Real-time prediction method and system for carbon content of RH refined molten steel based on machine learning

Abstract

The invention belongs to the technical field of ferrous metallurgy, and particularly relates to an RH refined molten steel carbon content real-time prediction method and system based on machine learning, RH refined flue gas time series data are analyzed and excavated, a flue gas correction coefficient and representative characteristic variables are provided around an RH decarburization process, a prediction model is constructed by adopting a machine learning algorithm, and the carbon content of the RH refined molten steel is predicted in real time. Characteristic parameters in the flue gas data can be fully mined, the deviation between the flue gas data and the actual carbon content is described, and high-precision real-time prediction of the carbon content of the molten steel in the RH refining process is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of iron and steel metallurgy, and specifically to a real-time prediction method and system for the carbon content of molten steel in RH refining based on machine learning. Background Art

[0002] Decarburization is a key step in the RH refining process. Through vacuum cyclic degassing, carbon and oxygen in the molten steel react to form carbon monoxide or carbon dioxide and are discharged through a vacuum pump, thereby achieving the purpose of decarburization. In order to achieve precise control of the decarburization process, by predicting the carbon content of the molten steel in real time, operators can timely understand the current refining state, and thus adjust parameters such as oxygen blowing amount and temperature to optimize the refining process, which helps to shorten the refining cycle and improve production efficiency.

[0003] At present, real-time prediction of the carbon content of molten steel in RH refining in iron and steel enterprises is rare, and the refining process still mainly relies on manual experience for process control. Some scholars have carried out research on real-time prediction methods for the carbon content of molten steel in RH refining, such as: combining the carbon and oxygen balance equations of the ladle and vacuum chamber to construct a decarburization mechanism model for RH refining; on the basis of the decarburization mechanism model for RH refining, introducing a decarburization factor, and determining the decarburization factor under different production scenarios through data driving to improve the adaptability of the mechanism model to the complex production environment; and also through the collected real-time flue gas data of RH refining, based on carbon balance calculation, real-time prediction of the carbon content of molten steel is carried out. However, the methods proposed above have not been well applied in the production site, mainly due to the following problems: 1) The black-box model constructed based on the decarburization mechanism has many assumed parameters and is difficult to accurately predict the real-time carbon content of molten steel due to the complex changes in real-time perception of on-site production conditions; 2) Although flue gas data collection is an important means to improve the perception of the RH refining production site, it is difficult to obtain satisfactory prediction results for the carbon content of molten steel only by carbon balance calculation; 3) The current research methods still do not fully explore the RH refining flue gas data, resulting in poor application effects of machine learning in flue gas data. Summary of the Invention

[0004] To solve the problems existing in the prior art, the main purpose of the present invention is to propose a real-time prediction method and system for the carbon content of molten steel in RH refining based on machine learning. By analyzing and mining the time-series data of RH refining flue gas, a flue gas correction coefficient and representative characteristic variables are proposed around the RH decarburization process, and a prediction model is constructed using a machine learning algorithm to achieve higher-precision real-time prediction of the carbon content of molten steel in the RH refining process.

[0005] According to one aspect of the present invention, the following technical solution is provided:

[0006] A real-time prediction method for the carbon content of molten steel in RH refining based on machine learning, comprising the following steps:

[0007] S1. Collect the production data of RH refining historical heats, screen and preprocess abnormal heats, and process the flue gas time-series data of each historical heat as follows:

[0008] S11. Divide the flue gas time-series data into multiple segments according to the set time step, and calculate the cumulative decarburization amount, cumulative flue gas amount, average flue gas content, cumulative CO amount, average CO content, cumulative CO 2 amount, and average CO 2 content within each segment through flue gas integration.

[0009] S12. Superimpose the cumulative decarburization amounts within all segments to obtain the cumulative decarburization amount calculated based on flue gas analysis during the smelting cycle;

[0010] S13. Calculate the actual decarburization amount during the smelting cycle according to the initial carbon content and end-point carbon content data of this historical heat;

[0011] S14. Define the flue gas correction coefficient to represent the deviation between flue gas analysis and actual detection, and obtain it by calculating the ratio of the actual decarburization amount to the cumulative decarburization amount;

[0012] S15. Combine the flue gas correction coefficient to calculate the actual decarburization amount within each time step segment;

[0013] S2. Store the process parameters related to the decarburization process in the RH refining production data and the parameters generated after processing the flue gas time-series data in step S1 into the model database for subsequent modeling;

[0014] S3. Use the cumulative flue gas amount, average flue gas content, cumulative CO amount, average CO content, cumulative CO 2 amount, and average CO 2 content, and process parameters within each time step segment as model input variables, use the actual decarburization amount within each time step segment as the model output variable, adopt machine learning algorithms for weight extraction and feature selection, and construct a prediction model;

[0015] S4. Real-time collect the production data of the current heat in RH refining. After each time step ends, calculate the cumulative decarburization amount, cumulative flue gas amount, average flue gas content, cumulative CO amount, average CO content, cumulative CO 2 amount, and average CO 2 content during this time step; substitute the model input variables into the prediction model to output the predicted result of the actual decarburization amount within each time step segment; combine with the initial carbon content of the current heat to realize the real-time prediction of the molten steel carbon content.

[0016] According to another aspect of the present invention, the present invention provides the following technical solution:

[0017] A real-time prediction system for the carbon content of molten steel in RH refining based on machine learning, comprising:

[0018] Model database construction module: Collect the production data of historical RH refining heats, screen and preprocess abnormal heats, and process the flue gas time series data of each historical heat to construct a model database for modeling;

[0019] Prediction model construction module: Determine the input variables and output variables of the model, and construct a prediction model for the actual decarburization amount within each time step through machine learning algorithms;

[0020] Real-time prediction module for the carbon content of molten steel: According to the collected real-time heat production data, the prediction results of the actual decarburization amount within each time step are output through the model to achieve real-time prediction of the carbon content of molten steel.

[0021] The beneficial effects of the present invention are as follows:

[0022] The present invention proposes a real-time prediction method and system for the carbon content of molten steel in RH refining based on machine learning. By analyzing and mining the time series data of RH refining flue gas, a flue gas correction coefficient and representative characteristic variables are proposed around the RH decarburization process, and a prediction model is constructed using machine learning algorithms. It can fully mine the characteristic parameters in the flue gas data, describe the deviation between the flue gas data and the actual carbon content, and achieve high-precision real-time prediction of the carbon content of molten steel in the RH refining process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the structures shown in these drawings without creative efforts.

[0024] Figure 1 It is a framework schematic diagram of the prediction method of the present invention.

[0025] Figure 2 It is the real-time prediction of the carbon content of molten steel for the heats with an incoming carbon content of 200 - 300 ppm in the embodiments of the present invention.

[0026] Figure 3 It is the real-time prediction of the carbon content of molten steel for the heats with an incoming carbon content of 300 - 400 ppm in the embodiments of the present invention.

[0027] Figure 4 It is the real-time prediction of the carbon content of molten steel for the heats with an incoming carbon content of 400 - 500 ppm in the embodiments of the present invention.

[0028] Figure 5It is the real-time prediction of the molten steel carbon content for the furnace charges with an inlet carbon content of more than 500 ppm in the embodiments of the present invention.

[0029] The realization, functional features and advantages of the objectives of the present invention will be further described in conjunction with the embodiments and with reference to the accompanying drawings. Specific embodiments

[0030] The technical solutions in the embodiments will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0031] The present invention proposes a real-time prediction method and system for the molten steel carbon content in RH refining based on machine learning. By analyzing and mining the time-series data of RH refining flue gas, a flue gas correction coefficient and representative characteristic variables are proposed around the RH decarbonization process, and a prediction model is constructed using machine learning algorithms to achieve a higher-precision real-time prediction of the molten steel carbon content in the RH refining process.

[0032] According to one aspect of the present invention, the following technical solutions are provided:

[0033] As Figure 1 shown, a real-time prediction method for the molten steel carbon content in RH refining based on machine learning includes the following steps:

[0034] S1. Collect the production data of historical furnace charges in RH refining, screen and preprocess the abnormal furnace charges, and perform the following processing on the time-series data of the flue gas of each historical furnace charge:

[0035] S11. Divide the time-series data of the flue gas into multiple segments according to the set time step, and calculate the cumulative decarburization amount, cumulative flue gas amount and average flue gas content, cumulative CO amount and average CO content, cumulative CO 2 amount and average CO 2 content in each segment through flue gas integration.

[0036] S12. Superimpose the cumulative decarburization amounts in all segments to obtain the cumulative decarburization amount calculated based on flue gas analysis during the smelting cycle;

[0037] S13. Calculate the actual decarburization amount during the smelting cycle according to the initial carbon content and end-point carbon content data of the historical furnace charge;

[0038] S14. Define the flue gas correction coefficient to represent the deviation between flue gas analysis and actual detection, and obtain it by calculating the ratio of the actual decarburization amount to the cumulative decarburization amount;

[0039] S15. Calculate the actual decarbonization amount within each time step segment in combination with the flue gas correction coefficient;

[0040] S2. Store the process parameters related to the decarbonization process in the RH refining production data and the parameters generated after processing the flue gas time series data in step S1 into the model database for subsequent modeling;

[0041] S3. Take the cumulative flue gas volume and average flue gas content, cumulative CO volume and average CO content, cumulative CO 2 volume and average CO 2 content and process parameters as model input variables, take the actual decarbonization amount within each time step segment as the model output variable, use machine learning algorithms for weight extraction and feature selection, and build a prediction model;

[0042] S4. Real-time collect the production data of the current heat in RH refining. After each time step ends, calculate the cumulative decarbonization amount, cumulative flue gas volume and average flue gas content, cumulative CO volume and average CO content, cumulative CO 2 volume and average CO 2 content within this time step; Substitute the model input variables into the prediction model to output the predicted result of the actual decarbonization amount within each time step segment; Combine with the initial carbon content of the current heat to achieve real-time prediction of the molten steel carbon content.

[0043] Preferably, in step S1, the following situations are determined as abnormal heats: 1) Adding carbon powder during the production process; 2) Adjusting the temperature by adding scrap steel; 3) Abnormal signal acquisition; 4) Abnormal detection results.

[0044] Preferably, in step S1, the lower limit of the time step setting should be greater than the flue gas data acquisition time interval.

[0045] Preferably, in step S1, the calculation method of the cumulative decarbonization amount within each time step is

[0046]

[0047] In the formula, ΔC i represents the cumulative decarbonization amount within the time step, ppm; Q gas represents the flue gas flow rate, kg / h; represents the percentage content of CO in the flue gas, %; represents the percentage content of CO 2 in the flue gas, %; M C represents the relative atomic mass of C; M CO represents the relative atomic mass of CO; represents the relative atomic mass of CO 2 ; t represents time, s; Wsteel Indicates the weight of molten steel, in kg.

[0048] Preferably, in step S1, the cumulative flue gas volume, average flue gas content, cumulative CO volume, average CO content, cumulative CO 2 volume and average CO 2 The content calculation method is

[0049] m 烟气累积 = ∫Q gas dt

[0050] m 烟气平均 = ∫Q gas dt / t

[0051]

[0052]

[0053]

[0054]

[0055] Preferably, in step S1, the flue gas correction coefficient calculation method is

[0056]

[0057] In the formula, W represents the flue gas correction coefficient; C represents the incoming carbon content, in ppm; C ′ represents the outgoing carbon content, in ppm; ∫ΔC i represents the cumulative decarburization amount of the flue gas during the smelting time.

[0058] Preferably, in step S1, the actual decarburization amount within each time step is calculated as

[0059] ΔC i ′ = W·ΔC i

[0060] Preferably, in step S2, the process parameters related to decarburization in the RH refining production data include the molten steel weight, incoming carbon content, incoming oxygen activity, vacuum chamber life, dip tube life, incoming temperature, slag layer thickness, decarburization time, etc.

[0061] Preferably, in step S3, if there is a delay in the on-site flue gas data, the real-time prediction result of the molten steel carbon content should consider the delay time.

[0062] According to another aspect of the present invention, the present invention provides the following technical solution:

[0063] A real-time prediction system for the carbon content of molten steel in RH refining based on machine learning, comprising:

[0064] Model database construction module: Collect the production data of historical RH refining heats, screen and preprocess abnormal heats, and process the flue gas time-series data of each historical heat to construct a model database for modeling;

[0065] Prediction model construction module: Determine the input variables and output variables of the model, and construct a prediction model for the actual decarburization amount within each time step through machine learning algorithms;

[0066] Real-time prediction module for molten steel carbon content: According to the collected real-time heat production data, the prediction results of the actual decarburization amount within each time step are output through the model to achieve real-time prediction of the molten steel carbon content.

[0067] Embodiment

[0068] Taking the RH refining production data of low-carbon steel and ultra-low-carbon steel from August 2023 to October 2024 of a certain steel plant as an example, after the data extraction is completed, the screening process for abnormal heats is carried out. If a heat appears in the following five situations during the production process, it is identified as an abnormal heat:

[0069] 1) Adding carbon powder during the production process, which is determined as an abnormal heat during the production process;

[0070] 2) Adding scrap steel to adjust the temperature. Since the end-point carbon content is relatively low and the amount of scrap steel added is large, it has a great impact on the end-point carbon content. Therefore, the heats with added scrap steel are screened out to exclude their influence on the calculation of the real-time carbon content;

[0071] 3) The off-station carbon content is greater than 30 ppm. The off-station requirement for low-carbon steel and ultra-low-carbon steel is that the carbon content is less than 30 ppm. If the carbon content at off-station is too high, it is determined as abnormal production;

[0072] 4) Abnormal signal acquisition, without parameters such as flue gas composition, vacuum degree, oxygen blowing amount, etc. in the trend software;

[0073] 5) Abnormal detection results, without recording the in-station carbon content, off-station carbon content or the off-station carbon content detection result is 0.

[0074] After screening according to the above criteria, 1401 heats meet the requirements. On-site, an energy spectrometer is used to detect the flue gas at the cold end, and at the same time, the real-time flue gas flow is obtained through a flue gas flow detector.

[0075] Set the time step to 10 s. For the flue gas time-series data of 1401 heats, calculate the cumulative decarburization amount, cumulative flue gas amount and average flue gas content, cumulative CO amount and average CO content, cumulative CO 2 amount and average CO 2Content; by calculating the ratio of the actual decarburization amount to the cumulative decarburization amount within the smelting cycle of the heat, the flue gas correction coefficient is obtained, and then the actual decarburization amount within each time step is calculated; combined with the above analysis and mining of the flue gas time series data, a total of 1,734,553 pieces of data are formed and stored in the model database.

[0076] The XGBoost algorithm is used to construct a prediction model, and the model expression is:

[0077]

[0078] In the formula, T represents the number of regression trees; x i represents the i-th sample feature value; represents the predicted value of the i-th sample after T iterations of the model; f j (x i ) represents the prediction result of the j-th tree. As an accumulative model, it can be transformed into the accumulative result of the previous T - 1 trees plus the last tree.

[0079] The objective function obj of the XGBoost algorithm consists of the loss function L and the regularization term complexity function Ω:

[0080]

[0081] In the formula, L represents the mean square error of the loss function; Ω represents the regularization term of the loss caused by the model complexity, which is obtained by accumulating the regularization terms of T classification and regression trees.

[0082] The regression tree complexity represented by the regularization term complexity function Ω is affected by two points. One is the weight w on the leaf nodes, and the other is the number of leaf nodes T on the tree 1 , and the smaller the parameters of these two parts, the lower the complexity of the model. The expression is:

[0083]

[0084] In the formula, γ represents the difficulty of node splitting; λ represents the regularization coefficient.

[0085] The XGBoost algorithm sets four types of hyperparameters, namely general hyperparameters, learning task parameters, Booster parameters, and regularization parameters, as shown in Table 1.

[0086] Table 1 XGBoost algorithm hyperparameter settings

[0087]

[0088]

[0089] Predictions are made for four different heats with different inlet carbon contents on site. The real-time prediction results of the molten steel carbon content are as Figures 2 to 5As shown, the incoming carbon content is respectively in four ranges: 200 - 300 ppm, 300 - 400 ppm, 400 - 500 ppm, and above 500 ppm. It can be found from the figure that the present method realizes the real-time and accurate prediction of the molten steel carbon content during the RH refining process under various incoming carbon content conditions.

[0090] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural transformation made by using the content of the specification of the present invention under the inventive concept of the present invention, or any direct / indirect application in other related technical fields is included in the patent protection scope of the present invention.

Claims

1. A real-time prediction method for carbon content in RH refined steel liquid based on machine learning, characterized in that: The steps include: S1. Collect the production data of the historical furnaces of RH refining, screen and pre-process the abnormal furnaces, and process the flue gas time series data of each historical furnace as follows: S11, dividing the flue gas time series data into multiple segments according to the set time step, and calculating the cumulative decarbonization amount, cumulative flue gas amount and average flue gas content, cumulative CO amount and average CO content, cumulative CO2 amount and average CO2 content in each segment through flue gas integration; S12, superimposing the cumulative decarburization amounts in all segments to obtain the cumulative decarburization amount calculated based on flue gas analysis during the smelting cycle; S13, calculating the actual decarburization amount within the smelting cycle according to the initial carbon content and the final carbon content data of the historical furnace; S14. Define a flue gas correction factor to represent the deviation between flue gas analysis and actual detection, which is obtained by calculating the ratio of actual decarburization amount to cumulative decarburization amount; S15, calculating the actual decarbonization amount in each time step segment in combination with the flue gas correction coefficient; S2, storing the process parameters related to the decarbonization process in the RH refining production data and the parameters generated after the flue gas time series data processing in step S1 into the model database for subsequent modeling; S3. The cumulative flue gas volume and average flue gas content, the cumulative CO volume and average CO content, the cumulative CO2 volume and average CO2 content and process parameters in each time step segment are used as model input variables, and the actual decarbonization amount in each time step segment is used as the model output variable. The machine learning algorithm is used for weight extraction and feature selection, and a prediction model is constructed. S4. Real-time collection of production data of the current RH refining furnace. After each time step, the cumulative decarburization amount, cumulative flue gas amount and average flue gas content, cumulative CO amount and average CO content, cumulative CO2 amount and average CO2 content within the time step are calculated; the model input variables are substituted into the prediction model, and the actual decarburization amount prediction results within each time step segment are output; combined with the initial carbon content of the current furnace, the real-time prediction of the carbon content of the molten steel is realized.

2. The method for real-time prediction of carbon content in RH refined steel liquid based on machine learning according to claim 1, characterized in that: In step S1, the following situations are determined as abnormal heats: 1) adding carbon powder during the production process; 2) adding scrap steel to adjust the temperature; 3) abnormal signal collection; 4) abnormal detection results.

3. The method for real-time prediction of carbon content in RH refined steel liquid based on machine learning according to claim 1, characterized in that: In step S1, the lower limit of the time step should be set greater than the time interval for collecting flue gas data.

4. The method for real-time prediction of carbon content in RH refined steel liquid based on machine learning according to claim 1, characterized in that: In step S1, the cumulative decarburization amount in each time step is calculated as follows: Where, ΔC i Indicates the cumulative decarburization amount within the time step, ppm; Q gas Indicates flue gas flow rate, kg / h; Indicates the percentage content of CO in flue gas, %; Indicates the percentage content of CO2 in flue gas, %; M C represents the relative atomic mass of C; M CO represents the relative atomic mass of CO; represents the relative atomic mass of CO2; t represents time, s; W steel Indicates the weight of molten steel, kg.

5. The method for real-time prediction of carbon content in RH refined steel liquid based on machine learning according to claim 1, characterized in that: In step S1, the cumulative smoke volume and average smoke content, the cumulative CO volume and average CO content, the cumulative CO2 volume and average CO2 content in each time step segment are calculated as follows: 烟气累积 =∫Q gas dt m 烟气平均 =∫Q gas dt / t 6. The method for real-time prediction of carbon content in RH refined steel liquid based on machine learning according to claim 1, characterized in that: In step S1, the flue gas correction coefficient is calculated as follows: Where W is the flue gas correction factor; C is the carbon content at the inbound station, ppm; C′ is the carbon content at the outbound station, ppm; ∫ΔC i Indicates the cumulative decarbonization amount of flue gas during the smelting time.

7. The method for real-time prediction of carbon content in RH refined steel liquid based on machine learning according to claim 1, characterized in that: In step S1, the actual decarburization amount in each time step is calculated as ΔC i ′=W·ΔC i .

8. The method for real-time prediction of carbon content in RH refined steel liquid based on machine learning according to claim 1, characterized in that: In step S2, the process parameters related to decarburization in the RH refining production data include molten steel volume, carbon content at the station, oxygen activity at the station, vacuum chamber life, immersion tube life, station temperature, slag layer thickness, and decarburization time.

9. The method for real-time prediction of carbon content in RH refined steel liquid based on machine learning according to claim 1, characterized in that: In step S3, if there is a delay in the generation of on-site flue gas data, the real-time prediction result of the carbon content of the molten steel should take the delay time into consideration.

10. A real-time prediction system for carbon content in RH refined steel liquid based on machine learning, used to implement the prediction method according to any one of claims 1 to 9, comprising: Model database construction module: collects the production data of historical RH refining furnaces, screens and pre-processes abnormal furnaces, processes the flue gas time series data of each historical furnace, and constructs a model database for modeling; Prediction model building module: Determine the input variables and output variables of the model, and build a prediction model for the actual decarbonization amount in each time step through machine learning algorithms; Real-time prediction module for carbon content in molten steel: Based on the collected real-time furnace production data, the model outputs the prediction results of the actual decarburization amount in each time step to achieve real-time prediction of the carbon content in molten steel.

Images