Digital twinning-based molten steel injection atmosphere protection system and protection method

Abstract

The invention discloses a digital twinning-based molten steel injection atmosphere protection system and method, and the system comprises a data collection module, a twinning model module, a control analysis module, an air inlet device module and a fault analysis module. The measured data of the monitoring points in the inert atmosphere state and the calculation data of the twinborn model are obtained; the control analysis module analyzes a data set transmitted by the data collection module, calls a parameter database and outputs an optimal decision matched with real-time boundary conditions to the air inlet device module and the twin model module, it is guaranteed that the low-oxygen inert atmosphere surrounding the molten steel is always formed, and secondary oxidation of the molten steel is effectively prevented. According to the invention, the problems that the inert gas atmosphere state is unknown and the stability is uncontrollable when an existing molten steel injection atmosphere protection device deals with dynamic change working conditions are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of molten steel pouring, and in particular relates to a molten steel injection atmosphere protection system and a protection method based on digital twin. Background Art

[0002] Existing steel liquid injection atmosphere protection devices often adopt fixed air intake methods and air intake parameters, which cannot cope with the atmosphere changes caused by changes in actual working parameters. However, changes in working parameters are inevitable during steel liquid injection, and the inert gas atmosphere with low oxygen concentration is very likely to be destroyed. As the steel liquid injection time increases, the steel liquid temperature usually drops by 20 to 80 ° C, and the steel liquid viscosity increases, affecting the interaction between the steel liquid and the inert atmosphere. At the same time, in order to ensure a certain pouring speed and thus ensure the quality of the ingot, as the height of the steel liquid in the ladle decreases, the shape and size of the injection port need to be continuously changed (the injection port is elliptical, and the shape and size can be adjusted by adjusting the major and minor axes) to adjust the injection speed. In addition, a ladle usually needs to inject into multiple middle injection pipes of different heights, which also causes the exposed height of the steel liquid to change continuously in one operation. The above factors will affect the multiphase flow field of argon, air, and steel liquid. Even if the protection device can still form and maintain a full argon atmosphere, the actual working condition change means that an excessively high inert gas intake pressure may be adopted, wasting energy. In actual applications, the working environment of the molten steel injection protection system is harsh, and the molten steel may splash and injure people. This means that when existing devices want to adjust parameters (such as intake pressure and intake angle, etc.) based on experience, they are also significantly affected by human factors and pose safety hazards.

[0003] Therefore, it is urgently necessary to design an intelligent digital injection atmosphere protection system that can adapt to the dynamically changing working conditions during molten steel pouring, so as to adjust the process parameters of the protection system in real time, accurately and automatically, and always form an ideal inert atmosphere during the molten steel pouring operation. Summary of the invention

[0004] The purpose of the present invention is to provide a molten steel injection atmosphere protection system and protection method based on digital twin, which can always form an inert atmosphere surrounding the molten steel under dynamic injection conditions, thereby solving the problem that the molten steel injection protection system cannot adjust the protection system process parameters in real time, intelligently and automatically, and cannot ensure that an ideal inert atmosphere is always formed during the pouring operation.

[0005] To achieve the above purpose, the technical solution used in the present invention is:

[0006] The steel liquid injection atmosphere protection system based on digital twin includes: a data collection module, a control analysis module, a twin model module, and an air intake device module; the data collection module and the twin model module communicate wirelessly with the control analysis module respectively, the control analysis module is connected to the air intake device module by wired or wireless communication, and the data collection module is connected to the twin model module wirelessly; wherein

[0007] The data collection module collects the measured data of the monitoring point, the calculated data of the twin model module of the monitoring point, and the first boundary condition and the second boundary condition required for the twin model module to calculate, so as to form a data set; the measured data of the monitoring point and the calculated data of the twin model module include: pressure, temperature and oxygen concentration; the first boundary condition includes: the major axis length, the minor axis length, the molten steel injection flow rate, the molten steel temperature and the injection height of the elliptical molten steel injection port; the second boundary condition includes: the intake pressure and intake angle of the intake pipe;

[0008] A control analysis module, used to receive a data set from a data collection module, and after analyzing the data set, determine whether to send a decision signal to an intake device module and a twin model module; the data set includes: measured data of a monitoring point, calculated data of a twin model of a monitoring point, and first and second boundary conditions; when the control analysis module determines that the first boundary condition has changed, the control analysis module calls a parameter database of the control analysis module, outputs a second boundary condition that matches the first boundary condition, and sends the updated second boundary condition to the intake device module, and at the same time sends the updated first boundary condition and second boundary condition to the twin model module;

[0009] The twin model module is used to receive the decision signal from the control analysis module, and build a geometric model including: the air intake device, the upper pouring gate, the ladle bottom plate, the center pouring pipe and the ingot mold based on the decision signal, automatically divide the geometric model into grids, build a physical model for multiphase flow field calculation, and calculate the three-dimensional distribution, pressure and temperature distribution of the molten steel, inert atmosphere and air between the air intake device module 4 and the ladle bottom plate, and output the results in the form of charts to monitor the inert atmosphere state in real time;

[0010] The air intake device module is used to receive the decision signal of the control analysis module for updating the second boundary condition, and to adjust the intake angle and intake pressure of the intake pipe; the air intake device module includes: an intake pipe, an annular air storage chamber, a narrow gap, a hollow spherical universal joint, an intake pipe, and an automatic pressure valve. The intake pipe is connected to the annular air storage chamber, and inert gas is input into the annular air storage chamber.

[0011] Furthermore, it also includes a fault analysis module, which communicates wirelessly with the control analysis module. The fault analysis module is used to receive the data set sent by the control analysis module and the hardware self-test report of each monitoring point, analyze and issue a fault report.

[0012] Furthermore, the parameter database of the control analysis module stores the optimal intake angle and intake pressure that match the first boundary condition. The quantitative relationship between the optimal intake angle, intake pressure and the first boundary condition is obtained by a series of numerical simulations performed by the twin model module and based on machine learning fitting.

[0013] Furthermore, the rotation angle range of the spherical hollow universal joint of the intake device module covers all intake angles in the parameter database of the control analysis module; the spherical hollow universal joint has a fixing plate, which is welded to the annular air storage chamber; the geometric shape of the fixing plate is a spherical wall formed by rotating a semicircle 30° around the y-axis, and the inner diameter of the fixing plate is the same as the outer diameter of the hollow spherical universal joint to fix the hollow spherical universal joint; the contact surface between the universal joint and the fixing plate is smooth to ensure the free rotation of the universal joint.

[0014] Furthermore, there is a narrow slit outlet on the upper surface of the annular air storage chamber for spraying a uniform inert gas curtain; the center of the hollow spherical universal joint is located at half the height of the outer wall of the annular air storage chamber and at any point of maximum diameter; the intake pipe is fixed through the inner hole of the hollow spherical universal joint and is consistent with the rotation angle of the hollow spherical universal joint; the intake pipe mover is connected to the end of the intake pipe, and promotes the adjustment of the intake pipe angle after receiving the decision signal of the control analysis module to update the second boundary condition; the automatic pressure valve is located at the end of the intake pipe where the inert gas enters, and adjusts the intake pressure after receiving the decision signal of the control analysis module to update the second boundary condition.

[0015] Furthermore, the monitoring points of the data collection module include pressure, temperature and oxygen concentration monitoring points. At least 4 pressure monitoring points are evenly distributed on the bottom plate of the ladle and are located within a radius from 2 cm outside the edge of the molten steel inlet to the outer diameter of the annular gas storage chamber. At least 2 are evenly distributed on the inner wall of the annular gas storage chamber, and at least 2 are distributed at the midpoint of the exposed height of the molten steel just above the widest part of the outer diameter of the annular gas storage chamber. The number of temperature monitoring points and oxygen concentration monitoring points is the same as that of pressure monitoring points, and they are 2 to 4 cm away from the pressure monitoring points to avoid overlapping and affecting the measurement between the monitoring points.

[0016] Furthermore, after each injection operation is completed, the measured data of the monitoring points of the data collection module, the calculated data of the twin model module, and the first boundary conditions and the second boundary conditions are input into the twin model module through the control analysis module, and the neural network learning and training of the twin model is performed to continuously optimize the parameter database of the twin model module and the control analysis module.

[0017] Furthermore, when the control analysis module determines that the difference between the measured data and the twin model calculated data at the same monitoring point is greater than the upper limit of 5% to 10%, the data set is passed to the fault analysis module. The pressure, temperature, and oxygen concentration in the measured data and the calculated data have different weights at each monitoring point, and the difference is obtained by summing the weights.

[0018] The steel liquid injection atmosphere protection method based on digital twin includes:

[0019] The data collection module collects the measured data of the monitoring point, the calculated data of the twin model module of the monitoring point, and the first boundary condition and the second boundary condition required for the twin model module to calculate, so as to form a data set; the measured data of the monitoring point and the calculated data of the twin model module include: pressure, temperature and oxygen concentration; the first boundary condition includes: the major axis length, the minor axis length, the steel liquid injection flow rate, the steel liquid temperature and the injection height of the elliptical steel liquid injection port; the second boundary condition includes: the intake pressure and intake angle of the intake pipe;

[0020] The control analysis module receives the data set from the data collection module, and after analyzing the data set, determines whether to send a decision signal to the air intake device module and the twin model module; the data set includes: measured data of the monitoring point, calculated data of the twin model of the monitoring point, and the first and second boundary conditions; when the control analysis module determines that the first boundary condition has changed, the parameter database of the control analysis module is called, the second boundary condition matching the first boundary condition is output, and the updated second boundary condition is sent to the air intake device module, and the updated first boundary condition and the second boundary condition are sent to the twin model module at the same time;

[0021] The twin model module receives the decision signal from the control analysis module, and builds a geometric model including: the air intake device, the upper pouring gate, the ladle bottom plate, the center pouring pipe and the ingot mold based on the decision signal, automatically divides the geometric model into grids, builds a physical model for multiphase flow field calculation, and calculates the three-dimensional distribution, pressure and temperature distribution of the molten steel, inert atmosphere and air between the air intake device module 4 and the ladle bottom plate, outputs the results in the form of charts, and monitors the inert atmosphere state in real time;

[0022] The air intake device module receives the decision signal of updating the second boundary condition from the control analysis module, and executes the adjustment of the intake angle and intake pressure of the intake pipe; the air intake device module includes: an intake pipe, an annular air storage chamber, a narrow gap, a hollow spherical universal joint, an intake pipe, and an automatic pressure valve. The intake pipe is connected to the annular air storage chamber, and inert gas is input into the annular air storage chamber.

[0023] Preferably, the fault analysis module receives the data set sent by the control analysis module and the hardware self-check report of each monitoring point, analyzes and issues a fault report.

[0024] The technical effects of the present invention include:

[0025] The present invention can always form an inert atmosphere surrounding the molten steel under dynamic injection conditions, solving the problem that the molten steel injection protection system cannot adjust the protection system process parameters in real time, intelligently and automatically, and cannot ensure that an ideal inert atmosphere is always formed during the pouring operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0027] Figure 2 A schematic diagram of real-time inert atmosphere distribution output by the twin model module in the present invention;

[0028] Figure 3 It is a schematic diagram of the air intake device module and monitoring points of an embodiment of the present invention;

[0029] Figure 4 It is a schematic diagram of the three-dimensional structure of the hollow spherical universal joint and the intake pipe of the intake device module of the present invention.

[0030] The markings in the figure are:

[0031] 1. Data collection module; 2. Control analysis module; 3. Twin model module; 4. Intake device module; 5. Fault analysis module; 6. Intake pipe; 7. Annular air storage chamber; 8. Narrow gap; 9. Hollow spherical universal joint; 10. Intake pipe mover; 11. Automatic pressure valve. DETAILED DESCRIPTION

[0032] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0033] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0034] In the embodiments of the present disclosure, the terms "upper", "lower", "inside", "middle", "outside", "front", "back" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. These terms are mainly intended to better describe the embodiments of the present disclosure and their embodiments, and are not intended to limit the indicated devices, elements or components to have a specific direction, or to be constructed and operated in a specific direction. Moreover, in addition to being used to indicate directions or positional relationships, some of the above terms may also be used to indicate other meanings. For example, the term "upper" may also be used to indicate a certain dependency or connection relationship in certain circumstances. For those of ordinary skill in the art, the specific meanings of these terms in the embodiments of the present disclosure can be understood according to specific circumstances.

[0035] In addition, the terms "disposed", "connected", and "fixed" should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection, or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present disclosure can be understood according to specific circumstances.

[0036] Unless otherwise stated, the term "plurality" means two or more.

[0037] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0038] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0039] It should be noted that, in the case of no conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other. The following description fully illustrates the specific embodiments of the present invention so that those skilled in the art can practice and reproduce.

[0040] like Figure 1 FIG. 1 is a schematic diagram of the system structure of the present invention.

[0041] The molten steel injection atmosphere protection system based on digital twin includes: a data collection module 1, a control analysis module 2, a twin model module 3, an air intake device module 4 and a fault analysis module 5; the data collection module 1, the twin model module 3 and the fault analysis module 5 are wirelessly communicated with the control analysis module 2 respectively, the control analysis module 2 is connected with the air intake device module 4 by wired or wireless communication, and the data collection module 1 is wirelessly connected with the twin model module 3;

[0042] The data collection module 1 collects the measured data of the monitoring point, the calculated data of the twin model module 3 of the monitoring point, and the first boundary condition and the second boundary condition required for the twin model module 3 to calculate, so as to form a data set; the measured data of the monitoring point and the calculated data of the twin model module 3 include: pressure, temperature and oxygen concentration; the first boundary condition includes: the major axis length, the minor axis length, the molten steel injection flow rate, the molten steel temperature and the injection height of the elliptical molten steel injection port; the second boundary condition includes: the intake pressure and intake angle of the intake pipe 6;

[0043] In actual operation, the parameters included in the first boundary condition will be dynamically adjusted. For example, as the injection time increases, the temperature of the molten steel decreases and the viscosity increases. To ensure the injection speed, the length of the major axis and minor axis of the injection port changes, so as to adjust the size of the molten steel injection port and the injection speed. The change of the first boundary condition also requires adjustment of the intake pressure and the intake angle of the intake pipe 6 to ensure a stable and oxygen-concentrated inert atmosphere. That is, there is a high correlation between the first boundary condition and the second boundary condition.

[0044] The control analysis module 2 is used to receive the data set of the data collection module 1, and after analyzing the data set, determine whether to send a decision signal to the intake device module 4 and the twin model module 3; the data set includes: measured data of the monitoring point, twin model calculation data of the monitoring point, and the first and second boundary conditions; when the control analysis module 2 determines that the first boundary condition has changed, it calls the parameter database of the control analysis module 2, outputs the second boundary condition that matches the first boundary condition, and sends the updated second boundary condition to the intake device module 4, and at the same time sends the updated first boundary condition and the second boundary condition to the twin model module 3.

[0045] The parameter database of the control analysis module 2 stores the optimal intake angle and intake pressure that match the first boundary condition. The quantitative relationship between the optimal intake angle, intake pressure and the first boundary condition is obtained by a series of numerical simulations performed by the twin model module 3 and based on machine learning fitting.

[0046] When the control analysis module 2 determines that the difference between the measured data and the twin model calculated data of the same monitoring point is greater than the upper limit of 5% to 10%, the data set is passed to the fault analysis module 5. The pressure, temperature, and oxygen concentration in the measured data and the calculated data have different weights at each monitoring point, and the difference is obtained by summing the weights.

[0047] The twin model module 3 is used to receive the decision signal from the control and analysis module 2, and construct a geometric model including: the air intake device, the upper pouring gate, the ladle bottom plate, the center pouring pipe and the ingot mold based on the decision signal, automatically divide the geometric model into grids, construct a physical model for multiphase flow field calculation, and calculate the three-dimensional distribution, pressure and temperature distribution of the molten steel, inert atmosphere and air between the air intake device module 4 and the ladle bottom plate, output the results in the form of charts, and monitor the inert atmosphere state in real time;

[0048] The physical model of the multiphase flow field couples the numerical calculation of heat convection, heat conduction and heat radiation. Because during injection, there is heat convection and heat conduction between multiple fluids, heat conduction inside the solid ingot mold, the wall of the center injection pipe and the bottom plate of the ladle, heat conduction between the fluid and the solid, and the high-temperature molten steel produces a thermal radiation effect, the multiphase flow field model considers three heat transfer modes.

[0049] like Figure 2 As shown, this is a schematic diagram of the real-time inert atmosphere distribution output by the twin model module in the present invention.

[0050] In this implementation case, the twin model module 3 outputs the real-time inert atmosphere distribution at a certain moment according to the decision signal.

[0051] like Figure 3 Schematic diagram of the air intake device module and monitoring points of an embodiment of the present invention is shown.

[0052] The air intake device module 4 is used to receive the decision signal of the control analysis module 2 for updating the second boundary condition, and to adjust the air intake angle and the air intake pressure of the air intake pipe 6;

[0053] The air intake device module 4 is composed of an air intake pipe 6, an annular air storage chamber 7, a narrow slit 8, a hollow spherical universal joint 9, an air intake pipe 10, and an automatic pressure valve 11. The air intake pipe 6 is connected to the annular air storage chamber 7, and inert gas is input into the annular air storage chamber 7.

[0054] like Figure 4 , which is a schematic diagram of the three-dimensional structure of the hollow spherical universal joint and the intake pipe of the intake device module of the present invention.

[0055] There is a narrow slit 8 outlet on the upper surface of the annular gas storage chamber 7, which is used to spray a uniform inert gas curtain; the center of the hollow spherical universal joint 9 is located at half the height of the outer wall of the annular gas storage chamber 7 and at any point of maximum diameter. The center of the ball rotates -88° to 88° around the x-axis and -62° to 62° around the y-axis.

[0056] The x-axis starts from the center of the hollow spherical universal joint 9 and points in a direction away from the outer wall of the annular air storage chamber 7 . The y-axis and the z-axis are clockwise Cartesian coordinate axes based on the x-axis.

[0057] The air inlet pipe 6 passes through the inner hole of the hollow spherical universal joint 9 and is fixed thereto, and its rotation angle is consistent with that of the hollow spherical universal joint 9 .

[0058] The intake pipe mover 10 is connected to the end of the intake pipe 6, and pushes the angle of the intake pipe 6 to adjust after receiving the decision signal of the control analysis module 2 to update the second boundary condition; the automatic pressure valve 11 is located at the end of the intake pipe 6 entering the inert gas, and adjusts the intake pressure after receiving the decision signal of the control analysis module 2 to update the second boundary condition.

[0059] The fault analysis module 5 is used to receive the data set sent by the control analysis module 2 and the hardware self-check report of each monitoring point, analyze and issue a fault report.

[0060] The rotation angle range of the spherical hollow universal joint of the air intake device module 4 covers all the intake angles in the parameter database of the control analysis module 2. The spherical hollow universal joint has a fixing plate 12, which is welded to the annular air storage chamber 7. The geometric shape of the fixing plate 12 is a spherical wall formed by rotating a semicircle 30° around the y-axis, and the inner diameter of the fixing plate 12 is the same as the outer diameter of the hollow spherical universal joint 9 to fix the hollow spherical universal joint 9. The contact surface between the universal joint and the fixing plate is smooth, ensuring that the universal joint can rotate freely and the universal joint will not fall off.

[0061] The monitoring points of the data collection module 1 include pressure, temperature and oxygen concentration monitoring points.

[0062] At least 4 pressure monitoring points are evenly distributed on the bottom plate of the ladle and are located within the radius from 2 cm outside the edge of the molten steel inlet to the outer diameter of the annular gas storage chamber 7. At least 2 are evenly distributed on the inner wall of the annular gas storage chamber 7, and at least 2 are distributed at the midpoint of the exposed height of the molten steel just above the widest part of the outer diameter of the annular gas storage chamber 7. The number of temperature monitoring points and oxygen concentration monitoring points is the same as that of pressure monitoring points, and they are 2 to 4 cm away from the pressure monitoring points to avoid overlapping and affecting the measurement between the monitoring points.

[0063] The number of temperature monitoring points and oxygen concentration monitoring points is consistent with that of pressure monitoring points, and they are 2 to 4 cm away from the pressure monitoring points to avoid overlapping and affecting the measurement between the monitoring points. After testing, the above monitoring point distribution can correctly reflect the physical state of the inert atmosphere. Table 1 shows the oxygen concentration of the monitoring points at the start, halfway and end of the injection of this embodiment, and the oxygen concentration is below 1%. The present invention ensures the stability of the low-oxygen inert atmosphere in complex working conditions and effectively avoids secondary oxidation.

[0064] The data collection module 1 collects the measured data from the monitoring points, the twin model module 3 calculates the data, and the first boundary conditions and the second boundary conditions. After each injection operation is completed, the control analysis module 2 inputs the data set into the twin model module 3, and performs neural network learning training on the twin model to continuously optimize the parameter database of the twin model module 3 and the control analysis module 2.

[0065] In summary, the present invention relates to a molten steel injection atmosphere protection system based on digital twin, which can collect information, make intelligent decisions and high-precision automated operations under the dynamic conditions of molten steel injection, to ensure that a low-oxygen inert atmosphere is always formed around the molten steel, effectively preventing the secondary oxidation of the molten steel.

[0066] Example 1

[0067] This embodiment adopts 8 pressure monitoring points, 2 of which are evenly distributed on the bottom plate of the ladle, and are located within the radius of 2 cm from the edge of the molten steel inlet to the outer diameter of the annular gas storage chamber 7. 3 monitoring points are evenly distributed on the inner wall of the annular gas storage chamber 7, and 3 monitoring points are distributed at the midpoint of the exposed height of the molten steel just above the widest part of the outer diameter of the annular gas storage chamber 7.

[0068] Table 1 Oxygen concentrations at monitoring points at the start, halfway and end of injection

[0069]

[0070] The data collection module 1 collects the measured data of the monitoring point, the calculated data of the twin model module 3 of the monitoring point, and the first boundary condition and the second boundary condition required for the twin model module 3 to calculate, so as to form a data set; the measured data of the monitoring point and the calculated data of the twin model module 3 include: pressure, temperature and oxygen concentration; the first boundary condition includes: the major axis length, the minor axis length, the molten steel injection flow rate, the molten steel temperature and the injection height of the elliptical molten steel injection port; the second boundary condition includes: the intake pressure and intake angle of the intake pipe 6;

[0071] In actual operation, the parameters included in the first boundary condition will be dynamically adjusted. For example, as the injection time increases, the temperature of the molten steel decreases and the viscosity increases. To ensure the injection speed, the length of the major axis and minor axis of the injection port changes, so as to adjust the size of the molten steel injection port and the injection speed. The change of the first boundary condition also requires adjustment of the intake pressure and the intake angle of the intake pipe 6 to ensure a stable and oxygen-concentrated inert atmosphere. That is, there is a high correlation between the first boundary condition and the second boundary condition.

[0072] The control analysis module 2 is used to receive the data set of the data collection module 1, and after analyzing the data set, determine whether to send a decision signal to the intake device module 4 and the twin model module 3; the data set includes: measured data of the monitoring point, twin model calculation data of the monitoring point, and the first and second boundary conditions; when the control analysis module 2 determines that the first boundary condition has changed, it calls the parameter database of the control analysis module 2, outputs the second boundary condition that matches the first boundary condition, and sends the updated second boundary condition to the intake device module 4, and at the same time sends the updated first boundary condition and the second boundary condition to the twin model module 3.

[0073] The parameter database of the control analysis module 2 stores the optimal intake angle and intake pressure that match the first boundary condition. The quantitative relationship between the optimal intake angle, intake pressure and the first boundary condition is obtained by a series of numerical simulations performed by the twin model module 3 and based on machine learning fitting.

[0074] When the control analysis module 2 determines that the difference between the measured data and the twin model calculated data of the same monitoring point is greater than the upper limit of 5% to 10%, the data set is passed to the fault analysis module 5. The pressure, temperature, and oxygen concentration in the measured data and the calculated data have different weights at each monitoring point, and the difference is obtained by summing the weights.

[0075] The twin model module 3 is used to receive the decision signal from the control and analysis module 2, and construct a geometric model including: the air intake device, the upper pouring gate, the ladle bottom plate, the center pouring pipe and the ingot mold based on the decision signal, automatically divide the geometric model into grids, construct a physical model for multiphase flow field calculation, and calculate the three-dimensional distribution, pressure and temperature distribution of the molten steel, inert atmosphere and air between the air intake device module 4 and the ladle bottom plate, output the results in the form of charts, and monitor the inert atmosphere state in real time;

[0076] The physical model of the multiphase flow field couples the numerical calculation of heat convection, heat conduction and heat radiation. Because during injection, there is heat convection and heat conduction between multiple fluids, heat conduction inside the solid ingot mold, the wall of the center injection pipe and the bottom plate of the ladle, heat conduction between the fluid and the solid, and the high-temperature molten steel produces a thermal radiation effect, the multiphase flow field model considers three heat transfer modes.

[0077] In this implementation case, the twin model module 3 outputs the real-time inert atmosphere distribution at a certain moment according to the decision signal.

[0078] The air intake device module 4 is used to receive the decision signal of the control analysis module 2 for updating the second boundary condition, and to adjust the air intake angle and the air intake pressure of the air intake pipe 6;

[0079] The air intake device module 4 is composed of an air intake pipe 6, an annular air storage chamber 7, a narrow slit 8, a hollow spherical universal joint 9, an air intake pipe 10, and an automatic pressure valve 11. The air intake pipe 6 is connected to the annular air storage chamber 7, and inert gas is input into the annular air storage chamber 7.

[0080] There is a narrow slit 8 outlet on the upper surface of the annular gas storage chamber 7, which is used to spray a uniform inert gas curtain; the center of the hollow spherical universal joint 9 is located at half the height of the outer wall of the annular gas storage chamber 7 and at any point of maximum diameter. The center of the ball rotates -88° to 88° around the x-axis and -62° to 62° around the y-axis.

[0081] The x-axis starts from the center of the hollow spherical universal joint 9 and points in a direction away from the outer wall of the annular air storage chamber 7 . The y-axis and the z-axis are clockwise Cartesian coordinate axes based on the x-axis.

[0082] The air inlet pipe 6 passes through the inner hole of the hollow spherical universal joint 9 and is fixed thereto, and its rotation angle is consistent with that of the hollow spherical universal joint 9 .

[0083] The intake pipe mover 10 is connected to the end of the intake pipe 6, and pushes the angle of the intake pipe 6 to adjust after receiving the decision signal of the control analysis module 2 to update the second boundary condition; the automatic pressure valve 11 is located at the end of the intake pipe 6 entering the inert gas, and adjusts the intake pressure after receiving the decision signal of the control analysis module 2 to update the second boundary condition.

[0084] The fault analysis module 5 is used to receive the data set sent by the control analysis module 2 and the hardware self-check report of each monitoring point, analyze and issue a fault report.

[0085] The rotation angle range of the spherical hollow universal joint of the air intake device module 4 covers all the intake angles in the parameter database of the control analysis module 2. The spherical hollow universal joint has a fixing plate 12, which is welded to the annular air storage chamber 7. The geometric shape of the fixing plate 12 is a spherical wall formed by rotating a semicircle 30° around the y-axis, and the inner diameter of the fixing plate 12 is the same as the outer diameter of the hollow spherical universal joint 9 to fix the hollow spherical universal joint 9. The contact surface between the universal joint and the fixing plate is smooth, ensuring that the universal joint can rotate freely and the universal joint will not fall off.

[0086] The monitoring points of the data collection module 1 include pressure, temperature and oxygen concentration monitoring points.

[0087] The number of temperature monitoring points and oxygen concentration monitoring points is consistent with that of pressure monitoring points, and they are 2 to 4 cm away from the pressure monitoring points to avoid overlapping and affecting the measurement between the monitoring points. After testing, the above monitoring point distribution can correctly reflect the physical state of the inert atmosphere. Table 1 shows the oxygen concentration of the monitoring points at the start, halfway and end of the injection of this embodiment, and the oxygen concentration is below 1%. The present invention ensures the stability of the low-oxygen inert atmosphere in complex working conditions and effectively avoids secondary oxidation.

[0088] The data collection module 1 collects the measured data from the monitoring points, the twin model module 3 calculates the data, and the first boundary conditions and the second boundary conditions. After each injection operation is completed, the control analysis module 2 inputs the data set into the twin model module 3, and performs neural network learning training on the twin model to continuously optimize the parameter database of the twin model module 3 and the control analysis module 2.

[0089] Example 2

[0090] Four pressure monitoring points are evenly distributed on the bottom plate of the ladle and are located within the radius from 2 cm outside the edge of the molten steel inlet to the outer diameter of the annular gas storage chamber 7. Two are evenly distributed on the inner wall of the annular gas storage chamber 7, and two are distributed at the midpoint of the exposed height of the molten steel just above the widest part of the outer diameter of the annular gas storage chamber 7. The number of temperature monitoring points and oxygen concentration monitoring points is the same as that of pressure monitoring points, and they are 2 to 4 cm away from the pressure monitoring points to avoid overlapping and affecting the measurement between the monitoring points.

[0091] The data collection module 1 collects the measured data of the monitoring point, the calculated data of the twin model module 3 of the monitoring point, and the first boundary condition and the second boundary condition required for the twin model module 3 to calculate, so as to form a data set; the measured data of the monitoring point and the calculated data of the twin model module 3 include: pressure, temperature and oxygen concentration; the first boundary condition includes: the major axis length, the minor axis length, the molten steel injection flow rate, the molten steel temperature and the injection height of the elliptical molten steel injection port; the second boundary condition includes: the intake pressure and intake angle of the intake pipe 6;

[0092] In actual operation, the parameters included in the first boundary condition will be dynamically adjusted. For example, as the injection time increases, the temperature of the molten steel decreases and the viscosity increases. To ensure the injection speed, the length of the major axis and minor axis of the injection port changes, so as to adjust the size of the molten steel injection port and the injection speed. The change of the first boundary condition also requires adjustment of the intake pressure and the intake angle of the intake pipe 6 to ensure a stable and oxygen-concentrated inert atmosphere. That is, there is a high correlation between the first boundary condition and the second boundary condition.

[0093] The control analysis module 2 is used to receive the data set of the data collection module 1, and after analyzing the data set, determine whether to send a decision signal to the intake device module 4 and the twin model module 3; the data set includes: measured data of the monitoring point, twin model calculation data of the monitoring point, and the first and second boundary conditions; when the control analysis module 2 determines that the first boundary condition has changed, it calls the parameter database of the control analysis module 2, outputs the second boundary condition that matches the first boundary condition, and sends the updated second boundary condition to the intake device module 4, and at the same time sends the updated first boundary condition and the second boundary condition to the twin model module 3.

[0094] The parameter database of the control analysis module 2 stores the optimal intake angle and intake pressure that match the first boundary condition. The quantitative relationship between the optimal intake angle, intake pressure and the first boundary condition is obtained by a series of numerical simulations performed by the twin model module 3 and based on machine learning fitting.

[0095] When the control analysis module 2 determines that the difference between the measured data and the twin model calculated data of the same monitoring point is greater than the upper limit of 5% to 10%, the data set is passed to the fault analysis module 5. The pressure, temperature, and oxygen concentration in the measured data and the calculated data have different weights at each monitoring point, and the difference is obtained by summing the weights.

[0096] The twin model module 3 is used to receive the decision signal from the control and analysis module 2, and construct a geometric model including: the air intake device, the upper pouring gate, the ladle bottom plate, the center pouring pipe and the ingot mold based on the decision signal, automatically divide the geometric model into grids, construct a physical model for multiphase flow field calculation, and calculate the three-dimensional distribution, pressure and temperature distribution of the molten steel, inert atmosphere and air between the air intake device module 4 and the ladle bottom plate, output the results in the form of charts, and monitor the inert atmosphere state in real time;

[0097] The physical model of the multiphase flow field couples the numerical calculation of heat convection, heat conduction and heat radiation. Because during injection, there is heat convection and heat conduction between multiple fluids, heat conduction inside the solid ingot mold, the wall of the center injection pipe and the bottom plate of the ladle, heat conduction between the fluid and the solid, and the high-temperature molten steel produces a thermal radiation effect, the multiphase flow field model considers three heat transfer modes.

[0098] In this implementation case, the twin model module 3 outputs the real-time inert atmosphere distribution at a certain moment according to the decision signal.

[0099] The air intake device module 4 is used to receive the decision signal of the control analysis module 2 for updating the second boundary condition, and to adjust the air intake angle and the air intake pressure of the air intake pipe 6;

[0100] The air intake device module 4 is composed of an air intake pipe 6, an annular air storage chamber 7, a narrow slit 8, a hollow spherical universal joint 9, an air intake pipe 10, and an automatic pressure valve 11. The air intake pipe 6 is connected to the annular air storage chamber 7, and inert gas is input into the annular air storage chamber 7.

[0101] There is a narrow slit 8 outlet on the upper surface of the annular gas storage chamber 7, which is used to spray a uniform inert gas curtain; the center of the hollow spherical universal joint 9 is located at half the height of the outer wall of the annular gas storage chamber 7 and at any point of maximum diameter. The center of the ball rotates -88° to 88° around the x-axis and -62° to 62° around the y-axis.

[0102] The x-axis starts from the center of the hollow spherical universal joint 9 and points in a direction away from the outer wall of the annular air storage chamber 7 . The y-axis and the z-axis are clockwise Cartesian coordinate axes based on the x-axis.

[0103] The air inlet pipe 6 passes through the inner hole of the hollow spherical universal joint 9 and is fixed thereto, and its rotation angle is consistent with that of the hollow spherical universal joint 9 .

[0104] The intake pipe mover 10 is connected to the end of the intake pipe 6, and pushes the angle of the intake pipe 6 to adjust after receiving the decision signal of the control analysis module 2 to update the second boundary condition; the automatic pressure valve 11 is located at the end of the intake pipe 6 entering the inert gas, and adjusts the intake pressure after receiving the decision signal of the control analysis module 2 to update the second boundary condition.

[0105] The fault analysis module 5 is used to receive the data set sent by the control analysis module 2 and the hardware self-check report of each monitoring point, analyze and issue a fault report.

[0106] The rotation angle range of the spherical hollow universal joint of the air intake device module 4 covers all the intake angles in the parameter database of the control analysis module 2. The spherical hollow universal joint has a fixing plate 12, which is welded to the annular air storage chamber 7. The geometric shape of the fixing plate 12 is a spherical wall formed by rotating a semicircle 30° around the y-axis, and the inner diameter of the fixing plate 12 is the same as the outer diameter of the hollow spherical universal joint 9 to fix the hollow spherical universal joint 9. The contact surface between the universal joint and the fixing plate is smooth, ensuring that the universal joint can rotate freely and the universal joint will not fall off.

[0107] The monitoring points of the data collection module 1 include pressure, temperature and oxygen concentration monitoring points.

[0108] The number of temperature monitoring points and oxygen concentration monitoring points is consistent with that of pressure monitoring points, and they are 2 to 4 cm away from the pressure monitoring points to avoid overlapping and affecting the measurement between the monitoring points. After testing, the above monitoring point distribution can correctly reflect the physical state of the inert atmosphere. Table 1 shows the oxygen concentration of the monitoring points at the start, halfway and end of the injection of this embodiment, and the oxygen concentration is below 1%. The present invention ensures the stability of the low-oxygen inert atmosphere in complex working conditions and effectively avoids secondary oxidation.

[0109] The data collection module 1 collects the measured data from the monitoring points, the twin model module 3 calculates the data, and the first boundary conditions and the second boundary conditions. After each injection operation is completed, the control analysis module 2 inputs the data set into the twin model module 3, and performs neural network learning training on the twin model to continuously optimize the parameter database of the twin model module 3 and the control analysis module 2.

[0110] The terms used in the present invention are illustrative and exemplary, rather than restrictive. Since the present invention can be implemented in various forms without departing from the spirit or essence of the technical solution, it should be understood that the above embodiments are not limited to any of the aforementioned details, but should be widely interpreted within the spirit and scope defined by the attached claims, so all changes and modifications falling within the scope of the claims or their equivalents should be covered by the attached claims.

Claims

1. A molten steel injection atmosphere protection system based on digital twin, characterized in that: include: Data collection module, control analysis module, twin model module, air intake device module; The data collection module and the twin model module are in wireless communication with the control analysis module respectively, the control analysis module is connected with the air intake device module by wired or wireless communication, and the data collection module is in wireless communication with the twin model module; A data collection module collects measured data of monitoring points, calculated data of the twin model module of the monitoring points, and first boundary conditions and second boundary conditions required for input by the twin model module for calculation, so as to form a data set; The measured data of the monitoring point and the calculated data of the twin model module include: pressure, temperature and oxygen concentration; the first boundary condition includes: the major axis length, minor axis length, steel liquid injection flow rate, steel liquid temperature and injection height of the elliptical steel liquid injection port; the second boundary condition includes: the intake pressure and intake angle of the intake pipe; A control analysis module, used to receive a data set from a data collection module, and after analyzing the data set, determine whether to send a decision signal to an intake device module and a twin model module; the data set includes: measured data of a monitoring point, calculated data of a twin model of a monitoring point, and first and second boundary conditions; when the control analysis module determines that the first boundary condition has changed, the control analysis module calls a parameter database of the control analysis module, outputs a second boundary condition that matches the first boundary condition, and sends the updated second boundary condition to the intake device module, and at the same time sends the updated first boundary condition and second boundary condition to the twin model module; The twin model module is used to receive the decision signal from the control analysis module, and build a geometric model including: the air intake device, the upper pouring gate, the ladle bottom plate, the center pouring pipe and the ingot mold based on the decision signal, automatically divide the geometric model into grids, build a physical model for multiphase flow field calculation, and calculate the three-dimensional distribution, pressure and temperature distribution of the molten steel, inert atmosphere and air between the air intake device module 4 and the ladle bottom plate, and output the results in the form of charts to monitor the inert atmosphere state in real time; The air intake device module is used to receive the decision signal of the control analysis module for updating the second boundary condition, and to adjust the intake angle and intake pressure of the intake pipe; the air intake device module includes: an intake pipe, an annular air storage chamber, a narrow gap, a hollow spherical universal joint, an intake pipe, and an automatic pressure valve. The intake pipe is connected to the annular air storage chamber, and inert gas is input into the annular air storage chamber.

2. The molten steel injection atmosphere protection system based on digital twinning according to claim 1, characterized in that: It also includes a fault analysis module, which communicates wirelessly with the control analysis module. The fault analysis module is used to receive the data set sent by the control analysis module and the hardware self-test report of each monitoring point, analyze and issue a fault report.

3. The molten steel injection atmosphere protection system based on digital twinning according to claim 1, characterized in that: The parameter database of the control analysis module stores the optimal intake angle and intake pressure that match the first boundary condition. The quantitative relationship between the optimal intake angle, intake pressure and the first boundary condition is obtained through a series of numerical simulations performed by the twin model module and based on machine learning fitting.

4. The molten steel injection atmosphere protection system based on digital twinning according to claim 1, characterized in that: The rotation angle range of the spherical hollow universal joint of the intake device module covers all intake angles in the parameter database of the control analysis module; the spherical hollow universal joint has a fixing plate, which is welded to the annular air storage chamber; the geometric shape of the fixing plate is a spherical wall formed by rotating a semicircle 30° around the y-axis, and the inner diameter of the fixing plate is the same as the outer diameter of the hollow spherical universal joint to fix the hollow spherical universal joint; the contact surface between the universal joint and the fixing plate is smooth to ensure the free rotation of the universal joint.

5. The molten steel injection atmosphere protection system based on digital twinning according to claim 1, characterized in that: There is a narrow slit outlet on the upper surface of the annular air storage chamber for spraying a uniform inert gas curtain; the center of the hollow spherical universal joint is located at half the height of the outer wall of the annular air storage chamber and at any point of maximum diameter; the intake pipe is fixed through the inner hole of the hollow spherical universal joint and is consistent with the rotation angle of the hollow spherical universal joint; the intake pipe mover is connected to the end of the intake pipe, and promotes the adjustment of the intake pipe angle after receiving the decision signal of the control analysis module to update the second boundary condition; the automatic pressure valve is located at the end of the intake pipe where the inert gas enters, and adjusts the intake pressure after receiving the decision signal of the control analysis module to update the second boundary condition.

6. The molten steel injection atmosphere protection system based on digital twinning according to claim 1, characterized in that: The monitoring points of the data collection module include pressure, temperature and oxygen concentration monitoring points. At least 4 pressure monitoring points are evenly distributed on the bottom plate of the ladle and are located within a radius from 2 cm outside the edge of the molten steel inlet to the outer diameter of the annular gas storage chamber. At least 2 are evenly distributed on the inner wall of the annular gas storage chamber, and at least 2 are distributed at the midpoint of the exposed height of the molten steel just above the widest part of the outer diameter of the annular gas storage chamber. The number of temperature monitoring points and oxygen concentration monitoring points is the same as that of pressure monitoring points, and they are 2 to 4 cm away from the pressure monitoring points to avoid overlapping and affecting the measurement between the monitoring points.

7. The molten steel injection atmosphere protection system based on digital twinning according to claim 1, characterized in that: The data collection module’s monitored point measured data, the twin model module’s calculated data, and the first and second boundary conditions are input into the twin model module through the control analysis module after each injection operation is completed. The twin model is trained through neural network learning to continuously optimize the parameter database of the twin model module and the control analysis module.

8. The molten steel injection atmosphere protection system based on digital twinning according to claim 1, characterized in that: When the control analysis module determines that the difference between the measured data and the twin model calculated data at the same monitoring point is greater than the upper limit of 5% to 10%, the data set is passed to the fault analysis module. The pressure, temperature, and oxygen concentration in the measured data and the calculated data have different weights at each monitoring point, and the difference is obtained by summing the weights.

9. The molten steel injection atmosphere protection method based on digital twin of the molten steel injection atmosphere protection system according to any one of claims 1 to 8, characterized in that: include: The data collection module collects measured data of the monitoring point, calculated data of the twin model module of the monitoring point, and the first boundary condition and the second boundary condition required for the twin model module to calculate, so as to form a data set; The measured data of the monitoring point and the calculated data of the twin model module include: pressure, temperature and oxygen concentration; the first boundary condition includes: the major axis length, minor axis length, steel liquid injection flow rate, steel liquid temperature and injection height of the elliptical steel liquid injection port; the second boundary condition includes: the intake pressure and intake angle of the intake pipe; The control analysis module receives the data set from the data collection module, and after analyzing the data set, determines whether to send a decision signal to the air intake device module and the twin model module; the data set includes: measured data of the monitoring point, calculated data of the twin model of the monitoring point, and the first and second boundary conditions; when the control analysis module determines that the first boundary condition has changed, the parameter database of the control analysis module is called, the second boundary condition matching the first boundary condition is output, and the updated second boundary condition is sent to the air intake device module, and the updated first boundary condition and the second boundary condition are sent to the twin model module at the same time; The twin model module receives the decision signal from the control analysis module, and builds a geometric model including: the air intake device, the upper pouring gate, the ladle bottom plate, the center pouring pipe and the ingot mold based on the decision signal, automatically divides the geometric model into grids, builds a physical model for multiphase flow field calculation, and calculates the three-dimensional distribution, pressure and temperature distribution of the molten steel, inert atmosphere and air between the air intake device module 4 and the ladle bottom plate, outputs the results in the form of charts, and monitors the inert atmosphere state in real time; The air intake device module receives the decision signal of updating the second boundary condition from the control analysis module, and executes the adjustment of the intake angle and intake pressure of the intake pipe; the air intake device module includes: an intake pipe, an annular air storage chamber, a narrow gap, a hollow spherical universal joint, an intake pipe, and an automatic pressure valve. The intake pipe is connected to the annular air storage chamber, and inert gas is input into the annular air storage chamber.

10. The method for molten steel injection atmosphere protection based on digital twinning according to claim 9, characterized in that: The fault analysis module receives the data set sent by the control analysis module and the hardware self-test report of each monitoring point, analyzes and issues a fault report.

Images