Continuous casting adjustment method and system for crystallizer assembly simulation

Abstract

The invention discloses a continuous casting adjustment method and system for crystallizer assembly simulation, and relates to the technical field of continuous casting process optimizing.The method comprises the steps that networking data collection is conducted according to equipment ID and molten steel component information of a crystallizer assembly, and continuous casting historical data are obtained; performing working condition expansion on the continuous casting historical data to obtain continuous casting coverage data; establishing an initial finite element model; calibrating boundary conditions to obtain a continuous casting finite element model; clustering analysis is carried out, and a continuous casting optimization difference starting point is positioned; parallel local iteration optimization is started, and a continuous casting multi-target equilibrium solution set is obtained; and performing global iteration optimization to obtain the continuous casting adjustment control reference. The technical problem that in the prior art, the blank shell uniformity and thickness are difficult to accurately control in the continuous casting process, and consequently the continuous casting quality is unstable is solved, and the technical effects that the blank shell uniformity and thickness are indirectly optimized and controlled in the continuous casting process, and the continuous casting quality is improved are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of continuous casting process optimization, and specifically relates to a continuous casting adjustment method and system for mold assembly simulation. Background Art

[0002] In modern steel production, the continuous casting process, as a key link, has a crucial impact on the quality of steel billets, production efficiency, and energy consumption. However, the current continuous casting process faces many challenges. On the one hand, when controlling the uniformity and thickness of the shell, there are lack of accurate and effective means. Traditional methods often have difficulty in adjusting in a timely manner according to complex and changeable working conditions, resulting in uneven quality of the shell and affecting the subsequent processing performance and product quality of the steel. On the other hand, it is difficult to balance the continuous casting efficiency and heat dissipation energy consumption. In order to pursue efficiency and increase the casting speed, it often leads to insufficient heat dissipation, increasing energy consumption while reducing product quality.

[0003] There are technical problems in the prior art that it is difficult to accurately control the uniformity and thickness of the shell during the continuous casting process, resulting in unstable continuous casting quality. Summary of the Invention

[0004] The present application provides a continuous casting adjustment method and system for mold assembly simulation, which is used to solve the technical problem that in the prior art, it is difficult to accurately control the uniformity and thickness of the shell during the continuous casting process, resulting in unstable continuous casting quality.

[0005] In view of the above problems, the present application provides a continuous casting adjustment method and system for mold assembly simulation.

[0006] In the first aspect of the present application, a continuous casting adjustment method for mold assembly simulation is provided. The method includes: Collecting network data according to the equipment ID of the mold assembly and the molten steel component information to obtain continuous casting historical data; expanding the working conditions of the continuous casting historical data by linear interpolation to obtain continuous casting coverage data; locally calling the component structure information according to the equipment ID to establish an initial finite element model; calibrating the boundary conditions of the initial finite element model with the continuous casting coverage data to obtain a continuous casting finite element model; performing cluster analysis on the continuous casting historical data according to the shell quality index to locate W starting points of continuous casting optimization differences; copying the continuous casting finite element model to W continuous casting thermal simulation containers; after inputting the W starting points of continuous casting optimization differences into the W continuous casting thermal simulation containers, starting parallel local iterative optimization to obtain a continuous casting multi-objective equilibrium solution set; screening the solution with the lowest energy consumption from the continuous casting multi-objective equilibrium solution set as the reference solution, and inputting the reference solution into the continuous casting finite element model for global iterative optimization to obtain a continuous casting adjustment control reference.

[0007] In the second aspect of the present application, an air pollution diffusion path tracing system based on meteorological data is provided. The system includes: The continuous casting historical data acquisition module is used to perform network data acquisition based on the equipment ID of the mold assembly and the molten steel component information to obtain continuous casting historical data; the working condition expansion module is used to expand the working conditions of the continuous casting historical data by linear interpolation to obtain continuous casting coverage data; the model establishment module is used to locally call the component structure information according to the equipment ID to establish an initial finite element model; the continuous casting finite element model acquisition module is used to calibrate the boundary conditions of the initial finite element model with the continuous casting coverage data to obtain a continuous casting finite element model; the clustering analysis module is used to perform clustering analysis on the continuous casting historical data according to the shell quality index to locate W starting points of continuous casting optimization differences; the model replication module is used to replicate the continuous casting finite element model to W continuous casting thermal simulation containers; the local iterative optimization module is used to start parallel local iterative optimization after inputting the W starting points of continuous casting optimization differences into the W continuous casting thermal simulation containers to obtain a continuous casting multi-objective equilibrium solution set; the global iterative optimization module is used to select the solution with the lowest energy consumption from the continuous casting multi-objective equilibrium solution set as the reference solution, and input the reference solution into the continuous casting finite element model for global iterative optimization to obtain a continuous casting adjustment control reference.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: Perform network data acquisition based on the equipment ID of the mold assembly and the molten steel component information to obtain continuous casting historical data; expand the working conditions of the continuous casting historical data by linear interpolation to obtain continuous casting coverage data; establish an initial finite element model; calibrate the boundary conditions of the initial finite element model to obtain a continuous casting finite element model; perform clustering analysis to locate W starting points of continuous casting optimization differences; replicate the continuous casting finite element model to W continuous casting thermal simulation containers; start parallel local iterative optimization after inputting the W starting points of continuous casting optimization differences into the W continuous casting thermal simulation containers to obtain a continuous casting multi-objective equilibrium solution set; select the solution with the lowest energy consumption from the continuous casting multi-objective equilibrium solution set as the reference solution, and input the reference solution into the continuous casting finite element model for global iterative optimization to obtain a continuous casting adjustment control reference. It achieves the technical effect of indirectly optimizing and controlling the shell uniformity and thickness during continuous casting and improving the quality of continuous casting. Description of the Drawings

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0010] Figure 1Schematic flow chart of a continuous casting adjustment method for mold assembly simulation provided by an embodiment of the present application; Figure 2 Schematic structural diagram of a continuous casting adjustment system for mold assembly simulation provided by an embodiment of the present application.

[0011] Explanation of reference numerals: Continuous casting historical data acquisition module 10, working condition expansion module 20, model establishment module 30, continuous casting finite element model acquisition module 40, clustering analysis module 50, model replication module 60, local iterative optimization module 70, global iterative optimization module 80. Detailed implementation manners

[0012] The present application provides a continuous casting adjustment method and system for mold assembly simulation, which is used to solve the technical problem that in the prior art, the shell uniformity and thickness in the continuous casting process are difficult to accurately control, resulting in unstable continuous casting quality.

[0013] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0014] Embodiment 1, as Figure 1 shown, the present application provides a continuous casting adjustment method for mold assembly simulation, and the method includes: Step S100: Perform network data collection according to the equipment ID of the mold assembly and the molten steel component information to obtain continuous casting historical data.

[0015] Specifically, first identify the equipment ID of the mold assembly. The ID is the identity identifier of the equipment and can accurately locate the target mold. At the same time, obtain the information of the molten steel components participating in the continuous casting process, because the chemical composition of the molten steel will affect its solidification characteristics and continuous casting effect. Based on the equipment ID and the molten steel component information, start the network data collection work. With the help of the network connections with various sensors, monitoring devices, and databases on the production line, widely collect the historical data generated during the continuous casting process. These data cover multiple key parameters, including multiple sets of water spray volume data. The water spray volume is directly related to the cooling effect of the mold, and different water spray volumes will affect the solidification speed of the molten steel; the scale removal frequency data, which reflects the cleaning and maintenance situation of the mold. An appropriate scale removal frequency can ensure the cleanliness inside the mold and avoid scale formation affecting the cooling efficiency; the angle data of the water refinement component. The change in this angle will change the spraying direction and dispersion degree of the water flow, thereby affecting the uniformity of molten steel cooling; the injection speed data, which controls the rate of molten steel entering the mold and plays an important role in the forming quality of the billet; the shell uniformity and shell thickness data. These two parameters directly reflect the quality of the continuous casting product. Uniform shells and appropriate thickness are important indicators of high-quality billets. By comprehensively collecting these data, the continuous casting historical data is obtained.

[0016] Step S200: Use linear interpolation to expand the working conditions of the continuous casting historical data to obtain continuous casting coverage data.

[0017] Specifically, determine the continuous casting adjustment constraints according to the component structure information. These constraints include the water spray volume range, the scale removal frequency range, the angle range of the water refinement component, etc. After presetting the multi-dimensional interpolation scale, perform multi-dimensional grid interpolation within the continuous casting adjustment constraints to generate grid interpolation data. Then, use the continuous casting historical data to traverse the grid interpolation data and locate multiple missing data points. Guided by these missing data points, perform adjacent working condition expansion on the continuous casting historical data to obtain multiple sets of updated working condition data. Based on the adjacent working condition relationship between the continuous casting historical data and the multiple sets of updated working condition data, use linear calculation of intermediate values to predict the shell quality and obtain multiple sets of updated shell quality. Associate and store the multiple sets of updated working condition data and the multiple sets of updated shell quality to obtain multiple working condition prediction data. These working condition prediction data and the continuous casting historical data together constitute the continuous casting coverage data. This continuous casting coverage data can more comprehensively reflect the various parameter situations under different working conditions during the continuous casting process, providing strong support for establishing a more accurate continuous casting model and optimizing the continuous casting process in the future.

[0018] Step S300: Locally call the component structure information according to the equipment ID to establish an initial finite element model.

[0019] Specifically, through precise positioning by the device ID, the component structure information corresponding to the mold assembly is called from the local storage, providing a key basis for establishing the finite element model. This component structure information details the geometric shapes, dimensional specifications, and mutual connection relationships of various parts of the mold. Using this data, an initial finite element model containing multiple functional modules is constructed, including a cooling water injection dynamics module, a self-cleaning mechanics module, a droplet sputtering optimization module, and a molten steel solidification thermodynamics module. The cooling water injection dynamics module is used to simulate the injection process of cooling water in the mold and analyze the influence of water flow velocity, pressure distribution, etc. on the cooling effect; the self-cleaning mechanics module focuses on the cleaning mechanism of the mold during the continuous casting process and studies the role of operations such as scale scraping on the equipment operation; the droplet sputtering optimization module simulates and optimizes the sputtering situation when the cooling water droplets impact the mold and the molten steel; the molten steel solidification thermodynamics module focuses on simulating the solidification process of the molten steel in the mold, including key parameters such as temperature change and solidification rate. By integrating these modules, an initial finite element model that can comprehensively reflect the physical phenomena in the continuous casting process is established.

[0020] Step S400: Calibrate the boundary conditions of the initial finite element model using the continuous casting coverage data to obtain a continuous casting finite element model.

[0021] Specifically, the initial finite element model established according to the component structure information includes a cooling water injection dynamics module, a self-cleaning mechanics module, a droplet sputtering optimization module, and a molten steel solidification thermodynamics module. Then, the continuous casting coverage data is decomposed according to the requirements of each module to obtain a cooling water injection data group, a self-cleaning mechanics data group, a droplet sputtering data group, and a molten steel solidification data group. These data groups are respectively mapped and loaded into the corresponding modules for single-module calibration. For example, the cooling water injection data group is loaded into the cooling water injection dynamics module to calibrate boundary conditions such as water flow velocity and injection angle; the self-cleaning mechanics data group is used to calibrate the boundary conditions of relevant parameters such as scale scraping frequency and scale scraping force in the self-cleaning mechanics module. After completing the single-module calibration, a multi-physical field coupling co-verification is performed on the initial finite element model. This process considers the interaction and influence between various physical fields, such as the coupling of the cooling water flow field and the molten steel solidification temperature field, and the mutual influence between the self-cleaning process and the droplet sputtering process. After strict calibration and verification, a continuous casting finite element model that can more accurately reflect the actual working conditions of continuous casting is output, providing a reliable model basis for subsequent continuous casting process analysis and optimization.

[0022] Step S500: Perform cluster analysis on the continuous casting historical data according to the shell quality index to locate W continuous casting optimization difference starting points.

[0023] Specifically, by deeply analyzing the continuous casting historical data based on the shell quality indicators, the starting point of continuous casting optimization differences is determined. The shell quality indicators mainly involve the shell uniformity and the requirements for the shell thickness, and these two indicators are directly related to the quality of the continuous casting products. When performing clustering analysis, first calculate the Euclidean distances between the shell quality indicators and multiple shell quality records in the continuous casting historical data (including the historical shell uniformity and the historical shell thickness), and extract H continuous casting working condition records with descending distances from numerous continuous casting working condition records (constituted by the water injection amount parameter, the scale removal frequency parameter, the water refinement component angle parameter, and the injection speed parameter), where H ≥ 20W (H and W are positive integers). Then, perform combined enumeration on these H continuous casting working condition records to obtain multiple groups of continuous casting working condition record combinations. Take the H continuous casting working condition records as topological nodes and the Euclidean distance of each group of continuous casting working condition record combinations as the topological length to construct a continuous casting working condition topology. After that, perform a topological connection removal operation on the continuous casting working condition topology using a preset working condition topology distance. After screening, W isolated nodes are obtained, and the W continuous casting working condition records corresponding to these isolated nodes are the starting points of continuous casting optimization differences. Determining these difference starting points helps to conduct optimization analysis for different working conditions subsequently, thereby improving the overall quality of the continuous casting process and achieving the balanced optimization of the continuous casting efficiency and product quality.

[0024] Step S600: Copy the continuous casting finite element model to W continuous casting thermal simulation containers.

[0025] Specifically, when a continuous casting finite element model is successfully constructed through the previous steps, in order to achieve multi-condition parallel optimization analysis, the model needs to be copied to W continuous casting thermal simulation containers. These W continuous casting thermal simulation containers are the basic carriers for subsequent parallel local iterative optimization. Since there are various different working condition possibilities in the continuous casting production process, each continuous casting thermal simulation container can independently simulate a working condition scenario. Copying the continuous casting finite element model completely to each container ensures that each container has a comprehensive and consistent model basis, including the cooling water injection dynamics module, the self-cleaning mechanics module, the droplet sputtering optimization module, and the molten steel solidification thermodynamics module in the model, etc. In this way, each continuous casting thermal simulation container can simulate and analyze the continuous casting process under its respective working condition settings, providing a parallel computing environment basis for inputting the starting points of continuous casting optimization differences and conducting parallel local iterative optimization subsequently, which helps to improve the efficiency of optimization analysis, explore the optimization directions of the continuous casting process from multiple perspectives simultaneously, and ultimately achieve the multi-objective balanced optimization of the continuous casting process.

[0026] Step S700: After inputting the W starting points of continuous casting optimization differences into the W continuous casting thermal simulation containers, start parallel local iterative optimization to obtain a continuous casting multi-objective balanced solution set.

[0027] Specifically, after the collection and processing of continuous casting historical data and the positioning of the starting point of continuous casting optimization differences, it enters the parallel local iterative optimization stage. First, to ensure efficient calculation, independent computing resources, including CPU / GPU cores and memory, are allocated to each continuous casting thermal simulation container. These independent computing resources enable each continuous casting thermal simulation container to carry out computing work simultaneously and without interference, greatly improving the overall computing efficiency. The W starting points of continuous casting optimization differences obtained previously are respectively input into the corresponding W continuous casting thermal simulation containers. Each starting point of continuous casting optimization represents a combination of continuous casting working conditions with potential optimization value. After entering the container, taking one of the continuous casting thermal simulation containers as an example, the first starting point of continuous casting optimization is input into the first continuous casting thermal simulation container for unit continuous casting production simulation. During the simulation process, through the pre-constructed simulation solution evaluation weight, factors such as energy consumption, shell uniformity deviation, shell thickness deviation, scale residue amount, and water consumption are comprehensively considered to quantify the continuous casting performance and output the first simulation solution coefficient. Then, the preset continuous casting working condition search scale is used to update this starting point of continuous casting optimization to obtain the first updated continuous casting working condition, and the continuous casting performance is quantified again for the first continuous casting thermal simulation container to output the second simulation solution coefficient. If the second simulation solution coefficient is better than the first simulation coefficient, the continuous casting working condition search scale is updated according to the deviation between the two to obtain the first updated search scale, and then the continuous casting working condition is adjusted and simulated again, and this process continues. In this way, the continuous casting working condition search scale is continuously updated and the continuous casting performance is quantitatively evaluated according to the simulation solution coefficients obtained from adjacent optimizations until the deviation between the adjacent optimized simulation solution coefficients is less than the preset threshold, and the first local iterative optimal solution is output. For the remaining W - 1 continuous casting thermal simulation containers, the iterative optimization work is carried out in parallel in the same way. Finally, the W local iterative optimal solutions output by the W continuous casting thermal simulation containers together constitute the continuous casting multi-objective equilibrium solution set. This solution set comprehensively considers multiple objectives such as continuous casting quality, efficiency, and heat dissipation energy consumption, provides a rich variety of optimization schemes for screening the solution with the lowest energy consumption from the solution set and further inputting it into the continuous casting finite element model for global iterative optimization to determine the continuous casting adjustment control benchmark, and strongly promotes the overall optimization process of the continuous casting process.

[0028] Step S800: Select the solution with the lowest energy consumption from the continuous casting multi-objective equilibrium solution set as the reference solution, and input the reference solution into the continuous casting finite element model for global iterative optimization to obtain the continuous casting adjustment control benchmark.

[0029] Specifically, through screening from the continuous casting multi-objective equilibrium solution set, which contains multiple solutions that are balanced and optimized in terms of energy consumption, shell quality, etc., and energy consumption is an important consideration factor in continuous casting production. By comparing the energy consumption corresponding to each solution in the solution set, the solution with the lowest energy consumption is selected as the benchmark solution. This benchmark solution represents a combination of continuous casting condition settings with the best energy consumption performance in the previous local iterative optimization. Subsequently, the benchmark solution is input into the continuous casting finite element model, which integrates multiple modules such as cooling water injection dynamics, self-cleaning mechanics, droplet sputtering optimization, and molten steel solidification thermodynamics, and can comprehensively simulate the continuous casting process. Taking the benchmark solution as the initial condition, global iterative optimization is carried out in the model. During the iterative process, various parameters in the model, such as water injection volume, descaling frequency, angle of the water refinement component, injection speed, etc., are continuously adjusted, and the impacts of these parameter changes on continuous casting quality, efficiency, and energy consumption are comprehensively considered. After multiple iterative calculations, the model gradually converges to a better state, and finally, the continuous casting adjustment control benchmark is obtained. This benchmark provides an accurate adjustment basis for actual continuous casting production, helping operators to balance continuous casting efficiency and heat dissipation energy consumption while ensuring continuous casting quality by controlling the water spraying system and tundish injection speed, etc., and optimizing the continuous casting production process.

[0030] In a possible implementation manner, step S200 further includes: Step S210: Define continuous casting adjustment constraints according to the component structure information, where the continuous casting adjustment constraints include a water injection volume range, a descaling frequency range, and an angle range of the water refinement component.

[0031] Step S220: Preset a multi-dimensional interpolation scale, and perform multi-dimensional grid interpolation within the continuous casting adjustment constraints with the multi-dimensional interpolation scale as the constraint to generate grid interpolation data.

[0032] Step S230: Traverse the grid interpolation data using the continuous casting historical data to locate multiple missing data points.

[0033] Step S240: Expand and cover the continuous casting historical data based on the multiple missing data points to obtain continuous casting prediction data, where the continuous casting prediction data includes multiple condition prediction data, and the continuous casting prediction data and the continuous casting historical data constitute the continuous casting coverage data.

[0034] Specifically, read the component structure information of the mold assembly, which covers key contents such as the design specifications, material characteristics, and connection relationships between various parts of the mold, and determine the adjustment constraint range during the continuous casting process. The limitation of the water spray amount range takes into account the cooling requirements of the mold and the influence of water flow on the solidification process of the molten steel. Excessive or too little water spray amount may lead to uneven cooling, affecting the quality of the shell and the continuous casting efficiency; the scale frequency range is related to the cleaning and maintenance inside the mold. A reasonable scale frequency can not only prevent the accumulation of scale from affecting the cooling effect but also avoid unnecessary wear on the equipment due to excessive scaling; the determination of the angle range of the water refinement component is because this angle will change the spraying direction and dispersion degree of the water flow, thereby affecting the cooling uniformity of the molten steel and the quality of the billet. By limiting these three ranges, clear boundary conditions are provided for subsequent continuous casting process adjustment and optimization, ensuring that the continuous casting process is carried out within a reasonable parameter range.

[0035] Preset a multi-dimensional interpolation scale, which is set according to the complexity of the continuous casting process and the requirements for data accuracy. It comprehensively considers multiple key factors affecting the continuous casting process, such as the water spray amount, scale frequency, and angle of the water refinement component, and is an important basis for multi-dimensional grid interpolation. After setting the multi-dimensional interpolation scale, perform operations within the determined continuous casting adjustment constraint range, which includes the water spray amount range, scale frequency range, and angle range of the water refinement component, and it limits the reasonable range of data changes. Within this range, with the preset multi-dimensional interpolation scale as a constraint, perform multi-dimensional grid interpolation. This means that the system will perform interpolation calculations on data in multiple dimensions, establishing connections between the water spray amount dimension, scale frequency dimension, and angle dimension of the water refinement component, etc. Through such calculations, grid interpolation data is generated.

[0036] Take the continuous casting historical data as a reference basis and conduct a comprehensive and detailed traversal analysis of the grid interpolation data. The continuous casting historical data contains key information such as multiple sets of water spray amounts, scale frequencies, angles of the water refinement component, injection speeds, shell uniformity, and shell thickness, and is a record of the actual continuous casting production process. During the traversal process, compare each data point in the continuous casting historical data with the corresponding position data in the grid interpolation data one by one. Through this point-by-point comparison method, identify the data points in the grid interpolation data that do not have corresponding actual records in the continuous casting historical data, and these data points are the so-called missing data points.

[0037] Guided by these missing data points, adjacent working conditions of the continuous casting historical data are expanded. This means referring to the working condition information near the missing data points, and on the basis of the continuous casting historical data, parameters such as water spray amount, scale cleaning frequency, and angle of the water refinement component are slightly adjusted, and then multiple groups of updated working condition data are obtained. For example, if the water spray amount in the historical working condition near a certain missing data point is X, then when expanding, a certain proportion can be fluctuated up and down around X to obtain a new water spray amount value, and so on to determine other parameters to form a new group of working condition data. Then, based on the adjacent working condition relationship between the continuous casting historical data and multiple groups of updated working condition data, the method of linearly calculating the intermediate value is used to predict the shell quality. For each group of updated working condition data, find the two closest working condition data points in the continuous casting historical data, and according to the shell uniformity and shell thickness corresponding to these two working condition data points, calculate the predicted values of the shell uniformity and shell thickness corresponding to the updated working condition data according to the linear relationship, so as to obtain multiple groups of updated shell qualities. Finally, multiple groups of updated working condition data and the corresponding multiple groups of updated shell qualities are stored in association. Each group of updated working condition data and the corresponding updated shell quality constitute a complete information unit, and these information units are multiple working condition prediction data, which together form the continuous casting prediction data. The continuous casting prediction data combined with the original continuous casting historical data constitutes the continuous casting coverage data, providing more comprehensive and rich data support for more accurate analysis and optimization of the continuous casting process in the future.

[0038] In a possible implementation manner, step S240 further includes: Step S241: Guided by the multiple missing data points, expand the adjacent working conditions of the continuous casting historical data to obtain multiple groups of updated working condition data.

[0039] Step S242: According to the adjacent working condition relationship between the continuous casting historical data and the multiple groups of updated working condition data, use linear calculation of the intermediate value to predict the shell quality to obtain multiple groups of updated shell qualities.

[0040] Step S243: Store the multiple groups of updated working condition data and multiple groups of updated shell qualities in association to obtain the multiple working condition prediction data as the continuous casting prediction data.

[0041] Specifically, taking the missing data points as clues, the continuous casting historical data is deeply analyzed. For each missing data point, the data point with the closest operating conditions is searched in the continuous casting historical data. For example, if the missing data point involves a water spray volume of X, a descaling frequency of Y, and an angle of the water refinement component of Z, search for data records in the continuous casting historical data with similar water spray volume, descaling frequency, and angle of the water refinement component. After finding the similar data points, based on these similar data points, slight adjustments are made to each parameter, such as appropriately increasing or decreasing the water spray volume, changing the descaling frequency, and slightly adjusting the angle of the water refinement component, etc., so as to generate multiple groups of updated operating condition data, making the operating condition data more rich and diverse.

[0042] Start predicting the shell quality. At this time, make full use of the adjacent operating condition relationship between the continuous casting historical data and multiple groups of updated operating condition data. For each group of updated operating condition data, find the two operating condition data in the continuous casting historical data that are most similar to it. The principle of linearly calculating the intermediate value is based on the assumption that: between adjacent operating conditions, the change in shell quality (shell uniformity and thickness) is linear. That is to say, assume that during the process from a water spray volume of 900 L / min to 1100 L / min, the change in shell quality is uniform. The specific calculation process is as follows: Assume that the shell uniformity at a water spray volume of 900 L / min is U 1 , and the shell thickness is T 1 ; the shell uniformity at a water spray volume of 1100 L / min is U 2 , and the shell thickness is T 2 . For the updated operating condition of an inserted water spray volume of 1000 L / min, its shell uniformity U can be calculated by the formula U = U 1 +(1000 - 900) / (1100 - 900)×(U 2 - U 1 ); its shell thickness T can be calculated by the formula T = T 1 +(1000 - 900) / (1100 - 900)×(T 2 - T 1 ). Through such a linear calculation method, the shell uniformity and thickness under the updated operating condition of a water spray volume of 1000 L / min can be obtained, that is, a group of updated shell quality is obtained. For other similar updated operating condition data points, the same method is also used for calculation, so as to obtain multiple groups of updated shell quality, providing more comprehensive data support for the subsequent analysis and optimization of the continuous casting process.

[0043] After obtaining multiple sets of updated working condition data and multiple sets of updated shell quality through the previous steps, these two types of data will be integrated and correlated. For each set of updated working condition data, the corresponding updated shell quality data will be accurately matched. For example, the updated working condition data with a specific water injection volume, a scaling frequency within a certain range, and a water refinement component angle at a certain angle will be corresponded to the updated shell quality data of the corresponding shell uniformity and shell thickness obtained by linearly calculating the intermediate value. Through this one-to-one correspondence, each set of updated working condition data and updated shell quality are combined into a complete information unit, and these information units are multiple working condition prediction data. According to certain storage rules, these working condition prediction data are stored in an orderly manner, and finally continuous casting prediction data are formed.

[0044] In a possible implementation manner, step S241 further includes: The continuous casting historical data includes multiple continuous casting working condition records and multiple shell quality records. The continuous casting working condition records are composed of a water injection volume parameter, a scaling frequency parameter, a water refinement component angle parameter, and an injection speed parameter. The shell quality records are composed of historical shell uniformity and historical shell thickness.

[0045] Specifically, the continuous casting historical data, as an important basis for the optimization analysis of the continuous casting process, includes multiple continuous casting working condition records and multiple shell quality records. Among them, the continuous casting working condition records detail various key parameters in the continuous casting process. The water injection volume parameter directly affects the cooling rate of the molten steel in the mold. An appropriate water injection volume can ensure uniform cooling of the molten steel and form a shell with good quality. The scaling frequency parameter is related to the cleanliness inside the mold. Regular scaling can prevent the accumulation of scale and affect the cooling effect. Different scaling frequencies have different degrees of influence on the stability of the continuous casting process and the product quality. The water refinement component angle parameter determines the spraying direction and dispersion degree of the cooling water. A reasonable angle can make the cooling water act on the molten steel more uniformly and promote uniform growth of the shell. The injection speed parameter controls the rate at which the molten steel enters the mold. It cooperates with other parameters to jointly affect the forming quality of the billet. The shell quality records are mainly composed of historical shell uniformity and historical shell thickness. The historical shell uniformity reflects the uniformity of the shell during growth. A uniform shell helps improve the quality and performance of the billet. The historical shell thickness reflects the thickness of the shell after the solidification of the molten steel. An appropriate shell thickness is the key factor to ensure the strength and stability of the billet. These continuous casting historical data comprehensively record various information in the past continuous casting process.

[0046] In a possible implementation manner, step S500 further includes: Step S510: According to the Euclidean distance between the shell quality index and the multiple shell quality records, extract H continuous casting working condition records with descending distance from the multiple continuous casting working condition records, where H≥20W, and H and W are positive integers.

[0047] Step S520: After combining and enumerating H continuous casting condition records to obtain a group of continuous casting condition records, use the H continuous casting condition records as topological nodes, and use the Euclidean distance of the group of continuous casting condition records as the topological length to construct a continuous casting condition topology.

[0048] Step S530: Use a preset condition topology distance to eliminate topological connections of the continuous casting condition topology, obtaining W isolated nodes.

[0049] Step S540: Use the W continuous casting condition records of the W isolated nodes as the W starting points of continuous casting optimization differences.

[0050] Specifically, clarify the shell quality index, which is an important basis for measuring the shell quality during continuous casting and mainly involves standard requirements for key parameters such as shell uniformity and shell thickness. At the same time, the continuous casting historical data contains multiple shell quality records, which detail the actually generated shell uniformity and shell thickness data under different continuous casting conditions. Using the Euclidean distance algorithm, calculate the distance between the shell quality index and each shell quality record. The Euclidean distance can accurately measure the difference degree between two data points in a multi-dimensional space. In this scenario, it is to measure the difference between the actual shell quality and the ideal shell quality index. Through this calculation, each shell quality record has a corresponding Euclidean distance value. Then, based on these Euclidean distance values, screen multiple continuous casting condition records. The continuous casting condition records include parameters such as water injection volume, descaling frequency, water refinement component angle, and injection speed, which jointly determine the actual conditions of continuous casting. From numerous continuous casting condition records, extract H continuous casting condition records in the order of descending Euclidean distance (i.e., distance in descending order). It should be emphasized here that there is a quantitative relationship between H and W, H≥20W, and both H and W are positive integers. This means that the number of extracted continuous casting condition records is at least 20 times that of W. The larger value of H ensures that the selected condition records have sufficient diversity and representativeness, covering a variety of different continuous casting condition situations, thus providing a rich data basis for accurately constructing the continuous casting condition topology and locating the starting points of continuous casting optimization differences later, and helping to analyze and optimize the continuous casting process more comprehensively and deeply.

[0051] Perform a combination enumeration operation on these H continuous casting condition records. Each continuous casting condition record is a unique condition combination composed of parameters such as water injection volume, descaling frequency, water refinement component angle, and injection speed. Through combination enumeration, combine these H continuous casting condition records in pairs, and finally obtain Group of continuous casting condition records combination. Based on these H continuous casting condition records, they are respectively used as topological nodes, and each node represents a specific continuous casting condition, occupying a unique position in the entire topological structure. Then, for the group of continuous casting condition records obtained by previous combination enumeration, calculate the Euclidean distance between each group of records. The Euclidean distance can quantify the degree of difference between different continuous casting conditions. In the continuous casting process scenario, it is a comprehensive measure of the differences in parameters such as water spray amount, scale removal frequency, angle of water refinement components, and injection speed. These calculated Euclidean distances are used as the topological lengths. Finally, based on the above-determined topological nodes and topological lengths, a continuous casting condition topology is constructed. In this topological structure, each topological node is connected to each other through the topological length, and the topological length reflects the size of the difference between different conditions. This continuous casting condition topology intuitively shows the associations and differences between different continuous casting conditions, providing a clear structural framework for subsequent topological connection removal using a preset condition topology distance, and then locating the starting point of continuous casting optimization differences, which helps to deeply analyze the continuous casting process and find the optimization direction.

[0052] Based on the constructed continuous casting condition topology, further process it to determine the starting point of continuous casting optimization differences. After the construction of the continuous casting condition topology is completed, this topology contains H topological nodes (representing H continuous casting condition records) and topological connections connecting these nodes (whose lengths are determined by the Euclidean distances of the corresponding group of continuous casting condition records). At this time, introduce a preset condition topology distance, which is preset according to the actual experience of the continuous casting process, historical data, and in-depth understanding of the continuous casting process. It is used to measure whether the difference between different continuous casting conditions is of practical significance. Compare the preset condition topology distance with the length of each topological connection (i.e., the Euclidean distance) in the continuous casting condition topology one by one. For those topological connection lengths greater than the preset condition topology distance, it is considered that the difference between the two continuous casting conditions connected by them is too large and does not have a close association in the current analysis. Therefore, these connections are removed from the topological structure. After this removal operation, the originally connected topological structure changes, and some nodes are no longer connected to other nodes, thus forming isolated nodes. Select W from these isolated nodes. The continuous casting condition records corresponding to these W isolated nodes have special significance in subsequent process optimization and will be used as the starting point of continuous casting optimization differences, providing a key starting point for subsequent exploration of the continuous casting process optimization direction and helping to achieve the balanced optimization of continuous casting quality, efficiency, and energy consumption.

[0053] The casting operation records corresponding to the W isolated nodes obtained through pre - processing are identified as the starting points of W casting optimization differences. Before this, through the clustering analysis of the casting historical data, a casting operation topology was constructed, and then a topology connection elimination operation was performed using a preset operation topology distance to screen out these W isolated nodes. Each isolated node represents a unique casting operation record, and these records contain key information such as the water injection volume parameter, the descaling frequency parameter, the angle parameter of the water refinement component, and the injection speed parameter, etc. Taking the casting operation records of these isolated nodes as the starting points of casting optimization differences is because they have relatively large difference characteristics compared with other operation records. This difference may mean that there are unique aspects in certain aspects of the casting process under these conditions. For example, under a specific combination of parameters such as water injection volume and descaling frequency, there will be a shell quality performance different from the conventional conditions. Starting from these difference points, subsequent targeted simulation and optimization exploration can be carried out in the casting thermal simulation container. Through in - depth research and adjustment of these starting points of casting optimization differences, it is expected to discover more optimal combinations of casting process parameters, thereby improving the casting quality, while balancing the casting efficiency and heat dissipation energy consumption, and providing strong support for the improvement of the casting process.

[0054] In a possible implementation manner, step S700 further includes: Step S710: Input the first starting point of casting optimization difference into the first casting thermal simulation container for unit casting production simulation, and then perform casting performance quantification to output the first simulation solution coefficient.

[0055] Step S720: Update the first starting point of casting optimization difference using a preset casting operation search scale. After outputting the first updated casting operation, perform casting performance quantification on the first casting thermal simulation container to output the second simulation solution coefficient.

[0056] Step S730: If the second simulation solution coefficient is better than the first simulation coefficient, update the casting operation search scale according to the deviation between the first simulation solution coefficient and the second simulation solution coefficient, and output the first updated search scale.

[0057] Step S740: And so on, perform casting operation search scale update and casting performance quantification evaluation according to the simulation solution coefficients obtained from adjacent optimization until the deviation between the obtained adjacent optimization simulation solution coefficients is less than a preset threshold, and output the first local iteration optimal solution.

[0058] Step S750: And so on, through the parallel local iteration optimization of the W casting thermal simulation containers, obtain W local iteration optimal solutions to form the multi - objective equilibrium solution set of casting.

[0059] Specifically, to ensure computational efficiency, independent computing resources, including CPU / GPU cores and memory, are allocated to each continuous casting thermal simulation container. Subsequently, the starting point of the first continuous casting optimization difference is input into the first continuous casting thermal simulation container. Unit continuous casting production simulation is carried out inside the container. After the simulation ends, the continuous casting performance is quantitatively evaluated. During the quantification process, a simulation solution evaluation weight is pre-constructed, covering energy consumption weight, shell uniformity deviation weight, shell thickness deviation weight, scale residue weight, water consumption weight, etc. Based on these weights, combined with the first continuous casting energy consumption, first simulation uniformity, first simulation thickness, first scale residue amount, and first water consumption output by the simulation, and then according to the shell quality index, the first uniformity deviation and the first thickness deviation are calculated. Finally, these data are fused to output the first simulation solution coefficient.

[0060] After the preliminary simulation of the starting point of the first continuous casting optimization difference in the first continuous casting thermal simulation container has been completed and the first simulation solution coefficient has been obtained, the starting point of the first continuous casting optimization difference is adjusted according to the pre-set search scale of the continuous casting working conditions. This search scale is set according to the characteristics of the continuous casting process, past experience, and the expectation of optimization accuracy. It stipulates the adjustment amplitude of each continuous casting working condition parameter (such as water injection volume, scale cleaning frequency, water refinement component angle, injection speed, etc.) each time. According to this search scale, the corresponding changes are made to each working condition parameter included in the starting point of the first continuous casting optimization difference, so as to obtain the first updated continuous casting working condition. For example, if the original water injection volume is X, according to the setting of the search scale, it may be adjusted to X±ΔX (ΔX is determined by the search scale), and similar adjustments are made to other parameters at the same time. Subsequently, the first updated continuous casting working condition is input into the first continuous casting thermal simulation container, and the unit continuous casting production simulation is carried out again. After the simulation ends, just like the process of calculating the first simulation solution coefficient, based on the pre-constructed simulation solution evaluation weight, combined with the data such as continuous casting energy consumption, simulation uniformity, simulation thickness, scale residue amount, and water consumption output by this simulation, and then according to the shell quality index, the corresponding uniformity deviation and thickness deviation are calculated. Finally, these data are fused and calculated to output the second simulation solution coefficient. This second simulation solution coefficient is used to compare with the first simulation solution coefficient to determine whether the adjustment of the continuous casting working condition this time is developing in a more optimal direction, thereby providing a basis for the subsequent update of the continuous casting working condition search scale and the optimization of the continuous casting process.

[0061] After completing the simulation of the first updated continuous casting working condition in the first continuous casting thermal simulation container and obtaining the second simulation solution coefficient, compare the first and second simulation solution coefficients. If the second simulation solution coefficient performs better, it means that the current adjustment direction of the continuous casting working condition is correct and is moving towards the goal of improving continuous casting performance, balancing continuous casting quality, efficiency, and heat dissipation energy consumption. At this time, the search scale of the continuous casting working condition will be updated based on the deviation between the first simulation solution coefficient and the second simulation solution coefficient. Convert this deviation into an adjustment amount for the search scale of the continuous casting working condition to obtain the first updated search scale. This updated search scale will be used to adjust the first updated continuous casting working condition again. For example, if the continuous casting working condition parameters such as the water spray amount and the descaling frequency have specific set values in the first updated continuous casting working condition, according to the first updated search scale, these parameters are adjusted accordingly, either increased or decreased, and then the second updated continuous casting working condition is output. After obtaining the second updated continuous casting working condition, input it into the first continuous casting thermal simulation container to perform the unit continuous casting production simulation again. After the simulation is completed, quantitative analysis of the simulation results is carried out based on the pre-constructed simulation solution evaluation weight values. These weight values include the energy consumption weight, the shell uniformity deviation weight, the shell thickness deviation weight, the scale residue weight, and the water consumption weight, etc. Combining the data such as the continuous casting energy consumption, the simulated uniformity, the simulated thickness, the scale residue amount, and the water consumption output by the simulation, calculate the corresponding uniformity deviation and thickness deviation based on the shell quality index, and calculate these data comprehensively to finally output the third simulation solution coefficient.

[0062] After obtaining the third simulation solution coefficient, enter a cyclic iteration process. In each iteration, compare the simulation solution coefficient obtained this time with the previous one, and update the search scale of the continuous casting working conditions based on the deviation between the two. For example, if the simulation solution coefficient this time shows an improvement in continuous casting performance, adjust the search scale accordingly according to the size of the deviation, making the subsequent adjustment of the continuous casting working conditions more targeted. If the deviation is positive and large, appropriately increase the search scale to speed up the search for a better working condition; if the deviation is small, reduce the search scale to explore the potential better working conditions in the vicinity more finely. After updating the search scale, adjust the current continuous casting working conditions with the new search scale, generate a new continuous casting working condition, and perform a unit continuous casting production simulation again in the first continuous casting thermal simulation container. After the simulation ends, quantitatively evaluate the simulation results through the simulation solution evaluation weight value to obtain a new simulation solution coefficient. This process is repeated continuously, that is, continuously compare the simulation solution coefficients obtained by adjacent optimizations, update the search scale of the continuous casting working conditions, and quantitatively evaluate the continuous casting performance. Continue this cycle until the deviation between the adjacent optimization simulation solution coefficients obtained is less than the preset threshold. The preset threshold is set according to the accuracy requirements and actual experience of the continuous casting process, and it represents the optimization degree that the system considers acceptable. When this standard is reached, determine that the current continuous casting working condition is the first local iteration optimal solution and output it. This optimal solution is a better working condition obtained by comprehensively considering multiple objectives such as continuous casting quality, efficiency, and heat dissipation energy consumption in the current local search space, laying a foundation for subsequent parallel optimization in multiple continuous casting thermal simulation containers to obtain a multi-objective balanced solution set for continuous casting.

[0063] After completing the local iterative optimization of the first continuous casting thermal simulation container and obtaining the first local iterative optimal solution, this process is extended to W continuous casting thermal simulation containers. There are W continuous casting thermal simulation containers in the system, and each container is allocated independent computing resources (CPU / GPU cores, memory) to ensure the efficiency of parallel computing. For each container, the local iterative optimization steps previously performed in the first container are repeated. The corresponding starting points of continuous casting optimization differences are input into the corresponding continuous casting thermal simulation containers for unit continuous casting production simulation. The simulation results are quantified through the simulation solution evaluation weights, and the simulation solution coefficients are output. Then, the continuous casting condition search scale is continuously updated according to the simulation solution coefficients obtained from adjacent optimizations, the continuous casting conditions are adjusted, simulated and quantified again, and so on until the deviation of the simulation solution coefficients obtained from adjacent optimizations is less than the preset threshold, and the local iterative optimal solution of each container is obtained. Due to the parallel computing of each container, these operations can be carried out simultaneously, greatly shortening the time cost of optimization. Finally, the W local iterative optimal solutions output by these W continuous casting thermal simulation containers together constitute the multi-objective equilibrium solution set for continuous casting. This solution set comprehensively considers multiple objectives such as continuous casting quality, efficiency, and heat dissipation energy consumption, covering various possible combinations of continuous casting conditions, providing a rich and comprehensive reference basis for subsequently screening out the solution with the lowest energy consumption from the solution set and inputting it into the continuous casting finite element model for global iterative optimization, and then determining the continuous casting adjustment control benchmark, which strongly promotes the optimization process of the continuous casting process.

[0064] In a possible implementation manner, step S710 further includes: Step S711: Pre-construct the simulation solution evaluation weights, where the simulation solution evaluation weights include energy consumption weight, shell uniformity deviation weight, shell thickness deviation weight, scale residue weight, and water consumption weight.

[0065] Step S712: Input the first continuous casting optimization difference starting point into the first continuous casting thermal simulation container for unit continuous casting production simulation, and output the first continuous casting energy consumption, the first simulated uniformity, the first simulated thickness, the first scale residue amount, and the first water consumption.

[0066] Step S713: Evaluate the deviation of the first simulated uniformity and the first simulated thickness according to the shell quality index, and output the first uniformity deviation and the first thickness deviation.

[0067] Step S714: Use the simulation solution evaluation weights to fuse the first continuous casting energy consumption, the first uniformity deviation, the first thickness deviation, the first scale residue amount, and the first water consumption, and output the first simulation solution coefficient.

[0068] Specifically, first, the evaluation weights for the simulation solutions are pre-constructed. Before starting the continuous casting thermal simulation, based on the actual data accumulated over a long period of continuous casting production, the specific standards of the production process, and the comprehensive goals of the enterprise for cost control, product quality, and resource utilization, a weight system for measuring the simulation results is constructed. The energy consumption weight in this system is determined based on the proportion of energy consumption in the total cost during continuous casting, the trend of energy market price fluctuations, and the enterprise's strategic plan for energy conservation and emission reduction. The weights for the shell uniformity deviation and the shell thickness deviation are mainly set around the core requirements of the slab quality. Since the shell uniformity directly affects the stability of the internal structure and the flatness of the surface of the slab, and the shell thickness affects the strength and subsequent processing performance of the slab, these two weights are accurately assigned according to the strictness of the enterprise's slab quality standards and the differentiated requirements of different industries for slab quality. The determination of the scale deposit residue weight refers to the accumulation rate of scale on the surface of the mold and related equipment during past production, as well as the impact on the cooling efficiency and equipment life, aiming to measure the comprehensive impact of the scale problem on the continuity of continuous casting production and the equipment maintenance cost. The water consumption weight is set in combination with the scarcity of local water resources, the enterprise's water-saving policy, and the sustainable development goal, emphasizing the importance of the rational use of water resources in continuous casting production. These weights together constitute the evaluation weights for the simulation solutions, providing a unified and scientific quantitative evaluation standard for the various data obtained through the continuous casting thermal simulation in the subsequent process.

[0069] Input the starting point of the first continuous casting optimization difference into the first continuous casting thermal simulation container for unit continuous casting production simulation. This simulation process will fully consider various physical phenomena and process parameters during continuous casting and finally output several key indicators, including the first continuous casting energy consumption, the first simulated uniformity, the first simulated thickness, the first scale deposit residue amount, and the first water consumption. These indicators intuitively reflect the performance under the current continuous casting conditions.

[0070] According to the pre-set shell quality indicators, the deviation evaluation of the first simulated uniformity and the first simulated thickness is carried out. The shell quality indicators stipulate the ideal state of the continuous casting shell in terms of uniformity and thickness. By comparing the differences between the first simulated uniformity and the first simulated thickness and the ideal indicators, the first uniformity deviation and the first thickness deviation are calculated. These two deviation values quantify the gap between the current shell quality and the ideal state.

[0071] Using the constructed simulation solution evaluation weights, perform a comprehensive calculation on multiple results of the continuous casting thermal simulation to obtain the first simulation solution coefficient. First, obtain several key data: the first continuous casting energy consumption, the first uniformity deviation, the first thickness deviation, the first scale residue amount, and the first water consumption. These data respectively reflect the operation of the continuous casting process under specific working conditions from different aspects. Among them, the first continuous casting energy consumption reflects the energy consumption level during continuous casting, the first uniformity deviation and the first thickness deviation show the gap between the shell quality and the ideal state, the first scale residue amount reflects the potential impact of equipment cleanliness on the process, and the first water consumption represents the utilization status of water resources. Then, call the pre-constructed simulation solution evaluation weights, which include the energy consumption weight, the shell uniformity deviation weight, the shell thickness deviation weight, the scale residue weight, and the water consumption weight. Multiply these weights by the corresponding first continuous casting energy consumption, the first uniformity deviation, the first thickness deviation, the first scale residue amount, and the first water consumption respectively, to give the corresponding proportion of each data in the comprehensive evaluation. For example, if the energy consumption weight is 0.3 and the first continuous casting energy consumption is 500 (units), then the contribution value of the energy consumption item in the comprehensive calculation is 500×0.3. Finally, add the above product results. After this series of fusion calculations, a value that comprehensively reflects the overall performance of the continuous casting process under the current working conditions is obtained, and this value is the first simulation solution coefficient.

[0072] In a possible implementation manner, step S400 further includes: Step S410: Establish the initial finite element model according to the component structure information, where the initial finite element model includes a cooling water injection dynamics module, a self-cleaning mechanics module, a droplet sputtering optimization module, and a molten steel solidification thermodynamics module.

[0073] Step S420: Decompose the continuous casting coverage data according to the module composition of the initial finite element model to obtain a cooling water injection data group, a self-cleaning mechanics data group, a droplet sputtering data group, and a molten steel solidification data group.

[0074] Step S430: After mapping and loading the cooling water injection data group, the self-cleaning mechanics data group, the droplet sputtering data group, and the molten steel solidification data group to the cooling water injection dynamics module, the self-cleaning mechanics module, the droplet sputtering optimization module, and the molten steel solidification thermodynamics module for single-module calibration, perform a multi-physics field coupling co-verification on the initial finite element model, and output the continuous casting finite element model.

[0075] Specifically, the component structure information covers the detailed characteristics of each component of the continuous casting equipment, such as the geometric shape, size, and material properties of each component. This information provides the necessary parameters and basis for the construction of the model. The initial finite element model consists of four key modules. The cooling water injection dynamics module mainly focuses on simulating the cooling water injection process at the water spray holes. Through the dynamic analysis of the water flow, it verifies the uniformity of the water flow coverage, with a requirement that its standard deviation ≤ 3%. This is crucial for ensuring that the molten steel can dissipate heat evenly during the cooling process and thus form a shell with good quality. The self-cleaning mechanics module focuses on simulating the expansion and scale scraping of the water delivery ring and the impact process of the scale-breaking components, with its impact frequency set at 10 - 30 times per minute. Through such simulation, this module aims to ensure that the scale removal rate ≥ 90% to maintain the cleanliness inside the continuous casting equipment and reduce the adverse effects of scale on the cooling effect and the quality of the cast billet. The droplet sputtering optimization module mainly calibrates the influence of the elastic annular deformation angle on the sputtering uniformity. Through the simulation and analysis of the droplet sputtering process, it requires that the temperature gradient ≤ 50°C / mm to ensure that the droplets can be evenly distributed during the sputtering process, thereby better realizing the cooling and protection effects on the molten steel. The molten steel solidification thermodynamics module mainly adjusts the molten steel injection speed (in the range of 0.5 - 2.5 m / min). Through the simulation and analysis of the heat transfer and phase change during the molten steel solidification process, it ensures that the shell thickness error ≤ 2 mm, thereby guaranteeing the quality and dimensional accuracy of the cast billet. By integrating these modules together, the initial finite element model can comprehensively and meticulously simulate various phenomena during the continuous casting process from multiple physical levels, providing a powerful tool and platform for the subsequent in-depth analysis and optimization of the continuous casting process.

[0076] According to the module composition of the initial finite element model, the continuous casting coverage data is decomposed. The continuous casting coverage data is a comprehensive data set containing various physical phenomena and process parameters during the continuous casting process. Through the decomposition operation, it is split into four data groups, namely the cooling water injection data group, which contains parameters related to the cooling water injection, such as injection speed, pressure, etc.; the self-cleaning mechanics data group, which covers the mechanical data during the self-cleaning process, such as friction force, impact force, etc.; the droplet sputtering data group, which records information related to droplet sputtering, such as sputtering angle, speed, etc.; and the molten steel solidification data group, which contains the thermal data during the molten steel solidification process, such as temperature change, solidification time, etc.

[0077] The four decomposed data groups are respectively mapped and loaded into the corresponding modules of the initial finite element model. The cooling water injection data group is loaded into the cooling water injection dynamics module, the self-cleaning mechanics data group is loaded into the self-cleaning mechanics module, the droplet sputtering data group is loaded into the droplet sputtering optimization module, and the molten steel solidification data group is loaded into the molten steel solidification thermodynamics module. After completing the data loading, each individual module is calibrated to ensure that the simulation results of the module are consistent with the actual physical phenomena. For example, the parameters in the module are adjusted to make the simulated cooling water injection effect consistent with the actual observed situation. After completing the calibration of the individual modules, a co-verification of multi-physical field coupling is carried out on the initial finite element model. During the continuous casting process, different physical phenomena interact with each other. For example, the change in the water injection volume will affect the refinement angle and uniformity of the water, and further affect the cooling effect and solidification process of the molten steel. Therefore, it is necessary to comprehensively consider the interactions between various modules and conduct co-verification. By continuously adjusting and optimizing the model parameters, the model can accurately simulate the multi-physical field coupling phenomenon during the continuous casting process. Finally, after the above series of operations, a continuous casting finite element model is output.

[0078] In a possible implementation manner, step S200 further includes: Step S250: During the continuous casting production process where the control unit of the mold assembly conducts continuous casting according to the continuous casting adjustment control benchmark, real-time monitoring and acquisition of the shell uniformity and real-time shell thickness are carried out.

[0079] Step S260: Extract the shell uniformity requirement and the shell thickness requirement from the shell quality indicators.

[0080] Step S270: Perform PID closed-loop feedback control on the continuous casting adjustment control benchmark according to the first dynamic deviation between the real-time shell uniformity and the shell uniformity requirement, and the second dynamic deviation between the real-time shell thickness and the shell requirement thickness.

[0081] Specifically, when the control unit of the mold assembly conducts continuous casting according to the continuous casting adjustment control benchmark, in order to ensure that the production process always remains in the best state, key indicators are monitored and acquired in real time. The real-time shell uniformity and real-time shell thickness are closely monitored, and through various high-precision sensors installed on the mold assembly, relevant data are continuously collected. These real-time data can accurately reflect the actual state of the shell during the current continuous casting process.

[0082] The shell uniformity requirement and the shell thickness requirement are extracted from the pre-set shell quality indicators. The shell quality indicators are ideal shell state parameters determined based on various factors such as the quality standards of continuous casting products and production process requirements. The shell uniformity requirement and the shell thickness requirement are key parts of them, representing the shell quality level that continuous casting production expects to achieve.

[0083] Compare and analyze the embryo shell data collected in real time with the ideal requirements, calculate the first dynamic deviation between the real-time embryo shell uniformity and the required embryo shell uniformity, and the second dynamic deviation between the real-time embryo shell thickness and the required embryo shell thickness. Based on these two dynamic deviations, adopt a PID closed-loop feedback control mechanism to adjust the continuous casting adjustment control benchmark. PID control is a commonly used feedback control algorithm that adjusts the control quantity according to three parameters: the proportional (P), integral (I), and derivative (D) of the deviation. In this process, according to the magnitude and change trend of the dynamic deviation, automatically calculate and adjust relevant parameters in the continuous casting process, such as the water spray volume, injection speed, etc., so that the continuous casting production can continuously approach the ideal embryo shell quality state, thereby continuously ensuring the stability of the continuous casting quality, while optimizing the balance of continuous casting efficiency and heat dissipation energy consumption.

[0084] Embodiment 2, based on the same inventive concept as the continuous casting adjustment method simulated by a mold assembly in the foregoing embodiment, as Figure 2 shown, the present application provides a continuous casting adjustment system simulated by a mold assembly. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes: A continuous casting historical data acquisition module 10, configured to perform network data acquisition according to the equipment ID of the mold assembly and the molten steel component information to obtain continuous casting historical data.

[0085] A working condition expansion module 20, configured to perform working condition expansion on the continuous casting historical data by using linear interpolation to obtain continuous casting coverage data.

[0086] A model establishment module 30, configured to locally call component structure information according to the equipment ID to establish an initial finite element model.

[0087] A continuous casting finite element model acquisition module 40, configured to calibrate the boundary conditions of the initial finite element model by using the continuous casting coverage data to obtain a continuous casting finite element model.

[0088] A clustering analysis module 50, configured to perform clustering analysis on the continuous casting historical data according to the embryo shell quality index to locate W starting points of continuous casting optimization differences.

[0089] A model replication module 60, configured to replicate the continuous casting finite element model to W continuous casting thermal simulation containers.

[0090] A local iterative optimization module 70, configured to start parallel local iterative optimization after inputting the W starting points of continuous casting optimization differences into the W continuous casting thermal simulation containers to obtain a continuous casting multi-objective equilibrium solution set.

[0091] The global iterative optimization module 80 is used to screen the solution with the lowest energy consumption from the continuous casting multi-objective equilibrium solution set as the reference solution, and input the reference solution into the continuous casting finite element model for global iterative optimization to obtain the continuous casting adjustment control reference.

[0092] Furthermore, the system is also used to implement the following functions: Define the continuous casting adjustment constraints according to the component structure information, where the continuous casting adjustment constraints include the water injection amount interval, the descaling frequency interval, and the water refinement component angle interval; preset the multi-dimensional interpolation scale, and perform multi-dimensional grid interpolation within the continuous casting adjustment constraint range with the multi-dimensional interpolation scale as the constraint to generate grid interpolation data; traverse the grid interpolation data with the continuous casting historical data to locate multiple missing data points; based on the multiple missing data points, expand and cover the continuous casting historical data to obtain continuous casting prediction data, where the continuous casting prediction data includes multiple working condition prediction data, and the continuous casting prediction data and the continuous casting historical data constitute the continuous casting coverage data.

[0093] Furthermore, the system is also used to implement the following functions: Guided by the multiple missing data points, expand the adjacent working conditions of the continuous casting historical data to obtain multiple groups of updated working condition data; according to the adjacent working condition relationship between the continuous casting historical data and the multiple groups of updated working condition data, use linear calculation of the intermediate value to predict the shell quality to obtain multiple groups of updated shell qualities; associate and store the multiple groups of updated working condition data and multiple groups of updated shell qualities to obtain the multiple working condition prediction data as the continuous casting prediction data.

[0094] Furthermore, the system is also used to implement the following functions: The continuous casting historical data includes multiple continuous casting working condition records and multiple shell quality records. The continuous casting working condition records are composed of water injection amount parameters, descaling frequency parameters, water refinement component angle parameters, and injection speed parameters. The shell quality records are composed of historical shell uniformity and historical shell thickness.

[0095] Furthermore, the system is also used to implement the following functions: According to the Euclidean distance between the shell quality index and the multiple shell quality records, extract H continuous casting working condition records with descending distance from the multiple continuous casting working condition records, where H≥20W, and H and W are positive integers; after combining and enumerating the H continuous casting working condition records to obtain groups of continuous casting working condition records, use the H continuous casting working condition records as topological nodes, and use the Taking the Euclidean distance of the continuous casting condition records of the group as the topological length, a continuous casting condition topology is constructed; the topological connection lines of the continuous casting condition topology are removed using a preset condition topology distance to obtain W isolated nodes; the W continuous casting condition records of the W isolated nodes are used as the W starting points of continuous casting optimization differences.

[0096] Furthermore, the system is also used to implement the following functions: Input the first starting point of continuous casting optimization differences into the first continuous casting thermal simulation container to conduct unit continuous casting production simulation and then quantify the continuous casting performance, and output the first simulation solution coefficient; update the first starting point of continuous casting optimization differences using a preset continuous casting condition search scale, and after outputting the first updated continuous casting condition, quantify the continuous casting performance of the first continuous casting thermal simulation container and output the second simulation solution coefficient; if the second simulation solution coefficient is better than the first simulation coefficient, update the continuous casting condition search scale according to the deviation between the first simulation solution coefficient and the second simulation solution coefficient, and output the first updated search scale; and so on, update the continuous casting condition search scale and conduct quantitative evaluation of the continuous casting performance according to the simulation solution coefficients obtained from adjacent optimizations until the deviation between the obtained adjacent optimization simulation solution coefficients is less than a preset threshold, and output the first locally iterated optimal solution; and so on, through the parallel local iteration optimization of the W continuous casting thermal simulation containers, obtain W locally iterated optimal solutions to form the continuous casting multi-objective equilibrium solution set.

[0097] Furthermore, the system is also used to implement the following functions: Pre-construct a simulation solution evaluation weight, where the simulation solution evaluation weight includes an energy consumption weight, a shell uniformity deviation weight, a shell thickness deviation weight, a scale residue weight, and a water consumption weight; input the first starting point of continuous casting optimization differences into the first continuous casting thermal simulation container to conduct unit continuous casting production simulation, and output the first continuous casting energy consumption, the first simulated uniformity, the first simulated thickness, the first scale residue amount, and the first water consumption; conduct deviation evaluation on the first simulated uniformity and the first simulated thickness according to the shell quality index, and output the first uniformity deviation and the first thickness deviation; use the simulation solution evaluation weight to fuse the first continuous casting energy consumption, the first uniformity deviation, the first thickness deviation, the first scale residue amount, and the first water consumption, and output the first simulation solution coefficient.

[0098] Furthermore, the system is also used to implement the following functions: An initial finite element model is established according to the component structure information, where the initial finite element model includes a cooling water injection dynamics module, a self-cleaning mechanics module, a droplet sputtering optimization module, and a molten steel solidification thermodynamics module; the continuous casting coverage data is decomposed according to the module composition of the initial finite element model to obtain a cooling water injection data set, a self-cleaning mechanics data set, a droplet sputtering data set, and a molten steel solidification data set; after mapping and loading the cooling water injection data set, the self-cleaning mechanics data set, the droplet sputtering data set, and the molten steel solidification data set to the cooling water injection dynamics module, the self-cleaning mechanics module, the droplet sputtering optimization module, and the molten steel solidification thermodynamics module for single-module calibration, a co-verification of multi-physical field coupling is performed on the initial finite element model, and the continuous casting finite element model is output.

[0099] Furthermore, the system is also used to implement the following functions: During the continuous casting production process in which the control unit of the mold assembly conducts continuous casting according to the continuous casting adjustment control benchmark, real-time monitoring and acquisition of the shell uniformity and real-time shell thickness are performed; the shell uniformity requirement and the shell thickness requirement are extracted from the shell quality indicators; according to the first dynamic deviation between the real-time shell uniformity and the shell uniformity requirement, and the second dynamic deviation between the real-time shell thickness and the shell requirement thickness, a PID closed-loop feedback control of the continuous casting adjustment control benchmark is performed.

[0100] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification is given. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

[0101] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0102] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A continuous casting adjustment method for crystallizer assembly simulation, characterized in that: The method comprises: Network data collection is performed based on the equipment ID of the mold assembly and the steel liquid composition information to obtain continuous casting historical data; Using linear interpolation to expand the working conditions of the continuous casting historical data to obtain continuous casting coverage data; Locally call component structure information based on device ID to establish an initial finite element model; Using the continuous casting coverage data to calibrate the boundary conditions of the initial finite element model to obtain a continuous casting finite element model; Performing cluster analysis on the continuous casting history data according to the embryo shell quality index to locate W continuous casting optimization difference starting points; The continuous casting finite element model is copied to W continuous casting thermal simulation containers; After the W continuous casting optimization difference starting points are input into the W continuous casting thermal simulation containers, parallel local iterative optimization is started to obtain a continuous casting multi-objective equilibrium solution set; The solution with the lowest energy consumption is selected from the continuous casting multi-objective equilibrium solution set as a benchmark solution, and the benchmark solution is input into the continuous casting finite element model for global iterative optimization to obtain a continuous casting adjustment control benchmark.

2. A continuous casting adjustment method for crystallizer assembly simulation according to claim 1, characterized in that: The continuous casting historical data is expanded using linear interpolation to obtain continuous casting coverage data. The method includes: Defining continuous casting adjustment constraints according to the component structure information, wherein the continuous casting adjustment constraints include a water spray volume interval, a scale wiping frequency interval, and a water refinement component angle interval; Preset a multidimensional interpolation scale, and perform multidimensional grid interpolation within the continuous casting adjustment constraint range with the multidimensional interpolation scale as a constraint to generate gridded interpolation data; Using the continuous casting historical data to traverse the gridded interpolation data, a plurality of missing data points are located; According to the multiple missing data points, the continuous casting historical data is covered and expanded to obtain continuous casting prediction data, wherein the continuous casting prediction data includes multiple working condition prediction data, and the continuous casting prediction data and the continuous casting historical data constitute the continuous casting coverage data.

3. A continuous casting adjustment method for crystallizer assembly simulation as claimed in claim 2, characterized in that: According to the multiple missing data points, the continuous casting historical data is covered and expanded to obtain continuous casting prediction data, and the method includes: Using the multiple missing data points as a guide, the continuous casting historical data is expanded with adjacent working conditions to obtain multiple groups of updated working condition data; According to the adjacent working condition relationship between the continuous casting historical data and the multiple groups of updated working condition data, the embryo shell quality is predicted by using the linear calculation intermediate value to obtain multiple groups of updated embryo shell qualities; The plurality of groups of updated working condition data and the plurality of groups of updated embryo shell qualities are associated and stored to obtain the plurality of working condition prediction data as the continuous casting prediction data.

4. A continuous casting adjustment method for crystallizer assembly simulation as claimed in claim 3, characterized in that: The continuous casting historical data includes multiple continuous casting condition records and multiple embryo shell quality records. The continuous casting condition records are composed of water spray volume parameters, scale scraping frequency parameters, water refinement component angle parameters, and injection speed parameters. The embryo shell quality records are composed of historical embryo shell uniformity and historical embryo shell thickness.

5. A continuous casting adjustment method for crystallizer assembly simulation as claimed in claim 4, characterized in that: Cluster analysis is performed on the continuous casting history data according to the embryo shell quality index to locate W continuous casting optimization difference starting points, and the method includes: Extracting H continuous casting condition records in descending order of distance from the multiple continuous casting condition records according to the Euclidean distance between the embryo shell quality index and the multiple embryo shell quality records, wherein H≥20W, H and W are positive integers; By combining and enumerating H continuous casting condition records, we can get After the continuous casting condition records are assembled, the H continuous casting condition records are used as topological nodes. The Euclidean distance of the continuous casting condition records is used as the topological length to construct the continuous casting condition topology; Using a preset working condition topological distance to remove topological connections of the continuous casting working condition topology, and obtaining W isolated nodes; The W continuous casting operating condition records of the W isolated nodes are used as the W continuous casting optimization difference starting points.

6. A method for adjusting continuous casting of a mold assembly simulation as claimed in claim 5, characterized in that: After the W continuous casting optimization difference starting points are input into the W continuous casting thermal simulation containers, parallel local iterative optimization is started to obtain a continuous casting multi-objective equilibrium solution set, and the method includes: Inputting the first continuous casting optimization difference starting point into the first continuous casting thermal simulation container to perform unit continuous casting production simulation, then quantifying the continuous casting performance, and outputting the first simulation solution coefficient; The first continuous casting optimization difference starting point is updated by using a preset continuous casting condition search scale, and after outputting a first updated continuous casting condition, the continuous casting performance of the first continuous casting thermal simulation container is quantified, and a second simulation solution coefficient is output; If the second simulation solution coefficient is better than the first simulation solution coefficient, updating the continuous casting condition search scale according to the deviation between the first simulation solution coefficient and the second simulation solution coefficient, and outputting a first updated search scale; In this way, the continuous casting condition search scale is updated and the continuous casting performance is quantitatively evaluated according to the simulation solution coefficients obtained by the adjacent optimization search, until the deviation of the obtained adjacent optimization simulation solution coefficients is less than the preset threshold, and the first local iterative optimal solution is output; By analogy, through the parallel local iterative optimization of the W continuous casting thermal simulation containers, W local iterative optimal solutions are obtained to constitute the continuous casting multi-objective equilibrium solution set.

7. A continuous casting adjustment method for crystallizer assembly simulation according to claim 6, characterized in that: The first continuous casting optimization difference starting point is input into the first continuous casting thermal simulation container to perform unit continuous casting production simulation, and then the continuous casting performance is quantified, and the first simulation solution coefficient is output. The method includes: Pre-constructing simulation solution evaluation weights, wherein the simulation solution evaluation weights include energy consumption weight, embryo shell uniformity deviation weight, embryo shell thickness deviation weight, scale residue weight, and water consumption weight; Inputting the first continuous casting optimization difference starting point into the first continuous casting thermal simulation container to perform unit continuous casting production simulation, and outputting the first continuous casting energy consumption, the first simulated uniformity, the first simulated thickness, the first scale residue and the first water consumption; performing deviation evaluation on the first simulated uniformity and the first simulated thickness according to the embryo shell quality index, and outputting a first uniformity deviation and a first thickness deviation; The simulation solution evaluation weight is used to fuse the first continuous casting energy consumption, the first uniformity deviation, the first thickness deviation, the first scale residue and the first water consumption, and the first simulation solution coefficient is output.

8. A method for adjusting continuous casting of a mold assembly simulation according to claim 1, characterized in that: The continuous casting coverage data is used to calibrate the boundary conditions of the initial finite element model to obtain a continuous casting finite element model. The method includes: Establishing the initial finite element model according to the component structure information, wherein the initial finite element model includes a cooling water injection dynamics module, a self-cleaning mechanics module, a droplet sputtering optimization module and a molten steel solidification thermodynamics module; Decomposing the continuous casting coverage data according to the module structure of the initial finite element model to obtain a cooling water injection data group, a self-cleaning mechanics data group, a droplet splashing data group and a molten steel solidification data group; After the cooling water injection data group, self-cleaning mechanics data group, droplet sputtering data group and molten steel solidification data group are mapped and loaded into the cooling water injection dynamics module, self-cleaning mechanics module, droplet sputtering optimization module and molten steel solidification thermodynamics module for single module calibration, the initial finite element model is collaboratively verified by multi-physical field coupling and the continuous casting finite element model is output.

9. A continuous casting adjustment method for crystallizer assembly simulation as claimed in claim 1, characterized in that: The continuous casting historical data is expanded using linear interpolation to obtain continuous casting coverage data. The method further includes: During the continuous casting production process, the control unit of the crystallizer assembly monitors and collects the real-time embryo shell uniformity and the real-time embryo shell thickness according to the continuous casting adjustment control benchmark; Extracting the embryo shell uniformity requirement and the embryo shell thickness requirement from the embryo shell quality index; According to the first dynamic deviation between the real-time embryo shell uniformity and the embryo shell uniformity requirement and the second dynamic deviation between the real-time embryo shell thickness and the embryo shell required thickness, the PID closed-loop feedback control of the continuous casting adjustment control benchmark is performed.

10. A continuous casting adjustment system for crystallizer assembly simulation, characterized in that: The system is used to implement a continuous casting adjustment method for crystallizer assembly simulation according to any one of claims 1 to 9, and the system comprises: The continuous casting historical data acquisition module is used to collect network data according to the equipment ID of the crystallizer assembly and the steel liquid component information to obtain the continuous casting historical data; A working condition expansion module, used for expanding the working condition of the continuous casting historical data by linear interpolation to obtain continuous casting coverage data; The model building module is used to locally call the component structure information according to the equipment ID and build the initial finite element model; A continuous casting finite element model acquisition module, used to calibrate the boundary conditions of the initial finite element model using the continuous casting coverage data to obtain a continuous casting finite element model; A cluster analysis module, used to perform cluster analysis on the continuous casting history data according to the embryo shell quality index, and locate W continuous casting optimization difference starting points; A model replication module, used for replicating the continuous casting finite element model to W continuous casting thermal simulation containers; A local iterative optimization module is used to input the W continuous casting optimization difference starting points into the W continuous casting thermal simulation containers, start parallel local iterative optimization, and obtain a continuous casting multi-objective equilibrium solution set; The global iterative optimization module is used to select the solution with the lowest energy consumption from the continuous casting multi-objective equilibrium solution set as a benchmark solution, and input the benchmark solution into the continuous casting finite element model for global iterative optimization to obtain a continuous casting adjustment control benchmark.

Images