Prediction method for RH refining end temperature and related equipment

Abstract

The invention discloses an RH refining end temperature prediction method and related equipment, and relates to the technical field of metallurgy, the method comprises the steps that steel grade information corresponding to molten steel to be refined is obtained, and the steel grade information comprises the liquidus temperature, the superheat degree, the casting period and the vacuum period of a steel grade; on the basis of the vacuum period, the RH refining ending moment is calculated; based on the RH refining ending moment, RH sedation duration is calculated; and based on the RH sedation duration and the temperature drop parameter, the RH refining ending temperature is calculated, so that optimal prediction of the RH refining ending temperature is achieved.

Description

Technical Field

[0001] The present application relates to the field of metallurgical technology, and in particular to a method for predicting the end temperature of RH refining and related equipment. Background Art

[0002] In iron and steel metallurgical production, RH (Ruhrstahl-Heraeus) refining is a key link in improving molten steel quality, and accurate prediction of RH refining end temperature plays a vital role in ensuring molten steel quality, improving production efficiency and reducing costs. Traditional RH refining temperature prediction methods often rely on empirical parameters. With the continuous development of metallurgical processes, empirical parameters have gradually become difficult to adapt to the dynamically changing production environment.

[0003] In addition, during the process from the end of RH refining to the casting machine, the temperature of the molten steel will change due to many factors, such as changes in casting order, thermal state of the ladle, abnormal conditions of the casting machine, etc. At present, there is a lack of effective technical means to correct the RH refining temperature in real time in actual production, which causes the superheat of the steel grade to exceed the reasonable range, affecting the constant casting speed control of the casting machine and the accurate hit rate of the molten steel temperature. Therefore, a prediction method for the end temperature of RH refining is urgently needed to solve the above technical problems. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] In a first aspect, the present application provides a method for predicting RH refining end temperature, comprising:

[0006] Obtaining steel grade information corresponding to the molten steel to be refined, wherein the steel grade information includes liquidus temperature, superheat, casting cycle and vacuum cycle of the steel grade;

[0007] Calculate the end time of RH refining based on the vacuum cycle;

[0008] Based on the end time of RH refining, the duration of RH sedation was calculated;

[0009] Based on the RH calming time and temperature drop parameters, the RH refining end temperature is calculated to achieve the optimal prediction of the RH refining end temperature. The temperature drop parameters include the temperature drop due to the calming time, the abnormal temperature drop of the ladle and the abnormal temperature drop of the casting machine.

[0010] In some embodiments, the RH refining end time is determined based on the following formula, expressed as:

[0011] RH refining end time = vacuum start time + vacuum cycle.

[0012] In some embodiments, the duration of RH sedation is determined based on the following formula, expressed as:

[0013] RH calming time = pouring change time + casting cycle - RH refining end time.

[0014] In some embodiments, the RH refining end temperature is determined based on the following formula, expressed as:

[0015] RH refining end temperature = liquidus temperature + superheat + temperature drop parameter + furnace compensation.

[0016] In some embodiments, the specific steps of obtaining the temperature drop parameter include:

[0017] Based on the ladle thermal state, establish a ladle temperature drop expert database, and calculate the abnormal ladle temperature drop according to the ladle thermal state type, where the ladle thermal state types include baking ladle, minor repair ladle and normal ladle;

[0018] Calculate the temperature drop during the cooling time based on the cooling time and the temperature drop coefficient of the steel grade;

[0019] Based on the abnormal conditions of the casting machine, the abnormal temperature drop of the casting machine is calculated. The abnormal conditions of the casting machine include low tonnage, before flying ladle and normal continuous casting. The abnormal temperature drop of the casting machine is obtained through self-learning of historical data.

[0020] In some embodiments, the method also includes: based on big data technology, determining the abnormal deviation of the RH refining end temperature, wherein the abnormal deviation includes abnormal self-learning of the middle ladle temperature, abnormal time deviation, abnormal thermal state of the ladle, abnormal casting sequence, and abnormal deviation of the middle ladle temperature.

[0021] In some embodiments, the method further comprises:

[0022] Based on the accuracy of RH refining end temperature, the control strategy of steel grade superheat standard line is optimized.

[0023] In a second aspect, the present application proposes a device for predicting the end temperature of RH refining, comprising:

[0024] A steel grade information acquisition unit, used to acquire steel grade information corresponding to the molten steel to be refined, wherein the steel grade information includes liquidus temperature, superheat, casting cycle and vacuum cycle of the steel grade;

[0025] An end time determination unit calculates the end time of RH refining based on the vacuum cycle;

[0026] A sedation duration calculation unit, which calculates the RH sedation duration based on the RH refining end time;

[0027] The end temperature prediction unit calculates the end temperature of RH refining based on the RH calming time and temperature drop parameters to achieve the optimal prediction of the end temperature of RH refining, wherein the temperature drop parameters include the temperature drop due to the calming time, the abnormal temperature drop of the ladle and the abnormal temperature drop of the casting machine.

[0028] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the method for predicting the RH refining end temperature of any one of the first aspects when executing the computer program stored in the memory.

[0029] In a fourth aspect, the present application further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for predicting the RH refining end temperature of any one of the first aspects is implemented.

[0030] In summary, this application obtains comprehensive steel grade information, combines accurate calculation methods to determine the RH refining end time and RH calming time, and comprehensively considers multiple temperature drop parameters to calculate the RH refining end temperature, thereby achieving an optimized prediction of the refining end temperature. Based on metallurgical mechanisms and big data technology, an expert database and self-learning mechanism have been established, which can dynamically adjust parameters according to actual production conditions, effectively improving the accuracy and reliability of temperature prediction. At the same time, the accuracy of temperature control is further improved by determining deviation anomalies and optimizing the superheat standard line control strategy, thereby optimizing the temperature matching of the continuous casting process, reducing fluctuations in molten steel quality, reducing energy consumption, and improving the target performance of steel. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0032] Figure 1 A schematic flow chart of a method for predicting the RH refining end temperature provided in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of an abnormal furnace condition interface of RH refining end temperature provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of the structure of a device for predicting the end temperature of RH refining provided in an embodiment of the present application;

[0035] Figure 4 A schematic diagram of the structure of an electronic device for predicting the RH refining end temperature provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0037] See also Figure 1 , is a schematic flow chart of a method for predicting the RH refining end temperature provided in an embodiment of the present application, which may specifically include:

[0038] S110, obtaining steel grade information corresponding to the molten steel to be refined, wherein the steel grade information includes liquidus temperature, superheat, casting cycle and vacuum cycle of the steel grade;

[0039] For example, steel grade information is the basis for RH refining end temperature prediction, and its core parameters include liquidus temperature, superheat, casting cycle and vacuum cycle. Liquidus temperature is the lowest temperature of a steel grade in a completely liquid state, which determines the critical point of molten steel solidification; superheat is the difference between the actual temperature of molten steel and the liquidus temperature, which directly affects the fluidity and solidification behavior of the casting process; casting cycle refers to the time required for continuous casting of a furnace of molten steel, and vacuum cycle is the duration of the vacuum treatment stage during RH refining. Accurate acquisition of these parameters provides key inputs for subsequent temperature prediction models, ensuring that the model can dynamically adjust the calculation logic based on the characteristics of the steel grade and avoid prediction errors caused by parameter deviations.

[0040] In specific implementation, the liquidus temperature and superheat are predetermined by the chemical composition of the steel grade and the process requirements. For example, the liquidus temperature of low-carbon steel and high-carbon steel is significantly different, and needs to be calibrated according to the metallurgical database or experimental data; the casting cycle and vacuum cycle are derived from the production plan and historical process data. For example, the casting cycle of each furnace of molten steel in the same casting can be averaged through big data analysis, and the vacuum cycle is set to a fixed value or a dynamically adjusted value according to the characteristics of the steel grade (such as degassing requirements). By acquiring or calling the steel grade information in the pre-stored database in real time, the system can quickly match the key parameters of the current furnace and provide a reliable basis for subsequent calculations.

[0041] S120, calculating the RH refining end time based on the vacuum cycle;

[0042] For example, in the RH refining process, the vacuum cycle is an extremely critical and relatively stable process parameter. It is based on metallurgical principles and long-term production practice experience, and represents the standard time required for molten steel to complete a series of specific refining reactions in a vacuum environment. These refining reactions include but are not limited to degassing, removing impurities, adjusting the composition of molten steel, etc., which are crucial to improving the quality of molten steel. Calculating the end time of RH refining is an indispensable part of the entire refining process. It provides a clear time node basis for subsequent production processes, helps to reasonably arrange the production rhythm, coordinate the connection between various processes, and ensure the efficient and orderly progress of the entire production process.

[0043] S130, calculating the RH sedation duration based on the RH refining end time;

[0044] For example, in the temperature prediction system of the RH refining process, calculating the RH calming time is a key link in achieving accurate temperature prediction. The calming time characterizes the standing time of molten steel from the end of refining to before casting. During this stage, the molten steel will experience a temperature drop, which has a direct impact on the final refining end temperature value. By accurately calculating the calming time, the temperature drop changes of the molten steel during this period can be accurately grasped, providing key parameter support for optimizing the prediction results of the refining end temperature. The principle of this calculation process is based on a systematic combing of various time nodes and related factors in the production process. In actual production scenarios, factors such as casting changes and casting cycles will affect the calming time of molten steel. Taking the end of RH refining as the key time node, combined with relevant data such as the casting change time and casting cycle, the actual calming time of molten steel can be accurately determined. This calculation method is based on an in-depth analysis of the production process and long-term accumulated practical data, and fully considers various factors that may affect the calming time, aiming to improve the accuracy and reliability of the calculation results and provide a solid data foundation for subsequent temperature prediction.

[0045] S140. Calculate the RH refining end temperature based on the RH calming time and the temperature drop parameters to achieve an optimized prediction of the RH refining end temperature, wherein the temperature drop parameters include the temperature drop due to the calming time, the abnormal temperature drop due to the ladle, and the abnormal temperature drop due to the casting machine.

[0046] For example, in the temperature prediction system of the RH refining process, calculating the RH refining end temperature based on the RH calming time and the temperature drop parameter is a key step to achieve accurate temperature prediction. In the process from the end of refining to casting, the temperature of the molten steel will change due to various factors, and these changes directly affect the quality and performance of the molten steel during the final casting. By combining the RH calming time with the temperature drop parameter for calculation, the various temperature drops of the molten steel at this stage can be comprehensively considered, so as to accurately determine the appropriate RH refining end temperature. The temperature drop during the calming time reflects the temperature drop of the molten steel caused by factors such as heat dissipation during the static period. Its size is closely related to the calming time and is one of the important factors affecting the temperature change of the molten steel. The abnormal temperature drop of the ladle takes into account the influence of the ladle in different thermal states (such as baking ladle, minor repair ladle, etc.) on the temperature of the molten steel. Different thermal states of the ladle will cause different heat dissipation rates of the molten steel, thereby producing different degrees of temperature drop. The abnormal temperature drop of the casting machine covers the impact of abnormal conditions such as low tonnage and flying ladle on the temperature of the molten steel. These abnormal conditions will change the flow and heat dissipation conditions of the molten steel, resulting in additional temperature drop. Through the comprehensive consideration of these temperature drop parameters, the temperature change law of the molten steel in the whole process can be fully and accurately grasped, providing a scientific basis for determining the reasonable RH refining end temperature.

[0047] In summary, this application realizes the accurate prediction and dynamic optimization of RH refining end temperature by combining metallurgical mechanism and big data technology. Specifically, this application can accurately predict the RH refining end temperature by obtaining steel grade information, calculating the refining end time, calming time and temperature drop parameters, and automatically judges the temperature deviation abnormality by combining big data technology, further improving the intelligent level of temperature control. In addition, this application realizes the dynamic optimization of molten steel temperature by optimizing the steel grade superheat standard line control strategy, effectively improving the accuracy and stability of temperature prediction.

[0048] In some examples, the RH refining end time is determined based on the following formula, expressed as:

[0049] RH refining end time = vacuum start time + vacuum cycle.

[0050] Exemplarily, the core of RH refining is to accurately control the vacuum treatment time of molten steel to ensure the effect of gas removal and composition homogenization. Therefore, in the RH refining process, calculating the end time of RH refining based on the vacuum cycle is a key link in temperature control and production rhythm management. The vacuum cycle refers to the vacuum degassing time that the molten steel experiences in the RH furnace, which is usually determined by the process requirements, steel grade characteristics and gas removal requirements. In the production process, the start time of RH refining (i.e., the vacuum start time) is set by the operator or the automatic control system, wherein the length of the vacuum cycle determines the heat loss of the molten steel in the RH furnace, and also affects the final temperature of the molten steel. The vacuum cycle of different steel grades is different. For example, the vacuum cycle of low carbon steel is usually shorter, while special steel grades (such as silicon steel, stainless steel, etc.) requiring high cleanliness require a longer vacuum time. Therefore, accurately calculating the vacuum cycle based on the steel grade information and calculating the end time of RH refining accordingly are the keys to ensure the refining quality and temperature control accuracy.

[0051] When calculating the end time of RH refining, it is necessary to consider the heat loss during the vacuum process to ensure that the molten steel remains within a reasonable superheat range after refining. In a vacuum environment, the heat loss of molten steel mainly comes from radiation heat dissipation and the heat taken away by gas escape, so different vacuum cycles will result in different temperature drops. If the RH refining time is too long, the temperature of the molten steel may drop too much, affecting the stability of subsequent continuous casting; if the time is insufficient, it may lead to insufficient degassing and affect the quality of the molten steel. Therefore, in production control, the vacuum cycle at the end of RH refining can be optimized through self-learning of historical process data. For example, for the production data of multiple furnaces of the same steel grade, the actual degassing efficiency is counted and the cycle value is dynamically adjusted to balance the process quality and production efficiency. This dynamic adaptation based on the characteristics of the steel grade not only avoids the problem of over-processing or under-processing caused by fixed cycles, but also provides a scientific basis for the accurate calculation of the end time of refining.

[0052] In some embodiments, the duration of RH sedation is determined based on the following formula, expressed as:

[0053] RH calming time = pouring change time + casting cycle - RH refining end time.

[0054] For example, after RH refining is completed, the molten steel does not immediately enter the casting stage, but goes through a calming stage, that is, the molten steel is left in the ladle for a period of time to allow its temperature, composition and fluidity to reach a suitable state. Therefore, calculating the RH calming time based on the end time of RH refining is crucial to ensure accurate control of the molten steel temperature. The calculation of the RH calming time is usually based on the casting change time, the casting cycle and the end time of RH refining.

[0055] The pouring change time marks the start time of the previous heat of molten steel casting, and the casting cycle refers to the time span from the completion of RH refining to the injection of molten steel into the casting machine. The calculation of the calming time is extremely critical for the temperature control of molten steel, because during the calming stage, the molten steel will experience a certain degree of temperature drop, which is mainly caused by heat transfer from the ladle, environmental heat dissipation, and thermal radiation of the molten steel itself. If the calming time is not calculated accurately, the molten steel temperature may deviate from the set range, thereby affecting the stability of the continuous casting process.

[0056] In order to ensure the accuracy of the calculation of the calming time, it is necessary to optimize and adjust in combination with the thermal state of the ladle, the current casting progress and historical data. For example, if the ladle is in a high temperature state (such as a newly baked ladle), the calming time may be slightly shorter, and if the ladle is in a cold state or is used for the first time after a minor repair, the temperature of the molten steel will drop faster, and the calming time needs to be appropriately extended. In addition, in the case of multiple furnaces pouring continuously, the calculation of the calming time should also consider the time deviation caused by the change of pouring times, as well as the additional waiting time that may be caused by casting machine abnormalities (such as shutdowns, flow rate fluctuations). Therefore, the core goal of calculating the RH calming time based on the end time of RH refining is to ensure that the molten steel is still in the optimal temperature range when it enters the casting machine, so as to improve the stability of the casting process and the accuracy of molten steel temperature control.

[0057] In some examples, the RH refining end temperature is determined based on the following formula, expressed as:

[0058] RH refining end temperature = liquidus temperature + superheat + temperature drop parameter + furnace compensation

[0059] For example, after RH refining is completed, the temperature of the molten steel will gradually decrease as the cooling process proceeds. Therefore, calculating the RH refining end temperature based on the RH cooling time and temperature drop parameters is a key step to ensure that the molten steel remains within a reasonable temperature range when entering the casting stage. The calculation model of the RH refining end temperature needs to comprehensively consider the cooling time temperature drop, the abnormal temperature drop of the ladle, and the abnormal temperature drop of the casting machine to correct the temperature loss during the refining process.

[0060] The temperature drop during the calming time mainly depends on the residence time of the molten steel after the end of RH refining and before casting. The longer the time, the greater the temperature drop. The abnormal temperature drop of the ladle is affected by the thermal state of the ladle. For example, the heat loss of a newly baked ladle is small, while a ladle with minor repairs or long-term use may cause a large heat loss due to the deterioration of the lining brick state. The abnormal temperature drop of the casting machine is due to the increase in the waiting time of the molten steel in the initial startup of the casting machine or during abnormal shutdown, resulting in additional temperature drop. Therefore, when calculating the end temperature of RH refining, it is necessary to dynamically compensate for various temperature drop factors to improve the prediction accuracy.

[0061] In order to achieve the optimal prediction of the end temperature of RH refining, it is necessary to adopt a method that combines historical data modeling and real-time monitoring to dynamically adjust the temperature drop parameters. Through big data analysis of the actual temperature drop of the ladle under different thermal conditions, an expert database of ladle temperature drop is established, and the temperature loss law under abnormal conditions of different casting machines is self-learned based on historical furnace data, thereby improving the accuracy of temperature drop parameter calculation. In addition, error correction can also be performed in combination with real-time temperature measurement data. For example, when the actual measured molten steel temperature deviates from the predicted value beyond the set range, the system can automatically adjust the temperature drop calculation parameters to improve the adaptability of the prediction model. Finally, based on the calculation of RH calming time and temperature drop parameters, the end temperature of RH refining is always within a reasonable range, ensuring that the molten steel maintains optimal fluidity during the casting process and improving the stability of temperature control and production efficiency.

[0062] In some examples, the specific steps of obtaining the temperature drop parameter include:

[0063] Based on the ladle thermal state, establish a ladle temperature drop expert database, and calculate the abnormal ladle temperature drop according to the ladle thermal state type, where the ladle thermal state types include baking ladle, minor repair ladle and normal ladle;

[0064] Calculate the temperature drop during the cooling time based on the cooling time and the temperature drop coefficient of the steel grade;

[0065] Based on the abnormal conditions of the casting machine, the abnormal temperature drop of the casting machine is calculated. The abnormal conditions of the casting machine include low tonnage, before flying ladle and normal continuous casting. The abnormal temperature drop of the casting machine is obtained through self-learning of historical data.

[0066] For example, in the prediction process of RH refining end temperature, accurate calculation of temperature drop parameters is crucial. In order to improve the accuracy of temperature prediction, it is necessary to establish a ladle temperature drop expert database based on the ladle thermal state, and calculate the abnormal temperature drop of the ladle according to the ladle thermal state type. The thermal state of the ladle directly affects the temperature loss of the molten steel during the calming process, mainly including three types: baking ladle, minor repair ladle and normal ladle. The baking ladle has a high heat storage capacity because it has just been preheated at high temperature, and its molten steel temperature drop is small; the minor repair ladle has undergone local repairs and a short period of baking, and the thermal conductivity of the lining brick has changed, and the temperature drop is relatively large; the normal ladle refers to a ladle in a stable use state, and its temperature drop is between the baking ladle and the minor repair ladle. By collecting ladle temperature drop data under different thermal states for a long time and establishing a ladle temperature drop expert database, the expert database is established through historical production data statistics and metallurgical mechanism analysis. For example, for the actual temperature drop data of multiple furnaces under different ladle states, regression analysis is used to determine the compensation value. The system matches the current ladle thermal state type in real time and automatically calls the corresponding compensation value to ensure accurate adaptation of abnormal ladle temperature drop.

[0067] The calculation of the temperature drop during the calming time needs to be combined with the temperature drop coefficient of the steel grade to quantify the temperature loss of the molten steel during the calming process. The longer the calming time, the greater the temperature drop of the molten steel, but the temperature drop rate of different steel grades is different, so it is necessary to introduce the temperature drop coefficient of the steel grade for correction. For example, high alloy steel has a slow temperature drop rate due to its high specific heat capacity, while the temperature drop rate of ordinary carbon steel is relatively fast. In the temperature drop parameter calculation, the system will calculate the temperature drop during the calming time based on the characteristics of the steel grade and the calming time, and dynamically adjust it in combination with the real-time temperature measurement data. If the calming time is too long, the system can automatically increase preheating or compensation measures to ensure that the molten steel is still in a suitable superheat range when it enters the casting stage. In addition, the calculation of the temperature drop coefficient of the steel grade needs to be combined with factors such as ambient temperature and ladle material characteristics to further optimize the temperature drop model and ensure the accuracy of temperature prediction. For example, if a certain steel grade has an average temperature drop of 18°C ​​within a 30-minute calming time, the temperature drop coefficient is 0.6°C / min.

[0068] The impact of casting machine abnormalities on molten steel temperature loss cannot be ignored. It is necessary to self-learn based on historical data to calculate the abnormal temperature drop of the casting machine. Abnormal conditions of casting machines mainly include low tonnage, before ladle flying and normal continuous casting. During low-tonnage casting, due to the low flow rate of molten steel, the heat transfer loss is large, and the temperature drop is significantly higher than normal continuous casting; the state before ladle flying refers to the retention stage of molten steel while waiting for casting. At this time, due to the long-term stay of molten steel in the ladle, the heat loss is further increased; during normal continuous casting, the molten steel has good fluidity, the heat exchange is relatively stable, and the temperature drop is relatively small. In order to accurately calculate the abnormal temperature drop of the casting machine, the system will collect a large amount of historical furnace data, establish a temperature drop prediction model through a self-learning algorithm, and correct the prediction error in real time. When an abnormal situation is detected, the system can automatically adjust the temperature compensation strategy to ensure that the end temperature of RH refining meets the casting requirements, improve casting stability, and ultimately optimize the temperature control system of the entire production process.

[0069] In some instances, the method further includes: based on big data technology, determining the abnormal deviation of the RH refining end temperature, wherein the abnormal deviation includes abnormal self-learning of the middle ladle temperature, abnormal time deviation, abnormal thermal state of the ladle, abnormal casting sequence, and abnormal deviation of the middle ladle temperature.

[0070] For example, in the process of RH refining end temperature prediction, there are many factors that affect the final temperature accuracy. Therefore, it is necessary to determine the deviation anomaly of RH refining end temperature based on big data technology to ensure the stability and reliability of temperature prediction. Temperature prediction errors may be caused by many factors, such as measurement equipment accuracy, molten steel temperature drop fluctuations, changes in production rhythm, etc. Therefore, it is necessary to establish a deviation anomaly determination system to automatically identify and classify abnormal situations. Among them, the self-learning anomaly of the middle package temperature refers to the significant deviation of the middle package temperature data automatically collected by the system compared with the historical furnace rules after the RH refining is completed. This may be caused by changes in the state of the middle package lining, errors in the temperature measuring equipment, or improper control of the superheat of the steel grade. Through big data analysis, a historical trend model of the middle package temperature can be established. When it is detected that the middle package temperature of a new furnace deviates from the normal range, the system can automatically adjust the temperature drop compensation coefficient to improve the temperature prediction accuracy.

[0071] In addition, abnormal time deviation and abnormal ladle thermal state are key factors affecting the accuracy of RH refining end temperature prediction. Abnormal time deviation refers to the large deviation between the temperature measurement time point and the actual RH refining end time, resulting in temperature drop calculation errors. For example, if the temperature measurement time is advanced or delayed by more than 3 minutes, it may cause a temperature error of more than 5°C. Therefore, it is necessary to establish a temperature measurement time error correction mechanism through data analysis to ensure the timeliness and accuracy of data acquisition. The abnormal thermal state of the ladle mainly involves the use history and current state of the ladle, such as whether the ladle has been fully preheated, whether local lining bricks are damaged or repaired, and whether long-term use has caused a decrease in thermal conductivity. These factors directly affect the temperature drop rate of the ladle. If the thermal state of the ladle does not match the historical data, the system can automatically adjust the ladle temperature drop compensation strategy to ensure the accuracy of the RH refining end temperature.

[0072] In addition to the above abnormal factors, abnormal pouring sequence and abnormal tundish temperature deviation are also important variables affecting the end temperature of RH refining. Abnormal pouring sequence refers to the order of molten steel casting not conforming to the established production rhythm, such as abnormal pauses in the furnace that should be normally poured, or low-tonnage furnaces being inserted into high-tonnage casting plans, resulting in temperature drop calculation deviations. The system can use big data to analyze the pouring change mode and adjust the temperature drop compensation in combination with the real-time casting rhythm. Abnormal tundish temperature deviation refers to different furnaces within the same pouring, where the temperature change of the ladle exceeds the normal process range. For example, if the temperature of the tundish of a furnace is higher or lower than that of the previous and next furnaces by more than 4°C, it may mean that the molten steel temperature control is abnormal, and the system needs to recalibrate the RH refining end temperature prediction model. Through the abnormal judgment method based on big data technology, the stability of the RH refining end temperature can be improved, so that the molten steel temperature is always maintained within a reasonable range, the production process is optimized, the quality of steel is improved, and energy consumption is reduced.

[0073] In some examples, the method further comprises:

[0074] Based on the accuracy of RH refining end temperature, the control strategy of steel grade superheat standard line is optimized.

[0075] For example, in the RH refining process, the superheat of the steel grade is one of the key parameters that affect the precise control of the molten steel temperature and the subsequent casting stability. In order to optimize the temperature control accuracy, it is necessary to optimize the steel grade superheat standard line control strategy based on the accuracy of the RH refining end temperature. The superheat of a steel grade refers to the temperature difference between the actual temperature of the molten steel and the liquidus temperature of the steel grade. The rationality of the superheat control directly affects the fluidity, solidification characteristics and constant pulling speed stability of the molten steel. Due to the different temperature drop characteristics of different steel grades during the RH refining process, their optimal superheat ranges are also different. Therefore, by collecting the RH refining end temperature data of historical furnaces and counting the temperature deviation, the superheat standard lines of different steel grades can be dynamically adjusted. If the RH refining end temperature deviation of a certain steel grade is large and often exceeds the set range, it means that its superheat control strategy needs to be optimized to ensure that the temperature of the molten steel after refining is more accurate.

[0076] In the process of optimizing the superheat standard line of steel grades, it is necessary to combine temperature prediction models, historical data analysis and dynamic adjustment strategies to achieve accurate control of the refining end temperature. First, the system will calculate the temperature prediction deviation of each steel grade based on the statistical data of the RH refining end temperature, and analyze its temperature distribution range. The superheat of steel grades is usually divided into three intervals: upper limit, middle limit and lower limit. If the temperature accuracy of a certain steel grade is high, it means that its current superheat standard line is reasonable and can be maintained as it is; if the RH refining end temperature of a certain steel grade is too high, it is necessary to appropriately lower its superheat upper limit to adjust it to a more reasonable range; conversely, if the RH refining end temperature of a certain steel grade is too low, it is necessary to increase its superheat standard line to compensate for the temperature drop loss. In addition, during the casting process, some special circumstances (such as shutdown, low tonnage casting, etc.) may cause additional temperature drop. Therefore, when optimizing the superheat standard line, the influence of these abnormal factors also needs to be considered.

[0077] In order to continuously optimize the control strategy of the superheat standard line of steel grades, big data analysis and machine learning technology can be introduced to enable the system to automatically adjust the superheat standard line to adapt to the actual production needs of different steel grades. By real-time monitoring of the RH refining end temperature and comparing it with the set standard line, the superheat target value of the steel grade can be dynamically adjusted to keep it within a reasonable range. In addition, during the optimization process, the impact of molten steel temperature on the casting process needs to be considered. For example, if the superheat adjustment causes the fluidity of the molten steel to change during the continuous casting process, it may be necessary to adjust the casting machine pulling speed or the crystallizer cooling intensity synchronously. Finally, through the superheat standard line optimization strategy based on the accuracy of the RH refining end temperature, the accuracy of the RH refining temperature prediction can be improved, the quality risk caused by the molten steel temperature fluctuation can be reduced, and the energy utilization efficiency can be optimized to improve the overall production stability.

[0078] The technical solution of the present application is further described in detail below through specific embodiments.

[0079] like Figure 2 As shown, it is a schematic diagram of the abnormal furnace condition judgment interface of the RH refining end temperature. In this embodiment, the steel grade BQ378016 of the smelting furnace 242B06468 is taken as the research object, the weight of the molten steel is 297 tons, the casting abnormality is before the low tonnage, and the pouring sequence number is 5. First, an expert database of the RH refining temperature model is established based on the metallurgical mechanism, and the calming time is calculated in combination with the pouring change and the casting cycle to correct the RH refining end temperature. Specifically, the liquidus temperature of the steel grade BQ378016 is 1532°C, the superheat is set to 35°C, its casting cycle is 40.5min, and the vacuum cycle is 27min. During the RH treatment process, the vacuum start time is 2:20:53, and the RH refining end time is calculated to be 2:47:53. Subsequently, combined with the pouring change time (2:40:24), the calming time is calculated to be 33.02min. According to this calming time, combined with the calming temperature drop of 22.34℃ and abnormal casting factors, the RH end temperature is calculated, and the final result is 1597℃, including liquidus temperature, superheat, temperature drop during calming time and furnace compensation. The other abnormal temperature drops of the ladle and the casting machine are not involved, so they are not calculated.

[0080] During the actual measurement of the RH end temperature, it was found that the actual RH end temperature of the furnace was 1594°C, with a deviation of only 3°C from the theoretical calculated value, which was less than the set threshold of 5°C. Therefore, it was determined that the temperature control of the furnace was normal and no additional correction was required. At the same time, the accuracy of the RH refining end temperature of this steel grade reached 90%, which is a high-precision temperature-controlled steel grade. Therefore, the superheat standard line of this steel grade was further evaluated. BQ378016 is an ultra-low carbon and low-carbon steel, which usually requires the superheat of the middle package to be controlled at 20 to 35°C. The superheat of this furnace is 35°C, which is in the upper limit range. In the optimization strategy, in order to reduce temperature deviation and improve casting stability, the control target of the superheat standard line of the steel grade is adjusted from the upper limit of 35°C to the middle limit of 30°C to reduce the impact of excessive temperature and improve the stability of the RH end temperature.

[0081] Based on the above adjustments, this embodiment further implements a dynamic optimization strategy. After the implementation of the new superheat standard line, the system continuously collects smelting data and regularly evaluates the accuracy of the end temperature prediction of steel grade BQ378016. Through multiple rounds of iterative optimization, the prediction deviation is gradually reduced to ensure its adaptability and accuracy. With the accumulation of data and optimization iterations, the RH refining end temperature prediction model of this steel grade can be further improved to make it more accurate and less volatile, thereby optimizing the casting process and improving the reliability and production efficiency of molten steel temperature control. Among them, the smelting data includes actual temperature, casting cycle, and abnormal markings; iterative optimization includes recalibrating the temperature drop coefficient and updating the ladle thermal state expert database.

[0082] See also Figure 3 , is a schematic diagram of a device structure for predicting the end temperature of RH refining provided in an embodiment of the present application, comprising:

[0083] The steel grade information acquisition unit 21 is used to acquire the steel grade information corresponding to the molten steel to be refined, wherein the steel grade information includes the liquidus temperature, superheat, casting cycle and vacuum cycle of the steel grade;

[0084] The end time determination unit 22 calculates the RH refining end time based on the vacuum cycle;

[0085] A sedation duration calculation unit 23 calculates the RH sedation duration based on the RH refining end time;

[0086] The end temperature prediction unit 24 calculates the RH refining end temperature based on the RH calming time and the temperature drop parameters to achieve the optimal prediction of the RH refining end temperature, wherein the temperature drop parameters include the temperature drop due to the calming time, the abnormal temperature drop due to the ladle and the abnormal temperature drop due to the casting machine.

[0087] See also Figure 4The embodiment of the present application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any method of the device for predicting the end temperature of refining are implemented.

[0088] Since the electronic device introduced in this embodiment is a device used to implement a prediction device for the refining end temperature in the embodiment of the present application, based on the method introduced in the embodiment of the present application, the technical personnel in this field can understand the specific implementation mode of the electronic device of the present embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by the technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0089] During the specific implementation process, when the computer program 311 is executed by a processor, any implementation method in the embodiments corresponding to the first aspect can be implemented.

[0090] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0091] Those skilled in the art will appreciate that the embodiments of the present application may provide methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0092] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0095] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes Figure 1 The flowchart of a method for predicting the refining end temperature in the corresponding embodiment.

[0096] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. Available media may be magnetic media, (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid state disk (SSD)), etc.

[0097] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0098] In the several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0102] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0103] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0104] Obviously, those skilled in the art can make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if these modifications and modifications of this specification fall within the scope of the claims of this specification and their equivalents, this specification is also intended to include these modifications and modifications.

Claims

1. A method for predicting the end temperature of RH refining, characterized in that: The method comprises: Obtaining steel grade information corresponding to the molten steel to be refined, wherein the steel grade information includes liquidus temperature, superheat, casting cycle and vacuum cycle of the steel grade; Based on the vacuum cycle, calculating the RH refining end time; Based on the RH refining end time, calculating the RH sedation duration; Based on the RH calming time and temperature drop parameters, the RH refining end temperature is calculated to achieve the optimized prediction of the RH refining end temperature, wherein the temperature drop parameters include the temperature drop due to the calming time, the abnormal temperature drop due to the ladle and the abnormal temperature drop due to the casting machine.

2. The method according to claim 1, characterized in that The RH refining end time is determined based on the following formula, expressed as: RH refining end time = vacuum start time + vacuum cycle.

3. The method according to claim 1, characterized in that The RH sedation duration is determined based on the following formula, expressed as: RH calming time = pouring change time + casting cycle - RH refining end time.

4. The method according to claim 1, characterized in that: The RH refining end temperature is determined based on the following formula, expressed as: RH refining end temperature = liquidus temperature + superheat + temperature drop parameter + furnace compensation.

5. The method according to claim 1, characterized in that: The specific steps of obtaining the temperature drop parameter include: Based on the ladle thermal state, a ladle temperature drop expert database is established, and according to the ladle thermal state type, the abnormal ladle temperature drop is calculated, wherein the ladle thermal state type includes baking ladle, minor repair ladle and normal ladle; Calculate the temperature drop during the cooling time based on the cooling time and the temperature drop coefficient of the steel grade; Based on the abnormal conditions of the casting machine, the abnormal temperature drop of the casting machine is calculated, wherein the abnormal conditions of the casting machine include low tonnage, before ladle flying and normal continuous casting, and the abnormal temperature drop of the casting machine is obtained through self-learning of historical data.

6. The method according to claim 1, characterized in that The method further comprises: Based on big data technology, the deviation abnormality of the RH refining end temperature is judged, wherein the deviation abnormality includes the self-learning abnormality of the tundish temperature, the time deviation abnormality, the thermal state abnormality of the ladle, the casting sequence abnormality, and the tundish temperature deviation abnormality.

7. The method according to claim 1, characterized in that The method further comprises: Based on the accuracy of RH refining end temperature, the control strategy of steel grade superheat standard line is optimized.

8. A device for predicting the end temperature of RH refining, characterized in that: include: A steel grade information acquisition unit, used to acquire steel grade information corresponding to the molten steel to be refined, wherein the steel grade information includes liquidus temperature, superheat, casting cycle and vacuum cycle of the steel grade; an end time determination unit, which calculates the RH refining end time based on the vacuum cycle; a sedation duration calculation unit, which calculates the RH sedation duration based on the RH refining end time; The end temperature prediction unit calculates the RH refining end temperature based on the RH calming time and temperature drop parameters to achieve the optimized prediction of the RH refining end temperature, wherein the temperature drop parameters include the temperature drop due to the calming time, the abnormal temperature drop due to the ladle and the abnormal temperature drop due to the casting machine.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the method for predicting the RH refining end temperature according to any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the RH refining end temperature according to any one of claims 1 to 7 is implemented.

Images