A method, system, control terminal and storage medium for efficient slag splash control in a top-and-bottom combined blowing converter.

Abstract

This invention provides a method, system, control terminal, and storage medium for efficient slag splashing control in a top-and-bottom combined blowing converter, belonging to the field of steelmaking technology. It collects current heat information and performs material balance calculations; blows the converter, and performs alloying tapping after blowing; and detects the LIBS value of slag composition content. After tapping, the slag weight is detected and calculated; after slag dumping and adjustment, slag splashing is performed according to a preset slag splashing lance position control height value; the slag splashing lance position control height value, slag splashing lance position adjustment value, and slag splashing lance position adjustment value are input into a feedforward neural network for calculation, obtaining the slag splashing lance position height control network calculation value on the current heat time axis. This invention achieves scientific control of slag retention and precise control of slag splashing lance position, improving the slag splashing protection effect and increasing converter operating rate.

Description

Technical Field

[0001] This invention belongs to the field of steelmaking technology, specifically relating to a method, system, control terminal, and storage medium for efficient slag splashing control in a top-and-bottom combined blowing converter. Background Technology

[0002] Slag splashing technology is a technique that uses a high-speed nitrogen jet to impact the high-melting-point slag remaining in the converter after tapping, causing it to splash up and adhere to the converter lining surface to form a protective layer, thereby improving the lining's lifespan. After tapping, the final slag, with MgO content reaching saturation or supersaturation, is cooled and solidified by high-pressure nitrogen jets from an oxygen lance, forming a high-melting-point molten slag layer on the lining surface that adheres well to the lining. The splashed slag layer exhibits good corrosion resistance, inhibits oxidation and decarburization of the lining bricks, and reduces the erosion and scouring of the lining bricks by the high-temperature slag, thus protecting the lining bricks, reducing refractory material wear, decreasing the consumption of patching materials, reducing worker workload, increasing lining lifespan, improving converter operating rates, and lowering production costs.

[0003] High-efficiency slag splashing for furnace protection involves the final slag composition at the blowing endpoint (such as basicity, MgO content, and FeO content), appropriate slag quantity, final slag temperature, nitrogen pressure and flow rate for slag splashing, oxygen lance nozzle process parameters and oxygen lance position control, bottom blowing process parameters for combined blowing converters, slag splashing time, steel grade endpoint control targets, and related process equipment, furnace charge structure, technical operation level, and management requirements. Converters mostly use magnesia-carbon bricks as furnace linings, and an important measure to reduce furnace lining erosion is to increase the MgO content in the slag.

[0004] When MgO in the slag reaches saturation, the amount of MgO dissolved in the furnace lining decreases, thereby increasing the furnace lining life. Thus, the MgO content in the slag is related to the slag basicity; a final slag basicity (CaO / SiO2%) of around 3 and an MgO content of around 8% are sufficient to ensure adequate MgO content.

[0005] The MgO content in converter slag splashing is generally controlled between 8% and 14%. The FeO content in the slag has a significant impact on furnace lining erosion and slag splashing effect. The mineral composition of FeO in the slag is mostly various low-melting-point ferrates, with melting points far below the tapping temperature. Higher FeO content results in more ferrates, better slag fluidity, increased erosion of the furnace lining, and less adhesion to the lining. Conversely, too low FeO content makes converter slag formation and P / S removal difficult. Therefore, strict control of the FeO content in the slag is essential. Appropriate slag viscosity is beneficial for slag splashing and furnace protection. High slag viscosity makes it difficult to splash, leading to a rapid decrease in splashed slag volume, requiring more jet impact energy to maintain the splashed slag volume. Furthermore, thick slag has poor adhesion to the furnace lining; low viscosity results in thinner slag, making splashing and coverage easier, but the covering layer is thinner. Slag dripping during furnace shaking requires slag addition to adjust the viscosity and ensure appropriate slag viscosity.

[0006] In existing technologies, reasonable slag quantity control depends on the splashability of the slag, the slag splashing requirements of the furnace condition, the slag splashing time requirements, and the limitations of slag splashing costs. According to the slag splashing kinetics study of the molten pool, slag splashing in the upper part of the converter mainly relies on nitrogen gas to splash the slag. Insufficient slag quantity results in a thin slag layer, allowing the gas flow to easily penetrate the slag layer, weakening the emulsification and abrasion effects of the gas flow on the slag layer, reducing the number of liquid slag droplets carried in the reflected gas flow, which is detrimental to slag splashing in the upper part of the converter. Excessive slag retention in the converter enhances the effect of upper-part slag splashing, often causing slag adhesion at the furnace mouth and furnace deformation. Regarding the thickness and uniformity of the splashed slag layer, insufficient slag quantity results in a thin, uneven upper layer, or even no slag splashing at all; moreover, the slag splashing time increases with the increase in slag quantity. However, insufficient slag quantity reduces the efficiency and quality of slag splashing; of course, excessive slag retention increases the amount of slag conditioning agent used, raising the cost of slag splashing. Summary of the Invention

[0007] This invention provides a method for controlling slag splashing in a top-and-bottom combined blowing converter. The method achieves scientific control of the amount of slag left and precise control of the slag splashing lance position, thereby improving the slag splashing protection effect and increasing the converter operating rate.

[0008] The methods include:

[0009] S101: Collect current furnace information and perform material balance calculations;

[0010] S102: The converter is blown, and after the blowing is completed, alloying and tapping operations are carried out;

[0011] S103: During the tapping process, LIBS technology is used to detect the slag in the converter and obtain the LIBS detection value of the slag composition content of the current heat.

[0012] S104: The slag composition content detected by LIBS and the theoretical calculation value are calculated using a symmetric neural network to obtain the network-calculated value W of the slag composition content for the current furnace. i--网络 ;

[0013] S105: After tapping, the weight of the slag is measured;

[0014] S106: Calculate the weight information of the slag;

[0015] S107: Determine whether the slag dumping conditions are met based on the weight information of the current furnace batch, and whether to add slag conditioner for slag conditioning and quality improvement;

[0016] S108: After slag dumping and slag adjustment, control the height value H according to the preset slag splashing gun position. t-设定 Splashing;

[0017] S109: Set the slag splashing lance position control height value H of the current furnace model. t-设定 Adjustment value H of splash lance position control based on oxygen lance vibration detection t-振动 Adjustment value H of slag splashing gun position based on furnace opening visualization detection t-可视化 And the slag gun position adjustment value H based on audio detection t-音频 The input is fed into a feedforward neural network for calculation, and the calculated value H of the slag splashing lance position height control network on the time axis of the current furnace is obtained. t-网络 .

[0018] It should be further noted that step S109 also includes: real-time detection of the vibration state of the oxygen lance by installing a force sensor on the wire rope or pulley suspending the oxygen lance, and obtaining the adjustment value H of the slag splashing lance position control height. t-振动 .

[0019] It should be further noted that step S109 also includes: detecting the height of the oxygen lance at the furnace opening by installing a video acquisition device at the furnace opening, and adjusting the oxygen lance height to obtain the slag splashing lance position adjustment value H. t-可视化 .

[0020] It should be further noted that step S109 also includes: collecting, processing, and analyzing the noise inside the converter during slag splashing, converting it into an audio signal, and obtaining the slag splashing furnace protection gun position control height based on the magnitude of the audio signal;

[0021] Based on the audio signal, the height of the splash gun position is adjusted in real time to obtain the splash gun position adjustment value H based on audio detection. t-音频 .

[0022] It should be further noted that in step S101, the furnace information includes: molten iron conditions, scrap steel conditions, slag-forming auxiliary materials, coolant, slag-forming agent conditions, converter bottom blowing process parameters, converter lining life, and endpoint data after blowing, as well as converter blowing oxygen consumption.

[0023] The theoretical calculated value G of the final slag weight for the current furnace is determined based on the furnace information. 渣-理论 And the theoretical calculated value W of the component content in the final residue. i--理论 .

[0024] It should be further noted that in step S105, a camera is used to photograph the slag inside the converter.

[0025] The industrial control computer acquires images of the slag captured in the image and identifies the area of ​​the slag inside the furnace.

[0026] Based on the converter's location, tilting angle, and slag area within the furnace, the volume and weight are calculated according to the converter's structure and depth, yielding a visually detectable value G of the slag weight for the current furnace cycle. 渣-检测 .

[0027] It should be further noted that the slag weight information in step S106 is the average slag weight G of the current furnace batch. 渣-检测 ;

[0028] The average weight of slag in the current furnace (G) 渣-检测 Calculated as follows:

[0029]

[0030] G 渣-理论 This is the theoretically calculated value of the final slag weight for the current furnace batch;

[0031] G 渣-检测 To visualize the detection values.

[0032] This application also provides a high-efficiency slag splashing control system for a top-and-bottom combined blowing converter. The system includes: an information acquisition module, a blowing and tapping control module, a LIBS slag detection module, a neural network calculation module, a slag weight detection module, a slag weight calculation module, a judgment module, a slag splashing control module, and a slag splashing lance position height control module.

[0033] The information acquisition module is used to collect information on the current furnace batch and perform material balance calculations;

[0034] The blowing and tapping control module is used to blow the converter and perform alloying tapping after the blowing is completed.

[0035] The LIBS slag detection module is used during the steel tapping process to detect the slag in the converter using LIBS technology, and obtain the LIBS detection value of the slag composition content of the current heat.

[0036] The neural network calculation module is used to perform symmetrically connected neural network calculations on the slag composition content detected by LIBS and the theoretical calculation values ​​to obtain the network-calculated value W of the slag composition content for the current furnace. i--网络 ;

[0037] The slag weight detection module is used to detect the weight of slag after steel tapping.

[0038] The slag weight calculation module is used to calculate the weight information of the slag.

[0039] The judgment module is used to determine whether the slag dumping conditions are met and whether slag conditioners need to be added for slag conditioning and quality improvement based on the weight information of the current furnace.

[0040] The slag splashing control module is used to control the height value H according to the preset slag splashing gun position after slag dumping and slag adjustment. t-设定 Splashing;

[0041] The slag splashing lance position height control module is used to control the slag splashing lance position height value H set in the current furnace model. t-设定 Adjustment value H of splash lance position control based on oxygen lance vibration detection t-振动 Adjustment value H of slag splashing gun position based on furnace opening visualization detection t-可视化 And the slag gun position adjustment value H based on audio detection t-音频 The input is fed into a feedforward neural network for calculation, and the calculated value H of the slag splashing lance position height control network on the time axis of the current furnace is obtained. t-网络 .

[0042] According to another embodiment of this application, a control terminal is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of a method for efficient slag splashing control in a top-and-bottom combined blowing converter.

[0043] According to another embodiment of this application, a storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the efficient slag splashing control method for the top and bottom combined blowing converter.

[0044] As can be seen from the above technical solutions, the present invention has the following advantages:

[0045] The efficient slag splashing control method for top-and-bottom blown converters provided by this invention can accurately grasp the relationship between raw material input and product output in the current heat, which helps optimize the raw material ratio in the smelting process, reduce waste, and improve resource utilization efficiency. Based on blowing and alloying tapping operations, combined with accurate material balance data, it can ensure that the composition and temperature of molten steel reach the predetermined standards during tapping, improving the quality stability of molten steel. Using LIBS technology to detect slag composition in real time, combined with symmetric connection neural network calculations, it can quickly and accurately obtain real-time data on slag composition and compare it with theoretical values, promptly identifying deviations and providing data support for subsequent slag treatment. Furthermore, by detecting slag weight and determining whether slag dumping conditions are met, and whether slag conditioners need to be added, intelligent slag management is achieved. This helps reduce the negative impact of slag on the smelting process and improve smelting efficiency. By integrating data from multiple sensors (such as the slag splashing lance position control height setpoint, oxygen lance vibration detection value, furnace mouth visual detection value, and audio detection value) and using a feedforward neural network for calculation, precise control of the slag splashing lance position height is achieved. The entire process of this application, from material balance, alloying and tapping, slag detection to slag splash control, incorporates advanced detection technologies and intelligent algorithms, which significantly improves the automation and intelligence level of the smelting process and reduces errors and uncertainties caused by human operation. Attached Figure Description

[0046] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 Flowchart of an embodiment of a method for efficient slag splash control in a top-and-bottom combined blowing converter;

[0048] Figure 2 The graph shows a specific embodiment of the method.

[0049] Figure 3 This is a graph representing another specific embodiment of the method. Detailed Implementation

[0050] The efficient slag splashing control method for top and bottom blown converters provided in this application is based on a reasonable slag quantity and final slag physicochemical state. It takes into account the changes and differences in the raw materials, hot metal and scrap steel conditions, smelting process, steel grade smelting requirements, process equipment and parameters, operator skill level, furnace life, as well as the slag splashing and furnace protection requirements for different furnaces at different furnace ages and the degree of erosion of various parts of the furnace lining refractory bricks. The method systematically and comprehensively considers all factors to explore the optimal slag splashing effect and efficiency under the conditions of the furnace, so as to achieve the purpose of precise, efficient and economical slag splashing.

[0051] Various embodiments of this disclosure will now be described more fully. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0052] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0053] In various embodiments of this disclosure, the expression "or" or "at least one of A and / or B" includes any combination or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A and / or B" may include A, may include B, or may include both A and B.

[0054] The terms used in the various embodiments of this disclosure (such as "first," "second," etc.) may modify various components in the various embodiments, but do not limit the corresponding components. For example, the above terms do not limit the order and / or importance of the components. The above terms are only used for the purpose of distinguishing one component from others. For example, a first user device and a second user device refer to different user devices, although both are user devices. For example, a first component may be referred to as a second component without departing from the scope of the various embodiments of this disclosure, and similarly, a second component may also be referred to as a first component.

[0055] It should be noted that if a description is made of "connecting" one component to another, then the first component can be directly connected to the second component, and a third component can be "connected" between the first and second components. Conversely, when a component is "directly connected" to another component, it can be understood that there is no third component between the first and second components.

[0056] The term "user" as used in various embodiments of this disclosure may refer to an operator using steelmaking equipment, or a monitoring person, etc.

[0057] The terminology used in the various embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the various embodiments of this disclosure. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this disclosure pertain. Terms (such as those defined in a generally used dictionary) are to be interpreted as having the same meaning as in the context of the relevant technical field and are not to be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this disclosure.

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] Please see Figure 1 The above is a flowchart of a method for controlling efficient slag splashing in a top-and-bottom combined blowing converter according to a specific embodiment. The method includes:

[0060] S101: Collect current furnace information and perform material balance calculations.

[0061] In an exemplary embodiment, the furnace charge information includes the following: molten iron conditions (molten iron composition, temperature, weight, slag quantity, etc.), scrap steel conditions (scrap steel structure type, weight, scrap steel addition ratio, etc.), slag-forming auxiliary materials, coolant, slag-forming agent, etc. (type, composition, addition amount), converter bottom blowing process parameters, converter lining life, etc., as well as the endpoint data after blowing (endpoint oxygen content, endpoint temperature, and final slag composition), converter blowing oxygen consumption, and the model calculates the theoretical value G of the final slag weight for the current furnace charge. 渣-理论 And the theoretical calculated value W of the main component content in the final residue. i--理论 .

[0062] In the embodiments of this application, a material balance calculation model is established based on the collected information of the current furnace run. The model can be established using algebraic methods, graphical methods, or mathematical modeling methods. When establishing the model, the time period and spatial scope of the calculation are clearly defined, i.e., the entire process of the current furnace run from start to finish. Based on the principle of material conservation, mathematical equations describing material flow and transformation are established. Specifically, this can cover various stages such as raw material input, intermediate product generation, product output, and losses. Collected equipment parameters and raw material properties are used as input parameters for the model.

[0063] This embodiment uses the established model to perform calculations and obtain the material balance results.

[0064] The calculation process may include the following steps:

[0065] The collected information on the current furnace run is input into the model. The material balance equation is solved to obtain the actual consumption and production of each material. The calculation results are output in the form of tables, charts, etc., for easy analysis and evaluation. Here, the calculation results are analyzed to evaluate the material balance and identify potential problems and improvement measures.

[0066] This embodiment can assess raw material utilization rate by analyzing the consumption and proportion of various raw materials. It can also analyze various losses during the production process to identify the main points and causes of these losses. Based on the analysis results, it proposes methods to optimize material balance, improve raw material utilization, reduce losses, and increase equipment efficiency.

[0067] S102: The converter is blown, and after the blowing is completed, alloying and tapping operations are performed.

[0068] (3) During the tapping process, LIBS technology is used to detect the slag in the converter and obtain the LIBS detection value W of the main components of the slag for that heat. i--LIBS .

[0069] S103: During the tapping process, LIBS technology is used to detect the slag in the converter and obtain the LIBS detection value of the slag composition content of the current heat.

[0070] Among them, the use of LIBS technology to detect the content of major components such as CaO, SiO2, MgO, and FeO in the slag of the converter is to detect the content of these components.

[0071] S104: The slag composition content detected by LIBS and the theoretical calculation value are calculated using a symmetric neural network to obtain the network-calculated value W of the slag composition content for the current furnace. i--网络 .

[0072] As an example, the slag composition content detected by LIBS (laser-induced breakdown spectroscopy) is compared with the theoretically calculated value using a symmetric connected neural network (such as a multilayer perceptron MLP, or more specifically a variant of a convolutional neural network CNN) to obtain the network-calculated value of the slag composition content for the current furnace.

[0073] The specific process can be divided into the following steps:

[0074] Collecting slag spectral data obtained through LIBS technology can include the content of various components in the slag.

[0075] Features are extracted from LIBS spectral data, such as light intensity, peak position, and peak area at specific wavelengths.

[0076] The slag composition information is cleaned and normalized to ensure it is on the same order of magnitude, facilitating model training. The preprocessed slag composition information is then divided into training, validation, and test sets, typically in proportions of 70%, 15%, 15%, or similar.

[0077] For LIBS data, a multilayer perceptron (MLP) can be chosen as the neural network model.

[0078] Optionally, the network structure can be defined such that the number of neurons in the input layer matches the number of features extracted. Then, depending on the problem complexity and data volume, one or more hidden layers can be designed, each containing a certain number of neurons. Hidden layers can use activation functions such as ReLU and Sigmoid.

[0079] In this embodiment, the number of neurons in the output layer is consistent with the number of slag components to be predicted, and a linear activation function is used or an appropriate activation function is selected according to the specific problem.

[0080] In this embodiment, if certain components should theoretically have similar content, a regularization term can be added to the loss function to encourage the model to output similar values ​​for these components.

[0081] The neural network is trained using the training set data, and the network weights and biases are adjusted using the backpropagation algorithm to minimize the error between the predicted values ​​and the theoretical calculation values. During training, a validation set is used to monitor the model's performance and prevent overfitting.

[0082] The model's performance is evaluated using a test set, and the errors between predicted and theoretical values ​​(such as mean squared error (MSE) and mean absolute error (MAE)) are calculated. Based on the analysis of the model's prediction results, its accuracy and reliability are assessed.

[0083] The model involved in subsequent steps is the model trained and evaluated in this step.

[0084] S105: After tapping, the weight of the slag is measured.

[0085] Specifically, a high-temperature resistant, high-definition camera lens can be used to photograph and detect the area of ​​slag inside the converter. After image recognition, the image is input into a model. The model calculates the volume and weight of the slag according to the specific location, tilting angle, and relative area of ​​the slag inside the converter, based on the corresponding furnace structure and depth, thus obtaining a visualized detection value G of the slag weight for the current furnace batch. 渣-检测 .

[0086] S106: Calculate the weight information of the slag.

[0087] Regarding the slag weight determination method in this embodiment, it can be based on the theoretically calculated value G of the final slag weight of the current furnace. 渣-理论 With visual detection value G 渣-检测 The average weight G of the slag in this furnace was obtained by averaging. 渣-检测 ,Right now:

[0088]

[0089] S107: Determine whether the slag dumping conditions are met based on the current furnace weight information, and whether to add slag conditioner for slag conditioning and quality improvement.

[0090] In this embodiment, the model comprehensively judges whether to dump slag and add slag conditioner for slag conditioning and quality improvement based on various data conditions of the current furnace, production rhythm (duration of slag splashing time), refractory life of furnace lining, target steel grade plan, furnace bottom condition, slag splashing layer thickness, etc., and then calculates the amount of slag left and the amount of slag conditioner added.

[0091] When slag removal is required, precise control of the slag amount and retention is achieved through model calculations, visual detection, and coordination with the converter tilting angle. The amount of slag used for splashing is then obtained after slag removal, G. 渣-溅渣用 .

[0092] S108: After slag dumping and slag adjustment, control the height value H according to the preset slag splashing gun position. t-设定 Splashing is performed.

[0093] S109: Set the slag splashing lance position control height value H of the current furnace model. t-设定 Adjustment value H of splash lance position control based on oxygen lance vibration detection t-振动 Adjustment value H of slag splashing gun position based on furnace opening visualization detection t-可视化 And the slag gun position adjustment value H based on audio detection t-音频 The input is fed into a feedforward neural network for calculation, and the calculated value H of the slag splashing lance position height control network on the time axis of the current furnace is obtained. t-网络 .

[0094] The oxygen lance vibration detection and adjustment method in this embodiment is as follows: When the oxygen lance position is high, the slag is thin and has good fluidity during the slag splashing process, the nitrogen gas flow from the oxygen lance is relatively "soft", and the oxygen lance vibration is relatively small; conversely, when the oxygen lance position is low, the slag is viscous and has poor fluidity, the nitrogen gas flow from the oxygen lance is relatively "hard", and the oxygen lance vibration is relatively large.

[0095] The weight of the oxygen lance is monitored in real time by force sensors installed on the wire rope or pulley suspending the oxygen lance. Combined with a weighing instrument, the force on the wire rope is converted into a weight signal, which is collected, processed, and analyzed by a computer system. This analysis accurately determines the slag melting state, fluidity, and lance position within the furnace. The model then calculates the adjustment value H for the slag splashing lance position control height at that moment. t-振动 .

[0096] The furnace opening visualization detection adjustment method in this embodiment is as follows: the furnace opening visualization detection device is used to detect the state and particle size of the slag splashed at the furnace opening position during the slag splashing process.

[0097] When the slag detected at the furnace mouth is in sheet-like form and its trajectory shows a large inclination, it indicates that the slag is relatively thin and the temperature is high, requiring a reduction in the slag splashing lance position. Conversely, when the detected slag particles are small and their trajectory shows little inclination, it indicates that the slag temperature is already low and the viscosity is high, requiring a corresponding increase in the slag splashing lance position. Through furnace mouth visualization detection, the model determines and adjusts the oxygen lance control height, obtaining the slag splashing lance position adjustment value H based on furnace mouth visualization detection. t-可视化 .

[0098] The furnace mouth audio detection and adjustment method in this embodiment is as follows: The noise inside the converter during slag splashing is collected, processed, and analyzed, and then digitally converted into an audio signal. The magnitude of the audio signal reflects the control height of the slag splashing lance position. Based on the audio signal from the audio slag-forming system, the slag splashing lance position height is further adjusted and corrected in real time to obtain the slag splashing lance position adjustment value H based on audio detection. t-音频 .

[0099] In this embodiment, the slag splashing lance position control height value H is set in the furnace model. t-设定 Adjustment value H of splash lance position control based on oxygen lance vibration detection t-振动 Adjustment value H of slag splashing gun position based on furnace opening visualization detection t-可视化 , Splatter gun position adjustment value H based on audio detection t-音频 Feedforward neural network calculations were performed to obtain the calculated value H of the slag splashing lance position height control network on the time axis of this furnace. t-网络 .

[0100] The high-efficiency slag splashing control method for top-and-bottom blown converters provided in this application considers that the erosion resistance of the slag layer is a crucial factor affecting the furnace protection effect. Poor erosion resistance necessitates slag splashing for each furnace, increasing nitrogen consumption and prolonging the smelting cycle. This invention increases the slag melting temperature to improve the protection effect. Furthermore, a slag conditioner is added to modify the slag, meeting the need for increased melting temperature. The slag conditioner not only raises the slag splashing melting point but also improves the kinetics of slag splashing by making the slag easier to splash. In addition, it generates dispersed solid particles in the slag, thereby improving the bonding ability between the slag and the furnace lining.

[0101] The reasonable control of slag quantity and modification of final slag composition in this application can significantly improve the effect and efficiency of slag splashing for furnace protection.

[0102] This application presents a slag condition detection device based on oxygen lance vibration, which can be used to solve the problem of accurately determining the melting state of slag. A force sensor installed on the wire rope or pulley suspending the oxygen lance detects the weight of the lance in real time. Combined with a weighing instrument, the force on the wire rope is converted into a weight signal, which is collected, processed, and analyzed by a computer system to determine the slag condition and guide the adjustment of the oxygen lance position control.

[0103] This application also includes an auxiliary detection system for online detection of slag conditions inside the converter through converter noise analysis. The basic principle is to use the magnitude of characteristic noise inside the converter during smelting to determine the slag formation status. The supersonic nitrogen gas flow from the oxygen lance impacting the molten pool generates strong noise. The noise is greatest when the contact area between nitrogen and slag is small and least when the contact area is large. By collecting, processing, and analyzing the noise inside the converter during slag splashing, it is digitized and converted into an audio signal. The magnitude of the audio signal reflects the control height of the slag splashing lance position.

[0104] Under reasonable slag quantity and final slag physical and chemical conditions, and taking into account the changes and differences in raw materials, molten iron and scrap steel conditions, smelting process system, steel grade smelting requirements, process equipment and parameters, operating skills, furnace life, etc., as well as the requirements for slag splashing and furnace protection at different furnace ages and different furnaces, and the degree of erosion of various parts of the furnace lining refractory bricks, we will systematically and comprehensively consider and explore the optimal slag splashing effect and efficiency under the current furnace conditions, so as to achieve the goal of precise, efficient and economical slag splashing.

[0105] Based on the above-mentioned efficient slag splashing control method for top-and-bottom combined blowing converters, the theoretical value of the final slag weight G for that heat is calculated using a model by collecting relevant information from each heat and performing material balance calculations. 渣-计算 The theoretical value W of the main component content in the final residue i--理论 By combining LIBS detection and steel tapping visualization detection for correction and analysis, the amount of slag left is determined. During the slag splashing process, feedforward neural network calculations and corrections to the slag splashing lance position are performed using oxygen lance vibration, furnace mouth visualization, and audio slag-forming detection technologies. This achieves scientific control of the amount of slag left and precise control of the slag splashing lance position, improving the slag splashing effect, increasing the converter operation rate, and reducing process production costs. It has significant economic benefits and broad prospects for promotion.

[0106] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0107] Based on the above embodiments, in order to further improve the slag splashing protection effect of the high-efficiency slag splashing control method for top and bottom blowing converters provided in the above embodiments, in one embodiment, material balance calculation can be performed based on furnace information.

[0108] The specific parameters are as follows: molten iron temperature upon entering the furnace is 1326℃; molten iron composition: C: 4.28%; Si: 0.56%; Mn: 0.32%; P: 0.075%; S: 0.030%; scrap steel + molten iron addition amount is (181+50)t; main slag-forming materials and alloy addition amount: lime 28kg / t, dolomite 6.1kg / t, ore 7.6kg / t; the blowing process is stable, with no splashing or re-drying phenomena, and the endpoint is hit on the first attempt.

[0109] The TSO results of the converter's final auxiliary lance in this embodiment are as follows: [C]: 0.078%, T: 1656℃, molten pool height h: 836mm; oxygen consumption is 49Nm³. 3 / t; Model material balance calculation of the theoretical calculated value of the final slag weight G for this furnace. 渣-理论 The value is 21.8t, and the visual inspection value at the furnace opening is G. 渣-检测 The average weight of slag in this furnace batch was 22.0t. 渣-检测 The model's material balance calculations yielded a theoretical content of 41.38% CaO, 14.46% SiO2, 7.20% MgO, and 16.92% FeO in the final slag. LIBS measurements showed 41.33% CaO, 14.42% SiO2, 7.32% MgO, and 16.88% FeO. After calculation using a symmetrically connected neural network, the final values ​​were 41.36% CaO, 14.45% SiO2, 7.28% MgO, and 16.91% FeO. The model automatically determined that slag removal was necessary, but no slag adjustment was required. With the aid of visual detection and converter tilting angle, 5t of slag was removed and 16.9t of slag was retained. The model's set slag splashing gun position control height curve value H on the time axis for this furnace was [data missing]. t-设定 Adjustment value H of the splash lance position control height curve based on oxygen lance vibration detection t-振动 Adjustment value H of slag splashing gun position height curve based on furnace opening visualization detection t-可视化 Adjustment value H of the slag-splashing gun position height curve based on audio detection t-音频 And the feedforward neural network calculates the curve value H t-网络 like Figure 2 As shown, controlling the height of the slag splashing lance according to the network calculation values ​​resulted in good slag splashing effect.

[0110] In one embodiment of the present invention, another possible embodiment will be given below, and its specific implementation will be described in a non-limiting manner.

[0111] The molten iron temperature at the furnace was 1352℃, and the composition was C: 4.35%; Si: 0.48%; Mn: 0.39%; P: 0.073%; S: 0.026%. The amount of scrap steel and molten iron added was (180+51)t. The main slag-forming materials and alloys added were: lime 29.3kg / t, dolomite 7.1kg / t, and ore 7.7kg / t. The blowing process was stable, with no splashing or back-drying phenomena, and the endpoint was hit on the first attempt. The TSO results of the auxiliary lance at the converter endpoint were: [C]: 0.075%, T: 1645℃, molten pool height h: 831mm; and oxygen consumption was 49Nm³. 3 / t; Model material balance calculation of the theoretical calculated value of the final slag weight G for this furnace. 渣-理论 The value is 18.86t, and the visual inspection value at the furnace opening is G. 渣-检测 The average weight of slag in this furnace was 18.88t. 渣-检测 The model's material balance calculations yielded the following theoretical values ​​for the main components in the final slag of this furnace: CaO: 43.66%, SiO2: 14.62%, MgO: 8.95%, FeO: 21.26%. LIBS analysis showed CaO: 43.68%, SiO2: 14.66%, MgO: 8.91%, FeO: 21.32%. After calculation using a symmetric connected neural network, the values ​​were: CaO: 43.67%, SiO2: 14.64%, MgO: 8.93%, FeO: 21.28%. The model automatically determined that slag adjustment was necessary but not slag dumping, and calculated the addition of 350 kg of slag adjuster. The model's set slag splashing gun position control height curve value H on the time axis for this furnace was [value missing]. t-设定 Adjustment value H of the splash lance position control height curve based on oxygen lance vibration detection t-振动 Adjustment value H of slag splashing gun position height curve based on furnace opening visualization detection t-可视化 Adjustment value H of the slag-splashing gun position height curve based on audio detection t-音频 And the feedforward neural network calculates the curve value H t-网络 like Figure 3 As shown, controlling the height of the slag splashing lance according to the network calculation values ​​resulted in good slag splashing effect.

[0112] The following are embodiments of the high-efficiency slag splashing control system for top-and-bottom combined blowing converter provided in this disclosure. This system and the high-efficiency slag splashing control method for top-and-bottom combined blowing converter in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the high-efficiency slag splashing control system for top-and-bottom combined blowing converter, please refer to the embodiments of the high-efficiency slag splashing control method for top-and-bottom combined blowing converter described above.

[0113] The system includes: an information acquisition module, a blowing and tapping control module, a LIBS slag detection module, a neural network calculation module, a slag weight detection module, a slag weight calculation module, a judgment module, a slag splashing control module, and a slag splashing gun position height control module.

[0114] The information acquisition module is used to collect information on the current furnace batch and perform material balance calculations;

[0115] The blowing and tapping control module is used to blow the converter and perform alloying tapping after the blowing is completed.

[0116] The LIBS slag detection module is used during the steel tapping process to detect the slag in the converter using LIBS technology, and obtain the LIBS detection value of the slag composition content of the current heat.

[0117] The neural network calculation module is used to perform symmetrically connected neural network calculations on the slag composition content detected by LIBS and the theoretical calculation values ​​to obtain the network-calculated value W of the slag composition content for the current furnace. i--网络 ;

[0118] The slag weight detection module is used to detect the weight of slag after steel tapping.

[0119] The slag weight calculation module is used to calculate the weight information of the slag.

[0120] The judgment module is used to determine whether the slag dumping conditions are met and whether slag conditioners need to be added for slag conditioning and quality improvement based on the weight information of the current furnace.

[0121] The slag splashing control module is used to control the height value H according to the preset slag splashing gun position after slag dumping and slag adjustment. t-设定 Splashing;

[0122] The slag splashing lance position height control module is used to control the slag splashing lance position height value H set in the current furnace model. t-设定 Adjustment value H of splash lance position control based on oxygen lance vibration detection t-振动 Adjustment value H of slag splashing gun position based on furnace opening visualization detection t-可视化 And the slag gun position adjustment value H based on audio detection t-音频 The input is fed into a feedforward neural network for calculation, and the calculated value H of the slag splashing lance position height control network on the time axis of the current furnace is obtained. t-网络 .

[0123] In an embodiment of this application, a control terminal is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the method for efficient slag splashing control in a top-and-bottom combined blowing converter.

[0124] The efficient slag splashing control method for top and bottom blowing converters is applied to one or more control terminals. The control terminal is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0125] The control terminal can also represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The control terminal can also represent various forms of mobile devices, such as personal digital processors and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments described and / or claimed herein.

[0126] The visualization detection method and video acquisition device in this embodiment can both use industrial cameras, and the industrial cameras used have high temperature resistance.

[0127] This application can also utilize computer vision technology. Machine vision, which uses cameras and computers to replace human eyes for target recognition, tracking, and measurement, further processes images to create images more suitable for human observation or transmission to instruments. As a scientific discipline, computer vision researches related theories and technologies, attempting to establish artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technology typically includes image processing, recognition, semantic understanding, and video processing of the steelmaking process, enabling the identification and analysis of information related to oxygen lance height at the furnace opening and other relevant information during the steelmaking process.

[0128] The high-efficiency slag splashing control system for top-and-bottom combined blowing converters of this application comprises the units and algorithm steps of various examples described in conjunction with the embodiments disclosed herein. It can be implemented using electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0129] The storage medium provided in this application stores a program product capable of implementing the methods described above in this specification. In some possible implementations, various aspects of this disclosure can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0130] The storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example,, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0131] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for efficient slag splash control in a top-and-bottom combined blowing converter, characterized in that, The methods include: S101: Collect current furnace information and perform material balance calculations; S102: The converter is blown, and after the blowing is completed, alloying and tapping operations are carried out; S103: During the tapping process, LIBS technology is used to detect the slag in the converter and obtain the LIBS detection value of the slag composition content of the current heat. S104: The slag composition content detected by LIBS and the theoretical calculation value are calculated using a symmetric neural network to obtain the network-calculated value W of the slag composition content for the current furnace. i--网络 ; S105: After tapping, the weight of the slag is measured; S106: Calculate the weight information of the slag; S107: Determine whether the slag dumping conditions are met based on the weight information of the current furnace batch, and whether to add slag conditioner for slag conditioning and quality improvement; S108: After slag dumping and slag adjustment, control the height value H according to the preset slag splashing gun position. t-设定 Splashing; S109: Set the slag splashing lance position control height value H in the current furnace model. t-设定 Adjustment value H of splash lance position control based on oxygen lance vibration detection t-振动 Adjustment value H of slag splashing gun position based on furnace opening visualization detection t-可视化 And the slag gun position adjustment value H based on audio detection t-音频 The input is fed into a feedforward neural network for calculation, and the calculated value H of the slag splashing lance position height control network on the time axis of the current furnace is obtained. t-网络 .

2. The method for controlling efficient slag splashing in a top-and-bottom combined blowing converter according to claim 1, characterized in that, Step S109 further includes: real-time detection of the vibration state of the oxygen lance by installing a force sensor on the wire rope or pulley suspending the oxygen lance, and obtaining the adjustment value H of the slag splashing lance position control height. t-振动 .

3. The method for controlling efficient slag splashing in a top-and-bottom combined blowing converter according to claim 1, characterized in that, Step S109 further includes: detecting the height of the oxygen lance at the furnace opening by installing a video acquisition device at the furnace opening, and adjusting the oxygen lance height to obtain the slag splashing lance position adjustment value H. t-可视化 .

4. The method for controlling efficient slag splashing in a top-and-bottom combined blowing converter according to claim 1, characterized in that, Step S109 also includes: collecting, processing, and analyzing the noise inside the converter during slag splashing, converting it into an audio signal, and obtaining the slag splashing furnace protection gun position control height based on the magnitude of the audio signal; Based on the audio signal, the height of the splash gun position is adjusted in real time to obtain the splash gun position adjustment value H based on audio detection. t-音频 .

5. The method for controlling efficient slag splashing in a top-and-bottom combined blowing converter according to claim 1, characterized in that, In step S101, the furnace information includes: molten iron conditions, scrap steel conditions, slag-forming auxiliary materials, coolant, slag-forming agent conditions, converter bottom blowing process parameters, converter lining life, and endpoint data after blowing, as well as converter blowing oxygen consumption. The theoretical calculated value G of the final slag weight for the current furnace is determined based on the furnace information. 渣-理论 And the theoretical calculated value W of the component content in the final residue. i--理论 .

6. The method for controlling efficient slag splashing in a top-and-bottom combined blowing converter according to claim 1, characterized in that, In step S105, a camera is used to photograph the slag inside the converter; The industrial control computer acquires images of the slag captured in the image and identifies the area of ​​the slag inside the furnace. Based on the converter's location, tilting angle, and slag area within the furnace, the volume and weight are calculated according to the converter's structure and depth, yielding a visually detectable value G of the slag weight for the current furnace cycle. 渣-检测 .

7. The method for controlling efficient slag splashing in a top-and-bottom combined blowing converter according to claim 1, characterized in that, In step S106, the slag weight information is the average slag weight G of the current furnace batch. 渣-检测 ; The average weight of slag in the current furnace (G) 渣-检测 Calculated as follows: G 渣-理论 This is the theoretically calculated value of the final slag weight for the current furnace batch; G 渣-检测 To visualize the detection values.

8. A high-efficiency slag splashing control system for a top-and-bottom combined blowing converter, characterized in that, The system employs the high-efficiency slag splashing control method for top-and-bottom combined blowing converter as described in any one of claims 1 to 7; The system includes: an information acquisition module, a blowing and tapping control module, a LIBS slag detection module, a neural network calculation module, a slag weight detection module, a slag weight calculation module, a judgment module, a slag splashing control module, and a slag splashing gun position height control module. The information acquisition module is used to collect information on the current furnace batch and perform material balance calculations; The blowing and tapping control module is used to blow the converter and perform alloying tapping after the blowing is completed. The LIBS slag detection module is used during the steel tapping process to detect the slag in the converter using LIBS technology, and obtain the LIBS detection value of the slag composition content of the current heat. The neural network calculation module is used to perform symmetrically connected neural network calculations on the slag composition content detected by LIBS and the theoretical calculation values ​​to obtain the network-calculated value W of the slag composition content for the current furnace. i--网络 ; The slag weight detection module is used to detect the weight of slag after steel tapping. The slag weight calculation module is used to calculate the weight information of the slag. The judgment module is used to determine whether the slag dumping conditions are met and whether slag conditioners need to be added for slag conditioning and quality improvement based on the weight information of the current furnace. The slag splashing control module is used to control the height value H according to the preset slag splashing gun position after slag dumping and slag adjustment. t-设定 Splashing; The slag splashing lance position height control module is used to control the slag splashing lance position height value H set in the current furnace model. t-设定 Adjustment value H of splash lance position control based on oxygen lance vibration detection t-振动 Adjustment value H of slag splashing gun position based on furnace opening visualization detection t-可视化 And the slag gun position adjustment value H based on audio detection t-音频 The input is fed into a feedforward neural network for calculation, and the calculated value H of the slag splashing lance position height control network on the time axis of the current furnace is obtained. t-网络 .

9. A control terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the efficient slag splashing control method for top and bottom combined blowing converter as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the efficient slag splashing control method for top and bottom combined blowing converter as described in any one of claims 1 to 7.

Images