Non-oriented silicon steel performance stability control method based on prediction model

Abstract

The invention discloses a non-oriented silicon steel performance stability control method based on a prediction model, and the method comprises the steps: extracting the process actual performance of a completed process and the process setting data of an uncompleted process through an established non-oriented silicon steel performance prediction model, substituting the data into the performance prediction model, and predicting the performance of the non-oriented silicon steel. And dynamically adjusting the process parameters of the non-oriented silicon steel according to the performance prediction value calculated by the performance prediction model, so that the performance meets the contract requirement and is stabilized near the target value of the internal control requirement. According to the method, stability control over the performance of the non-oriented silicon steel is achieved, and the qualification rate and the performance stability of non-oriented silicon steel products are improved.

Description

Technical Field

[0001] The present invention relates to the production process control technology of non-oriented electrical steel products in iron and steel metallurgy, and more specifically, to a method for controlling the performance stability of non-oriented electrical steel based on a prediction model. Background Art

[0002] Cold-rolled non-oriented electrical steel is a soft magnetic material and is the alloy material with the largest consumption in magnetic materials, occupying a very important position in the electric power, electronics, and military industries. With the continuous enhancement of the global awareness of energy conservation and emission reduction, the development trend is towards thin gauges, low iron loss, high magnetic induction, and high mechanical properties, and the market potential is huge.

[0003] The product performance is always the most important indicator for evaluating product quality and is the lifeline of whether the product has market competitiveness. Currently, major steel mills are conducting in-depth research on how to improve product performance, maintain performance stability, and reduce variation. Now, with the rapid development of computer technology, big data has been applied in various industries. The steel industry can use a large amount of data stored in various links such as production management for quality management, process optimization, and process improvement, which can effectively improve enterprise productivity and efficiency, optimize the business decision-making process, and make the enterprise more competitive, creative, vital, and intelligent in the steel market.

[0004] The process route of non-oriented electrical steel is relatively long, there are many grades, and the corresponding relationship between the tapping mark and the grade is complex. Due to different requirements, the production process is also very complex. Currently, the performance is detected by off-line sampling after annealing. There is an obvious lag in quality management. For unqualified steel coils, no effective remedy can be obtained, and the product performance obtained has a large difference and poor stability.

[0005] Therefore, it is necessary to consider establishing a performance prediction model through historical data, predicting the performance before important production processes, and combining the prediction results to modify the design values of process parameters so that the prediction results are close to the internal control target value, that is, the historical mean, thereby reducing product losses, improving product performance and performance stability, and greatly improving work efficiency and liberating the manual workload.

[0006] In the field of research on the properties of non-oriented electrical steel, the focus is mainly on the analysis of the effects of alloying elements, annealing processes, etc. on properties. Common modeling ideas include statistical learning method modeling (methods such as regression analysis and principal component analysis), mechanism modeling based on metallurgical principles, etc. For example, invention patent CN103823974A discloses a principal component regression analysis method for factors affecting the properties of non-oriented electrical steel. Using this method, the influence laws of inclusions, texture, and grain size on the properties of non-oriented electrical steel can be comprehensively studied, and the factors significantly affecting the properties can be found. For example, invention patent CN103823975A discloses a principal component regression analysis method for the influence of texture components on the magnetic induction of non-oriented electrical steel. Using this method, the influence laws of different texture components on the magnetic induction of non-oriented electrical steel can be quantitatively studied, and the texture components significantly affecting the magnetic induction can be found, providing directional guidance for the actual production of non-oriented electrical steel products with excellent properties. For example, invention patent CN114139350A discloses an iron loss prediction method for optimizing the continuous annealing process of non-oriented electrical steel. By substituting the composition and process parameters into the regression equation of the established prediction model, the iron loss prediction value can be obtained, and adjustments can be made for situations that do not meet the target range. Through this model, the product quality can be improved. For example, invention patent CN109252101B discloses a method for improving the properties of non-oriented electrical steel. By controlling the finish rolling temperature according to the phase transformation temperature of the steel, the internal tissue state of the hot rolled sheet is regulated to obtain lower deformation energy storage. Coarse grains are obtained through high-temperature coiling, so that the strength of the favorable texture of the finished sheet is increased, and the strength of the unfavorable texture is decreased, achieving a significant improvement in the grain size and properties of the finished sheet.

[0007] Generally speaking, there are relatively many studies on the factors affecting the properties of non-oriented electrical steel, especially on the tissue composition; in addition, there are also relatively many studies on how to improve the properties; however, these studies mainly focus on experimental studies under specific processes or grades, and tend to focus on mechanism studies such as texture and grains, and there is almost no involvement in the research on the full-process process performance prediction model and stability control of non-oriented electrical steel. Summary of the Invention

[0008] Aiming at the defects existing in the prior art, the purpose of the present invention is to provide a method for controlling the performance stability of non-oriented electrical steel based on a prediction model, realizing the stability control of the performance of non-oriented electrical steel, and improving the qualification rate and performance stability of non-oriented electrical steel products.

[0009] To achieve the above purpose, the present invention adopts the following technical solutions:

[0010] A method for controlling the performance stability of non-oriented electrical steel based on a prediction model:

[0011] Through the established performance prediction model for the properties of non-oriented electrical steel, extract the process actual performance of the completed processes and the process setting data of the uncompleted processes, substitute them into the performance prediction model, and predict the properties of the non-oriented electrical steel; and dynamically adjust the process parameters of the non-oriented electrical steel according to the performance prediction values calculated by the performance prediction model, so that the performance meets the contract requirements and is stabilized near the target value required by the internal control.

[0012] Preferably, the method for controlling the performance stability of the non-oriented electrical steel specifically includes the following steps:

[0013] S1. Before the production plan of hot rolling / normalizing annealing / SACL annealing is issued, retrieve the steelmaking composition data, steelmaking process parameters, hot rolling process parameters, hot rolling process thresholds, normalizing process parameters, normalizing process thresholds, SACL process parameters, SACL process thresholds, contract performance requirements, internal control requirements, and specification parameters;

[0014] S2. Substitute the parameters in step S1 into the performance prediction model to predict the performance of the non-oriented electrical steel planned to be produced;

[0015] S3. Combine the contract performance requirements and the internal control requirements to determine whether the predicted performance of the non-oriented electrical steel is qualified;

[0016] S4. For the steel coils whose performance does not meet the quality requirements, establish an objective function and constraint conditions in combination with the threshold range of the process parameters, and optimize the process parameters;

[0017] S5. For the steel coils with successful optimization, produce them according to the optimized process parameters; for the steel coils with failed optimization, produce them according to the boundary values of the recommended process parameters.

[0018] Preferably, in step S1, the steelmaking composition data includes elements such as Si, Al, Mn, P, Ti, S, C, N, Nb, and V;

[0019] The steelmaking process parameters include the ladle slag thickness and the free oxygen at the end of decarburization;

[0020] The hot rolling process parameters include the furnace inlet temperature, residence time in the furnace, furnace outlet temperature, rough rolling temperature, finish rolling temperature, and coiling temperature;

[0021] The hot rolling process thresholds include the upper and lower limits of the hot rolling process parameters;

[0022] The normalizing process parameters include the soaking section furnace temperature and the heating section furnace temperature;

[0023] The normalizing process thresholds include the upper and lower limits of the normalizing process parameters;

[0024] The SACL process parameters include annealing speed, soaking furnace temperature in the annealing process, heating furnace temperature in the annealing process, and annealing furnace tension;

[0025] The SACL process thresholds include the upper and lower limits of the SACL process parameters;

[0026] The specification parameters include strip thickness and width;

[0027] The contract performance requirements include the minimum magnetic induction requirement and the maximum iron loss requirement for product delivery; and / or the minimum and maximum iron loss requirements for product delivery;

[0028] The internal control requirements include the internal control requirements for the performance in actual production, that is, the upper and lower limits and the target values of the performance indicators.

[0029] Preferably, in step S1, before the hot rolling rolling plan is issued, the steelmaking composition data and the steelmaking process parameters retrieved are the actual production values; the hot rolling process parameters, the normalizing process parameters, and the SACL process parameters are the process set values;

[0030] Before the normalizing annealing plan is issued, the steelmaking composition data, the steelmaking process parameters, and the hot rolling process parameters retrieved are the actual production values; the normalizing process parameters and the SACL process parameters are the process set values;

[0031] Before the SACL annealing plan is issued, the steelmaking composition data, the steelmaking process parameters, the hot rolling process parameters, and the normalizing process parameters retrieved are the actual production values; the SACL process parameters are the process set values.

[0032] Preferably, in step S1, the hot rolling process thresholds, the normalizing process thresholds, and the SACL process thresholds are customized according to the steel grade type and grade type conditions of non-oriented silicon steel;

[0033] The contract performance requirements are the release requirements formulated by the user and are determined according to different user needs;

[0034] The internal control requirements are the performance control requirements formed based on long-term actual production and are stricter than the contract performance requirements.

[0035] Preferably, the performance prediction values calculated by the performance prediction model include the iron loss and magnetic induction of non-oriented silicon steel.

[0036] Preferably, the determination of whether the performance of the predicted non-oriented silicon steel is qualified in step S3 specifically includes:

[0037] Judgment is made by calculating the probability that the performance prediction value meets the upper and lower limit requirements of the performance, and a probability of ±2σ is selected for judgment.

[0038] Preferably, the optimization of process parameters in step S4 specifically includes:

[0039] When performing optimization adjustment calculation of process parameters, it is necessary to comprehensively determine the optimization objective function based on multiple performance prediction values and the target value, and determine the constraint conditions based on multiple performance prediction values, as well as the hot rolling process threshold, normalizing process threshold, and SACL process threshold. An optimization algorithm is used to solve the objective function to obtain the optimal process parameter values.

[0040] Preferably, for the steel coils with optimization failure in step S5, the production according to the boundary values of the recommended process parameters specifically includes:

[0041] For the steel coils with optimization failure, that is, the steel coils for which the objective function has no solution within the constrained range, the process parameter optimization will also give a set of boundary values of process parameters to make the predicted performance closest to the target value. At this time, production is carried out according to the boundary values of these process parameters.

[0042] Preferably, the calculation of the performance prediction model is as follows:

[0043] TS = f1(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, NOF, SF, HS, SS, Speed, Thick);

[0044] CG = f2(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, NOF, SF, HS, SS, Speed, Thick);

[0045] Among them, TS and CG are the performance indicators iron loss and magnetic induction respectively;

[0046] Among them, Si, Al, Mn, P, Ti, S, C, N respectively represent the contents of silicon element, aluminum element, manganese element, phosphorus element, titanium element, sulfur element, carbon element, and nitrogen element;

[0047] Among them, FRN, FT, CT, NOF, SF, HS, SS, Speed, Thick respectively represent the tapping temperature, finish rolling temperature, coiling temperature, normalizing annealing heating section furnace temperature, normalizing annealing soaking section furnace temperature, SACL continuous annealing furnace heating section high temperature zone furnace temperature, SACL continuous annealing furnace soaking section furnace temperature, annealing speed, and SACL outlet thickness.

[0048] A method for controlling the performance stability of non-oriented silicon steel based on a prediction model provided by the present invention enables the performance to meet the contract requirements and stabilizes it near the target value of the internal control requirements. The technology of the present invention is based on a performance prediction model of non-oriented silicon steel, dynamically adjusts process parameters, realizes the stability control of the performance of non-oriented silicon steel, and can improve the qualification rate of non-oriented silicon steel products and the stability of performance. The production lines and steel grades covered by this control method are wide, and it can be widely applied to the field of performance control of non-oriented silicon steel. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a schematic flow chart of the method for controlling the performance stability of non-oriented silicon steel of the present invention;

[0050] Figure 2 is a schematic flow chart of Embodiment 1 of the method for controlling the performance stability of non-oriented silicon steel of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0051] In order to better understand the above technical solutions of the present invention, the technical solutions of the present invention will be further described below with reference to the drawings and embodiments.

[0052] A method for controlling the performance stability of non-oriented silicon steel based on a prediction model provided by the present invention:

[0053] By establishing a performance prediction model for the performance of non-oriented silicon steel, retrieving steelmaking composition data, steelmaking process parameters, hot rolling process parameters, hot rolling process thresholds, normalizing process parameters, normalizing process thresholds, SACL process parameters, SACL process thresholds, contract performance requirements, internal control requirements, and specification parameters, substituting them into the performance prediction model, and predicting the performance of non-oriented silicon steel; within the temperature adjustment range allowed by metallurgical mechanism, dynamically adjusting the performance indexes of non-oriented silicon steel according to the performance prediction values calculated by the performance prediction model, so that the performance meets the contract requirements and stabilizes near the target value of the internal control requirements, and improving the performance stability.

[0054] Combined with Figure 1 shown, the method for controlling the performance stability of non-oriented silicon steel of the present invention specifically includes the following steps:

[0055] S1. Before the production plan of hot rolling / normalizing annealing / SACL annealing (referred to as SACL) is issued, retrieve steelmaking composition data, steelmaking process parameters, hot rolling process parameters, hot rolling process thresholds, normalizing process parameters, normalizing process thresholds, SACL process parameters, SACL process thresholds, contract performance requirements, internal control requirements, and specification parameters;

[0056] S2. Substitute the parameters in step S1 into the performance prediction model to predict the performance of the non-oriented silicon steel planned to be produced;

[0057] S3. Compare the predicted values of the performance with the contract performance requirements and internal control requirements to determine whether the performance of the predicted non-oriented silicon steel is qualified;

[0058] S4. For the steel coils whose performance does not meet the quality requirements, establish the objective function and constraint conditions in combination with the threshold range of the process parameters, and optimize the process parameters;

[0059] S5. For the steel coils with successful optimization, produce them according to the optimized process parameters; for the steel coils with failed optimization, produce them according to the boundary values of the recommended process parameters.

[0060] In the above step S1, the steelmaking composition data includes elements such as Si, Al, Mn, P, Ti, S, C, N, Nb, and V;

[0061] The steelmaking process parameters include the ladle slag thickness and the free oxygen at the end of decarburization;

[0062] The hot rolling process parameters include the furnace inlet temperature, the time in the furnace, the furnace outlet temperature, the rough rolling temperature, the finish rolling temperature, and the coiling temperature;

[0063] The hot rolling process thresholds include the upper and lower limits of the hot rolling process parameters;

[0064] The normalizing process parameters include the soaking section furnace temperature and the heating section furnace temperature;

[0065] The normalizing process thresholds include the upper and lower limits of the normalizing process parameters;

[0066] The SACL process parameters include the annealing speed, the soaking section furnace temperature of annealing, the heating section furnace temperature of annealing, and the annealing furnace tension;

[0067] The SACL process thresholds include the upper and lower limits of the SACL process parameters;

[0068] The specification parameters include the strip thickness and width;

[0069] The contract performance requirements include the minimum magnetic induction requirement and the maximum iron loss requirement for product delivery; and / or the minimum and maximum iron loss requirements for product delivery;

[0070] The internal control requirements include the internal control requirements for the performance of actual production, that is, the upper and lower limits and the target values of the performance indicators.

[0071] In the above step S1, before the hot rolling rolling plan is issued, the retrieved steelmaking composition data and steelmaking process parameters are the actual production values; the hot rolling process parameters, normalizing process parameters, and SACL process parameters are the process set values;

[0072] Before the normalizing annealing plan is issued, the retrieved steelmaking composition data, steelmaking process parameters, and hot rolling process parameters are the actual production values; the normalizing process parameters and SACL process parameters are the process set values;

[0073] Before the SACL annealing plan is issued, the steelmaking composition data, steelmaking process parameters, hot rolling process parameters, and normalizing process parameters retrieved are the actual production values; the SACL process parameters are the process set values.

[0074] In the above step S1, the hot rolling process threshold, normalizing process threshold, and SACL process threshold are customized according to the steel grade type and grade type conditions of non-oriented electrical steel.

[0075] The contract performance requirements are the release requirements formulated by the user and are determined according to different user needs.

[0076] The internal control requirements are the performance control requirements formed based on long-term actual production and are stricter than the contract performance requirements.

[0077] In the above step S2, the performance prediction values calculated by the performance prediction model include the iron loss (such as P15 / 50, P10 / 400) and magnetic induction (such as B50) of non-oriented electrical steel.

[0078] In the above step S3, the determination of whether the performance of the predicted non-oriented electrical steel is qualified specifically includes:

[0079] Judgment is made by calculating the probability that the performance prediction value meets the upper and lower limit requirements of the performance, and the probability of ±2σ is selected for judgment.

[0080] In the above step S4, the optimization of process parameters specifically includes:

[0081] When calculating the optimization adjustment of process parameters, it is necessary to comprehensively determine the optimization objective function based on multiple performance prediction values and target values, and determine the constraint conditions based on multiple performance prediction values as well as the hot rolling process threshold, normalizing process threshold, and SACL process threshold. An optimization algorithm is used to solve the objective function to obtain the optimal process parameter values.

[0082] In the above step S5, for the steel coils with optimization failure, the production according to the boundary values of the recommended process parameters specifically includes:

[0083] For the steel coils with optimization failure, that is, the steel coils for which the objective function has no solution within the constrained range, the process parameter optimization will also give a set of boundary values of the process parameters to make the predicted performance closest to the target value. At this time, production is carried out according to the boundary values of these process parameters.

[0084] Example 1

[0085] Combined with Figure 2As shown in the figure, this embodiment provides a method for controlling the performance stability of non-oriented silicon steel based on a prediction model. By combining the actual process performance or process design data of processes such as steelmaking, hot rolling, normalizing, and SACL, dynamic adjustment of the performance indicators of non-oriented silicon steel products is carried out based on the performance prediction model to improve performance stability. The method includes the following steps:

[0086] S1. Before the hot rolling rolling plan is issued, retrieve the steelmaking composition and actual process performance values, hot rolling process parameter setting values, hot rolling process thresholds, normalizing process setting values, SACL process parameter setting values, performance contract requirement values, internal control requirement values, specification parameters, etc.; among them, the steelmaking composition data includes elements such as Si, Al, Mn, P, Ti, S, C, N, Nb, V, etc.; the steelmaking process parameters include ladle slag thickness, free oxygen at the end of decarburization, etc.; the hot rolling process parameters include furnace inlet temperature, residence time in the furnace, furnace outlet temperature, rough rolling temperature, finish rolling temperature, coiling temperature, etc.; the hot rolling process thresholds include the upper and lower limits of the hot rolling process parameters; the normalizing process setting values include furnace temperature in the heating section, furnace temperature in the soaking section, etc.; the SACL process parameters include annealing speed, annealing soaking section furnace temperature, annealing heating section furnace temperature, annealing furnace tension, etc.; the specification parameters include strip thickness and width; the contract performance requirements include the minimum value of magnetic induction and the maximum value of iron loss; the internal control requirements refer to the control requirements for actual production, including the upper and lower limits and target values (i.e., historical average values) of performance indicators.

[0087] The hot rolling process thresholds are configured individually according to conditions such as the steel grade type and grade type of non-oriented silicon steel; the contract performance is determined according to different user requirements.

[0088] S2. Substitute the above data into the performance prediction model to predict the performance of the non-oriented silicon steel to be rolled in the hot rolling process. The predicted performance indicators include iron loss and magnetic induction, etc.

[0089] S3. Combine the contract performance requirements and internal control requirements to determine whether the predicted performance is qualified.

[0090] Since there may be a certain deviation between the model prediction value and the actual value of the performance, when using the predicted value of the performance to determine whether the performance is qualified, it is not directly judged whether the predicted performance is qualified according to the upper and lower limits, but by calculating the probability that the predicted value meets the requirements of the performance upper and lower limits to make a judgment, and the probability of ±2σ (i.e., 0.9545) is selected to judge whether the predicted performance is qualified.

[0091] S4. For the steel coils that do not meet the performance requirements, optimize the process parameters. In order to make multiple final performance indicators meet the contract performance requirements and simultaneously approach the performance target values required by internal control, based on the predicted values and target values, combined with the performance prediction model and the thresholds of hot rolling process parameters, establish an optimization objective function and constraint conditions, and use optimization algorithms such as the gradient descent method to solve, so that the value of the objective function is minimized, thereby obtaining the optimal values of the hot rolling process parameters.

[0092] S5. For the coils with successful optimization, carry out hot rolling production according to the new process; for the coils with failed optimization, carry out hot rolling production according to the hot rolling process boundary values recommended by the optimization model.

[0093] S6. After the hot rolling is completed, for the steel coils that have undergone the normalizing process, retrieve the steelmaking composition and actual process values, actual hot rolling process parameter values, normalizing process parameter setting values, normalizing process thresholds, SACL process parameter setting values, performance contract requirement values, internal control requirement values, specification parameters, etc.; for the steel coils that do not undergo the normalizing process, jump to step S11, that is, directly carry out SACL dynamic quality design.

[0094] Among them, the normalizing process parameters include the soaking furnace temperature in the normalizing annealing and the heating furnace temperature in the normalizing annealing, etc.; the normalizing process thresholds include the upper and lower limits of the normalizing process parameters.

[0095] The normalizing process thresholds are personalized configured according to conditions such as the steel type and grade type of the steel coil.

[0096] S7. Substitute the above data into the performance prediction model to predict the performance of non-oriented silicon steel planned for normalizing annealing. The predicted performance indicators include iron loss, magnetic induction, etc.

[0097] S8. Combine the contract performance requirements and internal control requirements to determine whether the predicted performance is qualified.

[0098] S9. For the steel coils that do not meet the performance requirements, optimize the process parameters. In order to make multiple final performance indicators meet the contract performance requirements and simultaneously approach the performance target values required by internal control, based on the predicted values and target values, combined with the performance prediction model and the thresholds of the normalizing process parameters, establish an optimization objective function and constraint conditions, and use optimization algorithms such as the gradient descent method to solve, so that the value of the objective function is minimized, thereby obtaining the optimal values of the normalizing process parameters.

[0099] S10. For the coils with successful optimization, carry out normalizing production according to the new process; for the coils with failed optimization, carry out normalizing production according to the normalizing process boundary values recommended by the optimization model.

[0100] S11. After the normalization production is completed, retrieve the steelmaking composition and process actual values, hot rolling process parameter actual values, normalization process parameter actual values (the normalization process parameters of coils not undergoing normalization are not retrieved), SACL process parameter set values, SACL process thresholds, performance contract requirement values, internal control requirement values, specification parameters, etc.; among them, the SACL process parameters include annealing speed, annealing soaking section temperature, annealing heating section temperature, etc.

[0101] The SACL process thresholds include the upper and lower limits of the SACL process parameters.

[0102] The SACL process thresholds are personalized configured according to conditions such as the steel grade type and brand type of the coil.

[0103] S12. Substitute the above data into the performance prediction model to predict the properties of non-oriented silicon steel planned for SACL annealing. The predicted performance indicators include iron loss, magnetic induction, etc.

[0104] S13. Combine the contract performance requirements and internal control requirements to determine whether the predicted performance is qualified.

[0105] S14. For coils with unqualified performance requirements, optimize the process parameters; in order to make multiple final performance indicators meet the contract performance requirements and at the same time be close to the performance target values of the internal control requirements, based on the predicted values and target values, combine the performance prediction model and the thresholds of the SACL process parameters to establish an optimization objective function and constraint conditions, and use optimization algorithms such as the gradient descent method to solve, so that the objective function value is minimized, thereby obtaining the optimal values of the SACL process parameters.

[0106] S15. For coils with successful optimization, perform SACL production according to the new process; for coils with failed optimization, perform SACL production according to the SACL process boundary values recommended by the optimization model.

[0107] Example 2

[0108] This Example 2 relates to the full-process production process of non-oriented silicon steel products of a certain steel plant, and selects the coils produced by a certain production line as a case for illustration.

[0109] The performance prediction model selected in this Example 2 is as follows:

[0110] TS = f1(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, NOF, SF, HS, SS, Speed, Thick);

[0111] CG = f2(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, NOF, SF, HS, SS, Speed, Thick);

[0112] Among them, TS and CG are the performance indicators of iron loss and magnetic induction respectively;

[0113] Among them, Si, Al, Mn, P, Ti, S, C, and N represent the content of silicon element, aluminum element, manganese element, phosphorus element, titanium element, sulfur element, carbon element, and nitrogen element respectively;

[0114] Among them, FRN, FT, CT, NOF, SF, HS, SS, Speed, and Thick represent the tapping temperature, finish rolling temperature, coiling temperature, furnace temperature in the heating section of normalizing annealing, furnace temperature in the soaking section of normalizing annealing, high-temperature zone furnace temperature in the heating section of SACL continuous annealing furnace, furnace temperature in the soaking section of SACL continuous annealing furnace, annealing speed, and SACL exit thickness respectively.

[0115] The actual measured content of the steelmaking chemical composition of a selected non-oriented silicon steel coil 1 is as follows in the table:

[0116] Si_ACT AL_ACT Mn_ACT P_ACT 0.914％ 0.4044％ a1％ b1％ Ti_ACT S_ACT C_ACT N_ACT c1％ d1％ e1％ f1％

[0117] The design values and process range requirements of the hot rolling process of coil 1 are as follows:

[0118] FRN_AIM FT_AIM CT_AIM T_frn_aim1 T_ft_aim1 T_ct_aim1 FRN_MAX FT_MAX CT_MAX T_frn_max1 T_ft_max1 T_ct_max1 FRN_MIN FT_MIN CT_MIN T_frn_min1 T_ft_min1 T_ct_min1

[0119] The production of coil 1 does not go through normalizing, so the normalizing process parameters are not listed.

[0120] The design values and process range requirements of the SACL process of coil 1 are as follows:

[0121] HS_AIM T_hs_aim1 HS_MIN T_hs_min1 HS_MAX T_hs_max1 SS_AIM T_ss_aim1 SS_MIN T_ss_min1 SS_MAX T_ss_max1

[0122] The contract performance requirement range of coil 1 is as follows:

[0123] Iron loss TS TS ≤ 5.10 Magnetic induction CG CG ≥ 1.72

[0124] The internal control requirement range of coil 1 is as follows:

[0125] TS_AIM 4.90 TS_MIN 4.70 TS_MAX 5.10 CG_AIM 1.735 CG_MIN 1.730 CG_MAX 1.740

[0126] The target value of the finished thickness of coil 1 is 0.50 mm, and the target value of the SACL central section speed is vl m / min.

[0127] The internal control requirements are within the contract requirements, so only the internal control requirements need to be considered.

[0128] 1) Adjustment of hot rolling process parameters

[0129] Before the hot rolling production plan, input data such as the actual values of steelmaking components, hot rolling process target values, SACL process target values, and finished product thickness target values into the performance prediction model to calculate the target values of iron loss and magnetic induction indicators. The prediction results of the model are as follows:

[0130] Predicted value of iron loss P_TS Predicted value of magnetic induction P_CG 5.065854 1.727022 Standard deviation of iron loss TS_STD Standard deviation of magnetic induction CG_STD 0.088406 0.007386

[0131] Since the predicted value of magnetic induction performance P_CG = 1.727022, which is greater than the contract requirement value of 1.72 but less than the minimum value of 1.730 required by internal control, it does not meet the internal control requirements. Therefore, it is necessary to optimize the hot rolling process parameters and adjust the process parameter values.

[0132] To stabilize the final performance near the target value, establish an optimization objective function for iron loss and magnetic induction:

[0133] Delta_TS=(P_TS - TS_AIM)^2

[0134] Delta_CG=(P_CG - CG_AIM)^2

[0135] LOSS = Delta_TS + m * Delta_CG

[0136] Among them, m is the coefficient for balancing the weights of iron loss and magnetic induction, which is determined by the specific steel grade; when LOSS is smaller, the comprehensive index of iron loss and magnetic induction is closer to the target value.

[0137] Based on the relationship between hot rolling process parameters and performance indicators, as well as the thresholds of hot rolling process parameters and performance indicators, determine the constraint conditions:

[0138] (1)TS = f1(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, HS, SS, Speed, Thick);

[0139] (2)CG = f2(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, HS, SS, Speed, Thick);

[0140] (3)FRN_MIN <= FRN <= FRN_MAX;

[0141] (4)FT_MIN <= FT <= FT_MAX;

[0142] (5)CT_MIN <= CT <= CT_MAX;

[0143] (6)TS_MIN <= TS <= TS_MAX;

[0144] (7) CG_MIN <= CG <= CG_MAX.

[0145] And due to the requirements of process settings, the temperature value needs to be in increments of 5°C. Therefore, the calculated adjusted temperature needs to be rounded to the nearest 5°C.

[0146] Using the gradient descent method to solve this optimization problem, the optimal design values of the three temperatures are obtained:

[0147] FRN = frn_c1

[0148] FT = ft_c1

[0149] CT = ct_c1

[0150] Substitute the new hot rolling process temperature into the performance prediction model, and the new predicted performance can be calculated as follows:

[0151] Predicted value of iron loss P_TS Predicted value of magnetic induction P_CG 4.914160 1.735050 Standard deviation of iron loss TS_STD Standard deviation of magnetic induction CG_STD 0.000442 0.000052

[0152] The predicted performance values of the optimized iron loss and magnetic induction both meet the internal control requirements. However, since there may be a certain deviation between the model predicted values and the actual values of the performance, when using the predicted values of the performance to determine whether the performance is qualified, it is not directly judged according to the upper and lower limits whether the predicted performance is qualified, but by calculating the probability that the predicted value meets the requirements of the performance upper and lower limits to make a judgment. The probability of ±2σ (i.e., 0.9545) is selected to judge whether the predicted performance is qualified.

[0153] The qualification rate formula is as follows:

[0154] CDF_Y = CDF('NORMAL', (Y_MAX - P_Y) / Y_STD) - CDF('NORMAL', (Y_MIN - P_Y) / Y_STD)

[0155] Among them, Y represents the performance index, which can be TS, CG;

[0156] Y_MAX, Y_MIN, P_Y, and Y_STD respectively represent the performance maximum value, performance minimum value, performance predicted value, and performance prediction standard deviation.

[0157] Substitute the performance requirements and performance predicted values, and calculate the qualification rates of different performance indicators:

[0158] CDF_TS = 0.9999; CDF_CG = 0.9999;

[0159] Both CDF_TS and CDF_CG are greater than 0.9545. Therefore, the hot rolling process optimization is successful, and the hot rolling process is produced according to the new process.

[0160] Adjusted tapping temperature Adjusted finishing rolling temperature Adjusted coiling temperature frn_c1 ft_c1 ct_c1

[0161] 2) Adjustment of SACL Process Parameters

[0162] (Since the steel coil 1 does not go through normalizing, the dynamic quality design of the normalizing process is not carried out.) After the hot rolling process is completed, retrieve the actual hot rolling temperature:

[0163] Tapping temperature Finishing rolling temperature Coiling temperature frn_r1 ft_r1 ct_r1

[0164] Because this steel coil does not go through normalizing, it directly proceeds to SACL production.

[0165] Before issuing the SACL plan, input data such as steelmaking composition, hot rolling process, SACL process target values, finished product thickness target values, etc. into the magnetic property prediction model, and calculate the predicted values of indicators such as iron loss and magnetic induction as follows:

[0166] Predicted value of iron loss P_TS Predicted value of magnetic induction P_CG 4.955841 1.734056 Standard deviation of iron loss TS_STD Standard deviation of magnetic induction CG_STD 0.088831 0.001162

[0167] Substitute the performance requirements and performance predicted values, and calculate the qualified rates of different performance indicators:

[0168] CDF_TS = 0.9457; CDF_CG = 0.9999;

[0169] Since CDF_TS is slightly less than 0.9545, that is, under the probability of ±2σ, the iron loss may not meet the internal control requirements of the performance. Therefore, it is necessary to optimize the SACL process parameters and adjust the SACL annealing temperature.

[0170] In order to make the final performance stable near the target value, similarly establish an optimization objective function for iron loss and magnetic induction to adjust the annealing temperature of the heating section and soaking section of SACL, and obtain the following optimization equations:

[0171] Delta_TS = (P_TS - TS_AIM)^2

[0172] Delta_CG = (P_CG - CG_AIM)^2

[0173] LOSS = Delta_TS + m * Delta_CG

[0174] Constraint conditions:

[0175] (1) TS = f1(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, HS, SS, Speed, Thick);

[0176] (2) CG = f2(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, HS, SS, Speed, Thick);

[0177] (3) HS_MIN <= HS <= HS_MAX;

[0178] (4) SS_MIN <= SS <= SS_MAX;

[0179] (5) TS_MIN <= TS <= TS_MAX;

[0180] (6) CG_MIN <= CG <= CG_MAX.

[0181] Solve this optimization problem using the gradient descent method to obtain the optimal design values of the two furnace temperatures:

[0182] HS = hs_c1

[0183] SS = ss_c1

[0184] Substitute the new SACL process temperature into the performance prediction model, and the new predicted performance can be calculated as follows:

[0185] Predicted value of iron loss P_TS Predicted value of magnetic induction P_CG 4.89968 1.735032 Standard deviation of iron loss TS_STD Standard deviation of magnetic induction CG_STD 0.0106249 0.000134

[0186] Substitute the performance requirements and performance prediction values, and calculate the qualified rates of different performance indicators:

[0187] Calculate CDF_TS = 0.9999; CDF_CG = 0.9999

[0188] Both CDF_TS and CDF_CG are greater than 0.9545, that is, both performance indicators are qualified after optimizing and adjusting the SACL process temperature. Therefore, the SACL process optimization is successful, and the SACL process is produced according to the new process.

[0189] Adjusted temperature of SACL heating section Adjusted temperature of SACL soaking section hs_c1 ss_c1

[0190] Example 3

[0191] The actual chemical composition content of a selected non-oriented steel coil 2 in this Example 3 is as follows:

[0192] Si_ACT AL_ACT Mn_ACT P_ACT 2.796％ 1.0384％ a2％ b2％ Ti_ACT S_ACT C_ACT N_ACT c2％ d2％ e2％ f2％

[0193] The hot rolling process design values and process range requirements of steel coil 2 are as follows:

[0194] FRN_AIM FT_AIM CT_AIM T_frn_aim2 T_ft_aim2 T_ct_aim2 FRN_MAX FT_MAX CT_MAX T_frn_max2 T_ft_max2 T_ct_max2 FRN_MIN FT_MIN CT_MIN T_frn_min2 T_ft_min2 T_ct_min2

[0195] Steel coil 2 is normalized. The normalization process design values and process range requirements of steel coil 2 are as follows:

[0196] NOF_AIM T_nof_aim2 NOF_MIN T_nof_min2 NOF_MAX T_nof_max2 SF_AIM T_sf_aim2 SF_MIN T_sf_min2 SF_MAX T_sf_max2

[0197] The SACL process design values and process range requirements for Coil 2 are as follows:

[0198] HS_AIM T_hs_aim2 HS_MIN T_hs_min2 HS_MAX T_hs_max2 SS_AIM T_ss_aim2 SS_MIN T_ss_min2 SS_MAX T_ss_max2

[0199] The contract performance requirement range for Coil 2 is as follows:

[0200] Iron loss TS TS ≤ 2.30 Magnetic induction CG CG ≥ 1.62

[0201] The internal control requirement range for Coil 2 is as follows:

[0202] TS_AIM 2.17 TS_MIN 2.02 TS_MAX 2.28 CG_AIM 1.67 CG_MIN 1.65 CG_MAX 1.69

[0203] The target value of the finished thickness of Coil 2 is 0.30 mm, and the target value of the SACL central section speed is v2 m / min.

[0204] The internal control requirements are within the contract range requirements, so only the internal control requirements need to be considered.

[0205] 1) Adjustment of hot rolling process parameters

[0206] Before the hot rolling rolling plan, input data such as the actual value of the steelmaking composition, the hot rolling process target value, the SACL process target value, and the target value of the finished thickness into the magnetic property prediction model to calculate the target values of the iron loss and magnetic induction indicators. The prediction results of the model are as follows:

[0207] Predicted value of iron loss P_TS Predicted value of magnetic induction P_CG 2.226366 1.662513 Standard deviation of iron loss TS_STD Standard deviation of magnetic induction CG_STD 0.064419 0.012056

[0208] Substitute the performance requirements and performance prediction values to calculate the qualification rates of different performance indicators:

[0209] It is calculated that CDF_TS = 0.7967; CDF_CG = 0.8390.

[0210] Since both CDF_TS and CDF_TS are less than 0.9545, that is, the magnetic properties may not meet the internal control requirements of the performance under the probability of ±2σ, so it is necessary to optimize the hot rolling process parameters and adjust the hot rolling process temperature.

[0211] In order to make the final performance stable near the target value, an optimization objective function for iron loss and magnetic induction is established:

[0212] Delta_TS=(P_TS - TS_AIM)^2

[0213] Delta_CG=(P_CG - CG_AIM)^2

[0214] LOSS = Delta_TS + m * Delta_CG

[0215] Determine the constraint conditions based on the relationship between hot rolling process parameters and performance indicators, as well as the thresholds of hot rolling process parameters and performance indicators:

[0216] (1)TS = f1(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, NOF, SF, HS, SS, Speed, Thick);

[0217] (2)CG = f2(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, NOF, SF, HS, SS, Speed, Thick);

[0218] (3)FRN_MIN <= FRN <= FRN_MAX;

[0219] (4)FT_MIN <= FT <= FT_MAX;

[0220] (5)CT_MIN <= CT <= CT_MAX;

[0221] (6)TS_MIN <= TS <= TS_MAX;

[0222] (7)CG_MIN <= CG <= CG_MAX.

[0223] Solve this optimization problem using the gradient descent method to obtain the optimal design values of the three temperatures:

[0224] FRN = frn_c2

[0225] FT = ft_c2

[0226] CT = ct_c2

[0227] Substitute the new hot rolling process temperature into the performance prediction model, and the new predicted performance can be calculated as follows:

[0228] Predicted value of iron loss P_TS Predicted value of magnetic induction P_CG 2.188357 1.667745 Standard deviation of iron loss TS_STD Standard deviation of magnetic induction CG_STD 0.001564 0.000552

[0229] Substitute the performance requirements and performance prediction values, and calculate the qualification rates of different performance indicators:

[0230] CDF_TS = 0.9999; CDF_CG = 0.9999;

[0231] Both CDF_TS and CDF_CG are greater than 0.9545, that is, the performance indicators calculated using the new hot rolling process temperature are all qualified. Therefore, the hot rolling process optimization is successful, and the hot rolling process is produced according to the new process.

[0232] Adjusted tapping temperature Adjusted finishing rolling temperature Adjusted coiling temperature frn_c2 ft_c2 ct_c2

[0233] 2) Adjustment of Normalizing Process Parameters

[0234] After the hot rolling process is completed, retrieve the actual hot rolling temperature:

[0235] Tapping temperature Finishing rolling temperature Coiling temperature frn_r2 ft_r2 ct_r2

[0236] Before the normalizing plan is issued, input data such as steelmaking composition, hot rolling process, normalizing process target values, SACL process target values, and finished product thickness target values into the magnetic property prediction model, and calculate the predicted values of indicators such as iron loss and magnetic induction as follows:

[0237]

[0238]

[0239] Substitute the performance requirements and performance predicted values, and calculate the qualification rates of different performance indicators:

[0240] CDF_TS = 0.7984; CDF_CG = 0.9999;

[0241] Since CDF_TS is less than 0.9545, that is, the iron loss may not meet the internal control requirements of the performance under the probability of ±2σ, so it is necessary to optimize the normalizing process parameters and adjust the normalizing annealing temperature.

[0242] In order to stabilize the final performance near the target value, similarly establish an optimization objective function for iron loss and magnetic induction to adjust the annealing temperature of the normalizing heating section and soaking section, and the obtained optimization equations are as follows:

[0243] Delta_TS = (P_TS - TS_AIM)^2

[0244] Delta_CG = (P_CG - CG_AIM)^2

[0245] LOSS = Delta_TS + m * Delta_CG

[0246] Constraints:

[0247] (1) TS = f1(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, HS, SS, Speed, Thick);

[0248] (2) CG = f2(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, HS, SS, Speed, Thick);

[0249] (3) NOF_MIN <= NOF <= NOF_MAX;

[0250] (4) SF_MIN <= SF <= SF_MAX;

[0251] (5) TS_MIN <= TS <= TS_MAX;

[0252] (6) CG_MIN <= CG <= CG_MAX.

[0253] Solve this optimization problem using the gradient descent method to obtain the optimal design values of the two temperatures:

[0254] NOF = nof_c2

[0255] SF = sf_c2

[0256] The two normalizing temperatures obtained by calculation have reached the boundary values, that is, it is considered that the optimal values under the given conditions have been reached and cannot be adjusted anymore.

[0257] Substitute the new normalizing process temperature into the performance prediction model, and the new predicted performance can be calculated as follows:

[0258] Predicted value of iron loss P_TS Predicted value of magnetic induction P_CG 2.169983 1.668456 Standard deviation of iron loss TS_STD Standard deviation of magnetic induction CG_STD 0.001016 0.001543

[0259] Substitute the performance requirements and performance prediction values to calculate the qualification rates of different performance indicators:

[0260] It is calculated that CDF_TS = 0.9999; CDF_CG = 0.9999

[0261] Both CDF_TS and CDF_CG are greater than 0.9545, that is, both performance indicators are qualified after optimizing and adjusting the normalizing process temperature. Therefore, the normalizing process optimization is successful, and the production of the normalizing process is carried out according to the new process.

[0262] Adjusted normalizing heating section temperature Adjusted normalizing soaking section temperature nof_c2 sf_c2

[0263] 3) Adjustment of SACL process parameters

[0264] After the normalizing process is completed, retrieve the actual furnace temperature of normalization:

[0265] Normalizing heating section temperature Normalizing soaking section temperature nof_r2 sf_r2

[0266] Before the SACL plan is issued, input data such as steelmaking composition, hot rolling process, normalizing process, SACL process target values, finished product thickness target values, etc. into the magnetic property prediction model, and calculate the predicted values of indicators such as iron loss and magnetic induction as follows:

[0267] Predicted value of iron loss P_TS Predicted value of magnetic induction P_CG 2.171224 1.667945 Standard deviation of iron loss cold TS_STD Standard deviation of magnetic induction CG_STD 0.002374 0.002251

[0268] Substitute the performance requirements and performance prediction values to calculate the qualification rates of different performance indicators:

[0269] The calculated CDF_TS = 0.9999; CDF_CG = 0.9999

[0270] Both CDF_TS and CDF_CG are greater than 0.9545, and the performance indicators are qualified. Therefore, there is no need to perform SACL dynamic quality design, and SACL production is carried out according to the original SACL process setting values.

[0271] Those of ordinary skill in the art should recognize that the above embodiments are only used to illustrate the present invention and are not intended to limit the present invention. As long as it is within the spirit of the present invention, changes and modifications to the above embodiments will fall within the scope of the claims of the present invention.

Claims

1. A method for controlling the performance stability of non-oriented electrical steel based on a prediction model, characterized in that: By establishing a performance prediction model for the performance of non-oriented electrical steel, extracting the process actual performance of the completed processes and the process setting data of the uncompleted processes, substituting them into the performance prediction model, and predicting the performance of the non-oriented electrical steel; And dynamically adjusting the process parameters of the non-oriented electrical steel according to the performance prediction value calculated by the performance prediction model, so that the performance of the non-oriented electrical steel meets the contract requirements and is stabilized near the target value required by the internal control.

2. The method for controlling the performance stability of non-oriented electrical steel based on a prediction model according to claim 1, characterized in that, The method for controlling the performance stability of non-oriented electrical steel specifically includes the following steps: S1. Before the production plan of hot rolling / normalizing annealing / SACL annealing is issued, retrieve the steelmaking composition data, steelmaking process parameters, hot rolling process parameters, hot rolling process thresholds, normalizing process parameters, normalizing process thresholds, SACL process parameters, SACL process thresholds, contract performance requirements, internal control requirements, and specification parameters; S2. Substitute the parameters in step S1 into the performance prediction model to predict the performance of the non-oriented electrical steel planned to be produced; S3. Combine the contract performance requirements and the internal control requirements to determine whether the performance of the predicted non-oriented electrical steel is qualified; S4. For the steel coils whose performance does not meet the quality requirements, establish an objective function and constraint conditions in combination with the threshold range of the process parameters, and optimize the process parameters; S5. For the steel coils with successful optimization, produce them according to the optimized process parameters; for the steel coils with failed optimization, produce them according to the boundary values of the recommended process parameters.

3. The method for controlling the performance stability of non-oriented electrical steel based on a prediction model according to claim 2, characterized in that, In step S1, the steelmaking composition data includes elements such as Si, Al, Mn, P, Ti, S, C, N, Nb, and V; The steelmaking process parameters include the ladle slag thickness and the free oxygen at the end of decarburization; The hot rolling process parameters include the furnace inlet temperature, the time in the furnace, the furnace outlet temperature, the rough rolling temperature, the finish rolling temperature, and the coiling temperature; The hot rolling process thresholds include the upper and lower limits of the hot rolling process parameters; The normalizing process parameters include the soaking section furnace temperature and the heating section furnace temperature; The normalizing process thresholds include the upper and lower limits of the normalizing process parameters; The SACL process parameters include the annealing speed, the annealing soaking section furnace temperature, the annealing heating section furnace temperature, and the annealing furnace tension; The SACL process thresholds include the upper and lower limits of the SACL process parameters; The specification parameters include the strip thickness and width; The contract performance requirements include the minimum magnetic induction requirement for product delivery and the maximum iron loss requirement; and / or the minimum and maximum iron loss requirements for product delivery; The internal control requirements include the internal control requirements for the performance of actual production, that is, the upper and lower limits and the target value of the performance index.

4. The method for controlling the performance stability of non-oriented electrical steel based on a prediction model according to claim 3, characterized in that, In step S1, before the hot rolling rolling plan is issued, the steelmaking composition data and the steelmaking process parameters retrieved are the actual production values; the hot rolling process parameters, the normalizing process parameters, and the SACL process parameters are the process set values; Before the normalizing annealing plan is issued, the steelmaking composition data, the steelmaking process parameters, and the hot rolling process parameters retrieved are the actual production values; The normalizing process parameters and the SACL process parameters are the process set values; Before the SACL annealing plan is issued, the steelmaking composition data, the steelmaking process parameters, the hot rolling process parameters, and the normalizing process parameters retrieved are the actual production values; The SACL process parameters are the process set values.

5. The method for controlling the performance stability of non-oriented silicon steel based on a prediction model according to claim 4, wherein, in step S1, the hot rolling process threshold, the normalizing process threshold, and the SACL process threshold are customized according to the steel type and grade type conditions of non-oriented silicon steel; the contract performance requirements are the release requirements formulated by the user and are determined according to different user needs; the internal control requirements are the performance control requirements formed based on long-term actual production and are stricter than the contract performance requirements.

6. The method for controlling the performance stability of non-oriented silicon steel based on a prediction model according to claim 1, characterized in that: the performance prediction values calculated by the performance prediction model include the iron loss and magnetic induction of non-oriented silicon steel.

7. The method for controlling the performance stability of non-oriented silicon steel based on a prediction model according to claim 1, wherein, the determination of whether the performance of the predicted non-oriented silicon steel in step S3 is qualified specifically includes: judging by calculating the probability that the performance prediction value meets the upper and lower limit requirements of the performance, and choosing the probability of ±2σ for judgment.

8. The method for controlling the performance stability of non-oriented silicon steel based on a prediction model according to claim 1, wherein, the optimization of the process parameters in step S4 specifically includes: When calculating the optimization adjustment of the process parameters, it is necessary to comprehensively determine the optimization objective function according to multiple performance prediction values and the target value, and determine the constraint conditions based on multiple performance prediction values and the hot rolling process threshold, the normalizing process threshold, and the SACL process threshold, and use an optimization algorithm to solve the objective function to obtain the optimal process parameter value.

9. The method for controlling the performance stability of non-oriented silicon steel based on a prediction model according to claim 7, wherein, in step S5, for the steel coils with optimization failure, the production according to the boundary values of the recommended process parameters specifically includes: For the steel coils with optimization failure, that is, the steel coils for which the objective function has no solution within the constrained range, the process parameter optimization will also give a set of boundary values of the process parameters to make the predicted performance closest to the target value, and at this time, the production will be carried out according to the boundary values of this process parameter.

10. The method for controlling the performance stability of non-oriented silicon steel based on a prediction model according to claim 1, wherein, the calculation of the performance prediction model is as follows: TS = f1(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, NOF, SF, HS, SS, Speed, Thick); CG = f2(Si, Al, Mn, P, Ti, S, C, N, FRN, FT, CT, NOF, SF, HS, SS, Speed, Thick); wherein, TS and CG are performance indexes of iron loss and magnetic induction respectively; wherein, Si, Al, Mn, P, Ti, S, C, and N respectively represent the contents of silicon element, aluminum element, manganese element, phosphorus element, titanium element, sulfur element, carbon element, and nitrogen element; wherein, FRN, FT, CT, NOF, SF, HS, SS, Speed, and Thick respectively represent the tapping temperature, finish rolling temperature, coiling temperature, furnace temperature in the heating section of normalizing annealing, furnace temperature in the soaking section of normalizing annealing, high temperature zone furnace temperature in the heating section of SACL continuous annealing furnace, furnace temperature in the soaking section of SACL continuous annealing furnace, annealing speed, and SACL outlet thickness.

Images