Method, device, equipment and medium for determining addition amount of in-furnace refining agent

Abstract

This application relates to the field of data processing, and in particular, to a method, device, equipment and medium for determining the addition amount of in-furnace refining agent. The method includes: By collecting various data during the refining process (such as the addition amount of the refining agent, basic data, stirring intensity, furnace temperature) and environmental humidity, and based on the basic data of the refining agent (particle size, surface roughness, category), stirring intensity and furnace temperature, it is possible to evaluate the natural adhesion situation of the refining agent during the refining process, that is, the first adhesion rate. Further, by considering the influence of environmental humidity on the adhesion situation of the refining agent, the second adhesion rate is determined accordingly, enhancing the practicability and accuracy of the method. By comprehensively considering the first adhesion rate and the second adhesion rate, the adjustment amount of the refining agent is calculated, and the actual addition amount of the refining agent is determined accordingly, thus ensuring the accuracy and rationality of the addition amount of the refining agent, and helping to improve the refining effect and product quality.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular, to a method, device, equipment, and medium for determining the addition amount of in-furnace refining agent. Background Art

[0002] The metallurgical industry is an important part of modern manufacturing. Especially in steel production, in-furnace refining technology is of great significance for improving product quality and reducing energy consumption. With the progress of technology, the in-furnace refining process has been continuously optimized, and it has become an industry consensus to improve the purity and performance of metal materials by precisely controlling various parameters. The reasonable use of refining agent is one of the key factors to achieve this goal. Reasonable addition of refining agent can not only effectively remove impurities, but also improve the distribution of alloy components, thereby improving the quality and performance of the final product.

[0003] During the melting process of aluminum alloy, refining agent is added to the refining machine. Generally, the refining agent is in powder form. Due to reasons such as the temperature in the furnace and the reaction process in the furnace, part of the refining agent will adhere to the inner wall of the refining machine, resulting in a decrease in the actual mass of the refining agent participating in the reaction, and causing consequences such as insufficient refining reaction. In actual operation, in order to ensure the effectiveness and stability of the refining process, it usually relies on experienced operators to manually adjust the addition amount of the refining agent. However, the method of relying on operators to manually adjust the addition amount has a large error, and there may be situations where the refining agent is excessive or insufficient, which will affect the quality stability and production efficiency of the final product. Summary of the Invention

[0004] In order to improve the accuracy of the quality of the in-furnace refining agent added to the refining machine, the present application provides a method, device, equipment, and medium for determining the addition amount of in-furnace refining agent.

[0005] In the first aspect, the present application provides a method for determining the addition amount of in-furnace refining agent, adopting the following technical solution:

[0006] A method for determining the addition amount of in-furnace refining agent includes:

[0007] Obtain the refining information corresponding to the current refining process, and obtain the environmental humidity. The refining information includes the addition amount situation of the refining agent, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace. The addition amount situation includes the mass of the refining agent to be added at each moment during the refining process. The basic data of the refining agent includes the particle size of the refining agent, the surface roughness of the refining agent, and the type of the refining agent;

[0008] Based on the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace, determine the first adhesion rate of the refining agent;

[0009] Determine the influence degree of the environmental humidity on the refining agent, and based on the influence degree, determine the second adhesion rate of the refining agent;

[0010] Based on the first adhesion rate and the second adhesion rate, calculate the adjustment amount corresponding to the refining agent, and determine the actual addition amount of the refining agent based on the adjustment amount.

[0011] By adopting the above technical solution, by collecting various data in the refining process (such as the addition amount of the refining agent, basic data, stirring intensity, furnace temperature) and environmental humidity, and based on the basic data of the refining agent (particle size, surface roughness, category), stirring intensity and furnace temperature, the natural adhesion situation of the refining agent in the refining process, that is, the first adhesion rate, can be evaluated. Further, by considering the influence of environmental humidity on the adhesion situation of the refining agent and determining the second adhesion rate accordingly, the practicability and accuracy of the method are enhanced. By comprehensively considering the first adhesion rate and the second adhesion rate, the adjustment amount of the refining agent is calculated, and the actual addition amount of the refining agent is determined accordingly, thus ensuring the accuracy and rationality of the addition amount of the refining agent, and helping to improve the refining effect and product quality.

[0012] In a possible implementation manner, determining the first adhesion rate of the refining agent based on the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace includes:

[0013] Obtain the historical refining data corresponding to the refining agent, and determine the activation energy corresponding to the current refining process. The historical refining data includes the historical refining information and historical adhesion rate corresponding to each historical refining process;

[0014] According to the form of the Arrhenius equation, construct a temperature model including a temperature exponential term, and the temperature model is used to describe the relationship between temperature and adhesion rate;

[0015] Optimize the temperature model based on the historical refining data to obtain a target temperature model, where the target temperature model is A is a model parameter, E is the activation energy, R is the ideal gas constant, and T is the absolute temperature corresponding to the historical temperature;

[0016] Based on the target temperature model, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace, determine the first adhesion rate of the refining agent.

[0017] By adopting the above technical solution, historical refining data corresponding to the refiner is obtained, including historical refining information (such as refining agent type, particle size, stirring intensity, etc.) and historical adhesion rate of each historical refining process. During the current refining process, the corresponding activation energy is determined, and according to the form of the Arrhenius equation, a temperature model including a temperature exponential term is constructed to clarify the relationship between temperature and adhesion rate in the form of a mathematical expression, and the temperature model is optimized based on the historical refining data to obtain the target temperature model. Combining the target temperature model, the basic data of the refining agent, the refining stirring intensity, and the current temperature in the refining furnace, the first adhesion rate of the refining agent is comprehensively calculated, realizing the accurate prediction of the adhesion of the refining agent.

[0018] In a possible implementation manner, determining the first adhesion rate of the refining agent based on the target temperature model, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace includes:

[0019] Calculating the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity; substituting the target temperature model into Formula 1 to obtain Formula 2, where Formula 1 is A1 is the first adhesion rate, k is the comprehensive correction coefficient, S is the surface roughness of the refining agent, T is the temperature in the refining furnace, a is the temperature influence index, G is the particle size of the refining agent, b is the particle size influence index, I is the refining stirring intensity, c is the stirring intensity influence index, and Formula 2 is

[0020] Substitute the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace into Formula 2 to calculate the first adhesion rate of the refining agent.

[0021] By adopting the above technical solution, according to the particle size and stirring intensity of the refining agent, the particle size influence index and the stirring intensity influence index are respectively calculated. Based on the existing Formula 1, by substituting the target temperature model, Formula 2 including the comprehensive correction coefficient, the temperature influence index, the particle size influence index, and the stirring intensity influence index is obtained. Substitute the basic data of the refining agent, the stirring intensity, and the temperature in the furnace into Formula 2, and the first adhesion rate of the refining agent is calculated through calculation, thus realizing the accurate quantification of the adhesion behavior of the refining agent.

[0022] In a possible implementation manner, calculating the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity includes:

[0023] Filter out the first historical sub - data that meets the first preset condition and the second historical sub - data that meets the second preset condition from the historical refined data to obtain the first historical sequence and the second historical sequence. The first preset condition is that the corresponding feature values of any first feature in the first target feature are the same in each corresponding historical refining process. The first feature is any one of the addition amount of the historical refining agent, the surface characteristics of the historical refining agent, the category of the historical refining agent, the historical refining stirring intensity, and the temperature in the historical refining furnace. The second preset condition is that the corresponding feature values of any second feature in the second target feature are the same in each corresponding historical refining process. The second feature is any one of the addition amount of the historical refining agent, the surface characteristics of the historical refining agent, the category of the historical refining agent, the particle size of the historical refining agent, and the temperature in the historical refining furnace;

[0024] Establish the first curve corresponding to the first historical sequence and the second curve corresponding to the second historical sequence;

[0025] Based on the first curve and the second curve, determine the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity.

[0026] By adopting the above - mentioned technical solution, by setting the first preset condition and the second preset condition, filter out the data subsets that meet specific conditions from the historical refined data, and construct the first historical sequence and the second historical sequence respectively, so that the feature values in each sequence are consistent, which is convenient for observing and analyzing the influence of particle size and stirring intensity on the adhesion behavior of the refining agent. Use the filtered data to construct the first curve and the second curve. Based on the drawn first curve and second curve, determine the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity, so as to accurately quantify the influence degree of particle size and stirring intensity on the adhesion behavior of the refining agent.

[0027] In a possible implementation manner, the historical refined data includes the historical environmental humidity. Determining the influence degree of the environmental humidity on the refining agent includes:

[0028] Perform time - domain analysis and frequency - domain analysis on the historical refined data to obtain the humidity time - domain function relationship corresponding to the refining agent and the frequency - domain feature vector matrix;

[0029] Based on the humidity time - domain function relationship, predict the first change curve corresponding to the current refining process. The first change curve is the curve of environmental humidity changing with time;

[0030] Input the frequency - domain feature vector matrix and the basic data of the refining agent into the recurrent network model, and obtain the second change curve output by the recurrent network model. The second change curve is the curve of the influence degree changing with the environmental humidity;

[0031] Based on the first change curve and the second change curve, determine the influence degree of the environmental humidity on the refining agent.

[0032] By adopting the above technical solution, by deeply analyzing the time characteristics and frequency characteristics of the data, performing time-domain analysis and frequency-domain analysis on the historical refining data, obtaining the humidity time-domain function relationship and frequency-domain feature vector matrix corresponding to the refining agent, and based on the humidity time-domain function relationship, predicting the first change curve corresponding to the current refining process, that is, the curve of the environmental humidity changing with time. Then, by introducing an advanced machine learning model, inputting the frequency-domain feature vector matrix and the basic data of the refining agent into the recurrent network model, and obtaining the second change curve output by the model, that is, the curve of the influence degree changing with the environmental humidity, based on the first change curve and the second change curve, the influence degree of the environmental humidity on the refining agent is determined, providing strong data support for the optimization of the refining process.

[0033] In a possible implementation manner, based on the influence degree, determining the second adhesion rate of the refining agent includes:

[0034] Based on the second change curve, determine the historical influence degree corresponding to the environmental humidity in each historical refining process, and calculate the historical first adhesion rate corresponding to each historical refining process;

[0035] Based on the historical first adhesion rate, the historical adhesion rate, and the historical influence degree in each historical refining process, determine the influence coefficient corresponding to the influence degree;

[0036] Based on the influence coefficient and the influence degree, determine the second adhesion rate of the refining agent.

[0037] By adopting the above technical solution, based on the second change curve (that is, the curve of the influence degree changing with the environmental humidity), the historical influence degree corresponding to the environmental humidity in each historical refining process is determined. At the same time, the historical first adhesion rate corresponding to each historical refining process is calculated. Based on the historical first adhesion rate, the historical adhesion rate, and the historical influence degree in each historical refining process, by methods such as data fitting or regression analysis, a quantitative relationship between the influence degree and the adhesion rate, that is, the influence coefficient, is established, and based on the influence coefficient and the influence degree, the second adhesion rate of the refining agent is determined.

[0038] In a possible implementation manner, based on the first adhesion rate and the second adhesion rate, calculating the adjustment amount corresponding to the refining agent includes:

[0039] Based on the above addition amount situation, analyze the reaction process, diffusion process, and adhesion process of the refining agent respectively, calculate the corresponding reaction rate coefficient, diffusion coefficient, and proportionality coefficient of the refining agent, and establish a physical model corresponding to the refining agent;

[0040] Determine the proportionality coefficient based on the physical model, and the proportionality coefficient is used to correct the gap between the actual adhesion situation of the refining agent in the refining process and the result calculated solely based on the adhesion rate;

[0041] Substitute the mass of the refining agent to be added at each moment, the first adhesion rate, and the second adhesion rate into Formula 3 to obtain the adjustment amount corresponding to the refining agent. Formula 3 is Δm = m0 * (A1 + A2) * (1 + kt), where Δm is the adjustment amount, m0 is the mass of the refining agent, A1 is the first adhesion rate, A2 is the second adhesion rate, k is the proportionality coefficient, and t is the duration of adding the refining agent.

[0042] By adopting the above technical solution, the reaction process, diffusion process, and adhesion process are deeply analyzed, and accordingly, the reaction rate coefficient, diffusion coefficient, and proportionality coefficient are calculated. The proportionality coefficient is determined using the physical model, thereby correcting the gap between the actual adhesion situation of the refining agent in the refining process and the result calculated solely based on the adhesion rate, effectively improving the accuracy and reliability of the calculation result. The mass of the refining agent to be added at each moment, the first adhesion rate, and the second adhesion rate are substituted into Formula 3 to calculate the adjustment amount corresponding to the refining agent.

[0043] In a second aspect, the present application provides a device for determining the addition amount of the in-furnace refining agent, adopting the following technical solution:

[0044] A device for determining the addition amount of the in-furnace refining agent includes:

[0045] An acquisition module, configured to acquire the refining information corresponding to the current refining process and acquire the environmental humidity. The refining information includes the addition amount situation of the refining agent, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace. The addition amount situation includes the mass of the refining agent to be added at each moment during the refining process. The basic data of the refining agent includes the particle size of the refining agent, the surface roughness of the refining agent, and the type of the refining agent;

[0046] A first determination module, configured to determine the first adhesion rate of the refining agent based on the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace;

[0047] A second determination module, configured to determine the influence degree of the environmental humidity on the refining agent and determine the second adhesion rate of the refining agent based on the influence degree;

[0048] A calculation module, configured to calculate an adjustment amount corresponding to the refining agent based on the first adhesion rate and the second adhesion rate, and determine an actual addition amount of the refining agent based on the adjustment amount.

[0049] In a third aspect, the present application provides an electronic device, adopting the following technical solution:

[0050] An electronic device, comprising:

[0051] At least one processor;

[0052] A memory;

[0053] At least one application program, wherein at least one application program is stored in the memory and configured to be executed by at least one processor, and the at least one application program is configured to: execute the method for determining the addition amount of the in-furnace refining agent described in the first aspect above.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium, adopting the following technical solution:

[0055] A computer-readable storage medium, comprising: a computer program stored therein that can be loaded and executed by a processor to execute the method for determining the addition amount of the in-furnace refining agent described in the first aspect above.

[0056] In summary, the present application includes the following beneficial technical effects:

[0057] By collecting various data during the refining process (such as the addition amount of the refining agent, basic data, stirring intensity, in-furnace temperature) and the environmental humidity, and based on the basic data of the refining agent (particle size, surface roughness, category), stirring intensity, and in-furnace temperature, the natural adhesion situation of the refining agent during the refining process, that is, the first adhesion rate, can be evaluated. Further, by considering the influence of environmental humidity on the adhesion situation of the refining agent and determining the second adhesion rate accordingly, the practicability and accuracy of the method are enhanced. By comprehensively considering the first adhesion rate and the second adhesion rate, the adjustment amount of the refining agent is calculated, and the actual addition amount of the refining agent is determined accordingly, thereby ensuring the accuracy and rationality of the addition amount of the refining agent, and contributing to improving the refining effect and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is a schematic flowchart of a method for determining the addition amount of an in-furnace refining agent provided by an embodiment of the present application;

[0059] Figure 2 is a schematic block diagram of a device for determining the addition amount of an in-furnace refining agent provided by an embodiment of the present application;

[0060] Figure 3 is a schematic diagram of an electronic device provided by an embodiment of the present application. Specific embodiments

[0061] The following will further describe the present application in detail with reference to the Figure 1 - attached Figure 3 drawings.

[0062] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0063] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0064] In addition, the term "and / or" in this document is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0065] The embodiment of the present application provides a method for determining the addition amount of in-furnace refining agent. As Figure 1 shown, the method provided in the embodiment of the present application is executed by an electronic device, which can be a server or a terminal device. Among them, the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected through wired or wireless communication methods. The embodiment of the present application does not limit this. The method includes steps S101-step S104, where: Step S101, obtain the refining information corresponding to the current refining process and obtain the environmental humidity.

[0066] Among them, the refined information includes the addition amount of the refining agent, the basic data of the refining agent, the refining stirring intensity, and the temperature inside the refining furnace. The addition amount includes the mass of the refining agent to be added at each moment during the refining process. The basic data of the refining agent includes the particle size of the refining agent, the surface roughness of the refining agent, and the type of the refining agent. During the refining process, in order to ensure the refining quality and improve the production efficiency, generally, a refining plan corresponding to this refining process will be formulated before the start of the refining. The refining plan includes the refining agent required for the refining process, the mass of the refining agent to be added at each moment, the stirring intensity inside the refiner at each moment, and the temperature required to be reached inside the refiner at each moment, and this refining plan is stored in the database corresponding to the refiner.

[0067] Specifically, the electronic device is connected to the refiner and reads the content in the database corresponding to the refiner in real time. More specifically, obtain the refining plan corresponding to the current refining process from the database corresponding to the refiner, and obtain the addition amount of the refining agent, the refining stirring intensity, and the temperature inside the refining furnace from this refining plan, and obtain the refining agent required for the current refining process from the database corresponding to the refiner, and obtain the basic data of the refining agent corresponding to this refining agent from the database corresponding to the refiner. Among them, the operator can use a laser particle size analyzer to measure the particle size of each refining agent and upload it to the database. Similarly, the operator can use a surface roughness measuring instrument to measure the surface roughness of the refining agent and upload it to the database.

[0068] More specifically, the temperature inside the refining furnace can also be collected in real time by temperature sensors such as thermocouples installed in the furnace and transmitted to the electronic device. The environmental humidity can be obtained by humidity sensors installed in the refining workshop, and the sensors transmit the humidity data to the electronic device in real time. The electronic device receives the temperature inside the refining furnace and the environmental humidity data. It should be noted that any of the above methods can be used to obtain the temperature inside the refining furnace, and the embodiments of the present application do not limit this.

[0069] Step S102: Determine the first adhesion rate of the refining agent based on the basic data of the refining agent, the refining stirring intensity, and the temperature inside the refining furnace.

[0070] Among them, the first adhesion rate is the proportion of the refining agent adhering to the surface of the substances inside the furnace determined based on factors such as the characteristics of the refining agent itself, the stirring intensity, and the temperature inside the furnace, which reflects the adhesion degree of the refining agent under normal conditions.

[0071] In this embodiment, determining the first adhesion rate of the refining agent based on the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace includes: obtaining the historical refining data corresponding to the refiner and determining the activation energy corresponding to the current refining process. The historical refining data includes the historical refining information and the historical adhesion rate corresponding to each historical refining process; constructing a temperature model including a temperature exponential term according to the form of the Arrhenius equation, where the temperature model is used to describe the relationship between temperature and the adhesion rate; optimizing the temperature model based on the historical refining data to obtain a target temperature model, where the target temperature model is A is a model parameter, E is the activation energy, R is the ideal gas constant, and T is the absolute temperature corresponding to the historical temperature; determining the first adhesion rate of the refining agent based on the target temperature model, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace.

[0072] The refining data corresponding to each refining process of the refiner is recorded in the database. For the historical adhesion rate corresponding to each historical refining process, the weighing mass of the attachments on the refiner before and after the completion of each refining can be obtained from the database corresponding to the refiner, and the difference between the two weighing masses can be calculated. The initial mass of the refining agent before the start of refining is obtained, and the historical adhesion rate can be obtained by dividing the difference by the initial mass.

[0073] Further, the electronic device obtains the historical refining data corresponding to the refiner from the database corresponding to the refiner and obtains the activation energy corresponding to the refining agent from the activation energy database; if no exactly matching data is found, the interpolation method or a machine learning algorithm (such as a neural network) can be used to predict the activation energy of the current refining process based on the existing data. Specifically, when no exactly matching data is found in the activation energy database, samples with similar compositions to the current refining agent can be obtained from the activation energy database, and the sample activation energy corresponding to each sample can be obtained. The characteristic values (either the particle size of the refining agent or the surface roughness of the refining agent) corresponding to each sample and the current refining agent are obtained, and the linear interpolation formula is used: the activation energy in the current refining process = the activation energy of the first sample + (the characteristic value corresponding to the current refining agent - the characteristic value of the first sample) / (the characteristic value of the second sample - the characteristic value of the first sample) * (the activation energy of the second sample - the activation energy of the first sample) to calculate the activation energy of the current refining process. Among them, the activation energy database is established by recording the reaction data (reaction rate, temperature change, etc.) of each refining agent sample in a large number of experiments, fitting and analyzing the data according to the Arrhenius equation, and calculating the activation energy of each sample. The basic data (category, composition, etc.) of the refining agent and the corresponding activation energy values are stored in association in the activation energy database.

[0074] Further, after obtaining the activation energy corresponding to the current refining process, a temperature model can be established based on the Arrhenius equation to obtain the relationship between the temperature in the refining furnace and the adhesion rate. Specifically, based on the Arrhenius equation for modeling, and converting the temperature in the refining furnace into absolute temperature, so as to introduce the absolute temperature, activation energy, and ideal gas constant into the above model, and construct a function containing the temperature exponential term , that is, the temperature model. Among them, K represents the reaction rate constant, A is the model parameter, E is the activation energy, R is the ideal gas constant, and T is the absolute temperature.

[0075] Further, convert the historical temperature in the refining furnace in the historical refining data into historical absolute temperature, and use the historical absolute temperature, historical activation energy, historical refining stirring intensity, and historical basic data of the refining agent corresponding to each historical refining process as inputs, and use the historical adhesion rate corresponding to each historical refining process as the output. Then, use an optimization algorithm (such as the least squares method, gradient descent method, etc.) to adjust the model parameters in the temperature model, and continuously iterate and calculate to minimize the error between the adhesion rate predicted by the model and the historical adhesion rate. After multiple iterations and optimizations, a set of optimal model parameter values is obtained. Substitute these model parameters into the temperature model to obtain the target temperature model.

[0076] After obtaining the target temperature model, the first adhesion rate of the refining agent can be determined based on the target temperature model, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace.

[0077] In this embodiment, determining the first adhesion rate of the refining agent based on the target temperature model, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace includes: calculating the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity; substituting the target temperature model into Formula 1 to obtain Formula 2, where Formula 1 is A1 is the first adhesion rate, k is the comprehensive correction coefficient, S is the surface roughness of the refining agent, T is the temperature in the refining furnace, a is the temperature influence index, G is the particle size of the refining agent, b is the particle size influence index, I is the refining stirring intensity, c is the stirring intensity influence index, and Formula 2 is Substitute the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace into Formula 2 to calculate the first adhesion rate of the refining agent.

[0078] Among them, the particle size influence index is a value used to measure the influence degree of the particle size of the refining agent on its adhesion rate. Different particle sizes will lead to different dispersion degrees of the refining agent in the furnace and different contact areas with the substances in the furnace, thereby affecting the adhesion rate.

[0079] The stirring intensity influence index is an index used to represent the degree of influence of the refining stirring intensity on the adhesion rate of the refining agent. Different stirring intensities will affect the distribution uniformity of the refining agent in the furnace and the contact frequency with the substances in the furnace.

[0080] In this embodiment, calculating the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity includes: screening out the first historical sub-data that meet the first preset condition and the second historical sub-data that meet the second preset condition from the historical refining data to obtain the first historical sequence and the second historical sequence. The first preset condition is that the characteristic values corresponding to any one of the first features in the first target feature are the same in each corresponding historical refining process. The first feature is any one of the historical refining agent addition amount situation, historical refining agent surface characteristics, historical refining agent category, historical refining stirring intensity, and historical refining furnace temperature. The second preset condition is that the characteristic values corresponding to any one of the second features in the second target feature are the same in each corresponding historical refining process. The second feature is any one of the historical refining agent addition amount situation, historical refining agent surface characteristics, historical refining agent category, historical refining agent particle size, and historical refining furnace temperature; establishing the first curve corresponding to the first historical sequence and the second curve corresponding to the second historical sequence; based on the first curve and the second curve, determining the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity.

[0081] Specifically, traverse the historical refining data. For each first feature in the first target feature (historical refining agent addition amount situation, historical refining agent surface characteristics, historical refining agent category, historical refining stirring intensity, and historical refining furnace temperature), check the characteristic value of this feature in each historical refining process. If the characteristic values of each first feature are the same in each corresponding historical refining process, then screen out these historical refining data that meet the conditions to form the first historical sub-data. For example, if the historical refining stirring intensity is selected as the first feature, screen out the data records with the same stirring intensity characteristic value in all historical refining processes, and then screen out the data records with the same historical refining agent addition amount situation from the data records with the same historical refining stirring intensity, and so on, to obtain the first historical sub-data with the same characteristic value of each first feature in each corresponding historical refining process, and organize all the first historical sub-data into the first historical sequence.

[0082] Similarly, check each second feature in the second target feature (historical refining agent addition amount situation, historical refining agent surface characteristics, historical refining agent category, historical refining agent particle size, and historical refining furnace temperature). When the characteristic values of each second feature are consistent in each corresponding historical refining process, screen out these data as the second historical sub-data, and organize the second historical sub-data into the second historical sequence.

[0083] Further, extract data pairs related to particle size and adhesion rate from the first historical sequence. Assume that the first historical sequence records the corresponding refining agent adhesion rates at different particle sizes, with the particle size as the horizontal axis and the adhesion rate as the vertical axis. Then, use a data fitting algorithm (such as polynomial fitting, linear fitting, etc.) to fit these data points to obtain a curve that can reflect the relationship between particle size and adhesion rate, i.e., the first curve. Similarly, extract data pairs related to stirring intensity and adhesion rate from the second historical sequence, with the stirring intensity as the horizontal axis and the adhesion rate as the vertical axis, and also use a data fitting algorithm to fit these data points to obtain a second curve that reflects the relationship between stirring intensity and adhesion rate.

[0084] Furthermore, since the particle size influence index reflects the degree of influence of particle size change on the adhesion rate, and the slope of the curve can reflect this change relationship, a derivative method can be used to perform mathematical analysis on the first curve. Specifically, take the derivative of the first curve, and the obtained derivative can be used as the particle size influence index. Similarly, the stirring intensity influence index reflects the degree of influence of stirring intensity change on the adhesion rate. Therefore, the slope of the curve can be obtained by taking the derivative. Specifically, perform a derivative operation on the second curve, and the obtained derivative can be used as the stirring intensity influence index.

[0085] Further, traverse the historical refining data. For each of the third target features (the addition amount of the historical refining agent, the surface characteristics of the historical refining agent, the type of the historical refining agent, the particle size of the historical refining agent, and the historical refining stirring intensity), check the feature values of this feature in each historical refining process. If the feature values of each third feature are the same in each corresponding historical refining process, then screen out these historical refining data that meet the conditions to form the third historical sub-data. Use a data fitting algorithm (such as polynomial fitting, linear fitting, etc.) to fit these data points to obtain a curve that can reflect the relationship between particle size and adhesion rate, i.e., the third curve, and take the derivative within the third curve. The obtained derivative can be used as the temperature influence index.

[0086] After obtaining the particle size influence index and the stirring intensity influence degree index, the target temperature model can be stored as an executable code expression. Then, implement Formula 1 in the code, substitute the target temperature model into the temperature-related part of Formula 1, so as to obtain Formula 2. Specifically, since temperature not only affects the chemical reaction rate, but may also affect the physical adsorption of the refining agent, the fluidity of the melt, the interfacial tension, etc., and these physical mechanisms cannot be directly described by the Arrhenius equation. Therefore, substitute Substitute into to obtain Formula 2 as Substitute the temperature influence index, particle size influence index, stirring intensity influence index, basic data of the refining agent, refining stirring intensity, and the temperature in the refining furnace into Equation 2 to calculate the first adhesion rate of the refining agent. Among them, k can be set according to experiments or actual situations, and this application embodiment does not limit it.

[0087] Step S103: Determine the influence degree of environmental humidity on the refining agent, and based on the influence degree, determine the second adhesion rate of the refining agent.

[0088] Among them, the second adhesion rate is the proportion of the refining agent adhering to the surface of the substances in the furnace under the influence of humidity.

[0089] In this embodiment, when the historical refining data includes the historical environmental humidity, determining the influence degree of environmental humidity on the refining agent includes: performing time-domain analysis and frequency-domain analysis on the historical refining data to obtain the humidity time-domain function relationship and frequency-domain feature vector matrix corresponding to the refining agent; based on the humidity time-domain function relationship, predicting the first change curve corresponding to the current refining process, and the first change curve is the curve of environmental humidity changing with time; inputting the frequency-domain feature vector matrix and the basic data of the refining agent into the recurrent network model, and obtaining the second change curve output by the recurrent network model, and the second change curve is the curve of the influence degree changing with environmental humidity; based on the first change curve and the second change curve, determining the influence degree of environmental humidity on the refining agent.

[0090] Extract the historical environmental humidity data and the corresponding timestamp information from the database corresponding to the refiner, and arrange these data in chronological order to construct a humidity-time series. Then use time-domain analysis methods, such as the moving average method, autoregressive integrated moving average model (ARIMA), etc., to fit the humidity-time series to obtain a humidity time-domain function relationship that can describe the law of humidity changing with time. And perform Fourier transform on the humidity-time series, and convert the time-domain signal to the frequency domain through Fourier transform to obtain the amplitude and phase information of different frequency components. Organize this information into a frequency-domain feature vector matrix, and each row of this matrix can represent a feature vector at a specific frequency, including amplitude and phase information.

[0091] Further, according to the obtained humidity time-domain function relationship, combined with the start time information of the current refining process, the forecast method in the ARIMA model can be used to input the predicted time range (the time period starting from the current refining process) to obtain the predicted values of environmental humidity over time. Arrange these predicted values in chronological order and draw the first change curve, which shows the change of environmental humidity over time during the current refining process. Among them, the ARIMA model is trained with a large number of historical sample data.

[0092] Furthermore, preprocess the obtained frequency-domain feature vector matrix and the basic data of the refining agent (such as the particle size of the refining agent, surface roughness, category, etc.) and convert them into a format suitable for input to the recurrent network model. For example, normalize the basic data of the refining agent so that its numerical range is between 0 and 1. Then, input the frequency-domain feature vector matrix and the basic data of the refining agent in the current refining process into the trained recurrent network model, and this recurrent network model will output the predicted values of the influence degree corresponding to different environmental humidities. Combine these predicted values with the corresponding environmental humidity values to draw a second change curve, which represents the change of the influence degree with the environmental humidity. Among them, use historical data (including the frequency-domain feature vector matrix, the basic data of the refining agent, and the corresponding influence degree data) to train the recurrent network model (such as the long short-term memory network LSTM or the gated recurrent unit GRU), and use the backpropagation algorithm to adjust the weights of the model to minimize the error between the influence degree predicted by the model and the actual influence degree.

[0093] Furthermore, correlate the first change curve and the second change curve. For the environmental humidity value corresponding to each time point on the first change curve, find the corresponding influence degree value on the second change curve. Specifically, if there is no exactly matching environmental humidity value on the second change curve, linear interpolation can be used with adjacent points to obtain an approximate influence degree value. Record the influence degree value corresponding to each time point, so as to determine the change of the influence degree of environmental humidity on the refining agent over time during the entire current refining process.

[0094] In this embodiment, based on the influence degree, determine the second adhesion rate of the refining agent, including: determining the historical influence degree corresponding to the environmental humidity in each historical refining process based on the second change curve, and calculating the historical first adhesion rate corresponding to each historical refining process; determining the influence coefficient corresponding to the influence degree based on the historical first adhesion rate, historical adhesion rate, and historical influence degree in each historical refining process; determining the second adhesion rate of the refining agent based on the influence coefficient and the influence degree.

[0095] Among them, the influence coefficient is used to reflect the proportional relationship between the influence degree of environmental humidity and the change of the adhesion rate.

[0096] Extract the environmental humidity value corresponding to each historical refining process from the historical refined data, and find the corresponding degree of influence of these environmental humidity values on the second change curve (the curve of the degree of influence changing with the environmental humidity). If there is no exactly matching environmental humidity value on the second change curve, interpolation methods (such as linear interpolation) can be used to estimate the corresponding historical degree of influence. For each historical refining process, according to the above method (the method for determining the first adhesion rate based on the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace), substitute the corresponding data (historical basic data of the refining agent, historical refining stirring intensity, historical temperature in the refining furnace) in this historical refining process into the relevant formulas such as the target temperature model, and calculate the historical first adhesion rate corresponding to each historical refining process.

[0097] Further, the least squares method can be used to determine the influence coefficient. Specifically, for the i-th historical refining process among multiple historical refining processes, the historical first adhesion rate is A 1i , the historical adhesion rate is A hi , the historical degree of influence is I i , determine the relationship between the historical adhesion rate, the historical first adhesion rate, and the historical degree of influence as A hi = A 1i + α * I i , and substitute the data (A hi , A 1i , I i ) in each historical refining process into the above relationship to construct the error function as where n is the number of historical refining processes. Further, take the derivative of the error function E(α), and calculate the derivative to be 0 to solve for the α value that minimizes the error function. This α value is the influence coefficient corresponding to the degree of influence.

[0098] Even further, based on the already calculated degree of influence of the environmental humidity on the refining agent in the current refining process and the determined influence coefficient, use the formula: the second adhesion rate = the influence coefficient * the degree of influence to calculate the second adhesion rate of the refining agent.

[0099] Step S104: Calculate the adjustment amount corresponding to the refining agent based on the first adhesion rate and the second adhesion rate, and determine the actual addition amount of the refining agent based on the adjustment amount.

[0100] After obtaining the first adhesion rate and the second adhesion rate, the mass of the refining agent adhering to the inner wall of the refining machine can be calculated based on the first adhesion rate and the second adhesion rate, and then the adjustment amount of the refining agent can be obtained according to this mass to determine the actual addition amount of the refining agent. Specifically, the sum of the second adhesion rate and the first adhesion rate can be calculated, and then multiplied by the mass of the refining agent planned to be added at the current moment to obtain the adjustment amount of the refining agent. For example, if the first adhesion rate is 10%, the second adhesion rate is 5%, and the mass of the refining agent planned to be added at the current moment is 100 kg, then the adjustment amount = 100×(5% + 10%) = 15 kg. If the adjustment amount is positive, it means that the addition amount of the refining agent needs to be reduced; if it is negative, it means that the addition amount needs to be increased. Add the adjustment amount to the mass of the refining agent planned to be added at the current moment to obtain the actual addition amount. That is, the actual addition amount = the planned addition amount at the current moment + the adjustment amount. In the above example, the actual addition amount = 100 + 15 = 115 kg.

[0101] In this embodiment, calculating the adjustment amount corresponding to the refining agent based on the first adhesion rate and the second adhesion rate includes: analyzing the reaction process, diffusion process, and adhesion process of the refining agent respectively according to the addition amount situation, and calculating the reaction rate coefficient, diffusion coefficient, and proportionality coefficient corresponding to the refining agent, and establishing a physical model corresponding to the refining agent; determining the proportionality coefficient based on the physical model, and the proportionality coefficient is used to correct the gap between the actual adhesion situation of the refining agent in the refining process and the result calculated simply based on the adhesion rate; substituting the mass of the refining agent to be added at each moment, the first adhesion rate, and the second adhesion rate into Equation 3 to obtain the adjustment amount corresponding to the refining agent. Equation 3 is Δm = m0*(A1 + A2)*(1 + kt), where Δm is the adjustment amount, m0 is the mass of the refining agent, A1 is the first adhesion rate, A2 is the second adhesion rate, k is the proportionality coefficient, and t is the duration of adding the refining agent.

[0102] Obtain the total volume inside the refining machine from the database corresponding to the refining machine, and obtain the reaction rate corresponding to the current refining process. Based on the total volume inside the refining machine and the mass of the refining agent, calculate the concentration of the refining agent, and based on this reaction rate, the concentration of the refining agent, and the reaction rate calculation formula, calculate the reaction rate coefficient, where the reaction rate = the reaction rate coefficient * the concentration of the refining agent.

[0103] Use computational fluid dynamics (CFD) software to simulate the flow field, temperature field, and mass transfer process in the furnace, and establish a diffusion and reaction model of the refining agent in the furnace. By inputting the initial conditions and boundary conditions in the furnace (such as furnace body structure, temperature distribution, gas flow, etc.), the concentration distribution of the refining agent at different positions and different times in the furnace can be predicted. Analyze the diffusion process of the refining agent based on Fick's diffusion law, obtain the data of the change of concentration with time and position, and use numerical methods (such as the finite difference method) to solve and fit Fick's second law to obtain the diffusion coefficient. Among them, the method of simulation by computational fluid dynamics and Fick's diffusion law are conventional technical means in this field, and are not elaborated in the embodiments of the present application.

[0104] Statistically analyze the data of multiple historical refining processes, calculate the ratio of the actual adhesion amount to the theoretical adhesion amount in each historical refining process, and take the average value as the preliminary estimated value of the proportionality coefficient.

[0105] Furthermore, comprehensively analyze the results of the reaction process, diffusion process, and adhesion process, establish a physical model describing the behavior of the refining agent in the furnace, and calibrate the physical model using historical refining data. Input parameters such as the addition amount, furnace temperature, and stirring intensity in the historical refining process into the physical model to obtain the adhesion amount predicted by the model. Compare the adhesion amount predicted by the model with the actually recorded adhesion amount, calculate the error between the two, and an optimization algorithm (such as the gradient descent method) can be used to find the optimal proportionality coefficient to minimize the error.

[0106] Even further, after obtaining the optimal proportionality coefficient, substitute the optimal proportionality coefficient into Formula Three, and substitute the mass of the refining agent to be added at each moment, the first adhesion rate, and the second adhesion rate into Formula Three Δm = m0 * (A1 + A2) * (1 + kt) to obtain the adjustment amount corresponding to the refining agent.

[0107] The embodiments of the present application provide a method for determining the addition amount of the refining agent in the furnace. By adopting the above technical solutions, various data in the refining process (such as the addition amount of the refining agent, basic data, stirring intensity, furnace temperature) and environmental humidity are collected, and based on the basic data of the refining agent (particle size, surface roughness, category), stirring intensity, and furnace temperature, the natural adhesion situation of the refining agent in the refining process, that is, the first adhesion rate, can be evaluated. Further, by considering the influence of environmental humidity on the adhesion situation of the refining agent and determining the second adhesion rate accordingly, the practicability and accuracy of the method are enhanced. By comprehensively considering the first adhesion rate and the second adhesion rate, the adjustment amount of the refining agent is calculated, and based on this, the actual addition amount of the refining agent is determined, thereby ensuring the accuracy and rationality of the addition amount of the refining agent, and contributing to improving the refining effect and product quality.

[0108] The above embodiments introduce a method for determining the addition amount of in-furnace refining agent from the perspective of the method flow. The following embodiments introduce a device for determining the addition amount of in-furnace refining agent from the perspective of virtual modules or virtual units. For details, see the following embodiments.

[0109] See Figure 2 , the device 20 for determining the addition amount of in-furnace refining agent may specifically include: an acquisition module 201, a first determination module 202, a second determination module 203, and a calculation module 204, where:

[0110] A device 20 for determining the addition amount of in-furnace refining agent includes:

[0111] The acquisition module 201 is configured to acquire the refining information corresponding to the current refining process and acquire the environmental humidity. The refining information includes the addition amount situation of the refining agent, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace. The addition amount situation includes the mass of the refining agent to be added at each moment during the refining process. The basic data of the refining agent includes the particle size of the refining agent, the surface roughness of the refining agent, and the type of the refining agent;

[0112] The first determination module 202 is configured to determine the first adhesion rate of the refining agent based on the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace;

[0113] The second determination module 203 is configured to determine the influence degree of the environmental humidity on the refining agent, and determine the second adhesion rate of the refining agent based on the influence degree;

[0114] The calculation module 204 is configured to calculate the adjustment amount corresponding to the refining agent based on the first adhesion rate and the second adhesion rate, and determine the actual addition amount of the refining agent based on the adjustment amount.

[0115] In a possible implementation manner of the embodiments of the present application, when the first determination module 202 determines the first adhesion rate of the refining agent based on the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace, it is specifically configured to:

[0116] Acquire the historical refining data corresponding to the refiner and determine the activation energy corresponding to the current refining process. The historical refining data includes the historical refining information and the historical adhesion rate corresponding to each historical refining process;

[0117] Construct a temperature model including a temperature exponential term according to the form of the Arrhenius equation. The temperature model is used to describe the relationship between temperature and adhesion rate;

[0118] Optimize the temperature model based on the historical refining data to obtain a target temperature model, where the target temperature model is A is a model parameter, E is the activation energy, R is the ideal gas constant, and T is the absolute temperature corresponding to the historical temperature;

[0119] Determine the first adhesion rate of the refining agent based on the target temperature model, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace.

[0120] In a possible implementation manner of the embodiment of the present application, when the first determination module 202 determines the first adhesion rate of the refining agent based on the target temperature model, the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace, it is specifically configured to: calculate the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity;

[0121] Substitute the target temperature model into Formula 1 to obtain Formula 2, where Formula 1 is A1 is the first adhesion rate, k is the comprehensive correction coefficient, S is the surface roughness of the refining agent, T is the temperature in the refining furnace, a is the temperature influence index, G is the particle size of the refining agent, b is the particle size influence index, I is the refining stirring intensity, c is the stirring intensity influence index, and Formula 2 is

[0122] Substitute the basic data of the refining agent, the refining stirring intensity, and the temperature in the refining furnace into Formula 2 to calculate the first adhesion rate of the refining agent.

[0123] In a possible implementation manner of the embodiment of the present application, when the first determination module 202 calculates the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity, it is specifically configured to:

[0124] Screen out the first historical sub-data that meets the first preset condition and the second historical sub-data that meets the second preset condition from the historical refining data to obtain the first historical sequence and the second historical sequence. The first preset condition is that any first feature in the first target feature has the same corresponding feature value in each corresponding historical refining process. The first feature is any one of the addition amount of the historical refining agent, the surface characteristics of the historical refining agent, the category of the historical refining agent, the historical refining stirring intensity, and the temperature in the historical refining furnace. The second preset condition is that any second feature in the second target feature has the same corresponding feature value in each corresponding historical refining process. The second feature is any one of the addition amount of the historical refining agent, the surface characteristics of the historical refining agent, the category of the historical refining agent, the particle size of the historical refining agent, and the temperature in the historical refining furnace;

[0125] Establish the first curve corresponding to the first historical sequence and the second curve corresponding to the second historical sequence;

[0126] Based on the first curve and the second curve, determine the particle size influence index corresponding to the particle size of the refining agent and the stirring intensity influence index corresponding to the refining stirring intensity.

[0127] In a possible implementation manner of the embodiment of the present application, the historical refined data includes historical ambient humidity. When the second determination module 203 determines the influence degree of the ambient humidity on the refining agent, it specifically is used for:

[0128] Perform time-domain analysis and frequency-domain analysis on the historical refined data to obtain the humidity time-domain function relationship corresponding to the refining agent and the frequency-domain eigenvector matrix;

[0129] Based on the humidity time-domain function relationship, predict the first change curve corresponding to the current refining process, where the first change curve is the curve of the ambient humidity changing with time;

[0130] Input the frequency-domain eigenvector matrix and the basic data of the refining agent into the recurrent network model, and obtain the second change curve output by the recurrent network model, where the second change curve is the curve of the influence degree changing with the ambient humidity;

[0131] Based on the first change curve and the second change curve, determine the influence degree of the ambient humidity on the refining agent.

[0132] In a possible implementation manner of the embodiment of the present application, when the second determination module 203 determines the second adhesion rate of the refining agent based on the influence degree, it specifically is used for:

[0133] Based on the second change curve, determine the historical influence degree corresponding to the ambient humidity in each historical refining process, and calculate the historical first adhesion rate corresponding to each historical refining process;

[0134] Based on the historical first adhesion rate, historical adhesion rate, and historical influence degree in each historical refining process, determine the influence coefficient corresponding to the influence degree;

[0135] Based on the influence coefficient and the influence degree, determine the second adhesion rate of the refining agent.

[0136] In a possible implementation manner of the embodiment of the present application, when the calculation module 204 calculates the adjustment amount corresponding to the refining agent based on the first adhesion rate and the second adhesion rate, it specifically is used for:

[0137] Based on the addition amount situation, analyze the reaction process, diffusion process, and adhesion process of the refining agent respectively, calculate the reaction rate coefficient, diffusion coefficient, and proportional coefficient corresponding to the refining agent, and establish a physical model corresponding to the refining agent;

[0138] Based on the physical model, determine the proportional coefficient, where the proportional coefficient is used to correct the gap between the actual adhesion situation of the refining agent in the refining process and the result calculated simply based on the adhesion rate;

[0139] Substitute the mass of the refining agent to be added at each moment, the first adhesion rate, and the second adhesion rate into Equation 3 to obtain the adjustment amount corresponding to the refining agent. Equation 3 is Δm = m0 * (A1 + A2) * (1 + kt), where Δm is the adjustment amount, m0 is the mass of the refining agent, A1 is the first adhesion rate, A2 is the second adhesion rate, k is the proportionality coefficient, and t is the duration of adding the refining agent.

[0140] 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 foregoing method embodiments and will not be elaborated herein.

[0141] See Figure 3 , this embodiment of the present application also introduces an electronic device from the perspective of an entity device, such as Figure 3 shown in Figure 3 The electronic device 300 shown in includes: a processor 301 and a memory 303. Among them, the processor 301 and the memory 303 are connected, such as connected through a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation to the embodiments of the present application.

[0142] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in combination with the disclosure of the present application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0143] The bus 302 may include a path for transmitting information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 3It is represented only by a thick line, but it does not mean that there is only one bus or one type of bus.

[0144] The memory 303 can be a ROM (Read Only Memory), or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory), or other types of dynamic storage devices that can store information and instructions. It can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0145] The memory 303 is used to store the application program code for implementing the solution of this application, and is controlled by the processor 301 for execution. The processor 301 is used to execute the application program code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0146] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and can also be a server, etc. Figure 3 The shown electronic device is only an example and should not bring any limitations to the functions and usage scopes of the embodiments of this application.

[0147] The embodiments of this application provide a computer-readable storage medium, on which a computer program is stored. When it runs on a computer, it enables the computer to execute the corresponding content in the foregoing method embodiments.

[0148] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the indication of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this document, there is no strict order restriction for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same moment, but can be executed at different moments, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0149] The above are only some implementation manners of the present application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A method for determining the amount of refining agent added in a furnace, characterized in that: include: Obtaining refining information corresponding to the current refining process and the ambient humidity, wherein the refining information includes the amount of refining agent added, basic data of the refining agent, refining stirring intensity, and temperature in the refining furnace, wherein the amount of refining agent added includes the mass of the refining agent to be added at each moment during the refining process, and the basic data of the refining agent includes the particle size of the refining agent, the surface roughness of the refining agent, and the type of the refining agent; Determining a first adhesion rate of the refining agent based on the basic data of the refining agent, the refining stirring intensity and the temperature in the refining furnace; Determining the degree of influence of the ambient humidity on the refining agent, and determining a second adhesion rate of the refining agent based on the degree of influence; Based on the first attachment rate and the second attachment rate, an adjustment amount corresponding to the refining agent is calculated, and based on the adjustment amount, an actual addition amount of the refining agent is determined.

2. The method for determining the amount of refining agent added in a furnace according to claim 1, characterized in that: The determining of the first adhesion rate of the refining agent based on the basic data of the refining agent, the refining stirring intensity and the temperature in the refining furnace comprises: acquiring historical refining data corresponding to the refining agent, and determining the activation energy corresponding to the current refining process, wherein the historical refining data comprises historical refining information and historical adhesion rates corresponding to each historical refining process; According to the form of the Arrhenius equation, a temperature model including a temperature exponential term is constructed, wherein the temperature model is used to describe the relationship between temperature and adhesion rate; The temperature model is optimized based on the historical refined data to obtain a target temperature model, wherein the target temperature model is A is the model parameter, E is the activation energy, R is the ideal gas constant, and T is the absolute temperature corresponding to the historical temperature; A first adhesion rate of the refining agent is determined based on the target temperature model, the refining agent basic data, the refining stirring intensity, and the temperature in the refining furnace.

3. The method for determining the amount of refining agent added in a furnace according to claim 2, characterized in that: Determining a first adhesion rate of the refining agent based on the target temperature model, the refining agent basic data, the refining stirring intensity, and the temperature in the refining furnace includes: Calculate the particle size influence index corresponding to the refining agent particle size and the stirring intensity influence index corresponding to the refining stirring intensity; bring the target temperature model into formula 1 to obtain formula 2, where formula 1 is A1 is the first adhesion rate, k is the comprehensive correction coefficient, S is the surface roughness of the refining agent, T is the temperature in the refining furnace, a is the temperature influence index, G is the refining agent particle size, b is the particle size influence index, I is the refining stirring intensity, c is the stirring intensity influence index, and formula 2 is The basic data of the refining agent, the refining stirring intensity and the temperature in the refining furnace are put into Formula 2 to calculate the first adhesion rate of the refining agent.

4. The method for determining the amount of refining agent added in a furnace according to claim 2 or 3, characterized in that: Calculating the particle size influence index corresponding to the refining agent particle size and the stirring intensity influence index corresponding to the refining stirring intensity includes: Filter out first historical sub-data satisfying a first preset condition and second historical sub-data satisfying a second preset condition from the historical refining data to obtain a first historical sequence and a second historical sequence, wherein the first preset condition is that the characteristic value corresponding to any first characteristic in the first target characteristic is the same in each corresponding historical refining process, and the first characteristic is any one of the amount of historical refining agent added, the surface characteristics of historical refining agent, the type of historical refining agent, the intensity of historical refining stirring, and the temperature in the historical refining furnace, and the second preset condition is that the characteristic value corresponding to any second characteristic in the second target characteristic is the same in each corresponding historical refining process, and the second characteristic is any one of the amount of historical refining agent added, the surface characteristics of historical refining agent, the type of historical refining agent, the particle size of historical refining agent, and the temperature in the historical refining furnace; Establishing a first curve corresponding to the first historical sequence and a second curve corresponding to the second historical sequence; Based on the first curve and the second curve, a particle size influence index corresponding to the refining agent particle size and a stirring intensity influence index corresponding to the refining stirring intensity are determined.

5. The method for determining the amount of refining agent added in a furnace according to claim 2, characterized in that: The historical refining data includes historical ambient humidity, and determining the degree of influence of the ambient humidity on the refining agent includes: Performing time domain analysis and frequency domain analysis on the historical refining data to obtain a humidity time domain function relationship and a frequency domain characteristic vector matrix corresponding to the refining agent; Based on the humidity time domain function relationship, predicting a first change curve corresponding to the current refining process, wherein the first change curve is a time change curve of the ambient humidity; Inputting the frequency domain eigenvector matrix and the refining agent basic data into a cyclic network model, and obtaining a second change curve output by the cyclic network model, wherein the second change curve is a curve of influence degree changing with environmental humidity; Based on the first change curve and the second change curve, the degree of influence of the ambient humidity on the refining agent is determined.

6. The method for determining the amount of refining agent added in a furnace according to claim 5, characterized in that: Based on the influence degree, determining a second adhesion rate of the refining agent comprises: Determine the historical impact degree corresponding to the ambient humidity in each historical refining process based on the second variation curve, and calculate the historical first adhesion rate corresponding to each historical refining process; Determining an influence coefficient corresponding to the influence degree based on the historical first attachment rate in each historical refining process, the historical attachment rate, and the historical influence degree; Based on the influence coefficient and the influence degree, a second adhesion rate of the refining agent is determined.

7. The method for determining the amount of refining agent added in a furnace according to claim 1, characterized in that: Calculating the adjustment amount of the refining agent based on the first attachment rate and the second attachment rate includes: Based on the addition amount, the reaction process, diffusion process and adhesion process of the refining agent are analyzed respectively, and the reaction rate coefficient, diffusion coefficient and proportional coefficient corresponding to the refining agent are calculated, and a physical model corresponding to the refining agent is established; Determining a proportionality coefficient based on the physical model, wherein the proportionality coefficient is used to correct the difference between the actual adhesion of the refining agent during the refining process and the result calculated based solely on the adhesion rate; The mass of the refining agent to be added at each moment, the first adhesion rate and the second adhesion rate are substituted into Formula 3 to obtain the adjustment amount corresponding to the refining agent. Formula 3 is Δm=m0*(A1+A2)*(1+kt), Δm is the adjustment amount, m0 is the mass of the refining agent, A1 is the first adhesion rate, A2 is the second adhesion rate, k is the proportional coefficient, and t is the duration of adding the refining agent.

8. A device for determining the amount of refining agent added in a furnace, characterized in that: include: An acquisition module is used to acquire the refining information corresponding to the current refining process and the ambient humidity. The refining information includes the amount of refining agent added, basic data of the refining agent, refining stirring intensity and temperature in the refining furnace. The amount of refining agent added includes the mass of the refining agent to be added at each moment during the refining process. The basic data of the refining agent includes the particle size of the refining agent, the surface roughness of the refining agent and the type of the refining agent. A first determination module, configured to determine a first adhesion rate of the refining agent based on the basic data of the refining agent, the refining stirring intensity and the temperature in the refining furnace; A second determination module is used to determine the influence degree of the environmental humidity on the refining agent, and determine a second adhesion rate of the refining agent based on the influence degree; A calculation module is used to calculate an adjustment amount corresponding to the refining agent based on the first attachment rate and the second attachment rate, and determine an actual addition amount of the refining agent based on the adjustment amount.

9. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the method for determining the amount of refining agent added in a furnace according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the method for determining the amount of refining agent added in a furnace according to any one of claims 1 to 7.

Images