Method, device, medium and equipment for predicting initiation of sub-surface corner cracks of continuous casting billets

Abstract

The present disclosure relates to the technical field of metallurgical continuous casting quality control, and provides a continuous casting billet corner subsurface crack initiation prediction method, device, medium and equipment. The method comprises: acquiring the time-space distribution data of the main tensile strain in the target depth region corresponding to the continuous casting billet corner of a target continuous casting billet; establishing a crack initiation criterion based on the coupling effect of strain amplitude and duration; performing time sequence scanning on the time-space distribution data of the main tensile strain by using the crack initiation criterion, and detecting whether there is a time window that simultaneously satisfies the conditions that the main tensile strain exceeds a critical threshold value and the continuous duration of the over-threshold value state reaches a critical duration in the time-space distribution data of the main tensile strain; if yes, it is predicted that the subsurface crack of the continuous casting billet corner will be initiated, and if no, it is predicted that the continuous casting billet corner is free of subsurface cracks. The embodiment realizes objective and quantitative determination of the subsurface crack initiation risk of the continuous casting billet corner, and improves the prediction accuracy and the reliability of online quality control.

Description

Technical Field

[0001] This disclosure relates to the field of metallurgical continuous casting quality control technology, and more specifically, to a method, apparatus, medium, and equipment for predicting the initiation of subcutaneous cracks at the corners of continuously cast billets. Background Technology

[0002] Subcutaneous corner cracks in large-section medium-carbon steel continuously cast billets are one of the key defects restricting product yield. These defects, located in the subcutaneous region below the billet surface, are difficult to weld during subsequent rolling and directly lead to product scrap. The formation of corner cracks in the high-temperature brittle zone of continuously cast billets involves microscopic damage mechanisms such as interdendritic liquid film separation, grain boundary slip, and micropore aggregation. It is a gradual cumulative process, influenced by both local strain conditions and high-temperature creep behavior. Accurately predicting the initiation of cracks in this region is crucial for optimizing secondary cooling regimes and adjusting casting speed processes.

[0003] In related technologies, the prediction of cracks in continuously cast billets generally adopts a single critical strain threshold criterion, which determines crack initiation when the local principal tensile strain instantaneously exceeds a certain fixed limit. However, in actual production, this criterion often exhibits prediction bias: some billets show local strain peaks exceeding the threshold without actually developing cracks; while other billets show corner subcutaneous cracks even before reaching the threshold. This bias stems from the fact that the single threshold criterion simplifies crack initiation as an instantaneous event, ignoring the time history experienced by the billet in the high-temperature brittle zone, leading to significant deviations between the predicted results and actual engineering conditions, making it difficult to provide effective guidance for process adjustments. Summary of the Invention

[0004] This disclosure provides at least one method, apparatus, medium, and device for predicting the initiation of subcutaneous cracks at the corner of continuously cast billets. By establishing a crack initiation criterion based on the coupling effect of strain amplitude and duration and performing a time-series scan of the spatiotemporal distribution data of the principal tensile strain, it achieves an objective and quantitative determination of the risk of subcutaneous crack initiation at the corner of continuously cast billets, thereby improving the accuracy of prediction and the reliability of online quality control.

[0005] This disclosure provides a method for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet, including: Acquire the spatiotemporal distribution data of principal tensile strain within the target depth region corresponding to the corner of the target continuous casting billet; A crack initiation criterion based on the coupling effect of strain amplitude and duration is established; wherein, in the crack initiation criterion, the crack initiation judgment condition is that the main tensile strain exceeds the critical threshold and the continuous duration of the over-threshold state reaches the critical duration. The spatiotemporal distribution data of the principal tensile strain is scanned using the crack initiation criterion to detect whether there is a time window in the spatiotemporal distribution data of the principal tensile strain that simultaneously satisfies the condition that the principal tensile strain exceeds a critical threshold and the duration of the over-threshold state reaches the critical duration. If the time window exists, it is predicted that a subcutaneous crack will initiate at the corner of the continuously cast billet; if the time window does not exist, it is predicted that there will be no subcutaneous crack at the corner of the continuously cast billet.

[0006] This disclosure provides a device for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet, comprising: The data acquisition module is used to acquire the spatiotemporal distribution data of principal tensile strain within the target depth region corresponding to the corner of the target continuous casting billet; The criterion establishment module is used to establish a crack initiation criterion based on the coupling effect of strain amplitude and duration; wherein, in the crack initiation criterion, the crack initiation judgment condition is that the main tensile strain exceeds the critical threshold and the continuous duration of the over-threshold state reaches the critical duration. The crack prediction module is used to perform a time-series scan of the spatiotemporal distribution data of the principal tensile strain using the crack initiation criterion, and to detect whether there is a time window in the spatiotemporal distribution data of the principal tensile strain that simultaneously satisfies the condition that the principal tensile strain exceeds a critical threshold and the continuous duration of the over-threshold state reaches the critical duration; if the time window exists, it is predicted that a subcutaneous crack will initiate at the corner of the continuously cast billet; if the time window does not exist, it is predicted that there is no subcutaneous crack at the corner of the continuously cast billet.

[0007] This disclosure provides a computer device, including a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the method for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet as described in any of the above possible embodiments is executed.

[0008] This disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet as described in any of the possible embodiments above.

[0009] The method, apparatus, medium, and equipment for predicting subcutaneous crack initiation at the corner of continuously cast billets provided in this embodiment of the present disclosure, by setting the crack initiation judgment condition as the main tensile strain exceeding the critical threshold and the continuous duration of the over-threshold state reaching the critical duration, and by detecting the time window that simultaneously meets the two conditions of strain exceeding the limit and duration reaching the standard through time-series scanning, realizes the characterization of the cumulative effect of load application time by the crack initiation criterion and the distinction between two different load conditions of high strain short-term application and low strain long-term application. It can reduce misjudgment caused by ignoring the time factor and make the prediction result match the physical nature of crack initiation as a progressive damage process.

[0010] In this way, by establishing a crack initiation criterion based on the coupling effect of strain amplitude and duration and performing a time-series scan of the spatiotemporal distribution data of the principal tensile strain, an objective quantitative judgment of the risk of subcutaneous crack initiation at the corner of the continuously cast billet is achieved, improving the accuracy of prediction and the reliability of online quality control.

[0011] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings referenced in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0013] Figure 1 A flowchart is shown below illustrating a method for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet, provided in an embodiment of this disclosure. Figure 2 A flowchart is shown below illustrating a method for calculating the spatiotemporal distribution data of principal tensile strain provided in an embodiment of this disclosure. Figure 3 This diagram illustrates the structure of a device for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet, as provided in an embodiment of this disclosure. Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of this disclosure is shown. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0015] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0016] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0017] To facilitate understanding of this embodiment, the executing entity of the method for predicting the initiation of subcutaneous cracks at the corner of continuously cast billets provided in this embodiment will first be described in detail. The executing entity of the method for predicting the initiation of subcutaneous cracks at the corner of continuously cast billets provided in this embodiment is a computer device. This computer device can be a terminal device or a server. The terminal device can also be a mobile device, a user terminal, a terminal, a handheld device, a computing device, an in-vehicle device, a wearable device, etc. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data, and artificial intelligence platforms. Optionally, this method can also be applied to an implementation environment composed of computer devices and servers.

[0018] The method for predicting the initiation of subcutaneous cracks at the corner of continuously cast billets provided in this application will be described in detail below with reference to the accompanying drawings. See also Figure 1 The diagram shows a flowchart of a method for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet, provided in an embodiment of this disclosure. The method includes the following steps S101 to S103: S101, obtain the spatiotemporal distribution data of principal tensile strain in the target depth region corresponding to the corner of the target continuous casting billet.

[0019] It is understood that the target continuously cast billet refers to a cast billet with a certain cross-sectional shape formed by continuously casting molten steel through a continuous casting machine. Its cross-sectional form can include rectangular billets, square billets, slabs, and round billets. The corner of the continuously cast billet refers to the edge region formed by the intersection of two adjacent side surfaces of the billet cross-section and its surrounding area. During solidification and cooling, the corner region bears comprehensive tensile stress in two dimensions. The target depth region refers to a subcutaneous region with a set thickness extending from the surface of the continuously cast billet inwards. In this region, the solidification structure is in the late stage of interdendritic feeding and the grain boundary brittleness sensitive stage. Under tensile stress, this region is prone to subcutaneous crack formation. The target depth region can be set according to the cross-sectional dimensions of the continuously cast billet, the depth of the high-temperature brittle zone of the target steel grade, and the casting machine speed. In specific applications, the target depth region can be set as a band-shaped region within the subcutaneous range of 20mm to 30mm.

[0020] Here, the principal tensile strain is the linear strain in the maximum principal direction experienced by the corner region of the continuously cast billet during solidification and cooling. This strain is a dimensionless positive number used to describe the degree of relative elongation deformation of the material in the direction of maximum principal stress. The spatiotemporal distribution data of the principal tensile strain in the target depth region of the corner of the continuously cast billet is the numerical set of the principal tensile strain at each spatial location in this region at different solidification times. This data reflects the mechanical loading history of the target depth region of the corner during the entire solidification and cooling process, and can provide quantitative input for determining crack initiation.

[0021] Specifically, the spatiotemporal distribution data of principal tensile strain within the target depth region at the corner of the continuously cast billet can be obtained through solidification heat transfer calculations and thermodynamic analysis, referring to... Figure 2 As shown, the acquisition process includes the following steps S201~S203: S201, obtain the process parameters of the continuous casting process corresponding to the target continuous casting billet, and calculate the solidification heat transfer process of the target continuous casting billet based on the process parameters to obtain the temperature field distribution data of the cross section of the target continuous casting billet.

[0022] Here, the continuous casting process corresponding to the target continuous casting billet refers to the complete process of continuously casting molten steel into a continuous casting billet through a continuous casting machine. The corresponding process parameters may include casting temperature, billet pulling speed, water spray flow rate of each cooling section, and cooling water flow rate of the crystallizer. These process parameters are collected and recorded in real time in the continuous casting process control system.

[0023] Specifically, the solidification heat transfer process of the target continuously cast billet refers to the physical process of heat release and transfer during the gradual solidification of molten steel from a liquid state to a solid state. This process involves the release of sensible heat from the liquid steel, the release of latent heat of phase change during solidification, and the further cooling of the solid billet shell. By solving the heat conduction control equation based on Fourier's law of thermal conductivity, and combining it with the corresponding initial and boundary conditions, the temperature distribution of the billet cross-section at different times can be determined. The billet cross-section is a section perpendicular to the direction of billet casting. Its corresponding temperature field distribution data includes the temperature values ​​at different spatial locations of the cross-section at different times. This data indicates the two-dimensional temperature distribution on the billet cross-section and its variation over time.

[0024] Here, the initial conditions for solidification heat transfer calculation refer to the temperature distribution on the cross-section of the billet at the start of the calculation. This start time corresponds to the moment when the molten steel begins to solidify at the meniscus of the crystallizer. The initial temperature can be set to the casting temperature. Boundary conditions are the heat flow constraints on the cross-sectional boundaries of the billet, which can specifically include contact heat transfer between the billet surface and the copper plate of the crystallizer, convective heat transfer between the spray water in the secondary cooling zone and the billet surface, and radiative heat dissipation in the radiative cooling zone. The initial and boundary conditions can be set according to the actual operating parameters of the continuous casting process. For example, the casting temperature can be set to the actual measured temperature when the molten steel enters the crystallizer, the billet speed can be read in real time from the continuous casting process control system, and the spray water flow rate of each cooling section can be obtained by measuring the flow rate through the flow meter installed in the pipeline. Specifically, the solidification heat transfer equation is determined based on the cross-sectional dimensions of the target continuous casting billet, the physical properties of the steel grade, and the cooling conditions of the continuous casting machine, and is not specifically limited here.

[0025] For example, when calculating the solidification heat transfer process of a continuously cast billet, the two-dimensional cross-sectional transient heat conduction equation can be used for solution. The latent heat release during solidification is handled by the equivalent heat capacity method, and the solidification heat transfer equation is numerically solved to obtain the temperature field distribution data of the billet cross-section. Specifically, the following steps are included: (1) to (2): (1) Obtain the measured water volume data of each side of the secondary cooling system corresponding to the target continuous casting billet, and calculate the heat transfer coefficient corresponding to each side based on the measured water volume data of each side. (2) Based on the process parameters and the heat transfer coefficients corresponding to each side, the solidification heat transfer process of the target continuous casting billet is calculated.

[0026] Here, the secondary cooling system refers to a collection of cooling devices located below the crystallizer of the continuous casting machine and arranged along the billet's running direction. It is a component of the continuous casting machine that provides forced cooling for the billet after it exits the crystallizer. The measured water volume data for each side of the secondary cooling system refers to the actual volume of water sprayed per unit time measured by flow meters installed in the corresponding cooling pipes on each of the four sides of the rectangular continuous casting billet. This data reflects the actual cooling intensity of each side under the current operating conditions.

[0027] Specifically, the heat transfer coefficient for each side can be calculated based on the measured water volume data of each side of the secondary cooling system. The heat transfer coefficient is a physical parameter characterizing the rate of heat exchange per unit area and unit temperature difference between the billet surface and the cooling water, and it is a parameter used as a boundary condition input in solidification heat transfer calculations. Furthermore, the solidification heat transfer process of the target continuously cast billet can be calculated based on the heat transfer coefficients corresponding to each side, as well as process parameters such as casting temperature and casting speed.

[0028] For example, taking a rectangular continuously cast billet with a cross-sectional size of 340mm×300mm as an example, the corresponding solidification heat transfer calculation process may include: establishing a two-dimensional cross-sectional geometric model based on the cross-sectional size of the rectangular continuously cast billet, and discretizing the geometric model into a finite number of mesh elements; obtaining the continuous casting process parameters corresponding to the rectangular continuously cast billet, which may include casting temperature, billet pulling speed, and water spray flow rate of each section of the secondary cooling system; obtaining the measured water volume data of each side of each section of the secondary cooling system, and calculating the heat transfer coefficient corresponding to each side based on the measured water volume data of each side; applying the calculated heat transfer coefficient of each side as a heat transfer boundary condition to the boundary of the corresponding side of the geometric model, and numerically solving the solidification heat transfer process using the two-dimensional cross-sectional transient heat conduction equation, and in the solution process, the equivalent heat capacity method can be used to handle the latent heat of crystallization released during the solidification of molten steel, that is, converting the latent heat of phase transformation into the equivalent specific heat capacity increment within the solid fraction change range, and superimposing it into the specific heat capacity of the material to participate in the iterative calculation of the temperature field. Here, the temperature distribution data of the cross section of the rectangular continuous casting billet at different solidification times are obtained through the above calculations. This disclosure is verified by the surface temperature measurement data of the billet under three different process conditions, and the average relative error of the temperature calculation value does not exceed 0.90%.

[0029] In this way, by obtaining the measured water volume data of each side and calculating the corresponding heat transfer coefficient of each side, the non-uniformity of secondary cooling on different sides of the billet circumference can be characterized, thus improving the accuracy of the temperature field calculation results.

[0030] S202, Perform thermodynamic analysis on the temperature field distribution data of the cross-section of the billet to calculate the principal tensile strain data at each position on the cross-section of the billet.

[0031] Here, the temperature field distribution data provides the temperature values ​​at different locations on the cross-section of the billet at different times. Performing thermodynamic analysis on the temperature field distribution data can determine the stress-strain response of the billet under the combined action of temperature change and external constraints, and then calculate the principal tensile strain data at each location on the cross-section of the billet.

[0032] Specifically, thermodynamic analysis is an analytical method based on thermoelastic or thermoelastic-plastic theory. It uses temperature field distribution data obtained from solidification heat transfer calculations as the thermal load boundary, and determines the internal stress and strain fields of the cast billet by solving stress balance equations, geometric equations, and physical equations. Based on the spatiotemporal distribution of the temperature field, the geometric constraints of the cast billet, and the mechanical constitutive relations of the material, thermodynamic analysis can determine the evolution of principal tensile strain in the corner region of the cast billet during solidification and cooling, and quantitatively characterize the mechanical driving conditions for crack initiation. The constitutive model used in thermodynamic analysis can include parameters that vary with temperature, such as high-temperature yield strength, elastic modulus, Poisson's ratio, and coefficient of thermal expansion.

[0033] In some possible embodiments, since the corner region of the billet is subjected to cooling from two adjacent sides during solidification and cooling, the stress state in this region is complex, which can be specifically analyzed by performing thermodynamic analysis through the following steps (a) to (c): (a) Determine the region on the cross-section of the billet where the solid fraction exceeds the critical value for bearing capacity; and obtain the spatial constraint coefficient determined by the solid fraction, geometric distance and temperature gradient of the region. (b) Perform thermodynamic analysis on the region based on the spatial constraint coefficient, and calculate the principal tensile strain of the region; (c) In the process of calculating the principal tensile strain, the shear strain component induced by the temperature gradient is superimposed on the principal tensile strain.

[0034] As can be understood, solid fraction refers to the volume fraction of the solid phase at a certain location during the solidification process of a cast billet. It is a dimensionless physical quantity characterizing the degree of solidification progress, with a value ranging from 0 to 1. The region on the cross-section of the cast billet where the solid fraction exceeds the bearing capacity threshold is a region that has formed a continuous solid skeleton and possesses the ability to bear mechanical loads. This region can effectively transfer and withstand stress. Regions where the solid fraction has not reached the bearing capacity threshold remain in a mushy state and do not possess effective bearing capacity; therefore, they are not included in the scope of mechanical analysis. Thus, the region where the solid fraction exceeds the bearing capacity threshold can be considered the effective computational domain for thermo-mechanical analysis. The bearing capacity threshold is a solid fraction threshold used to distinguish between the mushy region and the solid bearing region. It can be set according to the high-temperature mechanical properties and solidification morphology of the target steel grade. This threshold corresponds to the critical state where dendrites overlap to form a continuous solid skeleton and begin to possess significant tensile strength; no specific limitation is made here.

[0035] Here, the spatial constraint coefficient is a dimensionless correction multiplier, which can be determined by three physical quantities: the solid fraction of the region, the geometric distance, and the temperature gradient. It can be used as a correction factor in thermodynamic analysis to participate in the calculation of principal tensile strain, characterizing the stress amplification effect caused by uneven cooling and geometric constraints in the corner region. Among them, the geometric distance refers to the shortest spatial distance between the analyzed location and the adjacent billet surface, which can be used to measure the strength of the surface cooling constraint at this location. The smaller the geometric distance, the closer the location is to the billet surface, the stronger the external cooling constraint, and the more significant the stress concentration effect. The temperature gradient represents the amount of temperature change per unit distance along the cross-sectional direction, which can be used to quantify the degree of uneven cooling at this location. The larger the temperature gradient, the more significant the thermal expansion inconsistency at this location, and the greater the additional stress induced by it.

[0036] For example, the spatial constraint coefficient can be calculated by fusing the solid fraction value, geometric distance value, and temperature gradient value. A higher solid fraction value indicates a denser solid skeleton and higher stress transfer efficiency at that location. A smaller geometric distance value indicates stronger surface constraint and more significant stress concentration at that location. A larger temperature gradient value indicates more prominent thermal expansion inconsistencies and greater additional stress at that location. By normalizing the above three physical quantities according to their respective contribution weights to crack initiation and then multiplying or weighted summing them, a spatial constraint coefficient can be obtained to correct the thermodynamic analysis results. This quantifies the cooling inhomogeneity and geometric constraint effect in the corner region into correction factors that can participate in stress-strain calculations. For example, when the solid fraction at a certain location is 0.85, the geometric distance is 5 mm, and the temperature gradient is 2.5℃ / mm, the spatial constraint coefficient value obtained by the above fusing calculation method is 1.32. This value is greater than the baseline value of 1, indicating that the stress level at that location is amplified to 1.32 times the baseline state due to cooling inhomogeneity and geometric constraint effects.

[0037] Furthermore, a thermodynamic analysis can be performed on the region based on the spatial constraint coefficient. The spatial constraint coefficient can be used as a correction factor in the relevant terms of the stress balance equation or constitutive relation to calculate the principal tensile strain of the region and determine the degree of relative elongation deformation of the region in the direction of the principal tensile stress.

[0038] Here, due to the combined cooling effect of the two adjacent sides, the temperature gradient is more significant in the corner region of the cast billet. This temperature gradient induces a shear strain component in this region, which affects the synthesis result of the strain tensor. Therefore, in the calculation of the principal tensile strain, the shear strain component induced by the temperature gradient can be superimposed on the principal tensile strain. That is, during strain tensor synthesis, the shear strain component is included as an off-diagonal term in the calculation of the principal strain, so that the calculated principal tensile strain includes the driving effect of the shear effect caused by the temperature gradient on crack initiation. Specifically, during the strain tensor construction process, the shear strain component calculated based on the temperature gradient is filled into the corresponding position of the strain tensor matrix as an off-diagonal term. Then, eigenvalue decomposition is performed on the strain tensor, and the largest eigenvalue obtained from the decomposition is taken as the principal tensile strain at that position, thus realizing the fusion of the temperature gradient-induced shear effect with the principal tensile strain calculation result.

[0039] Thus, by using the region with a solid fraction exceeding the critical value for bearing capacity as the effective computational domain to exclude the mushy region that does not have the bearing capacity, introducing a spatial constraint coefficient to characterize the stress amplification effect caused by uneven cooling and geometric constraints, and superimposing the shear strain component induced by the temperature gradient when calculating the principal tensile strain, the principal tensile strain of the corner region of the billet during the solidification and cooling process can be calculated more accurately, making the calculation results closer to the actual stress state of the corner region, and providing a more accurate mechanical input for crack initiation determination.

[0040] S203, extract the spatiotemporal distribution data of the principal tensile strain in the target depth region corresponding to the corner of the continuously cast billet from the principal tensile strain data at each position on the cross-section of the billet.

[0041] Specifically, the above steps calculate the principal tensile strain data at each location on the cross-section of the billet where the solid fraction exceeds the critical bearing value. In the crack initiation prediction process, the spatial range can be further limited. That is, after obtaining the principal tensile strain data at each location where the solid fraction exceeds the critical bearing value, the data can be filtered according to the spatial coordinate range of the target depth region to extract the principal tensile strain values ​​at each location at different times that simultaneously meet the bearing conditions and spatial location conditions. This forms the spatiotemporal distribution data of the principal tensile strain in the target depth region of the corner of the continuously cast billet, which can be used in the subsequent crack initiation criterion determination process.

[0042] S102, establish the correlation between the critical threshold and the critical duration, and establish a crack initiation criterion based on the coupling effect of strain amplitude and duration according to the correlation.

[0043] Specifically, strain amplitude refers to the magnitude of the principal tensile strain during the solidification and cooling process, used to characterize the severity of tensile deformation experienced at that location at the current moment. Here, strain amplitude can specifically reflect the relationship between the principal tensile strain and the critical threshold. When the principal tensile strain exceeds the critical threshold, the amount of strain exceeding the threshold is the effective damage-driving amplitude. Duration represents the continuous duration of the over-threshold state, which is the time span from the moment the principal tensile strain first exceeds the critical threshold to the moment the principal tensile strain falls back below the critical threshold. It can be used to characterize the duration of the over-threshold state in the time dimension. Thus, establishing a crack initiation criterion based on the coupling effect of strain amplitude and duration can describe crack initiation as a damage process jointly controlled by strain over-limit and time accumulation, allowing the criterion to respond to both the strain amplitude and time length dimensions simultaneously, distinguishing it from a single-threshold criterion that treats crack initiation as an instantaneous event.

[0044] Here, in the crack initiation criterion, the condition for crack initiation can be set as the main tensile strain exceeding the critical threshold and the continuous duration of the over-threshold state reaching the critical duration. That is, the crack initiation condition is determined to be met only when both the strain amplitude exceeds the limit and the duration meets the standard. If only the strain exceeds the limit but the duration does not reach the critical value, the crack initiation judgment will not be triggered.

[0045] Understandably, considering the physical nature of crack initiation as damage accumulation, the critical conditions required for crack initiation are jointly determined by strain amplitude and time duration. The critical threshold and critical duration are not two independent empirical parameters; therefore, a correlation between the critical threshold and critical duration can be established using equal damage conditions. This correlation includes a first parameter characterizing the baseline ductility, a second parameter characterizing the feeding capability, and a third parameter characterizing the damage acceleration effect. Through this correlation defined by the first, second, and third parameters, the critical threshold decreases as the critical duration increases. In application, the crack initiation criterion can determine the corresponding critical threshold based on the actual duration of the state exceeding the threshold, overcoming the misjudgment caused by the fixed strain threshold criterion treating crack initiation as an instantaneous event.

[0046] Specifically, the equal damage condition means that the same amount of damage can be achieved through different combinations of strain amplitude and duration. A high strain amplitude can accumulate sufficient damage in a shorter duration, while a low strain amplitude requires a longer duration to achieve the same amount of damage. This physical relationship indicates that the critical threshold decreases as the critical duration increases.

[0047] Here, the relationship between the critical threshold and the critical duration can be expressed as follows: ; in, Represented as the critical threshold, it is the strain threshold value that the principal tensile strain needs to exceed under a given critical duration before it can effectively drive damage to the material. It is represented as the first parameter used to characterize the reference ductility. The reference ductility is the maximum variation limit of a material in the high-temperature brittle region without producing irreversible damage. When the principal tensile strain is below this value, no damage accumulation will occur regardless of the duration. It is expressed as the critical duration, which is the length of time required for the principal tensile strain to continuously exceed the critical threshold. The second parameter used to characterize the feeding ability, namely the characteristic feeding time, is a time constant that characterizes the effect of the feeding channel between dendrites in the mushy region on the damage accumulation rate modulation. The smaller the value, the stronger the feeding ability and the slower the damage accumulation rate. The third parameter used to characterize the damage acceleration effect is the damage acceleration index, which is a dimensionless index that characterizes the nonlinear cascade acceleration effect of micro-damage. Its value is greater than 1. The larger the value, the more significant the acceleration of the damage accumulation rate with the increase of the strain over-limit amplitude.

[0048] Here, the aforementioned baseline ductility, characteristic feeding time, and damage acceleration index can be set based on the high-temperature mechanical property test data of the target steel and the statistical data of cracks in the continuous casting site. Different steel grades correspond to different parameter values, which are not specifically limited here.

[0049] For example, taking the application of a 340mm×300mm rectangular billet of No. 45 steel from a steel plant as an example, parameter calibration was performed based on high-temperature tensile test data and field crack statistics. The baseline ductility was set to 0.005, the characteristic feeding time to 5.4 seconds, and the damage acceleration index to 1.75. When the critical duration was set to 6 seconds, the critical threshold calculated using the above formula was approximately 0.0097. The simplified criterion in engineering applications is that crack initiation is predicted when the principal tensile strain exceeds 0.009 after 6 seconds.

[0050] Specifically, in the crack initiation judgment condition generated based on this correlation, the critical threshold and critical duration can be used as a pair of coupled parameters to participate in the judgment. This allows the crack initiation criterion to dynamically adjust the corresponding critical threshold according to the actual duration of the state exceeding the threshold during application, avoiding misjudgment caused by using a fixed strain threshold.

[0051] In some other embodiments, when the damage acceleration index is obtained by parameter calibration based on the high-temperature tensile test data of the target steel, if the damage acceleration index is greater than 1, it indicates that the damage accumulation rate increases nonlinearly with the increase of the over-limit amplitude of the principal tensile strain. That is, the larger the over-limit amplitude, the faster the accumulated damage increases per unit time. This index can be used to characterize the acceleration effect caused by micropore aggregation and grain boundary slip instability during the micro-damage evolution process. The larger the value, the higher the sensitivity of the damage to the over-limit strain.

[0052] S103, using the crack initiation criterion, perform a time-series scan on the spatiotemporal distribution data of the principal tensile strain, and detect whether there is a time window in the spatiotemporal distribution data of the principal tensile strain that simultaneously satisfies the condition that the principal tensile strain exceeds a critical threshold and the duration of the over-threshold state reaches the critical duration; if the time window exists, predict that a subcutaneous crack will initiate at the corner of the continuously cast billet; if the time window does not exist, predict that there is no subcutaneous crack at the corner of the continuously cast billet.

[0053] Furthermore, after obtaining the spatiotemporal distribution data of the principal tensile strain within the target depth region of the continuously cast billet corner and establishing a crack initiation criterion based on the coupling effect of strain amplitude and duration, the spatiotemporal distribution data of the principal tensile strain can be time-series scanned using the crack initiation criterion to detect whether there exists a time window in the spatiotemporal distribution data that simultaneously satisfies the condition that the principal tensile strain exceeds the critical threshold and the continuous duration of the above-threshold state reaches the critical duration. This time window refers to a continuous time interval in which the value of the principal tensile strain remains above the critical threshold and the total length of this continuous interval reaches the critical duration. The existence or absence of this window directly reflects whether the target depth region at the corner has undergone a damage accumulation process sufficient to trigger crack initiation during solidification and cooling.

[0054] Specifically, if a time window exists, it means that the target depth region at the corner of the continuously cast billet has undergone a mechanical loading process during solidification and cooling where the strain amplitude exceeds the limit and the duration of the exceedance is sufficiently long. The damage in this region has accumulated to the critical level for crack initiation, and it can be predicted that subcutaneous cracks will initiate at the corner of the continuously cast billet. If no time window exists, it means that although there may be a brief period of strain amplitude exceeding the limit, the duration of the exceedance has not reached the critical duration, and the damage has not accumulated to the critical level. In this case, it can be predicted that there will be no subcutaneous cracks at the corner of the continuously cast billet.

[0055] For example, since the spatiotemporal distribution data of the principal tensile strain is recorded moment by moment along the casting direction of the continuously cast billet, during the detection time window, the temporal distribution data of the principal tensile strain in the target depth region at the corner of the continuously cast billet can be traversed along the casting direction of the target continuously cast billet, and it can be determined sequentially whether the principal tensile strain at each moment exceeds the current critical threshold. Here, the current critical threshold refers to the critical threshold corresponding to the cumulative duration of the over-threshold state at the current timing point, and is a dynamically changing judgment value as the duration of the over-threshold state increases. At the first timing, the current critical threshold can be set as the initial critical threshold, which can be set according to the specific characteristics of the target steel grade. Here, when the principal tensile strain is detected to exceed the current critical threshold for the first time, this moment can be recorded as the start time of the over-threshold state, timing can begin, and the principal tensile strain value at subsequent moments can be continuously monitored.

[0056] Specifically, during the timing process, since the continuous duration of the over-threshold state is continuously accumulated, and the current critical threshold is also dynamically changing, the current critical threshold can be updated based on the accumulated continuous duration of the over-threshold state through correlation. It is then used to determine whether the principal tensile strain at subsequent moments exceeds the updated current critical threshold, thus confirming whether the current moment is still in a valid over-threshold state. Simultaneously, the current critical duration corresponding to the updated current critical threshold is determined based on the correlation, to determine whether the currently accumulated timing duration has reached the corresponding critical duration.

[0057] Here, if the principal tensile strain falls below the updated current critical threshold during the timing period, it indicates that the over-threshold state has been interrupted. At this time, timing can be stopped and reset to zero, and timing can be restarted when the principal tensile strain exceeds the current critical threshold again, to ensure that the timing duration only includes the duration of the continuous over-threshold state. If the timing duration reaches the current critical duration, it is determined that a time window exists. The current critical duration is a duration value determined based on the correlation and corresponding to the updated current critical threshold, used to characterize the shortest continuous over-limit time required for crack initiation at the current threshold level.

[0058] In this way, by traversing and detecting the spatiotemporal distribution data of the principal tensile strain through time-series scanning, it is possible to identify the time window that simultaneously meets the two conditions of strain amplitude exceeding the limit and duration meeting the standard from the complete solidification and cooling process, thereby improving the matching degree between crack initiation prediction results and the physical reality of damage accumulation.

[0059] In some possible embodiments, based on the above prediction results, after determining the existence of a time window, the subcutaneous crack initiation zone of the target continuous casting billet can be determined according to the time period corresponding to the time window and the position interval along the casting direction of the target continuous casting billet within that time period. Since the time window corresponds to the solidification and cooling stage where the principal tensile strain continuously exceeds the limit and the duration reaches the critical value, this stage corresponds to a continuous position interval along the length direction of the continuous casting billet, and this position interval can be determined as the spatial range for crack initiation.

[0060] Furthermore, after determining the subcutaneous crack initiation zone, the corresponding cooling zone in the secondary cooling system can be determined based on the position of this zone along the length of the continuously cast billet. The cooling water volume, nozzle working status, and heat exchange conditions of this cooling zone can be investigated to locate the cause of the abnormal cooling that leads to the excessive and continuous strain at this location, thereby providing a basis for process adjustment.

[0061] The method, apparatus, medium, and equipment for predicting subcutaneous crack initiation at the corner of continuously cast billets provided in this embodiment establish a crack initiation criterion based on the coupling effect of strain amplitude and duration, and perform time-series scanning of the spatiotemporal distribution data of principal tensile strain. This enables an objective and quantitative determination of the risk of subcutaneous crack initiation at the corner of continuously cast billets, improving prediction accuracy and the reliability of online quality control.

[0062] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0063] Based on the same inventive concept, this disclosure also provides a device for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet, corresponding to the method for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet. Since the principle of the device in this disclosure for solving the problem is similar to the method for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0064] Reference Figure 3 The diagram shown is a schematic of a subcutaneous crack initiation prediction device 300 at the corner of a continuously cast billet provided in an embodiment of this disclosure. The device includes: Data acquisition module 301 is used to acquire the spatiotemporal distribution data of principal tensile strain in the target depth region corresponding to the corner of the target continuous casting billet; The criterion establishment module 302 is used to establish the correlation between the critical threshold and the critical duration, and to establish a crack initiation criterion based on the coupling effect of strain amplitude and duration according to the correlation; wherein, the correlation indicates that the critical threshold decreases as the critical duration increases; in the crack initiation criterion, the crack initiation judgment condition is that the main tensile strain exceeds the critical threshold and the continuous duration of the over-threshold state reaches the critical duration. The crack prediction module 303 is used to perform a time-series scan of the spatiotemporal distribution data of the principal tensile strain using the crack initiation criterion, and to detect whether there is a time window in the spatiotemporal distribution data of the principal tensile strain that simultaneously satisfies the condition that the principal tensile strain exceeds a critical threshold and the duration of the over-threshold state reaches the critical duration; if the time window exists, it is predicted that a subcutaneous crack will initiate at the corner of the continuously cast billet; if the time window does not exist, it is predicted that there is no subcutaneous crack at the corner of the continuously cast billet.

[0065] In some possible embodiments, the data acquisition module 301 is specifically used for: The process parameters of the continuous casting process corresponding to the target continuous casting billet are obtained, and the solidification heat transfer process of the target continuous casting billet is calculated based on the process parameters to obtain the temperature field distribution data of the cross section of the target continuous casting billet. Thermodynamic analysis was performed on the temperature field distribution data of the cross-section of the billet to calculate the principal tensile strain data at each location on the cross-section of the billet. From the principal tensile strain data at various locations on the cross-section of the billet, the spatiotemporal distribution data of the principal tensile strain within the target depth region corresponding to the corner of the continuously cast billet are extracted.

[0066] In some possible embodiments, the data acquisition module 301 is specifically used for: The measured water volume data of each side of the secondary cooling system corresponding to the target continuous casting billet are obtained respectively, and the heat transfer coefficient corresponding to each side is calculated based on the measured water volume data of each side. Based on the process parameters and the heat transfer coefficients corresponding to each side, the solidification heat transfer process of the target continuous casting billet is calculated.

[0067] In some possible embodiments, the data acquisition module 301 is specifically used for: On the cross-section of the billet, a region where the solid fraction exceeds the critical value for bearing capacity is determined; and a spatial constraint coefficient is obtained by the solid fraction, geometric distance, and temperature gradient of the region. Thermodynamic analysis is performed on the region based on the spatial constraint coefficient to calculate the principal tensile strain of the region; In the process of calculating the principal tensile strain, the shear strain component induced by the temperature gradient is superimposed on the principal tensile strain.

[0068] In some possible embodiments, the criterion establishment module 302 is specifically used for: A correlation between the critical threshold and the critical duration is established based on the condition of equal damage; wherein the correlation includes a first parameter for characterizing the baseline ductility, a second parameter for characterizing the compensation capability, and a third parameter for characterizing the damage acceleration effect.

[0069] In some possible embodiments, the crack prediction module 303 is specifically used for: The temporal distribution data of the principal tensile strain in the target depth region corresponding to the corner of the continuous casting billet is traversed along the casting direction of the target continuous casting billet, and it is determined in turn whether the principal tensile strain at each moment exceeds the current critical threshold. When the principal tensile strain is detected to exceed the current critical threshold for the first time, timing begins and the principal tensile strain is continuously monitored at subsequent moments. During the timing process, based on the accumulated continuous duration of the over-threshold state, the current critical threshold is updated through the correlation relationship, and it is further determined whether the main tensile strain at subsequent moments exceeds the updated current critical threshold. In addition, the current critical duration corresponding to the updated current critical threshold is determined through the correlation relationship. If the principal tensile strain falls below the updated current critical threshold during the timing period, the timing is stopped and reset to zero. The timing will restart when the principal tensile strain exceeds the current critical threshold again. If the timing duration reaches the current critical duration, it is determined that the time window exists.

[0070] In some possible embodiments, the crack prediction module 303 is further configured to: Based on the time period corresponding to the time window and the position interval along the casting direction of the target continuous casting billet within the time period, the subcutaneous crack initiation zone of the target continuous casting billet is determined, and the fault location is performed on the cooling zone corresponding to the subcutaneous crack initiation zone in the secondary cooling system corresponding to the target continuous casting billet.

[0071] Based on the same technical concept, this disclosure also provides a computer device. (See also...) Figure 4The diagram shown is a structural schematic of a computer device 400 provided in an embodiment of this disclosure, including a processor 401, a memory 402, and a bus 403. The memory 402 is used to store execution instructions and includes a main memory 4021 and an external memory 4022. The main memory 4021, also called internal memory, is used to temporarily store computational data in the processor 401, as well as data exchanged with external memory 4022 such as a hard disk. The processor 401 exchanges data with the external memory 4022 through the main memory 4021.

[0072] In this embodiment, the memory 402 is specifically used to store application code that executes the solution of this application, and its execution is controlled by the processor 401. That is, when the computer device 400 is running, the processor 401 communicates with the memory 402 through the bus 403, so that the processor 401 executes the application code stored in the memory 402, and then executes the method described in any of the foregoing embodiments.

[0073] The memory 402 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0074] Processor 401 may be an integrated circuit chip with signal processing capabilities. The aforementioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0075] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the computer device 400. In other embodiments of this application, the computer device 400 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0076] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the method for predicting the initiation of subcutaneous cracks at the corner of continuously cast billets as described in the above-described method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0077] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the method for predicting the initiation of subcutaneous cracks at the corner of continuously cast billets as described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0078] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0079] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0080] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0081] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0082] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0083] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit them. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure.

Claims

1. A method for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet, characterized in that, include: Acquire the spatiotemporal distribution data of principal tensile strain within the target depth region corresponding to the corner of the target continuous casting billet; A correlation is established between a critical threshold and a critical duration, and a crack initiation criterion based on the coupling effect of strain amplitude and duration is established according to the correlation. The correlation indicates that the critical threshold decreases as the critical duration increases. In the crack initiation criterion, the crack initiation condition is that the main tensile strain exceeds the critical threshold and the continuous duration of the over-threshold state reaches the critical duration. The spatiotemporal distribution data of the principal tensile strain is scanned using the crack initiation criterion to detect whether there is a time window in the spatiotemporal distribution data of the principal tensile strain that simultaneously satisfies the condition that the principal tensile strain exceeds a critical threshold and the duration of the over-threshold state reaches the critical duration. If the time window exists, it is predicted that a subcutaneous crack will initiate at the corner of the continuously cast billet; if the time window does not exist, it is predicted that there will be no subcutaneous crack at the corner of the continuously cast billet. The establishment of the correlation between the critical threshold and the critical duration includes: A correlation between the critical threshold and the critical duration is established based on the condition of equal damage; wherein, the correlation includes a first parameter for characterizing the baseline ductility, a second parameter for characterizing the compensation capability, and a third parameter for characterizing the damage acceleration effect; Accordingly, the correlation between the critical threshold and the critical duration is expressed as follows: ； in, Represented as the critical threshold; This is represented as the first parameter used to characterize the ductility of the reference. Represented as critical duration; This is represented as the second parameter used to characterize the ability to compensate for shrinkage. This is represented as the third parameter used to characterize the damage acceleration effect.

2. The method according to claim 1, characterized in that, The acquisition of spatiotemporal distribution data of principal tensile strain within the target depth region corresponding to the corner of the target continuously cast billet includes: The process parameters of the continuous casting process corresponding to the target continuous casting billet are obtained, and the solidification heat transfer process of the target continuous casting billet is calculated based on the process parameters to obtain the temperature field distribution data of the cross section of the target continuous casting billet. Thermodynamic analysis was performed on the temperature field distribution data of the cross-section of the billet to calculate the principal tensile strain data at each location on the cross-section of the billet. From the principal tensile strain data at various locations on the cross-section of the billet, the spatiotemporal distribution data of the principal tensile strain within the target depth region corresponding to the corner of the continuously cast billet are extracted.

3. The method according to claim 2, characterized in that, The calculation of the solidification heat transfer process of the target continuously cast billet based on the process parameters includes: The measured water volume data of each side of the secondary cooling system corresponding to the target continuous casting billet are obtained respectively, and the heat transfer coefficient corresponding to each side is calculated based on the measured water volume data of each side. Based on the process parameters and the heat transfer coefficients corresponding to each side, the solidification heat transfer process of the target continuous casting billet is calculated.

4. The method according to claim 2, characterized in that, The thermodynamic analysis of the temperature field distribution data of the cross-section of the billet includes: On the cross-section of the billet, a region where the solid fraction exceeds the critical value for bearing capacity is determined; and a spatial constraint coefficient is obtained by the solid fraction, geometric distance, and temperature gradient of the region. Thermodynamic analysis is performed on the region based on the spatial constraint coefficient to calculate the principal tensile strain of the region; In the process of calculating the principal tensile strain, the shear strain component induced by the temperature gradient is superimposed on the principal tensile strain.

5. The method according to claim 1, characterized in that, The step of performing a time-series scan of the spatiotemporal distribution data of the principal tensile strain using the crack initiation criterion includes: The temporal distribution data of the principal tensile strain in the target depth region corresponding to the corner of the continuous casting billet is traversed along the casting direction of the target continuous casting billet, and it is determined in turn whether the principal tensile strain at each moment exceeds the current critical threshold. When the principal tensile strain is detected to exceed the current critical threshold for the first time, timing begins and the principal tensile strain is continuously monitored at subsequent moments. During the timing process, based on the accumulated continuous duration of the over-threshold state, the current critical threshold is updated through the correlation relationship, and it is further determined whether the main tensile strain at subsequent moments exceeds the updated current critical threshold. In addition, the current critical duration corresponding to the updated current critical threshold is determined through the correlation relationship. If the principal tensile strain falls below the updated current critical threshold during the timing period, the timing is stopped and reset to zero. The timing will restart when the principal tensile strain exceeds the current critical threshold again. If the timing duration reaches the current critical duration, it is determined that the time window exists.

6. The method according to claim 1, characterized in that, After predicting that subcutaneous cracks will initiate at the corner of the continuously cast billet, the following steps are included: Based on the time period corresponding to the time window and the position interval along the casting direction of the target continuous casting billet within the time period, the subcutaneous crack initiation zone of the target continuous casting billet is determined, and the fault location is performed on the cooling zone corresponding to the subcutaneous crack initiation zone in the secondary cooling system corresponding to the target continuous casting billet.

7. A device for predicting the initiation of subcutaneous cracks at the corner of a continuously cast billet, characterized in that, include: The data acquisition module is used to acquire the spatiotemporal distribution data of principal tensile strain within the target depth region corresponding to the corner of the target continuous casting billet; The criterion establishment module is used to establish the correlation between the critical threshold and the critical duration, and to establish a crack initiation criterion based on the coupling effect of strain amplitude and duration according to the correlation; wherein, the correlation indicates that the critical threshold decreases as the critical duration increases; in the crack initiation criterion, the crack initiation judgment condition is that the main tensile strain exceeds the critical threshold and the continuous duration of the over-threshold state reaches the critical duration. The crack prediction module is used to perform a time-series scan of the spatiotemporal distribution data of the principal tensile strain using the crack initiation criterion, and to detect whether there is a time window in the spatiotemporal distribution data of the principal tensile strain that simultaneously satisfies the condition that the principal tensile strain exceeds a critical threshold and the continuous duration of the over-threshold state reaches the critical duration; if the time window exists, it is predicted that a subcutaneous crack will initiate at the corner of the continuously cast billet; if the time window does not exist, it is predicted that there is no subcutaneous crack at the corner of the continuously cast billet. Specifically, the criterion establishment module is used for: A correlation between the critical threshold and the critical duration is established based on the condition of equal damage; wherein, the correlation includes a first parameter for characterizing the baseline ductility, a second parameter for characterizing the compensation capability, and a third parameter for characterizing the damage acceleration effect; Accordingly, the correlation between the critical threshold and the critical duration is expressed as follows: ； in, Represented as the critical threshold; This is represented as the first parameter used to characterize the ductility of the reference. Represented as critical duration; This is represented as the second parameter used to characterize the ability to compensate for shrinkage. This is represented as the third parameter used to characterize the damage acceleration effect.

8. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

9. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

Images