A full-process intelligent refining system applied to LF refining furnace

Abstract

The present application provides a full-process intelligent refining system applied to an LF refining furnace, which relates to the field of iron and steel metallurgy and includes: a slag-making control module that calculates the addition amount of slag-making agent; a temperature prediction module that predicts and controls the molten steel temperature in real time; a blowing argon control module that establishes a relationship model between the exposed area of molten steel and the bottom blowing argon gas flow rate; a wire feeding prediction module that calculates the feeding amounts of aluminum wire and calcium wire; an alloy calculation module that automatically controls the alloy addition amount; a machine-assisted module that collects data and performs sampling and slag sticking work; a main control module that is used to control the system operation; and a server for data storage and interaction. The present application uses technologies such as statistical methods and mechanism calculations to establish mechanism models for each refining process, predict and automatically control the refining process, effectively improving the hit rate of alloy components and the temperature compliance rate, and at the same time reducing alloy consumption and power consumption.

Description

Technical Field

[0001] This application relates to the technical field of iron and steel metallurgy, and particularly relates to a full-process intelligent refining system applied to an LF refining furnace. Background Art

[0002] The refining process plays a crucial role in iron and steel smelting. Through refining, non-metallic inclusions and gas inclusions in steel can be effectively removed, and the contents of harmful elements such as oxygen content, sulfur content, and nitrogen content in steel can be reduced, thereby improving the quality and reliability of steel. In addition, the refining process can also improve the purity of molten steel, reduce the generation of slag, lower production costs, and improve production efficiency. Therefore, the refining process is an indispensable part of the iron and steel smelting process. The refining process usually includes two stages: primary refining and secondary refining. Primary refining is mainly carried out in blast furnaces and converters. The blast furnace is used to reduce iron ore into liquid pig iron, while the converter removes impurities in pig iron, such as elements like carbon, silicon, and phosphorus, through oxidation reactions and further adjusts the composition of steel. Secondary refining, also known as secondary refining, is usually carried out in equipment such as ladle refining furnaces and vacuum degassing furnaces. The main task of this stage is to further remove harmful elements such as oxygen, sulfur, and nitrogen in steel, and improve the purity and mechanical properties of steel. LF refining, that is, refining outside the furnace, is an important secondary refining process in iron and steel production. It uses white slag for desulfurization and deoxidation treatment of molten steel to produce ultra-low sulfur steel and low-oxygen steel. Its main purpose is to further process the primary molten steel to meet the requirements of the continuous casting process and improve the quality and stability of molten steel.

[0003] There are many problems in the traditional LF refining process, such as high manual labor intensity, high risk coefficient, chaotic smelting process and standards, large control fluctuations, high material consumption and energy consumption, high process cost, poor product quality stability, etc.

[0004] The existing LF refining mainly relies on manual subjective operations to complete. There is a lack of relatively unified standards for operations such as slag material ratio, alloy ratio, argon blowing intensity, temperature control, and wire feeding length. Most operations are manually controlled by workers in front of the furnace or in the control room, with low automation and informatization levels. This easily causes problems such as increased power consumption, material waste, and alloy composition exceeding the requirements of the steel grade. Moreover, the level of intelligence and automation is low, the manual labor intensity is high, which easily results in low control accuracy, long processing cycle, and energy waste, and is not conducive to the stability of steel quality and cost reduction.

[0005] At present, most of the LF process control and decision-making models are single-function or combined with partial functions, and the overall integrated application is less. Since the LF refining process involves characteristics such as multi-variables, non-linearity, and strong coupling, and the working environment is harsh with strong random interference, this makes the prediction of the control model distorted, the process standardization difficult, the on-site operation random, and affects quality, cost control, and the development of secondary models. In addition, the existing process control systems do not have the capabilities of analysis, prediction, and automatic control, and manual operation is required in high-temperature and dangerous areas, which all limit the development of intelligence. Summary of the Invention

[0006] This application is made in view of the above problems. Its purpose is to provide a full-process intelligent refining system applied to an LF refining furnace, which formulates relatively standard refining processes and feeding rules, ensures the standardization and consistency of refining operations, uses technologies such as statistical methods and mechanism calculations to establish mechanism models for each refining process, predicts and automatically controls the refining process, effectively improves the hit rate of alloy components and the temperature compliance rate, reduces alloy consumption and power consumption at the same time, reduces labor input, and realizes the intelligent control of the entire refining process.

[0007] Specifically, the first aspect of this application provides a full-process intelligent refining system applied to an LF refining furnace, including:

[0008] A slag-making control module, which is used to calculate the addition amount of slag-making agents in the refining process according to the mechanism model, and is electrically connected to the main control module and the machine assistance module;

[0009] The slag-making agents for LF refining include but are not limited to lime, calcium carbide, aluminum pellets, and fluorite, and can also be materials such as white lime and bauxite that can bring about desulfurization or deoxidation effects. The role of these slag-making agents is to convert the oxidizing slag in the molten steel into a 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 alkalinity of the slag, calcium carbide is used for desulfurization, and aluminum pellets are used to further reduce the oxygen content in the slag. The main role of fluorite as a slag-making agent is to lower the melting point of the slag and improve the fluidity of the slag.

[0010] A temperature prediction module, which is used to preprocess temperature data, and perform real-time prediction and control of the molten steel temperature through a prediction model, and is electrically connected to the main control module and the machine assistance module;

[0011] The preprocessing of temperature data specifically includes data cleaning, missing value processing, and outlier processing to ensure the accuracy and integrity of the data. The purpose of data cleaning is to convert the original data into a more structured and easy-to-analyze usable format.

[0012] The argon blowing control module is used to establish a relationship model between the exposed area of molten steel and the bottom argon blowing flow rate based on experimental data and historical process experience, so as to achieve automatic argon blowing, and is electrically connected to the main control module and the machine assistance module;

[0013] The wire feeding prediction module is used to calculate the feeding amounts of aluminum wire and calcium wire according to the steel grade and the composition of molten steel, verify and optimize the feeding amounts, and is electrically connected to the main control module and the machine assistance module;

[0014] Aluminum wire is mainly used for deoxidation during the LF refining process. By adding aluminum wire to the molten steel, the oxygen content in the steel can be effectively reduced, thereby improving the purity of the molten steel. It can also be used for alloying to adjust the composition in the molten steel. The addition of aluminum wire helps to promote the floating of high-melting-point alumina inclusions, thereby reducing the number and area fraction of these inclusions in the billet.

[0015] The addition of calcium wire is mainly used to change the morphology of alumina inclusions in the molten steel, converting them into low-melting-point calcium aluminate inclusions, thereby improving the purity and fluidity of the molten steel. Calcium treatment can effectively reduce the melting point of inclusions and ensure the stability of the continuous casting operation. The feeding speed of calcium wire and the temperature of the molten steel have a significant impact on the recovery rate of calcium. Appropriate wire feeding speed and higher molten steel temperature can improve the recovery rate of calcium.

[0016] The alloy calculation module is used to establish an alloy calculation model according to the process parameters and the in-furnace conditions of each heat, realize the automatic control of the alloy addition amount, and is electrically connected to the main control module and the machine assistance module;

[0017] The machine assistance module is used to collect the data related to in-furnace refining in real time, send the collected data to the slag making control module, the temperature prediction module, the wire feeding prediction module, and the alloy calculation module as needed, and perform sampling and slag sticking work through an industrial robot;

[0018] In the present invention, industrial six-axis robots are used for temperature measurement, sampling and slag sticking work. These robots have high-precision motion control capabilities, can adapt to high-temperature environments, and support rapid fixture replacement and anti-collision detection functions.

[0019] The main control module is electrically connected to all other modules and the server respectively, and is used to control the system operation and perform data interaction with the server;

[0020] The server is electrically connected to the main control module and is used for data storage and interaction.

[0021] Further, the calculation formulas for the addition amounts of each slag making agent in the slag making control module are as follows:

[0022] ;

[0023] ;

[0024] ;

[0025] ;

[0026] ;

[0027] ; ;

[0028] Wherein: is the amount of lime added during the refining process;

[0029] is the basic lime addition amount for the steel grade;

[0030] is the total amount of slag materials added during the smelting process of this heat of slag folding;

[0031] is the basicity of slag folding for the steel grade;

[0032] is the difference between the sulfur content in the molten steel and the target sulfur content;

[0033] is the weight of the molten steel;

[0034] is the amount of slag flowing from the converter;

[0035] is the amount of lime added after the converter;

[0036] is the amount of fluorite added during the refining process;

[0037] is the oxygen content in the steel slag;

[0038] is the amount of ferrosilicon added to the converter;

[0039] is the silicon content in the ferrosilicon;

[0040] is the amount of silicomanganese alloy added to the converter;

[0041] is the silicon content in the silicomanganese;

[0042] is the silicon content sampled at the argon station;

[0043] is the amount of calcium carbide added during the refining process;

[0044] is the addition amount of converter deoxidizer;

[0045] is the addition amount of aluminum pellets during refining;

[0046] is the additional amount of calcium carbide;

[0047] is the additional amount of aluminum pellets;

[0048] is the slag adhesion color grade;

[0049] is the calculation parameter obtained by linear programming based on the actual refining data on site.

[0050] (slag conversion coefficient), with a value range of 0.05 - 0.3;

[0051] (sulfur content influence coefficient), with a value range of 3000 - 20000;

[0052] (converter slagging calculation coefficient), with a value range of 0.4 - 0.6;

[0053] (fluorite calculation coefficient), with a value range of 0.1 - 0.5;

[0054] (silicon recovery rate and steel slag oxygen element content calculation coefficient), with a value range of ;

[0055] (converter slag and calcium carbide addition amount calculation coefficient), with a value range of 0.08 - 0.12;

[0056] (converter deoxidizer addition amount and calcium carbide addition amount calculation coefficient), with a value range of 0.12 - 0.16;

[0057] (steel slag oxygen element content and calcium carbide addition amount calculation coefficient), with a value range of ;

[0058] (converter slag and aluminum pellet addition amount calculation coefficient), with a value range of 0.07 - 0.14;

[0059] (converter deoxidizer addition amount and aluminum pellet addition amount calculation coefficient), with a value range of 0.01 - 0.02;

[0060] (Calculation coefficient of oxygen element content in steel slag and addition amount of aluminum particles), the value range is ;

[0061] (Calculation coefficient of addition amount of calcium carbide and addition amount of aluminum particles), the value range is 0.08 - 0.12;

[0062] (Corresponding coefficient of additional calcium carbide and slag adhesion color), the value range is 12 - 18;

[0063] (Corresponding coefficient of additional aluminum particles and slag adhesion color), the value range is 4 - 8;

[0064] Folding slag refers to the process of adding the remaining hot steel slag in the ladle back into the ladle to be refined in the next batch during the refining process in the LF furnace, so as to achieve recycling. This practice makes full use of the high alkalinity, low oxidability and low melting point characteristics of the steel slag, thereby replacing part of the basic slag materials, reducing the consumption of raw and auxiliary materials such as quicklime for refining, shortening the refining slag-making time, and improving the refining effect.

[0065] Furthermore, the slag adhesion color grades specifically include:

[0066] 1) Black, foaming: Oxidized slag, indicating that the content of FeO + MnO in the slag > 5%, and the value of the slag adhesion color grade is 1;

[0067] 2) Brown, gray: Indicating that the content of FeO + MnO in the slag is 2% - 4%, and a deoxidizer needs to be added, and the value of the slag adhesion color grade is 2;

[0068] 3) Yellow: Deoxidation is in progress, and a deoxidizer is added until white slag, and the value of the slag adhesion color grade is 3;

[0069] 4) White slag, off-white: Indicating that most of the oxides in the slag have been reduced and the deoxidation is good, and the value of the slag adhesion color grade is 4;

[0070] 5) The slag is glassy, yellowish-white: The final slag has good fluidity and good deoxidation, and the value of the slag adhesion color grade is 5.

[0071] Furthermore, the real-time temperature prediction formula of the temperature prediction module is:

[0072] ;

[0073] Where: is the predicted temperature of the molten steel;

[0074] is the measured temperature of the molten steel;

[0075] is the heating rate of molten steel at different gears;

[0076] is the temperature drop of the furnace lining;

[0077] is the temperature drop of the furnace charge;

[0078] is the temperature drop during argon blowing;

[0079] is the temperature drop of the flue gas;

[0080] is the time interval.

[0081] The temperature drop of the furnace lining is the heat absorbed by the furnace lining, the temperature drop of the furnace charge is the heat absorbed by adding alloys and slag materials, the temperature drop during argon blowing is the heat loss during argon blowing, and the temperature drop of the flue gas is the heat carried away by dust and flue gas.

[0082] Furthermore, the argon blowing control module specifically includes:

[0083] According to experimental data and historical process experience, establish a relationship model between the exposed area of molten steel and the bottom argon blowing flow rate. Then, based on the real-time exposed area data of molten steel provided by the image processing unit, calculate the required argon flow rate from the relationship model. Finally, automatically adjust the argon flow rate according to the deviation between the real-time monitored exposed area of molten steel and the target value.

[0084] Furthermore, the calculation formulas for the feeding amounts of aluminum wire and calcium wire in the wire feeding prediction module are as follows:

[0085] ;

[0086] ;

[0087] Where: is the length of aluminum wire to be added;

[0088] is the target aluminum content of the steel grade;

[0089] is the actual aluminum content of the steel grade;

[0090] is the amount of aluminum adsorbed by oxidation;

[0091] is the unit weight of the aluminum wire;

[0092] is the percentage of aluminum in the aluminum wire;

[0093] is the aluminum wire recovery rate;

[0094] is the weight of molten steel;

[0095] is the length of calcium wire to be added;

[0096] in the molten steel content;

[0097] is the unit weight of calcium wire;

[0098] is the calcium percentage of calcium wire;

[0099] is the calcium wire recovery rate;

[0100] is the calculation parameter obtained by linear programming according to the actual refining data on site.

[0101] Furthermore, in the case where the feeding alloy used for a certain element is unique, the single alloy dosage model of the alloy calculation module is as follows:

[0102] ;

[0103] Where: is the addition amount of the i-th alloy;

[0104] is the mass of molten steel;

[0105] is the final mass fraction of the required element in the molten steel;

[0106] is the initial mass fraction of the required element in the molten steel;

[0107] is the recovery rate of the required element in the i-th alloy;

[0108] is the mass fraction of the required element in the i-th alloy.

[0109] Furthermore, the machine assistance module specifically includes:

[0110] The relevant refining data in the furnace is collected in real time through sensors and system equipment. Through an industrial six-axis robot, according to the requirements of temperature measurement, sampling, and slag sticking, the system lance automatically installs a probe, inserts the probe into the molten steel in the ladle for temperature measurement and sampling, accurately locates the insertion depth of the probe into the molten steel by detecting the signal of the ladle slag liquid level height position, and places the sample in a fixed position after sampling.

[0111] Furthermore, the data related to in-furnace refining specifically includes: steel grade, molten steel surface image, molten steel weight, total amount of slag materials added during the smelting process of the slag-splitting furnace charge, basicity of the steel grade slag-splitting, sulfur content of the molten steel, amount of slag flowing from the converter, amount of ferrosilicon added to the converter, amount of silicomanganese alloy added to the converter, amount of deoxidizer added to the converter, actual aluminum content of the steel grade, and alumina content in the molten steel.

[0112] Furthermore, the specific refining process of the full-process intelligent refining system is as follows:

[0113] The ladle car arrives - the furnace cover descends - the dust removal valve opens - strong blowing to break the slag - the robot measures the temperature - the slag materials and alloys are automatically calculated and sent down - medium blowing and stirring - automatically calculating and feeding aluminum wire - the lower electrode heats - the electrode is lifted to stop heating - the robot measures the temperature, samples, and dips the slag - strong blowing for desulfurization - automatically feeding materials to supplement the alloy - secondary aluminum supplementation - the robot measures the temperature, samples, and dips the slag - the lower electrode heats - the robot measures the temperature, samples, and dips the slag - the electrode is lifted to stop heating - automatic soft blowing - automatic calcium feeding - secondary soft blowing - the dust removal valve closes - the argon gas shuts off - the ladle leaves the station.

[0114] In this process, strong blowing to break the slag, medium blowing and stirring, strong blowing for desulfurization, automatic soft blowing, and secondary soft blowing are controlled by the argon blowing control module; the robot measuring the temperature, sampling, and dipping the slag is controlled by the machine assistance module; the automatic calculation and sending down of the alloy, and automatically feeding materials to supplement the alloy are controlled by the alloy calculation module; automatically calculating and feeding aluminum wire, secondary aluminum supplementation, and automatic calcium feeding are controlled by the wire feeding prediction model; the lower electrode heating and lifting the electrode to stop heating are controlled by the temperature prediction model; the automatic calculation and sending down of the slag materials are controlled by the slag-making control model.

[0115] The flow rate and intensity of bottom blowing argon gas are divided into three modes: soft blowing, medium blowing, and strong blowing. The flow rate of soft blowing argon gas is relatively low, usually 80 L / min, mainly used to promote the floating and removal of non-metallic impurities in the molten steel, thereby improving the cleanliness of the molten steel. During the LF refining process, the soft blowing stage can effectively remove inclusions larger than 10 μm, significantly reducing the average size of the inclusions. In addition, soft blowing can also promote the floating of inclusions through weak stirring, reducing the floating time.

[0116] Medium blowing: The flow rate of medium blowing argon gas is moderate, usually 200 L / min, mainly used in the stable heating stage to maintain the uniformity of the molten steel temperature and composition through medium-intensity stirring. In the automatic mode of LF refining, the medium blowing stage usually lasts for 3 - 5 minutes to ensure the uniformity of the molten steel temperature and composition.

[0117] Strong blowing: The flow rate of strong blowing argon gas is relatively high, usually 500 L / min, mainly used in the slag melting and desulfurization stage to promote the removal of sulfur and other harmful elements in the molten steel through high-intensity stirring. In the automatic mode of LF refining, the strong blowing stage also lasts for 3 - 5 minutes to ensure that the sulfur content in the molten steel is reduced to the target level.

[0118] In a second aspect, the present application further provides a computing device that has the function of implementing the method described in the first aspect above. The beneficial effects can be referred to the description of the first aspect and will not be elaborated here. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions. In a possible design, the structure of the device includes an acquisition module and a training module. Optionally, it may further include a construction module. These modules can implement the functions of training nodes in the method example of the first aspect above. For specific details, refer to the detailed description in the method example and will not be elaborated here.

[0119] In a third aspect, the present application further provides a computing device that is used to implement the function of the method described in the first aspect above. The beneficial effects can be referred to the description of the first aspect and will not be elaborated here. The structure of the computing device includes a processor and a memory. The memory is used to store instructions and / or data. The memory is coupled to the processor. When the processor executes the program instructions stored in the memory, it can implement the functions of training nodes in the example of the first aspect above. The structure of the computing device further includes a communication interface for communicating with other devices.

[0120] In a fourth aspect, the present application further provides a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When it runs on a computer, it causes the computer to execute the methods in the first aspect and all possible designs of the first aspect.

[0121] In a fifth aspect, the present application further provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the methods in the first aspect and all possible designs of the first aspect.

[0122] In a sixth aspect, the present application further provides a computing chip. The chip is connected to a memory. The chip is used to read and execute the software program stored in the memory and execute the methods in the first aspect and all possible implementation manners of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0123] In order to more clearly illustrate the technical solutions in the embodiments of the present drawings or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present drawings. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on the structures shown in these drawings.

[0124] Figure 1 It is a schematic structural diagram of the present invention;

[0125] The realization, functional features and advantages of this accompanying drawing will be further described in conjunction with embodiments with reference to the accompanying drawings. Detailed implementation manners

[0126] In order to make the objectives, technical solutions and advantages of this application more clear and understandable, the following describes and explains this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application. Based on the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0127] Obviously, the accompanying drawings in the following description are only some examples or embodiments of this application. For those of ordinary skill in the art, without creative efforts, this application can also be applied to other similar scenarios based on these drawings. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in this application, some designs, manufacturing or production changes made based on the technical content disclosed in this application are only conventional technical means and should not be understood as the content disclosed in this application being insufficient.

[0128] If there is no special indication, all implementation manners and optional implementation manners of this application can be combined with each other to form a new technical solution.

[0129] If there is no special indication, all technical features and optional technical features of this application can be combined with each other to form a new technical solution.

[0130] If there is no special indication, all steps of this application can be carried out in sequence or randomly, and preferably in sequence. For example, the method includes steps (a) and (b), indicating that the method may include steps (a) and (b) carried out in sequence, or may also include steps (b) and (a) carried out in sequence. For example, it is mentioned that the method may further include step (c), indicating that step (c) can be added to the method in any order. For example, the method may include steps (a), (b) and (c), or may also include steps (a), (c) and (b), or may also include steps (c), (a) and (b), etc.

[0131] If there is no special indication, the "including" and "comprising" mentioned in this application mean open-ended or may also be closed-ended. For example, the "including" and "comprising" may mean that other components not listed may also be included or comprised, or may only include or comprise the listed components.

[0132] Unless otherwise specified, the term "or" is inclusive in this application. 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).

[0133] To better understand the solutions of the embodiments of this application, some related terms and concepts that may be involved in the embodiments of this application will be introduced below.

[0134] (1) Refining. The refining of steel is a crucial step in the steel production process. Its purpose is to remove impurities in pig iron, such as sulfur, phosphorus, etc., and adjust the composition of steel to meet the requirements of specific applications. The refining process usually includes two stages: primary refining and secondary refining. In the primary refining stage, pig iron is preliminarily processed through a converter or an electric arc furnace. The main task of this stage is to remove carbon and other impurities in pig iron, such as sulfur and phosphorus, and at the same time carry out alloying to obtain molten steel with basic properties. Secondary refining, also known as secondary refining outside the furnace, is carried out after primary refining. Secondary refining outside the furnace can be carried out under vacuum, inert gas or reducing atmosphere to further remove gases and harmful impurities.

[0135] (2) LF refining, that is, ladle furnace refining, is an important secondary refining process in steel production. Its main purpose is to further process the molten steel from primary refining 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, excellent temperature control ability, etc.

[0136] The basic principle of LF refining is to use basic synthetic slag, submerged arc heating and argon stirring to refine the molten steel under a reducing atmosphere. This process can effectively reduce the oxygen and sulfur content in steel, and adjust the composition and temperature of the molten steel by adding alloys and slag materials.

[0137] (3) LF refining furnace, that is, ladle refining furnace, is an important secondary refining equipment widely used in steel production. It realizes the refining effects of deoxidation, desulfurization, alloying and heating up of molten steel through means such as arc heating, reducing atmosphere, making white slag for refining and gas stirring, ensures the precise composition and uniform temperature of molten steel, effectively purifies molten steel, coordinates the steelmaking and continuous casting processes, and ensures multi-hearth continuous casting.

[0138] In this embodiment, as Figure 1 shown, a full-process intelligent refining system applied to an LF refining furnace includes:

[0139] The slag-making control module is used to calculate the addition amount of slag-making agents during the refining process according to the mechanism model and is electrically connected to the main control module and the machine assistance module;

[0140] The slag-making agents for LF refining mainly include lime, calcium carbide, aluminum pellets, and fluorite. The function of these slag-making agents is to convert the oxidizing slag in the molten steel into a 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, calcium carbide is used for desulfurization, aluminum pellets are used to further reduce the oxygen content in the slag, and the main function of fluorite as a slag-making agent is to lower the melting point of the slag and improve the fluidity of the slag.

[0141] The temperature prediction module is used to preprocess the temperature data, and perform real-time prediction and control of the molten steel temperature through the prediction model, and is electrically connected to the main control module and the machine assistance module;

[0142] The preprocessing of the temperature data specifically includes data cleaning, missing value processing, and outlier processing to ensure the accuracy and integrity of the data. The purpose of data cleaning is to convert the original data into a more structured and easy-to-analyze usable format.

[0143] The argon blowing control module is used to establish a relationship model between the exposed area of the molten steel and the bottom argon blowing flow rate based on experimental data and historical process experience to achieve automatic argon blowing, and is electrically connected to the main control module and the machine assistance module;

[0144] The wire feeding prediction module is used to calculate the feeding amounts of aluminum wire and calcium wire according to the steel grade and the composition of the molten steel, and verify and optimize the feeding amounts, and is electrically connected to the main control module and the machine assistance module;

[0145] Aluminum wire is mainly used for deoxidation during LF refining. By adding aluminum wire to the molten steel, the oxygen content in the steel can be effectively reduced, thereby improving the purity of the molten steel. It can also be used for alloying to adjust the composition in the molten steel. The addition of aluminum wire helps to promote the floating of high-melting-point alumina inclusions, thereby reducing the number and area fraction of these inclusions in the continuous casting billet.

[0146] The addition of calcium wire is mainly used to change the morphology of alumina inclusions in the molten steel, converting them into low-melting-point calcium aluminate inclusions, thereby improving the purity and fluidity of the molten steel. Calcium treatment can effectively reduce the melting point of inclusions and ensure the stability of continuous casting operation. The feeding speed of calcium wire and the temperature of the molten steel have a significant impact on the recovery rate of calcium. Appropriate wire feeding speed and higher molten steel temperature can improve the recovery rate of calcium.

[0147] The alloy calculation module is used to establish an alloy calculation model to achieve automatic control of the alloy addition amount according to the process parameters and the in-furnace conditions of each heat, and is electrically connected to the main control module and the machine assistance module;

[0148] A machine-assisted module for real-time collection of data related to in-furnace refining, sending the collected data to the slag-making control module, temperature prediction module, wire feeding prediction module, and alloy calculation module as needed, and performing sampling and slag sticking work through an industrial robot;

[0149] In the present invention, an industrial six-axis robot is used for temperature measurement, sampling, and slag sticking work. These robots have high-precision motion control capabilities, can adapt to high-temperature environments, and support rapid fixture replacement and anti-collision detection functions.

[0150] A main control module, electrically connected to all other modules and the server respectively, for controlling the system operation and performing data interaction with the server;

[0151] A server, electrically connected to the main control module, for data storage and interaction.

[0152] Furthermore, the calculation formulas for the addition amounts of various slag-making agents in the slag-making control module are as follows:

[0153] ;

[0154] ;

[0155] ;

[0156] ;

[0157] ;

[0158] ; ;

[0159] In this embodiment, the values of each coefficient are as follows:

[0160] (slag reduction coefficient), with a value of 0.2;

[0161] (sulfur content influence coefficient), with a value of 10000;

[0162] (converter bottom slag calculation coefficient), with a value of 0.5;

[0163] (fluorite calculation coefficient), with a value range of 0.1 - 0.5;

[0164] (silicon recovery rate and steel slag oxygen element content calculation coefficient), with a value of ;

[0165] (Calculation coefficient of converter slag falling and calcium carbide addition), with a value of 0.1;

[0166] (Calculation coefficient of converter deoxidizer addition and calcium carbide addition), with a value of 0.15;

[0167] (Calculation coefficient of oxygen element content in steel slag and calcium carbide addition), with a value of ;

[0168] (Calculation coefficient of converter slag falling and aluminum particle addition), with a value of 0.1;

[0169] (Calculation coefficient of converter deoxidizer addition and aluminum particle addition), with a value of 0.01;

[0170] (Calculation coefficient of oxygen element content in steel slag and aluminum particle addition), with a value of ;

[0171] (Calculation coefficient of calcium carbide addition and aluminum particle addition), with a value of 0.1;

[0172] (Corresponding coefficient of additional calcium carbide and slag adhesion color), with a value of 15;

[0173] (Corresponding coefficient of additional aluminum particles and slag adhesion color), with a value of 6;

[0174] In this embodiment, the basic lime addition is 400 kg, the slag conversion is 100 kg, k1 is taken as 0.2, the sulfur content at the furnace inlet is 0.025, the standard brick sulfur content is 0.03, then %S is 0.005, k2 is taken as 10000, the converter slag falling amount is 100 kg, k3 is taken as 0.5, and the lime addition after the converter is 100 kg. Then, the first batch of lime to be added for this steel grade is 380 kg.

[0175] k4 is taken as 0.3, and the first batch of fluorite added is calculated based on the first batch of lime addition, which is 114 kg;

[0176] The silicon element recovery rate is 0.6, k5 is taken as , then the oxygen content in the steel slag is 40 ppm;

[0177] A total of 700 kg of deoxidizers (such as ferrosilicon and silicomanganese) are added to the converter, the slag falling amount is 100 kg, k6 is taken as 0.1, k7 is taken as 0.15, k8 is taken as , then 140 kg of calcium carbide needs to be added;

[0178] Take k9 as 0.1, k10 as 0.01, k11 as , take k12 as 0.1, then 41 kg of aluminum pellets need to be added;

[0179] Take k13 as 15, k14 as 6, the color of the adhering slag is black, that is, the color grade is 5, then 30 kg of aluminum pellets need to be additionally added.

[0180] Folding slag means that during the refining process in the LF furnace, the remaining hot molten steel slag in the ladle is re-added to the ladle ready for refining in the next ladle to achieve recycling. This practice makes full use of the high alkalinity, low oxidability and low melting point characteristics of the molten steel slag, thereby replacing part of the basic slag materials, reducing the consumption of raw and auxiliary materials such as quicklime for refining, shortening the refining slag-making time, and improving the refining effect.

[0181] Furthermore, the color grades of the adhering slag specifically include:

[0182] 1) Black, foaming: Oxidized slag, indicating that the content of FeO + MnO in the slag > 5%, and the value of the adhering slag color grade is 1;

[0183] 2) Brown, gray: Indicating that the content of FeO + MnO in the slag is 2% - 4%, deoxidizer needs to be additionally added, and the value of the adhering slag color grade is 2;

[0184] 3) Yellow: Deoxidation is in progress, add deoxidizer until white slag, and the value of the adhering slag color grade is 3;

[0185] 4) White slag, grayish white: Indicating that most of the oxides in the slag have been reduced and the deoxidation is good, and the value of the adhering slag color grade is 4;

[0186] 5) The slag is glassy, yellowish white: The final slag has good fluidity and good deoxidation, and the value of the adhering slag color grade is 5.

[0187] Furthermore, the real-time temperature prediction formula of the temperature prediction module is:

[0188] ;

[0189] In this embodiment, the measured temperature is 1550 °C, the heating rate of the molten steel at the 5th gear is 4 °C / min, the temperature drop of the furnace lining is -0.5 °C / min, the temperature drop of the furnace charge is -0.5 °C / min, the temperature drop of argon blowing is -1 °C / min, the temperature drop of the fume and dust gas is -0.5 °C / min, and the time is 10 min, then the predicted temperature is 1565 °C.

[0190] The temperature drop of the furnace lining is the heat absorbed by the furnace lining, the temperature drop of the furnace charge is the heat absorbed by adding alloys and slag materials, the temperature drop of argon blowing is the heat loss of argon blowing, and the temperature drop of the fume and dust gas is the heat taken away by the fume and dust and the gas.

[0191] Furthermore, the argon blowing control module specifically includes:

[0192] Based on the experimental data and historical process experience, a relationship model between the molten steel exposed area and the bottom-blowing argon gas flow rate is established. Then, according to the real-time molten steel exposed area data provided by the image processing unit, the required argon gas flow rate is calculated by the relationship model. Finally, according to the deviation between the real-time monitored molten steel exposed area and the target value, the argon gas flow rate is automatically adjusted.

[0193] Further, the calculation formulas for the feeding amounts of aluminum wire and calcium wire in the wire feeding prediction module are as follows:

[0194] ;

[0195] ;

[0196] Where: is the length of the aluminum wire to be added;

[0197] is the target aluminum content of the steel grade;

[0198] is the actual aluminum content of the steel grade;

[0199] is the amount of aluminum adsorbed by oxidation;

[0200] is the unit weight of the aluminum wire;

[0201] is the percentage of aluminum in the aluminum wire;

[0202] is the recovery rate of the aluminum wire;

[0203] is the weight of the molten steel;

[0204] is the length of the calcium wire to be added;

[0205] is the content in the molten steel;

[0206] is the unit weight of the calcium wire;

[0207] is the percentage of calcium in the calcium wire;

[0208] is the recovery rate of the calcium wire;

[0209] is the calculation parameter obtained by linear programming based on the actual refining data on site.

[0210] Further, in the case where the feeding alloy used for a certain element is unique, the single alloy dosage model is as follows:

[0211] ;

[0212] In this embodiment, the target aluminum content of the special steel is 0.05, the aluminum content of the molten steel entering the station is 0.03, the aluminum content consumed by oxidation and adsorption is 0.01%, the single weight of the aluminum wire is 0.03 (kg / m), the aluminum content of the aluminum wire is 98%, the aluminum recovery rate is 60%, and the weight of the molten steel is 130t. Then the length of the aluminum wire to be added is 221m.

[0213] In this embodiment, the alumina content of the special steel is 0.11, the aluminum content of the molten steel entering the station is 0.03%, the aluminum content consumed by oxidation and adsorption is 0.01%, the single weight of the calcium wire is 0.035 (kg / m), the calcium content of the calcium wire is 98%, the calcium recovery rate is 60%, and k is taken as 1. Then the length of the calcium wire to be added is 119m.

[0214] Further, the machine-assisted module specifically includes:

[0215] Relevant data on in-furnace refining are collected in real time through sensors and system equipment. Through an industrial six-axis robot, according to the requirements of temperature measurement, sampling, and slag adhesion, the system lance automatically installs a probe, inserts the probe into the molten steel in the ladle for temperature measurement and sampling, accurately locates the insertion depth of the probe into the molten steel by detecting the signal of the ladle slag liquid level height position, and places the sample in a fixed position after sampling.

[0216] Further, the relevant data on in-furnace refining specifically include: steel type, molten steel surface image, molten steel weight, total amount of slag materials added during the smelting process of the slag-splitting furnace, basicity of the steel type slag-splitting, molten steel sulfur content, amount of slag flowing from the converter, amount of ferrosilicon added to the converter, amount of silicomanganese alloy added to the converter, amount of deoxidizer added to the converter, actual aluminum content of the steel type, and alumina content in the molten steel.

[0217] Further, the specific refining process of the full-process intelligent refining system is as follows:

[0218] The steel ladle car arrives - the furnace cover descends - the dust removal valve opens - strong blowing to break the slag - robot temperature measurement - automatic calculation and distribution of slag materials and alloys - medium blowing and stirring - automatic calculation of feeding aluminum wire - lower electrode heating - raise the electrode to stop heating - robot temperature measurement, sampling, and slag adhesion - strong blowing for desulfurization - automatic feeding to supplement alloys - secondary aluminum supplementation - robot temperature measurement, sampling, and slag adhesion - lower electrode heating - robot temperature measurement, sampling, and slag adhesion - raise the electrode to stop heating - automatic soft blowing - automatic feeding of calcium - secondary soft blowing - dust removal valve closes - argon gas closes - the ladle leaves the station.

[0219] In this process, the strong blowing for slag breaking, medium blowing for stirring, strong blowing for desulfurization, automatic soft blowing, and secondary soft blowing are controlled by the argon blowing control module; the robot for temperature measurement, sampling, and slag sticking is controlled by the machine assistance module; the automatic calculation and distribution of alloys, and the automatic feeding to replenish alloys are controlled by the alloy calculation module; the automatic calculation of feeding aluminum wire, secondary aluminum replenishment, and automatic calcium feeding are controlled by the wire feeding prediction model; the lower electrode heating and the upper electrode stopping heating are controlled by the temperature prediction model; the automatic calculation and distribution of slag materials are controlled by the slag making control model.

[0220] The flow rate and intensity of bottom blowing argon are divided into three modes: soft blowing, medium blowing, and strong blowing. The soft blowing argon flow rate is relatively low, usually 80 L / min, mainly used to promote the floating and removal of non-metallic impurities in the molten steel, thereby improving the cleanliness of the molten steel. During the LF refining process, the soft blowing stage can effectively remove inclusions larger than 10μm, significantly reducing the average size of the inclusions. In addition, soft blowing can also promote the floating of inclusions through weak stirring, reducing the floating time.

[0221] Medium blowing: The medium blowing argon flow rate is moderate, usually 200 L / min, mainly used in the stable heating stage to maintain the uniformity of the molten steel temperature and composition through medium-intensity stirring. In the automatic mode of LF refining, the medium blowing stage usually lasts for 3 - 5 minutes to ensure the uniformity of the molten steel temperature and composition.

[0222] Strong blowing: The strong blowing argon flow rate is relatively high, usually 500 L / min, mainly used in the slag melting and desulfurization stage to promote the removal of sulfur and other harmful elements in the molten steel through high-intensity stirring. In the automatic mode of LF refining, the strong blowing stage also lasts for 3 - 5 minutes to ensure that the sulfur content in the molten steel is reduced to the target level.

[0223] It should be noted that this application is not limited to the above embodiments. The above embodiments are only examples, and embodiments with the same composition and the same function and effect as the technical idea within the scope of the technical solution of this application are included in the technical scope of this application. In addition, within the scope of not departing from the main idea of this application, various deformations that can be thought of by those skilled in the art to the embodiments, and other ways constructed by combining some constituent elements of the embodiments are also included in the scope of this application.

Claims

1. An all-process intelligent refining system applied to an LF refining furnace, characterized in that, Including: A slag-making control module, which is used to calculate the addition amount of slag-making agent during the refining process according to the mechanism model, and is electrically connected to the main control module and the machine assistance module; A temperature prediction module, which is used to preprocess temperature data, and perform real-time prediction and control of the molten steel temperature through a prediction model, and is electrically connected to the main control module and the machine assistance module; The real-time temperature prediction formula of the temperature prediction module is: ； Wherein: is the predicted temperature of molten steel; For measuring the temperature of molten steel; The heating rate of molten steel at different gears; is the temperature drop of the furnace lining; is the temperature drop of the burden is the temperature drop during argon blowing; For the temperature drop of flue gas; is a time interval; An argon blowing control module, which is used to establish a relationship model between the exposed area of molten steel and the bottom argon blowing flow rate according to experimental data and historical process experience, and realize automatic argon blowing, and is electrically connected to the main control module and the machine assistance module; A wire feeding prediction module, which is used to calculate the feeding amounts of aluminum wire and calcium wire according to the steel grade and molten steel composition, and verify and optimize the feeding amounts, and is electrically connected to the main control module and the machine assistance module; The calculation formulas for the feeding amounts of aluminum wire and calcium wire in the wire feeding prediction module are as follows: ； ； Wherein: is the length of the aluminum wire to be added; is the target aluminum content of the steel grade; is the actual aluminum content of the steel grade; is the amount of aluminum adsorbed by oxidation; is the unit weight of the aluminum wire; is the aluminum content percentage of the aluminum wire; is the aluminum wire yield; is the weight of molten steel; is the length of the calcium wire to be added; For the molten steel content; is the unit weight of the calcium wire; is the calcium content percentage of the aluminum wire; is the calcium wire recovery rate; Calculation parameters obtained by linear programming based on actual refining data on-site; An alloy calculation module, which is used to establish an alloy calculation model according to the process parameters and in-furnace conditions of each heat, and realize automatic control of the alloy addition amount, and is electrically connected to the main control module and the machine assistance module; A machine assistance module, which is used to collect real-time data related to in-furnace refining, send the collected data to the slag-making control module, temperature prediction module, wire feeding prediction module, and alloy calculation module as needed, and perform sampling and slag sticking work through an industrial robot; A main control module, which is electrically connected to all other modules and the server respectively, is used to control the system operation, and perform data interaction with the server; A server, which is electrically connected to the main control module, is used for data storage and interaction.

2. The full-process intelligent refining system applied to an LF refining furnace according to claim 1, wherein The calculation formulas for the addition amounts of each slag-making agent in the slag-making control module are as follows: ； ； ； ； ； ； ； Wherein: is the amount of lime added during the refining process; is the basic lime addition amount for the steel grade; It is the total amount of slag materials added during the smelting process of this heat for slag folding; is the basicity of the slag folding for the steel grade; is the difference between the sulfur content of the molten steel and the target sulfur content; is the weight of molten steel; is the slag volume in the converter tapping; is the amount of lime added behind the converter; is the addition amount of fluorite during the refining process; is the oxygen content of steel slag; The amount of ferrosilicon added to the converter; is the silicon content in ferrosilicon; The amount of silicomanganese alloy added to the converter; is the silicon content in ferrosilicon manganese; For the silicon content sampled at the argon station; is the addition amount of calcium carbide during the refining process; is the addition amount of deoxidizer for the converter; is the addition amount of aluminum particles during the refining process; is the carbide addition amount; is the additional amount of aluminum particles; is the slag adhesion color grade; They are calculation parameters obtained by linear programming based on the actual refining data on site.

3. An all-process intelligent refining system applied to an LF refining furnace according to claim 1, characterized in that, The argon blowing control module specifically includes: Establish a relationship model between the exposed area of molten steel and the bottom argon blowing flow rate according to experimental data and historical process experience, then calculate the required argon flow rate from the relationship model according to the real-time exposed area data of the molten steel provided by the image processing unit, and finally automatically adjust the argon flow rate according to the deviation between the real-time monitored exposed area of the molten steel and the target value.

4. An all-process intelligent refining system applied to an LF refining furnace according to claim 1, characterized in that, When there is a unique feeding alloy for a certain element in the alloy calculation module, the single alloy dosage model is as follows: ； Wherein: is the addition amount of the i-th alloy; is the quality of molten steel; is the final mass fraction of the required elements in the molten steel; is the initial mass fraction of the required elements in the molten steel; is the recovery rate of the required element in the i-th alloy; is the mass fraction of the required element in the i-th alloy.

5. An all-process intelligent refining system applied to an LF refining furnace according to claim 1, characterized in that The machine assistance module specifically includes: Collect real-time data related to in-furnace refining through sensors and system equipment. Through an industrial six-axis robot, according to the requirements of temperature measurement, sampling, and slag sticking, the system lance automatically installs a probe, inserts the probe into the molten steel in the ladle for temperature measurement and sampling, accurately locates the insertion depth of the probe into the molten steel by detecting the signal of the ladle slag liquid level height position, and places the sample in a fixed position after sampling.

6. The full-process intelligent refining system applied to the LF refining furnace according to claim 5, characterized in that, The in-furnace refining related data specifically includes: molten steel surface image, molten steel weight, total amount of slag materials added during the smelting process of the slag-breaking heat, basicity of the slag-breaking for the steel grade, sulfur content of the molten steel, amount of slag flowing from the converter, amount of ferrosilicon added by the converter, amount of silicomanganese alloy added by the converter, amount of deoxidizer added by the converter, steel grade, actual aluminum content of the steel grade, and alumina content in the molten steel.

7. An all-process intelligent refining system applied to an LF refining furnace according to claim 1, characterized in that, The specific refining process of the full-process intelligent refining system is as follows: The ladle car arrives - the furnace cover descends - the dust removal valve opens - strong blowing to break slag - the robot measures temperature - the slag materials and alloys are automatically calculated and sent down - medium blowing for stirring - automatically calculating and feeding aluminum wire - the lower electrode heats - the electrode is lifted to stop heating - the robot measures temperature, samples and dips slag - strong blowing for desulfurization - automatically feeding materials to supplement alloys - secondary aluminum feeding - the robot measures temperature, samples and dips slag - the lower electrode heats - the robot measures temperature, samples and dips slag - the electrode is lifted to stop heating - automatic soft blowing - automatic calcium feeding - secondary soft blowing - the dust removal valve closes - the argon gas closes - the ladle leaves the station.

Images