Method, device, medium and equipment for diagnosing faults of continuous casting secondary cooling system

Abstract

The present disclosure relates to the technical field of metallurgical continuous casting equipment state monitoring, and provides a continuous casting secondary cooling system fault diagnosis method, device, medium and equipment, through obtaining continuous casting process parameters and performing solidification heat transfer calculation to determine the temperature field evolution data of the corner of the casting blank, and then establishing the position growth curve of the shell thickness along the direction of the casting flow and obtaining the inverse corresponding relationship between the position and the shell thickness through inverse mapping, converting the historical depth distribution statistical information of the subcutaneous crack of the corner of the casting blank into the crack formation spatial window along the direction of the casting flow, and then determining the corresponding main tensile strain space-time distribution data of the spatial window based on the real-time collected cooling water volume data of each section of the secondary cooling system and the continuous casting process parameters, and extracting the over-threshold feature parameter group after traversing and judging the over-threshold region in the window to determine the fault position and fault type. The present disclosure realizes the fault position and type diagnosis of the secondary cooling system through crack depth space mapping and water volume strain over-threshold analysis.

Description

Technical Field

[0001] This disclosure relates to the field of condition monitoring technology for metallurgical continuous casting equipment, and more specifically, to a method, apparatus, medium, and equipment for fault diagnosis of a continuous casting secondary cooling system. Background Technology

[0002] The secondary cooling system in continuous casting consists of multiple spray zones and is responsible for the controlled cooling of the billet after it leaves the crystallizer. The uniformity of the secondary cooling system directly affects the solidification process and stress state inside the billet, making it a critical factor in determining the billet quality. In actual production, frequent anomalies in the secondary cooling system can lead to uneven cooling at the corners of the billet, which in turn can induce quality defects such as subcutaneous cracks at the corners, severely restricting the billet yield and the stability of subsequent rolling performance.

[0003] In related technologies, the detection and location of secondary cooling system faults mainly rely on periodic manual inspections, monitoring alarms based on total water volume or total pressure, indirect inference based on billet surface temperature, and post-event analysis of low-magnification inspection results. However, manual inspections have poor timeliness and low coverage, making it difficult to detect some hidden faults; total water volume or total pressure monitoring can only detect large deviations in water volume or pressure across the entire section, failing to identify local anomalies or determine the specific location of the fault; surface temperature measurement is constrained by factors such as fixed measurement locations and oxide scale interference, making it difficult to accurately correlate temperature anomalies to specific sections and locations; low-magnification inspection is an offline post-event analysis with a long cycle, making it impossible to provide real-time early warnings during the casting process. Summary of the Invention

[0004] This disclosure provides at least one method, apparatus, medium, and equipment for diagnosing faults in a continuous casting secondary cooling system. By mapping the historical depth distribution of subcutaneous cracks at the corner of the billet to a spatial window along the casting flow direction, and combining real-time cooling water volume data to determine the spatiotemporal distribution of principal tensile strain within the window to extract over-threshold characteristic parameters, the diagnosis of the fault location and type of the secondary cooling system is realized.

[0005] This disclosure provides a method for diagnosing faults in a continuous casting secondary cooling system, including: Obtain the continuous casting process parameters corresponding to the target continuous casting billet, and perform solidification heat transfer calculation on the target continuous casting billet based on the continuous casting process parameters to determine the temperature field evolution data of the corner of the target continuous casting billet. Based on the temperature field evolution data, a growth curve of the billet shell thickness along the casting flow direction as a function of position is established, and the growth curve is inversely mapped to obtain the inverse correspondence between the position and the billet shell thickness. The historical depth distribution statistics of subcutaneous cracks at the corner of the target continuous casting billet are obtained, and the historical depth distribution statistics are mapped to a crack formation space window along the casting flow direction using the reverse correspondence; wherein, the historical depth distribution statistics are the statistical results of the inspection of continuous casting billets with subcutaneous cracks at the corner in historical heats corresponding to the steel grade and cross-sectional size of the target continuous casting billet; Real-time acquisition of cooling water volume data for each section and side of the secondary cooling system corresponding to the target continuous casting billet; and determination of the spatiotemporal distribution data of principal tensile strain corresponding to the crack formation space window based on the cooling water volume data and the continuous casting process parameters. Within the crack formation space window, the spatiotemporal distribution data of the principal tensile strain is traversed to determine whether there is an over-threshold region that satisfies the preset crack initiation criterion. If so, the over-threshold feature parameter group of the over-threshold region is extracted. The fault information of the secondary cooling system is determined based on the set of over-threshold feature parameters; wherein the fault information includes at least the fault location and the fault type.

[0006] This disclosure provides a fault diagnosis device for a continuous casting secondary cooling system, comprising: The data preparation module is used to obtain the continuous casting process parameters corresponding to the target continuous casting billet, and to perform solidification heat transfer calculations on the target continuous casting billet based on the continuous casting process parameters, so as to determine the temperature field evolution data of the corner of the target continuous casting billet. The relationship mapping module is used to establish a growth curve of the billet shell thickness along the casting flow direction with position based on the temperature field evolution data, and to perform inverse mapping on the growth curve to obtain the inverse correspondence between the position and the billet shell thickness. The window determination module is used to obtain the historical depth distribution statistics of subcutaneous cracks at the corner of the target continuous casting billet, and to map the historical depth distribution statistics into a crack formation space window along the casting flow direction using the reverse correspondence; wherein, the historical depth distribution statistics are the statistical results of the inspection of continuous casting billets with corner subcutaneous cracks that have occurred in historical heats corresponding to the steel grade and cross-sectional size of the target continuous casting billet; The data acquisition module is used to collect the cooling water volume data of each section and side of the secondary cooling system corresponding to the target continuous casting billet in real time, and determine the spatiotemporal distribution data of the principal tensile strain corresponding to the crack formation space window based on the cooling water volume data and the continuous casting process parameters. The crack detection module is used to traverse the spatiotemporal distribution data of the principal tensile strain within the crack formation space window, determine whether there is an over-threshold region that meets the preset crack initiation criterion, and if so, extract the over-threshold feature parameter group of the over-threshold region. The fault determination module is used to determine the fault information of the secondary cooling system based on the set of over-threshold feature parameters; wherein the fault information includes at least the fault location and the fault type.

[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, they perform the continuous casting secondary cooling system fault diagnosis method as described in any of the above possible embodiments.

[0008] This disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the continuous casting secondary cooling system fault diagnosis method as described in any of the above possible embodiments.

[0009] The continuous casting secondary cooling system fault diagnosis method, apparatus, medium, and equipment provided in this embodiment map the historical depth distribution of subcutaneous cracks at the corner of the billet into a spatial window along the casting flow direction, and combine real-time cooling water volume data to determine the spatiotemporal distribution of principal tensile strain within the window to extract over-threshold characteristic parameters. This achieves spatial alignment and correlation analysis between crack history statistical information and real-time cooling water volume and strain field, and can determine the fault location and type based on this correlation analysis, providing a quantifiable diagnostic basis for online condition assessment and targeted maintenance of the secondary cooling system.

[0010] 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

[0011] 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.

[0012] Figure 1 A flowchart of a fault diagnosis method for a continuous casting secondary cooling system provided in an embodiment of this disclosure is shown; Figure 2 A flowchart of a fault information determination method provided by an embodiment of this disclosure is shown; Figure 3 A flowchart of another fault information determination method provided by an embodiment of this disclosure is shown; Figure 4 This diagram shows a structural schematic of a fault diagnosis device for a continuous casting secondary cooling system provided in an embodiment of the present disclosure; Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of this disclosure is shown. Detailed Implementation

[0013] 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.

[0014] 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.

[0015] 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.

[0016] To facilitate understanding of this embodiment, the executing entity of the continuous casting secondary cooling system fault diagnosis method provided in this disclosure will first be described in detail. The executing entity of the continuous casting secondary cooling system fault diagnosis method provided in this disclosure is a computer device. This computer device can be a terminal device or a server. The terminal device can also be a mobile device, user terminal, terminal, handheld device, computing device, vehicle-mounted device, 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.

[0017] The fault diagnosis method for the continuous casting secondary cooling system provided in this application embodiment will be described in detail below with reference to the accompanying drawings. See also Figure 1 The diagram shows a flowchart of a fault diagnosis method for a continuous casting secondary cooling system provided in this embodiment of the present disclosure. The method includes the following steps S101 to S106: S101, obtain the continuous casting process parameters corresponding to the target continuous casting billet, and perform solidification heat transfer calculation on the target continuous casting billet according to the continuous casting process parameters to determine the temperature field evolution data of the corner of the target continuous casting billet.

[0018] It is understandable 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 continuous casting process parameters corresponding to the target continuously cast billet refer to the process parameters corresponding to the continuous casting process of molten steel into the billet through a continuous casting machine. These parameters can include casting temperature, casting speed, crystallizer cooling water flow rate, and the reference water flow rate of each cooling section. These process parameters are collected and recorded in real time in the continuous casting process control system.

[0019] Here, solidification heat transfer calculation refers to the process of numerically solving the temperature distribution and variation law of a continuously cast billet throughout the entire solidification process from the crystallizer to the end of the secondary cooling section, based on the basic principles of heat transfer. It is a quantitative description method of the solidification heat transfer process of a continuously cast billet. Solidification heat transfer calculation can numerically simulate the spatiotemporal distribution of the cross-sectional temperature field of a continuously cast billet during solidification and cooling, thereby providing basic data for subsequent calculation of billet shell thickness and thermal stress analysis.

[0020] Specifically, solidification heat transfer calculations can be performed numerically using the finite difference method to obtain the temperature distribution of the continuously cast billet at any time along its cross-section. The finite difference method is a numerical solution method for partial differential equations. Based on the governing equations and boundary conditions of the heat transfer problem, the continuous spatial domain can be discretized into a finite number of grid nodes, and the solution can be performed layer by layer in the time domain to obtain the complete evolution process of the temperature field. In the solidification heat transfer calculation of the continuously cast billet, the transient heat conduction equation of a two-dimensional cross-section can be used as the governing equation, and the equivalent heat capacity method can be used to handle the release process of latent heat during solidification, so as to accurately describe the thermodynamic behavior during the solid-liquid phase transition.

[0021] Furthermore, after obtaining the temperature data at various locations on the cross-section of the continuously cast billet, the temperature field evolution data of the corner of the target continuously cast billet can be determined. The corner of the billet refers to the edge region formed by the intersection of two adjacent sides of the continuously cast billet cross-section and its surrounding neighborhood. For example, for a rectangular billet, the corner includes four corner regions: the left corner of the inner arc, the right corner of the inner arc, the left corner of the outer arc, and the right corner of the outer arc, corresponding to the four right-angled positions of the billet cross-section.

[0022] Here, during the solidification and cooling process, the corner region will be subjected to combined tensile stress from two adjacent surface directions. That is, tensile stress along two mutually perpendicular directions acts on the corner region at the same time. This two-dimensional stress state is more complex than the uniaxial stress state of the planar region. Therefore, the corner region becomes a high-risk area for crack initiation.

[0023] Here, temperature field evolution data refers to the complete set of data on the change of the corner temperature of the billet with time and spatial location calculated along each time step within the continuous time range covered by the solidification heat transfer calculation. It can reflect the complete process of temperature decay with time in the corner region from the crystallizer outlet to the end of the secondary cooling section. It can provide a data basis for subsequent determination of the billet shell thickness growth curve and thermal stress distribution, and can track the temperature value at any location in the corner region at each calculation time step.

[0024] S102, Based on the temperature field evolution data, establish a growth curve of the billet shell thickness along the casting flow direction as a function of position, and perform inverse mapping on the growth curve to obtain the inverse correspondence between the position and the billet shell thickness.

[0025] Here, the growth curve is a functional relationship curve describing the gradual increase in billet shell thickness along the casting flow direction with position, reflecting the complete process of the solidification front advancing along the casting flow direction in the corner region of the billet. Since temperature field evolution data can provide the position information of the isotherms where the corner region temperature equals the solidus temperature at each time step, providing the spatiotemporal trajectory of the solidification front advancement, a growth curve of billet shell thickness varying with the casting flow direction can be established based on the temperature field evolution data. The billet shell thickness refers to the thickness of the solid metal layer from the billet surface along the surface normal direction inwards to the solidification front, and is a parameter measuring the solidification process of the continuously cast billet. In continuous casting production, due to the continuous forced cooling effect of the secondary cooling section's sprayed water on the billet shell surface, the solidification front continuously advances towards the center of the billet, so the billet shell thickness gradually increases as the billet moves downwards along the casting flow direction. The casting flow direction refers to the overall direction in which the continuously cast billet travels along the guide path of the continuous casting machine from the meniscus position of the crystallizer. For an arc-shaped continuous casting machine, the casting flow direction is vertically downward at the crystallizer outlet, gradually transitions to an arc shape after passing through the bending section, and then returns to the horizontal direction after passing through the straightening section.

[0026] For example, in continuous casting production, the position of the meniscus in the crystallizer can usually be used as the starting point of the casting flow direction, and any position along the casting flow direction can be calibrated by the arc length distance of that position from the meniscus. For example, in the growth curve, the horizontal axis represents the position along the casting flow direction, which physically means the arc length distance of that position from the meniscus, and the vertical axis represents the shell thickness of the billet corner at that position. Thus, a function curve of the shell thickness changing with the position of the casting flow direction can be formed, which can be denoted as S(z), where z represents the arc length distance along the casting flow direction from the meniscus.

[0027] In some possible embodiments, the process of establishing a growth curve based on temperature field evolution data may include the following steps (1) to (2): (1) Based on the temperature field evolution data, determine the position of the solidification front step by step along the surface normal of the corner of the billet; (2) Obtain the position along the casting flow direction and the billet shell thickness at the position corresponding to each calculation time step, and generate the growth curve with the position along the casting flow direction as the abscissa and the billet shell thickness as the ordinate.

[0028] It is understandable that the surface normal of the billet corner refers to the direction perpendicular to the corner surface and pointing towards the interior of the billet, serving as the spatial reference direction for determining the solidification front position. For the corner region of a continuously cast billet, there are two adjacent surfaces: the upper and lower surfaces, or the inner and outer arc surfaces. Each of these two surfaces has an independent normal direction. When searching for the solidification front position along the surface normal, one can start from the corner vertex along the angle bisector or along the normal directions of the two surfaces respectively. Based on temperature field evolution data, searching for the solidification front position time-step by time along the surface normal direction of the billet corner allows tracking the temperature change from the billet surface to the interior, determining the specific location of the solidus temperature isotherm within the billet corner cross-section. The solidification front position refers to the location of the isotherm within the billet corner cross-section where the temperature equals the solidus temperature. It represents the interface between the solidified shell and the unsolidified molten steel inside, identifying the inner boundary of the solidified shell and providing a spatial positioning basis for subsequent calculations of the shell thickness at this location.

[0029] Specifically, in the temperature field distribution of the corner cross-section of the billet, each calculation node can be gradually traversed from the corner surface along the normal direction towards the center. When the temperature of a node is equal to the solidus temperature of the steel grade, it can be determined that the node is located at the solidification front. The solidification front can divide the corner region into an outer solid billet shell and an inner solid-liquid two-phase region or liquid steel. The thickness of the outer solid billet shell is the billet shell thickness at that location.

[0030] Here, after determining the position of the solidification front, the position along the casting flow direction and the billet shell thickness at that position can be obtained for each calculation time step. The position along the casting flow direction can refer to the arc length distance traversed from the meniscus as the starting origin along the continuous casting billet's travel path to the current calculation position; the billet shell thickness refers to the vertical distance from the surface of the billet corner along the normal direction to the position of the solidification front, which is equal to the spatial interval between the solidification front position and the surface of the billet corner. After obtaining the position along the casting flow direction and the billet shell thickness at that position for each calculation time step, a growth curve can be established with the position along the casting flow direction as the abscissa and the billet shell thickness as the ordinate. This growth curve reflects the monotonically increasing change law of the billet shell thickness at the billet corner as the position along the casting flow direction increases throughout the entire solidification process from the meniscus to the end of the secondary cooling section, providing basic data for subsequently establishing a quantitative mapping relationship between the billet shell thickness and the position along the casting flow direction.

[0031] Furthermore, the growth curve is a graphical representation of the one-to-one correspondence between the billet shell thickness and the position along the casting flow direction, characterizing the monotonically increasing billet shell thickness with increasing casting flow distance during solidification. In solidification heat transfer calculations, the growth curve, with the position along the casting flow direction as the independent variable and the billet shell thickness as the dependent variable, reflects a forward mapping relationship. However, in practical engineering applications, it is sometimes necessary to determine the corresponding casting flow direction position from a known billet shell thickness. Therefore, the growth curve can also be reverse-mapped to determine the inverse correspondence between the billet shell thickness and the position along the casting flow direction, forming an inverse correspondence. The inverse correspondence refers to a functional mapping relationship where the billet shell thickness is the input variable and the position along the casting flow direction is the output variable. This allows for querying the casting flow direction position of any known billet shell thickness value, serving as a quantitative basis for subsequently converting the crack depth distribution range into a spatial window along the casting flow direction.

[0032] For example, when performing inverse mapping on the growth curve, a numerical inverse interpolation method can be used. This involves exchanging the coordinates of the billet shell thickness value and the position value along the casting flow direction in the original data points of the growth curve, and then performing interpolation fitting on the exchanged data points. An inverse mapping function is established with the billet shell thickness value as the independent variable and the position along the casting flow direction as the dependent variable, which can be denoted as z(S), where S represents the billet shell thickness value and z represents the position along the casting flow direction. This allows obtaining the position along the casting flow direction corresponding to any billet shell thickness value. Specifically, the numerical inverse interpolation method refers to exchanging the horizontal and vertical coordinates of discrete data points on the growth curve, and then performing interpolation fitting on the exchanged data points to establish a functional relationship with the billet shell thickness as the independent variable and the position along the casting flow direction as the dependent variable. For example, when it is known that subcutaneous cracks at the corners are concentrated in the range of 20mm to 30mm in the depth of the billet shell, the inverse mapping function z(S) can be used to query the position along the casting flow direction corresponding to a billet shell thickness of 20mm and the position along the casting flow direction corresponding to a billet shell thickness of 30mm, so that the depth range can be mapped to the positioning range along the casting flow direction.

[0033] S103, obtain the historical depth distribution statistics of subcutaneous cracks at the corner of the target continuous casting billet, and use the reverse correspondence to map the historical depth distribution statistics into a crack formation space window along the casting flow direction.

[0034] Here, historical depth distribution statistics refer to the set of data on the frequency distribution of cracks at different depths from the surface on the corner cross-section of billets that have developed subcutaneous corner cracks in a large number of historical heats of the same steel grade and cross-sectional dimensions as the target continuous casting billet. This data is obtained after low-magnification acid etching inspection of the billets. Historical depth distribution statistics can be obtained from the results of regular low-magnification inspections of billets conducted by the steel plant's quality management department. Specifically, during billet production, billets of different steel grades and cross-sections are sampled periodically. After the billet cross-section is cut, it undergoes acid etching treatment, making the cracks clearly visible on the etched test pieces. Quality inspectors then measure and record the vertical depth of each crack from the billet surface. All measurement results corresponding to the same steel grade and cross-section are statistically analyzed according to depth intervals to form a crack depth distribution histogram, which serves as the historical depth distribution statistics for each steel grade. Among them, the historical depth distribution statistics can include the distribution data of the number of cracks with depth, such as the depth range with the highest crack occurrence frequency, the total frequency of crack occurrence in each depth range, and the distribution range of cracks in the depth direction. These are the basic data reflecting the distribution law of corner subcutaneous crack depth of this steel grade under specific cross-section and process conditions.

[0035] Understandably, the inverse correspondence establishes a functional mapping between the billet shell thickness and its position along the casting flow direction. That is, given any billet shell thickness value, the corresponding position along the casting flow direction can be determined through the inverse correspondence. The depth range of concentrated crack distribution represents the range of vertical distances between the cracks on the corner cross-section of the billet and the billet surface. Since this vertical distance has the same dimensions and spatial scale as the billet shell thickness, and the crack initiation location is precisely at a certain depth inside the billet shell, this depth range can be considered a specific range of values ​​for the billet shell thickness. Therefore, using the aforementioned inverse correspondence, the depth range of concentrated crack distribution reflected by historical depth distribution statistics can be converted into the range of casting flow direction positions of the billet shell within that depth range.

[0036] Specifically, the crack initiation spatial window is a positioning interval along the casting flow direction determined jointly by historical depth distribution statistics and inverse correspondence. This positioning interval corresponds to the length range covered by the billet shell thickness range where cracks are most likely to initiate along the casting flow direction. Its start and end positions correspond to the lower and upper limits of the crack depth interval along the casting flow direction in the inverse correspondence, respectively. Thus, compared to a direct description of the depth interval, the crack initiation spatial window transforms depth-dimensional information into positional information along the casting flow direction, making it more suitable for subsequent extraction and analysis of the spatiotemporal distribution data of the principal tensile strain based on the casting flow direction.

[0037] For example, the depth range with the highest crack distribution frequency can be determined based on historical depth distribution statistics. The lower limit and upper limit of this depth range constitute a continuous depth range. The positions along the casting flow direction corresponding to the lower limit and upper limit of this continuous depth range are queried using the reverse correspondence, thereby determining the casting flow position range corresponding to the depth range with the highest crack distribution frequency. This range is a continuous range from the casting flow direction position corresponding to the lower limit to the casting flow direction position corresponding to the upper limit. This range covers the casting flow direction range with the highest risk of crack initiation, and thus the casting flow position range can be determined as the crack formation spatial window.

[0038] Here, taking the production of a continuously cast billet with a cross-section of 340mm × 300mm as an example, through statistical analysis of a large number of historical furnace low-magnification acid etching inspection records, it can be determined that the depth range with the highest crack distribution frequency is within the depth range of 20mm to 30mm from the corner surface of the billet. Based on this depth range, the positions along the casting flow direction corresponding to a billet shell thickness of 20mm and 30mm can be looked up using the reverse correspondence. The interval between these two positions can then be defined as the crack formation spatial window, which corresponds to a continuous interval along the casting flow direction.

[0039] In some other embodiments, the crack formation spatial window can also be determined based on other statistical parameters in the historical depth distribution statistics, such as the overall depth range of crack distribution in historical samples, or the depth range where the frequency of crack occurrence exceeds a predetermined threshold. No specific limitation is made here, and it can be determined based on the distribution characteristics of the actual statistical data.

[0040] S104, real-time acquisition of cooling water volume data for each section and side of the secondary cooling system corresponding to the target continuous casting billet, and determination of the spatiotemporal distribution data of principal tensile strain corresponding to the crack formation space window based on the cooling water volume data and the continuous casting process parameters.

[0041] 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 responsible for forced water cooling of the billet after exiting the crystallizer to control the solidification process. It is a component of the continuous casting machine for forced cooling of the billet after exiting the crystallizer. The secondary cooling system is divided into several independent cooling sections along the casting flow direction. Each cooling section has independent water supply pipes and nozzles at four points on the billet's cross-section, spraying and cooling the inner arc side, outer arc side, left side, and right side of the billet, respectively. The cooling water volume data for each section and side of the secondary cooling system refers to the actual volume of water sprayed per unit time measured by flow meters installed in the water supply pipes of each side within each cooling section. This data exists in the form of measured flow rate values ​​for each section and side, reflecting the actual cooling intensity of each side under current operating conditions and serving as the basic input for characterizing the current operating status of the secondary cooling system.

[0042] Specifically, by collecting cooling water volume data for each segment and edge in real time, the actual cooling boundary conditions experienced by the target continuously cast billet at the current moment can be obtained. Then, based on the cooling water volume data for each segment and edge and the continuous casting process parameters, the spatiotemporal distribution data of the principal tensile strain corresponding to the crack formation space window can be determined. This data can reflect the variation law of the principal tensile strain at the corner of the billet within the crack formation space window with time and position, providing a quantitative assessment basis for crack initiation risk.

[0043] Here, the spatiotemporal distribution data of the principal tensile strain can include the distribution of the principal tensile strain at each position along the casting flow direction in the target depth region at the corner of the billet within the crack formation space window, as well as the curve of the principal tensile strain at each position changing with time. This can then determine whether there is a situation where the principal tensile strain at each position exceeds the critical threshold, so as to identify the risk area for crack initiation.

[0044] In some possible embodiments, considering that cooling water volume data directly affects the heat exchange intensity of the billet surface, and that different cooling sections and different sides correspond to different crack initiation risk modes, solidification heat transfer and thermo-mechanical coupling calculations can be performed based on real-time water volume data to solve for the spatiotemporal distribution data of the principal tensile strain, specifically including the following steps (a) to (b): (a) Calculate the convective heat transfer coefficient of each side based on the cooling water volume data of each section and side of the secondary cooling system, and use the convective heat transfer coefficient as the boundary condition for solidification heat transfer calculation. Calculate the solidification heat transfer process of the target continuous casting billet in the crack formation space window to obtain the temperature field distribution of the target continuous casting billet in the crack formation space window. (b) Perform thermodynamic analysis on the temperature field distribution, calculate the principal tensile strain in the target depth region of the billet corner within the crack formation space window, and obtain the spatiotemporal distribution data of the principal tensile strain.

[0045] It is understandable that the convective heat transfer coefficient refers to the rate coefficient of heat transfer between the surface of the billet per unit area and the cooling water under a unit temperature difference. It is a physical quantity characterizing the heat exchange capacity between the surface of the billet and the cooling medium under spray cooling conditions. Based on the cooling water volume data of each section and each side, the convective heat transfer coefficient of each side can be calculated separately. This coefficient can be used as the boundary condition for solidification heat transfer calculation, that is, the heat flux density boundary or the third type of heat transfer boundary of the billet surface, thereby realizing the temperature field calculation based on the measured water volume data, and obtaining the temperature field distribution of the target continuously cast billet within the crack formation space window. Here, unlike the solidification heat transfer calculation in step S101 above, the solidification heat transfer calculation in step S104 is an online real-time calculation with water volume boundary conditions. Its purpose is to obtain the temperature field distribution under the current actual cooling conditions for subsequent strain analysis, while the solidification heat transfer calculation in step S101 is a benchmark calculation under typical process parameters. Its purpose is to obtain temperature field evolution data under standard operating conditions to establish the billet shell thickness growth curve. Even if the continuous casting process parameters are the same, the measured water volume data of each side of each section of the secondary cooling is different from the reference water volume data, so the calculated spatiotemporal distribution of the principal tensile strain is also different.

[0046] Here, the temperature field distribution provides the temperature values ​​at different times for various locations in the corner region of the billet within the crack formation space window. Performing thermodynamic analysis on the temperature field distribution can determine the thermal stress and thermal strain generated in the corner region of the billet due to the obstruction of thermal expansion during temperature changes, and then calculate the principal tensile strain in this region. The target depth region is the depth interval corresponding to the historical depth distribution statistics, and the principal tensile strain refers to the tensile strain component in the direction of the maximum principal strain in the corner region of the billet; it is a physical quantity characterizing the degree of tensile deformation of the material under complex stress conditions.

[0047] Specifically, thermodynamic analysis is an analytical method based on thermoelastic or thermoelastic-plastic theory. It uses the temperature field distribution 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. These parameters can be determined through high-temperature tensile tests or obtained from material property databases.

[0048] For example, the specific solution process of thermo-mechanical analysis may include: first, determining the temperature load sequence of each node in the target depth region of the billet corner at each time step based on the temperature field distribution, and then determining the thermal strain increment of each node based on the temperature load sequence, using the thermal strain increment as the initial strain condition; then, solving the stress balance equation to obtain the stress field distribution in the region based on the geometric constraint conditions of the billet corner region and the high-temperature mechanical constitutive parameters of the material, and further solving the stress field to obtain the strain field distribution based on the geometric equation and physical equation, and extracting the principal tensile strain component from the strain field as the principal tensile strain value at that location.

[0049] In this way, by converting the cooling water volume data of each segment and each side into the convective heat transfer coefficient of each side and using it as the boundary condition for solidification heat transfer calculation, the independent information of the actual cooling state of each direction of the secondary cooling system can be preserved, realizing the quantitative characterization of the anisotropy of the cooling space. Furthermore, through thermo-mechanical analysis calculation, the spatiotemporal distribution data of the principal tensile strain can be obtained, realizing the quantitative transmission from the abnormal cooling water volume to the mechanical driving conditions for crack initiation, and improving the accuracy of fault diagnosis.

[0050] S105, within the crack formation space window, traverse the spatiotemporal distribution data of the principal tensile strain to determine whether there is an over-threshold region that satisfies the preset crack initiation criterion. If so, extract the over-threshold feature parameter group of the over-threshold region.

[0051] Furthermore, the crack initiation spatial window is a continuous positional interval along the casting flow direction, and each position within this interval has corresponding principal tensile strain data in time series form. By traversing the spatiotemporal distribution data of principal tensile strain position by position along the casting flow direction within the crack initiation spatial window, it is possible to sequentially determine whether there is a time period that satisfies the crack initiation conditions at each position within the window. Here, the preset crack initiation criterion is a judgment criterion used to determine whether a crack has the conditions for initiation, which can identify abnormal states in the principal tensile strain time series data as crack initiation. The preset crack initiation criterion can be expressed as the principal tensile strain value exceeding a pre-calibrated critical strain threshold, and the duration of the principal tensile strain continuously exceeding the critical strain threshold is not less than the pre-calibrated critical duration. This judgment criterion is based on the physical mechanism of damage accumulation. When the principal tensile strain exceeds the critical level that the material can withstand and this over-threshold state continues for a certain duration, it is considered that the mechanical conditions for crack initiation are met at that position.

[0052] Here, the critical strain threshold and critical duration can be calibrated as follows: obtain the principal tensile strain time series data and corresponding low-magnification test results of multiple historical furnaces within the crack initiation space window, take the highest strain value and shortest duration of the furnaces in which no cracks appeared in the low-magnification test results as the benchmark, combine the strain value and duration of the furnaces in which cracks appeared, and adjust the critical strain threshold and critical duration to make the comprehensive matching degree between the crack initiation judgment results of historical furnaces and the low-magnification test results the highest, and determine the parameter pair corresponding to the highest comprehensive matching degree as the critical strain threshold and critical duration.

[0053] In some other embodiments, the critical strain threshold and critical duration can also be set according to the steel grade, cross-sectional size and casting speed of the target continuous casting billet through high-temperature mechanical property tests of materials or field experience, and are not specifically limited here.

[0054] For example, the process of traversing the spatiotemporal distribution data of principal tensile strain within the crack initiation space window and identifying regions exceeding the threshold may include the following steps (I) to (III): (I) Within the crack formation space window, the corresponding main tensile strain time sequence data is read point by point from the main tensile strain spatiotemporal distribution data along the casting flow direction.

[0055] Here, within the crack formation space window, the principal tensile strain time sequence data at each location can be read point by point along the casting flow direction according to the preset spatial step size, and then it can be determined in turn whether there is a time period within the space window that meets the crack initiation criterion.

[0056] (II) For each current reading point, determine whether there is a time period in the main tensile strain timing data that satisfies the preset crack initiation criterion.

[0057] Specifically, for each current reading point, all continuous time periods in the principal tensile strain time series data at that location can be extracted. Then, it can be determined whether there are any periods in these continuous time periods where the principal tensile strain continuously exceeds the critical strain threshold and the duration of this continuous over-threshold state at the current reading point is not less than the critical duration, so as to determine whether the mechanical conditions for crack initiation are met at that location.

[0058] (III) If it exists, the current reading point is marked as a crack initiation candidate point, and the continuous region along the casting flow direction formed by all the crack initiation candidate points is determined as the over-threshold region.

[0059] Here, if a time period exists that satisfies the preset crack initiation criterion, it indicates that a moment satisfying the mechanical conditions for crack initiation has occurred at that reading point. In this case, the current reading point can be marked as a candidate point for crack initiation. By marking points satisfying the criterion at the same spatial location as candidate points, multiple crack initiation candidate points continuously distributed along the casting flow direction can form a continuous spatial region, which can then be identified as the threshold-exceeding region. Within the threshold-exceeding region, each location has at least one time period that satisfies the preset crack initiation criterion.

[0060] Here, after determining the region exceeding the threshold, feature information within the region can be extracted as a quantitative indicator to characterize the crack initiation risk state of the region.

[0061] Specifically, the location where the first crack initiation candidate point appears along the casting flow direction within the super-threshold region can be determined as the first crack initiation location, reflecting the location where the mechanical conditions for crack initiation are earliest reached along the casting flow direction. Then, the maximum duration corresponding to each crack initiation candidate point within the super-threshold region is determined as the super-threshold duration, reflecting the most severe sustained super-threshold degree within the super-threshold region. Furthermore, the length covered by the super-threshold region along the casting flow direction can be determined as the super-threshold coverage length, reflecting the spatial influence range of crack initiation risk along the casting flow direction; and the maximum value of the principal tensile strain within the super-threshold region can be determined as the principal tensile strain peak value, reflecting the most severe strain intensity within the super-threshold region.

[0062] In this way, the location of the first crack initiation, the duration of exceeding the threshold, the length of the coverage of the threshold, and the peak value of the principal tensile strain can be jointly determined as the threshold feature parameter set of the threshold region. This feature parameter set provides a comprehensive quantitative description of the crack initiation risk of the threshold region from four dimensions: location, duration, spatial range, and strain intensity. This improves the completeness of the description of crack initiation risk characteristics and the amount of input information for subsequent fault diagnosis.

[0063] In some other embodiments, the threshold feature parameter set may also include the average or median value of the threshold duration corresponding to each crack initiation candidate point in the threshold region, the total time length during which the principal tensile strain in the threshold region exceeds the critical strain threshold, the total number of crack initiation candidate points in the threshold region, and other statistical feature parameters. These can be determined according to the actual fault diagnosis requirements and are not specifically limited here.

[0064] In some possible embodiments, to comprehensively and quantitatively assess the crack initiation risk in the super-threshold region, a crack initiation risk index can be calculated based on the super-threshold characteristic parameter set, and the warning level can be determined based on the comparison between the crack initiation risk index and a preset warning threshold. Specifically, the crack initiation risk index can be obtained by weighted summation of the ratio of the super-threshold duration to the critical duration, the ratio of the super-threshold coverage length to the total length of the crack formation window, and the ratio of the peak value of the principal tensile strain to the critical strain threshold, where the sum of the weight coefficients corresponding to each ratio is 1. When the crack initiation risk index exceeds the preset warning threshold, a risk warning is triggered. For example, multiple warning levels can be set according to the degree to which the risk index exceeds the threshold; the higher the risk index, the higher the warning level. Conversely, if the risk index does not exceed the preset warning threshold, monitoring continues without triggering a warning, thereby achieving quantitative and graded warning of crack initiation risk.

[0065] S106, determine the fault information of the secondary cooling system based on the over-threshold feature parameter group.

[0066] Here, the over-threshold characteristic parameter set can be used as a quantitative indicator to characterize the over-threshold state of principal tensile strain within the crack formation spatial window. It provides complete information on crack initiation risk in four dimensions: location, time, spatial range, and strain intensity. Based on the over-threshold characteristic parameter set, the fault information of the secondary cooling system can be determined. The fault information is a comprehensive diagnostic conclusion of the current operating status of the secondary cooling system and the risk of crack initiation in the billet, and can at least include the fault location and fault type. The fault location can indicate the specific orientation of the cooling section that induced crack initiation and its interior, providing clear spatial guidance for on-site maintenance; the fault type can reflect the category of the root cause of the current abnormal water volume, providing directional guidance for fault investigation.

[0067] For example, considering that the initial crack initiation location in the over-threshold characteristic parameter group directly reflects the location where the mechanical conditions for crack initiation are first met along the casting flow direction, and that this location has a spatial correspondence with the actual coverage area of ​​each cooling section in the secondary cooling system, the following reference is made during the determination of fault information: Figure 2 As shown, the steps S201~S203 may be included: S201, based on the spatial matching of the location where the crack first initiated and the coverage of each cooling section of the secondary cooling system in the casting flow direction, the associated cooling section is determined.

[0068] Here, since the initial crack initiation location is a specific coordinate value along the casting flow direction, and each cooling section of the secondary cooling system has a preset start and end position along the casting flow direction, spatial matching can be performed between the initial crack initiation location and the start and end positions of each cooling section to determine which cooling section's coverage area the initial crack initiation location falls into, thus identifying that cooling section as the associated cooling section. The associated cooling section is the cooling zone corresponding to the initial crack initiation location, that is, the cooling section into which the initial crack initiation location falls. Spatial matching can establish a correspondence between the crack initiation location and specific cooling equipment.

[0069] S202, Intra-segment positioning is performed based on the relative position of the initial crack initiation location within the associated cooling segment.

[0070] Furthermore, based on the relative position of the initial crack initiation location within the associated cooling section, the specific location of the cooling anomaly within that cooling section can be preliminarily determined.

[0071] Here, if the initial crack initiation location is in the beginning region of the associated cooling section, it indicates that the crack initiation occurred in the front end region of that cooling section. This region is mainly cooled by the spray equipment on the inlet side of the cooling section. In this case, the associated cooling section and its inlet-side equipment can be identified as the fault location to prompt inspection of the nozzles and pipelines on the inlet side of that section. The beginning region refers to a predetermined proportion of the area extending along the casting flow direction from the starting position of the associated cooling section in that direction. This predetermined proportion can be set according to specific needs, for example, one-third of the total length of the associated cooling section.

[0072] Here, if the crack first initiation location is in the boundary area between the associated cooling section and the adjacent cooling section, it indicates that the crack initiation location is at the junction of the two cooling sections. The cooling effect at this location may be affected by the spray equipment on the outlet side of the upstream cooling section and the inlet side of the downstream cooling section at the same time, indicating that there is an abnormal cooling water volume in this boundary area. At this time, the associated cooling section and the adjacent cooling section can be jointly identified as the fault location, thus indicating that a joint investigation of the two cooling sections is needed.

[0073] S203, determine the fault type based on the distribution of the crack initiation candidate points in each corner region of the cast billet.

[0074] Specifically, crack initiation candidate points can reflect whether there are locations in each corner region that meet the crack initiation criteria. Based on the distribution of crack initiation candidate points in each corner region, it can be determined whether the cooling anomaly occurs on a specific side or affects the entire cooling section, which serves as the basis for subsequent fault type determination.

[0075] Here, if the candidate crack initiation points are concentrated in a specific corner area, and the cooling water volume data of the adjacent side of the specific corner area is lower than the preset normal water volume threshold, it indicates that the insufficient cooling intensity of the specific corner area is caused by an abnormal supply of cooling medium on that side. The corner area develops cracks prematurely due to insufficient cooling, and the fault type can be determined as an abnormal supply of cooling medium in the specific corner area, indicating a local fault in the nozzle or water supply pipeline on that side. The preset normal water volume threshold refers to the minimum cooling water volume value that a certain section and side of the secondary cooling system should reach under normal operating conditions, corresponding to a specific steel grade, cross-sectional size, and casting speed. This threshold can be specifically set according to the target setting value of the continuous casting secondary cooling water distribution model under the current process parameters. For example, 80% of the target water volume for that section and side can be used as the preset normal water volume threshold; a value lower than this is considered an abnormal supply of cooling medium.

[0076] If multiple corner regions have potential crack initiation points, and the initial crack initiation location corresponding to each corner region falls within the same cooling section, it indicates that the overall cooling capacity of the cooling section is insufficient, and multiple corners are simultaneously at risk of crack initiation. The fault type can be determined as an abnormality in the total water supply of the cooling section, indicating that there is an overall fault in the total water supply pipeline or distribution valve of the cooling section.

[0077] In some possible embodiments, since the blockage or aging of cooling equipment is often a gradual process, the initial crack initiation location may gradually migrate along the casting flow direction with the increase of production heats. Therefore, in order to accurately identify such gradual failures and avoid sudden shutdowns, the initial crack initiation location can be continuously monitored and its trend tracked, referring to... Figure 3 As shown, the process of determining the fault information of the secondary cooling system may also include the following steps S301~S303: S301, based on the crack initiation location of the current monitoring cycle and multiple historical monitoring cycles, generate a sequence of crack initiation locations.

[0078] Here, the sequence of first crack initiation locations includes multiple first crack initiation locations arranged in chronological order of monitoring cycles. The first crack initiation location of each monitoring cycle corresponds to the earliest crack initiation location determined under the current cooling conditions within that cycle.

[0079] S302, calculate the forward movement rate of the first crack initiation position along the casting flow direction based on the crack initiation position sequence.

[0080] Specifically, based on the sequence of the first crack initiation locations, a trend line can be fitted showing the change of the first crack initiation location with the monitoring period. The slope of this trend line is then determined as the forward movement rate, which reflects the rate at which cooling capacity degrades over time.

[0081] S303, if the forward movement rate exceeds a preset threshold, the fault type of the associated cooling section is determined to be gradual decay of cooling capacity.

[0082] Here, if the forward movement rate exceeds the preset threshold, it indicates that the initial crack initiation location is moving upstream in the casting flow direction at a relatively fast speed, suggesting that the cooling capacity of the associated cooling section is continuously decreasing. At this point, the fault type of the associated cooling section can be determined as a gradual decay of cooling capacity. The preset threshold is the maximum allowable forward movement rate pre-set based on the actual working conditions. It can be set according to the equipment characteristics and production rhythm of the continuous casting machine, for example, based on the upper limit of the natural fluctuation range of the initial crack initiation location under normal working conditions.

[0083] Specifically, the gradual decline in cooling capacity refers to the state in which the actual cooling effect of the cooling section gradually decreases over time. It can reflect the process of the nozzle blockage gradually worsening or the pipeline flow gradually decreasing, thus providing a basis for predictive maintenance.

[0084] In some other embodiments, the failure types of the secondary cooling system may also include other failure categories such as partial nozzle blockage, abnormal crystallizer cooling, or cooling mismatch between the two cooling sections. The specific determination method can be based on the different parameter combinations in the over-threshold feature parameter group combined with the deviation characteristics of the water volume data on each side to make a comprehensive judgment, thereby achieving a finer-grained distinction of failure modes. No specific limitation is made here.

[0085] In some possible embodiments, to further verify the causal relationship between cooling anomalies and crack initiation, and to eliminate the interference of other continuous casting process parameter fluctuations on crack initiation, a causal attribution verification step can be added. While keeping other continuous casting process parameters such as superheat, casting speed, and crystallizer parameters constant, the measured cooling water volume data of each section and side of the secondary cooling system collected in real time are replaced with normal baseline water volume for comparative calculation. If an out-of-threshold window satisfying the crack initiation criterion only occurs under the measured water volume condition but not under the normal water volume condition, it indicates that the mechanical conditions for crack initiation originate solely from the current cooling water volume anomaly. In this case, the current cooling anomaly can be confirmed as an independent cause of crack initiation, thus determining the priority of maintenance.

[0086] In some possible embodiments, the continuous decline in cooling capacity can affect the quality of continuously cast billets and the continuity of production. The failure development process of the cooling equipment directly determines the time window for scheduled shutdown and maintenance. Therefore, the fault information can also include the remaining number of available furnace runs, i.e., the number of billet furnaces that the associated cooling section can continue to produce from to the critical failure state under the current cooling capacity decay state. Thus, the location of the first crack initiation and the beginning position of the associated cooling section in the current monitoring cycle can be determined based on the fault location, and the current available casting flow direction distance can be calculated. Dividing this distance by the forward movement rate yields the remaining number of available furnace runs. Based on the remaining number of available furnace runs, the number of remaining available furnace runs can be estimated (the forward movement rate is the migration distance per furnace run). Therefore, based on the remaining number of available furnace runs, the number of production furnace runs required for the cooling section to reach the critical state can be estimated, thus providing a time basis for formulating maintenance plans and improving the guiding value of fault diagnosis results for equipment maintenance decisions.

[0087] The continuous casting secondary cooling system fault diagnosis method, device, medium and equipment provided in this embodiment realize spatial alignment and correlation analysis of crack history statistical information with real-time cooling water volume and strain field. Based on the correlation analysis, the fault location and type can be determined, providing a quantifiable diagnostic basis for online condition assessment and targeted maintenance of the secondary cooling system.

[0088] The following example illustrates the implementation process of the continuous casting secondary cooling system fault diagnosis method proposed in this application, using the continuous casting production of 340mm×300mm rectangular billets of No. 45 steel in a steel plant as an example. Based on the solidification heat transfer model verified by on-site temperature measurement, under typical process parameters of casting speed of 0.65 to 0.70 meters per minute and superheat of 20 to 30 degrees Celsius, the position of the solidus temperature isotherm along the normal direction of the billet corner surface is searched. The correspondence between the billet shell thickness and the casting flow position is recorded step by step. It is calculated that when the corner billet shell thickness grows to 20 mm, it corresponds to a distance of approximately 0.78 meters from the meniscus, and when it grows to 30 mm, it corresponds to approximately 1.30 meters. Thus, the growth curve of the billet shell thickness and the position of the casting flow direction and its inverse correspondence are established. According to the statistical analysis of 183 low-magnification acid etching inspection records of the steel plant, the subcutaneous cracks at the corners are concentrated in the depth area of ​​20 to 30 mm from the surface. Using the above-mentioned reverse correspondence, this depth range is converted into a spatial window of 0.78 meters to 1.30 meters along the casting flow direction.

[0089] Furthermore, cooling water volume data for each side of the secondary cooling section were collected online. A two-dimensional cross-sectional transient heat conduction equation was used, and the latent heat of solidification was processed using the equivalent heat capacity method. The heat transfer coefficient of each side was calculated based on the real-time collected side-by-side water volume data, serving as the boundary condition for solidification heat transfer calculation, thus obtaining the temperature field distribution within the crack formation window. Thermodynamic analysis was performed on regions with a solid fraction exceeding 0.7 to obtain the spatiotemporal distribution data of the principal tensile strain. The spatiotemporal distribution data of the principal tensile strain were traversed within the crack formation window to determine if there were time periods where the principal tensile strain exceeded the critical strain threshold and the duration of the over-threshold state reached the critical duration. If such periods existed, the location was marked as a candidate crack initiation point. The continuous region formed by all candidate crack initiation points was defined as the over-threshold region. The initial crack initiation location, over-threshold duration, over-threshold coverage length, and peak principal tensile strain were extracted as a set of over-threshold characteristic parameters.

[0090] Here, taking the abnormal operating condition of 6.6 liters per minute on the outer arc of the secondary cooling section and 6.2 liters per minute on the west side as an example, the initial crack initiation location is 0.85 meters, the duration of exceeding the threshold is 1.8 times the critical duration, the length of the exceedance coverage is 0.32 meters, and the peak value of the principal tensile strain is 1.45 times the critical strain threshold. The calculated crack initiation risk index is 1.34. The risk index is pre-set as follows: exceeding the warning threshold of 0.8 triggers a risk warning; under the condition of complete flow interruption, the risk index is 2.47, triggering the highest level warning. At this time, the warning level can be determined according to the numerical range of the risk index; the higher the risk index, the higher the warning level.

[0091] Here, while keeping the superheat, casting speed, and crystallizer parameters constant, the measured water volume was replaced with the normal baseline water volume for recalculation. The crack initiation criterion was not met under the normal water volume, but was met under the measured water volume. This proves that the local anomaly in the secondary cooling system is an independent cause of crack initiation. Spatial matching was performed based on the initial crack initiation location and the coverage area of ​​each cooling section to determine the associated cooling section and fault location. The fault type was determined based on the distribution of candidate crack initiation points in each corner area. Analysis of monitoring data from six consecutive furnace runs showed a systematic forward shift in the initial crack initiation location sequence, with an average forward shift of approximately 0.012 meters per furnace run. It is estimated that the crack will shift to near the section head around the 15th furnace run, suggesting a shutdown for maintenance within 10 furnace runs. Based on the above method, targeted inspections were conducted on the secondary cooling system. After repairing 12 nozzle blockages and 2 pipeline distribution abnormalities, the incidence of subcutaneous cracks at the corners decreased from 48.33% before implementation to 17.1%, a reduction of 64.6%, verifying the engineering effectiveness of this method.

[0092] 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.

[0093] Based on the same inventive concept, this disclosure also provides a fault diagnosis device for a continuous casting secondary cooling system corresponding to the fault diagnosis method for a continuous casting secondary cooling system. Since the principle of the device in this disclosure for solving the problem is similar to the fault diagnosis method for a continuous casting secondary cooling system described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0094] Reference Figure 4 The diagram shown is a schematic of a fault diagnosis device 400 for a continuous casting secondary cooling system provided in an embodiment of this disclosure. The device includes: The data preparation module 401 is used to obtain the continuous casting process parameters corresponding to the target continuous casting billet, and to perform solidification heat transfer calculation on the target continuous casting billet according to the continuous casting process parameters, so as to determine the temperature field evolution data of the corner of the target continuous casting billet. The relationship mapping module 402 is used to establish a growth curve of the billet shell thickness along the casting flow direction with position based on the temperature field evolution data, and to perform inverse mapping on the growth curve to obtain the inverse correspondence between the position and the billet shell thickness. The window determination module 403 is used to obtain the historical depth distribution statistics of subcutaneous cracks at the corner of the target continuous casting billet, and to map the historical depth distribution statistics into a crack formation space window along the casting flow direction using the reverse correspondence; wherein, the historical depth distribution statistics are the statistical results of the inspection of continuous casting billets with corner subcutaneous cracks in historical heats corresponding to the steel grade and cross-sectional size of the target continuous casting billet; The data acquisition module 404 is used to acquire in real time the cooling water volume data of each section and side of the secondary cooling system corresponding to the target continuous casting billet, and determine the spatiotemporal distribution data of the principal tensile strain corresponding to the crack formation space window based on the cooling water volume data and the continuous casting process parameters. The crack judgment module 405 is used to traverse the spatiotemporal distribution data of the principal tensile strain within the crack formation space window, determine whether there is an over-threshold region that meets the preset crack initiation criterion, and if so, extract the over-threshold feature parameter group of the over-threshold region. The fault determination module 406 is used to determine the fault information of the secondary cooling system based on the set of over-threshold feature parameters; wherein the fault information includes at least the fault location and the fault type.

[0095] In some possible embodiments, the crack detection module 405 is specifically used for: Within the crack formation space window, the corresponding principal tensile strain time series data are read point by point from the principal tensile strain spatiotemporal distribution data along the casting flow direction; For each current reading point, determine whether there is a time period in the main tensile strain time series data that satisfies the preset crack initiation criterion; wherein, the preset crack initiation criterion is that the main tensile strain exceeds a critical threshold and the duration of the over-threshold state at the current reading point reaches the critical duration. If it exists, the current reading point is marked as a crack initiation candidate point, and the continuous region along the casting flow direction formed by all the crack initiation candidate points is determined as the over-threshold region. Accordingly, the crack detection module 405 is specifically used for: The location of the first candidate point for crack initiation along the casting flow direction within the super-threshold region is determined as the location of the first crack initiation. The maximum duration of each crack initiation candidate point within the threshold region is determined as the threshold duration. The length of the super-threshold region covered in the casting direction is defined as the super-threshold coverage length. The maximum value of the principal tensile strain within the above-threshold region is determined as the principal tensile strain peak value; The location of the first crack initiation, the duration of the overthreshold, the length of the overthreshold coverage, and the peak value of the principal tensile strain are determined as the overthreshold characteristic parameter set of the overthreshold region.

[0096] In some possible embodiments, the fault determination module 406 is specifically used for: Based on the spatial matching of the initial crack initiation location and the coverage of each cooling section of the secondary cooling system in the casting flow direction, the associated cooling section is determined; Intra-segment location is determined based on the relative position of the initial crack initiation location within the associated cooling segment, including: if the initial crack initiation location is located at the beginning region of the associated cooling segment, then the associated cooling segment and the inlet-side equipment of the associated cooling segment are identified as the fault location; if the initial crack initiation location is located at the boundary region between the associated cooling segment and the adjacent cooling segment, then the associated cooling segment and the adjacent cooling segment are identified as the fault location. The fault type is determined based on the distribution of the crack initiation candidate points in each corner region of the billet, including: if the crack initiation candidate points are concentrated in a specific corner region, and the cooling water volume data of the adjacent edge of the specific corner region is lower than the preset normal water volume threshold, then the fault type is determined to be an abnormal cooling medium supply in the specific corner region; if the crack initiation candidate points exist in multiple corner regions, and the first crack initiation position corresponding to the crack initiation candidate points in each corner region falls in the same cooling section, then the fault type is determined to be an abnormal total water supply in the cooling section.

[0097] In some possible embodiments, the fault determination module 406 is further configured to: Based on the current monitoring cycle and the crack initiation locations from multiple historical monitoring cycles, a sequence of crack initiation locations is generated. The forward movement rate of the first crack initiation location along the casting flow direction is calculated based on the crack initiation location sequence. If the forward movement rate exceeds a preset threshold, the fault type of the associated cooling section is determined to be gradual decay of cooling capacity; Accordingly, the fault information also includes the remaining number of available furnace cycles; the fault determination module 406 is specifically used for: The remaining number of furnace cycles for the associated cooling section are determined based on the location of the initial crack initiation, the location of the failure, and the rate of forward movement.

[0098] In some possible embodiments, the relationship mapping module 402 is specifically used for: Based on the temperature field evolution data, the position of the solidification front is determined step by step along the surface normal of the corner of the billet; wherein, the position of the solidification front is the location of the isotherm of the solidus temperature within the cross-section of the corner of the billet. The position along the casting flow direction and the billet shell thickness at each calculation time step are obtained, and the growth curve is generated with the position along the casting flow direction as the abscissa and the billet shell thickness as the ordinate.

[0099] In some possible embodiments, the window determination module 403 is specifically used for: Based on the historical depth distribution statistics, the depth range with the highest crack distribution frequency is determined, and the casting flow position range corresponding to the depth range with the highest crack distribution frequency is determined using the reverse correspondence. The casting flow position range is then defined as the crack formation spatial window.

[0100] In some possible embodiments, the data acquisition module 404 is specifically used for: The convective heat transfer coefficient of each side is calculated based on the cooling water volume data of each section and side of the secondary cooling system. The convective heat transfer coefficient is used as the boundary condition for solidification heat transfer calculation. The solidification heat transfer process of the target continuous casting billet in the crack formation space window is calculated to obtain the temperature field distribution of the target continuous casting billet in the crack formation space window. A thermodynamic analysis is performed on the temperature field distribution to calculate the principal tensile strain in the target depth region of the billet corner within the crack formation space window, thereby obtaining the spatiotemporal distribution data of the principal tensile strain; wherein, the target depth region is the depth interval corresponding to the historical depth distribution statistics.

[0101] Based on the same technical concept, this disclosure also provides a computer device. (See also...) Figure 5 The diagram shows the structure of a computer device 500 provided in this embodiment of the present disclosure, including a processor 501, a memory 502, and a bus 503. The memory 502 is used to store execution instructions and includes a main memory 5021 and an external memory 5022. The main memory 5021, also called internal memory, is used to temporarily store computational data in the processor 501, as well as data exchanged with external memory 5022 such as a hard disk. The processor 501 exchanges data with the external memory 5022 through the main memory 5021.

[0102] In this embodiment, the memory 502 is specifically used to store application code that executes the solution of this application, and its execution is controlled by the processor 501. That is, when the computer device 500 is running, the processor 501 communicates with the memory 502 through the bus 503, so that the processor 501 executes the application code stored in the memory 502, and then executes the method described in any of the foregoing embodiments.

[0103] The memory 502 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.

[0104] Processor 501 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.

[0105] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the computer device 500. In other embodiments of this application, the computer device 500 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.

[0106] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the continuous casting secondary cooling system fault diagnosis method described in the above-described method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0107] 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 continuous casting secondary cooling system fault diagnosis method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 fault diagnosis method for a continuous casting secondary cooling system, characterized in that, include: Obtain the continuous casting process parameters corresponding to the target continuous casting billet, and perform solidification heat transfer calculation on the target continuous casting billet based on the continuous casting process parameters to determine the temperature field evolution data of the corner of the target continuous casting billet. Based on the temperature field evolution data, a growth curve of the billet shell thickness along the casting flow direction as a function of position is established, and the growth curve is inversely mapped to obtain the inverse correspondence between the position and the billet shell thickness. The historical depth distribution statistics of subcutaneous cracks at the corner of the target continuous casting billet are obtained, and the historical depth distribution statistics are mapped to a crack formation space window along the casting flow direction using the reverse correspondence; wherein, the historical depth distribution statistics are the statistical results of the inspection of continuous casting billets with subcutaneous cracks at the corner in historical heats corresponding to the steel grade and cross-sectional size of the target continuous casting billet; Real-time acquisition of cooling water volume data for each section and side of the secondary cooling system corresponding to the target continuous casting billet; and determination of the spatiotemporal distribution data of principal tensile strain corresponding to the crack formation space window based on the cooling water volume data and the continuous casting process parameters. Within the crack formation space window, the spatiotemporal distribution data of the principal tensile strain is traversed to determine whether there is an over-threshold region that satisfies the preset crack initiation criterion. If so, the over-threshold feature parameter group of the over-threshold region is extracted. The fault information of the secondary cooling system is determined based on the set of over-threshold feature parameters; wherein the fault information includes at least the fault location and the fault type.

2. The method according to claim 1, characterized in that, The determination of whether there exists an over-threshold region that satisfies the preset crack initiation criterion includes: Within the crack formation space window, the corresponding principal tensile strain time series data are read point by point from the principal tensile strain spatiotemporal distribution data along the casting flow direction; For each current reading point, determine whether there is a time period in the main tensile strain time series data that satisfies the preset crack initiation criterion; wherein, the preset crack initiation criterion is that the main tensile strain exceeds a critical threshold and the duration of the over-threshold state at the current reading point reaches the critical duration. If it exists, the current reading point is marked as a crack initiation candidate point, and the continuous region along the casting flow direction formed by all the crack initiation candidate points is determined as the over-threshold region. Accordingly, the extraction of the super-threshold feature parameter set of the super-threshold region includes: The location of the first candidate point for crack initiation along the casting flow direction within the super-threshold region is determined as the location of the first crack initiation. The maximum duration of each crack initiation candidate point within the threshold region is determined as the threshold duration. The length of the super-threshold region covered in the casting direction is defined as the super-threshold coverage length. The maximum value of the principal tensile strain within the above-threshold region is determined as the principal tensile strain peak value; The location of the first crack initiation, the duration of the overthreshold, the length of the overthreshold coverage, and the peak value of the principal tensile strain are determined as the overthreshold characteristic parameter set of the overthreshold region.

3. The method according to claim 2, characterized in that, The step of determining the fault information of the secondary cooling system based on the set of over-threshold feature parameters includes: Based on the spatial matching of the initial crack initiation location and the coverage of each cooling section of the secondary cooling system in the casting flow direction, the associated cooling section is determined; Intra-segment location is determined based on the relative position of the initial crack initiation location within the associated cooling segment, including: if the initial crack initiation location is located at the beginning region of the associated cooling segment, then the associated cooling segment and the inlet-side equipment of the associated cooling segment are identified as the fault location; if the initial crack initiation location is located at the boundary region between the associated cooling segment and the adjacent cooling segment, then the associated cooling segment and the adjacent cooling segment are identified as the fault location. The fault type is determined based on the distribution of the crack initiation candidate points in each corner region of the billet, including: if the crack initiation candidate points are concentrated in a specific corner region, and the cooling water volume data of the adjacent edge of the specific corner region is lower than the preset normal water volume threshold, then the fault type is determined to be an abnormal cooling medium supply in the specific corner region; if the crack initiation candidate points exist in multiple corner regions, and the first crack initiation position corresponding to the crack initiation candidate points in each corner region falls in the same cooling section, then the fault type is determined to be an abnormal total water supply in the cooling section.

4. The method according to claim 3, characterized in that, The method of determining the fault type based on the distribution of candidate crack initiation points in each corner region of the cast billet also includes: Based on the current monitoring cycle and the crack initiation locations from multiple historical monitoring cycles, a sequence of crack initiation locations is generated. The forward movement rate of the first crack initiation location along the casting flow direction is calculated based on the crack initiation location sequence. If the forward movement rate exceeds a preset threshold, the fault type of the associated cooling section is determined to be gradual decay of cooling capacity; Accordingly, the fault information also includes the remaining number of furnace cycles; determining the fault information of the secondary cooling system based on the over-threshold feature parameter group includes: The remaining number of furnace cycles for the associated cooling section are determined based on the location of the initial crack initiation, the location of the failure, and the rate of forward movement.

5. The method according to claim 1, characterized in that, The step of establishing a growth curve of the billet shell thickness along the casting flow direction as a function of position based on the temperature field evolution data includes: Based on the temperature field evolution data, the position of the solidification front is determined step by step along the surface normal of the corner of the billet; wherein, the position of the solidification front is the location of the isotherm of the solidus temperature within the cross-section of the corner of the billet. The position along the casting flow direction and the billet shell thickness at each calculation time step are obtained, and the growth curve is generated with the position along the casting flow direction as the abscissa and the billet shell thickness as the ordinate.

6. The method according to claim 1, characterized in that, The step of mapping the historical depth distribution statistics to a crack formation space window along the casting flow direction using the reverse correspondence includes: Based on the historical depth distribution statistics, the depth range with the highest crack distribution frequency is determined, and the casting flow position range corresponding to the depth range with the highest crack distribution frequency is determined using the reverse correspondence. The casting flow position range is then defined as the crack formation spatial window.

7. The method according to claim 1, characterized in that, The step of determining the spatiotemporal distribution data of the principal tensile strain corresponding to the crack formation spatial window based on the cooling water volume data and the continuous casting process parameters includes: The convective heat transfer coefficient of each side is calculated based on the cooling water volume data of each section and side of the secondary cooling system. The convective heat transfer coefficient is used as the boundary condition for solidification heat transfer calculation. The solidification heat transfer process of the target continuous casting billet in the crack formation space window is calculated to obtain the temperature field distribution of the target continuous casting billet in the crack formation space window. A thermodynamic analysis is performed on the temperature field distribution to calculate the principal tensile strain in the target depth region of the billet corner within the crack formation space window, thereby obtaining the spatiotemporal distribution data of the principal tensile strain; wherein, the target depth region is the depth interval corresponding to the historical depth distribution statistics.

8. A fault diagnosis device for a continuous casting secondary cooling system, characterized in that, include: The data preparation module is used to obtain the continuous casting process parameters corresponding to the target continuous casting billet, and to perform solidification heat transfer calculations on the target continuous casting billet based on the continuous casting process parameters, so as to determine the temperature field evolution data of the corner of the target continuous casting billet. The relationship mapping module is used to establish a growth curve of the billet shell thickness along the casting flow direction with position based on the temperature field evolution data, and to perform inverse mapping on the growth curve to obtain the inverse correspondence between the position and the billet shell thickness. The window determination module is used to obtain the historical depth distribution statistics of subcutaneous cracks at the corner of the target continuous casting billet, and to map the historical depth distribution statistics into a crack formation space window along the casting flow direction using the reverse correspondence; wherein, the historical depth distribution statistics are the statistical results of the inspection of continuous casting billets with corner subcutaneous cracks that have occurred in historical heats corresponding to the steel grade and cross-sectional size of the target continuous casting billet; The data acquisition module is used to collect the cooling water volume data of each section and side of the secondary cooling system corresponding to the target continuous casting billet in real time, and determine the spatiotemporal distribution data of the principal tensile strain corresponding to the crack formation space window based on the cooling water volume data and the continuous casting process parameters. The crack detection module is used to traverse the spatiotemporal distribution data of the principal tensile strain within the crack formation space window, determine whether there is an over-threshold region that meets the preset crack initiation criterion, and if so, extract the over-threshold feature parameter group of the over-threshold region. The fault determination module is used to determine the fault information of the secondary cooling system based on the set of over-threshold feature parameters; wherein the fault information includes at least the fault location and the fault type.

9. 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 7.

10. 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 7.

Images