Intelligent control method and system for off-gas purification of an electric arc furnace, medium and product

Abstract

An intelligent control method and system for off-gas purification of an electric arc furnace, a medium and a product, relate to the field of industrial automation. By implementing the method, the control system dynamically adjusts the PID parameters according to the real-time changes of the furnace pressure value and the furnace flame image during the operation of the electric arc furnace, which improves the adaptability and flexibility of the smoke exhaust control compared with the traditional fixed PID parameters. The control system realizes smooth adjustment of the rotating speed of the smoke exhaust fan through the first control signal, ensuring the stability of the smelting process; through the second control signal, it realizes rapid response to sudden fire outbreak conditions, effectively avoiding the safety risks of fire outbreak and material injection. The control system realizes the combination of smooth control under normal conditions and rapid response under special conditions by fusing the two control signals, which not only ensures the safety and stability of the electric arc furnace operation, but also improves the control accuracy of the smoke exhaust system and reduces environmental pollution.

Description

Technical Field

[0001] This application relates to the field of industrial automation, and in particular to an intelligent control method, system, medium and product for purifying tail gas from a submerged arc furnace. Background Technology

[0002] Submerged arc furnaces are essential smelting equipment used to produce ferroalloys, industrial silicon, and other products. During operation, these closed furnaces generate large amounts of carbon monoxide and dust, which must be cooled and removed through a tail gas purification system before being discharged. A reasonable tail gas purification and control method for submerged arc furnaces is crucial for ensuring the safe and stable operation of the smelting process and reducing environmental pollution.

[0003] Currently, the main method for controlling flue gas exhaust in electric arc furnaces is to collect the pressure inside the furnace using pressure sensors. When the control system detects that the pressure inside the furnace exceeds the set pressure range, it calculates the corresponding control quantity based on preset PID parameters, thereby adjusting the speed of the exhaust fan.

[0004] However, the above methods for controlling flue gas in electric arc furnaces have obvious shortcomings: relying solely on pressure control results in a delayed response when drastic changes occur inside the furnace, such as material collapse, which can easily lead to dangers such as fires and material spraying. Summary of the Invention

[0005] This application provides an intelligent control method, system, medium, and product for purifying exhaust gas from a submerged arc furnace, which improves the safety and reliability of flue gas control.

[0006] In a first aspect, this application provides an intelligent control method for purifying exhaust gas from a submerged arc furnace, applied to a control system. The method includes: real-time acquisition of the furnace internal pressure value and furnace surface flame image, whereby the furnace internal pressure value reflects the gas pressure state inside the furnace, and the furnace surface flame image reflects the combustion state and flameout situation on the furnace surface; adjusting the current PID parameters to variable response PID parameters based on the furnace internal pressure value and furnace surface flame image; performing calculations using the variable response PID parameters based on the deviation between the furnace internal pressure value and a preset furnace internal pressure value to generate a first control signal that smoothly adjusts the exhaust fan speed; processing the furnace surface flame image to extract flame characteristic parameters; and generating a second control signal that rapidly increases the exhaust fan speed when the flame characteristic parameters meet preset sudden flameout judgment conditions; and fusing the first and second control signals and sending them to the frequency converter of the exhaust fan.

[0007] By adopting the above technical solution, the control system simultaneously collects furnace pressure values ​​and furnace surface flame images for multi-dimensional monitoring, providing comprehensive data support for precise flue gas control. The control system dynamically adjusts PID parameters based on real-time changes in the submerged arc furnace during operation, improving the adaptability and flexibility of flue gas control compared to traditional fixed PID parameters. The control system achieves stable adjustment of the flue gas fan speed through a first control signal, ensuring the stability of the smelting process; and achieves rapid response to sudden fire conditions through a second control signal, effectively avoiding safety risks such as fires and material spraying. By integrating dual control signals, the control system combines stable control under normal operating conditions with rapid response under special operating conditions, ensuring both the safety and stability of the submerged arc furnace operation and improving the control accuracy of the flue gas system, while reducing environmental pollution.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, the current PID parameters are adjusted to change-response PID parameters based on the furnace pressure value and the furnace flame image. Specifically, this includes: counting the total number of pixels and the number of flame pixels in the furnace flame image, determining the ratio of the number of flame pixels to the total number of pixels as the flame area ratio, where the number of flame pixels refers to the number of pixels that meet the preset flame pixel judgment conditions; determining the flame area change rate based on the flame area ratio and continuously acquired furnace flame images; determining the furnace pressure fluctuation rate based on continuously acquired furnace pressure values; substituting the flame area change rate and the furnace pressure fluctuation rate into the PID parameter dynamic correction function to obtain the change-response proportional coefficient, the change-response integral time, and the change-response derivative time; combining the change-response proportional coefficient, the change-response integral time, and the change-response derivative time to obtain the change-response PID parameters, and adjusting the current PID parameters to change-response PID parameters.

[0009] By adopting the above technical solution, the control system calculates the flame area change rate and furnace pressure fluctuation rate, and then substitutes them into the PID parameter dynamic correction function to accurately generate change response PID parameters that match the current operating conditions, ensuring the scientific nature and pertinence of the dynamic adjustment of PID parameters. This parameter correction method based on quantitative indicators of actual operating conditions avoids the problem of response lag when traditional fixed PID parameters change with sudden changes in operating conditions, significantly improves the dynamic response capability of the control system, and further ensures the timeliness and effectiveness of flue gas control in the electric arc furnace.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, the dynamic correction function for PID parameters includes a proportional coefficient correction function, an integral time correction function, and a derivative time correction function: the proportional coefficient correction function is: Kp'=Kp×(1+α×(Fd / ΔP-C)); the integral time correction function is: Ti'=Ti×(1-β×(Fd / ΔP-C)); the derivative time correction function is: Td'=Td×(1+γ×(Fd / ΔP-C)); where Kp' represents the proportional coefficient of the change response, Ti' represents the integral time of the change response, Td' represents the derivative time of the change response, Kp represents the current proportional coefficient, Ti represents the current integral time, Td represents the current derivative time, Fd represents the flame area change rate, ΔP represents the furnace pressure fluctuation rate, α, β, and γ represent preset positive correction coefficients, and C represents a preset reference constant.

[0011] By adopting the above technical solution, the dynamic correction function for PID parameters includes a proportional coefficient correction function, an integral time correction function, and a derivative time correction function. This achieves the mathematical and standardized adjustment of PID parameters, improving the accuracy and repeatability of PID parameter adjustment. Adjusting the proportional coefficient enhances the system's sensitivity to deviations, optimizing the integral time improves the system's ability to eliminate steady-state errors, and adapting the derivative time improves the system's ability to predict changes in operating conditions. The synergistic effect of these three functions enables PID control to more accurately match the real-time operating conditions of the electric arc furnace, effectively solving the problems of insufficient control accuracy and lag in traditional fixed PID parameters under complex operating conditions, and ensuring that the speed regulation of the exhaust fan is both fast and stable.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, based on the deviation between the furnace pressure value and the preset furnace pressure value, a variable response PID parameter is used for calculation to generate a first control signal for smoothly adjusting the speed of the exhaust fan. Specifically, this includes: inputting the deviation and variable response PID parameter to the PID control quantity calculation formula, and outputting the PID control quantity; mapping the PID control quantity to the exhaust fan speed adjustment quantity to obtain the first control signal for smoothly adjusting the exhaust fan speed; the PID control quantity calculation formula is: u(t) = Kp[e(t) + 1 / Ti∫e(t)dt + Td×de(t) / dt]; where u(t) represents the PID control quantity, Kp represents the variable response proportional coefficient, Ti represents the variable response integral time, Td represents the variable response derivative time, e(t) represents the deviation, and t represents the sampling time.

[0013] By adopting the above technical solution, the control system substitutes the deviation and change response PID parameters into the PID control quantity calculation formula. It then outputs the PID control quantity through a comprehensive calculation of proportional, integral, and derivative terms. The proportional term quickly responds to the deviation, the integral term eliminates steady-state error, and the derivative term predicts the deviation change trend. The synergistic effect of these three terms avoids the limitations of a single control term, ensuring the comprehensiveness and rationality of the PID control quantity calculation. The control system maps the PID control quantity to the exhaust fan speed adjustment, achieving an effective transformation of the control signal from theoretical calculation to actual execution.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, the furnace flame image is processed to extract flame feature parameters. When the flame feature parameters meet the preset sudden fire condition judgment conditions, a second control signal is generated to rapidly increase the speed of the exhaust fan. Specifically, this includes: extracting the pixel values ​​of the R channel, G channel, and B channel from the furnace flame image, and calculating the average pixel values ​​of the R channel, G channel, and B channel; substituting the average pixel values ​​of the R channel, G channel, and B channel into the flame color deviation index calculation formula to obtain the flame color deviation index; if both the flame area ratio and the flame color deviation index meet the preset sudden fire condition judgment conditions, a second control signal is generated to rapidly increase the speed of the exhaust fan.

[0015] By adopting the above technical solution, a dual-dimensional sudden fire judgment standard of "flame area ratio + flame color deviation index" was constructed, improving the control system's ability to identify and respond quickly to sudden fire conditions. Compared with the single flame area ratio judgment, the flame color deviation index can reflect the intensity of flame combustion (e.g., if the flame color is redder or brighter during a fire, the flame color deviation index will change significantly), further improving the accuracy of the condition judgment and effectively avoiding misjudgments caused by factors such as light interference. When both the flame area ratio and the flame color deviation index meet the preset sudden fire condition judgment conditions, a second control signal is generated to rapidly increase the exhaust fan speed. This can quickly increase the exhaust force in the early stage of a sudden fire, promptly expelling excess gas and flame from the furnace, significantly reducing the probability of fire expansion, material spraying, and other safety accidents. This provides a key risk control guarantee for the safe operation of the electric arc furnace and makes up for the shortcomings of traditional pressure control in responding to sudden conditions.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, the first control signal and the second control signal are merged and sent to the frequency converter of the smoke exhaust fan, specifically including: performing a weighted operation on the first control signal and the second control signal according to a preset weight to obtain an output control signal; calculating the target operating frequency of the frequency converter of the smoke exhaust fan according to the output control signal, and sending the target operating frequency to the frequency converter for execution.

[0017] By adopting the above technical solution, the fusion method of the first and second control signals was clarified, solving the core problem of the synergistic effect of the two signals. This achieved an organic combination of normal stable control and emergency control, significantly improving the comprehensive adaptability of the control system. By pre-setting weights for weighted calculations of the two signals, the weights can be flexibly adjusted according to actual production needs (e.g., increasing the weight of the first control signal under normal operating conditions to ensure stable operation; increasing the weight of the second control signal under emergency conditions to enhance emergency response), avoiding control conflicts or response imbalances that might result from the independent action of the two signals. The control system converts the fused output control signal into the target operating frequency of the frequency converter, directly driving the actuators and ensuring the rapid implementation of control commands. This fusion method retains the advantages of the first control signal in stable regulation under normal operating conditions while leveraging the rapid response capability of the second control signal to emergency conditions. It ensures the continuity and stability of the smelting process of the electric arc furnace, effectively prevents safety risks, and avoids equipment wear caused by frequent start-ups or sudden speed changes of the exhaust fan, extending the service life of the exhaust system.

[0018] In some embodiments of the first aspect, after the step of fusing the first control signal and the second control signal and sending them to the frequency converter of the exhaust fan, the method further includes: real-time acquisition of the filter inlet temperature and carbon monoxide concentration; if the furnace pressure, filter inlet temperature, and carbon monoxide concentration all meet the preset frequency reduction trigger conditions, the operating frequency of the frequency converter is gradually reduced at a preset frequency reduction rate, and the furnace flame image is continuously acquired during the frequency reduction process; when the furnace flame image shows that the flame area ratio exceeds the area ratio threshold or the flame color deviation index exceeds the color deviation index threshold, the frequency reduction is stopped; the operating frequency at which the frequency reduction is stopped is determined as the minimum safe operating frequency of the frequency converter.

[0019] By adopting the above technical solution, the control system constructs preset frequency reduction trigger conditions for multiple parameters (furnace pressure, filter inlet temperature, and carbon monoxide concentration), ensuring that frequency reduction operation is only carried out under the premise of stable system operation and no safety risks, thus avoiding the risk of fire caused by blind frequency reduction. During the frequency reduction process, the control system continuously monitors the flame image on the furnace surface. When the flame area ratio exceeds the critical value or the flame color deviation index exceeds the critical value, the frequency reduction is immediately stopped, accurately capturing the safe lower limit of the exhaust fan speed. This avoids energy waste caused by excessive speed and prevents safety problems caused by excessively low speed. The control system determines the operating frequency at which frequency reduction stops as the minimum safe operating frequency of the frequency converter, ensuring that the exhaust fan always operates in the optimal "safety-energy saving" range. While ensuring the safe and stable operation of the submerged arc furnace, it effectively reduces energy consumption and operating costs, achieving a dual improvement in safety and economic benefits.

[0020] In a second aspect, embodiments of this application provide a control system comprising: one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code, the computer program code including computer instructions, wherein the one or more processors invoke the computer instructions to cause the control system to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a control system, cause the control system to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a control system, cause the control system to perform the method described in the first aspect and any possible implementation thereof.

[0023] Understandably, the control system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By adopting the above technical solution, the control system simultaneously collects furnace pressure values ​​and furnace surface flame images for multi-dimensional monitoring, providing comprehensive data support for precise flue gas control. The control system dynamically adjusts PID parameters based on real-time changes in the submerged arc furnace during operation, improving the adaptability and flexibility of flue gas control compared to traditional fixed PID parameters. The control system achieves stable adjustment of the flue gas fan speed through a first control signal, ensuring the stability of the smelting process; and achieves rapid response to sudden fire conditions through a second control signal, effectively avoiding safety risks such as fires and material spraying. By integrating dual control signals, the control system combines stable control under normal operating conditions with rapid response under special operating conditions, ensuring both the safety and stability of the submerged arc furnace operation and improving the control accuracy of the flue gas system, while reducing environmental pollution.

[0025] 2. By adopting the above technical solution, a dual-dimensional sudden fire judgment standard of "flame area ratio + flame color deviation index" was constructed, improving the control system's ability to identify and respond quickly to sudden fire conditions. Compared with the single flame area ratio judgment, the flame color deviation index can reflect the intensity of flame combustion (e.g., if the flame color is redder or brighter during a fire, the flame color deviation index will change significantly), further improving the accuracy of the condition judgment and effectively avoiding misjudgments caused by factors such as light interference. When both the flame area ratio and the flame color deviation index meet the preset sudden fire condition judgment conditions, a second control signal is generated to rapidly increase the exhaust fan speed. This can quickly increase the exhaust force in the early stage of a sudden fire, promptly expelling excess gas and flame from the furnace, significantly reducing the probability of fire expansion, material spraying, and other safety accidents. This provides key risk control protection for the safe operation of the electric arc furnace and makes up for the shortcomings of traditional pressure control in responding to sudden conditions.

[0026] 3. By adopting the above technical solution, the control system constructs preset frequency reduction trigger conditions for multiple parameters (furnace pressure, filter inlet temperature, and carbon monoxide concentration), ensuring that frequency reduction operation is only carried out under the premise of stable system operation and no safety risks, thus avoiding the risk of fire caused by blind frequency reduction. During the frequency reduction process, the control system continuously monitors the flame image on the furnace surface. When the flame area ratio exceeds the critical value or the flame color deviation index exceeds the critical value, the frequency reduction is immediately stopped, accurately capturing the safe lower limit of the exhaust fan speed. This avoids energy waste caused by excessive speed and prevents safety problems caused by excessively low speed. The control system determines the operating frequency at which frequency reduction is stopped as the minimum safe operating frequency of the frequency converter, ensuring that the exhaust fan always operates in the optimal range of "safety-energy saving". While ensuring the safe and stable operation of the submerged arc furnace, it effectively reduces energy consumption and operating costs, achieving a dual improvement in safety and economic benefits. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating an intelligent control method for purifying tail gas from a submerged arc furnace, as described in an embodiment of this application. Figure 2 This is another flowchart illustrating the intelligent control method for purifying tail gas from a submerged arc furnace, as described in this application. Figure 3 This is a schematic diagram of the physical device structure of a control system in an embodiment of this application. Detailed Implementation

[0028] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0030] The following describes the process of the method provided in this implementation. Please refer to [link / reference]. Figure 1 This is a flowchart illustrating an intelligent control method for purifying tail gas from a submerged arc furnace, as described in this application.

[0031] S101. Real-time acquisition of furnace pressure value and furnace surface flame image of electric arc furnace. The furnace pressure value is used to reflect the gas pressure state inside the electric arc furnace, and the furnace surface flame image is used to reflect the combustion state and flame situation of the electric arc furnace surface. Among them, the submerged arc furnace refers to a large industrial equipment used for smelting ferroalloys, industrial silicon and other products; the furnace pressure value refers to a numerical parameter reflecting the gas pressure state inside the submerged arc furnace; the furnace surface flame image refers to a digital image reflecting the combustion state of the furnace surface; the combustion state refers to the degree of combustion of the material on the furnace surface, the flame distribution and other characteristics; the flameout situation is used to indicate the abnormal flame leakage phenomenon on the furnace surface.

[0032] Specifically, the control system continuously collects furnace pressure values ​​at preset sampling intervals (usually milliseconds) using pressure sensors installed at specific locations within the submerged arc furnace. Simultaneously, the control system uses an industrial camera mounted on top of the furnace to capture real-time images of the furnace flames at a preset frame rate (usually 25-30 frames per second). The collected furnace pressure values ​​are preprocessed, such as by filtering, and then converted to pressure values ​​in standard units. The collected furnace flame images are preprocessed to maintain their original resolution and RGB color space format.

[0033] S102. Based on the furnace pressure value and the furnace flame image, adjust the current PID parameters to change response PID parameters; Among them, PID parameters represent the key control parameters in the proportional-integral-derivative controller; current PID parameters refer to the PID parameters currently used by the control system, including the current proportional coefficient, current integral time, and current derivative time; variable response PID parameters refer to the new PID parameters dynamically adjusted according to the current operating conditions, including the variable response proportional coefficient, variable response integral time, and variable response derivative time.

[0034] Specifically, the control system can calculate the total number of pixels (width × height) based on the width and height of the flame image on the furnace surface. For example, if the resolution of the image captured by the industrial camera on the top of the submerged arc furnace is 1920 × 1080, then the total number of pixels is 2,073,600. The control system sets preset flame pixel judgment conditions. For example, when the R channel value of a pixel is >150, the G channel value is >100, and the B channel value is <50, the pixel is determined to be a flame pixel. The number of flame pixels that meet the preset flame pixel judgment conditions is counted to obtain the flame pixel count. The control system calculates the flame area ratio using the flame area ratio calculation formula ((flame pixel count / total pixel count) × 100%). Based on multiple continuously acquired furnace surface flame images, the control system calculates the rate of change of the flame area ratio and uses this rate of change as the flame area change rate. The control system calculates the furnace pressure fluctuation rate based on multiple continuously acquired furnace pressure values.

[0035] The control system substitutes the flame area change rate and furnace pressure fluctuation rate into a preset PID parameter dynamic correction function to obtain new proportional coefficient, integral time, and derivative time of the change response. These new PID parameters comprehensively consider the dynamic characteristics of the current operating conditions, enabling more precise and timely smoke exhaust control.

[0036] PID parameter dynamic correction functions include proportional coefficient correction function, integral time correction function, and derivative time correction function: The proportional coefficient correction function is: Kp'=Kp×(1+α×(Fd / ΔP-C); The integral time correction function is: Ti' = Ti × (1 - β × (Fd / ΔP - C)); The differential time correction function is: Td'=Td×(1+γ×(Fd / ΔP-C)); Wherein, Kp' represents the proportional coefficient of the change response, Ti' represents the integral time of the change response, Td' represents the derivative time of the change response, Kp represents the current proportional coefficient, Ti represents the current integral time, Td represents the current derivative time, Fd represents the flame area change rate, ΔP represents the furnace pressure fluctuation rate, α, β, and γ represent preset positive correction coefficients, and C represents the preset reference constant.

[0037] When Fd / ΔP>C, it means that the flame change is "too intense" relative to the pressure fluctuation, and the system has potential disturbance. At this time, (Fd / ΔP-C) is positive, Kp' and Td' increase, and Ti' decreases, allowing the adjustment to become more "aggressive" to quickly suppress the disturbance.

[0038] When Fd / ΔP<C, it means that the pressure fluctuation is "too intense" relative to the flame change, and the system may have been in an oscillating state. At this time, (Fd / ΔP-C) is negative, Kp' and Td' decrease, and Ti' increases, allowing the adjustment to become more "conservative" to avoid aggravating oscillation.

[0039] When Fd / ΔP=C, the system is in an ideal equilibrium state, and the PID parameters can remain unchanged.

[0040] Alternatively, under general circumstances, adjusting the current PID parameters to change response PID parameters based on the furnace pressure value and the furnace surface flame image can be implemented in the following manner, which is not limited herein: counting the total number of pixels and the number of flame pixels in the furnace surface flame image, determining the ratio of the number of flame pixels to the total number of pixels as the flame area proportion, wherein the number of flame pixels refers to the number of pixel points that meet the preset flame pixel judgment condition; determining the flame area change rate according to the flame area proportion and continuously collected furnace surface flame images; determining the furnace pressure fluctuation rate according to continuously collected furnace pressure values; substituting the flame area change rate and the furnace pressure fluctuation rate into the PID parameter dynamic correction function to obtain a change response proportional coefficient, a change response integration time and a change response derivative time; combining the change response proportional coefficient, the change response integration time and the change response derivative time to obtain the change response PID parameters, and adjusting the current PID parameters to the change response PID parameters.

[0041] A specific example is listed below to illustrate the PID parameter adjustment process. Assuming that at a certain moment, a furnace surface flame image with a resolution of 1920×1080 is collected, the total number of pixels is calculated to be 2073600, and after RGB channel analysis, the number of flame pixels that meet the preset flame pixel judgment condition (R>150, G>100, B<50) is 414720, from which it is calculated that flame area proportion=(414720 / 2073600)×100%=20%; The flame area proportion data of the previous 10 frames are: [18%, 18.5%, 19%, 19.2%, 19.4%, 19.5%, 19.6%, 19.8%, 19.9%, 20%]; Flame area change rate Fd=(20%-18%) / (10 frames×0.04 seconds / frame)=5% / second; The average value of the latest 100 furnace pressure values is -10Pa, and the standard deviation is 0.5Pa; Pressure fluctuation rate ΔP = 0.5Pa / 10Pa = 5%; Current PID parameters: The current scaling factor Kp = 1.0; The current integration time Ti = 2.0 seconds; The current differential time Td = 0.5 seconds; Positive value correction factor setting: α = 0.5 (proportional coefficient correction factor); β = 0.3 (integral time correction factor); γ = 0.4 (differential time correction factor); C=1.0 (preset baseline constant); Substitute the PID parameters into the dynamic correction function for calculation: Fd / ΔP=5% / 5%=1; Kp'=Kp×(1+α×(Fd / ΔP-C))=1.0×(1+0.5×(1-1))=1.0; Ti' = Ti × (1 - β × (Fd / ΔP - C)) = 2.0 × (1 - 0.3 × (1 - 1)) = 2.0 seconds; Td' = Td × (1 + γ × (Fd / ΔP - C)) = 0.5 × (1 + 0.4 × (1 - 1)) = 0.5 seconds; In this example, since the ratio of the flame area change rate to the furnace pressure fluctuation rate is exactly equal to the preset reference constant, it indicates that the system is in a relatively stable state. The calculated change response PID parameters are the same as the current PID parameters and do not need to be adjusted.

[0042] Assuming the rate of change of flame area increases to 10% / second, then Fd / ΔP = 10% / 5% = 2; Kp'=1.0×(1+0.5×(2-1))=1.5; Ti'=2.0×(1-0.3×(2-1))=1.4 seconds; Td'=0.5×(1+0.4×(2-1))=0.7 seconds; At this time, due to the rapid changes in the flame, the system automatically increases the proportional coefficient and derivative time to speed up the response and reduces the integral time to avoid integral saturation, making the smoke and fire control more timely and effective.

[0043] S103. Based on the deviation between the furnace pressure value and the preset furnace pressure value, the variable response PID parameters are used for calculation to generate a first control signal that smoothly adjusts the speed of the exhaust fan. Among them, the preset furnace pressure value refers to the desired pressure value set in advance; the first control signal refers to the output signal used to smoothly adjust the speed of the exhaust fan; the exhaust fan refers to the power equipment used to exhaust the waste gas in the furnace; and the speed refers to the rotational speed of the exhaust fan.

[0044] Specifically, firstly, the deviation between the control system's furnace pressure value and the preset furnace pressure value is measured. Then, the control system substitutes this deviation and the newly adjusted PID response parameters into the PID control quantity calculation formula u(t) = Kp[e(t) + 1 / Ti∫e(t)dt + Td×de(t) / dt] to calculate the PID control quantity. The control system then converts the PID control quantity into a speed adjustment signal for the exhaust fan, i.e., the first control signal, through a mapping function. This process considers the instantaneous value, cumulative value, and trend of the deviation, enabling smooth adjustment of the exhaust fan speed.

[0045] Optionally, under normal circumstances, the first control signal for smoothly adjusting the exhaust fan speed can be generated by using the variable response PID parameters to calculate based on the deviation between the furnace pressure value and the preset furnace pressure value. This can be achieved in the following way, without limitation: input the deviation and variable response PID parameters to the PID control quantity calculation formula, and output the PID control quantity; map the PID control quantity to the exhaust fan speed adjustment quantity to obtain the first control signal for smoothly adjusting the exhaust fan speed; the PID control quantity calculation formula is: u(t) = Kp[e(t) + 1 / Ti∫e(t)dt + Td×de(t) / dt]; where u(t) represents the PID control quantity, Kp represents the variable response proportional coefficient, Ti represents the variable response integral time, Td represents the variable response derivative time, e(t) represents the deviation, and t represents the sampling time.

[0046] The following is a specific example illustrating the generation process of the first control signal. Assume that at a certain moment: 1. Pressure-related parameters: Preset furnace pressure: -15Pa (negative pressure); Current furnace pressure: -12 Pa; Deviation e(t) = -12Pa - (-15Pa) = +3Pa (pressure is too high); Sampling period: 0.1 seconds; Deviations over the past 5 sampling points: [2.8 Pa, 2.9 Pa, 2.95 Pa, 2.98 Pa, 3 Pa]; 2. PID parameters for variable response (obtained from step S102): Kp = 1.5 (proportional response coefficient). Ti = 1.4 seconds (integral time of change response); Td = 0.7 seconds (differential time of change response); 3. PID control quantity calculation: Proportional term calculation: P term = Kp × e(t) = 1.5 × 3 = 4.5; Integral calculation: Cumulative integral value = (2.8 + 2.9 + 2.95 + 2.98 + 3) × 0.1 = 1.463; I term=Kp×(1 / Ti)×1.463=1.5×(1 / 1.4)×1.463=1.57; Differential calculation: The rate of change of the deviation between the two most recent two deviations = (3 - 2.98) / 0.1 = 0.2 Pa / second; Option D = Kp × Td × 0.2 = 1.5 × 0.7 × 0.2 = 0.21; PID control quantity: u(t) = P term + I term + D term = 4.5 + 1.57 + 0.21 = 6.28; 4. Mapping transformation: Assuming the exhaust fan's speed range is 0-1500 rpm, and the current speed is 900 rpm, the mapping relationship is as follows: The PID control range [-10, +10] corresponds to the exhaust fan speed adjustment [-300rpm, +300rpm]. Mapping formula: Exhaust fan speed adjustment = PID control quantity × 30; The exhaust fan speed adjustment is calculated as follows: Exhaust fan speed adjustment = 6.28 × 30 = +188.4 rpm; 5. Generation of the first control signal: The target speed of the exhaust fan = the current speed of the exhaust fan + the speed adjustment amount of the exhaust fan = 900 + 188.4 = 1088.4 rpm. The 1088.4 rpm is used as the first control signal output.

[0047] S104. Process the furnace flame image and extract flame feature parameters. When the flame feature parameters meet the preset sudden flameout judgment conditions, generate a second control signal to quickly increase the speed of the exhaust fan. Among them, flame characteristic parameters refer to quantitative indicators used to describe the flame state; preset sudden fire condition judgment conditions refer to the combination of threshold conditions used to determine abnormal fire conditions; and the second control signal refers to the emergency control command issued for sudden fire conditions.

[0048] Specifically, firstly, the control system extracts the pixel matrices of the R, G, and B channels from the flame image on the furnace surface, and calculates the pixel mean of each channel to obtain the pixel mean of the R channel, the pixel mean of the G channel, and the pixel mean of the B channel. The control system then substitutes the pixel mean of the R channel, the pixel mean of the G channel, and the pixel mean of the B channel into the flame color deviation index calculation formula ((R channel mean - G channel mean) / B channel mean) to obtain the flame color deviation index.

[0049] When the flame area ratio is greater than a preset percentage (e.g., 10%) and the flame color deviation index is greater than a preset value (e.g., 1.2), the control system determines that a sudden fire has occurred and triggers a second control signal to rapidly increase the speed of the exhaust fan. This second control signal is usually 120% of the rated speed of the exhaust fan.

[0050] Optionally, under normal circumstances, the flame image on the furnace surface is processed to extract flame feature parameters. When the flame feature parameters meet the preset sudden flameout condition judgment conditions, a second control signal to rapidly increase the speed of the exhaust fan can be generated in the following way, which is not limited here: Extract the pixel values ​​of the R channel, G channel, and B channel from the flame image on the furnace surface, and calculate the average pixel values ​​of the R channel, G channel, and B channel; substitute the average pixel values ​​of the R channel, G channel, and B channel into the flame color deviation index calculation formula to obtain the flame color deviation index; if both the flame area ratio and the flame color deviation index meet the preset sudden flameout condition judgment conditions, a second control signal to rapidly increase the speed of the exhaust fan is generated.

[0051] S105, the first control signal and the second control signal are combined and sent to the frequency converter of the smoke exhaust fan.

[0052] Here, fusion refers to combining control signals from different sources according to a specific strategy; frequency converter refers to power electronic equipment used to regulate the speed of exhaust fans.

[0053] Specifically, first, the control system checks the validity of the two control signals to ensure that the signal values ​​are within a reasonable range. Then, the control system automatically adjusts the weighting coefficients of the two control signals according to the current operating conditions. Under normal operating conditions, the first control signal has a larger weight (e.g., 0.8), while under sudden operating conditions, the second control signal has a larger weight (e.g., 0.9). The control system multiplies the two control signals by their corresponding weights and sums them to obtain the comprehensive output control signal. Finally, the control system converts this output control signal into the target operating frequency of the frequency converter (usually within the 0-50Hz range) through a preset mapping relationship and sends the frequency command to the frequency converter for execution via an industrial communication protocol (such as Modbus).

[0054] Optionally, under normal circumstances, the frequency converter that integrates the first control signal and the second control signal and sends them to the exhaust fan can be implemented in the following way, which is not limited here: the first control signal and the second control signal are weighted according to a preset weight to obtain the output control signal; the target operating frequency of the exhaust fan frequency converter is calculated based on the output control signal, and the target operating frequency is sent to the frequency converter for execution.

[0055] Preset weights refer to the importance coefficients of different control signals in the fusion process; output control signals refer to the final instructions sent to the frequency converter after fusion; target operating frequency is used to represent the frequency value expected to be output by the frequency converter; weighted operation represents the mathematical calculation process performed according to the weights.

[0056] By adopting the above technical solution, the control system simultaneously collects furnace pressure values ​​and furnace surface flame images for multi-dimensional monitoring, providing comprehensive data support for precise flue gas control. The control system dynamically adjusts PID parameters based on real-time changes in the submerged arc furnace during operation, improving the adaptability and flexibility of flue gas control compared to traditional fixed PID parameters. The control system achieves stable adjustment of the flue gas fan speed through a first control signal, ensuring the stability of the smelting process; and achieves rapid response to sudden fire conditions through a second control signal, effectively avoiding safety risks such as fires and material spraying. By integrating dual control signals, the control system combines stable control under normal operating conditions with rapid response under special operating conditions, ensuring both the safety and stability of the submerged arc furnace operation and improving the control accuracy of the flue gas system, while reducing environmental pollution.

[0057] The following provides a more detailed description of the process of the method provided in this implementation. Please refer to [link / reference]. Figure 2 This is another flowchart illustrating the intelligent control method for purifying tail gas from a submerged arc furnace in this application.

[0058] The following steps may or may not be performed after step S105; this is not limited here: S201. Real-time acquisition of filter inlet temperature and carbon monoxide concentration.

[0059] Among them, filter inlet temperature refers to the temperature at the filter inlet in the flue gas purification system; carbon monoxide concentration is used to represent the percentage of carbon monoxide in the exhaust gas; real-time acquisition refers to the process of continuously acquiring data at a preset frequency.

[0060] Specifically, the control system uses a thermocouple temperature sensor installed at the filter inlet to collect the filter inlet temperature at 1-second intervals, with a measurement range typically of 0-500℃; at the same time, the control system uses an infrared CO gas analyzer installed at the exhaust outlet to continuously monitor the carbon monoxide concentration, with a measurement range typically of 0-30%.

[0061] S202. If the furnace pressure, filter inlet temperature, and carbon monoxide concentration all meet the preset frequency reduction trigger conditions, the inverter's operating frequency will be gradually reduced at the preset frequency reduction rate, and the furnace flame image will be continuously acquired during the frequency reduction process.

[0062] Among them, the preset frequency reduction trigger condition represents the combination of judgment criteria for starting the frequency reduction operation of the frequency converter; the preset frequency reduction rate refers to the speed at which the frequency converter reduces its operating frequency; and the frequency reduction process refers to the time period during which the operating frequency of the frequency converter gradually decreases.

[0063] Specifically, first, the control system determines whether the furnace pressure is below 80% of the preset furnace pressure, whether the filter inlet temperature is below 150℃, and whether the carbon monoxide concentration is below 10%. When these conditions are met simultaneously, a frequency reduction operation is triggered. The control system gradually reduces the inverter's operating frequency according to the preset frequency reduction rate (usually 0.5Hz / s), while simultaneously acquiring a furnace flame image every 50ms.

[0064] S203. When the flame image on the furnace surface shows that the flame area ratio exceeds the critical value of the area ratio or the flame color deviation index exceeds the critical value of the color deviation index, stop reducing the frequency.

[0065] Among them, the area ratio critical value refers to the safe upper limit of the flame area ratio; the color deviation index critical value refers to the warning threshold of the flame color deviation index; and stop frequency reduction means interrupting the frequency reduction process of the frequency converter.

[0066] Specifically, the control system analyzes each frame of the furnace flame image in real time, calculating the flame area ratio and flame color deviation index. When the flame area ratio exceeds the critical value (usually 25%) or the flame color deviation index exceeds the critical value (usually 1.2), the control system determines that continuing to reduce the frequency may lead to an unsafe condition, and immediately sends a stop frequency reduction command to the frequency converter to maintain the current output frequency unchanged.

[0067] S204. The operating frequency at which frequency reduction stops is determined as the minimum safe operating frequency of the frequency converter.

[0068] Among them, the minimum safe operating frequency represents the minimum inverter output frequency that guarantees the safe operation of the system; the operating frequency when frequency reduction stops refers to the actual frequency value when frequency reduction is triggered to stop; the operating frequency is used to represent the actual operating frequency value of the inverter output.

[0069] Specifically, the control system records the actual output frequency of the inverter when the frequency reduction is triggered, sets this actual output frequency as the system's minimum safe operating frequency, and stores it in the control system's parameter database. The minimum safe operating frequency can be dynamically updated as operating conditions change, but each update requires a complete frequency reduction test process.

[0070] The control system in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference needed]. Figure 3 This is a schematic diagram of the physical device structure of the control system in an embodiment of this application.

[0071] It should be noted that, Figure 3 The structure of the control system shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0072] like Figure 3 As shown, the control system includes a CPU 301, which can perform various appropriate actions and processes based on a program stored in the read-only memory ROM 302 or a program loaded from the storage section 308 into the random access memory RAM 303, such as executing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0073] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including a hard disk, etc.; and communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0074] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by CPU 301, it performs the various functions defined in the present invention.

[0075] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0076] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0077] Specifically, the control system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the intelligent control method for purifying tail gas of the blast furnace provided in the above embodiment.

[0078] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the control system described in the above embodiments; or it may exist independently and not be assembled into the control system. The storage medium carries one or more computer programs, which, when executed by a processor of the control system, cause the control system to implement the intelligent control method for purifying the tail gas of the ferroalloy furnace provided in the above embodiments.

[0079] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0080] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0081] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for intelligent control of tail gas purification in a submerged arc furnace, characterized in that, The method, applied to a control system, includes: real-time acquisition of the furnace pressure value and furnace surface flame image of a submerged arc furnace, wherein the furnace pressure value reflects the gas pressure state inside the furnace, and the furnace surface flame image reflects the combustion state and flame emission of the furnace surface; counting the total number of pixels and the number of flame pixels in the furnace surface flame image, and determining the ratio of the number of flame pixels to the total number of pixels as the flame area ratio; determining the flame area change rate based on the flame area ratio and continuously acquired furnace surface flame images; determining the furnace pressure fluctuation rate based on continuously acquired furnace pressure values; and substituting the deviation of the ratio of the flame area change rate to the furnace pressure fluctuation rate from a preset reference constant into a PID parameter dynamic correction function. The variable response proportional coefficient, variable response integral time, and variable response derivative time are obtained from the data, and combined to obtain variable response PID parameters. The current PID parameters are adjusted to the variable response PID parameters. Based on the deviation between the furnace pressure value and the preset furnace pressure value, the variable response PID parameters are used to generate a first control signal to smoothly adjust the exhaust fan speed. The furnace flame image is processed to extract flame feature parameters. When the flame feature parameters meet the preset sudden flameout judgment conditions, a second control signal to rapidly increase the exhaust fan speed is generated. The first control signal and the second control signal are weighted and fused according to preset weights and sent to the frequency converter of the exhaust fan.

2. The method according to claim 1, characterized in that, The dynamic correction function for PID parameters includes a proportional coefficient correction function, an integral time correction function, and a derivative time correction function: the proportional coefficient correction function is: Kp'=Kp×(1+α×(Fd / ΔP-C)); the integral time correction function is: Ti'=Ti×(1-β×(Fd / ΔP-C)); the derivative time correction function is: Td'=Td×(1+γ×(Fd / ΔP-C)); where Kp' represents the proportional coefficient of the change response, Ti' represents the integral time of the change response, Td' represents the derivative time of the change response, Kp represents the current proportional coefficient, Ti represents the current integral time, Td represents the current derivative time, Fd represents the flame area change rate, ΔP represents the furnace pressure fluctuation rate, α, β, and γ represent preset positive correction coefficients, and C represents a preset reference constant.

3. The method according to claim 1, characterized in that, The method of calculating the first control signal for smoothly adjusting the exhaust fan speed based on the deviation between the furnace pressure value and the preset furnace pressure value using the variable response PID parameters specifically includes: inputting the deviation and the variable response PID parameters into the PID control quantity calculation formula, and outputting the PID control quantity; mapping the PID control quantity to the exhaust fan speed adjustment quantity to obtain the first control signal for smoothly adjusting the exhaust fan speed; the PID control quantity calculation formula is: u(t) = Kp[e(t) + 1 / Ti∫e(t)dt + Td×de(t) / dt]; where u(t) represents the PID control quantity, Kp represents the variable response proportional coefficient, Ti represents the variable response integral time, Td represents the variable response derivative time, e(t) represents the deviation, and t represents the sampling time.

4. The method according to claim 1, characterized in that, The process of processing the furnace flame image to extract flame feature parameters, and generating a second control signal to rapidly increase the exhaust fan speed when the flame feature parameters meet the preset sudden fire condition judgment conditions, specifically includes: extracting the pixel values ​​of the R channel, G channel, and B channel from the furnace flame image, and calculating the average pixel values ​​of the R channel, G channel, and B channel; substituting the average pixel values ​​of the R channel, G channel, and B channel into the flame color deviation index calculation formula to obtain the flame color deviation index; and generating the second control signal to rapidly increase the exhaust fan speed when both the flame area ratio and the flame color deviation index meet the preset sudden fire condition judgment conditions.

5. The method according to claim 1, characterized in that, The step of weighting and fusing the first control signal and the second control signal according to a preset weight and sending them to the frequency converter of the exhaust fan specifically includes: performing a weighted operation on the first control signal and the second control signal according to a preset weight to obtain an output control signal; calculating the target operating frequency of the frequency converter of the exhaust fan according to the output control signal, and sending the target operating frequency to the frequency converter for execution.

6. The method according to claim 1, characterized in that, After the step of sending the inverter to the exhaust fan, the method further includes: real-time acquisition of filter inlet temperature and carbon monoxide concentration; if the furnace pressure, filter inlet temperature, and carbon monoxide concentration all meet the preset frequency reduction trigger conditions, the operating frequency of the inverter is gradually reduced at a preset frequency reduction rate, and furnace flame images are continuously acquired during the frequency reduction process; when the furnace flame image shows that the flame area ratio exceeds the area ratio threshold or the flame color deviation index exceeds the color deviation index threshold, the frequency reduction is stopped; the operating frequency at which the frequency reduction is stopped is determined as the minimum safe operating frequency of the inverter.

7. A control system, characterized in that, The control system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the control system to perform the method as described in any one of claims 1 to 6.

8. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on the control system, the control system performs the method as described in any one of claims 1 to 6.

9. A computer program product, characterized in that, When the computer program product is run on the control system, the control system performs the method as described in any one of claims 1 to 6.

Images