A converter burden self-adaptive adjusting method applied to a steelmaking plant

Abstract

The application discloses a converter burden self-adaptive adjusting method applied to a steel mill.The method comprises the following steps: step 1, data acquisition and pretreatment; step 2, establishing a converter process model; step 3, initial setting of burden discharging quantity; step 4, real-time feedback and self-adaptive adjustment; and step 5, continuous optimization and iteration.The burden self-adaptive adjusting method can realize real-time monitoring of molten steel state, and dynamically adjusts the burden discharging quantity according to the quality change of the molten steel, thereby improving the converter efficiency, optimizing the molten steel quality and reducing material consumption.In addition, the method has the advantages of strong self-adaptive capacity, simple operation and easy integration into an existing converter control system.

Description

Technical Field

[0001] This invention relates to the field of automation control technology in the metallurgical industry, and in particular to an adaptive adjustment method for converter feeding in steel plants. Background Technology

[0002] In the steelmaking converter process, batching is a crucial production step. Its role is to control chemical reactions, regulate temperature, and optimize the composition of molten steel by scientifically proportioning various raw materials, thereby ensuring steelmaking efficiency and quality. Traditional batching adjustments rely on the operator's experience and preset process parameters, which often fail to adapt to changes in molten steel composition in a timely manner, leading to low converter efficiency, unstable molten steel quality, and material waste. Summary of the Invention

[0003] This invention proposes an adaptive adjustment method for converter feeding in steelmaking plants. This method achieves dynamic adjustment of the feeding amount by periodically monitoring the composition of molten steel and applying advanced control algorithms and intelligent decision-making systems, thereby optimizing the converter process and improving the quality of molten steel.

[0004] To achieve the above objectives, the present invention provides an adaptive adjustment method for converter feeding in steel plants, comprising the following steps: Step 1: Data Acquisition and Preprocessing; Step 2: Establish a converter process model; Step 3: Initial setting of ingredient feeding amount; Step 4: Real-time feedback and adaptive adjustment; Step 5: Continuous optimization and iteration.

[0005] Furthermore, step 1 specifically includes: 1.1 Collect molten steel regularly and analyze its composition; 1.2 Real-time acquisition of converter steel temperature, carbon dioxide content, and oxygen content; 1.3 Preprocess the collected data, including data cleaning, data smoothing, and data calibration.

[0006] Furthermore, step 2 specifically includes: 2.1 Establish a digital twin model of the converter process to simulate the steel quantity, temperature evolution, and material composition during the converter process; 2.2 The model is trained and validated using historical converter data and real-time data. Using a data-driven approach, based on the material balance (molten iron, scrap steel, auxiliary materials) and heat balance equations, the amount of lime and dolomite added is calculated. The model parameters are corrected by combining real-time steel composition feedback. The parameters and structure of the model are continuously optimized to improve the prediction accuracy and generalization ability of the model. 2.3 A neural network (genetic algorithm optimized backpropagation network) is used. Inputting molten iron composition, temperature, and target steel grade parameters, it predicts the final carbon and phosphorus content and auxiliary material requirements, and pre-determines the final steel grade. The model parameters are then corrected based on the feedback from the final steel grade monitoring and determination.

[0007] Furthermore, the historical data includes sensor data, operation records, multiple batches of molten steel composition data, and the final steel grade determination results from past converter processes.

[0008] Furthermore, step 3 specifically includes: 3.1 Set the initial batching and feeding amount based on the converter steel type, material composition data, and the initial state of the molten steel in the converter.

[0009] Furthermore, step 4 specifically includes: 4.1 Real-time monitoring of molten steel condition, including concentrations of gases such as CO and CO2, temperature, and degree of slag foaming; regular analysis of molten steel composition. 4.2 The central control unit inputs the monitoring data into the converter process model. Based on the current state of molten steel and the preset process parameters, the model calculates the optimal set value for the batching and feeding amount. 4.3 Fuzzy adaptive PID control is adopted to dynamically adjust PID parameters based on temperature and oxygen regulation and the degree of slag foaming. A segmented continuous feeding design is adopted to adaptively adjust the batching and feeding amount. 4.4 The batching control system adjusts the opening of the silo valve or the output of the feed rate controller according to the received adjustment command to achieve precise control of the batching feed rate.

[0010] Furthermore, step 4 also includes: 4.5 During the adjustment process, the central control unit also monitors the adjustment effect in real time, including the melting of slag, the concentration of CO and CO2 gases, and the removal of inclusions; and based on the monitoring results, further adjusts the parameters and strategies of the control algorithm to optimize the adjustment effect of the batching and feeding amount.

[0011] Furthermore, step 5 specifically includes: 5.1 Repeat steps 2 to 4, continuously collecting data during the converter process and iteratively optimizing the model to train the model using new converter data; 5.2 Adjust the parameters and strategies of the control algorithm based on converter results and molten steel quality feedback; 5.3 Periodically evaluate the performance of the adaptive adjustment method, including converter efficiency, molten steel quality stability, and material consumption, and make necessary adjustments and improvements based on the evaluation results.

[0012] The adaptive feeding method of this invention can monitor the state of molten steel in real time and dynamically adjust the feeding amount according to the timed quality changes of the molten steel, thereby improving converter efficiency, optimizing molten steel quality, and reducing material consumption. Furthermore, this method has the advantages of strong adaptability, simple operation, and easy integration into existing converter control systems. Attached Figure Description

[0013] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0014] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0015] In the description of this invention, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0016] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0017] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0018] An adaptive adjustment method for converter feeding in a steel plant, as proposed by the present invention, includes the following steps: 1. Sensor Placement: Sensors should be placed in appropriate locations within the converter to ensure comprehensive and accurate monitoring of the molten steel's condition. For example, thermocouples and pressure transmitters can be placed near the surface and bottom of the molten steel; exhaust gas analyzers and tapping port vision cameras can be placed at the converter mouth; sensors measuring the amount of material fed can be placed at the hopper's discharge point. 2. Data Acquisition and Transmission: Sensor data is transmitted to the data acquisition system in real time via wired or wireless means. Because the data acquisition system requires high-speed and stable data processing capabilities, a gigabit fiber optic network is used for data transmission to ensure data real-time performance and accuracy. Abnormal sensor values ​​(such as temperature surges exceeding the process range) are removed, and noisy data is smoothed using a moving average method.

[0019] 3. Model Training and Validation: During model training, a large amount of historical and real-time data is required to improve the model's prediction accuracy and generalization ability. Simultaneously, model validation is necessary to ensure its reliability and stability in practical applications. Model Inputs: Real-time collected data on molten steel temperature, CO and CO2 gas concentrations, converter steel composition, material composition, and target feed rate settings; Model Outputs: Converter feed material types and feed rates, dynamically adjusted using a PID algorithm combined with fuzzy logic.

[0020] 4. Control Algorithm Selection: Based on the characteristics and requirements of the converter process, select a suitable control algorithm for adaptive adjustment. For example, PID control algorithm is suitable for linear or near-linear systems; fuzzy logic control algorithm is suitable for nonlinear, uncertain, and time-varying systems; and machine learning algorithm is suitable for complex, high-dimensional, and dynamically changing systems.

[0021] 5. Ingredient feeding quantity adjustment strategy: Initial settings: Preset the baseline value of the feeding amount according to the steel type (such as low carbon steel, alloy steel) and converter stage (deoxidation, desulfurization); for example: 2000 kg of lime is required for carbon steel, 300 kg of silicon manganese alloy is required, and 500 kg of magnesium balls are required, etc.

[0022] Dynamic adjustment: A mechanism model based on material and heat balance is adopted, combined with real-time monitoring data (such as molten iron temperature and composition) to dynamically adjust the amount of auxiliary materials added. For example, the final steel composition and steel grade are predicted by neural network, and the ratio of lime to dolomite is optimized. The scrap steel ratio is adjusted according to the physical heat of molten iron. For example, when the molten iron temperature is below 1250℃, the amount of scrap steel should be reduced to avoid "cold furnace".

[0023] 6. Control and verification of the executing agency Actuators: The batching control system requires actuators with high precision, high reliability, and high response speed, such as solenoid valves, proportional valves, or feed rate controllers. These actuators need to be precisely controlled according to the instructions of the control algorithm to achieve adaptive adjustment of the batching feed rate. For example, an electric regulating valve (accuracy ±1%FS) and a proportional-integral valve (response time <0.5s) can be used in conjunction to control the feed rate.

[0024] Closed-loop verification: Compare the actual feed rate with the set value every 5 minutes. If the deviation is greater than 5%, trigger model parameter recalibration. At the end of the converter operation, the feed consumption is calculated and compared with historical data to optimize the algorithm weight. 7. Record key parameters and data during the converter process to provide experience and reference for subsequent converters.

[0025] 8. Safety Protection Mechanism: During the adaptive adjustment process, a safety protection mechanism needs to be set to prevent safety accidents caused by operational errors or equipment malfunctions. For example, upper and lower limit protection for material feeding and lower limits, and overheat protection for temperature sensors can be set. The present invention has been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention. Many other changes and modifications made without departing from the concept and scope of the present invention should be considered within the scope of protection of the present invention.

[0026] Example Figure 1 As one embodiment of the present invention, it includes: Step 1: Data Acquisition and Preprocessing 1.1 Install a converter steel molten steel collection robot to collect molten steel at regular intervals and automate the analysis of steel composition. Connect the data to the data acquisition system via wired or wireless means.

[0027] 1.2 Install a sensor network for temperature, carbon dioxide content, oxygen content, etc., to monitor the temperature changes and composition evolution (changes in the content of elements such as carbon dioxide and oxygen) of the converter steel in real time, and monitor the impurity removal process.

[0028] 1.3 The data acquisition system collects sensor data in real time and performs preprocessing, including data cleaning (removing noise and outliers), data smoothing (reducing data fluctuations through filtering algorithms), and data calibration (ensuring the accuracy and consistency of sensor data).

[0029] Step 2: Establish a converter process model 2.1 Based on the principles of thermodynamics and metallurgical reaction kinetics, a digital twin model of the converter process was established. This model can simulate the steel quantity, temperature evolution, and material composition during the converter process, combined with compositional analysis.

[0030] 2.2 The model is trained and validated using historical converter data and real-time data. Historical data includes sensor data, operation records, multiple batches of molten steel composition data, and final steel grade determination results from past converter processes. Real-time data consists of real-time sensor data from the current converter process. Using a data-driven approach, based on material balance (molten iron, scrap steel, auxiliary materials) and heat balance equations, the addition amounts of auxiliary materials such as lime and dolomite are calculated. Combined with real-time molten steel composition feedback, model parameters are corrected, continuously optimizing the model's parameters and structure to improve its predictive accuracy and generalization ability.

[0031] 2.3 A neural network (genetic algorithm optimized backpropagation network) is used. Input parameters such as molten iron composition, temperature, and target steel grade to predict the final carbon and phosphorus content and auxiliary material requirements. The final steel grade is pre-determined, and the model parameters are corrected based on the monitoring and determination of the final steel grade to reduce model error.

[0032] Step 3: Initial setting of ingredient feeding amount 3.1 Based on the converter steel type (e.g., carbon steel, stainless steel), material composition data, and the initial state of the molten steel in the converter (e.g., temperature, composition), set the initial batching and feeding amount. The initial feeding amount is generally less than the actual optimal feeding amount. This value can be a preset value based on experience or an optimal value predicted by a model.

[0033] Step 4: Real-time feedback and adaptive adjustment 4.1 Real-time monitoring of molten steel condition, including key parameters such as CO and CO2 gas concentrations, temperature, and slag foaming degree; regular analysis of molten steel composition. Sensor data is transmitted in real-time to the central control unit via a data acquisition system, while molten steel composition data is entered into the acquisition system via the laboratory.

[0034] 4.2 The central control unit inputs the monitoring data into the converter process model. Based on the current state of molten steel and the preset process parameters, the model calculates the optimal set value for the amount of raw materials to be fed.

[0035] 4.3 Fuzzy adaptive PID control is adopted, and the PID parameters are dynamically adjusted based on temperature and oxygen regulation, combined with the degree of slag foaming. A segmented continuous feeding design is used to adaptively adjust the batching feed rate. The algorithm calculates the adjustment amount based on the deviation between the optimal setpoint output by the model and the actual batching feed rate, and sends the adjustment command to the batching control system.

[0036] 4.4 The batching control system adjusts the opening of the silo valves or the output of the feed rate controller based on the received adjustment commands, thereby achieving precise control of the batching and feeding quantity. The control system may include actuators such as solenoid valves, proportional valves, or feed rate controllers.

[0037] 4.5 During the adjustment process, the central control unit also monitors the adjustment effect in real time, such as the melting of slag, the concentration of gases such as CO and CO2, and the removal of inclusions. Based on the monitoring results, the parameters and strategies of the control algorithm are further adjusted to optimize the adjustment effect of the batching and feeding rate.

[0038] Step 5: Continuous Optimization and Iteration 5.1 Repeat steps 2 through 4, continuously collecting data during the converter process and iteratively optimizing the model. This includes training the model using new converter data to improve its predictive accuracy and adaptability.

[0039] 5.2 Based on the converter results and molten steel quality feedback, adjust the parameters and strategies of the control algorithm. For example, the gain coefficient of the PID control algorithm, the rule base of the fuzzy logic control algorithm, or the model structure of the machine learning algorithm can be adjusted.

[0040] 5.3 Periodically evaluate the performance of the adaptive adjustment method, including indicators such as converter efficiency (e.g., converter time, energy consumption), steel quality stability (e.g., compositional uniformity, inclusion content), and material consumption. Make necessary adjustments and improvements based on the evaluation results.

[0041] In the description of this specification, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0042] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An adaptive adjustment method for converter feeding in steelmaking plants, characterized in that, Includes the following steps: Step 1: Data Acquisition and Preprocessing; Step 2: Establish a converter process model; Step 3: Initial setting of ingredient feeding amount; Step 4: Real-time feedback and adaptive adjustment; Step 5: Continuous optimization and iteration.

2. The adaptive adjustment method for converter feeding in steel plants according to claim 1, characterized in that, Step 1 specifically includes: 1.1 Collect molten steel regularly and analyze its composition; 1.2 Real-time acquisition of converter steel temperature, carbon dioxide content, and oxygen content; 1.3 Preprocess the collected data, including data cleaning, data smoothing, and data calibration.

3. The adaptive adjustment method for converter feeding in steel plants according to claim 1, characterized in that, Step 2 specifically refers to: 2.1 Establish a digital twin model of the converter process to simulate the steel quantity, temperature evolution, and material composition during the converter process; 2.2 The model is trained and validated using historical converter data and real-time data. Using a data-driven approach, based on the material balance (molten iron, scrap steel, auxiliary materials) and heat balance equations, the amount of lime and dolomite added is calculated. The model parameters are corrected by combining real-time steel composition feedback. The parameters and structure of the model are continuously optimized to improve the prediction accuracy and generalization ability of the model. 2.3 A neural network (genetic algorithm optimized backpropagation network) is used. Inputting molten iron composition, temperature, and target steel grade parameters, it predicts the final carbon and phosphorus content and auxiliary material requirements, and pre-determines the final steel grade. The model parameters are then corrected based on the feedback from the final steel grade monitoring and determination.

4. The adaptive adjustment method for converter feeding in steel plants according to claim 3, characterized in that, The historical data includes sensor data, operation records, multiple batches of molten steel composition data, and the final steel grade determination results from past converter processes.

5. The adaptive adjustment method for converter feeding in a steel plant according to claim 1, characterized in that, Step 3 specifically includes: 3.1 Set the initial batching and feeding amount based on the converter steel type, material composition data, and the initial state of the molten steel in the converter.

6. The adaptive adjustment method for converter feeding in a steel plant according to claim 1, characterized in that, Step 4 specifically includes: 4.1 Real-time monitoring of molten steel condition, including concentrations of gases such as CO and CO2, temperature, and degree of slag foaming; regular analysis of molten steel composition. 4.2 The central control unit inputs the monitoring data into the converter process model. Based on the current state of molten steel and the preset process parameters, the model calculates the optimal set value for the batching and feeding amount. 4.3 Fuzzy adaptive PID control is adopted to dynamically adjust PID parameters based on temperature and oxygen regulation and the degree of slag foaming. A segmented continuous feeding design is adopted to adaptively adjust the batching and feeding amount. 4.4 The batching control system adjusts the opening of the silo valve or the output of the feed rate controller according to the received adjustment command to achieve precise control of the batching feed rate.

7. The adaptive adjustment method for converter feeding in a steel plant according to claim 4, characterized in that, Step 4 further includes: 4.5 During the adjustment process, the central control unit also monitors the adjustment effect in real time, including the melting of slag, the concentration of CO and CO2 gases, and the removal of inclusions; and based on the monitoring results, further adjusts the parameters and strategies of the control algorithm to optimize the adjustment effect of the batching and feeding amount.

8. The adaptive adjustment method for converter feeding in a steel plant according to claim 1, characterized in that, Step 5 specifically includes: 5.1 Repeat steps 2 to 4, continuously collecting data during the converter process and iteratively optimizing the model to train the model using new converter data; 5.2 Adjust the parameters and strategies of the control algorithm based on converter results and molten steel quality feedback; 5.3 Periodically evaluate the performance of the adaptive adjustment method, including converter efficiency, molten steel quality stability, and material consumption, and make necessary adjustments and improvements based on the evaluation results.

Images