Automatic slagging method in LF refining process

Abstract

The invention provides an automatic slagging method in the LF refining process. The automatic slagging method comprises the steps that firstly, slagging related data are collected; 2, an LF refining slagging model is built, and the lime adding amount is calculated; 3, calculating the addition amount of fluorite; 4, the adding amount of the deoxidizing agent is calculated, and automatic discharging is carried out; 5, sampling the stained slag, and identifying the color grade and fluidity of the steel slag based on an image deep learning technology; 6, calculating the supplementing amount of the deoxidizing agent, supplementing the deoxidizing agent, and supplementing lime and fluorite according to the fluidity; and seventhly, the fifth step and the sixth step are repeated, and the white slag is kept till refining is finished. By constructing the mechanism model based on the slagging process and the convolutional network technology, rapid white slag making is achieved, the purity of molten steel is improved, and the automation level of the refining slagging process is improved.

Description

Technical Field

[0001] The present application relates to the technical field of steel smelting, and in particular to an automatic slag making method in a LF refining process. Background Art

[0002] LF refining furnace is an important equipment in the steel smelting process. It removes impurities from molten steel through refining treatment, thereby improving the quality of molten steel. Slag making technology is a key link in the operation of LF refining furnace, which has a vital impact on the chemical reaction in the furnace and the quality of molten steel. In recent years, with the continuous improvement of the steel industry's requirements for molten steel quality and production efficiency, the research and application of efficient slag making technology for LF refining furnace has received widespread attention. Steel companies urgently need to improve production efficiency, reduce production costs, and meet the market demand for high-quality steel by optimizing slag making technology.

[0003] The traditional refining process relies on manual judgment and operation, and there are problems such as large fluctuations in process control, high material consumption and energy consumption, and poor product quality stability. Due to the limitations of manual experience and operation, the slag-making effect of traditional slag-making technology is often not ideal, and the impurities in the molten steel are not completely removed. In addition, affected by the slag under the converter, the LF refining process often encounters problems such as difficulty in making white slag, long refining time, poor desulfurization and inclusion control effects, unstable product quality and high production costs. Chinese patent CN113278766A discloses "a process control method for improving the slag-making efficiency of a newly built ladle LF furnace". This method mainly uses a method of recovering the residual heat slag from continuous casting to improve the slag-making efficiency. Although this method can increase the slag-making speed, it is mainly achieved by diluting the FeO in the slag and is not suitable for steel grades with relatively high quality requirements. Chinese patent CN112322837A discloses "a smelting process for efficient slag making and desulfurization of LF aluminum killed steel". This process is mainly achieved by migrating the slag making process, that is, 80% of the slag making materials are added during the steel making process. However, this process cannot solve the problem of rapid white slag making, and the white slag is still manually scooped out, and the slag making is adjusted after visual observation, with a low degree of automation and intelligence. Summary of the invention

[0004] The present application is made in view of the above-mentioned problems, and its purpose is to provide an automatic slag-making method for the LF refining process. By constructing a mechanism model based on the slag-making process and convolutional network technology, it can achieve rapid white slag making, improve the purity of molten steel, improve the thermal efficiency of the refining process, prevent secondary oxidation and air absorption of molten steel, improve the automation level of the refining slag-making process, and reduce the problem of slag judgment errors caused by human factors.

[0005] Specifically, the first aspect of the present application provides an automatic slag making method for a LF refining process, comprising the following steps:

[0006] Step 1: Collect slag-making related data of LF refining furnace and perform preprocessing;

[0007] The slag-forming agents for LF refining mainly include lime, calcium carbide, aluminum particles, and fluorite. The function of these slag-forming agents is to convert the oxidizing slag in the molten steel into reducing slag, thereby forming the so-called "white slag" to achieve the purpose of deep desulfurization and deoxidation. Specifically, lime is used to adjust the basicity of the slag and participate in desulfurization, calcium carbide is used for deoxidation to form a reducing atmosphere, which helps to create foamy slag for arc burial to improve the thermal efficiency of the electrode, aluminum particles are used for deep deoxidation, and the main function of fluorite as a slag-forming agent is to reduce the melting point of the slag and improve the fluidity of the slag.

[0008] Step 2: According to the historical refining data and process principles, build the LF refining slag model, and calculate the amount of lime added according to the refining related data of the steel grade. The formula is as follows:

[0009]

[0010] Where: W js is the amount of lime added during the refining process;

[0011] W j The amount of lime added to the base of the steel grade;

[0012] k1 is the slag reduction coefficient;

[0013] W z The total amount of slag added during the smelting process of this furnace is slag-breaking;

[0014] is the basicity of the steel grade slag;

[0015] Slag slag refers to the process of adding the remaining hot slag in the ladle to the next ladle to be refined during the LF furnace refining process to achieve recycling. This practice makes full use of the high basicity, low oxidation and low melting point characteristics of slag, thereby replacing part of the basic slag, reducing the consumption of raw and auxiliary materials such as lime for refining, shortening the refining slag making time, and improving the refining effect.

[0016] k2 is the influence coefficient of sulfur content;

[0017] %S is the difference between the sulfur content of molten steel and the target sulfur content;

[0018] The sulfur content of molten steel has a significant impact on the quality and performance of steel. Sulfur is a harmful element in steel, mainly in the form of FeS, which can cause the "hot brittleness" of steel, that is, it is easy to break at high temperatures, and also reduce the plasticity, welding performance and corrosion resistance of steel. Therefore, controlling the sulfur content in molten steel is an important link in steel production. Desulfurization is one of the key steps in the molten steel refining process.

[0019] Wgs is the weight of molten steel;

[0020] k3 is the calculation coefficient of converter slag;

[0021] W zx is the slag amount of the converter;

[0022] The amount of slag in the converter refers to the amount of slag that flows into the ladle with the molten steel during the converter tapping process. The amount of slag in the converter has an important influence on the refining effect and quality of the molten steel. The ideal amount of slag in the converter should be controlled at a low level to avoid adverse effects on the refining process.

[0023] W zs is the amount of lime added after the converter furnace;

[0024] Step 3: Calculate the amount of fluorite added based on the amount of lime added. The formula is as follows:

[0025] W jy =k4W js ;

[0026] Where: W jy is the amount of fluorite added during the refining process;

[0027] k4 is the fluorite calculation coefficient;

[0028] W js is the amount of lime added during the refining process;

[0029] Step 4: Calculate the amount of deoxidizer added based on the converter data and molten steel data, and automatically discharge the corresponding amount of lime, fluorite and deoxidizer based on the above calculation results;

[0030] Step 5: Use robots to take slag samples and identify the color grade and fluidity of slag based on image deep learning technology;

[0031] Step 6: Calculate the amount of deoxidizer to be added based on the color grade of the slag in the image recognition result and add it, and add lime and fluorite according to the fluidity;

[0032] Step 7: Repeat steps 5 and 6, and keep the white slag until the refining is completed.

[0033] Furthermore, the slag-making related data specifically include: the amount of lime added in the refining process, the basic lime added in the steel grade, the total amount of slag added in the smelting process of this furnace, the sulfur content of molten steel, the weight of molten steel, the amount of slag under the converter, the amount of lime added after the converter, the amount of ferrosilicon added to the converter, the silicon content in ferrosilicon, the amount of silicon-manganese alloy added to the converter, the silicon content in silicon-manganese, the silicon content sampled from the argon station, the amount of deoxidizer added to the converter, etc.

[0034] Furthermore, the step four specifically includes: calculating the oxygen content of the slag according to the converter data and the molten steel data, and then calculating the addition amount of calcium carbide and aluminum particles based on the oxygen content of the slag, and automatically feeding the corresponding amount of lime, fluorite and deoxidizer according to the calculation results.

[0035] Furthermore, the calculation formula for the amount of calcium carbide added is as follows:

[0036]

[0037] W CaC2 =k6W zx -k7W zt +k8W o ;

[0038] Where: W O is the oxygen content of steel slag;

[0039] k5 is the calculation coefficient of silicon recovery rate and oxygen content in steel slag;

[0040] W zg The amount of ferrosilicon added to the converter;

[0041] q1 is the silicon content in ferrosilicon;

[0042] W zm The amount of silicon-manganese alloy added to the converter;

[0043] q2 is the silicon content in silicon manganese;

[0044] W gs is the weight of molten steel;

[0045] W si sampling silicon content for the argon station;

[0046] W CaC2 is the amount of calcium carbide added during the refining process;

[0047] k6 is the calculation coefficient of converter slag and calcium carbide addition;

[0048] W zx is the slag amount of the converter;

[0049] k7 is the calculation coefficient of the amount of converter deoxidizer added and the amount of calcium carbide added;

[0050] W zt is the amount of converter deoxidizer added;

[0051] k8 is the calculation coefficient of oxygen content in steel slag and amount of calcium carbide added.

[0052] Furthermore, the calculation formula for the addition amount of the aluminum particles is as follows:

[0053] Wl =k9W zx -k 10 W zt +k 11 W o -k 12 W CaC2 ;

[0054] Where: W l is the amount of aluminum particles added during the refining process;

[0055] k9 is the calculation coefficient of the amount of slag and aluminum particles added to the converter;

[0056] W zx is the slag amount of the converter;

[0057] k 10 is the calculation coefficient of the amount of converter deoxidizer added and the amount of aluminum particles added;

[0058] W zt is the amount of converter deoxidizer added;

[0059] k 11 is the calculation coefficient of oxygen content in steel slag and amount of aluminum particles added;

[0060] W o is the oxygen content of steel slag;

[0061] k 12 is the calculation coefficient of the amount of calcium carbide added and the amount of aluminum particles added;

[0062] W CaC2 It is the amount of calcium carbide added during the refining process.

[0063] Furthermore, the color grade of the sticky residue specifically includes:

[0064] 1) Black and foamy: oxidized slag, indicating that the FeO+MnO content in the slag is >5%, and the color grade of sticky slag is 1;

[0065] 2) Brown and gray: It indicates that the content of FeO+MnO in the slag is between 2% and 4%, and deoxidizer needs to be added. The color grade of sticky slag is 2;

[0066] 3) Yellow: Deoxidation is in progress, add deoxidizer until white slag, the color grade of sticky slag is 3;

[0067] 4) White slag, off-white: It indicates that most of the oxides in the slag are reduced, the deoxidation is good, and the color grade of the sticky slag is 4;

[0068] 5) The slag is glassy and yellow-white: the final slag has good fluidity and good deoxidation, and the color grade of the sticky slag is 5.

[0069] Furthermore, the slag sampling by a robot is specifically performed by an industrial six-axis robot to perform automatic slag sampling.

[0070] Furthermore, the image deep learning technology is used to identify the color grade and fluidity of steel slag, specifically including: labeling the color grade and fluidity grade of past steel slag images, and dividing them into training sets and test sets, and training the convolutional neural network model through the labeled images until the output recognition result meets expectations.

[0071] Furthermore, the calculation formula for the amount of the deoxidizer added is as follows:

[0072] W db =k 13 D;

[0073] W lb =k 14 D;

[0074] Where: W db is the amount of calcium carbide added;

[0075] W lb is the amount of aluminum particles added;

[0076] k 13 To add the corresponding coefficient of calcium carbide and sticky slag color;

[0077] k 14 It is the color correspondence coefficient of the added aluminum particles and sticky slag;

[0078] D is the color grade of sticky residue.

[0079] Furthermore, the adding of lime and fluorite according to fluidity specifically includes:

[0080] In the slag identification results, the lower the fluidity of the slag, the more fluorite is added, and the greater the fluidity, the more lime is added. The fluidity of the slag is adjusted according to the identification results until it meets expectations.

[0081] In the second aspect, the present application also provides a computing device, which has the function of implementing the method described in the first aspect above. The beneficial effects can be found in the description of the first aspect, which will not be repeated here. The function can be implemented by hardware, or by executing the corresponding software implementation through hardware. The hardware or software includes one or more modules corresponding to the above functions. In one possible design, the structure of the device includes an acquisition module, a training module, and optionally, a construction module. These modules can implement the function of the training node in the method example of the first aspect above. Please refer to the detailed description in the method example for details, which will not be repeated here.

[0082] In the third aspect, the present application also provides a computing device, which is used to implement the functions of the method described in the first aspect above. The beneficial effects can be found in the description of the first aspect and will not be repeated here. The structure of the computing device includes a processor and a memory, and the memory is used to store instructions and / or data. The memory is coupled to the processor, and when the processor executes the program instructions stored in the memory, the function of the training node in the example of the first aspect above can be implemented. The structure of the computing device also includes a communication interface for communicating with other devices.

[0083] In a fourth aspect, the present application also provides a computer-readable storage medium, in which instructions are stored, and when the computer-readable storage medium is run on a computer, the computer executes the method in the above-mentioned first aspect and various possible designs of the first aspect.

[0084] In a fifth aspect, the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method in the above-mentioned first aspect and various possible designs of the first aspect.

[0085] In a sixth aspect, the present application also provides a computing chip, which is connected to a memory, and the chip is used to read and execute a software program stored in the memory, and to execute the methods in the above-mentioned first aspect and various possible implementation methods of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] In order to more clearly illustrate the embodiments of the present drawings or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present drawings. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0087] Figure 1 It is a flow chart of the steps of the present invention.

[0088] The purpose, features and advantages of this figure will be further described in conjunction with the embodiments with reference to the accompanying drawings. DETAILED DESCRIPTION

[0089] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0090] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0091] Unless otherwise specified, all embodiments and optional embodiments of the present application can be combined with each other to form a new technical solution.

[0092] Unless otherwise specified, all technical features and optional technical features of this application can be combined with each other to form a new technical solution.

[0093] If there is no special explanation, all steps of the present application can be performed sequentially or randomly, preferably sequentially. For example, the method includes steps (a) and (b), which means that the method may include steps (a) and (b) performed sequentially, or may include steps (b) and (a) performed sequentially. For example, the method may further include step (c), which means that step (c) may be added to the method in any order. For example, the method may include steps (a), (b) and (c), or may include steps (a), (c) and (b), or may include steps (c), (a) and (b), etc.

[0094] If there is no special explanation, the "include" and "comprising" mentioned in this application are open-ended or closed-ended. For example, the "include" and "comprising" may mean that other components not listed may also be included or only the listed components may be included or only the listed components may be included.

[0095] If not specifically stated, in this application, the term "or" is inclusive. For example, the phrase "A or B" means "A, B, or both A and B". More specifically, any of the following conditions satisfies the condition "A or B": A is true (or exists) and B is false (or does not exist); A is false (or does not exist) and B is true (or exists); or both A and B are true (or exist).

[0096] In order to better understand the solutions of the embodiments of the present application, some relevant terms and concepts that may be involved in the embodiments of the present application are first introduced below.

[0097] (1) Refining. Steel refining is a vital part of the steel production process. Its purpose is to remove impurities in pig iron, such as sulfur and phosphorus, and adjust the composition of steel to meet the needs of specific uses. The refining process usually includes two stages: primary refining and secondary refining. In the primary refining stage, pig iron is preliminarily treated by a converter or an electric arc furnace. The main task of this stage is to remove carbon and other impurities such as sulfur and phosphorus in the pig iron, and to perform alloying at the same time to obtain molten steel with basic properties. Secondary refining, also known as off-furnace refining, is carried out after primary refining. Off-furnace refining can be carried out under vacuum, inert gas or reducing atmosphere to further remove gases and harmful impurities.

[0098] (2) LF refining, or Ladle Furnace Refining, is an important secondary refining process in steel production. Its main purpose is to further treat the primary molten steel to meet the requirements of the continuous casting process and improve the quality and stability of the molten steel. LF refining has many advantages, including precise composition adjustment, reduction of non-metallic inclusions, and excellent temperature control capabilities.

[0099] (3) White slag is an alkaline slag, usually composed of CaO, SiO2, Al2O3 and other components, and is characterized by high alkalinity, low oxidation and good fluidity. The main function of white slag is to remove sulfur and oxygen in steel and adsorb inclusions in steel through reaction with the molten steel interface, thereby purifying the molten steel and improving the quality of steel. Making white slag is an important link in improving the quality of molten steel. The formation and control of white slag plays a key role in desulfurization, deoxidation and adsorption of inclusions in steel.

[0100] In this embodiment, Figure 1 As shown, an automatic slag making method for LF refining process comprises the following steps:

[0101] Step 1: Collect slag-making related data of LF refining furnace and perform preprocessing;

[0102] The slag-forming agents for LF refining mainly include lime, calcium carbide, aluminum particles, and fluorite. The function of these slag-forming agents is to convert the oxidizing slag in the molten steel into reducing slag, thereby forming the so-called "white slag" to achieve the purpose of deep desulfurization and deoxidation. Specifically, lime is used to adjust the basicity of the slag and participate in desulfurization, calcium carbide is used for deoxidation to form a reducing atmosphere, which helps to create foamy slag for arc burial to improve the thermal efficiency of the electrode, aluminum particles are used for deep deoxidation, and the main function of fluorite as a slag-forming agent is to reduce the melting point of the slag and improve the fluidity of the slag.

[0103] Step 2: According to the historical refining data and process principles, build the LF refining slag model, and calculate the amount of lime added according to the refining related data of the steel grade. The formula is as follows:

[0104]

[0105] In this embodiment, the basic lime addition amount is 400kg, the slag is 100kg, k1 is 0.2, the sulfur content entering the station is 0.025, the sulfur content of the standard brick is 0.03, then %S is 0.005, k2 is 10000, the slag amount of the converter is 100kg, k3 is 0.5, and 100kg of lime is added after the converter. Then 380kg of lime needs to be added to the first batch of this steel grade.

[0106] Slag slag refers to the process of adding the remaining hot slag in the ladle to the next ladle to be refined during the LF furnace refining process to achieve recycling. This practice makes full use of the high basicity, low oxidation and low melting point characteristics of slag, thereby replacing part of the basic slag, reducing the consumption of raw and auxiliary materials such as lime for refining, shortening the refining slag making time, and improving the refining effect.

[0107] The sulfur content of molten steel has a significant impact on the quality and performance of steel. Sulfur is a harmful element in steel, mainly in the form of FeS, which can cause the "hot brittleness" of steel, that is, it is easy to break at high temperatures, and also reduce the plasticity, welding performance and corrosion resistance of steel. Therefore, controlling the sulfur content in molten steel is an important link in steel production. Desulfurization is one of the key steps in the molten steel refining process.

[0108] The amount of slag in the converter refers to the amount of slag that flows into the ladle with the molten steel during the converter tapping process. The amount of slag in the converter has an important influence on the refining effect and quality of the molten steel. The ideal amount of slag in the converter should be controlled at a low level to avoid adverse effects on the refining process.

[0109] Step 3: Calculate the amount of fluorite added based on the amount of lime added. The formula is as follows:

[0110] W jy =k4W js ;

[0111] In this embodiment, k4 is 0.3, and the first batch of fluorite added is calculated based on the first batch of lime added, which is 114 kg.

[0112] Step 4: Calculate the amount of deoxidizer added based on the converter data and molten steel data, and automatically discharge the corresponding amount of lime, fluorite and deoxidizer based on the above calculation results;

[0113] Step 5: Use robots to take slag samples and identify the color grade and fluidity of slag based on image deep learning technology;

[0114] Step 6: Calculate the amount of deoxidizer to be added based on the color grade of the slag in the image recognition result and add it, and add lime and fluorite according to the fluidity;

[0115] Step 7: Repeat steps 5 and 6, and keep the white slag until the refining is completed.

[0116] Furthermore, the slag-making related data specifically include: the amount of lime added in the refining process, the basic lime added in the steel grade, the total amount of slag added in the smelting process of this furnace, the sulfur content of molten steel, the weight of molten steel, the amount of slag under the converter, the amount of lime added after the converter, the amount of ferrosilicon added to the converter, the silicon content in ferrosilicon, the amount of silicon-manganese alloy added to the converter, the silicon content in silicon-manganese, the silicon content sampled at the argon station, the amount of deoxidizer added to the converter, etc.

[0117] Furthermore, step four specifically includes: calculating the oxygen content of the slag according to the converter data and the molten steel data, and then calculating the amount of calcium carbide and aluminum particles to be added based on the oxygen content of the slag, and automatically feeding the corresponding amount of lime, fluorite and deoxidizer according to the calculation results.

[0118] Furthermore, the calculation formula for the amount of calcium carbide added is as follows:

[0119]

[0120] W CaC2 =k6W zx -k7W zt +k8W o ;

[0121] In this embodiment, a total of 700 kg of deoxidizer (ferrosilicon, silicon manganese, etc.) is added to the converter, the slag amount is 100 kg, k6 is 0.1, k7 is 0.15, and k8 is 6.25*10 5 , then you need to add 140kg of calcium carbide;

[0122] Furthermore, the calculation formula for the addition amount of aluminum particles is as follows:

[0123] W l =k9W zx -k 10 W zt +k 11 W o -k 12 W CaC2 ;

[0124] In this embodiment, k9 is 0.1, k10 is 0.01, and k11 is 2.5*10 5 , k12 is 0.1, then 41kg of aluminum particles need to be added.

[0125] Furthermore, the color grade of sticky residue includes:

[0126] 1) Black and foamy: oxidized slag, indicating that the FeO+MnO content in the slag is >5%, and the color grade of sticky slag is 1;

[0127] 2) Brown and gray: It indicates that the content of FeO+MnO in the slag is between 2% and 4%, and deoxidizer needs to be added. The color grade of sticky slag is 2;

[0128] 3) Yellow: Deoxidation is in progress, add deoxidizer until white slag, the color grade of sticky slag is 3;

[0129] 4) White slag, off-white: It indicates that most of the oxides in the slag are reduced, the deoxidation is good, and the color grade of the sticky slag is 4;

[0130] 5) The slag is glassy and yellow-white: the final slag has good fluidity and good deoxidation, and the color grade of the sticky slag is 5.

[0131] Furthermore, the slag sampling is performed by a robot, specifically, automatic slag sampling is performed by an industrial six-axis robot.

[0132] Furthermore, the color grade and fluidity of steel slag are identified based on image deep learning technology, specifically including: annotating the color grade and fluidity grade of past steel slag images, and dividing them into training sets and test sets, and training the convolutional neural network model with the annotated images until the output recognition results meet expectations.

[0133] Furthermore, the calculation formula for the amount of deoxidizer added is as follows:

[0134] W db =k 13 D;

[0135] W lb =k 14 D;

[0136] In this embodiment, k13 is 15, k14 is 6, and the color of the sticky residue is black, that is, the color grade is 5, then 30 kg of aluminum particles need to be added.

[0137] Furthermore, lime and fluorite are added according to fluidity, specifically including:

[0138] In the slag identification results, the lower the fluidity of the slag, the more fluorite is added, and the greater the fluidity, the more lime is added. The fluidity of the slag is adjusted according to the identification results until it meets expectations.

[0139] It should be noted that the present application is not limited to the above-mentioned embodiments. The above-mentioned embodiments are only examples, and the embodiments having the same structure as the technical idea and exerting the same effect within the scope of the technical solution of the present application are all included in the technical scope of the present application. In addition, without departing from the scope of the main purpose of the present application, various modifications that can be thought of by those skilled in the art to the embodiments and other methods of combining some of the constituent elements in the embodiments are also included in the scope of the present application.

Claims

1. An automatic slag making method for LF refining process, characterized in that: The following steps are involved: Step 1: Collect slag-making related data of LF refining furnace and perform preprocessing; Step 2: According to the historical refining data and process principles, build the LF refining slag model, and calculate the amount of lime added according to the refining related data of the steel grade. The formula is as follows: Where: W js is the amount of lime added during the refining process; W j The amount of lime added to the base of the steel grade; k1 is the slag reduction coefficient; W z The total amount of slag added in the smelting process of this furnace is slag-breaking; The basicity of the steel grade slag; k2 is the influence coefficient of sulfur content; %S is the difference between the sulfur content of molten steel and the target sulfur content; W gs is the weight of molten steel; k3 is the calculation coefficient of converter slag; W zx is the slag amount of the converter; W zs is the amount of lime added after the converter furnace; Step 3: Calculate the amount of fluorite added based on the amount of lime added. The formula is as follows: IN jy =k4W js ; Where: W jy is the amount of fluorite added during the refining process; k4 is the fluorite calculation coefficient; W js is the amount of lime added during the refining process; Step 4: Calculate the amount of deoxidizer added based on the converter data and molten steel data, and automatically discharge the corresponding amount of lime, fluorite and deoxidizer based on the above calculation results; Step 5: Use robots to take slag samples and identify the color grade and fluidity of slag based on image deep learning technology; Step 6: Calculate the amount of deoxidizer to be added based on the color grade of the slag in the image recognition result and add it, and add lime and fluorite according to the fluidity; Step 7: Repeat steps 5 and 6, and keep the white slag until the refining is completed.

2. The automatic slag making method in the LF refining process according to claim 1, characterized in that: The slag-making related data specifically include: the amount of lime added in the refining process, the basic lime added in the steel grade, the total amount of slag added in the smelting process of this furnace, the sulfur content of molten steel, the weight of molten steel, the amount of slag under the converter, the amount of lime added after the converter, the amount of ferrosilicon added to the converter, the silicon content in ferrosilicon, the amount of silicon-manganese alloy added to the converter, the silicon content in silicon-manganese, the silicon content sampled from the argon station, and the amount of deoxidizer added to the converter.

3. The automatic slag making method in LF refining process according to claim 1, characterized in that: The step four specifically includes: calculating the oxygen content of the slag according to the converter data and the molten steel data, then calculating the amount of calcium carbide and aluminum particles to be added based on the oxygen content of the slag, and automatically feeding the corresponding amount of lime, fluorite and deoxidizer according to the calculation results.

4. The automatic slag making method in LF refining process according to claim 3, characterized in that: The calculation formula of the addition amount of the calcium carbide is as follows: IN CaC2 =k6W zx -k7W zt +k8W o ; Where: W o is the oxygen content of steel slag; k5 is the calculation coefficient of silicon recovery rate and oxygen content in steel slag; W zg The amount of ferrosilicon added to the converter; q1 is the silicon content in ferrosilicon; W zm The amount of silicon-manganese alloy added to the converter; q2 is the silicon content in silicon manganese; W gs is the weight of molten steel; W si sampling silicon content for the argon station; W CaC2 is the amount of calcium carbide added during the refining process; k6 is the calculation coefficient of converter slag and calcium carbide addition; W zx is the slag amount of the converter; k7 is the calculation coefficient of the amount of converter deoxidizer added and the amount of calcium carbide added; W zt is the amount of converter deoxidizer added; k8 is the calculation coefficient of oxygen content in steel slag and amount of calcium carbide added.

5. The automatic slag making method in LF refining process according to claim 3, characterized in that: The calculation formula for the addition amount of the aluminum particles is as follows: IN l =k9W zx -k 10 IN zt +k 11 IN o -k 12 IN CaC2 ; Where: W l is the amount of aluminum particles added during the refining process; k9 is the calculation coefficient of the amount of slag and aluminum particles added to the converter; W zx is the slag amount of the converter; k 10 is the calculation coefficient of the amount of converter deoxidizer added and the amount of aluminum particles added; W zt is the amount of converter deoxidizer added; k 11 is the calculation coefficient of oxygen content in steel slag and amount of aluminum particles added; W o is the oxygen content of steel slag; k 12 is the calculation coefficient of the amount of calcium carbide added and the amount of aluminum particles added; W CaC2 It is the amount of calcium carbide added during the refining process.

6. The automatic slag making method in LF refining process according to claim 1, characterized in that: The sticky residue color grades specifically include: 1) Black and foamy: oxidized slag, indicating that the FeO+MnO content in the slag is >5%, and the color grade of sticky slag is 1; 2) Brown and gray: It indicates that the content of FeO+MnO in the slag is between 2% and 4%, and deoxidizer needs to be added. The color grade of sticky slag is 2; 3) Yellow: Deoxidation is in progress, add deoxidizer until white slag, the color grade of sticky slag is 3; 4) White slag, off-white: It indicates that most of the oxides in the slag are reduced, the deoxidation is good, and the color grade of the sticky slag is 4; 5) The slag is glassy and yellow-white: the final slag has good fluidity and good deoxidation, and the color grade of the sticky slag is 5.

7. The automatic slag making method in LF refining process according to claim 1, characterized in that: The slag sampling by a robot is specifically to perform automatic slag sampling by an industrial six-axis robot.

8. The automatic slag making method in the LF refining process according to claim 1, characterized in that: The image deep learning technology is used to identify the color grade and fluidity of steel slag, specifically including: labeling the color grade and fluidity grade of past steel slag images, and dividing them into training sets and test sets, and training the convolutional neural network model through the labeled images until the output recognition result meets expectations.

9. The automatic slag making method in LF refining process according to claim 1, characterized in that: The calculation formula for the additional amount of the deoxidizer is as follows: W db =k 13 D; W lb =k 14 D; Where: W db is the amount of calcium carbide added; W lb is the amount of aluminum particles added; k 13 To add the corresponding coefficient of calcium carbide and sticky slag color; k 14 It is the color correspondence coefficient of the added aluminum particles and sticky slag; D is the color grade of sticky residue.

10. The automatic slag making method in LF refining process according to claim 1, characterized in that: The method of adding lime and fluorite according to fluidity specifically includes: In the slag sticking identification results, the smaller the fluidity of the slag, the larger the amount of fluorite added, and the larger the fluidity, the larger the amount of lime added.

Images