A method, system, and storage medium for controlling the level of a sinter mix tank

Abstract

This invention provides a method, system, and storage medium for controlling the level of a sintering mixing tank. The method includes: predicting the future level of the mixing tank; generating a feedforward control command vector for the current adjustment cycle based on the causes of future level fluctuations exceeding limits; generating a feedback correction command vector for the currently dominant feedforward channel based on the level deviation in the current adjustment cycle; generating a composite control command based on the feedforward control command vector and the feedback correction command vector; if the composite control command meets the constraints, updating the control parameters for the current adjustment cycle and sending them to the actuator; otherwise, re-predicting the future level of the mixing tank. This invention achieves feedforward-feedback composite control by predicting level fluctuations in advance and matching them with corresponding feedforward control strategies, and by combining feedback correction with the error between the actual and predicted level values. Simultaneously, the constraints ensure the rationality of the control commands, achieving accurate, stable, and safe level control.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for iron ore sintering production processes, specifically to a method, system, and storage medium for controlling the material level in a sintering mixing tank. Background Technology

[0002] Sintering is a crucial process in steel metallurgical production, and maintaining a stable material level in the sintering mixing tank is a key prerequisite for ensuring the continuous, efficient, and low-consumption operation of the sintering machine. Excessively high material levels can easily lead to the breakage of material pellets, affecting sintering permeability; conversely, excessively low material levels may cause machine shutdowns due to material shortages, disrupting the continuous production rhythm.

[0003] In the development of material level control technology, the earliest material level control relied entirely on manual adjustment by operators. This method was based on the operator's experience, had a large response lag, low control accuracy, and high labor intensity, and could not meet the needs of modern, high-paced sintering production.

[0004] To overcome the drawbacks of manual control, automatic control methods based on real-time material input-output deviations have emerged. For example, Chinese patent CN101441445B discloses a sintering material balance method and system. Its core idea is to calculate the input-output deviation of the mixing tank (Whsd = material level setpoint - material level measurement + expected discharge amount - expected inflow amount), and adjust the overall material conveying rate according to whether the deviation exceeds a preset threshold when the material level is in different ranges (such as the ideal material level range and the alarm range).

[0005] While these methods achieve automated control, they still have significant limitations: a) Response Lag and Perception Limitations: This type of method is essentially a reactive correction strategy, where control actions are only triggered after a level deviation has occurred. Due to a significant lag of 10-15 minutes in material transport from the batching point to the mixing tank, the control system cannot act in advance and is constantly passively chasing the deviation. Furthermore, its input parameters are insufficient, failing to perceive potential level fluctuations caused by changes in material physical properties (such as particle size and moisture content), resulting in poor control performance.

[0006] b) Rigid control strategy and lack of intelligent decision-making: When disturbances occur, the system cannot intelligently select the most appropriate control method based on the root cause of the disturbance (whether it is fluctuation in incoming materials, changes in sintering machine demand, or abnormal material properties) and complex operational constraints. Its control logic is relatively fixed and has poor adaptability.

[0007] c) Single control method and potential conflict of objectives: This type of method mainly relies on adjusting the feed rate (overall material flow rate) to achieve balance. However, under complex operating conditions, it is sometimes necessary to mobilize other control methods (such as fine-tuning the roller speed or adjusting material properties through steam). However, existing methods lack a strategy to consider these methods in a coordinated manner. For example, if attempting to stabilize the material level by adjusting the moisture content of the mixture, it may jeopardize the stability of the key quality indicator of moisture, causing a conflict between control objectives, and making operators hesitant to use automatic control mode.

[0008] Therefore, there is still room for improvement in existing technologies. There is an urgent need for a new material level control method and system that can act in advance, make intelligent decisions, make full use of all available control means, and ensure process quality and safety, so as to overcome the inherent bottlenecks of control methods based on real-time profit and loss deviations. Summary of the Invention

[0009] The purpose of this invention is to provide a method for controlling the material level in a sintering mixing tank. This method aims to achieve feedforward-feedback composite control by predicting material level fluctuations in advance and matching them with a corresponding feedforward control strategy. It also incorporates feedback correction based on the error between the actual material level and the model's predicted value. Simultaneously, constraints ensure the rationality of the control commands, ultimately achieving precise, stable, and safe control of the material level in the mixing tank. The specific technical solution is as follows: A method for controlling the material level in a sintering mixing tank, comprising the following steps: A1. In the current adjustment cycle Internal prediction obtains the material level value of the mixing tank at at least one future moment; A2. Determine whether the deviation between the predicted material level and the set material level exceeds the allowable fluctuation range. If it exceeds the limit, proceed to step A3. If it does not exceed the limit, keep the control parameters of the previous adjustment cycle unchanged and return to step A1. A3. Based on the relationship between the current material moisture content and the process dead zone, as well as the magnitude of future material level deviation, generate the current adjustment cycle according to the preset priority. Feedforward control command vector ; A4. Based on the current adjustment cycle The actual material level in the mixing tank and predicted material level The deviation between them generates a feedback correction command vector for the currently dominant feedforward channel. ; A5. Based on feedforward control command vector and feedback correction command vector Generate composite control commands ; Determine the composite control command If the constraints are met, then proceed based on the composite control command. Update the current adjustment cycle The control parameters are then sent to the actuator; if they are not met, the process returns to step A1.

[0010] Preferably, the feedforward control command vector is represented as follows: ; If the detected material moisture value Deviation from process dead zone And the duration is greater than the threshold Then, based on the ideal moisture value of the process... and The moisture setpoint adjustment amount for the current cycle is calculated. ,Will , and Set to zero and output the current feedforward control command vector. ; If the detected material moisture value In process dead zones Internal, and future material level deviation The duration is greater than the threshold Then, based on the material level setting value of the mixing tank. and future Predicted material level at any given time Calculate the ingredient quantity adjustment value for the current cycle. ,Will , and Set to zero and output the current feedforward control command vector. ; If the detected material moisture value In process dead zones Inside, and The duration is greater than the threshold Then, based on the material level setting value of the mixing tank. and future Predicted material level at any given time Calculate the roller speed adjustment value for the current cycle. ,Will , and After setting to zero, output the current feedforward control command vector. ; If the detected material moisture value In process dead zones Inside, and The duration is greater than the threshold Then, based on the material level setting value of the mixing tank. and future Predicted material level at any given time Calculate the steam injection flow rate adjustment value for the current cycle. ,Will , and After setting to zero, output the current feedforward control command vector. ; in, Indicates the current period The corresponding time, The delayed response time is the time taken to account for the impact of the actual overall conveying capacity of the batching area on the material level. Add a delayed response time to the effect of steam flow rate on material level in the secondary mixer. The delayed response time is the time required to account for the effect of the rotational speed of the roller feeder on the material level. The lower limit of the permissible moisture value, The upper limit of the allowable moisture content, , and All are preset thresholds. Indicates the future Material level deviation at any given time Indicates the future Material level deviation at any given time Indicates the future The deviation of material level at any given time.

[0011] Preferably, the moisture setpoint adjustment amount for the current cycle. Represented as: in, , This is the integral gain.

[0012] Preferred, the ingredient quantity adjustment value for the current cycle Represented as: in, This is the feedforward scaling factor.

[0013] Preferred adjustment value for the roller speed in the current cycle Represented as: in, This is the feedforward scaling factor.

[0014] Preferred steam injection flow rate adjustment value for the current cycle Represented as: in, This is the feedforward scaling factor.

[0015] Preferably, a feedback correction command vector is generated for the currently dominant feedforward channel. Specifically: A4.1 Establish a soft sensor model to predict the discharge rate of the mixing tank. ; A4.2, Based on the actual material level in the mixing tank during the previous cycle. Feed rate and output Calculate the predicted material level for the current cycle. ;in, , This indicates the system's correction period in seconds, with 3600 being the conversion factor between hours and seconds. A4.3, Based on the actual material level in the current cycle and predicted material level Calculate the current material level deviation Based on the current material level deviation Generate feedback correction command vector for the currently dominant feedforward channel. ; in, Feedback correction command vector It is a feedforward control command vector For vectors of the same dimension, only the component corresponding to the current dominant mode is non-zero; this is the feedback correction command vector. , For proportional gain, For integral gain, This is the cumulative sum of historical material level deviations.

[0016] Preferably, based on the set constraints... The non-zero components in the data are subjected to security checks. The non-zero components in the equation do not satisfy the rate of change constraint, according to After the non-zero components in the data are adjusted, the corresponding parameter amplitude does not meet the amplitude constraint or is adjusted according to... If the adjustment of non-zero components does not meet the process adjustment constraints, the safety check is considered to have failed, and the process needs to return to step A1. If the safety check passes, then... The non-zero component in the current cycle is added to the corresponding value in the previous cycle to generate the corresponding set value for the current cycle, which is then sent to the actuator.

[0017] The present invention also provides a material level control system for a sintering mixing tank, including a memory and a processor, wherein the memory stores a computer program, and the computer program is executed by the processor to perform the material level control method.

[0018] The present invention also provides a storage medium storing a computer program, which, when run, executes the material level control method.

[0019] The application of the technical solution of the present invention has the following beneficial effects: This invention enables advanced control of material level by predicting the future material level change trend in the mixing tank through a predictive model. It transforms post-event correction into proactive prediction, effectively solving the control lag problem caused by large material conveying delays. It can trigger control actions in advance and suppress material level fluctuations at the source.

[0020] This invention enables precise matching of control strategies. By analyzing the specific causes of material level fluctuations, it matches different fluctuation causes with corresponding feedforward control strategies one by one, avoiding the problems of rigid strategies and single control means in traditional control methods. It achieves personalized and precise control of material level and improves control effectiveness.

[0021] The invention employs a composite control system with strong anti-disturbance capabilities. Feedforward control addresses predictable material level fluctuations, while feedback correction corrects the inaccuracies of the feedforward model and unknown disturbances during the sintering process. The two work together to significantly improve the anti-disturbance capability and robustness of the control system. This invention can ensure safe and reasonable control actions. By setting constraints, it avoids large changes and out-of-range adjustments of control parameters, prevents equipment overload and process index exceeding the standard, and ensures the safety and process stability of sintering production. This invention employs a closed-loop control process with periodic adjustments. If the parameters are within limits, they remain unchanged; if they exceed limits, control is triggered; if safety constraints are not met, prediction is re-established. The process is simple and the logic is rigorous, ensuring that the material level in the mixing tank is always kept within the range allowed by the process, thus improving the overall stability of the material level control.

[0022] In addition to the objectives, features, and advantages described above, the present invention has other objectives, features, and advantages. The invention will now be described in further detail with reference to the figures. Attached Figure Description

[0023] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a schematic diagram of the iron ore sintering process; Figure 2 This is a flowchart of the material level prediction method in the sintering mixing tank in Example 1; Figure 3This is a diagram of the deep neural network architecture based on gated recurrent units (GRU) in Example 1; Figure 4 This is a flowchart of the sintering mixture tank level control method in Example 2. Detailed Implementation

[0024] To facilitate understanding of the present invention, a more complete description is provided below, along with preferred embodiments. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a thorough and complete understanding of the disclosure of the present invention.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0026] Example 1: Figure 1 This is a schematic diagram of the iron ore sintering process. The batching area is equipped with a return ore trough, a mixing ore trough, a solvent trough, a fuel trough, a dust trough, a dolomite trough, and a quicklime trough. The materials are metered and fed to the mixing-1A belt conveyor by the corresponding batching small belt scales to form a mixture. The mixture is then passed through a primary mixer and a secondary mixer for mixing and granulation before entering a mixing trough for temporary storage. Subsequently, the mixture is transported from the mixing trough to the sintering machine to complete the sintering operation. The sinter discharged from the sintering machine enters an annular cooler for cooling. After cooling, the sinter is classified by a screening system and divided into three paths: one path is transported to the return ore trough for recycling, one path is transported to the bottom material trough as the bottom material for the sintering machine, and the other path is transported to the blast furnace for smelting or sent to the finished ore bin for storage.

[0027] To address the inherent limitations of existing technologies in sensing dimensions, temporal alignment, and model selection, which lead to problems such as lag, inaccuracy, and poor robustness in predicting material levels in mixing troughs, such as... Figure 2 As shown, this embodiment provides a method for predicting the material level in a sintering mixing tank, aiming to accurately depict the causal chain of material flow and achieve early, high-precision material level prediction. The prediction method includes the following steps: S1. Obtain historical material conveying parameters of the batching area, operating parameters of the primary mixer, operating parameters of the secondary mixer, operating parameters of the mixing tank, and operating parameters of the sintering machine; S2. Based on the response delay time of different parameters to the material level in the mixing tank, perform time-series alignment of the historical parameters. S3. Divide the time-series aligned parameters into training, validation, and test sets to complete the training of the prediction model; S4. Deploy the trained prediction model online and collect the material conveying parameters in the batching area, the working parameters of the primary mixer, the working parameters of the secondary mixer, the working parameters of the mixing tank, and the working parameters of the sintering machine. S5. After aligning the real-time collected material conveying parameters of the batching area, the operating parameters of the primary mixer, and the operating parameters of the secondary mixer with the time sequence, input them together with the real-time collected operating parameters of the mixing trough and the sintering machine into the prediction model to predict the material level value of the mixing trough at future times. .

[0028] Steps S1-S5 will be explained in detail below: Preferably, the material conveying parameters of the batching area include the target comprehensive conveying capacity of the batching area X101 and the actual comprehensive conveying capacity of the batching area X102.

[0029] Specifically, the target comprehensive conveying capacity X101 and the actual comprehensive conveying capacity X102 of the batching area can be the actual material conveying capacity of the batching area and the batching error (i.e. the difference between the target comprehensive conveying capacity X101 and the actual comprehensive conveying capacity X102 of the batching area) can be used as inputs to the prediction model. The batching error, as a powerful feedforward signal, can provide early warning of future material level fluctuations caused by inaccurate batching.

[0030] like Figure 1 As shown, the batching area is fed by several small batching belt scales, all of which fall onto the mixing-1A conveyor belt below for conveying. When the mixing-1A conveyor belt starts, feeding begins from the first batching belt. After a delay of a few seconds (usually about 5 seconds), the next batching belt starts, and so on, until the last batching belt starts. This ensures that all materials are fed according to the proportions at startup, without material waste during the transition period. Similarly, if the mixing-1A conveyor belt stops for any reason during normal operation, all batching belts will stop with material on them. Upon startup, they must start simultaneously to ensure that the proportions are not affected. In this embodiment, the actual comprehensive conveying volume X102 of the batching area is the material volume at the material drop point of the last batching belt (i.e., the material volume where all materials converge simultaneously).

[0031] Preferably, the operating parameters of the primary mixer include the primary mixer inlet belt conveyor capacity x103, the primary mixer outlet belt conveyor capacity x104, and the primary mixer outlet material moisture content x105.

[0032] Specifically, the moisture content of the primary mixer outlet material multiplied by 10⁵ is one of the key inputs to the prediction model. This parameter characterizes the material's viscosity and flowability. Abnormal material moisture content (too high / too low) is one of the root causes of abnormal operating conditions such as overflowing or artificially high material levels. Using the primary mixer's operating parameters as input parameters allows the prediction model to learn the impact of changes in these parameters on the material level in the mixing trough, thus ensuring the accuracy of the material level prediction.

[0033] Preferably, the operating parameters of the secondary mixer include: secondary mixer inlet belt conveyor flow rate X106, secondary mixer outlet belt conveyor flow rate X107, secondary mixer outlet material moisture content X108, secondary mixer added steam flow rate X109, secondary mixer added steam pressure X110, secondary mixer added steam temperature X111, the proportion of secondary mixer (granulator) outlet material with a particle size distribution less than 3mm X112, the proportion of secondary mixer (granulator) outlet material with a particle size distribution of 3-8mm X113, and the proportion of secondary mixer (granulator) outlet material with a particle size distribution greater than 8mm X114.

[0034] Specifically, the moisture content of the material at the outlet of the secondary mixer, X108, is one of the key inputs to the prediction model. This parameter is used to characterize the viscosity and flowability of the material. Abnormal material moisture content (too high / too low) is one of the root causes of abnormal operating conditions such as material overflow or artificially high material levels.

[0035] Meanwhile, the steam flow rate X109, steam pressure X110, and steam temperature X111 added by the secondary mixer reflect the final conditioning of the material, affecting its temperature and pre-humidity, and are the final fine-tuning of the material's state before it enters the mixing tank.

[0036] Finally, the proportion of particles smaller than 3mm at the outlet of the secondary mixer (granulator) X112, the proportion of particles between 3-8mm at the outlet of the secondary mixer (granulator) X113, and the proportion of particles larger than 8mm at the outlet of the secondary mixer (granulator) X114 are the key physical properties of the material's bulk density and flowability. Specifically, a high proportion of fine particles (<3mm) leads to a high bulk density, occupying less space in the trough, resulting in a lower material level; at the same time, poor flowability easily causes poor discharge. A high proportion of qualified particles (3-8mm) indicates good material flowability and stable packing, which is an ideal state. A high proportion of coarse particles (>8mm) indicates excessively good material flowability and low bulk density, resulting in a lighter weight for the same volume, which easily leads to artificially high and fluctuating material levels. Parameters X112, X113, and X114 are key to explaining the unexplained fluctuations in the level of the mixing tank. Using them as inputs to the prediction model can directly explain and predict many unexplained level fluctuations, and they are key variables to make up for the blind spots in the existing prediction input parameter system.

[0037] Preferably, the operating parameters of the mixing tank include the inlet conveying rate of the mixing tank X115, the outlet material temperature of the mixing tank X116, the real-time material level of the mixing tank X117, the material level change rate of the mixing tank per unit time X118, the opening degree of each fine-tuning gate at the outlet of the mixing tank X119, the preheating steam flow rate of the mixing tank X120, the preheating steam pressure of the mixing tank X121, and the preheating steam temperature of the mixing tank X122; furthermore, depending on the size of the mixing tank, there are generally 5-8 fine-tuning gates. In this embodiment, the opening degree of each fine-tuning gate is recorded as X119_1-X119_N and input into the prediction model, where N represents the total number of fine-tuning gates.

[0038] Specifically, the operating parameters of the mixing tank can reflect the consumption of the mixture, the trend of material level changes, and momentum information, helping the prediction model learn the correlation between material level changes and various input parameters. Among them, the material temperature X116 at the outlet of the mixing tank can comprehensively reflect the thermal state of the material, indirectly verifying the regulation effect of steam.

[0039] Preferably, the sintering machine operating parameters include the rotary feeder speed x123, the sintering machine trolley speed x124, and the sintering machine trolley material layer thickness x125. Specifically, the sintering machine operating parameters reflect the consumption of the mixture in the mixing tank, helping the prediction model learn the correlation between sintering consumption and material level changes.

[0040] Specifically, in this embodiment, the units of the target comprehensive conveying capacity X101, the actual comprehensive conveying capacity X102, the inlet belt conveying capacity of the primary mixer X103, the outlet belt conveying capacity of the primary mixer X104, the inlet belt conveying capacity of the secondary mixer X106, the outlet belt conveying capacity of the secondary mixer X107, and the inlet conveying capacity of the mixing trough X115 are all t / h; the units of the moisture content of the material at the outlet of the primary mixer X105, the moisture content of the material at the outlet of the secondary mixer X108, the proportion of the particle size distribution of the material at the outlet of the secondary mixer (granulator) less than 3mm X112, the proportion of the particle size distribution of the material at the outlet of the secondary mixer (granulator) with a particle size distribution of 3-8mm X113, and the proportion of the particle size distribution of the material at the outlet of the secondary mixer (granulator) greater than 8mm X114, and the unit time The units for the material level change rate X118 of the inner mixing tank and the opening degree of each fine-tuning gate X119 at the outlet of the mixing tank are both %; the units for the steam flow rate X109 added to the secondary mixer and the preheating steam flow rate X120 of the mixing tank are kg / h; the units for the steam pressure X110 added to the secondary mixer and the preheating steam pressure X121 of the mixing tank are MPa; the unit for the real-time material level X117 of the mixing tank is t; the unit for the rotational speed X123 of the roller feeder is rpm; the unit for the sintering machine trolley speed X124 is m / min; the unit for the material layer thickness X125 of the sintering machine trolley is mm; and the units for the steam temperature X111 added to the secondary mixer, the material temperature at the outlet of the mixing tank X116, and the preheating steam temperature X122 of the mixing tank are all °C.

[0041] Preferably, the material conveying parameters of the batching area, the operating parameters of the primary mixer, the operating parameters of the secondary mixer, the operating parameters of the mixing tank, and the operating parameters of the sintering machine are obtained by measuring sensors distributed in the sintering equipment.

[0042] Preferably, due to material flow delays during sintering, the response delay times of various parameters to the material level in the mixing tank differ. To align the parameters in time and ensure the accuracy of subsequent predictions, the method for aligning the collected parameters in step S2 is as follows: If parameter The response delay to the material level in the mixing tank is a material flow delay, therefore, in the parameters... Searching in the collection sequence The collected values ​​at each time point are used as parameters. At the present moment The values ​​input into the prediction model, where, For parameters Response delay time to the material level in the mixing tank; If parameter It can affect the material level changes in the mixing tank in real time (i.e., parameters). If there is no response delay for the material level in the mixing tank, then the parameters are directly set. The current time in the acquisition sequence The collected values ​​are input into the prediction model.

[0043] Specifically, parameters If the sampling point is located in front of the mixing tank, the delay is due to the material flow transportation (such as the material transportation parameters in the batching area, the operating parameters of the primary mixer, and the operating parameters of the secondary mixer, i.e., parameters X101-X114). Its response delay time depends on the material flow parameters. The time required for the sample to travel from the collection point to the center of the mixing trough can be calculated based on the material's conveying distance and speed, or determined by analyzing the response curves of historical adjustment records and material level change rates. This type of parameter should be sought in the preceding data collection sequence. The collected value at time t is used as the current time. Input the values ​​into the prediction model.

[0044] Furthermore, the operating parameters of the mixing tank and the sintering machine can be considered as influencing the material level in real time or near real time. Therefore, the response delay time of these parameters to the material level in the mixing tank is... These parameters directly use the current time. The collected values ​​are input into the prediction model. These parameters specifically include: mixing trough inlet conveying rate X115, mixing trough outlet material temperature X116, mixing trough real-time material level X117, mixing trough material level change rate per unit time X118, mixing trough outlet fine-tuning gate opening X119, mixing trough preheating steam flow rate X120, mixing trough preheating steam pressure X121, mixing trough preheating steam temperature X122, roller feeder speed X123, sintering machine trolley speed X124, and sintering machine trolley material layer thickness X125.

[0045] Furthermore, by normalizing the parameters after time alignment, the current time step can be constructed. eigenvectors eigenvectors These are the input parameters of the prediction model, which can be used to predict the material level at future times. .

[0046] Preferably, the prediction model in this embodiment is a Long Short-Term Memory (LSTM) network or a deep neural network architecture based on Gated Recurrent Units (GRUs). In this embodiment, a deep neural network architecture based on GRUs is selected. Compared to LSTM, the deep neural network based on GRUs merges the input gate and forget gate of LSTM into a single update gate, reducing the number of parameters by approximately 25%. While ensuring the ability to effectively capture time-series dependencies of equal length (minutes to tens of minutes) during sintering, the training speed is improved by 30%–40%, better meeting the real-time requirements of industry. In addition, the fewer parameters of the GRU-based deep neural network enable the model to generalize more effectively in industrial scenarios with limited data, significantly reducing the risk of overfitting.

[0047] like Figure 3 As shown, the specific structure of the GRU-based deep neural network is as follows: Input layer: Receives feature vectors after batch normalization. ; Sequence coding layer: A three-layer bidirectional GRU structure is adopted, with the number of units being 128, 64 and 32 respectively. The temporal features are extracted progressively from short-term to long-term. A Dropout layer (dropout rate of 0.2) is connected after the first and second bidirectional GRU layers to suppress overfitting.

[0048] Attention Mechanism Layer: An attention mechanism is applied to the output of the third-layer bidirectional GRU, enabling the model to adaptively focus on the most critical historical moments for the current prediction, thereby enhancing the interpretability of the model.

[0049] Fully connected regression layer: The output of the attention mechanism is sequentially mapped to a 64-dimensional fully connected layer and a 32-dimensional fully connected hidden layer, and finally the predicted material level value is obtained from the linear output layer.

[0050] Furthermore, the training scheme for the prediction model in this embodiment is as follows: Data preparation: Collect no less than 6 months of sintering production data, construct more than 200,000 sets of time-aligned sample data, and after cleaning and normalizing the sample data, divide them into training set, validation set and test set according to proportion.

[0051] Specifically, sample data is cleaned using process rules (upper and lower limits) or the sliding window Z-score method (window=30, threshold=3) to remove outliers generated during production, ensuring data quality. Min-Max normalization, Z-score standardization, or L2 norm normalization are used to eliminate dimensional differences between different features, ensuring that all input features are within a comparable numerical range, thus improving the stability and convergence speed of model training.

[0052] Input sequence construction: except for the current time step eigenvectors In addition, feature vectors from the first 5 time steps are constructed to form a 3D input tensor of [batch size, 6, feature dimension] to help the model capture dynamic trends. Here, batch size represents the number of samples fed into the model for training or prediction in a single run; 6 is the time step size, representing the number of consecutive historical time points contained in each sample input to the model; and feature dimension represents the number of all variables used to describe the system state at each time point (i.e., X101-X125).

[0053] Loss Function: In this embodiment, adaptive Huber Loss is used as the loss function for training the prediction model. Its core design involves gradually decreasing the Huber Loss threshold parameter from an initial value (e.g., 1.0) to a final value (e.g., 0.5) as training epochs increase; or dynamically adjusting it based on the prediction model's performance on the independent validation set—when the prediction model training stabilizes, the threshold is automatically reduced in steps of 0.05 or 0.1 to enhance the loss function's sensitivity to prediction errors, thereby improving the model's fitting accuracy for small deviations.

[0054] Meanwhile, to prevent the GRU prediction model from overfitting to noisy industrial data during training and to improve its generalization ability, an L2 regularization term (with a weight decay coefficient set to 0.001) is introduced on top of the adaptive Huber Loss. This measure effectively constrains the size of the model parameters, making the mapping relationship between the learned input features and the material level smoother and more robust, thereby ensuring the reliability of the prediction system under actual complex working conditions.

[0055] Optimization and Preset Targets: The AdamW optimizer is used, with the learning rate decaying from 0.001 to 0.0001 over 100 epochs using cosine annealing. An early stopping strategy is employed, terminating training if the validation set loss does not decrease for 10 consecutive epochs. On the test set, if the root mean square error (RMSE) < 1.5t, the mean absolute error (MAE) < 1.2t, and 95% of the predicted point absolute errors are ≤ 2.0t, then the preset performance target (≤ 400) is met. The process requirements for sintering machine production capacity are as follows: the larger the sintering machine, the greater the production flow rate and the wider the allowable error range.

[0056] Preferably, after the prediction model is trained, TensorRT is used to optimize its inference, achieving a single prediction time of <10ms on an NVIDIA T4 GPU. Simultaneously, a model performance monitoring system is deployed to continuously track prediction errors. When performance degrades, a retraining process can be automatically triggered, forming a self-evolving capability.

[0057] Furthermore, in this embodiment, at a steel plant with a capacity of 400... Special tests were conducted on the sintering machine. A continuous production period (8 hours) was selected. During this period, the particle size distribution of the material at the outlet of the secondary mixer changed significantly due to adjustments in the upstream raw material ratio, while operating parameters such as the batching rate and roller speed remained constant. The prediction method of this embodiment and the traditional prediction method (a BP neural network model based on flow parameters and a fixed time window) were used to predict the material level, and the results were compared with the actual material level.

[0058] The test period includes three stages: T1, T2, and T3. Stage T1 is 0-120 min, stage T2 is 120-360 min, and stage T3 is 360-480 min. The particle size distribution of each stage is shown in Table 1.

[0059] Table 1. Particle size distribution in different time periods In this test, the prediction model uses the current time. The input parameters are used to predict the material level value 15 minutes later. (i.e., prediction) The material level at time T2. In the T2 stage, the actual material level gradually decreases due to the increase in fine particles (slowly decreasing from the baseline of 35t to 31t). However, the traditional prediction model, which does not introduce particle size parameters, fails to detect the change in physical properties and still predicts that the material level will remain around 35t based on the flow rate data, resulting in a continuous increase in prediction error (the maximum deviation reaches 3.4t).

[0060] The prediction method in this embodiment collects particle size data X112, X113, and X114 in real time and accurately correlates the causal relationship between the current particle size and the subsequent material level through time-series alignment. After capturing the increasing trend of fine particle proportion, the GRU model in this embodiment predicts in advance that the discharge level will gradually decrease, and the predicted value is highly consistent with the actual value. Table 2 shows a comparison of prediction data from typical moments within stage T2. Table 2 Comparison of Predicted Data for Typical Moments in Stage T2 Comparing the results of the prediction method in this embodiment with those of the traditional prediction method, it can be seen that in stage T2, the prediction method of this embodiment can accurately capture the downward trend of material level caused by the increase of fine particles 15 minutes in advance. The predicted value is highly consistent with the actual material level 15 minutes later, with an average absolute error (MAE) of 0.3t, a maximum absolute error of 0.6t, and an error of ≤0.8t at 95% of the prediction points. The traditional prediction method has an average absolute error (MAE) of 2.1t, a maximum absolute error of 3.4t, and an error of ≤3.2t at 95% of the prediction points. This fully demonstrates that particle size is a key physical variable affecting material level, and introducing a prediction model can significantly improve prediction accuracy (especially when material properties fluctuate). The prediction method of this embodiment solves the problems of lag, inaccuracy, and poor robustness of the traditional prediction method.

[0061] The prediction method in this embodiment systematically incorporates material physical property parameters (particle size, moisture) and process parameters into the prediction model, and performs time-series alignment on each parameter, so that the input data has physical completeness and time-series correctness, realizing the synergistic gain effect of the multi-source parameter system.

[0062] Among these parameters, particle size directly affects the bulk density and angle of repose of the material in the mixing tank during sintering. Finer particle size increases bulk density, leading to a higher material level (weight) for the same volume; conversely, finer particle size decreases. The predictive model uses this parameter to detect the invisible, slow drift in material level caused by changes in raw material source or fluctuations in granulation effect. Moisture content significantly affects the flowability and viscosity of the material during sintering. Excessive moisture reduces flowability, making the material prone to adhering in the mixing tank, resulting in poor discharge and a false increase in material level. Insufficient moisture may exacerbate segregation. The predictive model uses this parameter to identify material level distortion or discharge fluctuations caused by abnormal moisture levels. Steam parameters alter the material temperature and surface properties during sintering, indirectly affecting flowability and granulation effect, serving as a crucial bridge variable connecting process operation and material state. Material flow parameters (such as the secondary mixer outlet belt conveyor speed X107), roller feeder speed X123, and sintering machine trolley speed X124 directly reflect the balance between input and output in the mixing tank. The prediction method in this embodiment utilizes the synergistic effects of material conveying parameters in the batching area, operating parameters of the primary mixer, operating parameters of the secondary mixer, operating parameters of the mixing trough, and operating parameters of the sintering machine to construct a virtual material state-dynamic equilibrium digital image in the prediction model. Therefore, the system can provide high-precision early warnings of material level changes caused by gradual changes in physical properties or operational adjustments 5-15 minutes in advance. The measured absolute error of over 95% of prediction points is ≤2.0 tons, far superior to models relying solely on historical material level data.

[0063] The prediction method in this embodiment addresses the problem of traditional methods that simply stack parameters collected at different locations and times, thus disrupting the strict causal relationship between the model input features and the prediction target (material level). By aligning the parameters over time, this method ensures that the prediction model learns genuine physical causal relationships, rather than spurious correlations. Therefore, when faced with unfamiliar operating conditions or disturbances, the model can make more reasonable inferences based on physical logic, exhibiting stronger generalization ability and robustness, and reducing the risk of overfitting.

[0064] This embodiment employs a GRU-based deep neural network, which, while ensuring the ability to capture long-term temporal dependencies, has fewer parameters, higher training efficiency, and is easier to deploy in industrial real-time systems. Furthermore, the simpler structure helps reduce the risk of overfitting and improves model stability in industrial scenarios where the data volume is not infinite. The adaptive Huber loss function and L2 regularization used during predictive model training further ensure the robustness and generalization of the predictive model when dealing with industrial data noise. This embodiment's method, through mechanism-based multi-source parameter selection and temporal alignment, completes information purification at the input level, using the most relevant and timely data to drive the model, avoiding the computational burden and unreliability caused by brute-force fitting with large datasets.

[0065] The predictive method in this embodiment transforms material level control from a post-event reaction to a pre-event intervention, achieving an upgrade in the control paradigm. Simultaneously, its clear input-output relationship makes the decision-making process of the entire intelligent system interpretable and traceable, providing a high-quality, high-reliability perception core for constructing a digital twin of the sintering process and realizing full-process automation.

[0066] Example 2: See Figure 4 This embodiment provides a method for controlling the material level in a sintering mixing tank. The method aims to achieve feedforward-feedback composite control by predicting material level fluctuations in advance and matching them with a corresponding feedforward control strategy. It also incorporates feedback correction based on the error between the actual material level and the model's predicted value. Simultaneously, constraints ensure the rationality of the control commands, ultimately achieving precise, stable, and safe control of the material level in the mixing tank. The details are as follows: A1. In the current adjustment cycle Internal prediction obtains the material level value of the mixing tank at at least one future moment; A2. Determine whether the deviation between the predicted material level and the set material level exceeds the allowable fluctuation range. If it exceeds the limit, proceed to step A3. If it does not exceed the limit, keep the control parameters of the previous adjustment cycle unchanged and return to step A1. A3. Based on the relationship between the current material moisture content and the process dead zone, as well as the magnitude of future material level deviation, generate the current adjustment cycle according to the preset priority. Feedforward control command vector ; A4. Based on the current adjustment cycle The actual material level in the mixing tank and predicted material level The deviation between them generates a feedback correction command vector for the currently dominant feedforward channel. ; A5. Based on feedforward control command vector and feedback correction command vector Generate composite control commands ; Determine the composite control command If the constraints are met, then proceed based on the composite control command. Update the current adjustment cycle The control parameters are then sent to the actuator; if they are not met, the process returns to step A1.

[0067] Steps A1-A5 will be explained in detail below: Preferably, step A1 uses the prediction method in Example 1 to obtain the future mixing tank... material level at any given time ,in, This indicates the time corresponding to the current period. Indicates the predicted time length. This means any point in the future; therefore, this embodiment does not describe how to predict and obtain the material level value of the mixing tank at a future time. A detailed explanation is provided below. Of course, in addition to the prediction method in Example 1, those skilled in the art can also use other methods to predict the material level value of the mixing tank at future times, which will not be listed in detail in this embodiment.

[0068] Preferably, to avoid frequent adjustments to the control parameters of the sintering equipment, an allowable range for material level fluctuations needs to be set. ,like This indicates that the future material level is within a reasonable range, and there is no need to adjust the control parameters of the sintering equipment. This indicates that the future material level is outside the reasonable range, and the control parameters of the sintering equipment need to be adjusted to ensure that the material level in the mixing tank is within the reasonable range; among which, This is the lower limit of the allowable material level in the mixing tank. This represents the maximum allowable material level in the mixing tank.

[0069] Preferably, in this embodiment, the main cause of the fluctuation is determined based on the future material level fluctuation, whether it is a fluctuation in the batching flow rate, a change in the discharge demand, or an abnormality in material properties (such as abnormal moisture or steam). The feedforward control command vector ,in, This indicates the adjustment value for the ingredient quantity in the current cycle. This indicates the adjustment value of the roller speed for the current cycle. This indicates the amount of moisture setpoint adjustment for the current period. This indicates the adjustment amount of the setpoint for the secondary mixer steam main flow rate in the current cycle.

[0070] Furthermore, this embodiment determines the main causes of future material level fluctuations and obtains a feedforward control command vector based on these fluctuations. The specific method is as follows: If the detected material moisture value Deviation from process dead zone And the duration is greater than the threshold Then, based on the ideal moisture value of the process... and The moisture setpoint adjustment amount for the current cycle is calculated. ,Will , and After setting to zero, output the current feedforward control command vector. At this time, the feedforward control command vector is represented as , The lower limit of the permissible moisture value, This represents the maximum permissible moisture content.

[0071] Preferably, based on the ideal moisture value of the process. and The moisture setpoint adjustment amount for the current cycle is calculated. Specifically: in, ; For integral gain, its value should satisfy... The condition is that T is the cycle length for performing the correction (i.e., the current cycle). (duration of time), integral gain The range should ideally be between 0.001 and 0.01 (e.g., 0.005). This range ensures that a single corrective adjustment is only 1‰ to 1% of the deviation from the ideal moisture value, thus achieving slow compensation on a "ten-minute" timescale. By setting an extremely small value... This makes the single-step correction amount negligible. Even if the correction cycle T is a few minutes, it will take a great many cycles (i.e. a very long total time) to complete the correction. This actively constructs a time filter, which forcibly stretches the dynamic response of the loop to "ten minutes" or even longer. This naturally decouples the loop from the main control loop, which is on the second or minute scale, and will not cause system oscillation.

[0072] Furthermore, obtain the moisture setpoint adjustment amount for the current cycle. Then, the moisture setpoint for the current cycle is set according to... To be updated, among which, Indicates the previous cycle The moisture setting value.

[0073] If the detected material moisture value In process dead zones Internal, and future material level deviation The duration is greater than the threshold Then, based on the material level setting value of the mixing tank. and future Predicted material level at any given time Calculate the ingredient quantity adjustment value for the current cycle. ,Will , and Set to zero and output the current feedforward control command vector. At this time, the feedforward control command vector is represented as , The delayed response time is the time taken to account for the impact of the actual overall conveying capacity of the batching area on the material level. Indicates the current period The corresponding time, Indicates the future The deviation of material level at any given time.

[0074] Preferred, the ingredient quantity adjustment value for the current cycle Represented as: in, The feedforward proportional coefficient is initially set based on the steady-state gain between material flow rate and material level, and then optimized through simulation.

[0075] Furthermore, obtain the ingredient quantity adjustment value for the current cycle. Then, the target comprehensive conveying capacity setpoint for the batching area in the current cycle is calculated according to... To be updated, among which, Indicates the previous cycle The target comprehensive conveying capacity setting value for the batching area.

[0076] If the detected material moisture value In process dead zones Inside, and The duration is greater than the threshold Then, based on the material level setting value of the mixing tank. and future Predicted material level at any given time Calculate the roller speed adjustment value for the current cycle. ,Will , and After setting to zero, output the current feedforward control command vector. At this time, the feedforward control command vector is represented as , The delayed response time of the effect of the rotational speed of the roller feeder on the material level (as described in Example 1, here) =0), Indicates the future The deviation of material level at any given time.

[0077] Preferred adjustment value for the roller speed in the current cycle Represented as: in, This is the feedforward scaling factor.

[0078] Furthermore, obtain the roller speed adjustment value for the current cycle. Then, the setpoint for the roller feeder speed in the current cycle is set according to... To be updated, among which, Indicates the previous cycle The rotational speed setting value of the roller feeder in the middle.

[0079] It should be noted that since the rotational speed X123 of the roller feeder and the speed X124 of the sintering machine trolley are linked for control, in some embodiments the speed X124 of the sintering machine trolley may also be adjusted. The logic of its adjustment calculation is the same as that of the adjustment of the rotational speed X123 of the roller feeder. Therefore, it will not be described in detail in this embodiment.

[0080] If the detected material moisture value In process dead zones Inside, and The duration is greater than the threshold Then, based on the material level setting value of the mixing tank. and future Predicted material level at any given time Calculate the steam injection flow rate adjustment value for the current cycle. ,Will , and After setting to zero, output the current feedforward control command vector. At this time, the feedforward control command vector is represented as , Add a delayed response time to the effect of steam flow rate on material level in the secondary mixer. Indicates the future The deviation of material level at any given time.

[0081] Preferred steam injection flow rate adjustment value for the current cycle Represented as: in, This is the feedforward scaling factor.

[0082] Furthermore, obtain the steam addition flow rate adjustment value for the current cycle. Then, the steam addition flow rate setpoint for the current cycle is set according to... To be updated, among which, Indicates the previous cycle The steam addition flow rate setting value; This indicates an increase in steam flow, typically used in situations where the material level needs to be raised (appropriately increasing steam can raise the temperature of the mixture, reduce the material density in the trough, and facilitate discharge). This indicates a reduction in steam flow, used in situations where a lower material level is required; Then, keeping the current steam flow rate unchanged, the output will be... Also set to zero.

[0083] Preferably, a preset threshold Threshold , , , Configure according to actual needs. , , , They can be equal or unequal.

[0084] Preferred parameters , , , , and All units are %; , , , The unit is t (tons); , All units are ; , , , All units are (i.e., seconds); , The units are all in rpm; , All units are or .

[0085] Specifically, as those skilled in the art will understand, , , All of these are predictions of specific future moments obtained from a set of data. , or The material level value in this embodiment. The duration is greater than the threshold , The duration is greater than the threshold , The duration is greater than the threshold Essentially, it refers to the prediction of future material levels based on multiple sets of data, which indicates that the conditions for judgment will continue to be met.

[0086] Preferably, in step A4, based on the current adjustment cycle The actual material level in the mixing tank and predicted material level The deviation between them generates a feedback correction command vector for the currently dominant feedforward channel. Specifically: A4.1 Establish a soft sensor model to predict the discharge rate of the mixing tank. ; Preferably, in this embodiment, a lightweight machine learning model (such as GBDT) or empirical formula is used to predict the discharge volume of the mixing trough online in real time based on parameters such as the moisture content of the material at the outlet of the secondary mixer (x108), the proportion of the material with a particle size distribution less than 3mm at the outlet of the secondary mixer (granulator) (x112), the proportion of the material with a particle size distribution of 3-8mm at the outlet of the secondary mixer (granulator) (x113), the proportion of the material with a particle size distribution greater than 8mm at the outlet of the secondary mixer (granulator) (x114), the temperature of the material at the outlet of the mixing trough (x116), and the rotational speed of the roller feeder (x123). This is to address fluctuations in output caused by changes in material properties. The soft measurement model can be periodically trained and updated offline based on historical data, or fine-tuned online when the system has self-learning capabilities.

[0087] It should be noted that the input is given to the soft sensor model to predict the output volume. The parameters can be flexibly adjusted by those skilled in the art according to actual conditions and needs. The above-listed parameters are only the main parameters required for predicting the output.

[0088] A4.2, Based on the actual material level in the mixing tank during the previous cycle. Feed rate and output Calculate the predicted material level for the current cycle. ; Preferably, in this embodiment, the predicted material level for the current period is... Represented as: in, Indicates the system's correction period. The unit is , and The unit is .

[0089] The following will explain how to calculate the predicted material level for the current cycle. The formula is explained below: The material balance differential equation for the mixed material level is expressed as follows: That is, material level The rate of change is equal to the rate of change per unit time Material flowing in minus material flowing out; Because the control system operates at fixed intervals... Only one calculation and control operation is performed. Therefore, the continuous differential equations are transformed into discrete difference equations so that in each control cycle... Iterative calculations are performed. The core idea of ​​discretization is to approximate the differential with a small change, and then... Approximately: in, For the current period The material level value, For the previous cycle The material level value, The control period (unit: seconds, needs to be converted to hours in the flow rate unit).

[0090] Substituting this approximate relationship into the original differential equation, we get: Then, this equation is transformed to predict the expected material level for the current cycle: because This is the model's predicted current material level, which we'll name... Meanwhile, the actual material level in the previous cycle It is a known measurement value. Substituting these values, we obtain the final discretized model prediction formula: A4.3, Based on the actual material level in the current cycle and predicted material level Calculate the current material level deviation Based on the current material level deviation Generate feedback correction command vector for the currently dominant feedforward channel. ; Preferably, the current material level deviation Represented as: Current material level deviation This comprehensively reflects soft measurement errors, unmodeled disturbances, and process noise, and indicates the current material level deviation. The input is fed into a PI (proportional-integral) controller to generate a feedback correction command vector. Feedback correction command vector It is a feedforward control command vector A vector of the same dimension, in which only the component corresponding to the current dominant mode is non-zero, is the feedback correction command vector. Represented as: in, The proportional gain determines the response speed to instantaneous deviations; This is the integral gain, used to eliminate steady-state error. This is the cumulative sum of historical material level deviations, that is, from a certain reset moment to the current [number]th [time unit]. Up to the end of each control cycle, all model deviations The cumulative sum (integral term) serves to allow the controller to remember the historical total deviation and to perform integral action. Gradually eliminate the steady-state error of the system.

[0091] Specifically, feedback correction command vector Its function is to perform continuous, small-range, precise corrections to the feedforward channel. Therefore, its gain... and It should be set to a relatively small value, generally speaking. and The value should be significantly smaller than 1 / 10 to 1 / 50 of the corresponding gain of the underlying actuator, such as the PID controller of the frequency converter of the roller feeder. The specific value should be determined according to the actual debugging effect to ensure that it only performs slow and fine correction and only performs long-cycle compensation for model deviation, so as to avoid causing system oscillation.

[0092] Preferably, the composite control command in step A5 Represented as: In order to Able to When adding them, it is necessary to ensure that the units of both are consistent. and The unit must be the control quantity unit / ton. For example, when calibrating the actual comprehensive conveying capacity of the batching area, the unit should be... When calibrating the rotational speed of the roller feeder, the unit should be [unit missing]. When correcting steam flow rate, the unit should be _____. or When correcting for material moisture content, the unit should be 1. .

[0093] Furthermore, based on the set constraints... The non-zero components in the data are subjected to security checks. The non-zero components in the equation do not satisfy the rate of change constraint, according to After the non-zero components in the data are adjusted, the corresponding parameter amplitude does not meet the amplitude constraint or is adjusted according to... If the adjustment of non-zero components does not meet the process adjustment constraints, the safety check is considered to have failed, and the process needs to return to step A1. If the safety check passes, then... The non-zero component in the current cycle is added to the corresponding value in the previous cycle to generate the corresponding set value for the current cycle, which is then sent to the actuator.

[0094] In this embodiment, , , , The variation rate of each component per minute is strictly controlled, specifically: the variation rate of ingredient quantity ≤ ±10%. The rate of change of the roller speed is ≤ ±0.5 Moisture content change rate ±0.4 Steam flow rate variation rate ±1.5 Furthermore, the rate of change per minute for each component can be calculated based on the length of the correction cycle. By setting strict thresholds for the adjustment range per minute for each component, large-scale abrupt changes in control parameters can be avoided.

[0095] Furthermore, the amplitude constraint ensures that the updated setpoints for each component remain within the upper and lower limits of the equipment's rated capacity and the sintering process's allowable limits, preventing equipment overload or exceeding process specifications. The process adjustment constraint determines whether the current process allows adjustment of the corresponding component; for example, in some cases, adjusting the roller feeder speed and the actual comprehensive conveying capacity of the batching area may not be permitted. Those skilled in the art can flexibly adjust the constraints in this embodiment according to process requirements to ensure that the final adjustment meets the requirements of the process and equipment performance.

[0096] Specifically, the PID controller of the actuator adjusts the set target according to the updated set value of the current cycle. For example, it adjusts the actual comprehensive conveying volume of the batching area through the belt scales of each feeder, adjusts the speed of the roller feeder through the variable frequency motor, and changes the steam flow or moisture flow through the regulating valve. By collecting the actual values ​​of process variables in the material level control method in real time, the system continuously updates and generates new control signals based on the deviation between the set value and the actual value to adjust the actuator. This provides the sintering equipment with continuous, closed-loop feedback correction capability, ensuring that the system can eliminate residual errors that the intelligent feedforward cannot fully compensate for, and cope with unknown disturbances.

[0097] Furthermore, when the system switches between manual, automatic, or different modes, a disturbance-free switching algorithm is preferred to ensure that the setpoint sent to the PID controller does not change abruptly, thus maintaining stable production.

[0098] The material level control method of the sintering mixing tank in this embodiment is applicable to the material level control of the mixing tank of sintering machines of different specifications in various iron and steel metallurgical enterprises. It can be directly upgraded and modified in a modular manner on the basis of the existing sintering automatic control system without the need for large-scale replacement of on-site detection equipment and actuators. It has low modification cost, short commissioning cycle and strong on-site adaptability.

[0099] The control method in this embodiment effectively solves the problems of slow response, rigid strategy, and weak anti-disturbance capability of existing material level control methods by using advanced prediction, precise matching control strategy, feedforward-feedback composite control, and safety constraint verification. It achieves stable control of the material level in the mixing tank, avoiding problems such as decreased sintering permeability and machine shutdown due to excessively high or low material levels. At the same time, it ensures the stability of sintering process indicators, reduces energy consumption and equipment wear in sintering production, and improves the continuous operation capability and production efficiency of the sintering machine, which has significant economic benefits and broad industrial application value.

[0100] Implementation Case: To verify the actual effect of this embodiment, this case was conducted at a steel plant with a capacity of 400 cubic meters. The mixing tank control system of the sintering machine was industrially implemented and compared with traditional PID feedback control. Traditional PID feedback control relies on material level measurements. With set value The deviation is used to adjust the amount of ingredients; in the control method of this embodiment, the process adjustment constraint is set to allow adjustment of the amount of ingredients and prohibit adjustment of the roller speed.

[0101] The key parameters in this implementation case are: a correction period T of 1 minute, and prediction of material level changes over the next 10 minutes. =3.0 tons, =1.5 tons, =0.5 tons, moisture process dead zone is .

[0102] During a certain production day, due to a change of raw material warehouse upstream, the actual comprehensive conveying volume in the batching area decreased starting at 10:00 AM. The flow rate decreased from the normal 200 t / h to 185 t / h within 5 minutes. The system response of the control method in this embodiment is shown in Table 3. Table 3 System Response Action Table Under the same disturbance condition, the effects of traditional PID control and the control method of this embodiment are compared. The key indicators are shown in Table 4. Table 4 Performance Indicator Comparison Table As can be seen, the control action of the method in this embodiment is only one feedforward adjustment + one feedback fine adjustment, without frequent oscillation, which greatly reduces the number of actions of the actuator, reduces equipment wear, and achieves stable, safe and precise control of the material level in the sintering mixing tank.

[0103] Example 3: This embodiment provides a material level control system for a sintering mixing tank. The material level control system includes a memory and a processor. The memory stores a computer program, and the computer program is executed by the processor to perform the material level control method in Embodiment 2.

[0104] Example 4: This embodiment provides a storage medium storing a computer program, which, when run, executes the material level control method in Embodiment 2.

[0105] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for controlling the material level in a sintering mixing tank, characterized in that, Includes the following steps: A1. In the current adjustment cycle Internal prediction obtains the material level value of the mixing tank at at least one future moment; A2. Determine whether the deviation between the predicted material level and the set material level exceeds the allowable fluctuation range. If it exceeds the limit, proceed to step A3. If it does not exceed the limit, keep the control parameters of the previous adjustment cycle unchanged and return to step A1. A3. Based on the relationship between the current material moisture content and the process dead zone, as well as the magnitude of future material level deviation, generate the current adjustment cycle according to the preset priority. Feedforward control command vector ; A4. Based on the current adjustment cycle The actual material level in the mixing tank and predicted material level The deviation between them generates a feedback correction command vector for the currently dominant feedforward channel. ; A5. Based on feedforward control command vector and feedback correction command vector Generate composite control commands ; Determine the composite control command If the constraints are met, then proceed based on the composite control command. Update the current adjustment cycle The control parameters are then sent to the actuator; if they are not met, the process returns to step A1.

2. The material level control method according to claim 1, characterized in that, The feedforward control command vector is represented as follows: ; If the detected material moisture value Deviation from process dead zone And the duration is greater than the threshold Then, based on the ideal moisture value of the process... and The moisture setpoint adjustment amount for the current cycle is calculated. ,Will , and Set to zero and output the current feedforward control command vector. ; If the detected material moisture value In process dead zones Internal, and future material level deviation The duration is greater than the threshold Then, based on the material level setting value of the mixing tank. and future Predicted material level at any given time Calculate the ingredient quantity adjustment value for the current cycle. ,Will , and Set to zero and output the current feedforward control command vector. ; If the detected material moisture value In process dead zones Inside, and The duration is greater than the threshold Then, based on the material level setting value of the mixing tank. and future Predicted material level at any given time Calculate the roller speed adjustment value for the current cycle. ,Will , and Set to zero and output the current feedforward control command vector. ; If the detected material moisture value In process dead zones Inside, and The duration is greater than the threshold Then, based on the material level setting value of the mixing tank. and future Predicted material level at any given time Calculate the steam injection flow rate adjustment value for the current cycle. ,Will , and Set to zero and output the current feedforward control command vector. ; in, Indicates the current period The corresponding time, The delayed response time is the time taken to account for the impact of the actual overall conveying capacity of the batching area on the material level. Add a delayed response time to the effect of steam flow rate on material level in the secondary mixer. The delayed response time is the time required to account for the effect of the rotational speed of the roller feeder on the material level. The lower limit of the permissible moisture value, The upper limit of the allowable moisture content, , and All are preset thresholds. Indicates the future Material level deviation at any given time, Indicates the future Material level deviation at any given time Indicates the future The deviation of material level at any given time.

3. The material level control method according to claim 2, characterized in that, Moisture setpoint adjustment for the current cycle Represented as: in, , This is the integral gain.

4. The material level control method according to claim 2, characterized in that, Adjustment value of ingredient quantity for the current cycle Represented as: in, This is the feedforward scaling factor.

5. The material level control method according to claim 2, characterized in that, Current cycle roller speed adjustment value Represented as: in, This is the feedforward scaling factor.

6. The material level control method according to claim 2, characterized in that, Steam injection flow rate adjustment value for the current cycle Represented as: in, This is the feedforward scaling factor.

7. The material level control method according to claim 2, characterized in that, Generate feedback correction command vector for the currently dominant feedforward channel. Specifically: A4.1 Establish a soft sensor model to predict the discharge rate of the mixing tank. ; A4.2, Based on the actual material level in the mixing tank during the previous cycle. Feed rate and output Calculate the predicted material level for the current cycle. ;in, , This indicates the system's correction period in seconds, with 3600 being the conversion factor between hours and seconds. A4.3, Based on the actual material level in the current cycle and predicted material level Calculate the current material level deviation Based on the current material level deviation Generate feedback correction command vector for the currently dominant feedforward channel. ; in, Feedback correction command vector It is a feedforward control command vector For vectors of the same dimension, only the component corresponding to the current dominant mode is non-zero; this is the feedback correction command vector. , For proportional gain, For integral gain, This is the cumulative sum of historical material level deviations.

8. The material level control method according to claim 7, characterized in that, Based on the set constraints The non-zero components in the data are subjected to security checks. The non-zero components in the equation do not satisfy the rate of change constraint, according to After the non-zero components in the data are adjusted, the corresponding parameter amplitude does not meet the amplitude constraint or is adjusted according to... If the adjustment of non-zero components does not meet the process adjustment constraints, the safety check is considered to have failed, and the process needs to return to step A1. If the safety check passes, then... The non-zero component in the current cycle is added to the corresponding value in the previous cycle to generate the corresponding set value for the current cycle, which is then sent to the actuator.

9. A material level control system for a sintering mixing tank, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the computer program is executed by the processor to perform the material level control method as described in any one of claims 1-8.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when run, executes the material level control method as described in any one of claims 1-8.

Images