Furnace nose zinc ash inhibition method and device

Abstract

The invention provides a furnace nose zinc ash inhibition method and device and belongs to the technical field of metallurgy, a furnace nose is located between an annealing furnace and a zinc pot, the annealing furnace is used for annealing strip steel, the zinc pot is used for galvanizing the strip steel, and the method comprises the steps that the gas dew point temperature of a furnace nose area, the zinc pot temperature and the strip steel speed are obtained; the gas dew point temperature, the zinc pot temperature, the strip steel speed and the preset target dew point temperature are input into a preset mapping model, and the target humidification amount is obtained; the mapping model is constructed based on a pre-trained multi-layer perceptron model; and the humidification equipment is controlled to work based on the target humidification amount, so that generation of furnace nose zinc ash is inhibited. According to the furnace nose zinc ash inhibition method and device, the surface quality of the hot-dip galvanized strip steel can be improved.

Description

Technical Field

[0001] This application belongs to the field of metallurgical technology, and more specifically, relates to a method and apparatus for suppressing zinc ash in a furnace nose. Background Technology

[0002] In continuous hot-dip galvanizing production lines, zinc ash and zinc dross defects are the most common and difficult to control defects in hot-dip galvanized strip steel production, and the furnace nose is the main piece of equipment that generates these defects. The furnace nose is located between the annealing furnace and the zinc pot, serving as the connecting channel. The furnace nose is generally divided into three sections: section A, which is fixed and connected to the annealing furnace; section B, the middle section; and section C, the end of the furnace nose, which is directly inserted into the zinc pot. The area above the zinc pot, where the furnace nose is located, is constantly exposed to a high-temperature environment (450-550℃). During the galvanizing process, compounds formed by the reaction of iron, zinc, aluminum, and other elements molten into the zinc solution easily accumulate on the inner wall of the furnace nose, forming zinc ash. Simultaneously, the continuously generated zinc dross accumulates in large quantities on the surface of the molten zinc inside the furnace nose end. Zinc ash and zinc dross can cause defects such as slag adhesion, pitting, and incomplete coating on the strip steel surface, severely affecting the surface quality and product grade of the hot-dip galvanized strip steel. Summary of the Invention

[0003] The purpose of this application is to provide a method and apparatus for suppressing zinc ash at the furnace nose, so as to improve the surface quality of hot-dip galvanized steel strip.

[0004] A first aspect of this application provides a method for suppressing zinc ash at the furnace nose, wherein the furnace nose is located between an annealing furnace and a zinc pot, the annealing furnace is used for annealing strip steel, and the zinc pot is used for galvanizing strip steel, the method comprising: Obtain the gas dew point temperature, zinc pot temperature, and strip speed in the furnace nose area; The gas dew point temperature, zinc pot temperature, strip speed, and preset target dew point temperature are input into a preset mapping model to obtain the target humidification amount; the mapping model is constructed based on a pre-trained multilayer perceptron model. The humidification equipment is controlled based on the target humidification amount to suppress the formation of zinc ash at the furnace nose.

[0005] A second aspect of this application provides a furnace nose zinc ash suppression device, comprising: The data acquisition module is used to acquire the gas dew point temperature, zinc pot temperature, and strip speed in the furnace nose area; The humidification calculation module is used to input the gas dew point temperature, zinc pot temperature, strip speed and preset target dew point temperature into a preset mapping model to obtain the target humidification amount; the mapping model is constructed based on a pre-trained multilayer perceptron model. The humidification control module is used to control the operation of the humidification equipment based on the target humidification amount in order to suppress the generation of zinc ash at the furnace nose.

[0006] A third aspect of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described furnace nose zinc ash suppression method.

[0007] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described furnace nose zinc ash suppression method.

[0008] The beneficial effects of the furnace nose zinc ash suppression method and apparatus provided in this application embodiment are as follows: This application embodiment constructs a mapping model based on a pre-trained multilayer perceptron model. Using this mapping model, the target humidification amount is calculated based on the gas dew point temperature, zinc pot temperature, strip speed, and target dew point temperature. The gas dew point temperature in the furnace nose area is stabilized between -20°C and -5°C, which can reduce the activity of zinc ash and inhibit further oxidation of zinc vapor, thereby reducing the generation of zinc ash. At the same time, suitable humidity can generate liquid bridging forces between zinc ash particles, enhancing the adhesion of zinc ash to the furnace nose and reducing detachment. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a schematic flowchart of a furnace nose zinc ash suppression method provided in an embodiment of this application; Figure 2 This is a structural block diagram of a furnace nose zinc ash suppression device provided in an embodiment of this application; Figure 3 A schematic block diagram of an electronic device provided in an embodiment of this application; Detailed Implementation In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0012] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a method for suppressing zinc ash at the furnace nose according to an embodiment of this application. The method can be executed by an electronic device and may include: S101: Obtain the gas dew point temperature, zinc pot temperature, and strip speed in the furnace nose area.

[0013] In this embodiment, the electronic device can be an intelligent controller. The intelligent controller controls the humidification device to add water mist molecules to the furnace nose area, maintaining the gas dew point temperature in the furnace nose area between -20°C and -5°C, thus keeping the gas within a suitable humidity range. The water mist molecules in the gas adsorb onto the zinc ash surface, reducing its activity and inhibiting further oxidation of zinc vapor, thereby reducing zinc ash formation. Simultaneously, suitable humidity can create liquid bridging forces between zinc ash particles, enhancing the adhesion of zinc ash to the furnace nose and reducing detachment.

[0014] In order to control the gas dew point temperature in the furnace nose area between -20°C and -5°C, it is necessary to determine the corresponding increase in water mist molecules, i.e., the target humidification amount, based on the gas dew point temperature, zinc pot temperature and strip speed in the furnace nose area. Therefore, in this embodiment, the gas dew point temperature, zinc pot temperature and strip speed in the furnace nose area are first obtained.

[0015] The current gas dew point temperature is a direct reference for the amount of humidification. If the gas dew point temperature is below -20℃, it is necessary to increase the amount of water mist molecules to improve humidity. If the gas dew point temperature is between -20℃ and -5℃, it is only necessary to replenish the water vapor lost naturally. If the gas dew point temperature is above -5℃, humidification is not required.

[0016] Meanwhile, considering that the higher the temperature of the zinc pot, the faster the zinc liquid evaporates and the higher the concentration of zinc vapor in the furnace nose, it is necessary to maintain a relatively low gas dew point temperature to avoid a large amount of zinc vapor reacting with water vapor to generate zinc ash (Zn+H2O→ZnO+H2↑).

[0017] Specifically, a dew point sensor can be installed in the furnace nose area to monitor the gas dew point temperature in the furnace nose area in real time at a frequency of once per second; an immersion thermocouple can be installed in the zinc pot to collect the zinc pot temperature in real time; the strip speed can be obtained through the strip drive roller encoder; and the data collected by the above sensors can be synchronously transmitted to the intelligent controller.

[0018] S102: Input the gas dew point temperature, zinc pot temperature, strip speed and preset target dew point temperature into the preset mapping model to obtain the target humidification amount; the mapping model is constructed based on a pre-trained multilayer perceptron model.

[0019] In this embodiment, a mapping model can be pre-built based on a pre-trained multilayer perceptron model. The multilayer perceptron model (MLP model) can fit the nonlinear relationship between multiple parameters through the nonlinear activation of multiple layers of neurons. At the same time, the target dew point temperature can be pre-set based on empirical values ​​as the target value for humidity control, which is used to calculate the target humidification amount.

[0020] Based on this, by inputting the gas dew point temperature, zinc pot temperature, strip speed and preset target dew point temperature into the preset mapping model, the target humidification amount can be obtained.

[0021] S103: Control the operation of the humidification equipment based on the target humidification amount to suppress the formation of zinc ash at the furnace nose.

[0022] In this embodiment, the humidification device can be an atomizing nozzle or a steam humidifier, etc. The humidification device is driven to work based on the target humidification amount, which can control the gas dew point temperature in the furnace nose area between -20°C and -5°C, thereby inhibiting the formation of zinc ash in the furnace nose.

[0023] Specifically, the target humidification amount can be converted into equipment control signals (such as nozzle opening and steam flow) through a PID controller, and the increase of water mist molecules in the furnace nose area can be adjusted in real time until the gas dew point temperature in the furnace nose area is controlled between -20°C and -5°C.

[0024] As can be seen from the above, this embodiment constructs a mapping model based on a pre-trained multilayer perceptron model, and uses this mapping model to calculate the target humidification amount based on the gas dew point temperature, zinc pot temperature, strip speed, and target dew point temperature. This stabilizes the gas dew point temperature in the furnace nose area between -20℃ and -5℃, which can reduce the activity of zinc ash and inhibit further oxidation of zinc vapor, thereby reducing the generation of zinc ash. At the same time, suitable humidity can generate liquid bridging forces between zinc ash particles, enhancing the adhesion of zinc ash to the furnace nose and reducing detachment.

[0025] In one embodiment of this application, the mapping model includes a softmax layer, a first multilayer perceptron, a second multilayer perceptron, and a third multilayer perceptron. The first multilayer perceptron, the second multilayer perceptron, and the third multilayer perceptron are trained based on historical data corresponding to different zinc pot temperature ranges. The maximum value of the zinc pot temperature corresponding to the first multilayer perceptron is less than the minimum value of the zinc pot temperature corresponding to the second multilayer perceptron, and the maximum value of the zinc pot temperature corresponding to the second multilayer perceptron is less than the minimum value of the zinc pot temperature corresponding to the third multilayer perceptron. By inputting the gas dew point temperature, zinc pot temperature, strip speed, and preset target dew point temperature into a preset mapping model, the target humidification amount is obtained, including: The temperature of the zinc pot is input into the softmax layer to obtain three probability values; The input data is input into the first multilayer sensor, the second multilayer sensor, and the third multilayer sensor respectively to obtain the first humidification amount, the second humidification amount, and the third humidification amount; the input data includes the gas dew point temperature, the zinc pot temperature, the strip speed, and the preset target dew point temperature; The three probability values ​​are used as weights for the first humidification amount, the second humidification amount, and the third humidification amount, respectively. The first humidification amount, the second humidification amount, and the third humidification amount are weighted and summed to obtain the target humidification amount.

[0026] In this embodiment, considering the significant differences in the mapping relationship between the target humidification amount and the input data under different zinc pot temperature conditions, multiple sets of historical data can be collected in advance and divided into multiple training datasets based on the zinc pot temperature. Each set of historical data includes historical data corresponding to the gas dew point temperature, zinc pot temperature, strip speed, preset target dew point temperature, and target humidification amount. The multiple training datasets can include a first training dataset, a second training dataset, and a third training dataset. The first training dataset contains historical data with a zinc pot temperature range of [435℃, 460℃], the second training dataset contains historical data with a zinc pot temperature range of [461℃, 490℃], and the third training dataset contains historical data with a zinc pot temperature range of [491℃, 530℃]. Based on this, a first multilayer perceptron is trained based on the first training dataset, a second multilayer perceptron is trained based on the second training dataset, and a third multilayer perceptron is trained based on the third training dataset. This allows each multilayer perceptron to focus on learning the parameter coupling relationship of the corresponding temperature range.

[0027] In practical use, the zinc pot temperature is input into the softmax layer to obtain three probability values ​​corresponding to the three intervals. , and The input data is fed into the first multilayer sensor, the second multilayer sensor, and the third multilayer sensor respectively to obtain the corresponding first humidification amount. Second humidification capacity and the third humidification amount Then add the first humidifier. Second humidification capacity and the third humidification amount Weighted summation yields the target humidification amount. The specific calculation formula is as follows: .

[0028] By using the weighted summation described above, abrupt changes in humidification caused by traditional threshold division can be avoided. For example, when the temperature of the zinc pot rises from 460℃ to 461℃, the output of the Softmax layer transitions from "probability 0.9 in the first interval / 0.1 in the second interval / 0.0 in the third interval" to "0.1 in the first interval / 0.9 in the second interval / 0.0 in the third interval". The weighted target humidification gradually changes from being dominated by the output Q1 of the first multilayer sensor (0.9Q1 + 0.1Q2) to being dominated by the output Q2 of the second multilayer sensor (0.1Q1 + 0.9Q2), avoiding sudden changes in humidification under traditional threshold division and suppressing fluctuations in zinc ash formation.

[0029] As can be seen from the above, this embodiment learns the parameter coupling relationship of the corresponding temperature range based on the first multilayer perceptron, the second multilayer perceptron, and the third multilayer perceptron, respectively, and can obtain the accurate first humidification amount, the second humidification amount, and the third humidification amount; at the same time, by performing probability weighting through the Softmax layer, the interval transition can be realized, avoiding the sudden change in humidification amount caused by traditional threshold division.

[0030] In one embodiment of this application, the input data further includes a first coupling feature and a second coupling feature; The first coupling feature is obtained based on the difference between the gas dew point temperature and the target dew point temperature, while the second coupling feature is obtained based on the product between the zinc pot temperature and the strip speed.

[0031] In this embodiment, the first coupling feature is obtained by calculating the difference between the gas dew point temperature and the target dew point temperature. The first coupling feature can directly characterize the intensity of humidification demand. The zinc pot temperature can affect the zinc vapor volatilization rate, and the strip speed can affect the contact time between the strip and the gas in the furnace. The second coupling feature is obtained by calculating the product between the zinc pot temperature and the strip speed. The second coupling feature can quantify the dynamic environmental intensity of the reaction between zinc vapor and water vapor, and directly characterize the matching relationship between humidification amount and zinc ash suppression effect.

[0032] The first and second coupling features mentioned above, along with the original gas dew point temperature, zinc pot temperature, strip speed, and target dew point temperature, are used as input data and fed into the mapping model. Since the first and second coupling features can aggregate key correlation information in advance, the mapping model can more efficiently capture the nonlinear relationship between parameters, improve the prediction accuracy of target humidification amount under complex working conditions (such as high temperature + high speed), ensure stable control of gas dew point temperature, and enhance the zinc ash suppression effect.

[0033] In one embodiment of this application, the furnace nose zinc ash suppression method further includes: For the first multilayer perceptron, the feature weight of the first coupling feature is set to be greater than the feature weight of the strip speed, and the feature weight of the strip speed is greater than the feature weight of the second coupling feature. For the second multilayer perceptron, the feature weight of the first coupling feature is set to be greater than the feature weight of the second coupling feature, and the feature weight of the second coupling feature is greater than the feature weight of the strip speed. For the third multilayer perceptron, the feature weight of the second coupling feature is set to be greater than the feature weight of the first coupling feature, and the feature weight of the first coupling feature is greater than the feature weight of the strip speed.

[0034] In this embodiment, considering that the influence of each input data on the target humidification amount varies in different zinc pot temperature ranges, each input data has different feature weights during the calculation process of the first multilayer perceptron, the second multilayer perceptron, and the third multilayer perceptron, in order to highlight the input data that has a greater impact on the target humidification amount.

[0035] For example, in the network of the first multilayer perceptron, the first coupling feature has a higher feature weight. When the first layer neurons input data for weighted summation and activation operations, the influence of the first coupling feature will be amplified first.

[0036] Specifically, within the zinc pot temperature range [435℃, 460℃] corresponding to the first multilayer sensor, the zinc vapor concentration is low, and the main influencing factors of the target humidification amount include the first coupling feature, strip speed, and second coupling feature. Among these, the first coupling feature (i.e., dew point temperature deviation) is the core influencing factor of the target humidification amount; therefore, its weight is set to the highest (e.g., 0.5). Simultaneously, considering that strip speed affects the amount of water vapor carried out, thus affecting the humidity inside the furnace nose, and further considering that the zinc pot temperature is low and zinc vapor volatilization is low within this temperature range, the second coupling feature (zinc pot temperature × strip speed) has a weak impact on zinc ash formation. Therefore, the feature weight of strip speed is set greater than that of the second coupling feature. For example, the feature weight of strip speed can be set to 0.2, and the feature weight of the second coupling feature can be set to 0.15. Correspondingly, the weights of gas dew point temperature, target dew point temperature, and zinc pot temperature are all set to 0.05.

[0037] Within the zinc pot temperature range [461℃, 490℃] corresponding to the second multilayer sensor, the zinc vapor concentration is relatively high. The first coupling feature (i.e., dew point temperature deviation) still dominates, but the influence of the second coupling feature (zinc pot temperature × strip speed) on the reaction time is enhanced. Therefore, the feature weight of the second coupling feature is higher than that of the strip speed, and the differences between the feature weights corresponding to the first coupling feature, the second coupling feature, and the strip speed are reduced. For example, the feature weight of the first coupling feature can be set to 0.35, the feature weight of the second coupling feature to 0.3, and the weight of the strip speed to 0.2.

[0038] Within the zinc pot temperature range [491℃, 530℃] corresponding to the third multilayer sensor, the high zinc vapor concentration amplifies the influence of the second coupling feature on the zinc ash formation rate. For example, when the strip speed is 60 m / min, the second coupling feature is small, resulting in a longer reaction time between zinc vapor and water vapor, leading to a more complete reaction and a surge in zinc ash. When the speed increases to 180 m / min, the second coupling feature increases, shortening the reaction time between zinc vapor and water vapor and significantly reducing zinc ash formation. Therefore, for the third multilayer sensor, the feature weight of the second coupling feature is set to be the highest, followed by the first coupling feature, and then the strip speed is set to be the lowest. For example, the feature weight of the second coupling feature can be set to 0.6, the feature weight of the first coupling feature to 0.2, the feature weight of the strip speed to 0.1, the feature weight of the gas dew point temperature to 0.03, the feature weight of the target dew point temperature to 0.05, and the feature weight of the zinc pot temperature to 0.02.

[0039] As can be seen from the above, this embodiment, through differentiated weight allocation, enables the first, second, and third multilayer perceptrons to focus on the key influencing factors in this interval, thereby accurately capturing the parameter coupling relationship under different zinc pot temperatures and improving the prediction accuracy of the target humidification amount.

[0040] In one embodiment of this application, the target dew point temperature is determined by: If the temperature of the zinc pot is greater than the temperature threshold, set the target dew point temperature to the first dew point temperature. If the temperature of the zinc pot is less than or equal to the temperature threshold, the target dew point temperature is set to the second dew point temperature; the first dew point temperature is less than the second dew point temperature.

[0041] In this embodiment, considering that the zinc liquid evaporates rapidly at higher zinc pot temperatures, the zinc vapor concentration in the furnace nose area increases significantly. If the gas dew point temperature is high at this time (high water vapor content), the probability of contact and reaction between zinc vapor and water vapor increases, leading to a sharp increase in zinc ash formation. This results in defects such as pitting and incomplete plating on the strip surface, while also increasing zinc consumption. Therefore, this embodiment pre-sets a temperature threshold (e.g., 490°C). When the zinc pot temperature exceeds this threshold, indicating a high temperature, the target dew point temperature is set to a lower first dew point temperature, such as -15°C, thereby strictly controlling the water vapor content and reducing the reaction between zinc vapor and water vapor.

[0042] When the zinc pot temperature is low, the zinc liquid evaporates slowly, resulting in a low zinc vapor concentration in the furnace nose area. Even if the gas dew point temperature is slightly higher (with slightly higher water vapor content), the probability of the zinc vapor reacting with water vapor is low due to insufficient total zinc vapor content, resulting in minimal zinc ash formation and minimal impact on product quality. Simultaneously, a slightly higher dew point temperature can prevent secondary oxidation of the strip surface due to excessive dryness (the strip has high surface activity after annealing and easily combines with oxygen under low humidity), and it also reduces the energy consumption of the dehumidification system. Therefore, when the zinc pot temperature is less than or equal to the temperature threshold, the target dew point temperature can be set to a higher first dew point temperature, such as -10℃, to prevent secondary oxidation of the strip due to excessively low humidity, thus balancing ash control and strip quality.

[0043] As can be seen from the above, in this embodiment, when the zinc pot temperature is high, setting a smaller target dew point temperature can strictly control the moisture content and reduce the generation of zinc ash; when the zinc pot temperature is low, setting a larger target dew point temperature can prevent secondary oxidation of the strip steel.

[0044] In one embodiment of this application, the humidification device includes an atomizing nozzle, and the operation of the humidification device is controlled based on a target humidification amount, including: Based on the target humidification amount, the atomizing nozzle is controlled to cover the zinc ash accumulation surface at an angle of 30-45°.

[0045] In this embodiment, the humidification equipment can use high-temperature resistant nozzles, which are installed in the zinc ash-rich area of ​​the furnace nose (such as corners and seams). The nozzle density of the atomizing humidification module is configured according to the furnace nose structure (2-3 nozzles per square meter, spaced 40-60cm apart). The high-temperature resistant nozzles (made of 310S stainless steel, temperature resistant up to 1200℃) spray 30-50μm water mist, covering the ash-accumulated surface at a 30-45° angle. The water mist evaporates into water vapor before contacting the high-temperature surface, preventing liquid water from impacting the zinc liquid surface.

[0046] In one embodiment of this application, before obtaining the gas dew point temperature, zinc pot temperature, and strip speed in the furnace nose region, the following steps are further included: Obtain the image of the dust accumulation surface; Image analysis is performed on the image of the ash-accumulated surface to obtain the ash accumulation thickness. If the dust accumulation exceeds the thickness threshold, a prompt message will be output; the prompt message is used to instruct the user to stop the machine for cleaning.

[0047] In this embodiment, a high-temperature resistant industrial camera (resolution ≥ 5 megapixels, temperature resistance 600℃) can be installed above the furnace nose to capture real-time images of the ash accumulation area. Then, the zinc ash deposition boundary is extracted through grayscale conversion and noise reduction, and a zinc ash thickness detection model is trained based on the YOLOv5 algorithm to calculate the ash accumulation thickness. When the ash accumulation thickness exceeds a thickness threshold (e.g., 5mm), a prompt message is output to instruct the operator to stop the machine for cleaning.

[0048] Corresponding to the furnace nose zinc ash suppression method in the above embodiment, Figure 2 This is a structural block diagram of a furnace nose zinc ash suppression device provided according to an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The furnace nose zinc ash suppression device 20 includes: a data acquisition module 21, a humidification calculation module 22, and a humidification control module 23. Among them, the data acquisition module 21 is used to acquire the gas dew point temperature, zinc pot temperature and strip speed in the furnace nose area; The humidification calculation module 22 is used to input the gas dew point temperature, zinc pot temperature, strip speed and preset target dew point temperature into a preset mapping model to obtain the target humidification amount; the mapping model is constructed based on a pre-trained multilayer perceptron model. The humidification control module 23 is used to control the operation of the humidification equipment based on the target humidification amount in order to suppress the generation of zinc ash in the furnace nose.

[0049] In one embodiment of this application, the mapping model includes a softmax layer, a first multilayer perceptron, a second multilayer perceptron, and a third multilayer perceptron. The first, second, and third multilayer perceptrons are trained based on historical data corresponding to different zinc pot temperature ranges. The maximum value of the zinc pot temperature corresponding to the first multilayer perceptron is less than the minimum value of the zinc pot temperature corresponding to the second multilayer perceptron, and the maximum value of the zinc pot temperature corresponding to the second multilayer perceptron is less than the minimum value of the zinc pot temperature corresponding to the third multilayer perceptron. The humidification calculation module 22 is specifically used for: By inputting the gas dew point temperature, zinc pot temperature, strip speed, and preset target dew point temperature into a preset mapping model, the target humidification amount is obtained, including: The temperature of the zinc pot is input into the softmax layer to obtain three probability values; The input data is input into the first multilayer sensor, the second multilayer sensor, and the third multilayer sensor respectively to obtain the first humidification amount, the second humidification amount, and the third humidification amount; the input data includes the gas dew point temperature, the zinc pot temperature, the strip speed, and the preset target dew point temperature; The three probability values ​​are used as weights for the first humidification amount, the second humidification amount, and the third humidification amount, respectively. The first humidification amount, the second humidification amount, and the third humidification amount are weighted and summed to obtain the target humidification amount.

[0050] In one embodiment of this application, the input data further includes a first coupling feature and a second coupling feature; The first coupling feature is obtained based on the difference between the gas dew point temperature and the target dew point temperature, while the second coupling feature is obtained based on the product between the zinc pot temperature and the strip speed.

[0051] In one embodiment of this application, the humidification calculation module 22 is further used for: For the first multilayer perceptron, the feature weight of the first coupling feature is set to be greater than the feature weight of the strip speed, and the feature weight of the strip speed is greater than the feature weight of the second coupling feature. For the second multilayer perceptron, the feature weight of the first coupling feature is set to be greater than the feature weight of the second coupling feature, and the feature weight of the second coupling feature is greater than the feature weight of the strip speed. For the second multilayer perceptron, the feature weight of the second coupled feature is set to be greater than the feature weight of the first coupled feature, and the feature weight of the first coupled feature is greater than the feature weight of the strip speed.

[0052] In one embodiment of this application, the humidification calculation module 22 is specifically used for: If the temperature of the zinc pot is greater than the temperature threshold, set the target dew point temperature to the first dew point temperature. If the temperature of the zinc pot is less than or equal to the temperature threshold, the target dew point temperature is set to the second dew point temperature; the first dew point temperature is less than the second dew point temperature.

[0053] In one embodiment of this application, the humidification device includes an atomizing nozzle, and the humidification control module 23 is specifically used for: Based on the target humidification amount, the atomizing nozzle is controlled to cover the zinc ash accumulation surface at an angle of 30-45°.

[0054] In one embodiment of this application, before acquiring the gas dew point temperature, zinc pot temperature, and strip speed in the furnace nose region, the data acquisition module 21 is specifically used for: Obtain the image of the dust accumulation surface; Image analysis is performed on the image of the ash-accumulated surface to obtain the ash accumulation thickness. If the dust accumulation exceeds the thickness threshold, a prompt message will be output; the prompt message is used to instruct the user to stop the machine for cleaning.

[0055] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above-described device embodiments, for example... Figure 2 The functions of the data acquisition module 21, the humidification calculation module 22, and the humidification control module 23 are shown.

[0056] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0057] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0058] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store preset constants such as temperature thresholds and thickness thresholds.

[0059] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the furnace nose zinc ash suppression method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0060] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0061] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0062] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples 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 application.

[0063] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0064] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connections shown or discussed may be indirect coupling or communication connections through some interfaces or units, or they may be electrical, mechanical, or other forms of connection.

[0065] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0066] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0067] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for suppressing zinc ash at the furnace nose, wherein the furnace nose is located between an annealing furnace and a zinc pot, the annealing furnace being used for annealing strip steel, and the zinc pot being used for galvanizing strip steel, characterized in that... The method includes: Obtain the gas dew point temperature, zinc pot temperature, and strip speed in the furnace nose area; The gas dew point temperature, zinc pot temperature, strip speed, and preset target dew point temperature are input into a preset mapping model to obtain the target humidification amount; the mapping model is constructed based on a pre-trained multilayer perceptron model. The humidification equipment is controlled based on the target humidification amount to suppress the formation of zinc ash at the furnace nose.

2. The method for suppressing zinc ash at the furnace nose as described in claim 1, characterized in that, The mapping model includes a softmax layer, a first multilayer perceptron, a second multilayer perceptron, and a third multilayer perceptron. The first multilayer perceptron, the second multilayer perceptron, and the third multilayer perceptron are trained based on historical data corresponding to different zinc pot temperature ranges. The maximum value of the zinc pot temperature corresponding to the first multilayer perceptron is less than the minimum value of the zinc pot temperature corresponding to the second multilayer perceptron, and the maximum value of the zinc pot temperature corresponding to the second multilayer perceptron is less than the minimum value of the zinc pot temperature corresponding to the third multilayer perceptron. The gas dew point temperature, zinc pot temperature, strip speed, and preset target dew point temperature are input into a preset mapping model to obtain the target humidification amount, including: The temperature of the zinc pot is input into the softmax layer to obtain three probability values; The input data is input into the first multilayer sensor, the second multilayer sensor, and the third multilayer sensor respectively to obtain the first humidification amount, the second humidification amount, and the third humidification amount; the input data includes the gas dew point temperature, the zinc pot temperature, the strip speed, and the preset target dew point temperature; The three probability values ​​are used as weights for the first humidification amount, the second humidification amount, and the third humidification amount, respectively. The first humidification amount, the second humidification amount, and the third humidification amount are weighted and summed to obtain the target humidification amount.

3. The method for suppressing zinc ash at the furnace nose as described in claim 2, characterized in that, The input data also includes a first coupling feature and a second coupling feature; The first coupling feature is obtained based on the difference between the gas dew point temperature and the target dew point temperature, and the second coupling feature is obtained based on the product between the zinc pot temperature and the strip speed.

4. The method for suppressing zinc ash at the furnace nose as described in claim 3, characterized in that, Also includes: For the first multilayer sensor, the feature weight of the first coupling feature is set to be greater than the feature weight of the strip speed, and the feature weight of the strip speed is greater than the feature weight of the second coupling feature. For the second multilayer sensor, the feature weight of the first coupling feature is set to be greater than the feature weight of the second coupling feature, and the feature weight of the second coupling feature is greater than the feature weight of the strip speed. For the third multilayer sensor, the feature weight of the second coupling feature is set to be greater than the feature weight of the first coupling feature, and the feature weight of the first coupling feature is greater than the feature weight of the strip speed.

5. The method for suppressing zinc ash at the furnace nose as described in claim 1, characterized in that, The methods for determining the target dew point temperature include: If the temperature of the zinc pot is greater than the temperature threshold, the target dew point temperature is set as the first dew point temperature; If the temperature of the zinc pot is less than or equal to the temperature threshold, the target dew point temperature is set as the second dew point temperature; the first dew point temperature is less than the second dew point temperature.

6. The method for suppressing zinc ash at the furnace nose as described in claim 1, characterized in that, The humidification device includes an atomizing nozzle, and the operation of the humidification device is controlled based on the target humidification amount, including: Based on the target humidification amount, the atomizing nozzle is controlled to cover the zinc ash accumulation surface at an angle of 30-45°.

7. The method for suppressing zinc ash at the furnace nose as described in claim 1, characterized in that, Before obtaining the gas dew point temperature, zinc pot temperature, and strip speed in the furnace nose area, the following steps are also included: Obtain the image of the dust accumulation surface; Image analysis is performed on the image of the ash-accumulated surface to obtain the ash accumulation thickness; If the accumulated dust thickness exceeds a thickness threshold, a prompt message is output; the prompt message is used to instruct the user to stop the machine for cleaning.

8. A furnace nose zinc ash suppression device, characterized in that, include: The data acquisition module is used to acquire the gas dew point temperature, zinc pot temperature, and strip speed in the furnace nose area; The humidification calculation module is used to input the gas dew point temperature, zinc pot temperature, strip speed and preset target dew point temperature into a preset mapping model to obtain the target humidification amount; the mapping model is constructed based on a pre-trained multilayer perceptron model. The humidification control module is used to control the operation of the humidification equipment based on the target humidification amount in order to suppress the generation of zinc ash at the furnace nose.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images