Casting forming process for low-oxygen copper

Abstract

The invention relates to the technical field of low-oxygen copper production, in particular to a casting forming process for low-oxygen copper, which comprises the following steps: S1, setting the important performance of a copper casting blank, analyzing the influence degree of adjustable parameters, and setting an influence degree threshold value; s2, inputting the real-time fixed parameter and the required performance value into the prediction model to obtain an adjustable parameter prediction value; s3, preparing a copper casting blank; s4, obtaining abnormal importance performance; s5, combining the selectable sets corresponding to the abnormal importance performance to form a union set; correcting the calling sequence of the adjustable parameters to obtain a priority calling set; s6, carrying out serialization adjustment on the priority calling set to obtain a priority adjustment sequence; s7, calling at least one adjustable parameter in the priority adjustment sequence for adjustment; by constructing the prediction model, the parameter values meeting the specific performance requirements of the low-oxygen copper can be predicted in advance, the certainty and efficiency of the production process are remarkably improved, and meanwhile, the problem of performance abnormity can be quickly positioned and solved.

Description

Technical Field

[0001] The invention relates to the technical field of low-oxygen copper production, in particular to a casting molding process for low-oxygen copper. Background Art

[0002] Low-oxygen copper is a copper material with extremely low oxygen content, usually no more than 0.003%. It has excellent conductivity, good mechanical properties and high thermal stability. These characteristics make low-oxygen copper widely used in power transmission, electronic component manufacturing and communication equipment.

[0003] The SCR continuous casting process is an advanced metal forming technology that can continuously cast molten copper into copper billets with good continuity and high production efficiency.

[0004] In the long-term practice of using the SCR method for continuous casting to prepare low-oxygen copper, the traditional process has exposed a series of problems that seriously restrict the development of the industry; in the processing of adjustable parameters, the traditional method has been in a dilemma and can only rely on extremely limited past experience to make trial adjustments again and again in actual production; this method not only cannot predict in advance the parameter values ​​that meet the specific performance requirements of low-oxygen copper, but also makes the entire production process full of uncertainty; when the low-oxygen copper ingot produced has important performance abnormalities, the shortcomings of the traditional process are exposed; on the one hand, it is difficult to quickly and accurately find the core factors that cause performance abnormalities; there are many links and factors involved in the production process, and the traditional process lacks an effective troubleshooting mechanism, which makes technicians feel like looking for a needle in a haystack when facing problems, and they are at a loss; on the other hand, even if some possible problem points are found, there is no set of scientific and reasonable methods to adjust the relevant parameters in a targeted manner; usually only some simple and conventional measures can be taken, and these measures often cannot touch the essence of the problem and cannot fundamentally solve the performance abnormality problem.

[0005] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a casting molding process for low-oxygen copper. By constructing a prediction model, the parameter values ​​that meet the specific performance requirements of low-oxygen copper can be predicted in advance, which significantly improves the certainty and efficiency of the production process. At the same time, by prioritizing the call of sets and serialization adjustments, performance abnormalities can be quickly located and resolved, fundamentally optimizing the low-oxygen copper casting molding process and improving product quality and production stability.

[0007] The casting molding process for low-oxygen copper of the present invention comprises: S1 Set the important properties of the copper casting blank, analyze the influence degree of adjustable parameters on the important properties, set the influence degree threshold, and obtain multiple optional sets; S2 Input the real-time fixed parameters and the required property values into the pre-constructed prediction model to obtain the predicted values of the adjustable parameters; S3 Produce the copper casting blank according to the real-time fixed parameters and the predicted values of the adjustable parameters; S4 Detect the important properties of the copper casting blank to obtain the property values, compare them with the required property values, and obtain the abnormal important properties; S5 Merge the optional sets corresponding to the abnormal important properties to form a union; correct the call order of the adjustable parameters according to the occurrence times, influence degree, and deviation degree of the abnormal important properties of the adjustable parameters in the union to obtain the preferred call set; S6 Use the preset external conditions to serially adjust the preferred call set to obtain the preferred adjustment sequence; S7 Call at least one adjustable parameter in the preferred adjustment sequence for adjustment.

[0008] Through the above scheme, by constructing a prediction model and scientifically analyzing the influence degree of adjustable parameters on important properties, it is possible to predict in advance the numerical values of adjustable parameters that meet the specific property requirements of low-oxygen copper, significantly improving the certainty and efficiency of the production process and avoiding the low-efficiency problems of relying on experience and repeated trial and error in traditional processes; by obtaining the optional sets corresponding to abnormal important properties and correcting them in combination with the occurrence times, influence degree, and deviation degree of adjustable parameters, it is possible to quickly locate the core factors causing performance abnormalities and adjust relevant parameters targeted to fundamentally solve the problems; in addition, by serially adjusting the preferred call set with preset external conditions, the adjustment order and strategy of adjustable parameters are further optimized, ensuring the scientificity and effectiveness of the adjustment. This scheme not only improves the quality and performance stability of low-oxygen copper casting blanks, but also greatly improves production efficiency, reduces production costs, and provides reliable technical support for the large-scale and high-quality production of low-oxygen copper.

[0009] As a preferred scheme of the present invention, the important properties of the copper casting blank in S1 include: conductivity, oxygen content, tensile strength, elongation, hardness, and microstructure; Conductivity is a key indicator to measure the current conduction ability of copper materials. For fields such as power transmission and electronic component manufacturing, high conductivity means lower resistance loss and higher efficiency. Therefore, it is crucial to ensure that the copper casting blank has excellent conductive performance; Controlling the oxygen content helps reduce oxide inclusions, improve the purity and conductivity of the material, and at the same time avoid the decline in mechanical properties caused by oxidation; Tensile strength, elongation, and hardness reflect the response characteristics of the material under different stress conditions; tensile strength determines the maximum tensile force that the material can withstand; elongation indicates the deformation ability of the material before breaking; hardness affects the wear resistance and processing performance of the material; good mechanical properties ensure the reliability and durability of copper ingots in various application scenarios; Microstructure directly affects the internal organization of the material, such as grain size, distribution and the presence of defects; it not only affects the mechanical properties and conductivity of the material, but also affects the uniformity and consistency of the ingot, thus affecting the quality of the final product; Adjustable parameters include: cooling water flow and temperature on the crystallization wheel side, cooling water flow and temperature on the steel strip side, casting temperature, casting speed and casting angle; Among them, the cooling water flow and temperature on the crystallization wheel side and the cooling water flow and temperature on the steel strip side can affect the above-mentioned important properties: the appropriate cooling rate can promote the formation of fine and uniform grains, which is beneficial to improving the conductivity; too fast or too slow cooling rate may affect the removal of oxygen and indirectly affect the oxygen content; rapid cooling can inhibit the formation of coarse grains, which is helpful to improve mechanical properties such as tensile strength, elongation, and hardness; cooling conditions directly affect the crystal growth mode and size, thereby changing the microstructure; Casting temperature can also affect the above important properties: casting temperature directly affects the solidification process of copper liquid, thus affecting the microstructure and conductivity of the final product; higher casting temperature may cause more oxygen to dissolve in molten copper, increasing the oxygen content in the finished product; casting temperature that is too high or too low will affect the phase change path during solidification, thereby affecting mechanical properties; The casting speed can also affect the above important properties: a faster casting speed may lead to uneven internal structure of the casting, affecting the conductivity; the casting speed affects the cooling rate, thereby indirectly affecting the oxygen content; the casting speed also affects the uniformity and density of the internal structure of the casting, thereby affecting the mechanical properties and possible internal defects; The casting angle can also affect the above-mentioned important properties: the casting angle affects the way the molten metal enters the five-wheel casting machine. An improper angle may cause poor filling or bubbles, indirectly affecting the conductivity; the casting angle affects the flow of molten metal and gas discharge, thereby affecting the oxygen content; the casting angle affects the molding quality and thermal stress distribution of the ingot. An incorrect angle may cause stress concentration points or cracks inside the ingot, weakening the mechanical properties; a reasonable casting angle can ensure that the molten metal flows smoothly into the mold, forming a dense and uniform microstructure, reducing internal defects and improving overall performance.

[0010] As a preferred solution of the present invention, the method for obtaining the influence in S1 includes the following steps: S11 Obtain the set values of various adjustable parameters of copper cast billets in different production batches and the important performance results of the corresponding copper cast billets to obtain historical production data; Specifically, obtain historical production data from platforms such as the enterprise production management system (MES) and the automation control system (DCS), extract the important performance test results of copper cast billets in each production batch from the quality inspection system, and ensure that the timestamps of all data are consistent; To ensure the quality of the collected data, data cleaning can be performed on the data, filling missing values through methods such as mean filling and interpolation, identifying outliers using methods such as box plots and Z-scores, and making corrections or exclusions. If the dimensional differences of the parameters are large, the data can be standardized.

[0011] S12 According to the historical production data, set a quantification method to evaluate the independent influence degree of each adjustable parameter on the important performance of copper cast billets to obtain the parameter independent influence degree; S13 Based on metallurgical principles and materials science theories, predict the influence of adjustable parameters on the important performance of copper cast billets to obtain the parameter influence prediction results; Specifically, consult the latest metallurgical and materials science literature to understand the influence mechanism of each parameter on the performance of copper cast billets, and invite experts in the field for consultation to ensure the scientificity and rationality of the prediction.

[0012] S14 According to the historical production data and the parameter influence prediction results, select a quantification method to analyze the combined influence degree of each adjustable parameter on the important performance of copper cast billets to obtain the parameter combined influence degree; S15 Perform weight assignment on the parameter independent influence degree and the parameter combined influence degree, and calculate the influence degree of each adjustable parameter on the important performance of copper cast billets.

[0013] As an optimization of this embodiment, by combining the independent influence of a single parameter and the combined influence of multiple parameters, the influence degree of each parameter on the important performance of copper cast billets can be comprehensively and scientifically quantified; Conducting single-parameter analysis can evaluate the independent contribution of each adjustable parameter to the important performance, initially screen out key parameters, and exclude irrelevant parameters with little influence on performance; Conducting multi-parameter analysis can study the combined influence of multiple parameters on performance, especially the interaction between parameters. Before multi-parameter joint analysis, the influence of adjustable parameters on the important performance of copper cast billets can be predicted. Its main purpose is to preliminarily judge from the theoretical and data perspectives which parameters may have interaction relationships, narrow the analysis scope, optimize the experimental design and data analysis process. Through prediction, the interference of irrelevant parameters can be reduced, and targeted joint analysis can be carried out.

[0014] Among them, the quantification methods include: statistical analysis, effect size measurement, regression analysis, machine learning, multi-criteria decision analysis, and response surface method; Statistical analysis is a data-based method used to describe and interpret patterns and trends in data. By calculating statistics such as the mean, standard deviation, and correlation coefficient, the relationships between different parameters and their effects on external conditions can be evaluated. Statistical analysis also supports hypothesis testing to help determine whether the observed effects are statistically significant, thus providing reliable data support for decision-making; Effect size measurement is used to quantify the specific impact of a factor on the result. This method not only focuses on statistical significance but also emphasizes the importance of the actual effect. Through effect size measurement, the actual impact of parameter adjustment can be more accurately evaluated to ensure that the optimization strategy is not only statistically effective but also significantly meaningful in practical applications; Regression analysis is a statistical method used to model and analyze the relationships between variables. By establishing linear or non-linear regression models, the impact of one or more independent variables (such as adjustable parameters) on the dependent variable (such as performance indicators) can be predicted. Regression analysis helps identify key influencing factors and provides quantitative prediction capabilities, making the optimization process more scientific and reasonable; Machine learning uses algorithms and statistical models to automatically learn from large amounts of data and make predictions or decisions. By training models, machine learning can identify complex patterns, discover associations hidden in the data, and make high-precision predictions. Common machine learning methods include decision trees, random forests, and support vector machines, etc. These methods can help optimize parameter selection and improve production efficiency and product quality; Multi-criteria decision analysis is a systematic method for dealing with decision-making problems involving multiple conflicting objectives. By defining different evaluation criteria (such as cost, response time) and using weighted summation or other comprehensive scoring methods, MCDA can evaluate the overall advantages and disadvantages of different solutions. This method ensures that all factors are comprehensively considered in the decision-making process and provides a scientific and reasonable decision-making basis; Response surface methodology is a statistical and mathematical tool for optimizing process design and improvement. By constructing a design of experiments (DOE), RSM can systematically explore the parameter space and find the optimal operating conditions. Response surface methodology can not only determine the best parameter combination but also reveal the interactions between parameters, helping to understand complex process procedures and achieve efficient optimization; Through the above steps, the present invention can systematically obtain and quantify the impact of each adjustable parameter on the important properties of low-oxygen copper billets, providing a scientific basis for subsequent adjustment and optimization. This method not only improves the accuracy of evaluation but also provides solid data support for process improvement.

[0015] As a preferred embodiment of the present invention, the method for constructing the prediction model in S2 includes: S21 collects historical production data, including fixed parameters, adjustable parameters, and corresponding important performance data of copper billets; cleans the collected data, removes outliers and noise, and performs normalization processing; S22 randomly samples the processed historical production data to generate several sub-datasets; Specifically, to enhance the robustness of the model and avoid over-reliance of the model on a single data distribution, the processed historical production data can be randomly sampled to generate several sub-datasets. The sampling method can be sampling with replacement or sampling without replacement, and the size of the sub-dataset should be set in combination with the actual data volume and the complexity of the model, usually 60%-80% of the original dataset.

[0016] S23 selects several differentiated base learners, trains the base learners on each sub-dataset, and combines the prediction results of several base learners to obtain a prediction model; Specifically, in this step, differentiated base learners can be selected, including decision trees, logistic regression, neural networks, etc. The goal is to make the models complementary in terms of error distribution. Differentiated base learners can capture different patterns of data, which helps to improve the generalization ability of the model; by combining the prediction results of multiple base learners, such as averaging and voting, the bias of a single model can be reduced and the overall performance can be improved.

[0017] S24 integrates the constructed prediction model into the production environment to predict adjustable parameters.

[0018] The prediction model construction method of the present invention significantly improves the intelligent level and prediction accuracy of the low-oxygen copper casting forming process, ensures the stability and reliability of the model, greatly improves production efficiency and product quality, reduces the trial-and-error cost, promotes process optimization and technological progress, realizes data-driven precise decision-making, adapts to the needs of different scenarios, and thus provides a more competitive and efficient solution for enterprises.

[0019] As a preferred solution of the present invention, the correction method in S5 includes: S51 counts the number of times each adjustable parameter appears in the union set; Specifically, the optional sets corresponding to all abnormally important performances are merged to form a union set, and the frequency of each adjustable parameter in the union set is counted, and the number of times each adjustable parameter appears is recorded; By counting the number of occurrences, it can be intuitively seen which adjustable parameters repeatedly appear in multiple abnormal situations, indicating that these adjustable parameters may be the core factors causing problems, helping technicians quickly lock in the key parameters that may affect multiple performance indicators, and ensuring that adjusting these parameters can improve the performance in multiple aspects at the same time; S52 Obtain the influence degree of each adjustable parameter in the collection on the abnormally important performance; S53 Calculate the deviation degree of the abnormally important performance; S54 Assign weights to the occurrence times, influence degree, and deviation degree respectively; When assigning weights to the occurrence times, influence degree, and deviation degree, the following factors should be considered: 1) Evaluate the influence of different deviation degrees on product quality and production stability, determine which performance abnormalities are the most urgent, and appropriately increase the weight of the deviation degree for performance problems with larger deviation degrees; 2) Combine the data of multiple performance abnormalities, identify the key parameters that frequently appear in multiple abnormal situations, and appropriately increase the weight of the occurrence times for parameters with higher universality; 3) Adjust the weights of the occurrence times, influence degree, and deviation degree according to the enterprise's attention to different performance indicators; 4) If certain performance values are better than the optimal value of the required performance value, and the optional set of the corresponding performance value appears as a union with the collection, and there may be some room for decline in the corresponding performance value, then the influence degree of the adjustable parameter in the union can be appropriately reduced; S55 Calculate the comprehensive priority of each adjustable parameter to obtain the priority call set: More specifically, use the following formula to calculate the comprehensive priority: S = C × W 1 + D × W 2 + E × W 3 ; where S is the comprehensive priority of each adjustable parameter, C is the number of times the adjustable parameter appears in the collection, W 1 is the weight of the occurrence times, D is the influence degree, W 2 is the weight of the influence degree, E is the deviation degree, W 3 is the weight of the deviation degree, W 1 + W 2 + W 3 = 1; By comprehensively considering the occurrence times, influence degree, and deviation degree, the influence of each adjustable parameter on the important performance of low-oxygen copper billets can be comprehensively evaluated. A single index cannot fully reflect the importance of parameters in complex processes, while multi-dimensional evaluation can provide a more accurate judgment; the calculation of the comprehensive priority ensures that adjustable parameters with high priority are processed first, thereby improving the overall process optimization effect, which is crucial for improving product quality, reducing the scrap rate, and increasing production efficiency.

[0020] As a preferred solution of the present invention, the method of serial adjustment in S6 includes: S61 Evaluate the action value of each adjustable parameter in the priority call set on the external conditions; When evaluating the action value, the following factors should be considered: Adjusting certain adjustable parameters may bring unexpected risks or side effects. For example, although increasing the cooling rate can improve the conductivity, it may cause equipment overload or increase energy consumption, so its action value should be appropriately reduced; By evaluating the action value, these potential problems can be identified before adjustment and corresponding preventive measures can be taken; At the same time, adjusting different adjustable parameters may involve different resource inputs (such as time, manpower, and funds). By evaluating the action value, reasonable allocation of resources can be ensured, avoiding unnecessary waste and over-investment. When certain adjustable parameters bring more resource inputs, their action values should be appropriately reduced; S62 Calculate the call priority of each adjustable parameter in the priority call set; More specifically, the following formula is used to calculate the call priority of each adjustable parameter: S 1 =S×W 4 ; where S 1 is the call priority of each adjustable parameter, S is the comprehensive priority, and W 4 is the action value of the external conditions; The comprehensive priority reflects the potential contribution of the adjustable parameter to the important performance, while the action value of the external conditions reflects the risks and additional costs that may be brought by adjusting this parameter. Multiplying the two can achieve a balance between risks and benefits, ensuring the selection of parameters that can significantly improve performance without bringing excessive risks or costs for adjustment; S63 Sort the call priorities of each adjustable parameter in descending order to obtain the priority adjustment sequence; Compare the call priorities of all adjustable parameters numerically and arrange them in descending order. The higher the numerical value of an adjustable parameter, the greater the product of its comprehensive priority and the action value of the external conditions, indicating that this adjustable parameter is more important for overall optimization and should be called first.

[0021] As a preferred embodiment of the present invention, the external conditions in S6 include cost and response time; where the cost includes energy consumption, material usage, and equipment loss; the response time is the time required to reach a stable state after adjusting the adjustable parameter; If the adjustment of a certain adjustable parameter causes a significant increase in energy consumption (such as increasing the cooling rate), its action value of the external conditions should be correspondingly reduced, which helps to avoid the additional costs brought by high energy consumption and ensure the economic feasibility of the optimization process; The adjustment of certain adjustable parameters may cause material waste or additional raw material requirements (such as increasing the additive ratio), which will increase the production cost. Therefore, its action value should be appropriately reduced; If the adjustment of a certain adjustable parameter may cause equipment overload or accelerate equipment wear (such as increasing pressure or temperature), its acting value should be reduced accordingly, which helps to extend the service life of the equipment and reduce maintenance costs; If the adjustment of a certain parameter requires a long response time to reach a stable state, this will affect production efficiency, increase the production cycle and cost. Therefore, its acting value should be appropriately reduced; When evaluating the acting value of the above external conditions, a weighted summation method is used for quantification. Specifically, for each adjustable parameter, the specific influence values on cost and response time are defined respectively, then reasonable weights are assigned to each specific influence value, and then weighted calculation is performed to obtain the acting value.

[0022] As a preferred embodiment of the present invention, at least one adjustable parameter includes the adjustable parameter that is the most forward in the priority adjustment sequence; The most forward adjustable parameter is a key adjustment point for solving the current performance anomaly. By first adjusting the most forward adjustable parameter, the problem range can be quickly narrowed down, the most effective solution can be found, and time and resources can be avoided being wasted on unimportant parameters. At the same time, the most forward parameter can also take into account production cost and response time, which helps to achieve performance improvement with the minimum cost investment and improve economic benefits.

[0023] As a preferred embodiment of the present invention, the fixed parameters in S2 include: crystallizer wheel diameter, crystallizer wheel groove thickness, crystallizer wheel groove carbon layer thickness, and steel belt carbon layer thickness; Since different factories may have different fixed parameters, it is crucial to use these parameters as input variables for the prediction model; The crystallizer wheel diameter directly affects the forming process of the billet and the dimensional accuracy of the final product. A larger crystallizer wheel diameter can provide a longer cooling path, which helps to improve the cooling uniformity and structural stability of the billet, thereby improving conductivity and mechanical strength; The crystallizer wheel groove thickness determines the thickness and forming quality of the billet. Appropriate groove thickness can ensure good surface quality and dimensional accuracy of the billet, while reducing the occurrence of defects (such as cracks, pores); if the groove thickness is too large, it may lead to a slow cooling rate and affect the microstructure of the billet; if the groove thickness is too small, it may cause the cooling rate to be too fast, resulting in stress concentration and deformation; The carbon layer thickness in the crystallizer wheel groove plays a role in heat insulation and lubrication, which helps to reduce the friction between the billet and the crystallizer wheel, prevent adhesion phenomena. Appropriate carbon layer thickness can improve the surface finish and demoulding effect of the billet, while reducing equipment wear. If the carbon layer is too thick, it may affect the cooling effect of the billet and lead to performance degradation; if the carbon layer is too thin, it may cause the billet to adhere, increasing the production difficulty; The thickness of the carbon layer on the steel belt also plays a role in heat insulation and lubrication, protecting the steel belt from high-temperature damage and ensuring the smooth detachment of the cast billet from the steel belt. An appropriate carbon layer thickness can improve the surface quality and production efficiency of the cast billet, reduce the wear and maintenance requirements of the steel belt. If the carbon layer is too thick, it may lead to uneven heat transfer, affecting the cooling effect and performance of the cast billet; while if the carbon layer is too thin, it may cause adhesion problems and reduce production stability.

[0024] As a preferred embodiment of the present invention, the calculation method of the deviation degree in S53 includes: S531 Obtain the required performance value and the performance value of the copper cast billet; S532 Use the following calculation formula to obtain the deviation degree: R = ∣Q 1 -Q 2 ∣ / Q 2 ; wherein, R is the deviation degree, Q 1 is the performance value of the copper cast billet, and Q 2 is the required performance value.

[0025] The deviation degree can accurately quantify the risk level of each performance index. A higher deviation degree means a larger deviation, which may bring higher risks or potential problems. By monitoring the change of the deviation degree, potential risks can be identified and processed in advance to ensure the stability and reliability of the production process.

[0026] Compared with the prior art, the beneficial effects of the present invention are as follows: By introducing advanced prediction models and scientific analysis methods, the intelligent level of the low-oxygen copper casting process is greatly improved. First of all, this solution can predict in advance the parameter values that meet specific performance requirements, thus significantly improving the certainty and efficiency of the production process; In the traditional process, due to the lack of effective prediction tools, the selection of adjustable parameters often relies on limited experience and repeated trial and error, which not only wastes a large amount of time and resources, but also makes the production process full of uncertainties. The new solution uses a prediction model constructed by advanced technologies such as machine learning, which can accurately predict the expected performance results under different parameter settings based on historical data, enabling production enterprises to have a clear understanding of the final product quality before actual casting, thereby optimizing parameter selection and reducing unnecessary adjustments and tests; Secondly, when important performance anomalies occur in the produced low-oxygen copper billets, the present invention provides a systematic method to quickly locate and solve the core problems. Different from the traditional process, the new solution realizes the effective identification of key factors by combining and analyzing the optional sets corresponding to the abnormal performance, and considering factors such as the occurrence frequency, influence degree, and deviation degree of adjustable parameters. This method not only speeds up the troubleshooting process but also ensures the pertinence and effectiveness of the adjustment measures, fundamentally solving the problem of performance anomalies. In addition, by evaluating the values of external conditions, it further ensures that the adjustment measures taken can significantly improve performance without bringing excessive risks or costs, achieving a balance between risks and benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a schematic flowchart of the present invention; Figure 2 is a schematic flowchart of the method for correcting the call order of adjustable parameters according to the occurrence frequency, influence degree, and deviation degree of abnormal important performance of adjustable parameters in the union in step S5. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be given in conjunction with the accompanying drawings of the specification.

[0029] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0030] Secondly, the "embodiment" referred to herein means a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an individual or selectively exclusive embodiment with other embodiments. Embodiment

[0031] Referring to Figure 1 , this embodiment provides a casting process for low-oxygen copper, including: S1 Set the important performance of the copper billet, analyze the influence degree of adjustable parameters on the important performance, and set the influence degree threshold to obtain multiple optional sets; Analyzing the influence degree of adjustable parameters on key performance is to deeply understand how and to what extent each operating condition affects product quality. This analysis helps establish the causal relationship between parameter adjustment and performance change, providing a theoretical basis for formulating scientific and reasonable adjustment strategies in the subsequent stage; Important properties of copper cast billets include: conductivity, oxygen content, tensile strength, elongation, hardness, and microstructure; Conductivity is a key indicator for measuring the current conduction ability of copper materials. In fields such as power transmission and electronic component manufacturing, high conductivity means lower resistance losses and higher efficiency. Therefore, it is crucial to ensure that copper cast billets have excellent conductive properties; Controlling the oxygen content helps reduce oxide inclusions, improve the purity and conductivity of the material, and at the same time avoid a decrease in mechanical properties caused by oxidation; Tensile strength, elongation, and hardness reflect the response characteristics of the material under different stress conditions; Tensile strength determines the maximum tensile force that the material can withstand; Elongation represents the deformation ability of the material before fracture; Hardness affects the wear resistance and machining performance of the material; Good mechanical properties ensure the reliability and durability of copper cast billets in various application scenarios; The microstructure directly affects the internal structure of the material, such as grain size, distribution, and the presence of defects, etc.; It not only affects the mechanical properties and conductivity of the material, but also relates to the uniformity and consistency of the cast billet, thus affecting the quality of the final product; Adjustable parameters include: the cooling water flow rate and temperature on the crystallizer side, the cooling water flow rate and temperature on the steel belt side, the casting temperature, the withdrawal speed, and the casting angle; Among them, both the cooling water flow rate and temperature on the crystallizer side and the cooling water flow rate and temperature on the steel belt side can affect the above important properties: An appropriate cooling rate can promote the formation of fine and uniform grains, which is beneficial to improving conductivity; Too fast or too slow a cooling rate may affect the removal of oxygen, indirectly affecting the oxygen content; Rapid cooling can inhibit the formation of coarse grains, helping to improve mechanical properties such as tensile strength, elongation, and hardness; Cooling conditions directly affect the crystal growth mode and size, thereby changing the microstructure; The casting temperature can also affect the above important properties: The casting temperature directly affects the solidification process of the molten copper, thus affecting the microstructure and conductivity of the final product; A higher casting temperature may cause more oxygen to dissolve in the molten copper, increasing the oxygen content in the finished product; Too high or too low a casting temperature will affect the phase transformation path during solidification, thereby affecting mechanical properties; The withdrawal speed can also affect the above important properties: A faster withdrawal speed may cause non-uniform internal structure of the cast billet, affecting conductivity; The withdrawal speed affects the cooling rate, thus indirectly affecting the oxygen content; The withdrawal speed also affects the uniformity and density of the internal structure of the cast billet, thereby affecting mechanical properties and possible internal defects; The casting angle can also affect the above important properties: the casting angle affects the way the molten metal enters the five-wheel casting machine, and an improper angle may lead to poor filling or the generation of bubbles, indirectly affecting the conductivity; the casting angle affects the flow of the molten metal and the discharge of gas, thus affecting the oxygen content; the casting angle affects the forming quality of the billet and the distribution of thermal stress, and an incorrect angle may cause stress concentration points or cracks inside the billet, weakening the mechanical properties; a reasonable casting angle can ensure the smooth flow of the molten metal into the mold, form a dense and uniform microstructure, reduce internal defects, and improve the overall performance; Preferably, the method for obtaining the influence degree includes the following steps: S11 Based on metallurgical principles and materials science theories, predict the possible influence of each adjustable parameter on the important properties; Specifically, consult the latest metallurgical and materials science literature to understand the influence mechanism of each parameter on the properties of copper billets, and invite experts in the field for consultation to ensure the scientificity and rationality of the prediction; S12 Obtain the setting values of each adjustable parameter of copper billets in different production batches and the important property results of the corresponding copper billets; Specifically, obtain historical production data from platforms such as the enterprise production management system (MES) and the distributed control system (DCS), and extract the important property test results of copper billets in each production batch from the quality inspection system to ensure that the timestamps of all data are consistent, facilitating subsequent data cleaning and analysis; S13 Clean and preprocess the obtained historical production data; set a quantification method to evaluate the influence degree of each adjustable parameter on the important properties of copper billets; the quantification methods include statistical analysis, effect size measurement, regression analysis, machine learning, multi-criteria decision analysis, and response surface method; Specifically, set an influence degree threshold to obtain multiple optional sets. The main purpose of this step is to screen out the adjustable parameters that have a significant influence on the important properties of copper billets through scientific methods, so as to remove those adjustable parameters with low influence degrees and little contribution to the quality of the final product; Preferably, when setting the influence degree threshold, invite experts in the fields of metallurgy and materials science to participate in the discussion. According to their experience and professional knowledge, set a minimum influence degree threshold for each key performance index respectively. These thresholds will be used as screening criteria to distinguish which adjustable parameters have a significant influence on the performance and which are insignificant; for the remaining adjustable parameters with high influence degrees, generate multiple different configuration combinations to form multiple optional sets; S2 Input the real-time fixed parameters and the required performance values into the pre-constructed prediction model to obtain the predicted values of the adjustable parameters; The construction method of the prediction model includes: S21 Collect historical production data, including fixed parameters, adjustable parameters, and important performance data of the corresponding copper billets; clean the collected data to remove outliers and noise, and perform standardization processing; S22 Select a machine learning model as the infrastructure of the prediction model. The machine learning models include support vector machines, gradient boosting trees, long short-term memory networks, random forests, and neural networks; S23 Divide the processed data set into a training set, a validation set, and a test set; use the training set to train the prediction model and continuously adjust the model parameters; use the validation set to evaluate the stability and prediction performance of the model; use the test set to evaluate the accuracy and reliability of the model; deploy the trained model to production; S3 Produce copper billets according to the real-time fixed parameters and predicted values of adjustable parameters; In this embodiment, the method for producing copper billets adopts the SCR method. Continuously cast copper billets using the SCR method according to the real-time fixed parameters and predicted values of adjustable parameters, which not only ensures the efficiency and stability of the production process, but also provides a key opportunity to verify the output results of the prediction model. By comparing the performance of the actually produced copper billets with the expected results of the prediction model, the accuracy and reliability of the model can be evaluated, and then the model and production process can be optimized, while providing data support for continuous technological improvement; S4 Detect the important performance of the copper billets to obtain performance values, and compare them with the required performance values to obtain abnormally important performance; Specifically, the performance values are the actual detection results of the key performance indicators (such as conductivity, oxygen content, tensile strength, elongation, hardness, and microstructure) of the copper billets continuously cast by the SCR method; clarify the required performance values for each important performance indicator. The required performance values are usually set based on industry standards, customer requirements, or enterprise internal quality control specifications; Compare the actual performance values with the required performance values one by one to determine whether each performance is within an acceptable range. If the actual value of a certain performance indicator exceeds the preset tolerance range, it is marked as abnormally important performance; for example, if the conductivity is lower than expected, or the oxygen content is higher than the allowable maximum value, then these are all abnormal situations; S5 Combine the optional sets corresponding to the abnormally important performance to form a union; correct the call order of the adjustable parameters according to the number of occurrences, influence degree, and deviation degree of the abnormally important performance of the adjustable parameters in the union to obtain a priority call set; Specifically, the correction method is as follows Figure 2 shown, including: S51 Count the number of occurrences of each adjustable parameter in the union; Specifically, merge the optional sets corresponding to all the abnormally important performances obtained to form a union, count the frequencies of each adjustable parameter in the union, and record the number of times each parameter appears; By counting the number of occurrences, it can be intuitively seen which adjustable parameters repeatedly appear in multiple abnormal situations, indicating that these adjustable parameters may be the core factors causing problems, helping technicians quickly lock in the key parameters that may affect multiple performance indicators, and ensuring that adjusting these parameters can improve the performance in multiple aspects simultaneously; S52 Obtain the influence degree of each adjustable parameter in the set on the abnormally important performance, where the influence degree mentioned here is the influence degree obtained in step S1; S53 Calculate the deviation degree of the abnormally important performance; The calculation method of the deviation degree includes: S531 Obtain the required performance value and the performance value of the copper casting blank; S532 Use the following calculation formula to obtain the deviation degree: R = ∣Q 1 -Q 2 ∣ / Q 2 ; where R is the deviation degree, Q 1 is the performance value of the copper casting blank, and Q 2 is the required performance value; S54 Assign weights to the number of occurrences, influence degree, and deviation degree respectively; When assigning weights to the number of occurrences, influence degree, and deviation degree, the following factors should be considered: 1) Evaluate the impact of different deviation degrees on product quality and production stability, determine which performance anomalies are the most urgent, and appropriately increase the weight of the deviation degree for performance problems with larger deviation degrees; 2) Combine the data of multiple performance anomalies to identify the key parameters that frequently appear in multiple abnormal situations, and appropriately increase the weight of the number of occurrences for parameters with higher universality; 3) Adjust the weights of the number of occurrences, influence degree, and deviation degree according to the enterprise's emphasis on different performance indicators; 4) If some performance values are better than the optimal value of the required performance value, and if the optional set of the corresponding performance value appears in the union with the set, there may be some room for decline in the corresponding performance value, then the influence degree of the adjustable parameter in the union can be appropriately reduced; S55 Use the following formula to calculate the comprehensive priority of each adjustable parameter: S = C×W 1 +D×W 2 +E×W 3 ; Among them, S is the comprehensive priority of each adjustable parameter, C is the number of times the adjustable parameter appears in the collection, W 1 is the weight of the number of occurrences, D is the influence degree, W 2 is the weight of the influence degree, E is the deviation degree, W 3 is the weight of the deviation degree, W 1 +W 2 +W 3 = 1; S6 serializes and adjusts the priority call set using preset external conditions to obtain a priority adjustment sequence; Specifically, the external conditions include cost and response time; among them, the cost includes energy consumption, material usage, and equipment loss; the response time is the time required to reach a stable state after adjusting the adjustable parameter; The method of serializing and adjusting includes: S61 evaluates the action value of each adjustable parameter in the priority call set on the external conditions; When evaluating the action value, the following factors should be considered: Adjusting some adjustable parameters may bring unexpected risks or side effects. For example, increasing the cooling rate can improve the conductivity, but may cause equipment overload or increase energy consumption, so its action value should be appropriately reduced; by evaluating the action value, these potential problems can be identified before adjustment and corresponding preventive measures can be taken; at the same time, adjusting different adjustable parameters may involve different resource inputs (such as time, manpower, and funds). By evaluating the action value, reasonable allocation of resources can be ensured, avoiding unnecessary waste and excessive investment. When some adjustable parameters bring more resource inputs, their action values should be appropriately reduced; S62 uses the following formula to calculate the call priority of each adjustable parameter in the priority call set: S 1 = S × W 4 ; Among them, S 1 is the call priority of each adjustable parameter, S is the comprehensive priority, W 4 is the action value on the external conditions; The comprehensive priority reflects the potential contribution of the adjustable parameter to important performance, while the external condition action value reflects the risks and additional costs that may be brought by adjusting this parameter. Multiplying the two can achieve a balance between risks and benefits, ensuring that parameters that can significantly improve performance without bringing excessive risks or costs are selected for adjustment; S63 sorts the call priorities of each adjustable parameter in descending order to obtain a priority adjustment sequence; Numerically compare the call priorities of all adjustable parameters and arrange them in descending order. The higher the value of an adjustable parameter, the greater the product of its comprehensive priority and the effect value on external conditions, indicating that the adjustable parameter is more important for overall optimization and should be called first; S7 calls at least one adjustable parameter in the priority adjustment sequence for adjustment; among them, at least one adjustable parameter includes the adjustable parameter at the forefront of the priority adjustment sequence; Specifically, assume that the oxygen content of the copper billet is higher than the required performance value; Based on the foregoing analysis, the priority adjustment sequence is obtained as: casting temperature, cooling water flow rate on the crystallizer side, and withdrawal speed; First, select the parameter "casting temperature" at the forefront for adjustment; Based on historical data and expert advice, it is decided to reduce the casting temperature from the current 1140°C to 1138°C. This adjustment aims to reduce the oxygen solubility in the molten copper, thereby reducing the oxygen content in the finished product; Adjust the heating power of the melting furnace according to the new setting to ensure that the casting temperature accurately reaches the predetermined new value. During the adjustment process, closely monitor the change of the casting temperature and record the specific time and amplitude of the adjustment; After completing the preliminary adjustment, immediately produce a new batch of copper billets and conduct a rapid inspection on them, focusing on the change of the oxygen content; if it is found that the oxygen content has decreased but still has not fully reached the expected standard, further fine-tuning of the casting temperature or selecting to adjust the cooling water flow rate on the crystallizer side can be considered; Collect data from more batches to verify whether the adjustment effect is consistent and provide a reliable reference basis for future decisions. Feed back the results of this adjustment to the prediction model to help it learn the new parameter combinations and the corresponding product performance change rules.

[0032] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not restrictive. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A casting process for low-oxygen copper, characterized in that: include: S1 sets important properties of copper ingot, analyzes the influence of adjustable parameters on important properties, and sets influence thresholds to obtain multiple optional sets; S2 inputs the real-time fixed parameters and the required performance values ​​into the pre-built prediction model to obtain the prediction values ​​of the adjustable parameters; S3 produces copper casting billets according to the real-time fixed parameters and the predicted values ​​of the adjustable parameters; S4 detects important properties of copper ingots, obtains property values, and compares them with required property values ​​to obtain abnormally important properties; S5 combines the optional sets corresponding to the abnormally important performance into a union set; corrects the calling order of the adjustable parameters according to the number of occurrences, influence and deviation of the abnormally important performance of the adjustable parameters in the union set to obtain a priority calling set; S6 uses a preset additional condition to perform serialization adjustment on the priority call set to obtain a priority adjustment sequence; S7 calls at least one adjustable parameter in the priority adjustment sequence for adjustment.

2. The casting process for low-oxygen copper according to claim 1, characterized in that: The important properties of the copper ingot in S1 include: electrical conductivity, oxygen content, tensile strength, elongation, hardness and microstructure; The adjustable parameters include: cooling water flow and temperature on the crystallization wheel side, cooling water flow and temperature on the steel strip side, casting temperature, casting speed and casting angle.

3. The casting process for low-oxygen copper according to claim 1, characterized in that: The method for obtaining the influence in S1 comprises the following steps: S11 obtains the setting values ​​of various adjustable parameters of copper casting billets of different production batches and the important performance results corresponding to the copper casting billets to obtain historical production data; S12: according to the historical production data, a quantitative method is set to evaluate the independent influence of each adjustable parameter on the important properties of the copper casting billet to obtain the independent influence of the parameter; S13 predicts the influence of the adjustable parameters on the important properties of the copper ingot based on metallurgical principles and material science theories, and obtains parameter influence prediction results; S14: selecting a quantitative method to analyze the combined influence of each of the adjustable parameters on the important properties of the copper casting billet according to the historical production data and the parameter impact prediction result, and obtaining the combined influence of the parameters; S15 performs weight distribution on the independent influence of the parameters and the joint influence of the parameters, and calculates the influence of each adjustable parameter on the important properties of the copper ingot.

4. The casting process for low-oxygen copper according to claim 1, characterized in that: The method for constructing the prediction model in S2 includes: S21 collects historical production data, including fixed parameters, adjustable parameters and corresponding important performance data of copper ingots; cleans and standardizes the collected data; S22 randomly samples the processed historical production data to generate a plurality of sub-data sets; S23: selecting a plurality of differentiated base learners, training the base learners on each of the sub-data sets, and combining the prediction results of the plurality of base learners to obtain a prediction model; S24 integrates the constructed prediction model into the production environment to predict the adjustable parameters.

5. The casting process for low-oxygen copper according to claim 1, characterized in that: The correction method in S5 comprises: S51 counts the number of times each adjustable parameter appears in the collection; S52 obtains the influence of each adjustable parameter in the collection on the abnormally important performance; S53 calculates the deviation of abnormally important performance; S54 assigns weights to the number of occurrences, influence, and deviation respectively; S55 calculates the comprehensive priority of each adjustable parameter to obtain a priority call set.

6. The casting process for low-oxygen copper according to claim 5, characterized in that: The method for serialization adjustment in S6 includes: S61 evaluates the effect value of each adjustable parameter in the priority call set on the external condition; S62 calculates the calling priority of each adjustable parameter in the priority calling set; S63 sorts the calling priority of each adjustable parameter in descending order to obtain a priority adjustment sequence.

7. The casting process for low-oxygen copper according to claim 1, characterized in that: The additional conditions in S6 include cost and response time; Among them, cost includes energy consumption, material usage and equipment loss; response time is the time required to reach a stable state after adjusting the adjustable parameters.

8. The casting process for low-oxygen copper according to claim 3, characterized in that: The at least one adjustable parameter comprises a first adjustable parameter in the priority adjustment sequence.

9. The casting process for low-oxygen copper according to claim 1, characterized in that: The fixed parameters in S2 include: crystallization wheel diameter, crystallization wheel groove thickness, crystallization wheel groove carbon layer thickness and steel strip carbon layer thickness.

10. The casting process for low-oxygen copper according to claim 5, characterized in that: The method for calculating the deviation in S53 includes: R=|Q1-Q2| / Q2; Among them, R is the deviation, Q1 is the performance value of the copper ingot, and Q2 is the required performance value.

Images