operations described in any of the methods described in the first aspect.

[0015] A fourth aspect of this application provides an electronic device including one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to perform the operation as described in any of the methods in the first aspect.

[0016] The one or more technical solutions provided in the embodiments of the present invention achieve at least the following technical effects or advantages: The converter re-drying prediction method of this application includes: acquiring multiple first images of consecutive frames around the oxygen lance orifice of the converter, and determining whether metal splashing exists around the oxygen lance orifice based on the multiple first images; detecting the volume fraction of carbon monoxide in the flue gas composition of the converter, and determining the rising slope of the volume fraction within a preset time period; acquiring a second image around the taphole of the converter, and determining the flame length around the taphole based on the second image; in the middle stage of converter blowing, if there is metal splashing around the oxygen lance orifice, the rising slope of the volume fraction is greater than or equal to a preset rising slope threshold, and the flame length is greater than or equal to a preset length threshold, then it is determined that the converter has a re-drying phenomenon. Specifically, in the case where the converter is in the middle stage of blowing, the blowing ratio of the oxygen lance is greater than or equal to a first blowing ratio threshold and less than or equal to a second blowing ratio threshold. Therefore, this application embodiment senses the intensity of the interface between slag and molten steel based on metal splashing at the oxygen lance orifice; combined with the rising slope of the carbon monoxide volume parameter and the flame length at the taphole, it jointly achieves the prediction of slag re-drying phenomenon, thereby improving the accuracy of the prediction results.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings: Figure 1 A schematic diagram of the converter structure according to an embodiment of this application is shown; Figure 2 A flowchart of the converter re-drying prediction method according to an embodiment of this application is shown; Figure 3 A structural diagram of the converter re-drying prediction device according to an embodiment of this application is shown; Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0019] 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 a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0020] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0021] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different models and / or processor devices and / or microcontroller devices.

[0022] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0023] It should also be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such uses of these terms can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described.

[0024] During the mid-stage of converter blowing, slag re-drying is one of the most common and hazardous abnormal conditions in steelmaking. Re-drying refers to a sudden increase in the rate of decarburization in the molten pool and the large-scale consumption of FeO (iron oxide) in the slag. This causes the previously foamy slag to instantly become thinner and its tension to increase. The slag-metal interface loses lubrication, subsequently inducing severe metal splashing, oxygen lance sticking to steel, excessive phosphorus levels at the endpoint, and localized overheating and melting of the furnace lining. Statistics show that splashing caused by re-drying accounts for more than 60% of the total splashing in converters. Each major re-drying event results in an average loss of 1.2 to 2 tons of molten steel, and additional production time is required to clean the oxygen lance and slag sticking to the furnace mouth, severely impacting operational efficiency. Therefore, early identification and timely intervention of re-drying are both challenging and crucial aspects of steelmaking process control.

[0025] To identify reflow in advance, a dual-parameter model using audio and flue gas parameters is commonly used: a directional microphone is installed at the furnace mouth to collect real-time blowing noise; when the sound pressure level suddenly increases by ≥8 dB (decibels) and lasts for more than 5 seconds, slag surface instability is determined; simultaneously, an infrared CO analyzer is installed in the primary dust removal pipeline; if the CO volume fraction rises at a slope ≥0.5% / s within 10 seconds, a reflow alarm is triggered. Both signals are processed by the controller and logic to output a lance lifting or ore addition command to resolve the reflow phenomenon. However, in practical applications, the audio signal is easily interfered with by reflections from adjacent converters, dust removal fans, and plant structures, resulting in a high false alarm rate; the flue gas composition lags by about 20 seconds due to pipeline mixing, making it impossible to distinguish the intensity of reflow, leading to limited intervention measures (generally lifting the lance 200 mm + adding ore 1 kg / t), often resulting in low final temperature and high FeO due to excessive cooling, requiring a 0.3~0.5 min post-blowing, increasing metal consumption and refractory erosion. It lacks the ability to identify earlier or later re-drying processes, making it difficult to meet the current one-click steelmaking requirements for zero splashing during re-drying.

[0026] In view of this, the embodiments of this application use the metal splash at the oxygen lance nozzle to sense the intensity of the interface between the slag and the liquid steel; combined with the rising slope of the carbon monoxide volume parameter and the flame length at the tapping nozzle, the slag drying phenomenon is predicted, thereby improving the accuracy of the prediction results.

[0027] The converter re-drying prediction method of this application embodiment will be described below with reference to the accompanying drawings.

[0028] Figure 1 A schematic diagram of the converter structure according to an embodiment of this application is shown.

[0029] like Figure 1 As shown, the converter includes a converter body 1, which is provided with oxygen lance holes 2. An oxygen lance 3 enters the converter through the oxygen lance holes 2 to supply oxygen. The converter body 1 also has a tapping port 4. During production, the converter contains molten steel 5 and slag 6. To achieve image acquisition, image acquisition devices, such as industrial cameras, are installed around the oxygen lance holes to capture images of the area around them. Similarly, image acquisition devices, such as video cameras, are installed around the tapping port to capture images of the area around the tapping port.

[0030] For example, multiple industrial cameras are evenly distributed on the same cross-section of the outer wall of the oxygen lance body, around the oxygen lance orifice. For instance, four industrial cameras are deployed to acquire omnidirectional images around the oxygen lance orifice. The parameters of the industrial cameras can be: 1280×720 pixels, a 550 nm narrowband filter, and a 20° angle between the lens axis and the tangential direction of the lance body. The field of view of the multiple industrial cameras can cover a range of 0mm-300mm around the oxygen lance orifice.

[0031] For example, a color flame camera is installed above the steel outlet, such as at a position of 1.2m above it.

[0032] Figure 2 A flowchart of the converter back-drying detection method according to an embodiment of this application is shown.

[0033] The first aspect of this application provides a method for predicting converter reflow drying, including but not limited to: Step S10. Acquire multiple first images of consecutive frames around the oxygen lance hole of the converter, and determine whether there is metal spatter around the oxygen lance hole based on the multiple first images; For example, a high-temperature resistant industrial camera is installed around the oxygen lance orifice of the converter, and a protective device isolates it from high temperature and dust interference, allowing real-time acquisition of video streams of the oxygen lance orifice area. A continuous image sequence is extracted from the video stream at a fixed frame rate (e.g., 10-30 frames per second) as the first image.

[0034] In some embodiments, determining whether metal spatter exists around the oxygen lance orifice based on the plurality of first images includes: Step S101. Perform threshold segmentation on each of the first images to obtain a binarized image, and determine the splash particles based on the binarized image; In some embodiments, the step of thresholding each of the first images to obtain a binarized image includes: After performing contrast-limited adaptive histogram equalization on each of the first images, threshold segmentation is performed to obtain the binarized image.

[0035] Understandably, after contrast-limited adaptive histogram equalization, the contrast between the splash particles and the background in the image is significantly enhanced, eliminating arc overexposure. Thresholding segmentation is then performed: the grayscale image is converted into a binarized image using either an adaptive thresholding method or a fixed thresholding method. Specifically, by analyzing the image's grayscale histogram, the optimal threshold that separates the bright splash points from the dark background is selected. In the processed binarized image, for example, the metal splash area appears as a bright white blob (pixel value 1 or 255), while the background becomes black (pixel value 0). This allows the shape and position features of the splash particles to be extracted, providing a foundation for subsequent trajectory tracking and re-drying prediction.

[0036] In some embodiments, determining the splash particles based on the binarized image includes: Step S1011. Obtain all closed connected regions in the binarized image, and treat each connected region as a candidate splash particle; Understandably, by performing morphological analysis on the processed binarized image, a connected component labeling algorithm (such as the two-pass scanning method) is used to identify all closed regions in the image formed by interconnected white pixels. Each independent white region is labeled as an independent connected component and initially defined as a candidate splash particle. This process transforms the set of pixels in the image into object entities that can be used for subsequent geometric analysis. This effectively distinguishes independent metal droplets, potentially adhering clumps, and image noise, providing a dataset for subsequent shape-feature-based screening.

[0037] Step S1012. For each connected component, obtain the area and perimeter of the connected component, determine the roundness of the connected component based on the area and perimeter, and if the area of ​​the connected component is greater than or equal to a preset area and the roundness of the connected component is greater than or equal to a preset roundness, then the candidate splashing particle is taken as the splashing particle.

[0038] For example, roundness C = 4πA / P 2 A represents area, P represents perimeter, and the closer the roundness C is to 1, the closer the shape is to an ideal circle. Metal splash droplets tend to spherize in the air, and their images are usually close to circular or elliptical. Two thresholds are preset: an area threshold (e.g., 20 pixels) is used to filter out fine noise; a roundness threshold (e.g., 0.6) is used to exclude elongated streaks or irregular slag lumps. Candidate splash particles that simultaneously meet both area and roundness conditions are considered valid splash particles, thereby improving the accuracy of target identification.

[0039] Step S102. Determine the splash velocity of the splashing particles based on the positional change between two adjacent frames of the binarized image; Understandably, identifying and tracking the same splash particle that has been successfully matched in the previous and current frames is typically based on the principles of positional proximity and feature similarity. The pixel displacement Δs of the particle's centroid position in the two frames is calculated. Combined with the known image acquisition frame interval Δt (e.g., Δt ≈ 0.033 seconds for 30 frames per second), the two-dimensional pixel velocity of the splash particle on the image plane can be calculated using the physical kinematic formula v = Δs / Δt. To obtain the real-world velocity value (meters per second), the pixel displacement can be converted into actual physical displacement using camera calibration parameters.

[0040] Step S103. If, in multiple consecutive frames of the binarized image, the number of splashed particles is greater than or equal to a preset number threshold, and the splashing speed is greater than or equal to a preset speed threshold, then it is determined that there is metal splashing around the oxygen lance hole.

[0041] For example, if in a consecutive 10-frame image sequence, the number of spattered particles detected in each frame is no less than 5, and at least one spattered particle has an instantaneous velocity of 4 m / s or more, then metal spatter is considered to exist around the oxygen lance orifice. This ensures that the spattering phenomenon is not an accidental, isolated spark, but rather has the characteristics of being collective and continuous. The spattering velocity can, to some extent, reflect the energy required for molten metal droplets to be carried out of the molten pool by high-speed gas dynamics, and is a precursor to violent reactions in the furnace and the possibility of back-drying. Thus, it can both capture early signs of abnormality and avoid false alarms caused by brief sparks or image noise.

[0042] During logical processing, if the condition of step S103 is met, the metal splash flag can be set, for example, flag S=1; if there is no splash, flag S=0.

[0043] Step S20. Detect the volume fraction of carbon monoxide in the flue gas composition of the converter and determine the rising slope of the volume fraction within a preset time period; For example, a laser analyzer is installed on the converter gas pipeline. The instrument emits a laser beam of a specific wavelength that passes through the flue gas. Carbon monoxide molecules selectively absorb the light of that specific wavelength, causing the light intensity to attenuate. According to the Lambert-Beer law, the degree of attenuation is proportional to the concentration of carbon monoxide, and its real-time concentration, i.e., its volume fraction, can be calculated.

[0044] In some embodiments, the preset duration includes a start time and an end time, and determining the rising slope of the volume fraction within the preset duration includes: Step S201. Obtain the first volume fraction of carbon monoxide at the starting time and the second volume fraction at the ending time; Step S202. Determine the difference between the first volume fraction and the second volume fraction, and use the ratio of the difference to the preset duration as the rising slope.

[0045] To facilitate understanding, steps S201-S202 are explained below using formulas.

[0046] kCO(t) = [C(t) – C(t – 5)] / 5; Where kCO(t) represents the rising slope, C(t) represents the volume fraction at the end time, C(t–5) represents the volume fraction at the beginning time, and 5 is the preset duration.

[0047] For example, volume fractions over a period of time, such as 60 seconds, can be stored using caching techniques, and the rising slope can be calculated using a 5-second sliding window.

[0048] Step S30. Obtain a second image of the area around the tapping spout of the converter, and determine the flame length around the tapping spout based on the second image; For example, by installing a high-temperature resistant industrial camera, such as an infrared thermal imager or a pinhole camera with a heat-insulating protective cover and a compressed air cooling system, above the steel tapping outlet, the captured video signal can be transmitted to the main control room via cable or wireless network, thus obtaining a clear second image of the area around the steel tapping outlet in real time.

[0049] In some embodiments, determining the flame length around the taphole based on the second image includes: Step S301. Identify the flame region in the second image and determine the maximum vertical pixel length of the flame region; For example, after acquiring RGB (red, green, blue) images using a flame camera, gamma correction is performed to enhance shadow details and contrast. Subsequently, the images are converted to the HSV (Hue, Saturation, Value) color space, and the flame is separated from the background by utilizing the significant characteristics of the flame in hue, saturation, and value. An adaptive thresholding algorithm is applied to the luminance component or the processed image to obtain a clear binary flame region, and its maximum vertical pixel length is calculated. The maximum vertical pixel length can be the length of the column containing the most flame pixels in all consecutive vertical directions in the segmented binary flame image; it represents the furthest pixel distance the flame extends vertically and is the image basis for calculating the actual flame height.

[0050] Step S302. Based on the preset mapping relationship between pixel length and actual length, determine the actual flame length corresponding to the maximum vertical pixel length, and use the actual flame length as the flame length around the steel outlet.

[0051] For example, the preset mapping relationship between pixel length and actual length can be characterized by an on-site calibration curve.

[0052] Step S40. In the middle stage of the converter blowing process, if there is metal splashing around the oxygen lance nozzle, the rising slope of the volume fraction is greater than or equal to a preset rising slope threshold, and the flame length is greater than or equal to a preset length threshold, then it is predicted that the converter has a back-drying phenomenon. In the case that the converter is in the middle stage of the blowing process, the blowing ratio of the oxygen lance is greater than or equal to a first blowing ratio threshold and less than or equal to a second blowing ratio threshold.

[0053] The first blowing ratio threshold can be 30%, and the second blowing ratio threshold can be 80%. The blowing ratio refers to the ratio of the current oxygen supply to the target total oxygen supply.

[0054] For example, the rising slope threshold can be 1, 1.1, 1.2, 1.3, etc., and the length threshold can be 0.5m, 0.55m, 0.6m, etc.

[0055] Therefore, the embodiments of this application use the metal splash at the oxygen lance nozzle to sense the intensity of the interface between the slag and the liquid steel, and the signal is free from plant noise interference. By combining the rising slope of the carbon monoxide volume parameter and the flame length at the tapping nozzle, the slag drying phenomenon can be predicted, thereby improving the accuracy of the prediction results. This allows for early intervention in the drying phenomenon and avoids more serious consequences.

[0056] In some embodiments, after predicting that the converter exhibits a back-drying phenomenon, the method further includes: The severity of the re-drying phenomenon is determined based on the rising slope of the volume fraction and the flame length, wherein the rising slope of the volume fraction and the flame length are positively correlated with the severity of the re-drying phenomenon.

[0057] For example, the severity of re-drying can be characterized by re-drying levels, such as: small re-drying: rising slope kCO∈[1, 2), flame length L∈[0.5, 1); medium re-drying: kCO∈[2, 3), L∈[1, 1.3); large re-drying: kCO≥3, L≥1.3.

[0058] Therefore, the embodiments of this application can determine the severity of the back-drying phenomenon through parameter detection, thereby guiding the subsequent implementation of different back-drying relief measures, such as controlling the position of the oxygen lance and accurately dispensing the coolant, reducing the amount of iron ore added per ton of steel, and reducing the post-blowing time.

[0059] To facilitate understanding, the method for predicting the phenomenon of rice drying in this application will be illustrated below with examples.

[0060] For example: The planned total oxygen content for a 210 t converter is 10800 Nm³. When oxygen is blown to η≈32.7%, the high-speed camera continuously detects N=7, v_max=5.2 m / s, and S is set to 1; the laser CO meter shows kCO=2.3% / s; the flame camera shows L=1.1 m. A medium-sized re-drying is determined, and the following actions are immediately taken: the lance position is raised from 1.80 m to 1.95 m, and the iron ore increment is 1.0 kg / t. After 15 s, S=0, kCO=0.3% / s, the re-drying is lifted, and the original parameters are restored. There is no splashing throughout the process, the endpoint [P]=0.008%, there is no back-blowing, and the smelting cycle is shortened by 18 s compared to the historical average.

[0061] For example, a 210-ton converter has a planned total oxygen content of 10200 Nm³. When oxygen is blown to η≈55.1%, the high-speed camera continuously detects N=18, v_max=3.8 m / s, and S is set to 1; the laser CO meter shows kCO=2.5% / s; and the flame camera shows L=1.2 m. The system determines that there is a medium-sized back-drying and immediately executes the following: the lance position is raised from 1.9 m to 2.0 m, and the iron ore increment is 0.8 kg / t. After 18 seconds, S=0, kCO=0.2% / s, the back-drying is lifted, and the original parameters are restored. There is no splashing throughout the process, the endpoint [P]=0.01%, there is no back-blowing, and the smelting cycle is shortened by 20 seconds compared to the historical average.

[0062] Figure 3 A structural diagram of the converter re-drying prediction device according to an embodiment of this application is shown.

[0063] A second aspect of this application provides a converter re-drying prediction device 200, comprising: The first determining unit 201 is used to acquire multiple first images of consecutive frames around the oxygen lance hole of the converter, and determine whether there is metal splashing around the oxygen lance hole based on the multiple first images. The second determining unit 202 is used to detect the volume fraction of carbon monoxide in the flue gas composition of the converter and determine the rising slope of the volume fraction within a preset time period. The third determining unit 203 is used to acquire a second image around the tapping hole of the converter and determine the flame length around the tapping hole based on the second image; The fourth determining unit 204 is used to predict that the converter has a back-drying phenomenon if, during the middle stage of the blowing process of the converter, there is metal splashing around the oxygen lance nozzle, the rising slope of the volume fraction is greater than or equal to a preset rising slope threshold, and the flame length is greater than or equal to a preset length threshold. In the case that the converter is in the middle stage of the blowing process, the blowing ratio of the oxygen lance is greater than or equal to a first blowing ratio threshold and less than or equal to a second blowing ratio threshold.

[0064] A third aspect of this application provides a computer-readable storage medium storing at least one computer program instruction, which is loaded and executed by a processor to perform the operations as described in any of the methods in the first aspect.

[0065] Computer-readable storage media may be portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the computer-readable storage medium of this application is not limited thereto. In this application, the readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0066] A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0067] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0068] A fourth aspect of this application provides an electronic device including one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to perform the operation as described in any of the methods in the first aspect.

[0069] like Figure 4 As shown, the electronic device 400 is manifested in the form of a general-purpose computing device. The components of the electronic device 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including storage unit 420 and processing unit 410).

[0070] The storage unit stores program code, which can be executed by the processing unit 410, causing the processing unit 410 to perform the steps described in the "Embodiment Method" section above according to various exemplary embodiments of this application.

[0071] Storage unit 420 may include readable media in the form of volatile storage units, such as random access memory (RAM) 421 and / or cache 422, and may further include read-only memory (ROM) 423.

[0072] Storage unit 420 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0073] Bus 430 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0074] Electronic device 400 can also communicate with one or more external devices 500 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 400, and / or with any device that enables electronic device 400 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed through I / O (input / output) interface 450, which can also be connected to display unit 440 to display the communication content. Furthermore, electronic device 400 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) through network adapter 460. As shown, network adapter 460 communicates with other modules of electronic device 400 via bus 430. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0075] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be 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 displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0077] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0078] 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 invention, 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 invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0079] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for predicting converter reflow, characterized in that, include: Acquire multiple first images of consecutive frames around the oxygen lance orifice of the converter, and determine whether there is metal spatter around the oxygen lance orifice based on the multiple first images; The volume fraction of carbon monoxide in the flue gas of the converter is detected, and the rate of increase of the volume fraction within a preset time period is determined. A second image of the area around the taphole of the converter is obtained, and the flame length around the taphole is determined based on the second image. During the middle stage of the converter's blowing process, if there is metal splashing around the oxygen lance nozzle, the rising slope of the volume fraction is greater than or equal to a preset rising slope threshold, and the flame length is greater than or equal to a preset length threshold, then it is predicted that the converter is experiencing a drying phenomenon. In the case where the converter is in the middle stage of the blowing process, the blowing ratio of the oxygen lance is greater than or equal to a first blowing ratio threshold and less than or equal to a second blowing ratio threshold.

2. The method according to claim 1, characterized in that, The step of determining whether there is metal spatter around the oxygen lance hole based on the plurality of first images includes: Each of the first images is thresholded to obtain a binarized image, and the splash particles are determined based on the binarized image; The splashing velocity of the splashing particles is determined based on the positional change between two adjacent frames of the binarized image. If, within multiple consecutive frames of the binarized image, the number of splashed particles is greater than or equal to a preset number threshold, and the splashing speed is greater than or equal to a preset speed threshold, then it is determined that metal splashing exists around the oxygen lance hole.

3. The method according to claim 2, characterized in that, The step of thresholding each of the first images to obtain a binarized image includes: After performing contrast-limited adaptive histogram equalization on each of the first images, threshold segmentation is performed to obtain the binarized image.

4. The method according to claim 2, characterized in that, The step of determining the splash particles based on the binarized image includes: Obtain all closed connected regions in the binarized image, and treat each connected region as a candidate splash particle; For each connected component, the area and perimeter of the connected component are obtained, and the roundness of the connected component is determined based on the area and perimeter. If the area of ​​the connected component is greater than or equal to a preset area and the roundness of the connected component is greater than or equal to a preset roundness, then the candidate splash particle is selected as the splash particle.

5. The method according to any one of claims 1-4, characterized in that, The preset duration includes a start time and an end time, and determining the rising slope of the volume fraction within the preset duration includes: The first volume fraction of carbon monoxide at the initial time and the second volume fraction at the final time are obtained; The difference between the first volume fraction and the second volume fraction is determined, and the ratio of the difference to the preset duration is used as the rising slope.

6. The method according to any one of claims 1-4, characterized in that, Determining the flame length around the taphole based on the second image includes: The flame region in the second image is identified, and the maximum vertical pixel length of the flame region is determined. Based on a preset mapping relationship between pixel length and actual length, the actual flame length corresponding to the maximum vertical pixel length is determined, and the actual flame length is used as the flame length around the steel outlet.

7. The method according to claim 1, characterized in that, After predicting the presence of back-drying in the converter, the method further includes: The severity of the re-drying phenomenon is determined based on the rising slope of the volume fraction and the flame length, wherein the rising slope of the volume fraction and the flame length are positively correlated with the severity of the re-drying phenomenon.

8. A converter re-drying prediction device, characterized in that, include: The first determining unit is used to acquire multiple first images of consecutive frames around the oxygen lance hole of the converter, and determine whether there is metal spatter around the oxygen lance hole based on the multiple first images; The second determining unit is used to detect the volume fraction of carbon monoxide in the flue gas composition of the converter and determine the rising slope of the volume fraction within a preset time period. The third determining unit is used to acquire a second image around the tapping hole of the converter and determine the flame length around the tapping hole based on the second image. The fourth determining unit is used to predict that the converter has a back-drying phenomenon if, during the middle stage of the blowing process in the converter, there is metal splashing around the oxygen lance nozzle, the rising slope of the volume fraction is greater than or equal to a preset rising slope threshold, and the flame length is greater than or equal to a preset length threshold. In the case that the converter is in the middle stage of the blowing process, the blowing ratio of the oxygen lance is greater than or equal to a first blowing ratio threshold and less than or equal to a second blowing ratio threshold.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program instruction, which is loaded and executed by a processor to perform the operation as described in any one of claims 1-7.

10. An electronic device, characterized in that, It includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to perform the operation performed by the method as described in any one of claims 1-7.

Images