A method and system for alloying steel ladles based on steel molten surface image acquisition and processing

Abstract

This invention belongs to the field of image recognition and processing technology, specifically a method and system for adding alloys to a ladle based on the acquisition and processing of images of molten steel surface. It uses the initial image acquisition and processing results of the molten steel surface in the initial state of the ladle as the grayscale threshold of the molten steel surface. Based on the comparison between the image acquisition and processing results of the molten steel surface and the grayscale threshold during alloy addition, the opening of the alloy hopper and / or the argon flow rate are dynamically adjusted in real time until the alloy addition is complete. This invention enables rapid and accurate control of the alloy addition speed and argon flow rate, allowing for personalized alloy addition for different working conditions. It adjusts the image acquisition threshold according to the actual usage environment and the properties of the alloy itself, and is universally applicable to various ferroalloys used in steelmaking, meeting the production needs of different steel grades and equipment types.

Description

Technical Field

[0001] This invention relates to the field of image recognition and processing technology, specifically to a method and system for alloying steel ladles based on the acquisition and processing of images of molten steel surfaces. Background Technology

[0002] Alloying in molten steel is a crucial measure for adjusting the composition, temperature, and inclusion morphology of molten steel. However, without fixed evaluation criteria for the location, timing, method, and morphology and particle size of the alloy added, relying solely on on-site operational experience can lead to unstable alloy element recovery, significant alloy loss, and substantial fluctuations in molten steel composition. This negatively impacts reducing steel production costs and achieving narrow composition control in molten steel, and in severe cases, can even result in a decline in steel quality. Currently, there are two main methods for ladle alloying. One method involves adding alloys from a high-level silo or manually, based on calculated weighing and relying on the experience of on-site technicians. This method is simple and quick, but it is heavily influenced by human factors, resulting in unstable alloy recovery, significant alloy loss, and difficulty in achieving precise operation. The other method involves feeding alloys through a wire feeder. The feeding amount is calculated based on the molten steel composition and target values, and the composition of the molten steel is adjusted by controlling the feeding length of the wire feeder. This method allows for easier and more precise control of alloy addition, but it limits the types of alloys that can be used and imposes stringent requirements on the feeding angle, feeding speed, and wire diameter. If the relevant process parameters do not match the on-site equipment conditions, it can lead to insufficient wire feeding depth or even coiling at the slag shell. The final results of both methods are ultimately affected by the alloying rate and the flow field within the molten steel. Summary of the Invention

[0003] To address the problems existing in the prior art, the main objective of this invention is to propose a method and system for alloying steel ladles based on steel molten surface image acquisition and processing.

[0004] To address the aforementioned technical problems, according to one aspect of the present invention, the present invention provides the following technical solution:

[0005] A method for alloying steel ladles based on steel molten surface image acquisition and processing includes the following steps:

[0006] S1. After the ladle arrives at the argon station, adjust the argon flow rate to the minimum allowable value for the process, collect images of the molten steel surface, and obtain the temperature and initial image of the molten steel surface.

[0007] S2. Perform Blob analysis on the initial image to remove other backgrounds outside the molten steel surface, use the Sobel operator to obtain the accurate outline of the molten steel surface, and then convert the initial image of the molten steel surface into a grayscale image to obtain the grayscale threshold of the molten steel surface.

[0008] S3. Calculate the total mass of alloy to be added based on the steel composition and temperature information; in the initial stage of alloying, add 1 / 3 of the total alloy mass at a high initial alloying speed. When 1 / 3 of the total alloy mass is about to be added, gradually reduce the opening of the alloy hopper. At the same time, perform image acquisition and analysis on the steel surface to obtain the analysis results. Based on the comparison between the analysis results and the threshold, issue adjustment commands for the alloy hopper opening and / or argon flow rate and complete the setting.

[0009] S4. Add 1 / 3 of the total alloy mass according to the setting, and repeat step S3. If the image acquisition and analysis result does not exceed the threshold, maintain the setting and complete the addition of the remaining part; if the image acquisition and analysis result exceeds the threshold, complete the new setting according to the adjustment command, add 1 / 2 of the remaining alloy mass, and perform image acquisition and analysis again. Repeat the above steps until the alloy addition is complete.

[0010] As a preferred embodiment of the steel ladle alloying method based on steel liquid surface image acquisition and processing described in this invention, in step S1, after obtaining the temperature of the steel liquid surface and the initial image of the steel liquid surface, the method further includes gradually increasing the flow rate of bottom-blown argon gas.

[0011] As a preferred embodiment of the steel ladle alloying method based on steel liquid surface image acquisition and processing described in this invention, in step S2, pixel values ​​are extracted from the locations where peak values ​​appear in the grayscale image, and the radius of the circle is determined by using the position corresponding to the peak value as the center, and the total number of pixels within the area covered by the circle is calculated to obtain the grayscale threshold of the steel liquid surface.

[0012] As a preferred embodiment of the steel ladle alloying method based on steel liquid surface image acquisition and processing described in this invention, in step S3, the alloy hopper opening control motor adopts a continuous speed regulation method to ensure the accuracy of system operation and improve the response speed of system control signals.

[0013] In a preferred embodiment of the ladle alloying method based on steel molten surface image acquisition and processing described in this invention, in step S3, the weight of the alloy added to the ladle is the cumulative effect of the alloying rate on the alloying time, and has the following relationship:

[0014]

[0015] In the formula, W is the weight of the alloy added to the ladle, V is the alloying rate, and T is the alloying time.

[0016] As a preferred embodiment of the ladle alloying method based on steel molten surface image acquisition and processing described in this invention, wherein: in step S3, the alloying speed V is segmented according to the weighing weight:

[0017]

[0018] In the formula, V0 is a constant, n is the rate of descent of the velocity, and W L t represents the weight of the alloy not added to the ladle during speed conversion, t represents the total time taken to add the alloy, and t1 represents the time taken to add the alloy from the start to the current stage.

[0019] As a preferred embodiment of the ladle alloying method based on steel molten surface image acquisition and processing described in this invention, wherein: after step S4, the method further includes,

[0020] S5. Analyze the yield of this alloy addition process based on the composition information determined by the ladle sampling results, and compare it with other heats of the same steel grade to summarize the composition fluctuation and realize the self-learning of the ladle alloy addition method.

[0021] To solve the above-mentioned technical problems, according to another aspect of the present invention, the present invention provides the following technical solution:

[0022] A ladle alloying system that implements the above-mentioned ladle alloying method based on steel liquid surface image acquisition and processing.

[0023] An information data processing terminal for implementing the above-mentioned ladle alloying method based on steel liquid surface image acquisition and processing.

[0024] A computer-readable storage medium includes instructions that, when executed on a computer, cause the computer to perform the above-described ladle alloying method based on steel molten surface image acquisition and processing.

[0025] The beneficial effects of this invention are as follows:

[0026] This invention proposes a method and system for adding alloys to a ladle based on image acquisition and processing of molten steel surface. The method uses the initial image acquisition and processing results of the molten steel surface in the initial state of the ladle as the grayscale threshold. Based on the comparison between the image acquisition and processing results of the molten steel surface and the grayscale threshold during alloy addition, the opening of the alloy hopper and / or the argon flow rate are dynamically adjusted in real time until the alloy addition is complete. This invention enables rapid and accurate control of the alloy addition speed and argon flow rate, allowing for personalized alloy addition for different working conditions. The image acquisition threshold can be adjusted according to the actual usage environment and the properties of the alloy itself. It is applicable to various ferroalloys used in steelmaking and can meet the production needs of different steel grades and equipment types. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0028] Figure 1 This is a data acquisition and control logic diagram for the present invention;

[0029] Figure 2 This is an image from Embodiment 1 of the present invention.

[0030] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0031] The technical solutions described below in conjunction with the embodiments will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] This invention provides a method and system for adding alloys to a ladle based on steel molten surface image acquisition and processing. It solves the problem that the alloying process in a ladle relies solely on manual judgment of the amount added, which cannot be further refined. The method offers the following advantages:

[0033] (1) The present invention can achieve rapid and accurate control of the alloying speed and the blowing flow rate, and can realize personalized alloy addition for different working conditions.

[0034] (2) This invention can be used for alloys in different forms, including but not limited to block, spherical, linear and plate shapes. The image acquisition threshold can be adjusted according to the actual use environment and the properties of the alloy itself. It is universal for various steelmaking ferroalloys and can meet the production needs of different steel grades and equipment types.

[0035] (3) The image acquisition method and analysis processing used in this invention are all electronic testing methods, which only consume the power during operation, avoid the temperature measurement and sampling link of molten steel analysis, reduce the wear and tear of samplers and sensors, and are a resource-saving technical means that helps to realize the green, low-carbon and efficient transformation of the steel industry.

[0036] (4) By accumulating production data, this invention can summarize the yield of various alloying elements added to the ladle under different production conditions, which is more consistent with actual production, provides accurate reference values ​​for production technicians to calculate the amount of alloy used, and also lays the foundation for subsequent fully automated steelmaking operations.

[0037] According to one aspect of the present invention, the present invention provides the following technical solution:

[0038] A method for alloying steel ladles based on steel molten surface image acquisition and processing includes the following steps:

[0039] S1. After the ladle arrives at the argon station, adjust the argon flow rate to the minimum allowable value for the process, collect images of the molten steel surface, and obtain the temperature and initial image of the molten steel surface.

[0040] S2. Perform Blob analysis on the initial image to remove other backgrounds outside the molten steel surface, use the Sobel operator to obtain the accurate outline of the molten steel surface, and then convert the initial image of the molten steel surface into a grayscale image to obtain the grayscale threshold of the molten steel surface.

[0041] S3. Based on the steel composition and temperature information, calculate the total mass of alloy to be added; in the initial stage of alloying, add 1 / 3 of the total alloy mass at a high initial alloying speed. When 1 / 3 of the total alloy mass is about to be added, gradually reduce the opening of the alloy hopper. At the same time, perform image acquisition and analysis on the steel surface to obtain the analysis results. Based on the comparison of the analysis results with the threshold, determine whether the alloy added to the steel has phenomena such as exposure, smoke, or alloy floating. Issue adjustment commands for the alloy hopper opening and / or argon flow rate and complete the setting; if an instruction to reduce the alloy hopper opening is issued to reduce the alloying speed, or an instruction to reduce the argon flow rate is issued to change the flow field in the ladle, reduce the buoyancy of the alloy, and prevent the alloy from floating to the slag surface with the flow of the steel.

[0042] S4. Add 1 / 3 of the total alloy mass according to the setting, and repeat step S3. If the image acquisition and analysis result does not exceed the threshold, maintain the setting and complete the addition of the remaining part; if the image acquisition and analysis result exceeds the threshold, complete the new setting according to the adjustment command, add 1 / 2 of the remaining alloy mass, and perform image acquisition and analysis again. Repeat the above steps until the alloy addition is complete.

[0043] Preferably, in step S1, after obtaining the temperature of the molten steel surface and the initial image of the molten steel surface, the flow rate of bottom-blown argon gas is gradually increased; the image of the molten steel surface is acquired using image acquisition equipment commonly used in the art, such as, but not limited to, an infrared camera.

[0044] Preferably, in step S2, the brightness of the molten steel surface image reflects phenomena such as temperature, exposure, smoke, and alloy floating. Pixel values ​​are extracted from the locations where peaks appear in the grayscale image. Using the location corresponding to the peak as the center, the radius of the circle is determined by Hough transform. The total number of pixels within the area covered by the circle is calculated to obtain the grayscale threshold of the molten steel surface. Different threshold ranges can correspond to different molten steel surface conditions.

[0045] Preferably, in step S3, the alloy hopper opening control motor adopts a continuous speed regulation method to ensure the accuracy of system operation and improve the response speed of system control signals. The weight of alloy added into the ladle is the cumulative effect of the alloy adding speed on the alloy adding time, and has the following relationship:

[0046]

[0047] In the formula, W is the weight of the alloy added to the ladle, V is the alloying rate, and T is the alloying time.

[0048] The alloying speed V is segmented based on the weighed weight:

[0049]

[0050] In the formula, V0 is a constant, n is the rate of descent of the velocity, and W L t represents the weight of the alloy not added to the ladle during speed conversion, t represents the total time taken to add the alloy, and t1 represents the time taken to add the alloy from the start to the current stage.

[0051] Preferably, after step S4, the method further includes:

[0052] S5. Analyze the yield of this alloy addition process based on the composition information determined by the ladle sampling results, and compare it with other heats of the same steel grade to summarize the composition fluctuation and realize the self-learning of the ladle alloy addition method.

[0053] Preferably, the method further includes the following steps before step S1:

[0054] S0. The ladle alloying system receives the ladle transfer signal and the system starts to switch from standby to active state.

[0055] According to another aspect of the present invention, the present invention provides the following technical solution:

[0056] A ladle alloying system that implements the above-mentioned ladle alloying method based on steel liquid surface image acquisition and processing.

[0057] An information data processing terminal for implementing the above-mentioned ladle alloying method based on steel liquid surface image acquisition and processing.

[0058] A computer-readable storage medium includes instructions that, when executed on a computer, cause the computer to perform the above-described ladle alloying method based on steel molten surface image acquisition and processing.

[0059] The technical solution of the present invention will be further described below with reference to specific embodiments.

[0060] Example 1

[0061] A method for alloying steel ladles based on steel molten surface image acquisition and processing includes the following steps:

[0062] S0. The ladle alloying system receives the ladle transfer signal and the system starts to switch from standby to active state;

[0063] S1. After the ladle arrives at the argon station, adjust the argon flow rate to the minimum allowable value of 40 L / min. Use an infrared camera to capture images of the molten steel surface, obtaining the temperature and initial image of the molten steel surface (e.g., ...). Figure 2 As shown in a), the temperature is 1613℃, and the flow rate of bottom-blown argon is gradually increased to 100L / min;

[0064] S2. Perform Blob analysis on the initial image to remove background outside the molten steel surface, use the Sobel operator to obtain the accurate outline of the molten steel surface, and then convert the initial image of the molten steel surface into a grayscale image (e.g., ...). Figure 2 As shown in b), pixel values ​​are extracted from the locations where peaks appear in the grayscale image. Using the location corresponding to the peak as the center, the radius of the circle is determined by Hough transform. The total number of pixels within the area covered by the circle is then calculated to obtain the grayscale threshold of the molten steel surface.

[0065] S3. Based on the steel composition (as shown in Table 1) and temperature information, the total mass of alloy to be added is calculated to be 3786 kg. In the initial stage of alloying, 1 / 3 of the total alloy mass is added at an initial rate of 200 kg / s. When 1 / 3 of the total alloy mass is almost added, the opening of the alloy hopper is gradually reduced. Simultaneously, images of the steel surface are acquired and analyzed. The analysis results show that a large amount of exposed steel surface is observed (e.g., ...). Figure 2 As shown in c), an order was immediately issued to reduce the opening of the alloy hopper, so that the alloy addition rate was 100 kg / s, and the argon flow rate was adjusted to 60 L / min;

[0066] Table 1

[0067]

[0068] S4. Add 1 / 3 of the total alloy mass according to the setting, repeat step S3. The image acquisition and analysis results show that the threshold is not exceeded. Add 1 / 2 of the remaining alloy mass according to the setting, and perform image acquisition and analysis again. Repeat the above steps until the alloy is added.

[0069] S5. Analyze the yield of this alloy addition process based on the composition information determined by the ladle sampling results, and compare it with other heats of the same steel grade to summarize the composition fluctuation and realize the self-learning of the ladle alloy addition method.

[0070] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A method for alloying steel ladles based on steel molten surface image acquisition and processing, characterized in that, Includes the following steps: S1. After the ladle arrives at the argon station, adjust the argon flow rate to the minimum allowable value for the process, collect images of the molten steel surface, and obtain the temperature and initial image of the molten steel surface. S2. Perform Blob analysis on the initial image to remove other backgrounds outside the molten steel surface, use the Sobel operator to obtain the accurate outline of the molten steel surface, and then convert the initial image of the molten steel surface into a grayscale image to obtain the grayscale threshold of the molten steel surface. S3. Calculate the total mass of alloy to be added based on the steel composition and temperature information; in the initial stage of alloying, add 1 / 3 of the total alloy mass at a high initial alloying speed. When 1 / 3 of the total alloy mass is about to be added, gradually reduce the opening of the alloy hopper. At the same time, perform image acquisition and analysis on the steel surface to obtain the analysis results. Based on the comparison between the analysis results and the threshold, issue adjustment commands for the alloy hopper opening and / or argon flow rate and complete the setting. S4. Add 1 / 3 of the total alloy mass according to the setting; repeat the image acquisition and analysis operation of step S3. If the image acquisition and analysis result does not exceed the threshold, maintain the setting and complete the addition of the remaining alloy. If the image acquisition and analysis result exceeds the threshold, complete the new setting according to the adjustment command, add 1 / 2 of the remaining alloy mass, and perform image acquisition and analysis again. If the image acquisition and analysis result does not exceed the threshold, maintain the setting and complete the addition of the remaining alloy. If the image acquisition and analysis result exceeds the threshold, complete the new setting according to the adjustment command, add 1 / 2 of the remaining alloy mass, and repeat this cycle until the alloy addition is complete.

2. The method for adding alloys to a steel ladle according to claim 1, characterized in that, In step S1, after obtaining the temperature of the molten steel surface and the initial image of the molten steel surface, the flow rate of bottom-blown argon gas is gradually increased.

3. The method for adding alloys to a steel ladle according to claim 1, characterized in that, In step S2, pixel values ​​are extracted from the locations where peaks appear in the grayscale image. Using the location corresponding to the peak as the center, the radius of the circle is determined by Hough transform. The total number of pixels within the area covered by the circle is then calculated to obtain the grayscale threshold of the molten steel surface.

4. The method for adding alloys to a steel ladle according to claim 1, characterized in that, In step S3, the alloy hopper opening control motor adopts a continuous speed regulation method.

5. The method for adding alloys to a steel ladle according to claim 1, characterized in that, Following step S4, the following steps are also included: S5. Analyze the yield of this alloy addition process based on the composition information determined by the ladle sampling results, and compare it with other heats of the same steel grade to summarize the composition fluctuation and realize the self-learning of the ladle alloy addition method.

6. An information data processing terminal for implementing the ladle alloying method based on steel molten surface image acquisition and processing as described in any one of claims 1-5.

7. A computer-readable storage medium comprising instructions, when executed on a computer, causing the computer to perform the ladle alloying method based on steel molten surface image acquisition and processing as described in any one of claims 1-5.

Images