A method for automatically screening an electric furnace process for producing high-carbon bearing steel

Abstract

The application discloses a method for automatically screening an electric furnace process for producing high-carbon bearing steel, and comprises the following steps: calculating a similarity score according to the amount of molten iron, the temperature of molten iron, the content of carbon, silicon, manganese, phosphorus, titanium and chromium in the molten iron and the amount of scrap steel, screening a furnace period with similar similarity scores and the lowest cost in an electric furnace production database of high-carbon bearing steel, reading electric furnace process parameters of the furnace period, and performing electric furnace smelting according to the process parameters; the temperature of molten steel after electric furnace smelting can be controlled at 1640-1660 DEG C, the carbon content can be controlled at 0.4-0.6%, and the phosphorus content can be controlled below 0.011%. The application realizes the standardization and normalization of electric furnace smelting by automatic similarity score calculation and process screening, and avoids quality fluctuation caused by experience difference of different operators.

Description

Technical Field

[0001] This invention belongs to the field of metallurgical technology, specifically relating to automatic control technology for electric arc furnace steelmaking, and more particularly to a method for automatically screening electric arc furnace processes to produce high-carbon bearing steel. Background Technology

[0002] Bearing steel is considered one of the most difficult steel grades to produce, with the most testing items and the strictest quality requirements in the steel industry. It is regarded as a symbol of a country's industrial technology level and is hailed as the "King of Special Steels." Currently, the main types of bearings used worldwide include: high-carbon chromium bearing steel, medium-high temperature bearing steel, stainless bearing steel, carburized bearing steel, antimagnetic bearing steel, and special-purpose bearing materials. In its more than 100-year history, the quality of bearing steel has greatly improved with the development of science and technology, the improvement of smelting equipment, and the continuous optimization of smelting technology. However, compared with international advanced levels, my country's high-quality bearing steel still lags significantly. Bearing steel produced by domestic steel enterprises has problems such as high residual Ti content, high oxygen content, and high non-metallic inclusion content.

[0003] The electric arc furnace (EAF) process is one of the key processes determining the quality of bearing steel. High-quality molten steel from the EAF ensures stability during the LF refining process, reducing inclusions, stabilizing steel composition, and improving overall steel quality. However, because EAF production largely relies on the skill level and understanding of the process by on-site operators, differences in product quality arise between operators. Human factors increase the instability of the molten steel produced from the EAF. Specifically: (1) Different operators make different process choices for the same molten iron conditions, resulting in fluctuations in the quality of the produced steel; (2) The experience of operators cannot be effectively passed on, and the process parameters of excellent furnace batches are difficult to reuse in subsequent production; (3) There is a lack of objective and quantitative process screening standards, and the process selection is highly subjective; (4) It is impossible to systematically consider production cost optimization while ensuring quality.

[0004] Therefore, there is an urgent need in this field for a method that can automatically screen electric furnace processes to reduce the impact of human factors on steel quality and improve the production qualification rate and economy of high-carbon bearing steel. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an automatic screening method for producing high-carbon bearing steel in electric arc furnaces, which is an improvement over the prior art. By constructing a high-carbon bearing steel electric arc furnace production database and designing a similarity score calculation method, the process parameters of the furnace with the most similar raw material conditions and the lowest cost in the historical furnaces are automatically matched and executed, thereby reducing the impact of human factors on the quality of molten steel, improving the production qualification rate of high-carbon bearing steel, and reducing production costs.

[0006] The technical solution adopted by the present invention to solve the above problems is as follows: a method for producing high-carbon bearing steel using an automatic screening electric furnace process, the method comprising the following steps: Step 1: Construct a database for the production of high-carbon bearing steel in electric furnaces. The database contains production data of high-carbon bearing steel of the same grade that has met the required temperature and composition in previous batches produced in the target electric furnace. The following information is recorded for each furnace: (1) Furnace number and production time identifier; (2) Raw material information: amount of molten iron added (kg), temperature of molten iron entering the furnace (°C), composition of molten iron (content of carbon C, silicon Si, manganese Mn, phosphorus P, chromium Cr, and titanium Ti, wt%), amount of scrap steel added (kg) and type of scrap steel; (3) Electric furnace operating parameters: burner mode and gear, oxygen flow rate and time curve during oxygen blowing, amount and time of each solvent added during flux addition, type and quantity of alloys added during tapping, type and quantity of slag-forming material and addition time. (4) Electric furnace power supply curve: including voltage curve, current curve and corresponding energizing time; (5) Smelting results: Temperature and composition of molten steel at the end of electric furnace smelting; (6) Production cost of this batch; (7) The similarity score of this batch is calculated according to step two.

[0007] Step 2: Calculate the similarity score for the current furnace batch. Before the current furnace smelting, obtain the following parameters: molten iron inlet temperature. (°C), carbon content of molten iron (wt%), silicon content in molten iron (wt%) Manganese content in molten iron (wt%) Phosphorus content in molten iron (wt%) Chromium content in molten iron (wt%), molten iron and titanium content (wt%), weight of molten iron (kg), important scrap steel (kg).

[0008] At the same time, the following statistical values ​​are read from the database: the average temperature of molten iron entering the furnace for all furnace cycles in the database. (°C), average carbon content of molten iron (wt%), average silicon content of molten iron (wt%), average manganese content in molten iron (wt%) Average phosphorus content in molten iron (wt%), average chromium content in molten iron (wt%), average titanium content in molten iron (wt%), average weight of molten iron (kg), average scrap steel weight (kg).

[0009] Calculate the similarity score for the current furnace using the following formula. :

[0010] The numerator of this similarity score is the sum of the ratios of the nine parameters to their corresponding historical averages, and the denominator is the square root of the sum of the squares of each ratio multiplied by 3. Essentially, it reflects the overall deviation of the nine raw material parameters of the current furnace from the historical average level. The closer the similarity score is to 1, the closer the raw material conditions of the current furnace are to the historical average level; the closer the similarity scores of two furnaces are, the more similar their raw material conditions are.

[0011] Step 3: Filter the furnaces with similar scores and lowest costs from the database, using a progressive matching strategy, and execute in the following order: (1) Search the database for similarity scores with the current smelting furnace. All historical furnace data with the same value; (2) If the data can be searched, then compare the production costs of each batch, read the process parameters of the batch with the lowest cost, including the power supply curve, feeding process, oxygen blowing process, burner mode, etc., and proceed to step four. (3) If there is no agreement For data with the same value, update the similarity score to ( ). -0.05) and then perform the search; (4) If the data can be found, compare the cost of each furnace, read the electric furnace process parameters of the furnace with the lowest cost, and proceed to step four. (5) If no match is found, continue to update the similarity score to ( The search threshold is reduced by 0.05 each time, starting with -0.10, until at least one furnace process parameter is successfully read. Step 4: Perform smelting according to the selected process parameters. Send the process parameters read in Step 3 to the electric furnace control system and execute them automatically according to the following sub-steps. (1) Control the power supply of the electric furnace according to the read power supply curve (voltage and current change curve over time); (2) Perform the feeding operation according to the reading feeding process (the amount and time of adding all solvents such as carbon powder, lime, dolomite, and magnesium balls); (3) Perform the oxygen blowing operation according to the read oxygen blowing process (oxygen flow rate and oxygen blowing time curve); (4) Perform burner control according to the read burner mode; (5) Monitor the temperature and composition of molten steel in real time during the smelting process, and stop smelting when the electric furnace smelting endpoint is reached; Step 5: Result Verification and Database Update After smelting, the temperature and composition of the molten steel at the end of the electric furnace smelting process are measured to verify whether the following control objectives are met: Molten steel temperature: 1640~1660℃; Carbon content: 0.4%~0.6%; Phosphorus content: below 0.011%.

[0012] All data from this smelting process (including raw material parameters, process parameters, endpoint results, and actual costs) are entered into the database, and the similarity score for this heat is calculated as historical data for matching subsequent heats.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention avoids quality fluctuations caused by differences in experience among different operators by using automated similarity score calculation and process screening, thereby achieving standardization and normalization of electric furnace smelting.

[0014] 2. This invention saves the process parameters of historically excellent furnaces in the form of data and enables reuse through similarity matching, so that excellent smelting experience can be inherited and promoted.

[0015] 3. By applying the method of this invention, the final steel temperature of electric furnace smelting can be stably controlled at 1640℃~1660℃, the carbon content can be controlled at 0.4%~0.6%, and the phosphorus content can be controlled below 0.011%.

[0016] 4. The present invention adopts a progressive matching strategy (gradually relaxing from precise matching) to ensure that a usable historical process solution can be found under any raw material conditions, thus avoiding the predicament of being forced to return to manual operation due to matching failure. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the implementation of the present invention. Detailed Implementation

[0018] The technical solution of the present invention will be described in more detail below with reference to preferred embodiments. However, these embodiments are merely descriptions of preferred implementations of the present invention and should not be construed as limiting the scope of the present invention. Example 1

[0019] Furnace number 1, molten iron weight 60t, molten iron temperature 1340℃, molten iron C 4.1%, Si 0.3%, Mn 0.40%, P 0.11%, S 0.030%, Cr 0.05%, Ti 0.005%. Scrap steel added 30t. Based on the above raw material parameters, calculate the similarity fraction according to step two.

[0020] The database was used to filter heats with similar scores, and the heat with the lowest cost was selected. The power supply curve, flux addition amount and time, oxygen blowing curve, and burner setting for this heat were read, and smelting was carried out according to this process. After smelting, the following tests were conducted: the molten steel temperature at the end of the electric furnace smelting was 1643℃, the carbon content was 0.46%, and the phosphorus content was 0.010%, both meeting the control target requirements. Example 2

[0021] Furnace number 2, molten iron weight 65t, molten iron temperature 1360℃, molten iron C 4.0%, Si 0.4%, Mn 0.38%, P 0.10%, S 0.025%, Cr 0.06%, Ti 0.004%. Scrap steel added 28t. Similarity scores were calculated and matching furnace batches were selected using the same method. Process parameters were read and smelting was executed.

[0022] After smelting, the steel temperature was 1650℃, the carbon content was 0.42%, and the phosphorus content was 0.009%, both of which met the control target requirements. Example 3

[0023] Furnace number 3, molten iron weight 62t, molten iron temperature 1356℃, molten iron C 4.3%, Si 0.36%, Mn 0.35%, P 0.09%, S 0.015%, Cr 0.05%, Ti 0.006%. Scrap steel added 32t. Similarity scores were calculated and matching furnace batches were selected using the same method. Process parameters were read and smelting was executed.

[0024] After smelting, the steel temperature was 1649℃, the carbon content was 0.50%, and the phosphorus content was 0.009%, both of which met the control target requirements.

[0025] Example 4 (Initial Database Construction and Progressive Matching Validation) During the initial commissioning phase of a newly built electric arc furnace production line at a steel plant, the database contained only historical data from 50 heats, which were relatively scattered. The raw material parameters for a particular heat on a certain day were: 63 tons of molten iron, 1350℃, C 4.15%, Si 0.32%, Mn 0.36%, P 0.10%, Cr 0.055%, Ti 0.005%, and 31 tons of scrap steel. The calculations yielded... =0.987. No record found in the database. =0.987 furnace runs, continue searching Two furnace batches were found. The one with the lower cost was selected, and its process parameters were read and executed. The final smelting temperature was 1645℃, with carbon content of 0.44% and phosphorus content of 0.009%, all meeting the standards.

[0026] This embodiment verifies the effectiveness of the progressive matching strategy when the database sample is limited.

[0027] The specific embodiments described above are merely illustrative examples provided to facilitate understanding of the present invention and are not intended to limit the scope of protection of the present invention. Without causing conflict or rendering the technical solution impossible, the various technical features and embodiments of the present invention can be combined with each other. Any equivalent substitutions and modifications made to the present invention by any person skilled in the art without departing from the concept and principles disclosed herein should fall within the scope of protection of the present invention.

Claims

1. A method for producing high-carbon bearing steel using an automatic screening electric furnace process, characterized in that: The method includes the following steps: calculating a similarity score based on the amount of molten iron added, the temperature of the molten iron, the content of carbon, silicon, manganese, phosphorus, titanium, and chromium in the molten iron, and the amount of scrap steel added; selecting the heats with the closest similarity scores and the lowest cost from the high-carbon bearing steel electric arc furnace production database; reading the electric arc furnace process parameters for that heat; and performing electric arc furnace smelting according to the process parameters; the formula for calculating the similarity score is: ； in: The temperature of the molten iron when it enters the furnace, in °C; The average molten iron temperature (K) calculated for all furnace runs in the database when the molten iron enters the furnace; , , , , , The contents of carbon, silicon, manganese, phosphorus, chromium, and titanium in molten iron are respectively expressed in wt%; , , , , , These represent the average content (wt%) of carbon, silicon, manganese, phosphorus, chromium, and titanium in molten iron calculated for all furnace runs in the database. The weight of the molten iron is in kg. The average weight of molten iron calculated for all furnace runs in the database, in kg; The weight of the scrap steel is in kg. The average scrap weight, in kg, is calculated for all heats in the database.

2. The method for producing high-carbon bearing steel using an automatic screening electric furnace process according to claim 1, characterized in that: The high-carbon bearing steel electric arc furnace production database contains production data of high-carbon bearing steel of the same grade that has been produced in the target electric arc furnace with qualified temperature and composition. The data for each heat includes: heat number, amount of molten iron added, temperature of molten iron entering the furnace, composition of molten iron, amount of scrap steel added; burner mode, oxygen blowing process, flux addition process, type and quantity of alloys added during tapping, type and quantity of slag-forming materials and addition time; electric arc furnace power supply curve; temperature and composition of molten steel at the end of electric arc furnace smelting; and similarity score of that heat.

3. The method for producing high-carbon bearing steel using an automatic screening electric furnace process according to claim 1, characterized in that: The process of selecting the furnace batches with similar scores and lowest costs from the high-carbon bearing steel electric furnace production database includes the following steps: (1) Search the database for similarity scores with the current smelting furnace. All historical furnace data with the same value; (2) If the data can be searched, then compare the production costs of each batch and read the process parameters of the batch with the lowest cost. (3) If there is no agreement For data with the same value, update the similarity score to ( ). -0.05) and then perform the search; (4) If the data can be searched, then compare the cost of each furnace and read the electric furnace process parameters of the furnace with the lowest cost. (5) If no match is found, continue to update the similarity score to ( The search threshold is reduced by 0.05 each time until the electric furnace process parameters are successfully read.

4. The method for producing high-carbon bearing steel using an automatic screening electric furnace process according to claim 1, characterized in that: The electric furnace power supply curve includes the voltage change curve over time, the current change curve over time, and the energizing time.

5. The method for producing high-carbon bearing steel using an automatic screening electric furnace process according to claim 1, characterized in that: The feeding process includes information on the amount and timing of adding carbon powder, lime, dolomite, and magnesium balls to the solvent used in the electric furnace smelting process.

6. The method for producing high-carbon bearing steel using an automatic screening electric furnace process according to claim 1, characterized in that: The electric furnace process parameters include the oxygen flow rate versus time curve and oxygen blowing time information during the oxygen blowing process.

7. The method for producing high-carbon bearing steel using an automatic screening electric furnace process according to claim 1, characterized in that: The final steel temperature of the electric furnace smelting process is controlled at 1640~1660℃; Carbon content: 0.4%~0.6%; Phosphorus content: below 0.011%.

8. The method for producing high-carbon bearing steel using an automatic screening electric furnace process according to claim 1, characterized in that: The process includes a database update step: inputting the raw material parameters, process parameters, endpoint results, and actual costs for each smelting process into the database, and calculating the similarity score for that furnace, which serves as historical data for matching subsequent furnaces.

Images