Titanium-iron powder reduction preparation of oxygen potential temperature coordination control method and system

Abstract

The application discloses a method and system for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder, and belongs to the technical field of metallurgy. The method comprises the following steps: in the reduction preparation process of ferrotitanium powder, the oxygen potential value time sequence is calculated and the reduction environment is analyzed by acquiring temperature time sequence data and atmosphere composition data, and the oxygen potential value sequence and atmosphere state data are obtained. Combined with reaction condition data, reaction kinetics analysis and evolution trajectory deduction are carried out to determine the current reduction stage. Based on the current stage, the preset oxygen potential and temperature interval are matched, the boundary and trend deviation and chemical driving force are analyzed, and the comprehensive deviation matching result is obtained. Based on this, it is judged whether to perform an adjustment operation, and if necessary, the heating power or atmosphere supply parameter is adjusted to optimize the reaction process. The scheme accurately predicts the dynamic change of the reduction process, ensures that the reduction reaction of ferrotitanium powder is carried out in an ideal environment. The optimization and stability of the reduction process are realized, and the reaction efficiency and product quality are improved.

Description

Technical Field

[0001] This application belongs to the field of metallurgical technology, specifically relating to a method and system for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder. Background Technology

[0002] In the reduction process of ilmenite powder, precise control of the reduction environment is crucial to ensuring product composition uniformity and process stability. Since ilmenite reduction involves multiphase reaction equilibrium and kinetic competition, it is necessary to monitor the thermodynamic state within the furnace in real time and dynamically optimize process parameters to achieve efficient reduction of metallic iron and low oxidation retention of the titanium component.

[0003] Existing technology first collects temperature data from multiple points inside the furnace periodically using thermocouples, and then takes samples at regular intervals to detect the atmospheric composition offline using a gas chromatograph. Subsequently, it estimates the oxygen potential value based on empirical thermodynamic charts and divides the reduction stage according to a preset fixed temperature-oxygen potential range. Finally, based on the deviation between the target parameters and the measured values ​​of each stage, it adjusts the power of the heating element and the opening of the gas flow valve through manual experience or preset PID control logic.

[0004] However, the offline detection technology of the present technology leads to a time mismatch between atmosphere data and temperature data, and the oxygen potential calculation results lag behind the actual reaction process, resulting in a delay in decision-making for stage division; in addition, the fixed threshold does not take into account the impact of raw material activity fluctuations on reaction thermodynamics, which can easily lead to insufficient reduction in the low temperature zone or overburning in the high temperature zone; at the same time, the independent control of temperature and atmosphere parameters lacks synergy. For example, increasing the heating power alone may lead to a local increase in oxygen potential due to insufficient gas flow, which may cause secondary oxidation of titanium. Summary of the Invention

[0005] To overcome the above-mentioned defects, this invention is proposed to provide solutions or at least partially solve the technical problems of offline detection in the prior art, which leads to a time mismatch between atmosphere data and temperature data, and oxygen potential calculation results lagging behind the actual reaction process, resulting in decision-making delays in stage division; and fixed thresholds do not take into account the influence of raw material activity fluctuations on reaction thermodynamics, which can easily cause insufficient reduction in the low-temperature zone or overburning in the high-temperature zone; at the same time, the independent control of temperature and atmosphere parameters lacks synergy.

[0006] In a first aspect, the present invention provides a method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder, the method comprising: In the process of reducing ferrite powder, temperature time series data and atmosphere composition time series data inside the ferrite powder reduction furnace within a preset time window are obtained. Based on the temperature time series data and atmosphere composition time series data, oxygen potential value time series calculation and reduction environment analysis are performed to obtain the oxygen potential value time series sequence and atmosphere state data sequence inside the ferrite powder reduction furnace. Acquire reaction condition data, and based on the reaction condition data, oxygen potential time sequence, and atmosphere state data sequence, perform reduction reaction kinetic analysis and reaction evolution trajectory deduction to determine the current reduction stage of the ferrotitanium powder reduction process; Based on the current reduction stage, the corresponding preset oxygen potential range and preset temperature range are determined. The temperature time series data is matched with the preset temperature range for boundary and trend, and the oxygen potential value time series is matched with the preset oxygen potential range for chemical driving force to obtain the comprehensive deviation matching result. Based on the comprehensive deviation matching results and the preset adjustment trigger standard, it is determined whether an adjustment operation needs to be performed. If an adjustment operation needs to be performed, the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace are adjusted based on the comprehensive deviation matching results and the preset adjustment trigger standard.

[0007] In a second aspect, the present invention provides an oxygen potential-temperature synergistic control system for the reduction preparation of ferrotitanium powder, the system comprising: The data acquisition and analysis module is used to acquire temperature time-series data and atmosphere composition time-series data inside the ferrite powder reduction furnace within a preset time window during the ferrite powder reduction preparation process. Based on the temperature time-series data and atmosphere composition time-series data, the oxygen potential value time-series sequence is calculated and the reduction environment is analyzed to obtain the oxygen potential value time-series sequence and atmosphere state data sequence inside the ferrite powder reduction furnace. The reaction stage simulation module is used to acquire reaction condition data, and based on the reaction condition data, oxygen potential time sequence and atmosphere state data sequence, to perform reduction reaction kinetic analysis and reaction evolution trajectory simulation to determine the current reduction stage of the titanium iron powder reduction process. The deviation matching analysis module is used to determine the corresponding preset oxygen potential range and preset temperature range based on the current reduction stage, perform boundary and trend matching between the temperature time series data and the preset temperature range, and perform chemical driving force matching between the oxygen potential value time series and the preset oxygen potential range to obtain the comprehensive deviation matching result. The adjustment module is used to determine whether an adjustment operation needs to be performed based on the comprehensive deviation matching result and the preset adjustment trigger standard. If an adjustment operation needs to be performed, the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace are adjusted based on the comprehensive deviation matching result and the preset adjustment trigger standard.

[0008] In a third aspect, an electronic device is provided, comprising a processor, a memory, and a program or instructions stored in the memory and executable on the processor, the program or instructions being loaded and run by the processor to perform the steps of the above-described method for coordinated control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder.

[0009] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, the program codes being adapted to be loaded and run by a processor to perform the steps of the above-described method for coordinated control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder.

[0010] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects: In implementing the technical solution of this invention, by acquiring and analyzing data on temperature, atmosphere composition, oxygen potential, and reaction conditions in real time, the dynamic changes of the reduction process are accurately predicted, ensuring that the reduction reaction of ferrotitanium powder takes place under ideal conditions. By matching the deviations in temperature and oxygen potential, the heating power and atmosphere parameters are automatically adjusted to optimize and stabilize the process, thereby improving reaction efficiency and product quality. Attached Figure Description

[0011] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Furthermore, similar numbers in the drawings are used to denote similar components, wherein: Figure 1 This is a schematic diagram of the first main steps of a method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the second main step of a method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to an embodiment of the present invention. Figure 3 This is a schematic diagram of the main structure of an oxygen potential-temperature synergistic control system for titanium-iron powder reduction preparation according to an embodiment of the present invention. Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0012] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0013] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0014] See appendix Figure 1 , Figure 1 This is a schematic flowchart of the first main steps of a method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to an embodiment of the present invention. Figure 1 As shown, the oxygen potential and temperature synergistic control method for the reduction preparation of titanium iron powder in an embodiment of the present invention mainly includes the following steps S101-S104.

[0015] Step S101: During the reduction preparation of ferrotitanium powder, acquire the temperature time series data and atmosphere composition time series data inside the ferrotitanium powder reduction furnace within a preset time window. Based on the temperature time series data and atmosphere composition time series data, perform oxygen potential value time series calculation and reduction environment analysis to obtain the oxygen potential value time series sequence and atmosphere state data sequence inside the ferrotitanium powder reduction furnace.

[0016] The ilmenite reduction furnace is a specialized high-temperature equipment for converting ilmenite ore into ilmenite powder.

[0017] The preset time window is a specific time period pre-defined in the reduction process of ferrotitanium powder. During this period, the system continuously collects and analyzes relevant data. This time interval is usually set to match the key stages of the reduction reaction.

[0018] Temperature time series data is a complete record of the dynamic changes in the internal temperature of the ferrotitanium powder reduction furnace over time within a preset time window, which can show the trend and fluctuation characteristics of the temperature inside the furnace.

[0019] The oxygen potential time series is a sequence of data calculated within a preset time window, combining temperature time series data and atmospheric composition time series data. The oxygen potential value is an indicator characterizing the chemical activity of oxygen in a reaction environment.

[0020] Atmosphere composition time-series data is a sequence of data recording the dynamic changes in the composition of the atmosphere inside the furnace. It includes the concentration fluctuations of various gases within a preset time window, including key gases such as oxygen, nitrogen, hydrogen, carbon monoxide, and carbon dioxide. This data visually presents the real-time state of the atmosphere inside the furnace, focusing on the specific types and corresponding concentrations of gases at each moment.

[0021] Atmosphere state data sequence is a quantitative description of the furnace atmosphere state formed after further analysis and processing of the atmosphere composition time series data. It includes not only concentration information of various gases, but also aspects such as reaction atmosphere type and atmosphere stability, representing a deep refinement and abstraction of the original atmosphere composition data. Its function is to reflect the overall changing trend and real-time state of the furnace atmosphere, such as determining whether the current atmosphere is a reducing or oxidizing atmosphere.

[0022] In the process of reducing ferrotitanium powder, temperature and atmosphere composition time-series data are first collected within a preset time window inside the ferrotitanium powder reduction furnace. To acquire the temperature time-series data, various temperature sensors, including thermocouples and infrared temperature sensors, need to be installed in different key areas of the reduction furnace. These sensors are connected to the data acquisition system to record and store the dynamic changes in temperature in real time. The final temperature data is arranged chronologically, clearly showing the fluctuation pattern of the furnace temperature over time. To ensure the acquired data has practical application value, a scientifically reasonable preset time window needs to be set, taking into account the process characteristics of different reaction stages within the furnace. This time window typically covers the complete cycle of the reduction reaction from start to finish, and its length can be flexibly adapted to the adjustment needs of the actual production process. Within the set preset time window, the acquisition of atmosphere composition time-series data relies on various gas analysis instruments installed inside the reduction furnace, including gas sensors, infrared gas analyzers, and spectrometers. These devices can monitor the changes in the furnace atmosphere composition in real time, focusing on tracking the concentration fluctuations of key gases such as oxygen, nitrogen, hydrogen, carbon monoxide, and carbon dioxide. The atmosphere analyzer collects gas concentration information at a fixed frequency within a preset time window and organizes and stores it in chronological order.

[0023] After collecting temperature and atmosphere composition time-series data, the two types of data are first imported into the data processing system for data synchronization and calibration to ensure accurate matching of data from different data sources at the same time point. Based on historical experimental data and machine learning algorithms, a non-formulaic model based on temperature and atmosphere composition data can be constructed to achieve real-time prediction of oxygen potential. In practical applications, the model can directly call the real-time collected temperature and atmosphere composition time-series data to calculate the current oxygen potential in the furnace and simultaneously generate the corresponding oxygen potential time-series sequence. By deeply mining and learning the intrinsic relationship between temperature, atmosphere composition, and oxygen potential, the model can accurately predict oxygen potential in real time. During continuous data input, the model can dynamically update and generate a complete oxygen potential time series. The model training process is as follows: First, the collected historical data is split into training and test sets. Then, all data is standardized to ensure that the scale of different feature parameters remains consistent. Based on the specific needs of actual production applications, a suitable machine learning algorithm is selected, choosing either a regression model or a neural network, and the model training process is officially started. Temperature and atmosphere-related data are used as input features for the model, with oxygen potential as the target output. By continuously reducing the deviation between predicted and actual oxygen potential values, the model's parameter settings are constantly optimized, steadily improving prediction accuracy. During training, gradient descent is used to dynamically adjust model parameters, iterating multiple times until the prediction error is minimized. After model training, the prediction accuracy is comprehensively verified using a test set. Hyperparameters are also adjusted appropriately to effectively avoid overfitting, further enhancing the model's generalization ability and ensuring stable and reliable prediction results in practical production applications. After complete training, the model can receive newly acquired temperature and atmosphere data in real time, accurately predict the corresponding oxygen potential values, and ultimately generate a complete time-series sequence of oxygen potential values.

[0024] For time-series data on atmospheric composition, time-series smoothing and denoising are commonly performed using two methods: moving average and Kalman filtering. These two methods effectively eliminate high-frequency noise caused by insufficient sensor accuracy and external environmental interference, resulting in more stable data trends. After data preprocessing, the trend analysis stage begins. For the concentration changes of various gases such as oxygen, nitrogen, hydrogen, carbon monoxide, and carbon dioxide, the rising or falling trends of gas concentrations are identified by calculating the first-order difference or comparing the difference between short-term and long-term means. This analytical method can accurately identify the rate of change of gas concentration, further revealing the progress of the reduction reaction. For example, when oxygen concentration decreases while hydrogen concentration increases simultaneously, it means that the intensity of the reduction reaction is continuously increasing.

[0025] To quantify the intrinsic relationship between various gas concentrations and reduction reactions, a time-delay analysis method is employed. By measuring the time difference between changes in gas concentration and reaction rates, the dynamic relationship between atmospheric conditions and the reaction process can be more accurately characterized. For example, a significant decrease in oxygen concentration may precede an increase in hydrogen concentration, a phenomenon that can serve as a precursor signal of an impending intensification of the reaction. After integrating real-time temperature and pressure data within the furnace, the impact of temperature on the reaction rate is calculated using physical relationships such as the Arrhenius equation. Increased temperature generally accelerates gaseous reaction rates, not only leading to faster consumption of oxygen, but also indicating a rise in hydrogen concentration as a significant indicator of reaction acceleration. Utilizing these fundamental physical laws and based on real-time collected temperature and atmospheric composition data, the changing trends of the furnace atmosphere can be predicted.

[0026] Atmosphere state data sequences are further constructed using a threshold determination method. Specific gas concentration thresholds are set; for example, a lower limit for oxygen concentration is defined. When the oxygen concentration is below this value, the furnace is considered to be in a strong reducing atmosphere. When the hydrogen concentration exceeds a preset upper limit, it indicates a high reaction intensity, which may trigger the control system to automatically adjust parameters. Finally, all the above analysis results are integrated to form an atmosphere state data sequence, comprehensively and in detail describing the changes in the furnace atmosphere. This sequence not only reflects the fluctuation characteristics of gas concentrations such as oxygen, nitrogen, hydrogen, carbon monoxide, and carbon dioxide over time, but also quantitatively describes the dynamic changes in atmosphere type based on the physical and chemical correlation between gas concentration and the reaction process. For example, when a continuous decrease in oxygen concentration occurs simultaneously with an increase in hydrogen concentration, it usually indicates that the reduction reaction is accelerating.

[0027] Based on the above technical solution, optionally, oxygen potential time series calculation and reduction environment analysis are performed based on the temperature time series data and atmosphere composition time series data to obtain the oxygen potential time series and atmosphere state data series inside the ferrotitanium powder reduction furnace, including: Based on the atmospheric composition time series data and temperature time series data, gas concentration distribution analysis is performed to obtain oxidizing component concentration data and reducing component concentration data. The time series of oxygen potential values ​​inside the ferrotitanium powder reduction furnace was calculated based on the concentration data of oxidizing components and reducing components. Reaction kinetics correction analysis was performed based on temperature time series data, oxidizing component concentration data, and reducing component concentration data to obtain oxidizing component activity assessment data and reducing component activity assessment data. Based on the time sequence of oxygen potential values, the activity assessment data of oxidizing components, and the activity assessment data of reducing components, an overall atmospheric state analysis was conducted to obtain the atmospheric state data sequence inside the ferrotitanium powder reduction furnace.

[0028] In this scheme, the concentration data of oxidizing components refers to the concentration values ​​of oxidizing gases, such as oxygen and carbon dioxide, in the furnace atmosphere during the reduction of ferrotitanium powder at different time points. This data represents the dynamic changes in the oxidizing gases in the reaction atmosphere, influencing the interaction between oxygen and the reduction reactants within the reaction system.

[0029] The concentration data of reducing components are the concentration values ​​of gaseous components, such as hydrogen and carbon monoxide, that participate in the reduction process during the reduction reaction, reflecting the changes in the content of reducing gases throughout the reduction of ferrotitanium powder.

[0030] Oxidizing component activity assessment data are results obtained by analyzing oxidizing component concentration data to evaluate the reactivity of oxidizing gases. This data clarifies whether oxidizing components such as oxygen possess sufficient oxidizing power to influence the reduction reaction process.

[0031] The reactivity assessment data for reducing components is obtained by analyzing the concentration data of reducing components, ultimately leading to an assessment of the activity level of the gases participating in the reduction reaction. This data can accurately characterize the actual reactivity of reducing gases such as hydrogen and carbon monoxide.

[0032] By combining time-series data on temperature and atmosphere composition, the concentration variation patterns and reaction dynamics of various gases are identified. Real-time monitoring of temperature and atmosphere data, combined with historical experience data and current reaction conditions, employs various data analysis techniques such as trend analysis, correlation analysis, and principal component analysis to accurately distinguish between oxidizing and reducing gas components. Oxygen and carbon dioxide are classified as oxidizing components, while hydrogen and carbon monoxide are classified as reducing components. Based on this, and combining real-time data analysis results with empirical data, the specific impact of temperature on gas concentration distribution is analyzed in depth, thereby obtaining concentration data for oxidizing and reducing components. After statistical processing and presentation in charts, this analytical method clearly shows the changing trends of atmosphere components and the intrinsic relationship between these changes and the reaction environment.

[0033] After the gas concentration distribution analysis is completed, the time series of oxygen potential values ​​inside the ferrotitanium powder reduction furnace is calculated based on the obtained oxidizing and reducing component concentration data. During the calculation process, time series analysis, regression analysis, and trend prediction methods are used, combined with real-time acquired oxidizing and reducing component concentration data, to analyze the changes in gas concentration and the impact of temperature. This calculation mode based on real-time data can dynamically capture the changes in oxygen potential values ​​and provide a practical basis for adjustments to address fluctuations in the reaction environment.

[0034] By combining temperature time-series data, oxidizing component concentration data, and reducing component concentration data, a reaction kinetic correction analysis is conducted. The core objective is to assess the activity of the oxidizing and reducing components, thereby adjusting the reaction rate. During the analysis, data mining techniques such as cluster analysis and multiple regression analysis are employed, combined with actual reaction conditions, to deeply analyze the concentration changes of oxidizing and reducing components and assess their roles in the reaction. Based on historical data and the real-time reaction environment, the activity levels of each gaseous component are evaluated, and the reaction process is optimized accordingly. Through these techniques, activity assessment data for both oxidizing and reducing components are ultimately obtained.

[0035] The collected data underwent preprocessing, focusing on outlier removal, missing data completion, and time alignment. After preprocessing, key analytical features were extracted, primarily including the trend of oxygen potential changes and the activity levels of oxidizing and reducing components. These features effectively reveal the dynamic characteristics of the reaction environment. By calculating specific indicators such as the fluctuation amplitude and mean change of oxygen potential time-series data, the changing patterns of the atmosphere during the reaction process can be further understood. Data visualization techniques were used to transform the oxygen potential time-series data, oxidizing component activity assessment data, and reducing component activity assessment data into charts and graphs, presenting the dynamic changes in atmospheric components. Line graphs, heatmaps, and scatter plots are commonly used visualization methods that can comprehensively present the atmospheric fluctuations during the reaction process.

[0036] To further clarify the driving factors of atmosphere changes, Granger causality analysis and covariance analysis techniques were used to comprehensively assess the mutual influence between various data. This type of analysis revealed the correlation between oxygen potential and changes in oxidizing components, as well as the intrinsic relationship between the activity of reducing components and the reaction rate, leading to a better understanding of the specific impact of reaction conditions on atmosphere composition. Based on all the above analyses, an overall atmosphere state assessment was conducted, focusing on determining whether the furnace atmosphere was within the preset suitable range. A comprehensive analysis of key factors such as the ratio of oxidizing to reducing gases and the magnitude of oxygen potential was performed to comprehensively assess whether the current atmosphere conditions were conducive to the smooth progress of the titanium-iron powder reduction reaction. Combining all the analytical results, information extracted from multi-dimensional data sources such as oxygen potential time series, oxidizing and reducing component concentration data, and atmosphere supply was first fused and processed. After aligning the various data according to the time dimension, the system was integrated to finally generate an atmosphere state data sequence.

[0037] In this solution, by analyzing information such as atmosphere composition data, temperature data, and oxygen potential, the atmospheric changes during the reduction process of ferrotitanium powder can be accurately monitored, the reaction environment can be optimized, the reaction efficiency can be improved, and the reduction process can be ensured to proceed stably, thereby improving production quality and overall production efficiency.

[0038] Step S102: Obtain reaction condition data, and based on the reaction condition data, oxygen potential time sequence, and atmosphere state data sequence, perform reduction reaction kinetic analysis and reaction evolution trajectory deduction to determine the current reduction stage of the titanium iron powder reduction process.

[0039] Reaction condition data, besides temperature and atmosphere composition, encompasses all other key parameters affecting the reduction process of ferrotitanium powder. These include heating power, furnace pressure, and atmosphere supply. Heating power reflects the heating intensity within the furnace, directly determining the rate of temperature change, thus influencing the reaction rate and the activity of the reactants. Changes in furnace pressure alter the density and distribution of gases, affecting the reaction rate and oxygen consumption. The atmosphere supply controls the concentration of reducing gases, including hydrogen and nitrogen, thus influencing the progress of the reduction reaction.

[0040] The current reduction stage is based on reaction condition data, oxygen potential time series, and atmosphere state data series to clarify the reaction stage of the ferrotitanium powder reduction process. This includes the initial stage, the intermediate stage, and the final stage. In the initial stage, the oxygen concentration is relatively high, the oxygen potential is large, and the reaction atmosphere inside the furnace is in an oxidizing state. In the intermediate stage, oxygen is continuously consumed, the hydrogen concentration gradually increases, the oxygen potential decreases, and the atmosphere transitions to a reducing state. In the final stage, oxygen is almost completely consumed, the atmosphere inside the furnace becomes a strongly reducing state, the hydrogen concentration reaches a relatively high level, and the oxygen potential is close to its lowest value.

[0041] First, reaction condition data is acquired. Heating power data is monitored in real time through the furnace power system, recording the power output of the furnace heating equipment, which affects the rate of temperature change and the rate of reduction reaction. Furnace pressure data is collected by installed pressure sensors, which record real-time pressure fluctuations of the gas inside the furnace, providing support for the analysis of gas density and flow state. Atmosphere supply data is captured in real time by gas flow meters, which record the flow rate and concentration of reducing gases such as hydrogen and nitrogen, ensuring that the atmosphere concentration inside the furnace is maintained at an appropriate level.

[0042] After acquiring these reaction condition data, combined with the oxygen potential time series and atmosphere state data series, the kinetic analysis of the reduction reaction begins. The thermodynamic conditions of the reaction are inferred by the correlation between temperature data and heating power. Temperature changes directly affect the energy distribution of reactants, thus influencing the reaction rate. Specifically, by monitoring temperature in real time and analyzing heating power, it can be determined whether the reaction is currently in the heating or cooling stage, thereby predicting the reaction's progress and actual effect. Pressure data analysis mainly assesses gas distribution and flow patterns. Pressure fluctuations are closely related to gas flow patterns and affect the mixing effect of reactants and the reaction rate, especially changes in gas density, which directly drive the reaction process. By continuously tracking the trend of pressure data changes, the distribution of gas within the furnace and the specific impact of this distribution on the reaction rate can be understood. Atmosphere supply data analysis mainly focuses on changes in gas concentration, especially hydrogen concentration, which directly reflects the intensity of the reduction reaction. Specifically, by acquiring gas flow data in real time, it can be confirmed whether the atmosphere concentration is maintained within a stable range and whether it can promote the reduction reaction.

[0043] The oxygen potential time series reflects changes in oxygen concentration and the reduction reaction environment. By capturing fluctuations in oxygen concentration, the progress of the reaction can be understood; that is, an increase or decrease in oxygen concentration directly corresponds to a slowdown or acceleration of the reaction. The atmosphere state data series, on the other hand, shows the dynamic changes in the furnace atmosphere from the perspective of gas composition. For example, an increase in hydrogen concentration suggests that the reduction reaction intensity is continuously increasing; a decrease in hydrogen concentration means that the reaction intensity is weakening. Combining the oxygen potential time series and the atmosphere state data series allows for an assessment of the overall state of the reaction.

[0044] After thoroughly analyzing this data, the reaction evolution trajectory is then deduced. Specifically, based on changes in temperature, pressure, oxygen potential, and atmosphere concentration, the reaction evolution path can be predicted by comparing and tracking reaction conditions at different time points. For example, when the oxygen concentration decreases significantly and the hydrogen concentration increases simultaneously, it indicates that the reaction has entered the reduction stage; when the hydrogen concentration continues to rise and the oxygen concentration approaches zero, it can be confirmed that the reduction reaction is nearing completion. By comprehensively analyzing the changing trends of temperature, pressure, oxygen potential, and atmosphere data, the dynamic evolution trajectory of the titanium-iron powder reduction process can be calculated, and the current reduction stage can be identified.

[0045] Based on the above technical solution, optionally, based on the reaction condition data, oxygen potential time series, and atmosphere state data series, reduction reaction kinetic analysis and reaction evolution trajectory deduction are performed to determine the current reduction stage of the ferrotitanium powder reduction process, including: Feature extraction was performed based on the time series of oxygen potential values ​​to obtain the feature vector of the reaction process; The reaction rate is calculated based on the reaction process feature vector and the atmospheric state data sequence to obtain the reaction rate data. The reaction process feature vector and reaction rate data are mapped to a preset critical criterion space, and the critical conditions of the reaction are compared to obtain the critical state identification result. Based on reaction condition data, reaction rate data, reaction process feature vector, and critical state identification results, the current reaction kinetic feature data are generated by fusing them together. Obtain historical reaction kinetics feature data sequences, perform time series modeling based on historical reaction kinetics feature data sequences, and obtain historical evolution paths; Based on current reaction kinetics data and historical evolution paths, multidimensional coupling analysis is performed to determine the current reduction stage of the titanium-iron powder reduction process.

[0046] In this scheme, the reaction process feature vector is a data set representing the dynamic characteristics of the reaction process extracted from the time series of oxygen potential values. It can capture the stage changes of the reaction and reflect the changes of key parameters during the reaction process.

[0047] Reaction rate data are calculated based on the reaction process characteristic vector and atmospheric state data sequence. They describe the change of reaction rate over time and reveal the magnitude and trend of the reaction rate during the reaction process.

[0048] The preset critical criterion space is a reaction condition space pre-set based on empirical data of the reduction reaction of ferrotitanium powder. It is used to determine whether the reaction is approaching or has reached a critical state. It includes the ideal conditions and warning range of the reaction. Once reaction parameters such as reaction rate and oxygen potential exceed the boundary of this space, it may mean that the reaction conditions have changed or the reaction process has become unstable.

[0049] Critical state identification results are obtained by mapping the reaction process feature vector and reaction rate data to a preset critical criterion space, determining whether the reaction has reached or exceeded preset critical conditions. This indicates whether the reaction has entered or is about to enter a critical state, such as when the reaction rate is too fast or too slow, or when the oxygen potential deviates from a preset range.

[0050] The current reaction kinetics data is a comprehensive dataset generated by fusing reaction condition data, reaction rate data, reaction process feature vectors, and critical state identification results. It provides detailed kinetic characteristics of the current stage of the reaction, reflecting the reaction state, rate, and potential critical conditions.

[0051] Historical reaction kinetics data sequences are data sequences collected from historical reaction processes that reflect the characteristics of reaction kinetics. Including characteristic data from all previous reaction processes, they provide a reference benchmark for analyzing historical trends and patterns of reactions.

[0052] The historical evolution path is obtained through time-series modeling based on historical reaction kinetic characteristic data sequences, describing the changes and development paths of the reaction in the historical process. It reflects the changing trends of reaction conditions, rates, etc., over time.

[0053] Multiple features are extracted from the time-series data of oxygen potential, including fluctuation amplitude, mean change, and the difference between the maximum and minimum values. These features reflect the progress and trend of the reaction, helping to identify the key stages of the reaction. For example, calculating the rate of change of oxygen potential over a specific time period can determine whether the reaction is close to the ideal reduction state or whether abnormal deviations have occurred. The extracted feature data collectively constitute a reaction progress feature vector, representing the dynamic performance of the current reaction state.

[0054] Data preprocessing denoises and aligns all time-series data to ensure synchronization. Correlation analysis is applied to model the relationship between reaction process feature vectors and atmospheric state data sequences. The core of this approach is calculating the correlation between oxygen concentration, reducing gas concentration, and oxygen potential fluctuations to clarify how they collectively influence the reaction rate. In practice, the Pearson correlation coefficient measures the linear relationship between oxygen concentration changes and reaction rate. Combining these correlation results, reaction rate data for different time periods are calculated. Based on this acquired correlation data, linear regression or multiple linear regression is used for reaction rate prediction. Oxygen concentration, reducing gas concentration, oxygen potential in the reaction process feature vector, and oxygen potential fluctuations in the atmospheric state data sequence are all used as model input variables. The least squares method is used to solve for the regression coefficients, maximizing the fit and thus accurately obtaining the reaction rate data. For complex scenarios where reaction rate changes exhibit more complex nonlinear characteristics, multinomial regression or support vector regression is used to fit the data, achieving higher-precision prediction results.

[0055] After obtaining the reaction rate data, the reaction process feature vector and the reaction rate data are mapped to a pre-defined critical criterion space. This space is defined based on theoretical research or historical data and includes the threshold range of ideal reaction conditions, such as oxygen potential, upper and lower limits of the reaction rate, etc. Specifically, the construction of the ideal reaction condition space, based on the combination of theoretical research and historical data, focuses on defining the ideal operating range of the reaction to ensure that the reaction conditions are within this range. Theoretical research is conducted using principles of thermodynamics, reaction kinetics, etc., to clarify the ideal values ​​and ideal ranges of various key variables in the reaction process. Oxygen potential, as an important indicator for measuring the oxygen concentration in a reduction reaction, can have its ideal range determined through thermodynamic calculations to ensure that the reaction environment is suitable for the reduction reaction. Oxygen potential usually fluctuates within a certain range; too low a value will slow down the reaction rate, while too high a value may trigger an oxidation reaction, thus affecting product quality. Historical data further refines the definition of the ideal reaction condition space. By analyzing a large amount of experimental and production data, the upper and lower limits of key parameters such as oxygen potential, reaction rate, and atmosphere composition in actual reactions can be more accurately determined. For example, by analyzing reaction data from different production batches, the specific fluctuation range of oxygen potential that should be maintained in an ideal reduction reaction can be determined. The upper and lower limits of the reaction rate are also derived from historical data analysis; an excessively high reaction rate may lead to incomplete reaction, while an excessively low rate will reduce reaction efficiency. In this process, statistical methods such as regression analysis and cluster analysis can be used to identify key factors affecting the reaction rate, thereby setting reasonable upper and lower limits for various parameters. The combination of theoretical research and historical data provides a multi-dimensional definition of ideal reaction conditions, including key factors such as oxygen potential, reaction rate, and the concentration of various gases in the atmosphere. Through statistical analysis, the threshold ranges of these key parameters are clarified; for example, the oxygen potential needs to be maintained within a specific range, exceeding which may lead to a decline in reaction performance. The upper and lower limits of the reaction rate are determined by evaluating reaction efficiency and production stability.

[0056] After mapping the reaction process feature vector and reaction rate data to a preset critical criterion space, these data need to be compared with the ideal threshold range set in the space to determine whether the reaction is in a critical state. First, the reaction process feature vector and reaction rate data are compared one by one with the predefined thresholds in the critical criterion space. These thresholds include the upper and lower limits of key parameters such as oxygen potential and reaction rate, corresponding to the ideal operating conditions at different stages of the reaction. Once these ranges are exceeded, it means that the reaction may have entered a non-ideal or unstable state. During the comparison process, if the parameter value in the reaction process feature vector or the reaction rate exceeds the set threshold, a warning will be automatically triggered, indicating that the reaction may be in a critical condition. The critical state identification result is derived from the above comparative analysis, clarifying whether the reaction is in a preset critical state and providing an indication of whether the reaction conditions need to be adjusted. For example, if the oxygen potential or reaction rate exceeds the predetermined threshold range, it will be identified as a supercritical state, indicating that the reaction conditions need to be adjusted for correction; if all reaction parameters are within the set threshold range, it will be identified as a stable state, indicating that the reaction process is normal. This critical state identification result can promptly reflect the controllability of the reaction.

[0057] Then, by fusing reaction condition data, reaction rate data, reaction process feature vectors, and critical state identification results, current reaction kinetic characteristic data is generated. Specifically, all reaction-related data can be integrated, and a weighted average or multidimensional data fusion algorithm can be used to comprehensively reflect the kinetic characteristics of the reaction. This data not only includes the current kinetic state of the reaction but also integrates multidimensional information on reaction rate, oxygen potential, and atmospheric composition.

[0058] To improve prediction accuracy, historical reaction kinetic characteristic data sequences are obtained, and time-series modeling is performed based on this historical data. The core of time-series modeling is to analyze the changing trends, periodic fluctuations, and correlations between various reaction conditions in historical data, construct a mathematical model, and then predict the dynamic behavior of future reaction processes. To ensure modeling accuracy, various time-series modeling methods can be used, such as autoregressive models, autoregressive moving average models, and exponential smoothing. Autoregressive models analyze the time series of historical data to capture the inherent correlations within the data itself, utilizing the intrinsic connection between current data points and past data to predict subsequent data changes. For example, by combining the changing patterns of past oxygen potential and reaction rates, weighted calculations can be used to infer parameter trends over a future period, suitable for scenarios where the reaction process is relatively stable and data fluctuations are small. Autoregressive moving average models, building upon autoregressive models, further incorporate the influence of external fluctuation factors, capturing both long-term data trends and adapting to short-term fluctuations in the reaction process. This method can better handle parameter changes in complex reaction environments, such as temporary fluctuations in oxygen potential and sudden changes in reaction rates, making the model fit more closely to the actual reaction conditions. Exponential smoothing focuses on smoothing data fluctuations, weakening the interference of short-term outliers, and highlighting the overall trend of data changes. It is suitable for scenarios where reaction parameters fluctuate greatly and there are occasional outliers, making the prediction results more consistent with the actual reaction state in production. After the time series modeling is completed, the historical evolution path of the reaction will be output, clearly showing the trajectory of parameter changes from the start of the reaction to the current stage.

[0059] Finally, based on the current reaction kinetics data and historical evolution path, a multidimensional coupling analysis is conducted. This analysis integrates the current reaction state with historical evolution trends, revealing the similarities or differences between the current reaction stage and historical stages. Through multidimensional coupling analysis methods such as cluster analysis and multiple regression analysis, it is possible to identify whether the current reaction stage is similar to a past stage, thereby determining whether the reaction is in the initiation stage, stable stage, or near-completion stage. This analysis allows for precise determination of the current reduction stage of the titanium-iron powder reduction process.

[0060] This solution improves the precision control and stability of the reaction process by comprehensively analyzing the reaction process, atmospheric conditions, and historical data, thereby assessing the reaction stages in real time and predicting future developments.

[0061] Based on the above technical solution, optionally, multidimensional coupling analysis can be performed based on current reaction kinetics data and historical evolution paths to determine the current reduction stage of the ferrotitanium powder reduction process, including: Based on the current reaction kinetics characteristic data, the reaction rate change pattern is extracted to obtain the reaction rate change pattern; Stage identification parameters are extracted based on the current reaction kinetics characteristic data to obtain the stage identification parameters; Multidimensional trend comparisons were performed based on reaction rate change patterns and historical evolution paths to obtain deviation feature data; Reaction inflection point data is obtained by identifying reaction inflection points based on deviation feature data. Stability assessment is performed based on reaction inflection point data to obtain stability judgment results; Based on stage identification parameters, reaction inflection point data, and stability assessment results, a multi-dimensional weighted decision is made to determine the current reduction stage of the titanium iron powder reduction process.

[0062] In this scheme, the reaction rate change pattern is based on data extracted from current reaction kinetic characteristic data, presenting the trend and inherent laws of reaction rate changes with variables such as time and environmental conditions. It can clearly show the specific ways in which the reaction rate changes in different time periods and under different environments, accurately distinguish between normal fluctuations and abnormal deviations in the reaction process, and promptly capture the dynamic change patterns of the reaction rate.

[0063] Stage identification parameters are parameters extracted from reaction kinetic characteristic data to accurately classify different stages of a reaction. These parameters include the specific values ​​and trends of key variables such as reaction rate and oxygen potential, which can clearly distinguish different stages of the reaction, such as initiation, stabilization, and termination, and clarify the current process state of the reaction.

[0064] Deviation characteristic data is derived by comparing the current reaction with historical reactions, focusing on abnormal fluctuations in the reaction process. It can accurately capture deviations of key parameters such as reaction rate and oxygen potential from historical normal levels, clearly presenting abnormal nodes in the reaction process.

[0065] Reaction inflection point data are data identified through analysis of deviation characteristic data, marking key nodes in the reaction process. These nodes correspond to significant changes in core parameters such as reaction rate and oxygen potential, clearly reflecting the transition of the reaction state.

[0066] The stability assessment result is generated based on reaction inflection point data to evaluate the stability of the reaction process. By analyzing key information such as the amplitude and frequency of fluctuations during the reaction process, it is determined whether the reaction is within a stable range.

[0067] Reaction rate variation patterns are extracted based on current reaction kinetic data. The analysis of oxygen potential, atmospheric composition, and reaction rate information within the data captures fluctuation trends in the reaction rate. To effectively eliminate interference noise, data smoothing techniques and filtering algorithms are employed to extract long-term trends and short-term fluctuations in the reaction rate. Moving averages and Savitzky-Golay filters both prove effective. Furthermore, regression analysis techniques, including linear and polynomial regression, are used to fit the curve of reaction rate over time, accurately extracting periodic fluctuations and long-term trends, ultimately forming the corresponding reaction rate variation patterns.

[0068] Stage identification parameters are extracted based on current reaction kinetic data. Specifically, key features are screened from the reaction kinetic data; the magnitude of changes in reaction rate and the fluctuation range of oxygen potential are both core features. These features are extracted using methods such as cluster analysis or principal component analysis. Cluster analysis can employ K-means clustering, while principal component analysis (PCA) helps quantify the boundaries between different reaction stages. Significant changes in reaction rate often indicate a transition in reaction stage, and changes in oxygen potential can also effectively distinguish different reduction stages. Stage identification parameters extracted using these algorithms ensure that each stage of the reaction process is accurately identified.

[0069] Multidimensional trend comparisons are conducted based on extracted reaction rate change patterns and historical evolution paths. This involves a comprehensive comparison of the current reaction rate change pattern with the trends of historical reaction processes, and the quantitative differences in similarity are calculated. Cosine similarity and Euclidean distance are commonly used similarity calculation methods, which can be used to obtain deviation feature data. This deviation feature data clearly shows the differences between the current reaction and historical standard patterns, enabling timely detection of abnormal fluctuations and trajectory deviations in the reaction.

[0070] By combining deviation feature data to identify reaction inflection points, and analyzing abrupt changes and drastic fluctuations, key inflection points in the reaction process can be located. This process typically employs methods such as slope change analysis or peak detection to accurately capture moments when the reaction rate and oxygen potential value change significantly. Key inflection points are then identified from the time-series curves of the reaction data, further locating unstable regions and potential anomalies in the reaction.

[0071] Stability assessment based on reaction inflection point data focuses on calculating the fluctuation range and frequency of key parameters such as reaction rate and oxygen potential to determine whether the reaction is in a stable state. Statistical methods such as analysis of variance and standard deviation calculation are used to assess the stability of the reaction data. Large fluctuations indicate the presence of unstable factors, requiring timely intervention. A multi-dimensional weighted decision-making process is then implemented, combining stage identification parameters, reaction inflection point data, and stability assessment results. This process utilizes weighted averages and analytic hierarchy process (AHP) to comprehensively consider reaction characteristics across various dimensions, weighting these characteristics to ultimately determine the current reduction stage of the reaction.

[0072] This method, through comprehensive analysis of data such as reaction rate changes, stage identification, inflection point identification, and stability assessment, enables precise monitoring of the dynamic changes in the reduction process of ferrotitanium powder. This improves the controllability of the reaction process, ensures its stability and efficiency, and facilitates timely adjustments and optimizations.

[0073] Step S103: Based on the current reduction stage, determine the corresponding preset oxygen potential range and preset temperature range, perform boundary and trend matching between the temperature time series data and the preset temperature range, and perform chemical driving force matching between the oxygen potential value time series and the preset oxygen potential range to obtain the comprehensive deviation matching result.

[0074] A preset oxygen potential range is a predetermined range of oxygen potential values ​​that considers the characteristics of the reduction reaction and the target reaction stage. This range is typically set separately for different reduction stages to determine whether the oxygen concentration and chemical activity are at reasonable levels. In the reduction reaction of ferrotitanium powder, changes in oxygen potential directly correspond to the progress of the reaction. Setting this range ensures that the reaction proceeds under ideal oxygen concentration conditions.

[0075] The preset temperature range is a pre-determined temperature range based on the thermodynamic requirements of the reaction process. This range corresponds to the optimal temperature conditions required for different stages of the titanium-iron powder reduction process. Temperature is a core factor affecting the reaction rate; excessively high or low temperatures will interfere with the rate and efficiency of the reduction reaction. Therefore, the purpose of the preset temperature range is to maintain the furnace temperature within the optimal range, avoiding overly aggressive or mild reaction conditions, and ensuring the stable progress of the entire reaction process.

[0076] The comprehensive deviation matching result is a comprehensive conclusion drawn by comparing real-time monitoring data, such as temperature time series data and oxygen potential value time series, with preset oxygen potential ranges and temperature ranges, and analyzing the deviation between the two. It reflects the gap between the current reaction state and the ideal state. If the deviation value is large, it indicates that the reaction conditions have deviated from the expected ideal state. In this case, it is necessary to adjust parameters such as heating power and atmosphere supply to ensure the smooth progress of the reaction.

[0077] During the reduction of ferrotitanium powder, the system automatically determines the corresponding preset oxygen potential range and preset temperature range based on the current reduction stage. Specifically, it automatically retrieves the preset oxygen potential range and temperature range corresponding to the current stage and matches the real-time temperature data with the preset temperature range. First, it determines whether the real-time temperature falls within the preset range. If the temperature exceeds the range boundary, the system further analyzes the temperature change trend and fluctuation amplitude to determine whether the current heating power meets the reaction requirements. Through this boundary matching and trend analysis, the system can monitor temperature changes in real time, ensuring that the temperature is always maintained within the ideal range. The oxygen potential value time series is also synchronously matched with the preset oxygen potential range. The oxygen potential value directly reflects the dynamic changes in oxygen concentration and chemical activity during the reaction. Analyzing the trend of the oxygen potential value allows determination of whether it is within the preset oxygen potential range. The preset oxygen potential range is set based on the thermodynamic requirements of the reaction and the dynamic characteristics of the reduction reaction, while the temperature range is determined based on the ideal temperature range of the ferrotitanium powder reduction reaction, mostly referring to experimental data or historical experience. The comprehensive deviation matching result is derived by comparing and analyzing the deviations between real-time temperature data and preset temperature ranges, and between the time series of oxygen potential values ​​and preset oxygen potential ranges. The system calculates the temperature deviation and oxygen potential deviation values ​​for each time point, then summarizes and integrates these values ​​to form the comprehensive deviation matching result. This result can intuitively reflect the overall deviation of the current reaction.

[0078] Based on the above technical solution, optionally, the temperature time series data can be matched with the preset temperature range for boundary and trend analysis, and the oxygen potential value time series can be matched with the preset oxygen potential range for chemical driving force analysis, to obtain a comprehensive deviation matching result, including: Based on temperature time series data and preset temperature range, boundary matching analysis is performed to obtain the first deviation index of whether each data in the temperature time series data exceeds the preset temperature range. Based on temperature time series data and preset temperature range, trend matching analysis is performed to obtain a second deviation index between the temperature change trend of temperature time series data and preset temperature range. Chemical driving force analysis was performed based on the time series of oxygen potential values ​​and the preset oxygen potential range to obtain the driving force deviation characteristics of the time series of oxygen potential values ​​relative to the preset oxygen potential range. Based on the time series of oxygen potential values ​​and the preset oxygen potential range, a matching analysis is performed to obtain the third deviation index of whether each data point in the time series of oxygen potential values ​​deviates from the preset oxygen potential range. Based on the first deviation index, the second deviation index, the driving force deviation characteristics, and the third deviation index, a multi-dimensional weighted fusion and logical reasoning are performed to obtain a comprehensive deviation matching result.

[0079] In this scheme, the first deviation index is used to evaluate whether each data point in the temperature time series data exceeds the preset temperature range.

[0080] The second deviation index is used to assess the difference between the trend of temperature time-series data and the preset temperature range. It reflects whether the trend of temperature change over time is consistent with the expected temperature range.

[0081] The driving force deviation characteristic is the degree of deviation of the oxygen potential value time sequence from the preset oxygen potential range. It reflects whether the oxygen activity is maintained within the ideal range during the reaction process.

[0082] The third deviation index is used to measure whether data points in the oxygen potential value time series deviate from the preset oxygen potential range. The focus is on whether the oxygen potential value data points are within the preset oxygen potential range, and the specific degree of deviation.

[0083] Boundary matching analysis based on temperature time-series data and preset temperature ranges focuses on determining whether temperatures exceed the preset range. Each temperature data point is compared one by one with the upper and lower limits of the preset range. If a temperature value exceeds these limits, a deviation is generated, forming the first deviation index. The degree of deviation for each data point is calculated by directly comparing it with the range boundary values. The deviation calculation uses a simple interpolation operation, comparing each temperature value with the maximum and minimum values ​​of the preset range to obtain the deviation amount for each data point.

[0084] Trend matching analysis based on temperature time-series data and preset temperature ranges differs from boundary matching analysis in its focus. It emphasizes identifying whether the overall trend of temperature change aligns with the trend within the preset range. First, the fluctuation patterns and trends of the temperature time-series data are analyzed to assess their changing patterns over time. Then, by calculating relevant indicators such as the moving average and slope of the temperature time-series data, the trend is compared with the trend within the preset temperature range. When the current temperature trend matches the target range trend, the deviation indicator is small; if the trends are inconsistent, the deviation is amplified, forming a secondary deviation indicator. This method can identify whether temperature fluctuations conform to expected long-term patterns and promptly detect abnormal fluctuation trends.

[0085] Chemical driving force analysis is conducted based on the time series of oxygen potential values ​​and a preset oxygen potential range. Oxygen potential directly reflects changes in oxygen activity in the reaction atmosphere and has a direct impact on the reduction reaction. First, the changes in the time series of oxygen potential values ​​are analyzed, and the degree of deviation from the preset oxygen potential range is calculated. By calculating the amplitude and direction of the oxygen potential changes, it is determined whether the oxygen potential is within the normal range. If the oxygen potential value deviates significantly from the preset range, a driving force deviation characteristic is generated, clearly revealing abnormal fluctuations in oxygen activity in the atmosphere. By comparing the historical changes of the oxygen potential value data points, it is determined whether it is within the normal range, and it also reflects whether the oxygen activity is insufficient or excessive.

[0086] Matching analysis is performed based on the time series of oxygen potential values ​​and a preset oxygen potential range to determine whether the oxygen potential values ​​deviate from the preset range. Unlike previous analysis focusing on driving force deviation characteristics, this matching analysis places greater emphasis on whether the oxygen potential value of each data point strictly falls within the preset oxygen potential range. The oxygen potential value at each time point is directly compared with the upper and lower limits of the target range to calculate the deviation from that range, forming a third deviation index. When the oxygen potential value exceeds the preset range, the deviation value will show abnormal fluctuations; when the data point is within the normal range, the deviation value will be close to zero.

[0087] Based on the first deviation index, the second deviation index, the driving force deviation characteristics, and the third deviation index, multi-dimensional weighted fusion and logical reasoning are conducted. First, all deviation indices are quantified, and then different weights are assigned to each index according to its importance. After weighting, these indices comprehensively reflect whether the temperature and oxygen potential values ​​are within the normal range, and whether their changing trends meet the predetermined reaction conditions. Through logical reasoning, combined with the weighted values ​​of each deviation index, a comprehensive deviation matching result is obtained.

[0088] In this scheme, by comprehensively analyzing the deviation indicators of temperature and oxygen potential, abnormal fluctuations in the reaction process can be detected in a timely manner, potential problems can be predicted in advance, and the stability and reaction efficiency of the reduction process can be effectively guaranteed.

[0089] Step S104: Based on the comprehensive deviation matching results and the preset adjustment trigger standard, determine whether an adjustment operation needs to be performed. If an adjustment operation needs to be performed, adjust the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace based on the comprehensive deviation matching results and the preset adjustment trigger standard.

[0090] Preset adjustment trigger criteria are a predefined set of operating conditions and deviation thresholds, used to determine when to adjust the control parameters of the reaction process. When real-time temperature, oxygen potential, etc., deviate from the preset ideal range, and the deviation reaches the set threshold, the system will automatically trigger adjustment operations according to the preset criteria. The formulation of these trigger criteria requires consideration of historical operating data, experimental verification results, and reaction thermodynamic characteristics, with the ultimate goal of ensuring that the reaction is conducted under optimal process conditions throughout the entire process.

[0091] Heating power is the energy output of the furnace heating equipment at any given time point, measured in watts. The magnitude of the heating power directly determines the rate of temperature rise and fall within the furnace, thus having a crucial impact on the progress and efficiency improvement of the reduction reaction.

[0092] Atmosphere supply parameters are core parameters used to regulate gas flow rate and atmosphere composition, including three dimensions: gas velocity, gas concentration, and gas type. The real-time flow rates of reducing gases such as hydrogen and nitrogen can be adjusted via flow meters, while the concentration ratios of various gases can be precisely controlled. In the reduction reaction of ferrotitanium powder, the composition and concentration level of the furnace atmosphere are crucial, directly affecting the stability of oxygen potential, reaction rate, and reactant conversion efficiency.

[0093] When determining whether to perform an adjustment operation, the system compares the real-time calculated comprehensive deviation value with a preset threshold. The preset adjustment trigger criteria clearly define the ranges for temperature deviation and oxygen potential deviation. The system's comprehensive deviation calculation is based on two core data points: real-time temperature and oxygen potential, focusing on analyzing the degree of deviation of these two data points from their respective preset ranges. If the deviation of either indicator exceeds the preset threshold, the system immediately determines that an adjustment operation needs to be initiated. For example, if the temperature deviation exceeds ±5°C, or the oxygen potential deviation exceeds ±0.2V from the preset range, the system will automatically activate the adjustment mechanism. After the adjustment operation is initiated, the system will determine the specific adjustment amount based on the deviation magnitude.

[0094] The adjustment of heating power is based on temperature deviation. The system first compares real-time temperature data with the preset temperature range, calculating the difference between the current temperature and the target temperature—the temperature deviation. When the deviation is positive, it indicates that the furnace temperature is higher than the target value, and the system will actively reduce the heating power; when the deviation is negative, it indicates that the furnace temperature is lower than the target value, and the system will appropriately increase the heating power. The adjustment amount of heating power is usually proportional to the magnitude of the temperature deviation. For example, when the temperature deviation reaches 5°C, the system can correspondingly increase or decrease the heating power by 10%. During this process, the system continuously monitors the heating power output status and precisely controls the heating amount through proportional adjustment to ensure that the furnace temperature returns to the ideal range.

[0095] The adjustment of oxygen potential follows the same logic. The system compares the real-time oxygen potential with a preset range to analyze the direction of deviation and determine the trend of oxygen concentration change in the furnace. When the oxygen potential is too low, it means that the oxygen concentration in the furnace is too high, which will negatively affect the efficiency of the reduction reaction. At this time, the system can effectively reduce the oxygen concentration by reducing the flow rate of hydrogen or nitrogen, or by adjusting the ratio of the two gases. When the oxygen potential is too high, it means that the oxygen concentration in the furnace is too low, and the system can increase the oxygen concentration by increasing the gas flow rate or adjusting the gas composition. The adjustment amount of oxygen potential also depends on the deviation range, and the gas flow rate and concentration are precisely controlled throughout the process using flow meters. For example, when the oxygen potential deviation is 0.1V, the system can increase the hydrogen flow rate by 10% to optimize the atmosphere in the furnace and ensure that the reaction is always within the ideal oxygen potential range.

[0096] The system determines the specific adjustment ranges for heating power and atmosphere supply based on the deviations in temperature and oxygen potential. Then, it uses proportional control technology to precisely adjust various parameters, ultimately ensuring the stability and efficiency of the reaction process. After each adjustment, the system continuously tracks the reaction progress to verify whether the adjustment effect meets the expected standards. If deviations persist, the system will automatically initiate a secondary adjustment process until all reaction conditions meet the preset targets.

[0097] Based on steps S101-S104 above, by acquiring and analyzing data on temperature, atmosphere composition, oxygen potential, and reaction conditions in real time, the dynamic changes of the reduction process are accurately predicted, ensuring that the reduction reaction of ferrotitanium powder takes place under ideal conditions. By matching the deviations in temperature and oxygen potential, the heating power and atmosphere parameters are automatically adjusted to optimize and stabilize the process, thereby improving reaction efficiency and product quality.

[0098] Based on the above technical solution, optionally, the need for adjustment operation is determined based on the comprehensive deviation matching result and the preset adjustment trigger standard. If adjustment operation is required, the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace are adjusted based on the comprehensive deviation matching result and the preset adjustment trigger standard, including: The overall deviation matching results are compared with the preset adjustment trigger criteria to determine whether an adjustment operation needs to be performed. If an adjustment operation is required, the adjustment type is determined based on the comprehensive deviation matching results and the preset adjustment trigger criteria. If the adjustment type is to adjust the heating power, the heating power adjustment analysis is performed based on the comprehensive deviation matching results and the preset adjustment trigger standard to obtain the first heating power adjustment parameter, and the heating power of the ferrotitanium powder reduction furnace is adjusted based on the first heating power adjustment parameter. Accordingly, after determining the adjustment type based on the comprehensive deviation matching results and the preset adjustment trigger criteria, the method further includes: If the adjustment type is to adjust the atmosphere supply parameter, the atmosphere supply parameter adjustment analysis is performed based on the comprehensive deviation matching result and the preset adjustment trigger standard to obtain the first atmosphere supply adjustment data, and the atmosphere supply parameter of the ferrotitanium powder reduction furnace is adjusted based on the first atmosphere supply adjustment data. Accordingly, after determining the adjustment type based on the comprehensive deviation matching results and the preset adjustment trigger criteria, the method further includes: If the adjustment type is to adjust the heating power and atmosphere supply parameters, the heating power adjustment analysis and atmosphere supply parameter adjustment analysis are performed based on the comprehensive deviation matching results and the preset adjustment trigger standard to obtain the second heating power adjustment parameter and the second atmosphere supply adjustment data. The heating power and atmosphere supply parameters of the ferrotitanium powder reduction furnace are then adjusted based on the second heating power adjustment parameter and the second atmosphere supply adjustment data.

[0099] In this scheme, the adjustment type is the type of adjustment measure to be taken determined by comparing the comprehensive deviation matching result with the preset adjustment trigger standard. This determines the specific method for optimizing the reaction process, such as adjusting the heating power, atmosphere supply parameters, or adjusting both simultaneously.

[0100] The first heating power adjustment parameter is a set of values ​​calculated by combining the comprehensive deviation matching result and the preset adjustment trigger standard when adjusting the heating power alone, reflecting the specific method of adjusting the heating power.

[0101] The first atmosphere supply adjustment data is a set of parameters obtained by adjusting the atmosphere supply parameters individually based on the comprehensive deviation matching result and the preset adjustment trigger standard, which adjusts the atmosphere supply of the ferrotitanium powder reduction furnace.

[0102] The second heating power adjustment parameter is obtained after further analysis of the comprehensive deviation matching results and adjustment triggering criteria. It is used to ensure that the reaction temperature and reaction rate reach the ideal state when the heating power and atmosphere supply are adjusted simultaneously.

[0103] The second atmosphere supply adjustment data are atmosphere supply parameters derived from the analysis of comprehensive deviation matching results and adjustment triggering standards. They are used to adjust the rate or amount of atmosphere supply when simultaneously adjusting heating power and atmosphere supply, ensuring that the atmosphere inside the furnace is maintained within a suitable concentration range.

[0104] The overall deviation matching result is compared with the preset adjustment trigger standard to determine whether an adjustment operation is needed. The deviation value of each reaction parameter essentially represents the difference between the actual reaction conditions and the preset standard. Specifically, for temperature time series data, the deviation value reflects whether the actual temperature data exceeds the preset temperature range, corresponding to the first deviation index; for oxygen potential time series data, the deviation value reflects whether the actual oxygen potential value deviates from the preset range, corresponding to the third deviation index. During the comparison process, a threshold-based judgment method is used to compare each deviation value one by one. If the deviation exceeds the preset threshold, an adjustment operation is triggered. After the adjustment operation is triggered, the adjustment type is determined by combining the overall deviation matching result with the preset adjustment trigger standard. This step requires evaluating the deviation value of each reaction parameter and selecting an appropriate adjustment type based on the preset standard. If the temperature-related deviation is large, heating power adjustment is selected; if the oxygen potential-related deviation is large, atmosphere supply adjustment is selected. The selection of the adjustment type is entirely based on the deviation of each parameter to ensure that the adjustment direction aligns with the reaction requirements. In some cases, if both temperature and oxygen potential deviations are large, the system will simultaneously adjust the heating power and atmosphere supply.

[0105] If the adjustment type is determined to be heating power adjustment, a heating power adjustment analysis is conducted. Based on the comprehensive deviation matching results, the difference between the current temperature and the preset standard is analyzed to determine the range of heating power that needs adjustment. Using linear regression or least squares method, the specific heating power adjustment increment is calculated, forming the first heating power adjustment parameter, including the heating power increase / decrease range, adjustment response speed, etc., and the heating system is adjusted according to this parameter.

[0106] If the adjustment type is determined to be atmosphere supply adjustment, an atmosphere supply adjustment analysis is conducted. Focusing on the atmosphere supply quantity and concentration, the analysis compares the current atmosphere supply with the preset standard to clarify the gap between the current atmosphere supply and the ideal state, and determines the adjustment direction based on the reaction requirements. The appropriate adjustment range is calculated using relevant algorithms to generate the first atmosphere supply adjustment data, including the atmosphere concentration adjustment amount and supply rate, and the atmosphere supply parameters of the reduction furnace are automatically adjusted based on this data.

[0107] If the adjustment type involves simultaneously adjusting both heating power and atmosphere supply parameters, the analysis of both adjustments is performed concurrently. Based on the comprehensive deviation matching results, the adjustment requirements for heating power and atmosphere supply are calculated separately to ensure coordinated adaptation. The least squares method is used to analyze the heating power adjustment range, and a PID control algorithm is used to calculate the atmosphere supply adjustment amount, forming the second heating power adjustment parameter and the second atmosphere supply adjustment data. Based on these two parameters, the heating power and atmosphere supply are adjusted synchronously.

[0108] In this scheme, by accurately analyzing the deviations of reaction parameters and selecting appropriate adjustment types, the stability and efficiency of the reaction process are ensured. Real-time adjustment of heating power and atmosphere supply optimizes reaction conditions, effectively improving reaction efficiency, reducing the risk of abnormalities, and ensuring the smooth progress of the titanium-iron powder reduction process.

[0109] See appendix Figure 2 , Figure 2 This is a schematic flowchart of the second main step in a method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to an embodiment of the present invention. Figure 2 As shown, the oxygen potential and temperature synergistic control method for the reduction preparation of titanium iron powder in an embodiment of the present invention mainly includes the following steps S201-S208.

[0110] Step S201: During the reduction preparation of ferrotitanium powder, acquire the temperature time series data and atmosphere composition time series data inside the ferrotitanium powder reduction furnace within a preset time window. Based on the temperature time series data and atmosphere composition time series data, perform oxygen potential value time series calculation and reduction environment analysis to obtain the oxygen potential value time series sequence and atmosphere state data sequence inside the ferrotitanium powder reduction furnace.

[0111] Step S202: Obtain reaction condition data, and based on the reaction condition data, oxygen potential time sequence, and atmosphere state data sequence, perform reduction reaction kinetic analysis and reaction evolution trajectory deduction to determine the current reduction stage of the titanium iron powder reduction process.

[0112] Step S203: Based on the current reduction stage, determine the corresponding preset oxygen potential range and preset temperature range, perform boundary and trend matching between the temperature time series data and the preset temperature range, and perform chemical driving force matching between the oxygen potential value time series and the preset oxygen potential range to obtain the comprehensive deviation matching result.

[0113] Step S204: Based on the comprehensive deviation matching results and the preset adjustment trigger standard, determine whether an adjustment operation needs to be performed. If an adjustment operation needs to be performed, adjust the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace based on the comprehensive deviation matching results and the preset adjustment trigger standard.

[0114] Step S205: After each preset update time interval, reacquire the temperature time series data and atmosphere composition time series data inside the ferrotitanium powder reduction furnace within the preset time window. Based on the temperature time series data and atmosphere composition time series data, perform oxygen potential value time series calculation and reduction environment analysis to obtain the oxygen potential value time series sequence and atmosphere state data sequence inside the ferrotitanium powder reduction furnace.

[0115] Step S206: Reacquire reaction condition data, and based on the reaction condition data, oxygen potential time sequence, and atmosphere state data sequence, perform reduction reaction kinetic analysis and reaction evolution trajectory deduction to determine the current reduction stage of the titanium iron powder reduction process.

[0116] Step S207: Re-determine the corresponding preset oxygen potential range and preset temperature range based on the current reduction stage, perform boundary and trend matching between the temperature time series data and the preset temperature range, and perform chemical driving force matching between the oxygen potential value time series and the preset oxygen potential range to obtain the comprehensive deviation matching result.

[0117] Step S208: Re-determine whether adjustment operation needs to be performed based on the comprehensive deviation matching result and the preset adjustment trigger standard. If adjustment operation needs to be performed, adjust the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace based on the comprehensive deviation matching result and the preset adjustment trigger standard until the ferrotitanium powder is reduced.

[0118] In this embodiment, the preset update time interval is the time interval at which data is periodically monitored and updated during the reduction of ferrotitanium powder, ensuring real-time tracking of changes in the reaction environment inside the furnace.

[0119] Each time the preset update interval is reached, the data acquisition and analysis process is repeated, and the comprehensive deviation matching result is re-determined. If, based on the comprehensive deviation matching result and the preset adjustment trigger standard, it is determined that no adjustment operation is required, the above steps are repeated after the next preset update interval. If an adjustment operation is required, the heating power and / or atmosphere supply parameters are readjusted until the reduction of ferrotitanium powder is complete. The completion of the ferrotitanium powder reduction reaction requires comprehensive evaluation of multiple indicators, including oxygen concentration, oxygen potential, hydrogen concentration, temperature change, and reaction kinetics analysis. During the reduction reaction, the oxygen concentration in the furnace shows a continuous decreasing trend. When the oxygen is almost completely consumed and the oxygen potential value simultaneously drops to the preset minimum threshold, it means that the reaction is nearing its end. Simultaneously, the gradual increase in hydrogen concentration and the stable maintenance of the furnace temperature are also intuitive indicators of the orderly progress of the reaction. Reaction kinetics analysis can be used to further verify whether the reaction has entered the final stage. When all the above parameters meet the preset judgment criteria, or the actual reaction time is close to the theoretical estimate, it can be concluded that the ferrotitanium powder reduction process has been successfully completed.

[0120] In this embodiment, the changes in various key parameters during the reduction process of ferrotitanium powder can be monitored in real time to ensure that the reaction is in optimal condition. By regularly updating the data, abnormal situations can be detected in a timely manner, thereby quickly adjusting the reaction conditions to avoid excessively high or low reaction rates and ensuring the stability and efficiency of the reaction.

[0121] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0122] Furthermore, the present invention also provides an oxygen potential and temperature synergistic control system for the reduction preparation of ferrotitanium powder.

[0123] See appendix Figure 3 , Figure 3 This is a main structural block diagram of an oxygen potential-temperature synergistic control system for the reduction preparation of titanium-iron powder according to an embodiment of the present invention. Figure 3 As shown, it specifically includes: The data acquisition and analysis module 301 is used to acquire temperature time-series data and atmosphere composition time-series data inside the ferrite powder reduction furnace within a preset time window during the ferrite powder reduction preparation process, and to perform oxygen potential time-series calculation and reduction environment analysis based on the temperature time-series data and atmosphere composition time-series data to obtain the oxygen potential time-series sequence and atmosphere state data sequence inside the ferrite powder reduction furnace. The reaction stage deduction module 302 is used to acquire reaction condition data, and based on the reaction condition data, oxygen potential value time sequence and atmosphere state data sequence, to perform reduction reaction kinetic analysis and reaction evolution trajectory deduction, and to determine the current reduction stage of the titanium iron powder reduction process. The deviation matching analysis module 303 is used to determine the corresponding preset oxygen potential range and preset temperature range based on the current reduction stage, perform boundary and trend matching between the temperature time series data and the preset temperature range, and perform chemical driving force matching between the oxygen potential value time series and the preset oxygen potential range to obtain a comprehensive deviation matching result. The adjustment module 304 is used to determine whether an adjustment operation needs to be performed based on the comprehensive deviation matching result and the preset adjustment trigger standard. If an adjustment operation needs to be performed, the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace are adjusted based on the comprehensive deviation matching result and the preset adjustment trigger standard.

[0124] The oxygen potential and temperature coordinated control system for the reduction preparation of ferrotitanium powder provided in this application embodiment can achieve... Figure 1 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0125] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0126] Furthermore, the present invention also provides an electronic device 400, including a processor 401, a memory 402, and a program or instructions stored in the memory 402 and executable on the processor 401. When the program or instructions are executed by the processor 401, they implement the various processes of the above-described embodiment of the oxygen potential and temperature synergistic control method for the reduction preparation of titanium iron powder, and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0127] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0128] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program for performing a method for oxygen potential and temperature co-control of titanium-iron powder reduction preparation according to the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described method for oxygen potential and temperature co-control of titanium-iron powder reduction preparation. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0129] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0130] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0131] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for synergistic control of oxygen potential and temperature in the reduction preparation of titanium-iron powder, characterized in that, The method includes: In the process of reducing ferrite powder, temperature time series data and atmosphere composition time series data inside the ferrite powder reduction furnace within a preset time window are obtained. Based on the temperature time series data and atmosphere composition time series data, oxygen potential value time series calculation and reduction environment analysis are performed to obtain the oxygen potential value time series sequence and atmosphere state data sequence inside the ferrite powder reduction furnace. Acquire reaction condition data, and based on the reaction condition data, oxygen potential time sequence, and atmosphere state data sequence, perform reduction reaction kinetic analysis and reaction evolution trajectory deduction to determine the current reduction stage of the ferrotitanium powder reduction process; Based on the current reduction stage, the corresponding preset oxygen potential range and preset temperature range are determined. The temperature time series data is matched with the preset temperature range for boundary and trend, and the oxygen potential value time series is matched with the preset oxygen potential range for chemical driving force to obtain the comprehensive deviation matching result. Based on the comprehensive deviation matching results and the preset adjustment trigger standard, it is determined whether an adjustment operation needs to be performed. If an adjustment operation needs to be performed, the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace are adjusted based on the comprehensive deviation matching results and the preset adjustment trigger standard.

2. The method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to claim 1, characterized in that, in, After adjusting the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace based on the comprehensive deviation matching results and the preset adjustment trigger standard, the method further includes: After each preset update interval, the temperature time series data and atmosphere composition time series data inside the ferrotitanium powder reduction furnace within the preset time window are reacquired. Based on the temperature time series data and atmosphere composition time series data, the oxygen potential value time series sequence calculation and reduction environment analysis are performed to obtain the oxygen potential value time series sequence and atmosphere state data sequence inside the ferrotitanium powder reduction furnace. Reacquire reaction condition data, and based on the reaction condition data, oxygen potential time sequence, and atmosphere state data sequence, perform reduction reaction kinetic analysis and reaction evolution trajectory deduction to determine the current reduction stage of the ferrotitanium powder reduction process; The corresponding preset oxygen potential range and preset temperature range are redefined based on the current reduction stage. The temperature time series data are matched with the preset temperature range for boundary and trend. The oxygen potential value time series is matched with the preset oxygen potential range for chemical driving force to obtain the comprehensive deviation matching result. Based on the comprehensive deviation matching results and the preset adjustment triggering criteria, determine whether an adjustment operation is required. If an adjustment operation is required, adjust the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace based on the comprehensive deviation matching results and the preset adjustment triggering criteria until the ferrotitanium powder is completely reduced.

3. The method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to claim 1, characterized in that, in, Based on the aforementioned temperature time-series data and atmosphere composition time-series data, oxygen potential time-series calculation and reduction environment analysis are performed to obtain the oxygen potential time-series and atmosphere state data sequences inside the ferrotitanium powder reduction furnace, including: Based on the atmospheric composition time series data and temperature time series data, gas concentration distribution analysis is performed to obtain oxidizing component concentration data and reducing component concentration data. The time series of oxygen potential values ​​inside the ferrotitanium powder reduction furnace was calculated based on the concentration data of oxidizing components and reducing components. Reaction kinetics correction analysis was performed based on temperature time series data, oxidizing component concentration data, and reducing component concentration data to obtain oxidizing component activity assessment data and reducing component activity assessment data. Based on the time sequence of oxygen potential values, the activity assessment data of oxidizing components, and the activity assessment data of reducing components, an overall atmospheric state analysis was conducted to obtain the atmospheric state data sequence inside the ferrotitanium powder reduction furnace.

4. The method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to claim 1, characterized in that, in, Based on the aforementioned reaction condition data, oxygen potential time series, and atmosphere state data series, reduction reaction kinetic analysis and reaction evolution trajectory deduction are performed to determine the current reduction stage of the ferrotitanium powder reduction process, including: Feature extraction was performed based on the time series of oxygen potential values ​​to obtain the feature vector of the reaction process; The reaction rate is calculated based on the reaction process feature vector and the atmospheric state data sequence to obtain the reaction rate data. The reaction process feature vector and reaction rate data are mapped to a preset critical criterion space, and the critical conditions of the reaction are compared to obtain the critical state identification results. Based on reaction condition data, reaction rate data, reaction process feature vector, and critical state identification results, the current reaction kinetic feature data are generated by fusing them together. Obtain historical reaction kinetics characteristic data sequences, perform time series modeling based on historical reaction kinetics characteristic data sequences, and obtain historical evolution paths; Based on current reaction kinetics data and historical evolution paths, multidimensional coupling analysis is performed to determine the current reduction stage of the titanium-iron powder reduction process.

5. The method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to claim 4, characterized in that, in, Based on current reaction kinetics data and historical evolution paths, multidimensional coupling analysis is performed to determine the current reduction stage of the titanium-iron powder reduction process, including: Based on the current reaction kinetics characteristic data, the reaction rate change pattern is extracted to obtain the reaction rate change pattern; Stage identification parameters are extracted based on the current reaction kinetics characteristic data to obtain the stage identification parameters; Multidimensional trend comparisons were performed based on reaction rate change patterns and historical evolution paths to obtain deviation characteristic data; Reaction inflection point data is obtained by identifying reaction inflection points based on deviation feature data. Stability assessment is performed based on reaction inflection point data to obtain stability judgment results; Based on stage identification parameters, reaction inflection point data, and stability assessment results, a multi-dimensional weighted decision is made to determine the current reduction stage of the titanium iron powder reduction process.

6. The method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to claim 1, characterized in that, in, The temperature time series data is matched against the preset temperature range for boundary and trend analysis, and the oxygen potential value time series is matched against the preset oxygen potential range for chemical driving force analysis, to obtain a comprehensive deviation matching result, including: Based on temperature time series data and preset temperature range, boundary matching analysis is performed to obtain the first deviation index of whether each data in the temperature time series data exceeds the preset temperature range. Based on temperature time series data and preset temperature range, trend matching analysis is performed to obtain a second deviation index between the temperature change trend of temperature time series data and preset temperature range. Chemical driving force analysis was performed based on the time series of oxygen potential values ​​and the preset oxygen potential range to obtain the driving force deviation characteristics of the time series of oxygen potential values ​​relative to the preset oxygen potential range. Based on the time series of oxygen potential values ​​and the preset oxygen potential range, a matching analysis is performed to obtain the third deviation index of whether each data point in the time series of oxygen potential values ​​deviates from the preset oxygen potential range. Based on the first deviation index, the second deviation index, the driving force deviation characteristics, and the third deviation index, a multi-dimensional weighted fusion and logical reasoning are performed to obtain a comprehensive deviation matching result.

7. The method for synergistic control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to claim 1, characterized in that, in, Based on the comprehensive deviation matching results and the preset adjustment trigger criteria, it is determined whether an adjustment operation needs to be performed. If an adjustment operation is required, the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace are adjusted based on the comprehensive deviation matching results and the preset adjustment trigger criteria, including: The overall deviation matching results are compared with the preset adjustment trigger criteria to determine whether an adjustment operation needs to be performed. If an adjustment operation is required, the adjustment type is determined based on the comprehensive deviation matching results and the preset adjustment trigger criteria. If the adjustment type is to adjust the heating power, the heating power adjustment analysis is performed based on the comprehensive deviation matching results and the preset adjustment trigger standard to obtain the first heating power adjustment parameter, and the heating power of the ferrotitanium powder reduction furnace is adjusted based on the first heating power adjustment parameter. Accordingly, after determining the adjustment type based on the comprehensive deviation matching results and the preset adjustment trigger criteria, the method further includes: If the adjustment type is to adjust the atmosphere supply parameter, the atmosphere supply parameter adjustment analysis is performed based on the comprehensive deviation matching result and the preset adjustment trigger standard to obtain the first atmosphere supply adjustment data, and the atmosphere supply parameter of the ferrotitanium powder reduction furnace is adjusted based on the first atmosphere supply adjustment data. Accordingly, after determining the adjustment type based on the comprehensive deviation matching results and the preset adjustment trigger criteria, the method further includes: If the adjustment type is to adjust the heating power and atmosphere supply parameters, the heating power adjustment analysis and atmosphere supply parameter adjustment analysis are performed based on the comprehensive deviation matching results and the preset adjustment trigger standard to obtain the second heating power adjustment parameter and the second atmosphere supply adjustment data. The heating power and atmosphere supply parameters of the ferrotitanium powder reduction furnace are then adjusted based on the second heating power adjustment parameter and the second atmosphere supply adjustment data.

8. A synergistic control system for oxygen potential and temperature in the reduction preparation of titanium-iron powder, characterized in that, The system includes: The data acquisition and analysis module is used to acquire temperature time-series data and atmosphere composition time-series data inside the ferrite powder reduction furnace within a preset time window during the ferrite powder reduction preparation process. Based on the temperature time-series data and atmosphere composition time-series data, the oxygen potential value time-series sequence is calculated and the reduction environment is analyzed to obtain the oxygen potential value time-series sequence and atmosphere state data sequence inside the ferrite powder reduction furnace. The reaction stage simulation module is used to acquire reaction condition data, and based on the reaction condition data, oxygen potential time sequence and atmosphere state data sequence, to perform reduction reaction kinetic analysis and reaction evolution trajectory simulation to determine the current reduction stage of the titanium iron powder reduction process. The deviation matching analysis module is used to determine the corresponding preset oxygen potential range and preset temperature range based on the current reduction stage, perform boundary and trend matching between the temperature time series data and the preset temperature range, and perform chemical driving force matching between the oxygen potential value time series and the preset oxygen potential range to obtain the comprehensive deviation matching result. The adjustment module is used to determine whether an adjustment operation needs to be performed based on the comprehensive deviation matching result and the preset adjustment trigger standard. If an adjustment operation needs to be performed, the heating power and / or atmosphere supply parameters of the ferrotitanium powder reduction furnace are adjusted based on the comprehensive deviation matching result and the preset adjustment trigger standard.

9. An electronic device comprising a processor, a memory, and a program or instructions stored in the memory and executable on the processor, characterized in that, The program or instructions are adapted to be loaded and run by the processor to perform a method for coordinated control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform a method for coordinated control of oxygen potential and temperature in the reduction preparation of ferrotitanium powder according to any one of claims 1 to 7.

Images