CN118210281A

CN118210281A - Intelligent control system and method for top-blown smelting furnace

Info

Publication number: CN118210281A
Application number: CN202410284084.XA
Authority: CN
Inventors: 杨世亮; 刘鹏; 王明江; 唐都作; 袁海滨
Original assignee: Yunnan Tin Industry Co ltd; Kunming University of Science and Technology
Current assignee: Yunnan Tin Industry Co ltd; Kunming University of Science and Technology
Priority date: 2024-03-13
Filing date: 2024-03-13
Publication date: 2024-06-18

Abstract

The invention discloses an intelligent control system and method for a top-blown smelting furnace, wherein the system comprises the following components: the smelting device comprises a top-blowing spray gun and a smelting furnace; the data acquisition module is used for acquiring various spray gun parameters of the top-blowing spray gun; the intelligent prediction module is used for receiving the parameters of the spray gun and obtaining a prediction result through a preset algorithm, wherein the prediction result represents the distribution and change of smelting parameters in a molten pool of the smelting furnace; the control module is used for controlling the top-blowing spray gun to adjust the operation strategy based on the prediction result, and comprises the following steps: adjusting parameters of the spray gun based on the prediction result to meet preset working conditions; and controlling the gun position height, the ventilation amount and the feeding amount of the top-blowing spray gun based on the prediction result. The embodiment ensures the high efficiency and accuracy of the smelting process, reduces the dependence on manual experience, and obviously reduces the risk of misoperation.

Description

Intelligent control system and method for top-blown smelting furnace

Technical Field

The embodiment of the disclosure relates to the technical field of metal smelting, in particular to an intelligent control system and method for a top-blown smelting furnace.

Background

The top-blown molten pool smelting technology is widely applied to the field of metal refining of tin, copper, lead and the like due to high smelting strength and outstanding smelting efficiency. With the development of the smelting industry, the requirements on the operation precision and efficiency of the top-blown smelting furnace are gradually improved. Traditional control modes relying on manual experience and intuition cannot meet the modern smelting requirements.

Currently, the usual monitoring means are limited to the gas flow and pressure at the lance, and are not known from the speed field and pressure variations inside the bath. This lack of information causes a series of problems such as slag splashing, increased energy consumption, fluctuation in the amount of raw material, uneven stirring, etc., which not only affect the yield and quality of the metal, but also cause accretion in severe cases, even the shutdown of the entire smelting furnace. In the aspect of adjustment, the current method mainly depends on experience judgment of staff, and rough adjustment is performed by adjusting the flow of the spray gun gas and the pulverized coal. Because of the lack of a perfect quantitative regulation mechanism, the regulation mode is neither accurate nor reliable, and further optimization and development of the process of the top-blown smelting furnace are severely restricted.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.

Disclosure of Invention

The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure provide a top-blown smelting furnace intelligent control system, method, and computer-readable medium that address one or more of the technical problems set forth in the background section above.

In a first aspect, some embodiments of the present disclosure provide a top-blown smelting furnace intelligent control system, including: the smelting device comprises a top-blowing spray gun and a smelting furnace; the data acquisition module is used for acquiring various spray gun parameters of the top-blowing spray gun, wherein the spray gun parameters at least comprise gas flow, pressure and temperature information; the intelligent prediction module is used for receiving parameters of the spray gun and obtaining a prediction result through a preset algorithm, wherein the prediction result represents smelting parameter distribution and change in a molten pool of the smelting furnace, and the smelting parameters at least comprise smelting pressure, smelting speed and slag distribution; the control module is used for controlling the top-blowing spray gun to adjust the operation strategy based on the prediction result, wherein the operation strategy comprises the following steps: adjusting the spray gun parameters based on the prediction result to meet preset working conditions; controlling the gun position height of the top-blowing spray gun based on a prediction result; and controlling the ventilation quantity and the feeding quantity of the top-blowing spray gun based on the prediction result.

In a second aspect, some embodiments of the present disclosure provide an intelligent control method for a top-blown smelting furnace, including: collecting spray gun parameters of a top-blowing spray gun, wherein the spray gun parameters at least comprise gas flow, pressure and temperature information; receiving parameters of a spray gun and obtaining a prediction result through a preset algorithm, wherein the prediction result represents smelting parameter distribution and change in a molten pool of a smelting furnace, and the smelting parameters at least comprise smelting pressure, smelting speed and slag distribution; and controlling the top-blowing spray gun to adjust an operation strategy based on a prediction result, wherein the operation strategy comprises the following steps of: adjusting the spray gun parameters based on the prediction result to meet preset working conditions; controlling the gun position height of the top-blowing spray gun based on a prediction result; and controlling the ventilation quantity and the feeding quantity of the top-blowing spray gun based on the prediction result.

In a third aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the second aspect above.

The above embodiments of the present disclosure have the following advantageous effects: the comprehensive analysis of the complex and changeable physical environment in the smelting furnace is realized through the intelligent prediction module. And (3) performing high-precision simulation and calculation on various operating conditions by using a mathematical model iteration technology, so as to reveal deep dynamic characteristics in a molten pool, including splash details, stirring mechanisms, stirring dead zone forms, turbulent structures, dynamic pressure fluctuation, pressure gradient evolution, fine changes of flow velocity and flow track and the like. The acquisition of the information helps staff to know the condition in the furnace, automatically and accurately control the gas and fuel flow in the spray gun according to the actual condition, prolongs the service life of the furnace body, and optimizes the quantitative combined control of smelting process parameters. The automatic control guided by the prediction result ensures the high efficiency and accuracy of the smelting process, reduces the dependence on the manual experience, and obviously reduces the risk of misoperation.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a schematic diagram of some embodiments of a top-blown smelting furnace intelligent control system according to the present disclosure;

FIG. 2 is a flow chart of some embodiments of a method of intelligent control of a top-blown smelting furnace suitable for use in implementing some embodiments of the present disclosure;

Fig. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 illustrates a schematic structural diagram of some embodiments of a top-blown smelting furnace intelligent control system according to the present disclosure. The intelligent control system 100 for the top-blown smelting furnace comprises: smelting device 101, data acquisition module 102, intelligent prediction module 103 and control module 104.

In some embodiments, the workflow of the intelligent control system 100 for a top-blown smelting furnace may be: the data acquisition module 102 collects lance parameters, such as gas flow, pressure, temperature, etc., of the top-blowing lance 1011 in real time. The intelligent prediction module 103 receives the data, and processes and analyzes the data by using a preset algorithm to obtain the predicted result of the smelting parameter distribution and change of the molten pool in the smelting furnace 1012. The control module 104 adjusts the operating strategy of the top-blowing lance 1011 in real time based on the prediction results, including adjusting lance parameters, controlling lance height, ventilation and feed rates, etc., to optimize the smelting process and improve smelting efficiency.

In some embodiments, the smelting apparatus 101 includes a top-blowing lance 1011 and a smelting furnace 1012. The top-blowing lance 1011 is a key component in the smelting process and is responsible for injecting gas (e.g., oxygen, nitrogen, etc.) and/or fuel (e.g., coal fines, natural gas, etc.) into the smelting furnace 1012. The design and operation of the top-blowing lance 1011 directly affects smelting efficiency, energy consumption, and product quality.

In some embodiments, the furnace 1012 is the primary equipment for performing metal smelting, and the internal temperature and chemical environment thereof need to be precisely controlled to achieve an efficient smelting process. Smelting furnaces typically have high temperature and corrosion resistant properties to accommodate extreme smelting conditions. The smelting furnace 1012 may be an austempered furnace, which is mainly composed of a circular reactor, and performs metal smelting by continuously feeding fuel into a molten bath through a top-blowing lance 1011 installed at the center of the top. The temperature of the smelting furnace 1012 is typically as high as thousands of degrees celsius, and when the flow rate of the gas and pulverized coal injected from the top-blowing lance 1011 is too high or too low, it may have serious influence on the yield and quality of the metal and the stable operation of the apparatus.

In some embodiments, the data acquisition module 102 is responsible for monitoring and collecting various parameters of the top-blowing lance 1011 in real time, such as gas flow, injection pressure, temperature, etc. These data are important criteria for assessing the operating condition of the top-blowing lance 1011 and the efficiency of the smelting process.

In some embodiments, the lance parameter may be the flow of gas, fuel or oxygen through the lance. The magnitude of the flow directly influences the injection force and effect generated by the spray gun, and further influences the speed and efficiency of smelting reaction. If the flow rate is too low, the movement of the material in the furnace may not be sufficiently stimulated; if the flow rate is too high, energy waste may be caused, and even uneven temperature distribution in the furnace may be caused.

In some embodiments, pressure is another key parameter. The pressure changes may reflect the clogging of the top-blowing lance 1011, the stability of the gas supply, and the degree of nozzle wear. Too high or too low a pressure may negatively impact the performance and life of the spray gun. Temperature information is also one of the core parameters in the smelting process. For the top-blowing lance 1011, the temperatures that need to be monitored include the temperature of the top-blowing lance 1011 itself and the temperatures of different regions within the smelting furnace 1012. Excessive temperatures of the top-blowing lance 1011 may cause deformation or failure of the material, while non-uniformity of temperature within the smelting furnace 1012 may affect the quality and efficiency of the smelting reaction.

In some embodiments, the real-time collection of the operating parameters of the top-blowing lance 1011 also includes heat distribution information, which refers to the heat distribution of different regions within the furnace. By analyzing the heat distribution, it is possible to understand whether the injection mode of the top-blowing lance 1011 is reasonable, the movement state of the material in the furnace, and the utilization efficiency of heat energy. Uneven heat distribution may lead to uneven composition of the smelting products or unnecessary energy consumption.

In some embodiments, the data acquisition module 102 may be implemented by various sensors, such as flow sensors, pressure sensors, temperature sensors, and the like. These sensors need to have high accuracy and high reliability to ensure accuracy of the data. For example, a flow sensor is used to measure gas flow, a pressure sensor is used to measure injection pressure, and a temperature sensor is used to measure temperature. The sensors convert the acquired analog signals into digital signals and then transmit the digital signals to a processor or control system for processing.

In some embodiments, the intelligent prediction module 103 analyzes and processes the real-time data provided by the data acquisition module 102 by receiving the data and applying a predetermined algorithm (e.g., machine learning, deep learning, etc.). By analyzing the historical data and the real-time data, the intelligent prediction module 103 can predict the state changes of the molten pool in the smelting furnace, such as smelting pressure, smelting speed, slag distribution and the like. These predictions are critical to timely adjusting the lance operating strategy. The intelligent prediction module 103 is a core part of the disclosure, and is responsible for receiving the parameters of the spray gun transmitted by the data acquisition module 102, and processing and analyzing the parameters by using a preset algorithm to obtain a prediction result of the distribution and change of the smelting parameters of the molten pool in the smelting furnace.

In some embodiments, the smelting parameters may be smelting pressure, smelting speed, slag distribution, etc. The smelting pressure may be the pressure in the molten bath in the smelting furnace 1012. The change of smelting pressure can reflect the distribution and flow condition of gas in a molten pool and the intensity of smelting reaction. The smelting rate may be the rate of oxidation or reduction of the metal in the bath per unit time. The smelting speed directly influences the smelting production efficiency. Slag distribution the distribution and thickness of slag in the bath. The distribution of slag may reflect the uniformity of chemical reactions within the bath and the efficiency of heat transfer.

In some embodiments, the control module 104 is responsible for adjusting the operating strategy of the top-blowing lance 1011 in real time based on the prediction results provided by the intelligent prediction module 103. The adjustment of the operation strategy aims at optimizing the smelting process and ensuring that the working conditions in the smelting furnace are always kept in the optimal state. The control module 104 can realize comprehensive monitoring and real-time adjustment of the smelting process by precisely controlling key factors such as parameters of the spray gun, height of the gun position, ventilation quantity, feeding quantity and the like.

In some embodiments, the control module 104 may first determine whether the current lance parameters meet the preset operating conditions according to the prediction results provided by the intelligent prediction module 103, such as the smelting pressure, the smelting speed, the slag distribution, and the like. If not, the control module 104 calculates the parameter values to be adjusted and sends instructions to the gun actuator for adjustment. The parameters adjusted may include gas flow, injection pressure, etc. For example, if the prediction indicates that the smelting rate is too slow, the control module 104 may increase the gas flow or increase the injection pressure to increase the smelting reaction rate.

In some embodiments, lance height refers to the distance between the end of top-blowing lance 1011 and the surface of the molten bath. The control module 104 adjusts the lance height based on the change in the state of the molten bath in the prediction result. For example, when the bath temperature is too high or slag is not evenly distributed, the control module 104 may decrease the lance height to increase the stirring action of the gas on the bath and promote uniform distribution of heat and composition. The adjustment of gun position height is typically accomplished by controlling the gun lift mechanism. The control module 104 calculates the gun position height value to be adjusted according to the prediction result and the preset gun position height adjustment strategy, and sends a command to the lifting mechanism to perform adjustment.

In some embodiments, ventilation refers to the total amount of gas injected into the smelting furnace 1012 through the top-blowing lance 1011 per unit time, and the feed rate refers to the amount of material charged into the smelting furnace 1012 per unit time. The control module 104 adjusts ventilation and feed rate based on the predicted variations in parameters such as smelting rate, bath composition, etc. to ensure continuity and stability of the smelting process. The ventilation and feed amount adjustment can be achieved by controlling the gas supply system and the raw material delivery system. The control module 104 calculates parameter values such as the gas flow to be adjusted and the raw material delivery speed according to the prediction result and the preset ventilation and feed amount adjustment strategy, and sends a command to the corresponding actuator for adjustment.

In some embodiments, the intelligent prediction module 103 further includes a data iteration module 1031 for performing mathematical model iterative training based on lance parameters configured to: taking the spray gun parameters acquired in real time as initial conditions, and setting the historical spray gun parameters as training samples. The data iteration module 1031 is an important link in the module, and can improve the accuracy and instantaneity of prediction by continuously iterating and optimizing the mathematical model.

In some embodiments, inputting the initial conditions and the historical lance parameters into the data iteration model of the preconfigured data iteration model may include: a full convolution module, a residual convolution module sequence and a pooling module; selecting training samples from the training sample set, and executing the following training steps: and inputting the training sample into a full convolution module included in the initial data iteration model to obtain full convolution information. The full convolution module is responsible for receiving initial conditions (gun parameters acquired in real time) and performing global feature extraction. Through convolution operation, it can capture the spatial structure and correlation in the data.

In some embodiments, the full-scale convolution information is input into a residual convolution module sequence included in the initial data iteration model, so as to obtain residual convolution information, wherein the module is focused on capturing local details and variation trends in the data. By stacking multiple residual blocks, it is possible to efficiently extract deep features and alleviate the gradient vanishing problem. And inputting the residual convolution information into a pooling module included in the initial data iteration model to obtain initial spray gun parameter information, and performing dimension reduction and integration on the extracted features by the module to output more representative information. This helps to reduce the complexity and computation of the model and increase the prediction speed. Based on a preset loss function, determining an abnormal difference value of initial spray gun parameter characteristic information and sample spray gun parameter information included in a training sample; determining an initial data iteration model as a data iteration model in response to determining that the outlier is less than the target value; and/or in response to determining that the abnormal difference value is greater than or equal to the target value, adjusting relevant parameters in the initial data iterative model, determining the adjusted initial data iterative model as the initial data iterative model, and selecting training samples from the training sample set for executing the training step again.

In some embodiments, first, the system will collect in real time various lance parameters of the top-blowing lance 1011, such as gas flow, pressure, temperature, etc. These data are raw and require further analysis and processing by the intelligent prediction module 103. At the same time, the system will save historical lance parameters as training samples. The historical data contains various conditions and corresponding results in the past smelting process, and rich learning materials are provided for data iteration. During the training process, the system randomly selects a batch of training samples from the training sample set and inputs the training samples into the initial data iteration model. These samples contained various combinations of lance parameters and corresponding smelting results. Through the forward propagation process, the model will output initial lance parameter information. This information reflects the model's understanding and prediction of the current input data. The system then calculates a variance between the initial lance parameter characterization information and the sample lance parameter information in the training sample using a predetermined loss function. This difference value reflects the degree of deviation between the predicted result of the model and the actual data. Common loss functions include mean square error, cross entropy, etc. If the difference value is smaller than the target value (i.e. reaches the preset precision requirement), the prediction capability of the model is enough, and the initial data iteration model can be determined as the final data iteration model; otherwise, the relevant parameters in the model (such as convolution kernel size, learning rate, etc.) need to be adjusted to optimize the performance of the model, and the training step is performed again until the accuracy requirement is met. This process typically requires multiple iterations to complete.

In some embodiments, the data iterative model training is completed and reaches a preset accuracy requirement, and can be applied to the actual smelting process to predict in real time. In the prediction process, the model receives the spray gun parameters acquired in real time as input and outputs corresponding prediction results (such as smelting pressure, smelting speed, slag distribution and the like). The prediction results can provide basis for decision making of a control system, and accurate control of the smelting process is realized. Meanwhile, as the smelting process is carried out and data is continuously accumulated, the system can also update and optimize the data iteration model regularly to adapt to new smelting conditions and demand changes. This may be achieved by adding new training samples, adjusting model parameters, or introducing new algorithms.

In some embodiments, the intelligence module 103 can also include a physical model module 1032, a parameter calculation module 1033, and a post-processing module 1034. The physical model module 1032 is configured to construct a physical three-dimensional coordinate model based on the smelting equipment in practical use, where the physical three-dimensional coordinate model at least characterizes gun position information including structure and liquid level information of the smelting furnace and the top-blowing lance 1011, and performs grid division on the physical three-dimensional coordinate model, and each grid unit characterizes a three-dimensional coordinate. The physical model module 1032 is one of the important components of the intelligent prediction module 103. The method is based on smelting equipment in practical application to construct a physical three-dimensional coordinate model, and the model at least characterizes the structure of a smelting furnace 1012, liquid level information and gun position information of a top-blowing spray gun 1011. By meshing this physical model, each mesh cell is assigned a unique three-dimensional coordinate. Thus, the system can accurately simulate and track the state change of each position in the smelting furnace. The creation of the physical model module 1032 provides a basis for subsequent parameter calculations and predictions. By tightly combining with the actual smelting process, the module can accurately reflect the physical environment and the process conditions in the smelting furnace, and provides an important basis for the decision of a control system.

In some embodiments, the construction of the physical three-dimensional coordinate model may be performed in the following manner. First, the system builds a three-dimensional geometric model based on the size, shape and structural characteristics of the actual smelting plant 100. The model comprises key parts of a smelting furnace 1012, such as a furnace body, a furnace bottom, a furnace wall and the like, and position information of key elements, such as liquid level, a top-blowing spray gun 1011 and the like. To better simulate and calculate the physical process and state changes within the furnace, the physical model is divided into a series of small grid cells. Each grid cell is assigned a unique three-dimensional coordinate so that state changes within each cell can be precisely located and tracked. When constructing the physical model, various parameters are required to be set according to actual smelting conditions and process requirements. These parameters may include physical properties of the material (e.g., density, specific heat capacity, etc.), environmental parameters such as smelting temperature, pressure, etc., and operational parameters such as the blowing speed, angle, etc. of the top-blowing lance 1011.

In some embodiments, the parameter calculation module 1033 may be configured to select an appropriate preset algorithm based on different of the lance parameters to obtain the real-time smelting parameters. The parameter calculation module is a key component in the intelligent prediction module 103 responsible for calculating smelting parameters in real time. The workflow thereof can be divided into the following steps: and (3) data receiving: the parameter calculation module 1033 first receives real-time lance parameter information from the data acquisition module 102. The information comprises key parameters such as blowing speed, pressure, temperature and the like of the spray gun, and is an important basis for calculating real-time smelting parameters. Algorithm selection: according to different spray gun parameters and smelting conditions, the parameter calculation module can select a proper preset algorithm for calculation. These algorithms may be numerical simulation algorithms based on laws of physics or machine learning models trained based on a large amount of historical data. And (3) calculating in real time: the parameter calculation module 1033 performs real-time calculation to obtain the smelting parameters at the current time by using the selected algorithm and the received real-time spray gun parameters. These parameters may include key information on smelting speed, temperature distribution, slag composition, etc. And (3) outputting results: the calculated real-time smelting parameters are output to a post-processing module for further simulation and prediction. At the same time, these parameters are also saved in the database for subsequent analysis and optimization.

In some embodiments, the calculation method used by the calculation model provided by parameter calculation module 1033 may be based on the Navier-Stokes equation, which describes the motion of the fluid within the furnace, and is composed of conservation of momentum equations, which describe the equilibrium relationship of the internal and external forces of the fluid based on Newtonian mechanics. The conservation of momentum equation is typically part of the Navier-Stokes system of equations, which can be decomposed into three equations, corresponding to the movement of the fluid in three coordinate directions, respectively. The following is a form of momentum conservation equation in the three-dimensional case:

For the X direction: For the Y direction: /(I) For the Z direction:

Where ρ is the fluid density and u, v, w are the velocity components of the fluid in the x, y, z directions, respectively, p is the pressure, τij is the component of the stress tensor (describing the viscous effect inside the fluid), and gx, gy, gz are the weight components, respectively.

In some embodiments, the method used by the parameter calculation module 1033 to solve for turbulence in smelting is to select a corresponding turbulence model for solving, where the turbulence models are commonly used, such as a Reynolds average Navier-Stokes (RANS) model (including a k- ε model and a k- ω model), a Lagrange turbulence model (Large vortex simulation (LES)), a hybrid model (SST k- ω model), and so on, and these models can be arbitrarily tuned for calculation. Among the models commonly used for the bath smelting process splash is the lagrangian turbulence model (large vortex simulation (LES)), which has the advantage of numerically solving the larger scale turbulence structures of the Navier-Stokes equation set, while treating the smaller scale turbulence structures as models. Therefore, both the overall motion state of the bath and the local splash phenomenon can be described by the model, and the LES model has relatively low calculation cost. The basic equation of LES is obtained by spatially filtering the Navier-Stokes equation. The LES basic equation in the three-dimensional flow case is as follows:

Wherein the method comprises the steps of Is the filtered density,/>Is the filtered velocity component,/>Is the filtered pressure,/>Is the filtered stress tensor, ρu' _iu′_j is the small scale turbulence stress represented by the subgrid model. Here, the superscript "bar" denotes the filtering operation, while ρu' _iu′_j is a sub-grid model, representing modeling on small scale turbulence structures. Specific small vortex models are typically based on local characteristics of the flow field, such as simulation of sub-network dimensions, energy transfer, etc.

In some embodiments, the Solver in parameter calculation module 1033 may employ a Pressure-Based Solver (Pressure-Based Solver), which employs a SIMPLE algorithm that is particularly well suited for the calculation of fluid motion states in a smelting furnace, where the error of the predicted results obtained by the Solver from the actual parameters of the actual industrial smelting furnace can be kept below 10%, and thus the accuracy of the Solver is considered reliable and true. Furthermore, the solver updates the velocity and pressure fields by iteratively solving the continuous and momentum equations, the process being based primarily on numerical discretization and iterative solution of the numerical solution. The method comprises the following steps: 1. spatial discretization: the physical area of the smelting furnace is divided into limited grid cells, a partial differential equation is discretized into an algebraic equation by a numerical method in each grid cell, and an average value or a node value of a variable on each grid is defined; 2. time discretization: the running time is also discretized into small time steps, the total calculation time is divided into a plurality of discrete time steps, and in each time step, the value of the variable is updated through iterative calculation; 3. and (3) iteration solution: for each grid cell in each time step, iteratively solving a discretized algebraic equation, wherein the solution gradually converges to a stable solution in each iteration step; 4. boundary conditions: in the iterative solving process, boundary conditions, namely, variable values defined on problem boundaries, need to be considered; 5. convergence criteria: the termination of the iteration is typically determined by setting a convergence criterion, which may be based on the relative change of the solution, the size of the residual, etc., and stopping the iteration process when the convergence criterion is met; 6. time advance: after one time step is completed, the system proceeds to the next time step, where the previous solution is used as a new initial condition and the entire process loops until the desired simulation time is reached. The iterative process is performed in the whole space area, and involves calculation in each grid cell, and the iterative solution is an iterative approximation process, and the system gradually tends to be more true by continuously updating the variable values.

The post-processing module 1034 is configured to confirm the physical three-dimensional coordinates of the required grid unit, and obtain the smelting parameters on the grid unit at any time based on the real-time smelting parameters and the lance parameters. The post-processing module 1034 is the final link in the intelligent prediction module 103 responsible for integrating and outputting the prediction results. Its main functions include grid positioning, data mapping, and result output and presentation. Grid positioning is the physical three-dimensional coordinates of the desired grid cell that the post-processing module 1034 first validates. These grid cells, which may correspond to different locations or areas within the furnace, are the basic units for simulating and predicting state changes. The post-processing module 1034 maps the data to the corresponding grid cells based on the received real-time smelting parameters and lance parameter information. Thus, each grid cell has a set of smelting parameter values associated with it. And finally, the post-processing module 1034 displays the mapped data in a form of graph or table, so that the operator can check and analyze conveniently. At the same time, these predictions are also sent to other modules in the control system for guiding subsequent smelting operations and adjustments.

In some embodiments, the intelligent prediction module 103 further includes an image module 1035, where the main function of the image module 1035 is to convert the smelting parameters into an image display, and visually display the smelting parameters on any grid cell through different preset color levels. The graphical display mode is helpful for operators to understand the state change in the smelting furnace more quickly and accurately, so that more reasonable operation decisions can be made. The image module 1035 receives smelting parameter data from the post-processing module 1034 of the intelligent prediction module 103 that reflects state changes on individual grid cells within the smelting furnace. By converting these data into an image form, the image module 1035 enables visualization of the data so that an operator can intuitively see the state distribution and changes within the smelting furnace.

In some embodiments, to more clearly demonstrate the variation in the smelting parameters, the image module uses different preset color levels to map different smelting parameter values. For example, higher smelting pressures may be indicated in red, while lower smelting pressures may be indicated in blue. By means of this color mapping, the operator can quickly identify areas of high and low pressure within the smelting furnace. The image module 1035 may also support interactive operations that allow an operator to view detailed smelting parameter information on different grid cells by clicking or sliding on the image on the screen. This interactive mode of operation increases the ease of use and flexibility of the system.

In some embodiments, the image module 1035 may further provide a processing interface, where the processing interface provides a three-dimensional geometry of the smelting furnace and physical quantities (such as speed, pressure, etc.) to be displayed, when a macroscopic prediction result needs to be obtained, only a check box of the corresponding physical quantity needs to be opened, so that a real-time rendering result of slag splashing can be observed, when a microscopic prediction result needs to be obtained, a physical quantity check box at any position and moment can be selected, and further any physical information of a local position is obtained, where the physical information is beneficial to clearly knowing a gas-slag two-phase motion process and a change of multiple physical quantities in a molten pool.

In some embodiments, the control module 104 further includes an adaptive learning submodule 1041 and a dynamic optimization strategy library 1042. The control module 104 may utilize deep learning algorithms, a priori knowledge, and real time data to achieve adaptive adjustment and optimization of the operating strategy.

In some embodiments, the adaptive learning submodule 1041 may utilize a deep learning algorithm to construct a nonlinear mapping model between historical operating strategies and smelting parameters. This means that the submodule is able to learn past operating experience and corresponding smelting results in order to understand how the different operating strategies affect the smelting process. First, the adaptive learning submodule 1041 receives the historical operating strategy and corresponding smelting parameters as a training set. These data are a record of past operational experience and results, which are critical to training models. Then, a deep learning algorithm (such as a neural network) is utilized to construct a nonlinear mapping model between the historical operating strategy and the smelting parameters. This model enables capturing complex relationships between operating strategies and smelting parameters.

In some embodiments, to improve the convergence speed and prediction accuracy of the model, the adaptive learning submodule 1041 further sets a plurality of pre-stored operation strategies in the dynamic optimization strategy library 1042 as a priori knowledge. These pre-stored strategies are based on experience or previous research and can provide valuable references to the model. After the model is trained, the self-adaptive learning submodule 1041 inputs the spray gun parameters and smelting parameters acquired in real time into the model for online prediction. And dynamically adjusting an operation strategy according to the prediction result to achieve the optimal smelting effect. Model parameters and operating strategies are continuously optimized by comparison with feedback of actual smelting parameters. In this way, the adaptive learning submodule 1041 is able to continually learn and improve to accommodate changing smelting conditions.

In some embodiments, dynamic optimization strategy library 1042 stores a variety of pre-stored operating strategies that can provide a priori knowledge and references to the adaptive learning sub-module. Pre-stored policies may include rules-based operating policies (e.g., performing fixed actions based on certain conditions), model Predictive Control (MPC) based operating policies (predicting future states using models and optimizing control actions), and reinforcement learning algorithm based operating policies (learning optimal policies by trial and error). Rule-based policies are fixed rule sets formulated based on expert knowledge or experience. For example, when the smelting temperature is below a certain threshold, ventilation may be increased to raise the temperature. Rule-based policies are straightforward but may not be flexible enough to handle complex or nonlinear problems. The activated policy will be executed and its effect monitored in real time. If the effect reaches the expected value, continuing to execute the strategy; otherwise, it may be necessary to adjust the policy or select other alternatives. Model Predictive Control (MPC) based strategies are an advanced control method that uses mathematical models to predict future behavior of the system and optimize control actions to achieve predetermined goals. During the smelting process, the MPC may calculate optimal operating strategies, such as adjusting lance position, ventilation, and feed rate, based on real-time data and predictive models. MPC-based strategies are able to handle multivariate and nonlinear problems, but require accurate mathematical models and powerful computational power. Reinforcement learning is a machine learning method that learns the optimal strategy by trial and error. During smelting, the reinforcement learning algorithm can automatically adjust the operation strategy according to historical data and feedback signals (such as smelting efficiency, energy consumption and the like). The reinforcement learning-based strategy has adaptivity and learning ability and is capable of handling complex and dynamically changing environments.

In some embodiments, when the control module 104 needs to adjust the operating policies, it will select one or more appropriate policies from the dynamic optimization policy bank 1042 to activate. The selection criteria may include real-time data, predicted results, production targets, etc. The activated policy will be executed and its effect monitored in real time. If the effect reaches the expected value, continuing to execute the strategy; otherwise, it may be necessary to adjust the policy or select other alternatives. During execution, the control module evaluates the activated strategy and updates the strategy in the dynamic optimization strategy library according to the evaluation result. The evaluation criteria may include smelting efficiency, energy consumption, product quality, etc. By continuously updating and optimizing policies in the policy repository, the control system is able to adapt to continuously changing smelting conditions and demands. These pre-stored strategies may not only provide valuable reference information when the model is trained, but may also provide alternatives to the adaptive learning submodule 1041 during the online prediction and dynamic adjustment phases. When there is a large difference between the real-time collected data and the training set, the pre-stored policies in the dynamic optimization policies bank 1042 may be activated to cope with the abnormal situation.

In some embodiments, the control module 104 may further include a co-optimization sub-module 1043, where the co-optimization sub-module 1043 is a part of the control module 104 and has a main function of implementing co-optimization between different operation strategies in the smelting process to achieve more efficient, energy-saving and quality production goals. The method constructs a multi-objective optimization problem by comprehensively considering the influences of real-time smelting parameters, production objective requirements and various operation strategies, and applies a multi-objective optimization algorithm to solve so as to obtain an optimal operation strategy combination.

In some embodiments, the working principle of the collaborative optimization submodule 1043 may be divided into the following steps: first, the collaborative optimization submodule 1043 receives as input an optimized operating strategy from the adaptive learning submodule 1041 or other control module 104. Then, it constructs a multi-objective optimization problem according to smelting parameters (such as smelting temperature, pressure, speed, etc.), spray gun parameters (such as gas flow, pressure, temperature, etc.), and production objective requirements (such as maximizing smelting efficiency, minimizing energy consumption or improving product quality). In this problem, a plurality of operation strategies are used as decision variables, and a production target is used as an optimization target. In order to solve the multi-objective optimization problem, the collaborative optimization submodule adopts a multi-objective optimization algorithm, such as a genetic algorithm, a particle swarm optimization algorithm or an ant colony algorithm, and the like. The algorithms search for optimal combinations of operating strategies that can meet multiple production target requirements simultaneously through iterative searches. Finally, the collaborative optimization submodule 1043 feeds back the calculated optimal operation policy combination to the control module 104. The control module 104 adjusts the working states of the top-blowing lance 1011 and the smelting furnace 1012 according to the optimized strategies so as to realize the cooperative optimization control of the smelting process. The collaborative optimization submodule 1043 is closely cooperated with other control modules 104 and the adaptive learning submodule 1041 to realize intelligent control of the smelting process. It may receive as input the optimized operation strategy from the adaptive learning submodule 1041 and perform further collaborative optimization based on real-time data and production goal requirements. Meanwhile, the optimization result of the collaborative optimization submodule 1043 can also be fed back to the adaptive learning submodule 1041 to serve as a basis for continuous optimization and learning.

In some embodiments, the system further includes a fault pre-warning module 105 for analyzing potential fault risks based on the prediction results and sending pre-warning signals or controlling the top-blowing lance 1011 to adjust the operation strategy in time. The main function of the fault early warning module 105 is to analyze potential fault risks based on the prediction result obtained by the intelligent prediction module 103, and send early warning signals or control the top-blowing spray gun 1011 to adjust the operation strategy in time when the potential faults are detected so as to avoid or reduce the influence of the faults on the smelting process.

In some embodiments, the fault early warning module 105 may perform the following operations: the fault pre-warning module 105 first receives the prediction results from the intelligent prediction module 103. These predictions characterize the distribution and variation of smelting parameters, including smelting pressure, smelting speed, slag distribution, etc., within the molten bath of the smelting furnace. And secondly, based on the received prediction result, the fault early warning module analyzes potential fault risks by using a preset algorithm or model. For example, it may be monitored whether the smelting pressure is abnormally increased or decreased, whether the smelting speed is suddenly changed, whether the slag distribution is uniform, etc. If the fault early warning module 105 detects a potential risk of a fault, it will issue an early warning signal in time. These warning signals may be sounds, lights, text messages, or other forms of notification so that the operator or the automated system can respond quickly. In addition to sending out the early warning signal, the fault early warning module may also directly control the top-blowing lance 1011 to adjust the operation strategy to mitigate or avoid potential fault effects. For example, it may be possible to automatically adjust the gas flow, pressure or temperature, or to change the gun position height and ventilation and feed of the top-blowing gun 1011. The fault pre-warning module 105 works closely with the intelligent prediction module 103 and the control module 104. It receives as input the prediction results from the intelligent prediction module 103 and analyzes the potential risk of failure based on these results. When a potential fault is detected, it may send a signal to the control module 104 triggering a corresponding operational policy adjustment.

In some embodiments, the data acquisition module 102 further includes at least one pressure sensor for detecting pressure, at least one flow sensor for detecting gas flow, at least one temperature sensor for detecting temperature. These sensors not only provide real-time lance parameter data, but also provide a basis for subsequent intelligent prediction and control. The intelligent prediction module 103 may use the data to predict the distribution and variation of the smelting parameters within the smelting furnace 1012, and the control module 104 may adjust the operating strategy of the top-blowing lance 1011 based on the predictions to achieve a more optimal, more stable smelting process. The data acquisition module 102 cooperates closely with the intelligent prediction module 103 and the control module 104. It transmits the collected lance parameter data in real time to the intelligent prediction module 103, which uses the data for prediction and analysis. Meanwhile, the control module 104 may also obtain real-time lance parameter data from the data acquisition module 102 as needed to support its decision and control functions.

The above embodiments of the present disclosure have the following advantageous effects: the system can accurately adjust the operation strategy of the spray gun, including spray gun parameters, gun position height, ventilation quantity, feeding quantity and the like, by collecting various spray gun parameters of the top-blown spray gun in real time and combining an intelligent prediction module to predict smelting parameters of a molten pool in the smelting furnace, thereby ensuring that the smelting process is carried out in an optimal state and greatly improving smelting efficiency and stability. The self-adaptive learning sub-module in the control module can continuously learn and optimize the operation strategy, continuously adjust the model parameters and the operation strategy by comparing with the feedback of actual smelting parameters, and apply a multi-objective optimization algorithm to obtain the operation strategy combination so as to realize the collaborative optimization control of the top-blowing spray gun and the smelting furnace, thereby further improving the overall performance of the smelting process.

Fig. 2 illustrates a flow diagram of some embodiments of a top-blown smelting furnace intelligent control method according to the present disclosure.

As shown in fig. 2, the intelligent control method 200 of the top-blown smelting furnace comprises the following steps:

Step 201: and collecting the spray gun parameters of the top-blowing spray gun, wherein the spray gun parameters at least comprise gas flow, pressure and temperature information. This is the first step of the control method, where various lance parameters of the top-blowing lance are collected. These parameters include at least gas flow, pressure, and temperature information. These parameters are critical to understanding the operating conditions of the lance and subsequent control of the smelting process.

Step 202: and receiving the spray gun parameters and obtaining a prediction result through a preset algorithm, wherein the prediction result represents smelting parameter distribution and change in a molten pool of the smelting furnace, and the smelting parameters at least comprise smelting pressure, smelting speed and slag distribution. After the parameters of the lance are collected, these data are transmitted to an intelligent prediction module. The module processes the data using a preset algorithm and generates a prediction result. These predictions characterize the distribution and variation of smelting parameters (e.g., smelting pressure, smelting rate, slag distribution, etc.) within the smelting furnace melt pool.

Step 203: and controlling the top-blowing spray gun to adjust an operation strategy based on a prediction result, wherein the operation strategy comprises the following steps of: adjusting the spray gun parameters based on the prediction result to meet preset working conditions; controlling the gun position height of the top-blowing spray gun based on the prediction result; and controlling the ventilation quantity and the feeding quantity of the top-blowing spray gun based on the prediction result. And according to the prediction result provided by the intelligent prediction module, the control module generates a corresponding operation strategy to adjust the working state of the top-blowing spray gun. These operating strategies include: adjusting parameters of a spray gun: to meet preset operating conditions. For example, if the prediction shows that the smelting rate is too slow, the control module may increase the gas flow or increase the temperature to accelerate the smelting process. Controlling the gun position height of the top-blowing spray gun: the height of the lance can be adjusted to influence the position and angle of the gas injection into the bath, thereby affecting smelting efficiency and slag formation. Controlling ventilation and feeding amount of the top-blowing spray gun: the adjustment of ventilation and feed amount can directly influence the oxygen and raw material supply in the smelting furnace, and is an important means for controlling the smelting process.

It will be appreciated that the steps described in the furnace control method 200 correspond to the various steps in the furnace control system described with reference to fig. 1. Thus, the operations, features, and benefits of the above-described smelting furnace control system are equally applicable to the smelting furnace control method 200 and are not described in detail herein.

Referring now to fig. 3, a schematic diagram of an electronic device 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), car terminals (e.g., car navigation terminals), and the like, as well as stationary terminals such as digital TVs, desktop computers, and the like. The terminal device shown in fig. 3 is only one example and should not impose any limitation on the functionality and scope of use of the embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from ROM 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.

It should be noted that, the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: collecting spray gun parameters of a top-blowing spray gun, wherein the spray gun parameters at least comprise gas flow, pressure and temperature information; receiving the parameters of the spray gun and obtaining a prediction result through a preset algorithm, wherein the prediction result represents smelting parameter distribution and change in a molten pool of the smelting furnace, and the smelting parameters at least comprise smelting pressure, smelting speed and slag distribution; and controlling the top-blowing spray gun to adjust an operation strategy based on the prediction result, wherein the operation strategy comprises the following steps: adjusting the parameters of the spray gun based on the prediction result so as to meet preset working conditions; controlling the gun position height of the top-blowing spray gun based on the prediction result; and controlling the ventilation quantity and the feeding quantity of the top-blowing spray gun based on the prediction result.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, and the functions described herein above may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. An intelligent control system of a top-blown smelting furnace, comprising:

The smelting device comprises a top-blowing spray gun and a smelting furnace;

The data acquisition module is used for acquiring various spray gun parameters of the top-blowing spray gun, wherein the spray gun parameters at least comprise gas flow, pressure and temperature information;

The intelligent prediction module is used for receiving the spray gun parameters and obtaining a prediction result through a preset algorithm, wherein the prediction result represents smelting parameter distribution and change in a molten pool of the smelting furnace, and the smelting parameters at least comprise smelting pressure, smelting speed and slag distribution;

The control module is used for controlling the top-blowing spray gun to adjust an operation strategy based on the prediction result, wherein the operation strategy comprises the following steps of:

adjusting the spray gun parameters based on the prediction result to meet preset working conditions;

Controlling the gun position height of the top-blowing spray gun based on the prediction result;

and controlling the ventilation quantity and the feeding quantity of the top-blowing spray gun based on the prediction result.

2. The intelligent control system of a top-blown smelting furnace of claim 1, wherein the intelligent prediction module comprises:

and the data iteration module is used for carrying out mathematical model iteration training according to the spray gun parameters and is configured to carry out the following operations:

taking the spray gun parameters acquired in real time as initial conditions, and setting historical spray gun parameters as training samples;

inputting the initial conditions and the historical lance parameters into a pre-configured data iteration model, the data iteration model comprising: a full convolution module, a residual convolution module sequence and a pooling module;

selecting training samples from the training sample set, and executing the following training steps:

Inputting the training sample into a full convolution module included in the initial data iteration model to obtain full convolution information;

inputting the full convolution information into a residual convolution module sequence included in the initial data iteration model to obtain residual convolution information;

inputting residual convolution information into a pooling module included in an initial data iteration model to obtain initial spray gun parameter information;

Based on a preset loss function, determining an abnormal difference value of initial spray gun parameter characteristic information and sample spray gun parameter information included in a training sample;

Determining an initial data iteration model as a data iteration model in response to determining that the outlier is less than the target value; and/or

And in response to determining that the abnormal difference value is greater than or equal to the target value, adjusting relevant parameters in the initial data iterative model, determining the adjusted initial data iterative model as an initial data iterative model, and selecting training samples from the training sample set for executing the training step again.

3. The intelligent control system of a top-blown smelting furnace of claim 2, wherein the intelligent prediction module further comprises:

The physical model module is used for constructing a physical three-dimensional coordinate model based on the smelting equipment in actual application, the physical three-dimensional coordinate model at least represents gun position information including structure and liquid level information of the smelting furnace and the top-blowing spray gun, the physical three-dimensional coordinate model is subjected to grid division, and each grid unit represents a three-dimensional coordinate;

The parameter calculation module is used for selecting a proper preset algorithm based on different spray gun parameters to obtain real-time smelting parameters;

And the post-processing module is used for confirming the physical three-dimensional coordinates of the required grid unit and obtaining smelting parameters on the grid unit at any moment based on the real-time smelting parameters and the spray gun parameters.

4. A top-blown smelting furnace intelligent control system according to claim 3, wherein the intelligent prediction module further comprises:

And the image module is used for converting the smelting parameters into image display and displaying the smelting parameters on any grid unit according to different preset color levels.

5. The intelligent control system of a top-blown smelting furnace according to claim 1, wherein the control module comprises:

an adaptive learning sub-module and a dynamic optimization strategy library, the adaptive learning sub-module configured to:

Receiving a historical operation strategy and corresponding smelting parameters as a training set, and constructing a nonlinear mapping model between the historical operation strategy and the smelting parameters by using a deep learning algorithm;

setting a plurality of pre-stored operation strategies in a dynamic optimization strategy library as priori knowledge so as to improve the convergence speed and the prediction accuracy of the nonlinear mapping model;

Inputting the real-time collected spray gun parameters and smelting parameters into the trained nonlinear mapping model for online prediction, and dynamically adjusting the operation strategy according to the prediction result;

Continuously optimizing model parameters and the operation strategy by comparing with feedback of actual smelting parameters so as to realize self-adaptive learning and continuous optimization of the operation module;

The dynamic optimization strategy library comprises a dynamic optimization strategy library, wherein a plurality of prestored control strategies in the dynamic optimization strategy library comprise a rule-based operation strategy, a model prediction control-based operation strategy and an operation strategy obtained based on a reinforcement learning algorithm.

6. The intelligent control system of a top-blown smelting furnace of claim 5, wherein the control module further comprises a co-optimization sub-module configured to:

receiving an optimized operation strategy from the adaptive learning sub-module;

constructing a multi-objective optimization problem based on the smelting parameters, the spray gun parameters and the production objective requirements acquired in real time, wherein the production objective requirements comprise maximizing smelting efficiency, minimizing energy consumption or improving product quality;

Applying a multi-objective optimization algorithm to obtain an operation strategy combination, wherein the multi-objective optimization algorithm comprises a genetic algorithm, a particle swarm optimization algorithm or an ant colony algorithm;

And feeding back the operation strategy combination to the control module so as to realize the collaborative optimization control of the top-blowing spray gun and the smelting furnace.

7. The intelligent control system of a top-blown smelting furnace of claim 1, wherein the system further comprises:

and the fault early warning module is used for analyzing potential fault risks based on the prediction result and timely sending out early warning signals or controlling the top-blowing spray gun to adjust an operation strategy.

8. The intelligent control system of a top-blown smelting furnace according to claim 1, wherein the data acquisition module further comprises:

At least one pressure sensor for detecting pressure;

At least one flow sensor for detecting a flow of gas;

At least one temperature sensor for detecting a temperature.

9. An intelligent control method of a top-blown smelting furnace comprises the following steps:

Collecting spray gun parameters of a top-blowing spray gun, wherein the spray gun parameters at least comprise gas flow, pressure and temperature information;

receiving the spray gun parameters and obtaining a prediction result through a preset algorithm, wherein the prediction result represents smelting parameter distribution and change in a molten pool of the smelting furnace, and the smelting parameters at least comprise smelting pressure, smelting speed and slag distribution;

controlling the top-blowing spray gun to adjust an operation strategy based on the prediction result, wherein the operation strategy comprises the following steps: adjusting the spray gun parameters based on the prediction result to meet preset working conditions;

10. A computer readable medium having stored thereon a computer program, wherein the program when executed by a processor implements the method of claim 9.