METHOD FOR DETERMINING PRODUCT QUALITY, METHOD FOR DETERMINING THE QUALITY OF CONTINUOUSLY CAST BLADES AND DETERMINING THE DESTINATION, METHOD FOR DETERMINING CONTINUOUS CASTING CONDITIONS, AND METHOD FOR CONTINUOUSLY CASTING STEEL

Abstract

To provide a technique capable of determining quality of a cast slab being or having been cast by continuous casting, during or after the casting.SOLUTION: A quality determination method of a product, for determining quality of a product produced by rolling a cast slab cast by a continuous casting machine, predicts a hydrogen-induced crack in a center part of the product by using a prediction model of the hydrogen-induced crack in the center part of the product and using, as input variables, one or more values selected from actual measurement values of casting result data measured during casting. For determining, using the method, quality of a product produced by rolling a cast slab cast by a continuous casting machine, the prediction model associates the casting result data with a hydrogen-induced crack generation area ratio of the center part of the product, a method inputs, into the prediction model, one or more values selected from actual measurement values of casting result data measured during casting, and predicts a hydrogen-induced crack generation area ratio of the center part of the product obtained from the cast slab, during casting or after casting. On the basis of the obtained prediction value, a method determines a destination of the cast slab.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a method for determining the quality of a product and a continuously cast slab from the casting conditions and actual measurements during continuous casting of steel, a method for determining the destination of a continuously cast slab, and a method for determining continuous casting conditions. 3 kg, and the volume unit "L" is 10 -3 m 3 Represents. [Background technology]

[0002] In the final solidification process of continuous steel casting, solidification shrinkage causes a suction flow of unsolidified molten steel (called the "unsolidified phase," reference number 12 in Figure 1) in the direction of the slab's withdrawal. This unsolidified phase contains concentrated solute elements such as carbon (C), phosphorus (P), sulfur (S), and manganese (Mn), which form concentrated molten steel. When this concentrated molten steel flows to the center of the slab and solidifies, so-called center segregation occurs. In addition to the solidification shrinkage described above, factors that cause concentrated molten steel to flow in the final stage of solidification include slab bulging between the rolls due to the static pressure of the molten steel and misalignment of the slab support rolls.

[0003] This center segregation deteriorates the quality of steel products, especially thick steel plates. For example, in line pipe materials for transporting oil or natural gas, hydrogen-induced cracking occurs from the center segregation due to the action of sour gas. Similar problems also occur in offshore structures, storage tanks, oil tanks, etc. Furthermore, in recent years, steel products are often required to be used in harsh environments, such as at lower temperatures or in more corrosive environments, making it increasingly important to reduce center segregation in cast slabs.

[0004] For this reason, sour-resistant linepipe steel undergoes HIC (Hydrogen Induced Cracking) testing before shipping, and only products that do not experience HIC are shipped as sour-resistant. However, it takes several weeks for the results of the HIC test to become known, and if HIC occurs, the product cannot be shipped as sour-resistant, resulting in a significant decrease in yield. Therefore, if HIC performance could be evaluated at the slab stage before plate rolling without conducting HIC testing, it would be possible to shorten manufacturing time and significantly improve yield.

[0005] Patent Document 1 discloses a method for measuring the opening thickness of horizontal cracks and the maximum segregation grain size on the cut surface of a slab, determining a threshold value from the measurement results and the results of an HIC measurement test, and changing the casting destination. Patent Documents 2 and 3 disclose continuous casting methods for steel that satisfy the Ca / S ratio and the relationship between Ca, S, and O, and further compensate for HIC by keeping the Ca decrease below a threshold. Furthermore, Patent Document 4 discloses an evaluation method that can detect center segregation with high accuracy by binarizing an etched print image of the cross section of steel material. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-058473 [Patent Document 2] Japanese Patent Application Laid-Open No. 2016-125137 [Patent Document 3] Japanese Patent Application Laid-Open No. 2016-125140 [Patent Document 4] Japanese Patent Application Publication No. 2017-181030 Summary of the Invention [Problem to be solved by the invention]

[0007] However, the above-mentioned conventional techniques have the following problems. The technology disclosed in Patent Document 1 requires measuring segregated grains on the cut surface of the slab, which poses a problem in terms of shortening the manufacturing period. The technologies disclosed in Patent Documents 2 and 3 can deal with HIC cracking originating from Ca-based inclusions, but cannot deal with HIC cracking caused by center segregation of NbC or the like. Furthermore, the technology disclosed in Patent Document 4 simply evaluates center segregation, and the correlation with HIC cracking is not clarified.

[0008] For HIC cracking caused by center segregation, seven days of testing is required even after steel plate production. By the time a quality defect is discovered, a large number of products have already been manufactured, which can result in a large number of defective products being produced. Also, if defects are predicted after casting, it is possible to avoid subsequent processes and simply remelt the product, but since it is not possible to determine whether there are defects at the casting stage, it is necessary to continue manufacturing the product all the way to the final product. Since evaluation is required after the final product is manufactured and any defects cannot be converted into good products, this causes increased costs.

[0009] The present invention has been made in consideration of the above circumstances, and its first object is to propose a product quality assessment method that predicts the quality of a product obtained by rolling a slab at the slab stage. Another object is to propose a method that can assess the quality of a slab cast by a continuous casting machine, particularly the HIC characteristics caused by center segregation, during or after casting. Additionally, the present invention proposes a method for determining the destination of a continuously cast slab, a method for determining continuous casting conditions, and a method for continuously casting steel. [Means for solving the problem]

[0010] The inventors discovered that the area ratio of hydrogen-induced cracks (HICs) caused by centerline segregation can be predicted from actual casting data during casting, i.e., parameters such as the cross-sectional size of the slab, the chemical composition, the mold powder characteristics, the casting speed, the specific water content of the secondary cooling water, the amount of molten metal level fluctuation due to bulging, the soft reduction conditions, the amount of fluctuation in the slab thickness immediately before the soft reduction zone, and the distance from the meniscus to the final solidification position and the variation in that distance in the width direction, and thus completed the present invention.

[0011] That is, it has been found that the above problems can be advantageously solved by the following invention. [1] A method for assessing the quality of a product rolled from a slab cast in a continuous casting machine, using a prediction model for hydrogen-induced cracking in the center of the product and using one or more input variables selected from the actual values ​​of the casting performance data measured during casting to predict hydrogen-induced cracking in the center of the product. [2] A method for determining the quality of a slab cast by a continuous casting machine using the product quality determination method described in [1], wherein the prediction model links actual casting performance data with the area ratio of hydrogen-induced cracking in the center of the product, and one or more selected from actual values ​​of the casting performance data measured during casting are input into the prediction model to predict the area ratio of hydrogen-induced cracking in the center of the product obtained from the slab during or after casting. [3] In the method for determining the quality of continuously cast slab in [2], the casting performance data is some or all of the following: cross-sectional size of the slab, component composition, mold powder characteristics, casting speed, specific water amount of secondary cooling water, amount of molten metal level fluctuation due to bulging, soft reduction conditions, amount of slab thickness fluctuation just before the soft reduction zone, and the distance from the meniscus to the final solidification position and the widthwise variation of said distance. [4] The method for evaluating the quality of a continuously cast slab according to [3], wherein the component composition is at least one selected from the group consisting of C concentration, Mn concentration, and C equivalent calculated by the following formula in terms of Ceq (mass%): Ceq=[C]-0.0616[Al]+2.5275[S]-0.2652[P]+0.0023[Si]+0.0344[Mn]-1.525[S][ Mn]+0.021[Si][Mn]+0.02[Cu]-0.02[Mo]+0.06[Ni]+0.02[Cr]-0.04[V]-0.04[Nb] Here, [M] in the formula is the content of element M expressed as mass percentage. [5] A method for assessing the quality of a continuously cast slab in any one of [2] to [4], wherein the predictive model uses principal component analysis and regression using the Random Forest method, and optionally machine-learns the predictive model using actual measurements of the area ratio of hydrogen-induced cracking in the center of the product. [6] A method for determining the destination of a continuously cast slab, which determines the destination of the slab based on a quality prediction of the slab determined using the method for determining the quality of the continuously cast slab described in any one of [2] to [5]. [7] A method for determining continuous casting conditions, which determines casting conditions by reverse analysis based on the casting performance data and the prediction model, so that the predicted value of the area ratio of hydrogen-induced cracking in the center of the product approaches a predetermined value based on the quality prediction of the slab determined using the method for determining the quality of the continuous cast slab described in any one of [2] to [5]. [8] The method for determining continuous casting conditions according to [7], wherein the predetermined value is 2% or less. [9] A method for continuous casting of steel, which produces cast pieces according to the casting conditions determined by the method described in [7] or [8]. [Effects of the Invention]

[0012] According to the present invention, the quality of a product or slab, particularly the hydrogen-induced cracking area ratio in the product center, is predicted during or after casting by inputting actual values ​​from measured casting performance data into a pre-prepared prediction model. Therefore, it is possible to accurately predict whether a slab is suitable for a specific product, enabling the production of products with a high yield. Furthermore, by determining casting conditions so that the obtained predicted value asymptotically approaches a predetermined value and producing a slab under the determined casting conditions, products can be produced with a high yield, improving productivity and providing industrial utility. For example, the predicted HIC value of a product can be used to determine whether it is suitable for sour-resistant linepipe steel, without conducting time-consuming HIC testing. This makes it possible to quickly respond to demands for the production of steel products with diverse specifications, providing industrial utility. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a schematic side view showing a slab continuous casting machine suitable for carrying out the present invention. [Figure 2] 1A and 1B are schematic diagrams showing an example of a roll segment constituting the soft reduction zone of the above-mentioned slab continuous casting machine, in which (a) is a side view and (b) is a cross-sectional view taken along the line AA as seen from the conveying direction of the slab. [Figure 3] 1 is a graph showing the relationship between the measured value and the predicted value of the HIC crack area ratio (CAR) in the center. [Figure 4] FIG. 1 is a flow chart showing an example of a method for predicting the quality of a continuously cast slab. [Figure 5] This is a schematic flow diagram from continuous casting to shipping. [Figure 6] 1 is a graph showing the degree of influence of each variable on principal component 1 and principal component 2 in an example. DETAILED DESCRIPTION OF THE INVENTION

[0014] The following is a detailed description of embodiments of the present invention. The following embodiments are intended to exemplify equipment and methods for embodying the technical concept of the present invention, and are not intended to limit the configuration to those described below. In other words, the technical concept of the present invention can be modified in various ways within the technical scope defined in the claims.

[0015] FIG. 1 is a schematic side view showing a continuous slab caster suitable for use in a continuous steel casting method according to one embodiment of the present invention. As shown in FIG. 1, the continuous slab caster 1 is equipped with a mold 5 into which molten steel 9 is poured and solidified to form the outer shell shape (solidified shell 11) of a slab 10. A tundish 2 is installed at a predetermined position above the mold 5 to relay molten steel 9 supplied from a ladle (not shown) to the mold 5. A sliding nozzle 3 is installed at the bottom of the tundish 2 to adjust the flow rate of the molten steel 9, and an immersion nozzle 4 is installed below the sliding nozzle 3. Meanwhile, multiple pairs of slab support rolls 6, each consisting of a support roll, a guide roll, and a pinch roll, are arranged below the mold 5. A secondary cooling zone is formed in the gap between adjacent slab support rolls 6 in the casting direction (FD), and is equipped with spray nozzles (not shown), such as water spray nozzles or air mist spray nozzles. In the secondary cooling zone, the slab 10 is cooled as it is drawn out by cooling water (also referred to as "secondary cooling water") sprayed from spray nozzles. Downstream of the final slab support roll 6 in the casting direction, a plurality of transport rolls 7 for transporting the cast slab 10 are installed, and above these transport rolls 7, a slab cutter 8 is located for cutting a slab 10a of a predetermined length from the cast slab 10. The cross-sectional size of the slab is expressed by the slab width Lw (mm) and the slab thickness Lt (mm).

[0016] A soft reduction zone 14, consisting of multiple pairs of slab support rolls as shown in Figures 1 and 2, is installed upstream and downstream in the casting direction across the final solidification position (crater end: CE) 13 of the slab 10. In the soft reduction zone 14, the spacing between the opposing slab support rolls sandwiching the slab 10 (this spacing is called the "roll gap") is set to gradually narrower toward the downstream side in the casting direction. In other words, a reduction gradient (a state in which the roll gap is set to gradually narrow toward the downstream side in the casting direction) is set. In the soft reduction zone 14, it is possible to soft reduce the slab 10 in the entire area or in a selected area. Spray nozzles for cooling the slab 10 are also installed between each slab support roll in the soft reduction zone 14. The slab support rolls 6 arranged in the soft reduction zone 14 are also called reduction rolls.

[0017] The reduction gradient is usually expressed as the amount of roll gap reduction (mm) per meter in the casting direction, i.e., "mm / m." Therefore, the reduction rate Vl (mm / min) of the slab 10 in the soft reduction zone 14 is obtained by multiplying this reduction gradient (mm / m) by the slab withdrawal rate Vc (m / min).

[0018] In the continuous slab caster 1 shown in FIG. 1 , the soft reduction zone 14 is configured by three roll segments, each consisting of three pairs of slab support rolls 6, connected in the casting direction FD. However, in this embodiment, the soft reduction zone 14 does not need to be configured by three roll segments; the soft reduction zone 14 may be configured by one, two, or even four or more roll segments. Furthermore, although each roll segment is configured by three pairs of slab support rolls 6, any number of pairs of slab support rolls 6 may be configured in one roll segment, as long as they are two or more pairs. FIG. 2 shows an example of the roll segments that configure the soft reduction zone 14. FIG. 2(a) is a schematic side view showing an example in which six pairs of slab support rolls 6 are arranged in one roll segment as reduction rolls. FIG. 2(b) is a cross-sectional view taken along the line AA, perpendicular to the slab casting direction.

[0019] The chemical composition of a slab can be determined using analytical values ​​from samples taken from the molten steel in the ladle or tundish. For example, C and Mn are known to be elements that affect the centerline segregation of the slab. It is also known that the degree of centerline segregation increases as the C equivalent (Ceq, mass%), expressed by the following formula, increases. Ceq=[C]-0.0616[Al]+2.5275[S]-0.2652[P]+0.0023[Si]+0.0344[Mn]-1.525[S][ Mn]+0.021[Si][Mn]+0.02[Cu]-0.02[Mo]+0.06[Ni]+0.02[Cr]-0.04[V]-0.04[Nb] Here, [M] in the formula is the content of element M expressed in mass %.

[0020] Mold powder properties are expressed in terms of the crystallization temperature Tc (°C), basicity C / S (the ratio of CaO to SiO2 by mass), and viscosity η (dPa·s) at 1300°C. These parameters affect the solidification state of the steel in the mold and also affect the degree of center segregation in the slab. It is also well known that unsteady bulging worsens center segregation. The bulging-induced mold level fluctuation δME (mm), determined from the period, is the amount of mold level fluctuation on the mold inner surface at the final solidification point of the slab, and serves as an indicator of the impact of unsteady bulging on center segregation. The slab thickness fluctuation δLT (mm), calculated from the change in slab thickness measured by a water column ultrasonic distance meter 15 installed in the soft reduction zone 14, also serves as an indicator of the impact of unsteady bulging on center segregation. The final solidification position LCE (m), which is indicated by the casting length from the meniscus, and the variation in the final solidification position across the width, so-called peak-to-valley difference ΔCE (m), can be calculated using two-dimensional heat transfer solidification calculations. Here, the solid fraction is defined as 0 before solidification begins and 1.0 at the end of solidification. The position at which the solid fraction at the center of the slab thickness is 1.0 corresponds to the solidification end position 13. Two-dimensional heat transfer solidification calculations can be performed more accurately by performing correction calculations using the values ​​of a thermometer 16 installed in the continuous casting machine.

[0021] The above-mentioned casting performance data, which affect the centerline segregation of the slab, are used as input variables for a prediction model for the hydrogen-induced crack area ratio (CAR) in the product center. Here, the product center refers to the area from the center of the plate thickness to 10% of the plate thickness. For example, the prediction model can be used to reduce the number of variables through principal component analysis, followed by regression using the Random Forest method, making it possible to accurately predict the HIC crack area ratio (CAR) in the center.

[0022] Principal component analysis (PCA) is a method for compressing data with correlations between variables without reducing the amount of information, thereby simplifying analysis by reducing the number of variables in complex data. In this embodiment, variables such as "slab width (Lw) during casting, slab thickness (Lt), carbon concentration (C), manganese concentration (Mn), carbon equivalent (Ceq), mold powder characteristics, casting speed (Vc), secondary cooling specific water flow rate (Qw), molten metal level fluctuation due to bulging (δME), reduction rate (Vl) in the soft reduction segment, slab thickness fluctuation immediately before the soft reduction zone (δLT), final solidification position (LCE), and widthwise variation of final solidification position (ΔCE)" are compressed to, for example, five variables. When compressed to five variables, the compressed variables can be expressed using variables such as principal component 1 through principal component 5, allowing data expressed with many variables to be represented with fewer variables without reducing the amount of information. Narrowing down the data variables without using PCA requires discarding some variables. This can sometimes require discarding important variables. Principal component analysis generates principal components in order from the first principal component so as to include as much information as possible about each variable, making it possible to reduce the number of variables more efficiently than usual.

[0023] The Random Forest method is a machine learning algorithm. It is an ensemble learning algorithm that integrates multiple weak learners using decision trees and performs cross-validation and cross-validation to improve generalization ability. In the regression of this embodiment, approximately several hundred decision trees were calculated and integrated using the average value. In other words, by compressing the many explanatory variables to about five using principal component analysis and then performing regression using the Random Forest method, highly accurate regression is possible even with a small amount of data.

[0024] In this embodiment, an example is shown in which the hydrogen-induced crack area ratio (CAR) in the center of a product is predicted using all of the above-mentioned casting performance data. Even when only a portion of the casting performance data is used, it is possible to improve the accuracy of the regression by compressing variables using principal component analysis.

[0025] Figure 4 is a flow diagram showing an example of a method for predicting the HIC crack area ratio (CAR) at the product center. Casting conditions and online measurements are input into a prediction model (S1), and variables are reduced using principal component analysis (S2). Regression is performed using the reduced variables using the random forest method (S3), and the HIC crack area ratio (CAR) at the product center due to center segregation is predicted (S4). Furthermore, by using the measured values ​​of the HIC crack area ratio (CAR) at the product center as training data for principal component analysis (S5), it is possible to predict the HIC crack area ratio (CAR) with even greater accuracy. The obtained predicted CAR value can be used to determine whether or not to send the product to the next rolling process. Furthermore, the obtained predicted CAR value can be used to improve the quality of the slab by adjusting the secondary cooling specific water flow rate (Qw) so that it approaches a predetermined value during casting, or by adjusting the soft reduction roll gap to adjust the reduction rate (Vl) (S6).

[0026] FIG. 5 is a flow diagram showing the process from continuous casting (S11) to rolling (S12) to shipping (S13). Typically, centerline segregation is analyzed using an EPMA to determine the quality of slabs cast by a continuous caster (S14). This analysis takes one to two weeks. Furthermore, an HIC test is performed to determine whether the rolled product should be shipped (S15). The HIC test involves immersing a test specimen in hydrogen sulfide and evaluating the crack area ratio (CAR) when hydrogen-induced cracks occur in the center or surface of the plate (product). This test requires at least one week. Product shipping requires that the CAR be below a threshold value. Conventionally, by the time this test revealed a quality defect, a large number of products had already been manufactured, resulting in the production of a large number of defective products. In this embodiment, quality can be predicted during or immediately after casting without performing an HIC test, significantly shortening lead time and preventing mass nonconformity during this period. [Example]

[0027] Example 1 The present invention will be described in more detail below with reference to examples. The continuous casting machine used in the test was the same as the continuous casting machine 1 shown in Figure 1. Low-carbon aluminum-killed steel was cast using this continuous casting machine. Tables 1 to 3 show actual casting data, such as casting conditions, and the measured and predicted values ​​of the HIC crack area ratio (CAR) at the product center using the continuous casting method according to the above embodiment. Here, the product center refers to the area from the center of the plate thickness to 10% of the plate thickness in the plate thickness direction. Using the actual casting data shown in Tables 1 and 2 as input, a prediction model for the HIC crack area ratio (CAR) at the product center was used to perform regression using principal component analysis and the Random Forest method. Figure 3 shows a graph of the relationship between the measured and predicted values ​​of the HIC crack area ratio (CAR) at the product center. In this prediction model, the explanatory variables were reduced to five variables using principal component analysis, and regression was performed using the Random Forest method. Figure 6 shows the relationship between principal component 1 and principal component 2 of the principal component analysis and the correlation coefficients of various operating conditions. The operating conditions with the largest sum of the correlation coefficients between Principal Component 1 and Principal Component 2 were then determined to be the variables with the greatest influence on the HIC crack area ratio (CAR) in the product center. For example, from Figure 6, the following variables (operational conditions) were extracted as having the greatest influence: "C equivalent (Ceq)," "casting speed (Vc)," "reduction rate (Vl)" (reduction rate (Vl) in the soft reduction segment), "widthwise variation (ΔCE)" (widthwise variation (ΔCE) in the final solidification position), and "secondary cooling specific water flow rate (Qw)." Using this method, the measured and predicted values ​​of the HIC crack area ratio (CAR) in the product center showed good agreement, making it possible to predict HIC cracks in the product center during or immediately after casting.

[0028] Table 3 shows an example of control by adjusting the secondary cooling specific water flow rate Qw during casting so that the predicted CAR value approaches 0.00%, or by adjusting the reduction rate Vl by changing the roll gap for soft reduction. This control significantly reduced the area ratio of HIC cracks in the center of the product. In addition, the threshold value of the HIC crack area ratio CAR in the product center varies depending on the required quality. For example, in a steel product with a target HIC crack area ratio CAR in the product center of 2% or less, the prediction model for the HIC crack area ratio CAR in the product center according to the above embodiment was used to redirect slabs whose predicted CAR value was greater than 2%, resulting in a 5% improvement in yield.

[0029] [Table 1]

[0030] [Table 2]

[0031] [Table 3]

[0032] Example 2 An example of back-analysis of operating conditions will be described using Test No. 19 in Table 2. Under the initial operating conditions of Test No. 19, the predicted value of the HIC crack area ratio (CAR) in the product center was 4.80%, and the actual value was 5.03%. As a result of the principal component analysis of Example 1, the secondary cooling water volume Qw ​​and the rolling reduction rate Vl were extracted as variables that have a significant impact on CAR and are changeable during operation. By changing these variables and using a prediction model, back-analysis was performed to search for operating conditions that would result in a predicted CAR value of 0.1%. The secondary cooling water volume Qw ​​was then changed from 1.2 L / kg to 1.1 L / kg, and the rolling reduction rate Vl was changed from 0.78 mm / min to 0.98 mm / min. As a result, the actual measured value of the HIC crack area ratio (CAR) in the product center achieved the target value of 2% or less. [Explanation of symbols]

[0033] 1. Continuous casting machine 2 tundishes 3 Sliding Nozzle 4 Submerged Entry Nozzle 5. Mold 6. Casting support roll 7 Transport roll 8 Slab cutting machine 9 Molten Steel 10 Castings 10a (Cut) billet 11 Solidified shell 12 Unsolidified phase 13 Coagulation completion position (crater end) 14 Lightly Pressed Zone 15 Water column ultrasonic distance meter 16 Thermometer FD Casting direction

Claims

1. When judging the quality of products rolled from slabs cast by a continuous casting machine, Using a prediction model for hydrogen-induced cracking in the center of a product, the actual measured values ​​of casting performance data were used as input variables, and the actual values ​​of the HIC crack area ratio in the center of the product caused by center segregation were used as learning data through principal component analysis. Predict hydrogen-induced cracking in the center of the product using one or more input variables selected from the actual values ​​of casting performance data measured during casting, the measured values ​​of the casting performance data are or include a chemical composition, and further comprise some or all of the following: a cross-sectional size of a slab, mold powder characteristics, a casting speed, a specific water amount of secondary cooling water, a bulging-related molten metal level fluctuation, soft reduction conditions, a slab thickness fluctuation immediately before the soft reduction zone, a distance from the meniscus to the final solidification position, and a width-direction variation of the distance; The method for evaluating the quality of a product, wherein the component composition is at least one selected from a C concentration, a Mn concentration, and a C equivalent calculated in Ceq (mass%) by the following formula: Ceq=[C]-0.0616[Al]+2.5275[S]-0.2652[P]+0.0023[Si]+0.0344[Mn]-1.525[S][ Mn]+0.021[Si][Mn]+0.02[Cu]-0.02[Mo]+0.06[Ni]+0.02[Cr]-0.04[V]-0.04[Nb] Here, [M] in the formula is the content of element M expressed in mass percentage.

2. When determining the quality of a slab cast by a continuous casting machine using the product quality determination method according to claim 1, A method for assessing the quality of a continuously cast slab, comprising inputting into the prediction model one or more values ​​selected from the actual values ​​of the casting performance data measured during casting, and predicting the area ratio of hydrogen-induced cracking in the center of a product obtained from the slab during or after casting.

3. The prediction model uses principal component analysis and Random Forest regression, The method for determining the quality of a continuously cast slab according to claim 2 , optionally comprising machine learning the prediction model using an actual measurement value of an area ratio of hydrogen-induced cracks occurring in a center portion of the product.

4. A method for determining a destination of a continuously cast slab, the method comprising: determining a destination of the slab based on a prediction of the quality of the slab determined using the method for determining the quality of the continuously cast slab according to claim 2 or 3.

5. 4. A method for determining continuous casting conditions, comprising: determining casting conditions by reverse analysis based on the casting performance data and the prediction model, such that a predicted value of an area ratio of hydrogen-induced cracking in a center portion of a product asymptotically approaches a predetermined value based on a quality prediction of a slab determined using the method for determining the quality of a continuously cast slab according to claim 2 or 3.

6. The method for determining continuous casting conditions according to claim 5, wherein the predetermined value is set to 2% or less.

7. A method for continuous casting of steel, comprising producing a cast piece in accordance with the casting conditions determined by the method according to claim 5.

Images