Novel side-blowing feeding device and intelligent control system and method

Abstract

The invention relates to the technical field of nonferrous metallurgy, in particular to a novel side-blowing feeding device and an intelligent control system and method. The device comprises a gas compressor, a safety valve, a pressure sensor, a mechanical sealing device, an electric control valve, an additive storage tank, a pulverized coal storage tank and a raw material storage tank. The system comprises a data acquisition module, an intelligent prediction module and an operation module. The method comprises the steps of collecting particles injected into a molten pool and spray gun gas flow and other data in real time; based on the collected data such as the particles injected into the molten pool and the air flow of the spray gun, the appropriate feeding amount and the appropriate air amount are given through numerical calculation; and according to data obtained through calculation, a gas compressor and discharging valves of all the stock bins are controlled to achieve precise gas supply and feeding. Particles and air are injected into the molten pool from the spray guns on the two sides of the side-blown smelting furnace at the same time in a pneumatic conveying mode, waste of the material particles is reduced, the material feeding amount and the air flow are reasonably predicted and accurately controlled, and efficient operation of the side-blown smelting furnace is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of nonferrous metallurgy, and in particular to a novel side-blowing feeding device and an intelligent control system and method. Background Art

[0002] The smelting process of the side-blown furnace has the advantages of complete supporting facilities, low energy consumption, good environmental protection, low investment and low operating cost. It is mainly suitable for blast furnace production, casting and steel smelting industries, and is also used in copper metallurgy and zinc metallurgy. The energy-saving and environmental protection effect of the side-blown furnace is remarkable, which meets the requirements of green metallurgy, energy conservation and emission reduction. The side-blown furnace is widely used in the smelting of non-ferrous metals such as copper, lead and nickel. In the traditional side-blowing operation process, particles such as ore powder, coal powder and additives are thrown into the molten pool through the top of the furnace to participate in the smelting process. This leads to the following problems in the smelting process: (1) Some of these particles are thrown into the molten pool from the top of the furnace. (1) In the process of falling, the particles will be carried away by the rising flue gas on the surface of the molten pool, thus causing material waste and increasing the burden of downstream smoke treatment; (2) Due to the diverse sources of raw materials and large variations in taste, the amount of added particles needs to be adjusted in real time, but the existing feeding method is heavily dependent on the experience of workers, resulting in low efficiency during the smelting process; (3) The particles thrown into the molten pool are concentrated in the molten pool area below the feeding port, and the amount of particles in other positions is relatively small, resulting in serious uneven distribution of parameters such as temperature and pressure in the furnace, which greatly affects the product quality. In order to solve these problems, the present invention proposes a new side-blowing feeding device and an intelligent control system and method.

[0003] Prior art one, Chinese patent, application number 202210933211.5 discloses a side-blown furnace feeding device, which includes a storage piece, a conveying assembly and a metering assembly. The storage piece has an inlet and an outlet, one end of the conveying assembly is connected to the outlet, and the other end of the conveying assembly is suitable for being connected to the feed port of the side-blown furnace. The conveying assembly includes a lining plate, and the conveyed material is suitable for being placed on the lining plate. The metering assembly is arranged on the storage piece to measure the discharge amount of the storage piece. Although a side-blown furnace feeding device and method are proposed, which can realize continuous closed and precise feeding of high-temperature roasted sand. However, a part of the feed particles will be carried away by the rising flue gas on the surface of the molten pool in the process of falling from the top of the furnace, thereby causing material waste and increasing the burden of downstream smoke treatment;

[0004] Prior art 2, Chinese patent, application number 202310267663.9 discloses a pulverized coal quantitative feeding system for a side-blown furnace, including a bracket, a control mechanism, a quantitative mechanism and a feeding mechanism. A storage tank and a spray tank are fixedly connected to the bracket, a connecting pipe is fixedly connected to the top of the spray tank, and the top of the storage tank is connected to a feed pipe. The quantitative mechanism includes a quantitative tank, and the top of the quantitative tank is connected to a sliding pipe. This pulverized coal quantitative feeding system for a side-blown furnace controls the in and out of raw materials and the flow of gas through a control mechanism. After the set raw materials are stored in the quantitative tank by the quantitative mechanism, the connected state of the sliding pipe is closed by gas push, and the connection with the spray tank is opened. The airflow is used to blow the pulverized coal in the quantitative tank into the spray tank for quantitative feeding through the feeding mechanism. Although the uniformity of feeding is improved, the problem of uneven coal supply and difficulty in achieving quantitative uniform delivery and closing operation when the existing pulverized coal feeding system for side-blown furnaces is solved. However, the sources of raw materials are diverse and the taste varies greatly. The amount of added particles needs to be adjusted in real time, but the feeding method is more dependent on the workers' experience, and the efficiency of the smelting process is low;

[0005] Prior art three, Chinese patent, application number 202411040079.0 discloses a wind selection device, which includes a wind selection box, a supply part, a blowing component and an air regulating component; a feed port is arranged on the upper side of the wind selection box, and a first discharge port and a second discharge port are distributed on the lower side along a preset direction, and the first discharge port is located directly below the feed port; an air inlet and an air outlet are arranged on opposite sides of the wind selection box, respectively, and the air inlet and the air outlet are arranged along a preset direction, and the air inlet is close to the first discharge port; the supply part is configured to supply materials into the feed port and form a material curtain; the blowing component can blow air to the material curtain through the air inlet; the air regulating component is arranged at the air inlet, and the air regulating component is configured to adjust the amount of air blown by the blowing component onto the material curtain. Although it can adapt to different materials to adjust the amount of air blown by the blowing component onto the material curtain, it helps to improve the practicality of the wind selection equipment. However, the particles are concentrated in the area below the feeding port, and the amount of particles in other locations is relatively small, resulting in uneven distribution of parameters such as temperature and pressure in the furnace, affecting product quality.

[0006] At present, in the prior art one, the prior art two and the prior art three, a part of the particles will be carried away by the rising flue gas on the surface of the molten pool during the process of falling from the top of the furnace, thereby causing material waste and increasing the burden of downstream smoke treatment. Due to the diverse sources of raw materials and large changes in taste, the amount of added particles needs to be adjusted in real time, but the existing feeding method is heavily dependent on the experience of workers, resulting in low efficiency in the smelting process; the particles are concentrated in the molten pool area below the feeding port, and the amount of particles in other positions is relatively small, resulting in uneven distribution of parameters such as temperature and pressure in the furnace, affecting product quality; therefore, the present invention proposes a new side-blowing feeding device and an intelligent control system and method, which injects particles and air into the molten pool from the spray guns on both sides of the side-blown furnace at the same time through pneumatic conveying, so as to reduce material particle waste, reasonably predict and accurately control the material feed amount and air flow, and realize efficient operation of the side-blown smelting furnace. Summary of the invention

[0007] The main purpose of the present invention is to provide a new side-blowing feeding device and an intelligent control system and method to solve the problem in the prior art that a part of the particles will be carried away by the rising flue gas on the surface of the molten pool during the process of falling from the top of the furnace, thereby causing material waste and increasing the burden of downstream smoke treatment. Due to the diverse sources of raw materials and large changes in taste, the amount of added particles needs to be adjusted in real time, but the existing feeding method relies heavily on the experience of workers, resulting in low efficiency in the smelting process; the particles are concentrated in the molten pool area below the feeding port, and the amount of particles in other positions is relatively small, resulting in uneven distribution of parameters such as temperature and pressure in the furnace, affecting product quality.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A new side-blowing feeding device includes a compressor, a safety valve, a pressure sensor, a mechanical sealing device, an electric control valve, an additive storage tank, a coal powder storage tank and a raw material storage tank;

[0010] Among them, there is a compressor on one side of the pipeline, and multiple safety valves are installed on the pipeline; additives, coal powder, and mineral powder raw materials are stored in separate additive storage tanks, coal powder storage tanks and raw material storage tanks respectively. Multiple pressure sensors are installed on the wall of each storage tank, and the bottom of each storage tank is connected to the pipeline through an electric control valve; there is a mechanical sealing device on the top of each storage tank, and a pipeline is opened on one side of the top to connect to the compressor, and a safety valve is provided.

[0011] To achieve the above object, the present invention also provides the following technical solutions:

[0012] A new type of side-blowing feeding intelligent control system, including:

[0013] The data acquisition module is responsible for real-time collection of data such as particles injected into the molten pool and the air flow rate of the spray gun, and transmits the collected data to the intelligent prediction module;

[0014] The intelligent prediction module is responsible for providing the appropriate feed amount of materials, coal powder, additives and air volume through numerical calculation based on the parameters collected by the data acquisition module, and issuing instructions to the operation module;

[0015] The operation module is responsible for executing the instructions given by the intelligent prediction module and controlling the compressor and the discharge valves of each silo to achieve precise air delivery and material feeding.

[0016] As a further improvement of the present invention, the data acquisition module includes:

[0017] The pressure collection submodule consists of multiple pressure sensors installed on the inner wall of the storage tank, which are responsible for collecting the pressure of particles in the storage tank on the inner wall of the storage tank and pre-processing the collected data for subsequent data analysis and calculation;

[0018] The numerical calculation submodule is responsible for fusing the data collected by multiple sensors, processing the pressure data, establishing a relationship model between pressure and particle outflow, and obtaining the particle outflow based on the data collected by the sensors; if the fused pressure is less than the preset threshold, an alarm instruction is generated to indicate that there is insufficient particle in the storage tank;

[0019] The particle quantity output submodule is responsible for detecting whether an alarm instruction is generated. If an alarm instruction is detected, the alarm instruction is sent to the data center to indicate that there are insufficient particles in the storage tank. If no alarm instruction is detected, the particle outflow estimated by the relationship model between pressure and particle outflow is output to the intelligent prediction module.

[0020] As a further improvement of the present invention, the numerical calculation submodule includes:

[0021] The feature extraction unit is responsible for extracting features related to particle outflow from the preprocessed pressure data, including the average, maximum, minimum and standard deviation of the pressure;

[0022] The relationship building unit is responsible for training the model using the preprocessed data and the historical data of the particle outflow and the characteristic value of the pressure sensor, and obtaining the fitting curve of the particle outflow and the characteristic value of the pressure by monitoring the changes of the particle outflow and the characteristic value of the pressure sensor in real time;

[0023] The verification and optimization unit is responsible for cross-validating the trained model, evaluating the performance of the relationship model between pressure and particle outflow, and optimizing the model's hyperparameters through preset test data; when a change in the pressure sensor value is detected, the predicted particle outflow can be obtained.

[0024] As a further improvement of the present invention, the intelligent prediction module includes:

[0025] The three-phase flow prediction submodule is responsible for predicting the gas-liquid-solid three-phase flow process in the side-blown furnace; determining the volume occupied by the liquid and gas phases in each grid, identifying the gas-liquid interface; and tracking the solid phase separately;

[0026] The interface force submodule is responsible for calculating the resistance between particles and fluid (F d ), lift (F lif ), pressure gradient force (F p ), viscous stress (F ▽·τ ), virtual mass force (F vm ) and Basset force (F B );

[0027] The interface particle behavior submodule is responsible for discerning the particle behavior at the gas-liquid interface using the liquid volume fraction through the VOF method, which ranges from 0 to 1, indicating that the thickness is finite and the particles crossing the gas-liquid interface must overcome the surface tension of the liquid film;

[0028] As a further improvement of the present invention, the grid division in the three-phase flow prediction submodule includes:

[0029] The grid construction unit is responsible for selecting the hexahedral structured grid as the grid type, performing grid encryption in the area near the gas-liquid interface, and adjusting the grid size according to the liquid phase volume fraction gradient to ensure that the detailed changes of the interface are captured;

[0030] The mesh verification unit is responsible for verifying the independence of the constructed mesh. By comparing the calculation results under different mesh densities, the appropriate mesh size is determined, and the mesh quality is checked to ensure that the orthogonal quality of the mesh remains above 0.5.

[0031] The boundary layer unit is responsible for setting the boundary layer grid near the wall and where the particles are blown in, setting the appropriate number of layers and thickness of the grid, and performing verification calculations to obtain the optimal grid.

[0032] As a further improvement of the present invention, the gas-liquid interface is identified in the three-phase flow prediction submodule, including:

[0033] Volume calculation unit, responsible for introducing the liquid volume fraction and calculating the gas volume and liquid volume in each grid cell;

[0034] The phase interface tracking unit is responsible for solving the control equation of the liquid volume fraction to track the phase interface, and obtains the density and dynamic viscosity in a specific unit by linear interpolation of the liquid volume fraction;

[0035] The tension calculation unit is responsible for calculating the surface tension of the gas-liquid interface, introducing a smoothing function to solve the discontinuity of the interface, and calculating the local curvature of the interface;

[0036] As a further improvement of the present invention, the interface force submodule comprises:

[0037] The interface force calculation module is responsible for calculating the resistance between particles and fluid (F d ), lift (F lif ), pressure gradient force (F p ), viscous stress (F ▽·τ ), virtual mass force (F vm ) and Basset force (F B );

[0038] The resistance prediction module is responsible for selecting and establishing a resistance model, and using the established resistance model to calculate and predict the resistance between particles and fluid;

[0039] The lift calculation module is responsible for calculating the Saffman lift generated by fluid shear and the Magnus lift generated by particle rotation;

[0040] As a further improvement of the present invention, the interface particle behavior submodule includes:

[0041] Particle-particle / wall collisions are simulated using a complete DEM model based on the soft sphere collision model. The interaction force F between the collision pairs is cot It can be divided into normal component and tangential component, and the formula is as follows:

[0042]

[0043] Where k and η represent the spring constant and damping coefficient respectively; n and t represent the unit vectors of the collision pair along the normal and tangential directions respectively; δ t,ij and δ n,ij are the tangential and normal displacements of the colliding pair, respectively; the nonlinear Hertz-Mindlin contact type is used to evaluate the normal and tangential forces.

[0044] To achieve the above object, the present invention also provides the following technical solutions:

[0045] A novel side-blowing feeding intelligent control method includes:

[0046] Collect data such as particles injected into the molten pool and air flow rate of the spray gun in real time, and transmit the collected data to the intelligent prediction module;

[0047] Based on the collected data such as the particles injected into the molten pool and the air flow rate of the spray gun, the appropriate feed amount of materials, coal powder, additives and air volume are given through numerical calculation;

[0048] Based on the calculated data on material, coal powder, additive feed and air volume, the compressor and each silo discharge valve are controlled to achieve precise air delivery and feeding.

[0049] To achieve the above object, the present invention also provides the following technical solutions:

[0050] An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the layout method of the new side-blowing feeding system as described above is implemented.

[0051] To achieve the above object, the present invention also provides the following technical solutions:

[0052] A storage medium stores program instructions, which, when executed by a processor, implement a layout method for a novel side-blowing feeding system as described above.

[0053] The compressor of the present invention provides power for the particles in the pipeline, so that the particles can pass through the pipeline smoothly and quickly, and also provides the required air for the side-blowing furnace, thereby improving the conveying efficiency and accuracy of the particles and ensuring the continuity and stability of the production process; the safety valve automatically opens when the pipeline pressure is too high to release excess pressure and protect the pipeline and equipment from damage; the safety of the device is enhanced and safety accidents caused by excessive pressure are avoided; the pressure sensor monitors the pressure change in the storage tank in real time, thereby reflecting the inventory of particles and ensuring the continuity of production and the sufficiency of raw materials; the mechanical sealing device opens when adding particles to allow the particles to enter the storage tank, and closes and seals after the particles are added to prevent gas or particles from leaking, thereby ensuring the sealing of the storage tank and avoiding the waste of raw materials and environmental pollution; the electric control valve accurately controls the feed amount of the particles to ensure that various types of particles are mixed according to a predetermined ratio, thereby improving the accuracy and consistency of the product and meeting different production requirements; the additive storage tank, the coal powder storage tank and the raw material storage tank respectively store additives, coal powder and mineral powder raw materials, thereby ensuring the sufficiency and order of various raw materials required for production; the production process is simplified, the production efficiency is improved, and the confusion and waste of raw materials are avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a device diagram of an embodiment of the novel side-blowing feeding device of the present invention;

[0055] Figure 2 This is a functional module schematic diagram of an embodiment of a novel side-blowing feeding intelligent control system of the present invention;

[0056] Figure 3 It is a schematic diagram of an embodiment of the novel side-blowing feeding intelligent control system of the present invention;

[0057] Figure 4 A schematic diagram of the steps of an embodiment of a novel side-blowing feeding intelligent control method of the present invention;

[0058] Figure 5 It is a structural schematic diagram of an embodiment of an electronic device of the present invention;

[0059] Figure 6 It is a schematic structural diagram of an embodiment of the storage medium of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] The terms "first", "second" and "third" in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0062] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0063] like Figure 1As shown, this embodiment provides an embodiment of a novel side-blowing feeding device, including: a compressor 1, a safety valve 2, a pressure sensor 3, a mechanical sealing device 4, an electric control valve 5, an additive storage tank 6, a coal powder storage tank 7 and a raw material storage tank 8;

[0064] Among them, there is a compressor 1 on one side of the pipeline, and multiple safety valves 2 are arranged on the pipeline; additives, coal powder, and mineral powder raw materials are stored in separate additive storage tanks 6, coal powder storage tanks 7 and raw material storage tanks 8, respectively. Multiple pressure sensors 3 are installed on the wall of each storage tank, and the bottom of each storage tank is connected to the pipeline through an electric control valve 5; each storage tank has a mechanical sealing device 4 on the top, and a pipeline is opened on one side of the top to connect to the compressor 1, and a safety valve 2 is provided.

[0065] Preferably, the present embodiment changes the top feeding into the side feeding, that is, air and particles are injected into the molten pool from the side wall spray gun at the same time; the mineral powder raw material, coal powder and additives are stored in separate storage tanks respectively; each storage tank is connected to a compressor 1 for pressurizing the pipe to realize the transportation of a large number of particles; a plurality of pressure sensors 3 are arranged on the wall of each storage tank to monitor the remaining particles; each storage tank has a mechanical sealing device 4 on the top, which can be opened to add particles when the response particle amount is insufficient, and closed and sealed when the particles are added so that the connected compressor 1 can work normally; each storage tank has an electric control valve 5 at the bottom for precise control of the particle feed amount; the bottoms of all storage tanks are connected to the same pipeline, in which various types of particles can be mixed in any proportion; a compressor 1 is connected to the top of the pipeline to provide air to the side-blowing furnace, transport particles at the same time, and realize the mixing of particles during the transportation process; finally, the air-particle two-phase is injected into the molten pool from the side-blowing spray gun at the same time.

[0066] In summary, the compressor 1 of this embodiment provides power for the particles in the pipeline, so that they can pass through the pipeline smoothly and quickly, and also provides the required air for the side-blowing furnace, thereby improving the efficiency and accuracy of particle transportation and ensuring the continuity and stability of the production process; the safety valve 2 automatically opens when the pipeline pressure is too high to release excess pressure and protect the pipeline and equipment from damage; the safety of the device is enhanced and safety accidents caused by excessive pressure are avoided; the pressure sensor 3 monitors the pressure changes in the storage tank in real time, thereby reflecting the inventory of particles and ensuring the continuity of production and the sufficiency of raw materials; the mechanical sealing device 4 is opened when adding particles. The electric control valve 5 controls the feed amount of particles accurately to ensure that various types of particles are mixed in a predetermined proportion, thereby improving the accuracy and consistency of the product and meeting different production requirements. The additive storage tank 6, the pulverized coal storage tank 7 and the raw material storage tank 8 store additives, pulverized coal and mineral powder raw materials respectively, ensuring the sufficiency and orderliness of various raw materials required for production. The production process is simplified, the production efficiency is improved, and the confusion and waste of raw materials are avoided.

[0067] like Figure 2 As shown, this embodiment also provides an embodiment of a new side-blowing feeding intelligent control system. In this embodiment, the new side-blowing feeding intelligent control system is applied to the new side-blowing feeding device in the above embodiment. The new side-blowing feeding intelligent control system includes a data acquisition module, an intelligent prediction module and an operation module;

[0068] Among them, the data acquisition module is responsible for real-time collection of data such as particles injected into the molten pool and the air flow rate of the spray gun, and transmits the collected data to the intelligent prediction module;

[0069] The intelligent prediction module is responsible for providing the appropriate feed amount of materials, coal powder, additives and air volume through numerical calculation based on the parameters collected by the data acquisition module, and issuing instructions to the operation module;

[0070] The operation module is responsible for executing the instructions given by the intelligent prediction module and controlling the compressor and the discharge valves of each silo to achieve precise air delivery and material feeding.

[0071] Preferably, the data acquisition module of this embodiment collects key data such as particles injected into the molten pool and gun airflow in real time to ensure the accuracy and timeliness of the data, and provide a reliable basis for subsequent analysis and prediction; the intelligent prediction module uses advanced numerical calculation methods to make accurate predictions based on the data provided by the data acquisition module; gives appropriate material, coal powder, additive feed amount and air volume to ensure the stability of the production process and product quality; the operation module accurately executes the instructions given by the intelligent prediction module, controls the compressor and each silo discharge valve, and realizes accurate air supply and feeding; finally, the data acquisition platform continues to collect the parameters in the molten pool under the above-mentioned material and gas flow rates, and continues to send them to the intelligent prediction platform for prediction, and the dynamic cycle process of the trip is completed (refer to the attached schematic diagram for the specific principle diagram). Figure 3 ).

[0072] To sum up, through real-time monitoring, this embodiment can promptly discover abnormal changes in the production process, provide a basis for rapid response and adjustment, improve the transparency and controllability of the production process, and help improve overall production efficiency; realize intelligent control of the production process, significantly improve production efficiency and product quality; through accurate prediction, reduce the waste of raw materials and energy consumption, reduce production costs, enhance the flexibility and adaptability of the production process, and be able to quickly respond to changes in market demand; ensure the accurate execution of production instructions, and improve the stability and controllability of the production process; through precise control, further improve production efficiency and product quality; reduce the risk of operational errors and improve production safety.

[0073] Furthermore, in the novel side-blowing feeding intelligent control system of this embodiment, the data acquisition module specifically includes:

[0074] The pressure collection submodule consists of multiple pressure sensors installed on the inner wall of the storage tank, which are responsible for collecting the pressure of particles in the storage tank on the inner wall of the storage tank and pre-processing the collected data for subsequent data analysis and calculation;

[0075] The numerical calculation submodule is responsible for fusing the data collected by multiple sensors, processing the pressure data, establishing a relationship model between pressure and particle outflow, and obtaining the particle outflow based on the data collected by the sensors; if the fused pressure is less than the preset threshold, an alarm instruction is generated to indicate that there is insufficient particle in the storage tank;

[0076] The particle quantity output submodule is responsible for detecting whether an alarm instruction is generated. If an alarm instruction is detected, the alarm instruction is sent to the data center to indicate that there is insufficient particles in the storage tank; if no alarm instruction is detected, the particle outflow estimated by the relationship model between pressure and particle outflow is output to the intelligent prediction module;

[0077] Preferably, the pressure acquisition submodule of this embodiment can collect the pressure data of particles in the storage tank on the inner wall of the storage tank in real time and at multiple points by installing multiple pressure sensors on the inner wall of the storage tank, and pre-process the collected data to improve the accuracy and reliability of the data; the numerical calculation submodule fuses the data collected by multiple sensors and pre-processes the pressure data; establishes a relationship model between pressure and particle outflow, through which the particle outflow can be estimated; sets a preset threshold, and when the fused pressure is less than the threshold, generates an alarm instruction to indicate that there are insufficient particles in the storage tank; the particle quantity output submodule detects whether to generate an alarm instruction, and takes different actions according to the detection result. If an alarm instruction is detected, the alarm instruction is sent to the data center to indicate that there are insufficient particles in the storage tank; if no alarm instruction is detected, the particle outflow estimated by the relationship model between pressure and particle outflow is output to the intelligent prediction module.

[0078] In summary, this embodiment grasps the pressure distribution of particles in the storage tank on the inner wall in real time, ensures the accuracy and efficiency of processing, and reduces the possibility of false alarms and missed alarms; through data fusion and modeling, it realizes accurate estimation of particle outflow, provides strong support for production scheduling and inventory management, and the generation of alarm instructions can promptly remind operators to pay attention to the inventory of particles in the storage tank to avoid production interruptions; it realizes timely response and processing of alarm instructions, and ensures that the data center can obtain the inventory information of particles in the storage tank in time; when no alarm instruction is generated, the estimated particle outflow is output to the intelligent prediction module, which provides a reference for future production planning and inventory management.

[0079] Furthermore, in the novel side-blowing feeding intelligent control system of this embodiment, the numerical calculation submodule specifically includes:

[0080] The feature extraction unit is responsible for extracting features related to particle outflow from the preprocessed pressure data, including the average, maximum, minimum and standard deviation of the pressure;

[0081] The relationship building unit is responsible for training the model using the preprocessed data and the historical data of the particle outflow and the characteristic value of the pressure sensor, and obtaining the fitting curve of the particle outflow and the characteristic value of the pressure by monitoring the changes of the particle outflow and the characteristic value of the pressure sensor in real time;

[0082] The verification and optimization unit is responsible for cross-validating the trained model, evaluating the performance of the relationship model between pressure and particle outflow, and optimizing the model's hyperparameters through preset test data; when a change in the pressure sensor value is detected, the predicted particle outflow can be obtained.

[0083] Preferably, the feature extraction unit of this embodiment accurately extracts key features closely related to the particle outflow from the preprocessed pressure data, and these features can comprehensively reflect the fluctuation and overall trend of the pressure data in different time periods; the relationship establishment unit uses historical data to train the model, and successfully fits the curve relationship between the particle outflow and the pressure characteristic value by real-time monitoring the changes in the particle outflow and the characteristic value of the pressure sensor. The model can reflect the impact of pressure changes on the particle outflow in real time, thereby improving the accuracy and real-time performance of the prediction; the verification and optimization unit cross-validates the trained model, objectively evaluates the performance of the relationship model between pressure and particle outflow, and optimizes the model's hyperparameters through preset test data, thereby further improving the model's prediction accuracy and generalization ability. When a change in the pressure sensor value is detected, the predicted particle outflow can be quickly obtained, thereby improving the system's response speed and prediction accuracy.

[0084] In summary, this embodiment reduces the complexity of the data through feature extraction, making it easier for the model to capture the relationship between pressure and particle outflow, improving the efficiency of model training, and reducing the consumption of computing resources; by establishing an accurate relationship model, effective prediction of particle outflow is achieved, providing a scientific basis for production control and decision-making in related industries, and the real-time monitoring function of the model enables the system to respond to pressure changes in a timely manner and reduce risks in the production process; through verification and optimization, the stability and reliability of the model are ensured, the risks of false alarms and missed alarms are reduced, and the practicality and applicability of the system are improved, so that it can be applied in a wider range of production environments.

[0085] Furthermore, in the novel side-blowing feeding intelligent control system of this embodiment, the data acquisition module transmits parameters such as the spray gun gas flow rate and the particle flow rate to the intelligent prediction module, and the numerical calculation module predicts the smelting situation in real time based on the parameters, and then adjusts the flow rate of each particle and air in real time according to the calculation situation to achieve efficient smelting; wherein the intelligent prediction module specifically includes:

[0086] The three-phase flow prediction submodule is responsible for predicting the gas-liquid-solid three-phase flow process in the side-blown furnace; determining the volume occupied by the liquid and gas phases in each grid, identifying the gas-liquid interface; and tracking the solid phase separately;

[0087] Among them, in the process of predicting the gas-liquid-solid three-phase flow in the side-blown furnace, the algorithm embedded in it introduces the porosity ε based on the Navier-Stokes equation because of the influence of the solid phase. f Based on this, the continuity and momentum equations of the continuous phase can be expressed as:

[0088]

[0089] Where t is time; ρ f is the fluid density; u f is the fluid velocity; P is the fluid pressure; g is the gravitational acceleration; F pf is the force exerted by the particle on the fluid;

[0090] In the Lagrangian framework, the solid phase is tracked separately using Newton's second law. Specifically, considering the translational and rotational motions of the particle i, the corresponding equation is expressed as:

[0091]

[0092] Where m, u, and ω represent the mass, translational velocity, and angular velocity of particle i, respectively; I represents the moment of inertia of the particle, which can be expressed by m p d p 2 / 10 means; F col and M c represents the collision force and torque due to particle-particle / wall interactions; F pf and F BI represents the interaction force of the fluid on the particle and the surface tension of the bubble.

[0093] The interface force submodule is responsible for calculating the resistance between particles and fluid (F d ), lift (F lif ), pressure gradient force (F p ), viscous stress (F ▽·τ ), virtual mass force (F vm ) and Basset force (F B );

[0094] The interface particle behavior submodule is responsible for discerning the particle behavior at the gas-liquid interface using the liquid volume fraction through the VOF method, which ranges from 0 to 1, indicating that the thickness is finite and the particles crossing the gas-liquid interface must overcome the surface tension of the liquid film;

[0095] Among them, in actual situations, particles passing through the gas-liquid interface must overcome the surface tension of the liquid film. Therefore, the bubble surface tension has been incorporated into the numerical algorithm, and the formula is:

[0096]

[0097] Because its basic form is consistent with the CSF model, this force is called particle surface tension; when the particles have enough kinetic energy to overcome the bubble surface tension, they will eliminate the liquid film and break through the gas-liquid interface; on the contrary, if they lack this energy, they will be decelerated by the action of the bubble surface tension and eventually slide along the bubble surface.

[0098] Preferably, the three-phase flow prediction submodule of this embodiment predicts the gas-liquid-solid three-phase flow process in the side-blown furnace, determines the volume occupied by the liquid phase and the gas phase in each grid, and identifies the gas-liquid interface; tracks the movement of the solid phase separately, considers the influence of the solid phase on the flow, and introduces the porosity ε f The Navier-Stokes equations are modified to describe the continuity and momentum equations of the continuous phase. The interface force submodule calculates various interface forces between particles and fluids, including drag, lift, pressure gradient force, viscous stress, virtual mass force and Basset force. The interface particle behavior submodule uses the VOF method to identify the particle behavior at the gas-liquid interface, and characterizes the finite thickness of the gas-liquid interface by the liquid volume fraction. The influence of the surface tension of the liquid film on the particles passing through the gas-liquid interface is considered, and the numerical algorithm of the bubble surface tension is incorporated. The data acquisition module passes parameters such as the gun gas flow rate and particle flow rate to the intelligent prediction module, and the smelting situation is predicted in real time based on the parameters. Then, the flow rate of each particle and air is adjusted in real time according to the calculation situation to achieve efficient smelting.

[0099] In summary, this embodiment improves the ability to predict multiphase flow in complex industrial processes, helps to optimize process parameters and improve production efficiency; provides detailed flow information, and provides data support for equipment design, fault diagnosis and performance optimization; improves the understanding of the interaction mechanism between particles and fluids, helps to accurately predict the movement trajectory of particles in the fluid, and provides a theoretical basis for optimizing particle separation, mixing and transportation processes; improves the ability to understand the behavior of particles at the gas-liquid interface, and helps to optimize the bubble generation, rupture and merging processes; provides an important means for understanding and controlling chemical reactions, mass transfer and energy conversion at the gas-liquid interface.

[0100] Furthermore, in the novel side-blowing feeding intelligent control system of this embodiment, the three-phase flow prediction submodule specifically includes:

[0101] The grid construction unit is responsible for selecting the hexahedral structured grid as the grid type, performing grid encryption in the area near the gas-liquid interface, and adjusting the grid size according to the liquid phase volume fraction gradient to ensure that the detailed changes of the interface are captured;

[0102] The mesh verification unit is responsible for verifying the independence of the constructed mesh. By comparing the calculation results under different mesh densities, the appropriate mesh size is determined, and the mesh quality is checked to ensure that the orthogonal quality of the mesh remains above 0.5.

[0103] The boundary layer unit is responsible for setting the boundary layer grid near the wall and where the particles are blown in, setting the appropriate number of layers and thickness of the grid, and performing verification calculations to obtain the optimal grid.

[0104] Preferably, the grid construction unit of this embodiment selects a hexahedral structured grid, which has high computational efficiency and accuracy in calculations, especially when dealing with complex flows; by encrypting the grid, subtle changes at the gas-liquid interface can be captured, and the grid size can be adjusted according to the liquid phase volume fraction gradient to ensure sufficient grid resolution in areas where the interface changes drastically, thereby more accurately simulating flow phenomena; the grid verification unit determines the appropriate grid size by comparing the calculation structure under different grid densities, so that the calculation results no longer change significantly with the increase of grid density; ensuring that the orthogonal quality of the grid is maintained above 0.5 helps to reduce numerical errors and improve calculation stability; the boundary layer unit sets a boundary layer network near the wall and the particle blowing point, which can capture flow details, and through verification calculations, the optimal number and thickness of boundary layer grid layers can be determined, thereby further improving the accuracy of the simulation.

[0105] In summary, this embodiment improves the accuracy of simulation at the gas-liquid interface, optimizes the use of computing resources, and reduces computing costs by encrypting the grid only in areas where high resolution is required; ensures the reliability and accuracy of the simulation results, avoids unstable calculations or inaccurate results due to poor grid quality; accurately simulates wall effects and the interaction between particles and fluids, optimizes the setting of boundary layer grids, and improves the efficiency and accuracy of the simulation.

[0106] Furthermore, in the novel side-blowing feeding intelligent control system of this embodiment, the three-phase flow prediction submodule specifically includes:

[0107] Volume calculation unit, responsible for introducing the liquid volume fraction and calculating the gas volume and liquid volume in each grid cell;

[0108] The gas volume V in each grid cell is gas and the liquid volume V liquid It can be expressed as:

[0109] V gas =V cell ε f (1-α) (6)

[0110] V liquid =V cell ε f α (7)

[0111] Among them, V cell is the grid volume, α is the liquid volume fraction;

[0112] The phase interface tracking unit is responsible for solving the control equation of the liquid volume fraction to track the phase interface, and obtains the density and dynamic viscosity in a specific unit by linear interpolation of the liquid volume fraction;

[0113] Among them, the volume fraction (VOF) method is used to track the phase interface by solving the governing equation of the liquid volume fraction α, and its formula is:

[0114]

[0115] In the formula, u r is the relative velocity, called the compression velocity; the third term of formula (8) is the artificial interface compression term, which is introduced to avoid unreasonable numerical dissipation; in addition, the WLIC VOF scheme is used to reconstruct the gas-liquid interface; based on the VOF method, the density and dynamic viscosity in a specific unit are obtained by linear interpolation of α:

[0116] ρ f =αρ l +(1-α)ρ g (9)

[0117] μ f =αμ l +(1-α)μ g (10)

[0118] Where ρ and μ are density and dynamic viscosity respectively; subscripts f, l, and g represent fluid, liquid, and gas respectively;

[0119] The tension calculation unit is responsible for calculating the surface tension of the gas-liquid interface, introducing a smoothing function to solve the discontinuity of the interface, and calculating the local curvature of the interface;

[0120] Among them, F in formula (2) σ It represents the surface tension of the gas-liquid interface calculated according to the continuous surface force (CSF) model, and its formula is:

[0121]

[0122] Where σ represents the surface tension coefficient, Φ s is a smoothing function introduced to solve the interface discontinuity, and K is the local curvature of the interface, which is calculated as follows:

[0123]

[0124] The turbulence model used has the following form:

[0125]

[0126] G k is the turbulent kinetic energy generated by the mean velocity gradient, G b is generated by the turbulent kinetic energy caused by buoyancy, Y M is the compressible turbulent fluctuation expansion of the overall dissipation rate.

[0127] Preferably, the volume calculation unit of this embodiment calculates the gas volume and liquid volume in each grid unit by a given formula, which depends on the grid volume and liquid volume fraction; the phase interface tracking unit adopts the volume fraction (VOF) method to track the phase interface, solves the control equation of the liquid volume fraction α, and introduces an artificial interface compression term to avoid unreasonable numerical dissipation; the WLIC VOF scheme is used to reconstruct the gas-liquid interface, and the density and dynamic viscosity within a specific unit are obtained based on the linear interpolation of α; the tension calculation unit calculates the surface tension of the gas-liquid interface, introduces a smoothing function to solve the discontinuity of the interface, and calculates the local curvature of the interface; the turbulence model provides equations for describing the turbulent kinetic energy and the turbulent dissipation rate, including the generation of turbulent kinetic energy caused by the average velocity gradient, the expansion of compressible turbulent fluctuations for the overall dissipation rate, and other terms.

[0128] In summary, this embodiment provides an accurate description of the distribution of fluid in multiphase flow, which helps to understand the dynamic behavior of fluid under different conditions and provides basic data for density, viscosity and surface tension, etc.; it realizes the shape and dynamic tracking of the gas-liquid interface position, improves the accuracy and stability of interface tracking, and provides reliable interface information for multiphase flow simulation; makes the calculation of density and dynamic viscosity more accurate, which helps the accuracy of simulation results; accurately describes the interaction force between the gas-liquid interface, solves the problem of interface discontinuity, improves the accuracy of simulation, and the calculation of local curvature helps to understand the shape and evolution of the interface; it is of great significance for the simulation of physical phenomena in multiphase flow; describes the dynamic behavior of fluid in turbulent state, improves the simulation capability of complex flow phenomena, makes the simulation results closer to the actual situation, and improves the accuracy and credibility of simulation.

[0129] Furthermore, in the novel side-blowing feeding intelligent control system of this embodiment, the interface force submodule specifically includes:

[0130] The interface force calculation module is responsible for calculating the resistance between particles and fluid (F d ), lift (F lif ), pressure gradient force (F p ), viscous stress Virtual mass force (F vm ) and Basset force (F B );

[0131] Among them, for particle i, F pfi The formula is:

[0132]

[0133] The pressure gradient force, viscous stress, and virtual mass force are expressed as follows:

[0134]

[0135] The resistance prediction module is responsible for selecting and establishing a resistance model, and using the established resistance model to calculate and predict the resistance between particles and fluid;

[0136] Among them, drag is the most important interfacial force affecting particle motion. The selection of drag model takes into account two key factors: applicability to high solid volume fraction and adaptability to particle Reynolds number (R ep ) range, in this module, the following resistance model is used, which is specifically expressed as:

[0137]

[0138] Among them, V P represents the particle volume;

[0139] The lift calculation module is responsible for calculating the Saffman lift generated by fluid shear and the Magnus lift generated by particle rotation;

[0140] The formula for lift is as follows:

[0141]

[0142] Preferably, the interface force calculation module of this embodiment accurately predicts the resistance encountered by particles when moving in the fluid, considers the effects of fluid shear and particle rotation on lift, and makes the simulation closer to the actual situation; considers the effect of pressure gradient in the fluid on particles, which helps to understand the behavior of particles in complex flow fields; the resistance prediction module selects a suitable resistance model according to the high solid volume fraction and particle Reynolds number range to ensure the accuracy of the simulation results, and uses the established resistance model to accurately calculate the resistance between particles and fluid, providing key data for particle motion simulation; the victory calculation module considers the effect of fluid shear on particle lift, making the simulation results closer to the actual situation; considers the effect of particle rotation on lift, and improves the accuracy of the simulation.

[0143] In summary, the interface force calculation module of this embodiment provides an important physical basis for the simulation of the movement of particles in the fluid by accurately calculating the various interaction forces between the particles and the fluid, which helps to optimize the industrial process; the resistance prediction module provides physical parameters for the simulation of the movement of particles in the fluid by selecting a suitable resistance model and accurately calculating the resistance, which helps to optimize the industrial process and improve production efficiency; the lift calculation module provides a more comprehensive physical description for the simulation of the movement of particles in the fluid by accurately calculating the Saffman lift and Magnus lift, which helps to understand the behavior of particles in complex flow fields and optimize industrial processes such as particle suspension, deposition and separation.

[0144] Furthermore, in the novel side-blowing feeding intelligent control system of this embodiment, the particle-particle / wall collision in the interface particle behavior submodule is simulated by a perfect DEM model based on the soft ball collision model, and the interaction force F between the collision pairs is cot It can be divided into normal component and tangential component, and the formula is as follows:

[0145]

[0146] Where k and η represent the spring constant and damping coefficient respectively; n and t represent the unit vectors of the collision pair along the normal and tangential directions respectively; δ t,ij and δ n,ij are the tangential and normal displacements of the collision pair, respectively; the nonlinear Hertz-Mindlin contact type is used to evaluate the normal force and tangential force; the spring constant and damping coefficient of the collision pair are evaluated based on the formulas in Table 1.

[0147] Table 1 Detailed expressions for evaluating spring constants and damping coefficients

[0148]

[0149] The above equations use the PIMPLE algorithm to solve the continuity and momentum equations of fluid flow; in order to close the discretized equations, the nozzles on both sides are set as velocity inlet boundary conditions, the outlet is selected as pressure boundary conditions, and the side wall adopts no-slip boundary conditions.

[0150] Preferably, this embodiment uses a perfect DEM model based on a soft ball collision model to simulate particle-particle / wall collisions; the interaction force between the collision pairs is subdivided into normal components and tangential components, and is calculated using formulas respectively; the spring constant and the damping coefficient are evaluated based on a specific formula, and the nonlinear Hertz-Mindlin contact type is used to evaluate the normal force and the tangential force; the PIMPLE algorithm is used to solve the continuity and momentum equations of the fluid flow, the spray gun ports on both sides are set as velocity inlet boundary conditions, the outlet selects the pressure boundary condition, and the side wall adopts the no-slip boundary condition; the various modules work together to realize the intelligent control of the side-blowing feeding process, and can monitor and adjust the feeding parameters in real time to ensure the stability and accuracy of the feeding, improve production efficiency and product quality, and reduce energy consumption and production costs.

[0151] In summary, this embodiment improves the accuracy and reliability of particle behavior simulation, can more realistically reflect the dynamic behavior of particles in the side-blowing feeding process, provides accurate data support for the side-blowing feeding process, and helps to reduce energy consumption, improve production efficiency and product quality; the PIMPLE algorithm combines the advantages of the SIMPLE algorithm and the PISO algorithm, can more efficiently solve fluid flow problems, improve calculation speed and accuracy, and reasonable boundary condition settings can ensure the accuracy of fluid flow simulation, providing strong support for the optimal design of the side-blowing feeding system; it has promoted the intelligent development of side-blowing feeding technology, improved the level of industrial automation, promoted the sustainable development of related industries, and contributed to economic growth and social progress.

[0152] like Figure 4 As shown, this embodiment also provides an embodiment of a novel side-blowing feeding intelligent control method. In this embodiment, the novel side-blowing feeding intelligent control method is applied to the novel side-blowing feeding system in the above embodiment. The novel side-blowing feeding intelligent control method includes:

[0153] Step S1: collecting data such as particles injected into the molten pool and the air flow rate of the spray gun in real time, and transmitting the collected data to the intelligent prediction module;

[0154] Step S2: Based on the collected data such as the particles injected into the molten pool and the air flow rate of the spray gun, the appropriate feed amount of materials, coal powder, additives and air volume are given through numerical calculation;

[0155] Step S3: Based on the calculated data of material, coal powder, additive feed amount and air volume, the compressor and each silo discharge valve are controlled to achieve accurate air delivery and feed.

[0156] Preferably, step S1 of this embodiment can instantly obtain key parameters such as the particles injected into the molten pool and the air flow rate of the spray gun, ensure the timeliness and accuracy of the data, and quickly transmit the collected data to the intelligent prediction module; step S2 uses the collected data to determine the appropriate material, coal powder, additive feed amount and air volume through numerical calculation, to ensure that the material ratio and air volume in the production process are optimal, thereby improving production efficiency and product quality; step S3 accurately controls the compressor and each silo discharge valve according to the calculated data, to ensure that the material and air supply match the production demand, and to achieve precise control.

[0157] In summary, this embodiment realizes real-time monitoring and feedback, provides accurate data support, and helps to improve the controllability and efficiency of the entire production process; through intelligent calculation, it can achieve accurate batching, reduce resource waste, improve production efficiency and product quality, and reduce production costs; it realizes automation and intelligent control, reduces errors in human operation, improves production stability and controllability, and at the same time, accurate control helps to reduce energy consumption and improve resource utilization efficiency.

[0158] like Figure 5 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 9 includes a processor 91 and a memory 92 coupled to the processor 91.

[0159] The memory 92 stores program instructions for implementing the new side-blowing feeding intelligent control system of any of the above embodiments.

[0160] The processor 91 is used to execute the program instructions stored in the memory 92 to implement the layout of the new side-blowing feeding intelligent control system.

[0161] The processor 91 may also be referred to as a CPU (Central Processing Unit). The processor 91 may be an integrated circuit chip having the ability to process signals. The processor 91 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0162] Further, Figure 6 The schematic diagram of the structure of the storage medium of an embodiment of the present application is that the storage medium 10 of the embodiment of the present application stores program instructions 101 that can implement all the above methods, wherein the program instructions 101 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0163] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0164] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present invention.

[0165] The specific implementation methods of the invention are described in detail above, but they are only examples, and the invention is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention, therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the invention should be included in the scope of the invention.

Claims

1. A new side-blowing feeding device, characterized in that: The novel side-blowing feeding device comprises a compressor, a safety valve, a pressure sensor, a mechanical sealing device, an electric control valve, an additive storage tank, a coal powder storage tank and a raw material storage tank; Among them, there is a compressor on one side of the pipeline, and multiple safety valves are installed on the pipeline; additives, coal powder, and mineral powder raw materials are stored in separate additive storage tanks, coal powder storage tanks and raw material storage tanks respectively. Multiple pressure sensors are installed on the wall of each storage tank, and the bottom of each storage tank is connected to the pipeline through an electric control valve; there is a mechanical sealing device on the top of each storage tank, and a pipeline is opened on one side of the top to connect to the compressor, and a safety valve is provided.

2. A new type of side-blowing feeding intelligent control system, which is applied to the new type of side-blowing feeding device as claimed in claim 1, characterized in that: The novel side-blowing feeding intelligent control system comprises: The data acquisition module is responsible for collecting the data of particles injected into the molten pool and the air flow rate of the spray gun in real time, and transmitting the collected data to the intelligent prediction module; The intelligent prediction module is responsible for calculating the feed amount of materials, coal powder, additives and air volume based on the parameters collected by the data acquisition module, and giving instructions to the operation module; The operation module is responsible for executing the instructions given by the intelligent prediction module and controlling the compressor and the discharge valves of each silo to achieve precise air delivery and material feeding.

3. The new side-blowing feeding intelligent control system according to claim 2 is characterized in that: Data acquisition module, including: The pressure collection submodule, which consists of multiple pressure sensors installed on the inner wall of the storage tank, is responsible for collecting the pressure of particles in the storage tank on the inner wall of the storage tank and preprocessing the collected data; The numerical calculation submodule is responsible for fusing the data collected by multiple sensors, processing the pressure data, establishing a relationship model between pressure and particle outflow, and obtaining the particle outflow based on the data collected by the sensors; if the fused pressure is less than the preset threshold, an alarm instruction is generated to indicate that there is insufficient particle in the storage tank; The particle quantity output submodule is responsible for detecting whether an alarm instruction is generated. If an alarm instruction is detected, the alarm instruction is sent to the data center to indicate that there are insufficient particles in the storage tank. If no alarm instruction is detected, the particle outflow estimated by the relationship model between pressure and particle outflow is output to the intelligent prediction module.

4. The new side-blowing feeding intelligent control system according to claim 3 is characterized in that: Numerical calculation submodule, including: The feature extraction unit is responsible for extracting features related to particle outflow from the preprocessed pressure data, including the average, maximum, minimum and standard deviation of the pressure; The relationship building unit is responsible for training the model using the preprocessed data and the historical data of the particle outflow and the characteristic value of the pressure sensor, and obtaining the fitting curve of the particle outflow and the characteristic value of the pressure by monitoring the changes of the particle outflow and the characteristic value of the pressure sensor in real time; The verification and optimization unit is responsible for cross-validating the trained model, evaluating the performance of the relationship model between pressure and particle outflow, and optimizing the model's hyperparameters through preset test data; when a change in the pressure sensor value is detected, the predicted particle outflow is obtained.

5. The new side-blowing feeding intelligent control system according to claim 2 is characterized in that: Intelligent prediction module, including: The three-phase flow prediction submodule is responsible for predicting the gas-liquid-solid three-phase flow process in the side-blown furnace; determining the volume occupied by the liquid and gas phases in each grid, identifying the gas-liquid interface; and tracking the solid phase separately; Interface force module, responsible for calculating the resistance F between particles and fluid d , lift F lif , pressure gradient force F p , viscous stress F ▽·τ , virtual mass force F vm and Basset force F B ; The interface particle behavior submodule is responsible for identifying the particle behavior at the gas-liquid interface using the liquid volume fraction through the VOF method, which ranges from 0 to 1, indicating a finite thickness and that particles passing through the gas-liquid interface must overcome the surface tension of the liquid film.

6. The new side-blowing feeding intelligent control system according to claim 5 is characterized in that: The grid division in the three-phase flow prediction submodule includes: The grid construction unit is responsible for selecting the hexahedral structured grid as the grid type, performing grid encryption in the area near the gas-liquid interface, and adjusting the grid size according to the liquid phase volume fraction gradient; The mesh verification unit is responsible for verifying the independence of the constructed mesh, determining the mesh size by comparing the calculation results under different mesh densities, and performing mesh quality checks; The boundary layer unit is responsible for setting the boundary layer grid near the wall and where the particles are blown in, setting the appropriate number of layers and thickness of the grid, and performing verification calculations to obtain the optimal grid.

7. The new side-blowing feeding intelligent control system according to claim 5 is characterized in that: Identification of gas-liquid interface in the three-phase flow prediction submodule includes: Volume calculation unit, responsible for introducing the liquid volume fraction and calculating the gas volume and liquid volume in each grid cell; The phase interface tracking unit is responsible for solving the control equation of the liquid volume fraction to track the phase interface, and obtains the density and dynamic viscosity in a specific unit by linear interpolation of the liquid volume fraction; The tension calculation unit is responsible for calculating the surface tension of the gas-liquid interface, introducing a smoothing function to solve the discontinuity of the interface, and calculating the local curvature of the interface.

8. The new side-blowing feeding intelligent control system according to claim 5 is characterized in that: Interface force submodule, including: Interface force calculation module, responsible for calculating the resistance F between particles and fluid d , lift F lif , pressure gradient force F p , viscous stress F ▽·τ , virtual mass force F vm and Basset force F B ; The resistance prediction module is responsible for selecting and establishing a resistance model, and using the established resistance model to calculate and predict the resistance between particles and fluid; The lift calculation module is responsible for calculating the Saffman lift generated by fluid shear and the Magnus lift generated by particle rotation.

9. The novel side-blowing feeding intelligent control system according to claim 5 is characterized in that: Interface particle behavior submodule, including: Particle-particle / wall collisions are simulated using a complete DEM model based on the soft sphere collision model. The interaction force F between the collision pairs is cot It is divided into normal component and tangential component, and the formula is as follows: Where k and η represent the spring constant and damping coefficient respectively; n and t represent the unit vectors of the collision pair along the normal and tangential directions respectively; δ t,ij and δ n,ij are the tangential and normal displacements of the colliding pair, respectively; the nonlinear Hertz-Mindlin contact type is used to evaluate the normal and tangential forces.

10. A novel side-blowing feeding intelligent control method, which is applied to the novel side-blowing feeding system as claimed in any one of claims 1 to 9, characterized in that: The novel side-blowing feeding intelligent control method comprises: Collect the data of particles injected into the molten pool and the air flow rate of the spray gun in real time, and transmit the collected data to the intelligent prediction module; Based on the collected data of particle and gun gas flow injected into the molten pool, the material, coal powder, additive feed amount and air amount are given by numerical calculation; Based on the calculated data on material, coal powder, additive feed and air volume, the compressor and each silo discharge valve are controlled to achieve precise air delivery and feeding.

Images