Intelligent control method of zinc ash-containing tail gas purification system

Abstract

The invention discloses an intelligent control method of a zinc ash-containing tail gas purification system, which relates to the technical field of tail gas purification systems, and comprises the following steps of: firstly, continuously monitoring a condensation process of high-temperature zinc-containing steam in a cooler through a monitoring device, and collecting zinc steam condensation conditions and particle generation data of tail gas under different temperature and pressure states in real time; according to the invention, intelligent monitoring, signal analysis, machine learning identification and dynamic regulation and control are combined to realize accurate control of the zinc-ash-containing tail gas purification system. Key features are extracted through real-time monitoring and data preprocessing, intelligent recognition of particle concentration is achieved based on feature vectors and machine learning, the rotating speed of the centrifugal separator is adjusted in a self-adaptive mode, and efficient separation and system stability are ensured by linkage with pulse back-blowing dust removal. Compared with a traditional fixed rotating speed mode, the tail gas purification efficiency is improved, the maintenance cost is reduced, the service life of equipment is prolonged, the automatic operation capacity is enhanced, and the system is kept in the optimal working state during load fluctuation.

Description

Technical Field

[0001] The present invention relates to the technical field of tail gas purification systems, and particularly to an intelligent control method for a zinc ash-containing tail gas purification system. Background Art

[0002] The intelligent control of a zinc ash-containing tail gas purification system refers to the realization of efficient and precise management of the furnace gas purification process based on technologies such as automatic sensing, real-time monitoring, and intelligent regulation, so as to ensure the stable operation of the purification system and optimize energy efficiency. This system integrates multi-parameter on-line monitoring devices such as oxygen content, dew point, and hydrogen content, collects the purification effect of furnace gas in real time, and combines a pressure sensor, a variable-frequency fan controller, and an automatic ash discharge system to perform intelligent regulation through a PLC (programmable logic controller) or a DCS (distributed control system). When the system detects that the oxygen content or dew point exceeds the set threshold, it can automatically adjust the fan boost, filter switching, or start the purge mode to avoid a decrease in purification efficiency or system blockage. In addition, the variable-frequency regulation of the fan can dynamically adjust the air volume according to the real-time furnace pressure fluctuation to ensure the stability of the furnace pressure and prevent gas leakage or excessive air supply. At the same time, the system has an automatic / manual ash cleaning function, which can trigger the ash cleaning process when the filtration resistance increases to ensure long-term stable operation. All operating states, fault alarms, and historical data can be visually displayed through an HMI (human-machine interface) or a remote monitoring platform to achieve unattended operation, adaptive optimization, and intelligent operation and maintenance, improving the reliability of the system and production efficiency.

[0003] The prior art has the following deficiencies:

[0004] In the prior art, when a centrifugal separator is used to remove large-particle zinc ash from zinc ash-containing tail gas, a fixed rotation speed is usually used for separation, that is, a fixed rotation speed is preset to separate the large-particle zinc ash in the zinc ash-containing tail gas. However, when the zinc ash particle concentration in the tail gas significantly increases, the fixed rotation speed cannot adjust the centrifugal force in a timely and automatic manner, resulting in a large number of zinc ash particles not being effectively thrown out and thus entering the subsequent filtration device. This will significantly increase the blockage frequency of the filtration device, cause the filter element to be quickly blocked and frequently replaced, seriously reduce the service life of the filtration device, and greatly increase the equipment maintenance cost, reducing the economy and stability of the operation of the entire system.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and therefore it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The objective of the present invention is to provide an intelligent control method for a zinc ash tail gas purification system, which combines intelligent monitoring, signal analysis, machine learning recognition, and dynamic regulation to achieve precise control of the zinc ash tail gas purification system. By means of real-time monitoring and data preprocessing, key features are extracted. Based on the feature vectors and machine learning, intelligent recognition of particle concentration is realized, the rotation speed of the centrifugal separator is adjusted adaptively, and pulse reverse blowing for dust cleaning is carried out in parallel to ensure efficient separation and system stability. Compared with the traditional fixed rotation speed method, the present invention improves the tail gas purification efficiency, reduces the maintenance cost, extends the equipment life, and enhances the automatic operation ability, enabling the system to maintain the best working state under load fluctuations, so as to solve the problems in the above-mentioned background technology.

[0007] To achieve the above objective, the present invention provides the following technical solution: An intelligent control method for a zinc ash tail gas purification system, comprising the following steps:

[0008] Firstly, through a monitoring device, continuously monitor the condensation process of high-temperature zinc vapor in the cooler, and collect in real time the zinc vapor condensation situation and particle generation data of the tail gas under different temperature and pressure states;

[0009] Preprocess the obtained real-time monitoring data of zinc vapor condensation, and adopt a signal analysis method to extract key features from the purified real-time data that reflect the increasing trend of zinc ash particle concentration;

[0010] Deeply analyze the extracted key features to form a feature vector reflecting the current fluctuation state of zinc ash particle concentration, and quantify the dynamic fluctuation characteristics of zinc ash particle concentration;

[0011] Input the generated feature vector into a pre-trained machine learning model to determine whether there is a significant increasing trend in the current zinc ash particle concentration;

[0012] When the machine learning model real-time recognizes that the zinc ash particle concentration significantly increases, according to the amplitude of the increase in particle concentration, dynamically increase the rotation speed of the centrifugal separator to increase the rotor speed to increase the centrifugal force. At the same time, start pulse reverse blowing for dust cleaning, and through high-frequency and short-period pulsed air flow blowing, remove the zinc ash particles that rapidly accumulate inside the filter unit due to the sudden increase in particle concentration, preventing rapid blockage on the surface and inside of the filter element.

[0013] Preferably, the specific steps of collecting in real time the zinc vapor condensation situation and particle generation data of the tail gas under different temperature and pressure states through a monitoring device are as follows:

[0014] Firstly, deploy high-precision sensors at the internal and key pipeline positions of the cooler, including but not limited to temperature sensors, pressure sensors, humidity sensors, and laser particle sensors, for continuously collecting the condensation data of high-temperature zinc vapor;

[0015] When high-temperature zinc-containing vapor enters the cooler, as the temperature gradually decreases, the zinc vapor gradually condenses into solid zinc ash. The sensor will record in real time the condensation rate, particle concentration, particle diameter distribution, and gas transmittance changes of the tail gas under different temperature and pressure conditions;

[0016] All data are collected at high frequency through the data acquisition module, and time synchronization marks are used to ensure the time consistency of each data stream;

[0017] Finally, all monitoring data are stored in the central control system, serving as the basis for subsequent intelligent identification of the zinc ash particle concentration fluctuation trend and providing accurate data support for dynamic regulation.

[0018] Preferably, a signal analysis method is used to extract key features reflecting the increasing trend of zinc ash particle concentration from the purified real-time data. The extracted features include the scale change of the airflow turbulence structure and the nucleation rate of steam condensation to form solid particles. The scale change of the airflow turbulence structure and the nucleation rate of steam condensation to form solid particles are analyzed under the detection window to generate a reference value for the scale offset of the turbulent vortex and a reference value for the change rate of the average particle charge respectively. The dynamic fluctuation characteristics of the zinc ash particle concentration are quantified through the reference value for the scale offset of the turbulent vortex and the reference value for the change rate of the average particle charge.

[0019] Preferably, the specific steps for analyzing the scale change of the airflow turbulence structure under the detection window to generate a reference value for the scale offset of the turbulent vortex are as follows:

[0020] Under the detection window, first, the turbulence structure in the airflow is decomposed using the turbulence energy spectrum analysis and scale decomposition method to obtain the vortex characteristics at different scales. The wavelet packet decomposition is used to decompose the turbulent velocity field, and a local scale energy function is constructed to capture the vortex change patterns at different scales in the airflow. The local scale energy distribution of the turbulent velocity vector field is calculated, and the calculation expression is as follows:

[0021]

[0022] , where E s is the local turbulent energy at scale s, Ω is the spatial integration region, W n，s (x, y, z) is the nth wavelet packet decomposition coefficient at scale s in the three-dimensional space coordinates (x, y, z), α is the non-linear scaling exponent, and N is the wavelet decomposition order;

[0023] After obtaining the local turbulent energy E s at scale s, the reference value for the scale offset of the turbulent vortex is calculated to quantify the degree of abnormal scale offset of the turbulence. The contribution of scale s to the overall turbulence structure is characterized by defining a scale energy offset function, and the calculation expression is as follows:

[0024]

[0025] , where Φ(s) is the scale energy offset function, which is used to describe the contribution of different scales s to the overall turbulent structure, S is the set of all scales, representing all scale ranges S' divided in the wavelet decomposition, and ∑ S'∈S E S' is the total turbulent energy at all scales, representing the total turbulent energy at all scales S', and W s (x, y, z) is the wavelet decomposition coefficient of scale s in the three-dimensional space coordinates (x, y, z). is the high-order gradient of the turbulent velocity field, β is the turbulent nonlinear diffusion exponent, and γ is the exponent adjustment factor, which is used to adjust the weight of the high-order gradient term;

[0026] Based on the scale energy offset function Φ(s), calculate the reference value of the overall turbulent eddy scale offset, and the calculation expression is as follows:

[0027]

[0028] , where TESSI is the reference value of the turbulent eddy scale offset, and ε is a small positive number to avoid mathematical singularities when the scale approaches zero.

[0029] Preferably, the specific steps for analyzing the nucleation rate of steam condensation to form solid particles under the detection window to generate the reference value of the average charge change rate of particles are as follows:

[0030] First, calculate the instantaneous particle collision charge transfer rate, which is used to measure the charge exchange rate caused by particle collision and aggregation in a high-concentration environment after steam condensation forms solid particles. The calculation expression of the instantaneous particle collision charge transfer rate is as follows:

[0031]

[0032] , where Q c is the instantaneous particle collision charge transfer rate, ε0 is the vacuum permittivity, E is the local electrostatic field strength, A p is the average surface area of the particles, is the exponential decay factor, which describes the degree of reduction of the single-particle charge exchange rate when the particle concentration N p increases, e is the natural base, ω is the empirical adjustment parameter, K p is the particle kinetic energy, is the kinetic energy influence factor, which is used to adjust the influence degree of the kinetic energy on the charge exchange rate, F c is the Coulomb force between particles, which describes the electrostatic force between charged particles, λ is the correction factor for the influence of particle concentration, and θ is the adjustment parameter of the concentration exponent term;

[0033] Obtain the instantaneous particle collision charge transfer rate Q c After that, calculate the reference value of the average particle charge change rate to quantify the net charge growth trend of particles within the entire detection window. The calculation formula is as follows:

[0034]

[0035] , where PMCVI is the reference value of the average particle charge change rate, μ is the spatial region within the detection window, η is the charge exchange efficiency factor between particles, is the power scaling of the instantaneous particle collision charge transfer rate, δ reflects the non-linear growth of the particle charge exchange rate, is the potential inhibition factor, σ is the adjustment parameter, φ p is the particle surface potential, e is the natural logarithm base, ρ p is the particle mass density, is the local pressure gradient of the particle, ψ is the particle charge polarization influence factor, τ p is the particle polarization relaxation time, κ is the non-linear scaling exponent of the polarization relaxation time, used to adjust the influence degree of the polarization relaxation time on the overall charge change, is the high-concentration correction factor, ξ represents the exponential influence of the particle concentration on the correction term, v is the high-concentration correction factor.

[0036] Preferably, input the analyzed reference value of the turbulent eddy scale offset and the reference value of the average particle charge change rate into a pre-trained machine learning model. Generate the zinc ash particle concentration risk coefficient through the machine learning model, and judge whether the current zinc ash particle concentration shows a significant upward trend based on the zinc ash particle concentration risk coefficient.

[0037] Preferably, compare the zinc ash particle concentration risk coefficient generated when judging whether the current zinc ash particle concentration shows a significant upward trend through a pre-trained machine learning model with the pre-set reference threshold of the zinc ash particle concentration risk coefficient to judge whether the current zinc ash particle concentration shows a significant upward trend. The specific process is as follows:

[0038] If the zinc ash particle concentration risk coefficient is greater than the pre-set reference threshold of the zinc ash particle concentration risk coefficient, it is judged that the current zinc ash particle concentration shows a significant upward trend; if the zinc ash particle concentration risk coefficient is less than the pre-set reference threshold of the zinc ash particle concentration risk coefficient, it is judged that the current zinc ash particle concentration does not show an upward trend.

[0039] Preferably, when the machine learning model real-time recognizes that the concentration of zinc ash particles has significantly increased, according to the amplitude of the increase in particle concentration, the rotation speed of the centrifugal separator is dynamically increased to increase the rotor speed and centrifugal force. At the same time, pulse backwashing and dust cleaning are started. Through high-frequency and short-cycle pulsed air flow blowing, the specific steps for removing the zinc ash particles that have rapidly accumulated inside the filter unit due to the sudden increase in particle concentration are as follows:

[0040] When the machine learning model real-time recognizes that the concentration of zinc ash particles has significantly increased, immediately adjust the rotation speed of the centrifugal separator to enhance the centrifugal force and improve the particle separation efficiency. The dynamic adjustment speed calculation expression is as follows:

[0041]

[0042] , where Δω is the centrifugal separator speed adjustment increment, A is the centrifugal force gain coefficient, ZAPCR is the zinc ash particle concentration risk coefficient, ZAPCR thr is the zinc ash particle concentration risk coefficient reference threshold, e is the natural base, H is the non-linear adjustment exponent, R is the exponent adjustment parameter, κ i is the weight coefficient, indicating the contribution of the historical time window i to the current adjustment. n is the number of historical detection windows, is the weighted historical zinc ash particle concentration risk coefficient, indicating the weighted value of the zinc ash particle concentration risk coefficient at each moment in the past i time windows, and is adjusted using the square root exponent i / 2. δ i is the adjustment stability parameter;

[0043] After adjusting the centrifugal separator speed, at the same time start pulse backwashing and dust cleaning to ensure that the zinc ash particles that have entered the filter unit will not quickly accumulate due to the sudden increase in concentration and cause blockage. The frequency calculation expression for pulse backwashing is as follows:

[0044]

[0045] , where f p is the adjusted pulse backwashing frequency, f p0 is the initial flow scanning frequency, E is the frequency gain adjustment coefficient, D is the adjustment smoothing coefficient, B is the exponent adjustment parameter, m is the historical detection window size, indicating the historical detection window size used to calculate the pulse blowing frequency, μ j is the influence degree of the jth historical detection window on the current blowing frequency calculation, is the exponential decay term, θ j is the exponential decay factor, used to control the influence degree of the past zinc ash particle concentration risk coefficient on the current pulse blowing frequency, φ j is the feedback adjustment sensitivity parameter;

[0046] Calculate the backflush air flow pressure, and the calculation expression is as follows:

[0047]

[0048] , where P p is the adjusted pulse jetting pressure, P p0 is the initial jetting pressure, T is the pressure adjustment gain coefficient, X is the non-linear adjustment index, and L is the pressure response sensitivity control parameter;

[0049] After completing the calculation of the rotational speed adjustment increment Δω of the centrifugal separator, the adjusted pulse backflush frequency f p and the adjusted pulse jetting pressure P p , establish a closed-loop feedback control, and continuously optimize the centrifugal separation and pulse dust cleaning strategies to ensure the dynamic stability under different concentration states. The adjustment calculation expression of the real-time feedback control is as follows:

[0050]

[0051] , where K adj is the adjustment coefficient, which determines the correction amount of the rotational speed and backflush frequency in the next cycle, ζ is the feedback adjustment gain coefficient, U is the non-linear adjustment index to control the change range, G is the flow weight coefficient, Q is the flow rate, ψ f is the weight of the f-th time window, and v f is the smoothing adjustment factor.

[0052] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0053] The present invention realizes the precise control of the zinc ash tail gas purification system through a method combining intelligent monitoring, signal analysis, machine learning recognition and dynamic regulation, and significantly improves the efficient separation ability and system stability of zinc ash particles. First, by using real-time monitoring and data preprocessing technologies, key features that can accurately reflect the concentration fluctuation trend of zinc ash particles are obtained and extracted to ensure the high precision and real-time nature of the data; second, based on the feature vectors, machine learning intelligent recognition is constructed to realize the adaptive judgment of the change trend of particle concentration, avoiding the problem that the traditional fixed rotational speed method cannot adapt to dynamic load changes; finally, through the dynamic adjustment of the rotational speed of the centrifugal separator and the pulse backflush linkage dust cleaning, when the particle concentration rises abnormally, the separation efficiency is rapidly increased and the filter unit is prevented from being blocked, thereby greatly reducing the maintenance frequency and improving the operation life and energy efficiency of the purification system. The intelligent control method of the present invention effectively overcomes the problem that the fixed rotational speed centrifugal separator in the prior art is difficult to adjust when the particle load fluctuates, enables the tail gas purification system to have a higher automation level and operation reliability, reduces the equipment maintenance cost while improving the overall efficiency of tail gas purification. Description of the Drawings

[0054] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0055] Figure 1 It is a method flow chart of the intelligent control method for the zinc ash tail gas purification system of the present invention. Specific embodiments

[0056] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

[0057] The present invention provides an intelligent control method for the zinc ash tail gas purification system as shown in Figure 1 and includes the following steps:

[0058] First, through a monitoring device, continuously monitor the condensation process of high-temperature zinc-containing steam in the cooler, and collect in real time the zinc steam condensation situation and particle generation data of the tail gas under different temperature and pressure conditions;

[0059] Use a monitoring device (such as a temperature sensor, a pressure sensor, a humidity sensor, a laser particle sensor, etc.) to continuously and real-time monitor the condensation process of high-temperature zinc-containing steam in the cooler, and collect the steam condensation situation and zinc ash particle generation data of the tail gas under different temperature and pressure conditions. In the cooler, as the temperature of the high-temperature zinc-containing steam decreases, it will gradually condense into solid zinc ash, and the rate, particle size, and particle concentration of the condensation process are affected by factors such as temperature gradient, pressure fluctuation, and gas flow rate. Therefore, by real-time monitoring these key physical parameters, the condensation dynamics of zinc steam can be accurately grasped, and the formation trend and concentration change of particles can be analyzed. The main function of this step is to establish a real-time database of tail gas particle generation, provide high-precision and continuous original data support for subsequent intelligent identification of zinc ash particle concentration fluctuations, ensure that the entire tail gas purification system can accurately perceive and adapt to the real-time changes of zinc ash particle concentration, and improve the intelligent regulation ability of the system.

[0060] The specific steps of collecting in real time the zinc steam condensation situation and particle generation data of the tail gas under different temperature and pressure conditions through the monitoring device are as follows:

[0061] First, deploy high-precision sensors inside the cooler and at key pipeline locations, including temperature sensors, pressure sensors, humidity sensors, laser particle sensors, or optical scattering particle concentration detectors, for continuously collecting condensation data of high-temperature zinc-containing vapor. When the high-temperature zinc-containing vapor enters the cooler, as the temperature gradually decreases, the zinc vapor gradually condenses into solid zinc ash, and the sensors will record in real time the condensation rate, particle concentration, particle diameter distribution, and gas transmittance changes of the tail gas under different temperature and pressure conditions. All data are collected at high frequency through a data acquisition module (DAQ), and time synchronization marks are used to ensure the time consistency of each data stream. Finally, all monitoring data are stored in the central control system, serving as the basis for subsequent intelligent identification of the zinc ash particle concentration fluctuation trend and providing accurate data support for the dynamic adjustment of the system.

[0062] Preprocess the real-time monitoring data of zinc vapor condensation obtained, and use signal analysis methods (such as Fourier transform, wavelet analysis, or empirical mode decomposition, etc.) to extract key features from the purified real-time data that reflect the increasing trend of zinc ash particle concentration;

[0063] Preprocess the real-time data of zinc vapor condensation obtained by the monitoring device, and use signal analysis methods to extract key features that can accurately reflect the changes in zinc ash particle concentration. Since real-time monitoring data usually contain a large amount of noise and irrelevant information, such as environmental interference, measurement errors, or system fluctuations, it is necessary to denoise and smooth the data to ensure the accuracy of the analysis. After the preprocessing is completed, signal analysis techniques such as Fourier transform, wavelet analysis, or empirical mode decomposition (EMD) are used to identify hidden patterns in the data. Through these methods, the characteristic signals representing the increase in zinc ash particle concentration can be accurately extracted and converted into quantifiable characteristic parameters. The main role of this step is to extract core information from complex original monitoring data, accurately reflect the change trend of zinc ash particle concentration, provide high-quality input data for subsequent intelligent identification and control systems, ensure that the centrifugal separation system can respond in real time to fluctuations in particle concentration, and improve the purification efficiency and system stability.

[0064] Deeply analyze the extracted key features to form a feature vector reflecting the current zinc ash particle concentration fluctuation state, and quantify the dynamic fluctuation characteristics of the zinc ash particle concentration;

[0065] A signal analysis method is used to extract key features reflecting the increasing trend of zinc ash particle concentration from the purified real-time data. The extracted features include the scale change of the airflow turbulence structure and the nucleation rate of steam condensation to form solid particles. The scale change of the airflow turbulence structure and the nucleation rate of steam condensation to form solid particles are analyzed under the detection window to generate a reference value for the offset of the turbulent eddy scale and a reference value for the change rate of the average particle charge respectively. The dynamic fluctuation characteristics of the zinc ash particle concentration are quantified by the reference value of the offset of the turbulent eddy scale and the reference value of the change rate of the average particle charge.

[0066] The abnormal decrease in the scale of the airflow turbulence structure indicates an abnormal increase in the concentration during the current zinc ash particle condensation process. The core reason lies in the influence of high-concentration particles on the turbulent energy dissipation and the change of their particle transport behavior. Under normal circumstances, the eddy scale of the turbulence remains within a reasonable range. Larger-scale vortex structures can promote the uniform diffusion of zinc vapor in the airflow, enabling it to stably condense into solid particles and facilitating the uniform distribution and settlement of the particles. However, when the zinc ash particle concentration increases abnormally, a large number of particles collide and aggregate with each other and have a strong interaction with the airflow, resulting in the more rapid dissipation of the kinetic energy of the turbulence, causing the large-scale vortices to quickly split into small-scale vortices, and ultimately leading to a decrease in the turbulent eddy scale of the airflow. The direct consequence of this phenomenon is that the suspension time of the particles in the airflow is prolonged, the particle density in the local area further increases, forming higher-concentration particle clusters, and these particle clusters are difficult to be efficiently thrown out by the conventional centrifugal separator, thus increasing the burden on the subsequent filtration system. In addition, the abnormal decrease in the turbulence scale will also affect the transport capacity of the airflow, making the particles in some areas more concentrated, forming a local high-concentration zinc ash area, and further exacerbating the abnormal enrichment of the particles. Therefore, when the turbulent eddy scale decreases abnormally, it can be used as a key feature signal for the abnormal increase in particle concentration, and the system needs to timely adjust the operating parameters (such as increasing the speed of the centrifugal separator or optimizing the filtration mode) to maintain the stable operation of the system.

[0067] The specific steps for analyzing the scale change of the airflow turbulence structure under the detection window to generate a reference value for the offset of the turbulent eddy scale are as follows:

[0068] Under the detection window, first, the turbulence structure in the airflow is decomposed using the turbulence energy spectrum analysis and scale decomposition method to obtain the vortex characteristics at different scales. The wavelet packet decomposition (WPD) is used to decompose the turbulent velocity field, and a local scale energy function is constructed to capture the vortex change patterns at different scales in the airflow. The local scale energy distribution of the turbulent velocity vector field is calculated, and the calculation expression is as follows:

[0069]

[0070] , where E sis the local turbulent energy at scale s, Ω is the spatial integration region for calculating the overall turbulent energy contribution of the airflow within a specific window, W n，s (x, y, z) is the nth wavelet packet decomposition coefficient at scale s on the three-dimensional spatial coordinates (x, y, z), α is the non-linear scaling exponent, usually taken as α > 1 to emphasize the contribution of high-energy regions and make it more sensitive to abnormal turbulent changes, N is the wavelet decomposition order, representing the decomposition order used during the wavelet packet decomposition process;

[0071] The role of the above steps is: to extract the turbulent energy distribution at different scales through non-uniform scale analysis, avoiding the limitations of traditional mean processing, especially suitable for capturing local energy abnormal aggregation regions. In the case of increasing particle concentration, the vortex structure tends to smaller scales, resulting in W n，s (x, y, z) having an abnormally increased proportion at small scales, ultimately causing E s to deviate significantly at low scales, forming a characteristic signal of abnormally increased particle concentration.

[0072] After obtaining the local turbulent energy E at scale s s , calculate the reference value of the turbulent vortex scale offset, quantify the degree of abnormal offset of the turbulent scale, and characterize the contribution of scale s to the overall turbulent structure by defining a scale energy offset function. The calculation expression is as follows:

[0073]

[0074] , where Φ(s) is the scale energy offset function, used to describe the contribution of different scales s to the overall turbulent structure, measure the proportion of local energy at the current scale and its high-order change characteristics, S is the set of all scales, representing all scale ranges S' divided in the wavelet decomposition, ∑ S'∈S E S' is the total turbulent energy at all scales, representing the total turbulent energy at all scales S', serving as a normalization factor to make the scale energy E s participate in the calculation in the form of a ratio, W s (x, y, z) is the wavelet decomposition coefficient of scale s under the three-dimensional spatial coordinates (x, y, z), is the high-order gradient of the turbulent velocity field, representing the higher-order derivative of the turbulent velocity field at scale s in the x direction of space, used to measure the complexity of the local structure of the turbulence, β is the turbulent non-linear diffusion exponent, enhancing the sensitivity to changes in vortex intensity, γ is the exponent adjustment factor, used to adjust the weight of the high-order gradient term to balance the contributions between different scales;

[0075] Based on the scale energy offset function Φ(s), calculate the reference value of the overall turbulent vortex scale offset. The calculation expression is as follows:

[0076]

[0077] , where TESSI is the reference value of the turbulent eddy scale offset, and ε is a small positive number to avoid mathematical singularities when the scale approaches zero.

[0078] The larger the reference value of the turbulent eddy scale offset generated after analyzing the scale change of the airflow turbulent structure under the detection window, the more it indicates that the concentration of zinc ash particles abnormally increases during the current condensation process. On the contrary, if the reference value shows a small or stable value, it indicates that the concentration of zinc ash particles during the current condensation process is within the normal range. The core principle is that when the particle concentration increases, it will intensify the dissipation of turbulent energy, break the large-scale turbulent structure into more small-scale vortices, thus causing the eddy scale to shift and tend to the small-scale structure. When the reference value of the turbulent eddy scale offset rises, it means that the dominant eddy scale in the airflow turbulent structure significantly decreases in a short time, indicating an increase in the particle load in the airflow, an enhancement of the mutual collision and agglomeration effects between particles, resulting in particle aggregation and a local concentration surge. This change will directly lead to a decrease in the particle sedimentation velocity, an increase in the filtration system load, and even problems such as filter clogging. Therefore, under the monitoring window, by analyzing the scale change of the airflow turbulent structure, if the reference value of the turbulent eddy scale offset shows a significant increase, timely control measures should be taken, such as increasing the rotational speed of the centrifugal separator or enhancing the dust cleaning ability of the filtration system, to prevent a decrease in system efficiency and an increase in maintenance costs. On the contrary, if the reference value of the turbulent eddy scale offset remains within the normal range, it indicates that the current zinc ash particle concentration is stable, the airflow turbulent structure has not changed abnormally, and the purification system is operating well.

[0079] The sudden increase in the nucleation rate of steam condensation to form solid particles usually indicates an abnormal increase in concentration during the current zinc ash particle condensation process. The main reason is that the sharp increase in the nucleation rate means that the number of initial zinc ash particles generated per unit time far exceeds the normal level, resulting in a rapid increase in particle concentration. When steam enters the cooler and undergoes a supercooling process, if the local temperature drops suddenly or the steam supersaturation suddenly increases, it will cause a large amount of zinc vapor to condense rapidly in a short time, forming extremely dense tiny particles. This abnormal high nucleation rate will lead to a reference - level increase in the number of particles, significantly increasing the particle load in the airflow, and thus affecting subsequent particle sedimentation, transport, and separation. Especially when the airflow velocity is high or the turbulence is enhanced, a large number of newly formed particles cannot be effectively separated and will continue to be suspended in the airflow, forming a high - concentration zinc ash area, ultimately increasing the burden on the downstream filtration system. In addition, the particles formed under a high nucleation rate tend to have a smaller particle size and a larger surface area, which makes them more likely to agglomerate and form more complex particle aggregates, thus increasing the risk of filter clogging. Therefore, when the nucleation rate suddenly rises, it means that the particle concentration is already in an abnormally high state, and the system needs to promptly adjust the rotational speed of the centrifugal separator or optimize the cooling strategy to prevent excessive accumulation of zinc ash in the system, affecting the purification efficiency and equipment stability.

[0080] The specific steps for analyzing the nucleation rate of steam condensation to form solid particles under a detection window to generate a reference value of the average charge change rate of particles are as follows:

[0081] First, calculate the instantaneous particle collision charge transfer rate, which is used to measure the charge exchange rate caused by particle collision and aggregation in a high - concentration environment after steam condensation to form solid particles. The calculation expression of the instantaneous particle collision charge transfer rate is as follows:

[0082]

[0083] where Q c is the instantaneous particle collision charge transfer rate, ε0 is the vacuum permittivity, which characterizes the charge influence coefficient of particles in the air medium, E is the local electrostatic field strength, related to the particle charging situation, A p is the average particle surface area, which determines the interaction ability between the particle and the gas environment. is the exponential decay factor, which describes the degree of reduction of the single - particle charge exchange rate when the particle concentration N p increases, e is the natural base, ω is the empirical adjustment parameter, K p is the particle kinetic energy, which describes the kinetic energy of the particle in gas turbulence and determines the collision frequency between particles. is the kinetic energy influence factor, which is used to adjust the influence degree of kinetic energy on the charge exchange rate, F cis the Coulomb force between particles, describing the electrostatic force between charged particles. λ is the correction factor for the influence of particle concentration, used to correct the effect of the Coulomb force in a high-concentration environment. θ is the adjustment parameter of the concentration exponent term, used to describe the non-linear relationship between particle concentration and the Coulomb force F c ;

[0084] After obtaining the instantaneous particle collision charge transfer rate Q c , calculate the reference value of the average particle charge change rate to quantify the net charge growth trend of particles within the entire detection window. The calculation expression is as follows:

[0085]

[0086] , where PMCVI is the reference value of the average particle charge change rate, μ is the spatial region within the detection window, that is, the effective range for the system to monitor the change in zinc ash particle concentration, η is the charge exchange efficiency factor between particles, depending on the dielectric properties of the particle material, is the power scaling of the instantaneous particle collision charge transfer rate, and δ reflects the non-linear growth of the particle charge exchange rate, is the potential inhibition factor, σ is the adjustment parameter, φ p is the particle surface potential, reflecting the adsorption / rejection effect of the charge carried by the particle on the newly generated charge, e is the natural base, ρ p is the particle mass density, is the local pressure gradient of the particle, describing the non-uniform distribution of particles in gas flow. ψ is the particle charge polarization influence factor, τ p is the particle polarization relaxation time, indicating the time required for the charge to reach a stable state after the particle is affected by an external electric field. κ is the non-linear scaling exponent of the polarization relaxation time, used to adjust the influence degree of the polarization relaxation time on the overall charge change, is the high-concentration correction factor, ξ represents the exponential influence of particle concentration on the correction term, and v is the high-concentration correction factor.

[0087] The larger the reference value of the average particle charge change rate generated by analyzing the nucleation rate of steam condensation to form solid particles under the detection window, the more it indicates that the concentration of zinc ash particles has increased abnormally during the current condensation process. Conversely, it indicates that the particle concentration is at a normal level. This is because during the process of steam condensation to form solid particles, particles will undergo charge accumulation and transfer due to factors such as collision, adhesion, and surface interaction. When the nucleation rate increases abnormally, the number of particles generated within a short time surges, resulting in a significant increase in the chance of particle collision and aggregation, thereby accelerating the charge exchange on the particle surface and causing the reference value of the average particle charge change rate to rise sharply. In a high-particle-concentration environment, the electrostatic repulsion between particles is enhanced, making it more difficult for them to settle and easier to suspend in the air flow, further exacerbating the burden on the downstream filtration system.

[0088] Input the generated feature vectors into a pre-trained machine learning model to determine whether there is a significant upward trend in the current zinc ash particle concentration;

[0089] Input the analyzed reference value of the turbulent eddy scale offset and the reference value of the particle average charge change rate into a pre-trained machine learning model. Generate the zinc ash particle concentration risk coefficient through the machine learning model, and determine whether there is a significant upward trend in the current zinc ash particle concentration based on the zinc ash particle concentration risk coefficient.

[0090] The pre-trained machine learning model refers to a model that is offline trained with a large amount of historical data, experimental data, and simulation data before actual operation. This model can learn and identify the change patterns of zinc ash particle concentration, and perform intelligent prediction and classification on the real-time input data during the actual production process. In this solution, the reference value of the turbulent eddy scale offset and the reference value of the particle average charge change rate are two important characteristic parameters, which can reflect the changes in the airflow turbulent structure and the electrostatic interaction between particles. These factors are crucial for the condensation, aggregation, and separation of zinc ash particles. However, analyzing the change of a single parameter alone is often not sufficient to accurately judge whether the particle concentration abnormally increases. Therefore, it is necessary to use a machine learning model to perform correlation analysis on multiple characteristic parameters and generate the zinc ash particle concentration risk coefficient through pattern recognition technology to achieve more accurate prediction of concentration changes. The main role of the pre-trained machine learning model is to learn the law of particle concentration increase, construct a multi-dimensional feature space of concentration change, be able to identify the trend of abnormal concentration in real time and efficiently during actual operation, and provide decision support so that the system can take dynamic adjustment measures, such as adjusting the rotation speed of the centrifugal separator or triggering the pulse backblow mode.

[0091] To build an efficient and accurate prediction model for zinc ash particle concentration, a large amount of historical monitoring data needs to be collected first, including data under normal operating conditions and data when the concentration abnormally increases, to ensure that the model can cover all possible operating conditions. This data usually contains multiple variables, such as the reference value of the turbulent vortex scale offset, the reference value of the change rate of the average particle charge, the attenuation rate of gas transmittance, the particle aggregation rate, etc., and preprocessing such as data cleaning, noise reduction, and standardization needs to be carried out to improve the data quality. Then, a suitable machine learning algorithm is selected for training, such as Support Vector Machine (SVM), Random Forest, Long Short-Term Memory Neural Network (LSTM), or Deep Neural Network (DNN). By continuously iterating and optimizing the model parameters, the prediction accuracy is improved. During the training process, the model will learn the change trend of zinc ash particle concentration, extract implicit features, and establish a mapping relationship between the input parameters and the concentration risk coefficient. After training, the model will be deployed to a real-time monitoring system and dynamic prediction will be carried out using real-time input data of the reference value of the turbulent vortex scale offset and the reference value of the change rate of the average particle charge to calculate the zinc ash particle concentration risk coefficient. If the risk coefficient exceeds the set safety threshold, it indicates that the particle concentration is significantly increasing, and the system needs to take corresponding control measures to prevent filter clogging or the failure of the tail gas purification system. Through this pre-trained machine learning model, the intelligent level of zinc ash particle concentration monitoring can be greatly improved, achieving accurate prediction and dynamic optimization control, and ensuring the long-term stable and efficient operation of the system.

[0092] The machine learning model is not limited here. Any machine learning model that can comprehensively analyze the reference value of the turbulent vortex scale offset (TESSI) and the reference value of the change rate of the average particle charge (PMCVI) to generate the zinc ash particle concentration risk coefficient (ZAPCR) can be used. To implement the technical solution of the present invention, the present invention provides a specific implementation solution;

[0093] The formula for generating the zinc ash particle concentration risk coefficient (ZAPCR) is as follows: ZAPCR = k1·TESSI + k2·PMCVI, where k1 and k2 are the preset proportionality coefficients of the reference value of the turbulent vortex scale offset (TESSI) and the reference value of the change rate of the average particle charge (PMCVI) respectively, and both k1 and k2 are greater than 0.

[0094] The preset proportionality coefficients refer to the weighting factors used to measure the influence degrees of the turbulent eddy scale deviation reference value TESSI and the particle mean charge variation rate reference value PMCVI on the zinc ash particle concentration risk coefficient ZAPCR, namely k1 and k2 in the formula. The main function of these coefficients is to determine the weights of the turbulent eddy scale deviation reference value TESSI and the particle mean charge variation rate reference value PMCVI in the calculation of ZAPCR according to historical data, experimental results or models trained by machine learning, ensuring that the risk assessment can more accurately reflect the real changes in particle concentration. For example, if the change in the turbulent structure has a greater impact on particle concentration, the value of k1 should be higher; conversely, if the change in charge has a more significant impact on particle aggregation behavior, k2 should be dominant. These preset proportionality coefficients are usually determined by regression analysis, optimization algorithms or neural network training, and may be dynamically adjusted according to different working conditions to optimize the prediction accuracy and response ability of the system.

[0095] From the zinc ash particle concentration risk coefficient, it can be seen that the larger the turbulent eddy scale deviation reference value generated by analyzing the scale change of the air flow turbulent structure under the detection window, and the larger the particle mean charge variation rate reference value generated by analyzing the nucleation rate of steam condensation to form solid particles under the detection window, the larger the zinc ash particle concentration risk coefficient generated when judging whether the current zinc ash particle concentration shows a significant upward trend through a pre-trained machine learning model, indicating that the concentration of zinc ash particles abnormally increases during the current condensation process of zinc ash particles; on the contrary, it indicates that the current zinc ash particle concentration is stable.

[0096] Compare the zinc ash particle concentration risk coefficient generated when judging whether the current zinc ash particle concentration shows a significant upward trend through a pre-trained machine learning model with the pre-set zinc ash particle concentration risk coefficient reference threshold to judge whether the current zinc ash particle concentration shows a significant upward trend. The specific process is as follows:

[0097] If the zinc ash particle concentration risk coefficient is greater than the pre-set zinc ash particle concentration risk coefficient reference threshold, it is judged that the current zinc ash particle concentration shows a significant upward trend; if the zinc ash particle concentration risk coefficient is less than the pre-set zinc ash particle concentration risk coefficient reference threshold, it is judged that the current zinc ash particle concentration does not show an upward trend.

[0098] When the machine learning model real-time identifies a significant increase in the zinc ash particle concentration, according to the amplitude of the increase in particle concentration, dynamically increase the rotational speed of the centrifugal separator to increase the rotor speed to increase the centrifugal force. At the same time, start pulse backwashing and cleaning. Through high-frequency and short-period pulsed air flow blowing, remove the zinc ash particles that quickly accumulate inside the filter unit due to the sudden increase in particle concentration, preventing the surface and inside of the filter element from being quickly blocked;

[0099] When the concentration of zinc ash particles rises abnormally, the system's rapid response is achieved by dynamically adjusting the rotational speed of the centrifugal separator and pulse backblowing for cleaning, ensuring effective particle separation, preventing the filtration unit from being overloaded, and maintaining the stable operation of the entire purification system. When the machine learning model detects that the particle concentration exceeds the set threshold, it means that the large accumulation of zinc ash particles in the tail gas has exceeded the normal operating conditions. If the separation and cleaning strategies are not adjusted in a timely manner, it may lead to the rapid blockage of the subsequent filtration system, increase the system resistance, and ultimately affect the tail gas purification efficiency and even cause system failure. Therefore, in this step, first, according to the amplitude of the increase in particle concentration, the rotational speed of the centrifugal separator is dynamically increased. The rotational speed of the rotor is adjusted by frequency conversion drive to make the particles in the airflow subject to a stronger centrifugal force, ensuring that more large particles are effectively thrown out and reducing the dust load entering the filtration unit. At the same time, the pulse backblowing cleaning mode is triggered. Through high-frequency and short-cycle pulse air jet blowing, the zinc ash particles inside the filtration unit are quickly cleaned, causing the particles adhering to the surface of the filter material to fall off, preventing the particles from accumulating inside the filtration unit, and avoiding the formation of filter blockage. The core purpose of this step is to build an intelligent adaptive adjustment mechanism to ensure that when the particle concentration changes suddenly, the system can automatically optimize its operating state, improve the purification efficiency, and reduce the equipment maintenance cost and downtime risk. Through the linkage control of the rotational speed of the centrifugal separator and pulse backblowing for cleaning, it is ensured that the tail gas treatment system is always in an efficient and stable working state, effectively preventing problems such as equipment damage, filtration failure, or excessive tail gas emissions caused by a sudden increase in particle concentration.

[0100] When the machine learning model real-time identifies a significant increase in the concentration of zinc ash particles, according to the amplitude of the increase in particle concentration, the rotational speed of the centrifugal separator is dynamically increased to increase the rotational speed of the rotor to increase the centrifugal force. At the same time, the pulse backblowing for cleaning is started. Through high-frequency and short-cycle pulsed air jet blowing, the specific steps for removing the zinc ash particles that have rapidly accumulated inside the filtration unit due to a sudden increase in particle concentration are as follows:

[0101] When the machine learning model real-time identifies a significant increase in the concentration of zinc ash particles, the rotational speed of the centrifugal separator is immediately adjusted to enhance the centrifugal force and improve the particle separation efficiency. The dynamic adjustment rotational speed calculation expression is as follows:

[0102]

[0103] , where Δω is the rotational speed adjustment increment of the centrifugal separator, indicating the additional rotational speed required for the centrifugal separator after detecting an abnormal increase in the concentration of zinc ash particles. A is the centrifugal force gain coefficient, used to adjust the overall amplitude of Δω and determine the maximum response ability of the rotational speed adjustment. ZAPCR is the zinc ash particle concentration risk coefficient, ZAPCR thris the reference threshold of the zinc ash particle concentration risk coefficient, e is the natural base, H is the non-linear adjustment index, which controls the sensitivity of the control system to the change of zinc ash concentration and makes the adjustment process smoother. R is the exponential adjustment parameter, which is used to control the non-linear relationship in the calculation of Δω and affects the adjustment curvature of the rotational speed, κ i is the weight coefficient, which represents the contribution of the historical time window i to the current adjustment. n is the number of historical detection windows, which is used to calculate the data window quantity of historical influence and represents the time range within which the system considers the past change trend of zinc ash particle concentration. is the weighted historical zinc ash particle concentration risk coefficient, which represents the weighted value of the zinc ash particle concentration risk coefficient at each moment in the past i time windows and is adjusted by the square root exponent i / 2, δ i is the adjustment stability parameter, which prevents the adjustment amount from surging excessively;

[0104] Effect:

[0105] It can effectively increase the rotational speed of the centrifuge separator in a short time, enhance the particle separation ability; reduce the probability of large particles entering the subsequent filtering device and lower the blockage risk.

[0106] After adjusting the rotational speed of the centrifuge separator, start the pulse backflush cleaning at the same time to ensure that the zinc ash particles that have entered the filtering unit will not accumulate rapidly due to the sudden increase in concentration and cause blockage. The calculation expression of the pulse backflush frequency is as follows:

[0107]

[0108] , where f p is the adjusted pulse backflush frequency, f p0 is the initial flow rate scanning frequency, E is the frequency gain adjustment coefficient, D is the adjustment smoothing coefficient to prevent excessive fluctuation in a short time, B is the exponential adjustment parameter to control the non-linearity of frequency growth, m is the size of the historical detection window, which represents the size of the historical detection window used to calculate the pulse jetting frequency, that is, when calculating the current jetting frequency, consider the zinc ash particle concentration data in the past m time steps, μ j is the influence degree of the jth historical detection window on the calculation of the current jetting frequency, is the exponential decay term, which is used to perform exponential decay on the historical zinc ash particle concentration risk coefficient so that the influence of the concentration data in the more distant past on the current decision gradually decreases, θ j is the exponential decay factor, which is used to control the influence degree of the past zinc ash particle concentration risk coefficient on the current pulse jetting frequency, φ j is the feedback adjustment sensitivity parameter, which controls the response speed of the jetting frequency to the historical concentration change;

[0109] Calculate the backflush air flow pressure, and the calculation formula is as follows:

[0110]

[0111] , where P p is the adjusted pulse injection pressure, P p0 is the initial injection pressure, T is the pressure adjustment gain coefficient, X is the non-linear adjustment index, and L is the pressure response sensitivity control parameter;

[0112] Effect:

[0113] The pulse backflush frequency is adaptively adjusted according to the increase in concentration to improve the dust cleaning efficiency;

[0114] Appropriately increase the injection pressure to enhance the cleaning effect and avoid the rapid deposition of particles inside the filter unit;

[0115] Ensure that the system can maintain long-term stable operation under high-concentration load.

[0116] After calculating the rotational speed adjustment increment Δω of the centrifugal separator, the adjusted pulse backflush frequency f p and the adjusted pulse injection pressure P p establish a closed-loop feedback control to continuously optimize the centrifugal separation and pulse dust cleaning strategies to ensure dynamic stability under different concentration states. The adjustment calculation formula for real-time feedback control is as follows:

[0117]

[0118] , where K adj is the adjustment coefficient, which determines the correction amount of the rotational speed and backflush frequency in the next cycle, ζ is the feedback adjustment gain coefficient, U is the non-linear adjustment index to control the change range, G is the flow weight coefficient, Q is the flow rate, and ψ f is the weight of the f-th time window, which determines the contribution degree of this historical data in the current calculation, and v f is the smoothing adjustment factor, which controls the smoothing effect of historical data on the current concentration change and avoids too drastic adjustment.

[0119] Effect:

[0120] Form a closed-loop adjustment system to ensure that when the particle concentration changes, the centrifugal separator and the backflush system can be dynamically and adaptively optimized;

[0121] Make the entire purification system have both fast response ability and avoid instability caused by over-adjustment;

[0122] Further reduce equipment loss, improve purification efficiency, and reduce maintenance costs.

[0123] The present invention realizes the precise control of the zinc ash tail gas purification system through a method combining intelligent monitoring, signal analysis, machine learning recognition and dynamic regulation, significantly improving the efficient separation ability of zinc ash particles and the system stability. First, real-time monitoring and data preprocessing technologies are adopted to obtain and extract key features that can accurately reflect the fluctuation trend of zinc ash particle concentration, ensuring the high precision and real-time nature of the data; second, based on the feature vectors, machine learning intelligent recognition is constructed to achieve the adaptive judgment of the change trend of particle concentration, avoiding the problem that the traditional fixed rotation speed method cannot adapt to dynamic load changes; finally, through the dynamic adjustment of the rotation speed of the centrifugal separator and the pulse backblow linkage for dust cleaning, when the particle concentration abnormally increases, the separation efficiency is rapidly improved and the filter unit is prevented from being blocked, thereby greatly reducing the maintenance frequency and increasing the operation life and energy efficiency of the purification system. The intelligent control method of the present invention effectively overcomes the problem that the fixed rotation speed centrifugal separator in the prior art is difficult to adjust when the particle load fluctuates, enables the tail gas purification system to have a higher automation level and operation reliability, and improves the overall efficiency of tail gas purification while reducing the equipment maintenance cost.

[0124] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0125] Only some exemplary embodiments of the present invention have been described by way of illustration above. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0126] It should be noted that in this article, if there are relational terms such as first and second, they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0127] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not imply the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0128] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professionals can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0129] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, the functional units in various embodiments of the present application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0132] As mentioned above, only the specific implementation manners of the present application are described, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0133] Only some exemplary embodiments of the present invention have been described above by way of illustration. Undoubtedly, those of ordinary skill in the art can modify the described embodiments in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. An intelligent control method for a zinc ash tail gas purification system, characterized in that, It includes the following steps: First, through the monitoring device, continuously monitor the condensation process of high-temperature zinc-containing vapor in the cooler, and collect in real time the zinc vapor condensation situation and particle generation data of the tail gas under different temperature and pressure conditions; Preprocess the real-time monitoring data of zinc vapor condensation obtained, and use signal analysis methods to extract key features from the purified real-time data that reflect the increasing trend of zinc ash particle concentration; Deeply analyze the extracted key features to form a feature vector reflecting the current fluctuation state of zinc ash particle concentration, and quantify the dynamic fluctuation characteristics of zinc ash particle concentration; Input the generated feature vector into a pre-trained machine learning model to determine whether there is a significant increasing trend in the current zinc ash particle concentration; When the machine learning model real-time identifies that the zinc ash particle concentration significantly increases, according to the amplitude of the increase in particle concentration, dynamically increase the rotation speed of the centrifugal separator to increase the rotor speed to increase the centrifugal force. At the same time, start pulse backwashing to clean the ash, and through high-frequency and short-cycle pulsed air flow blowing, remove the zinc ash particles that rapidly accumulate inside the filter unit due to the sudden increase in particle concentration, and prevent the surface and inside of the filter element from being quickly blocked.

2. The intelligent control method of the zinc ash-containing tail gas purification system according to claim 1, characterized in that, The specific steps of collecting in real time the zinc vapor condensation situation and particle generation data of the tail gas under different temperature and pressure conditions through the monitoring device are as follows: First, deploy high-precision sensors at key pipeline positions inside the cooler, including but not limited to temperature sensors, pressure sensors, humidity sensors, and laser particle sensors, for continuously collecting the condensation data of high-temperature zinc-containing vapor; When the high-temperature zinc-containing vapor enters the cooler, as the temperature gradually decreases, the zinc vapor gradually condenses into solid zinc ash, and the sensors will record in real time the condensation rate, particle concentration, particle diameter distribution, and gas light transmittance change situation of the tail gas under different temperature and pressure conditions; All data is collected at high frequency through the data acquisition module, and time synchronization tags are used to ensure the time consistency of each data stream; Finally, all monitoring data is stored in the central control system, serving as the basis for subsequent intelligent identification of the zinc ash particle concentration fluctuation trend and providing accurate data support for dynamic adjustment.

3. The intelligent control method of the zinc ash-containing tail gas purification system according to claim 1, characterized in that, Use signal analysis methods to extract key features from the purified real-time data that reflect the increasing trend of zinc ash particle concentration. The extracted features include the scale change of the air flow turbulent structure and the nucleation rate of steam condensation to form solid particles. Analyze the scale change of the air flow turbulent structure and the nucleation rate of steam condensation to form solid particles under the detection window to generate a reference value for the scale offset of turbulent eddies and a reference value for the change rate of the average charge of particles respectively, and quantify the dynamic fluctuation characteristics of zinc ash particle concentration through the reference value for the scale offset of turbulent eddies and the reference value for the change rate of the average charge of particles.

4. The intelligent control method of the zinc ash-containing tail gas purification system according to claim 3, characterized in that, The specific steps of analyzing the scale change of the air flow turbulent structure under the detection window to generate a reference value for the scale offset of turbulent eddies are as follows: Under the detection window, first, the turbulence structure in the airflow is decomposed using the turbulence energy spectrum analysis and scale decomposition method to obtain the vortex characteristics at different scales. The wavelet packet decomposition is used to decompose the turbulence velocity field, and a local scale energy function is constructed to capture the vortex change patterns at different scales in the airflow. The local scale energy distribution of the turbulence velocity vector field is calculated, and the calculation expression is as follows: ， where E s is the local turbulent energy at scale s, Ω is the spatial integration region, and W n，s (x, y, z) is the nth wavelet packet decomposition coefficient at scale s on the three-dimensional spatial coordinates (x, y, z), α is the nonlinear scaling exponent, and N is the wavelet decomposition order; Obtain the local turbulent energy E at scale s s After that, calculate the reference value of the turbulent vortex scale offset, quantify the degree of abnormal offset of the turbulent scale, and characterize the contribution of scale s to the overall turbulent structure by defining a scale energy offset function. The calculation is expressed as follows: ， Where, Φ(s) is the scale energy offset function, which is used to describe the contribution of different scales s to the overall turbulent structure, S is the set of all scales, representing all scale ranges S' divided in the wavelet decomposition, ∑ S'∈S E S' is the total turbulent energy at all scales, representing the total turbulent energy at all scales S', W s (x, y, z) are the wavelet decomposition coefficients of scale s in the three-dimensional space coordinates (x, y, z), is the high-order gradient of the turbulent velocity field, β is the turbulent nonlinear diffusion exponent, and γ is the exponent adjustment factor, which is used to adjust the weight of the high-order gradient term; Based on the scale energy offset function Φ(s), the overall turbulence vortex scale offset reference value is calculated, and the calculation expression is as follows: ， In the formula, TESSI is the turbulence vortex scale offset reference value, and ε is a small positive number to avoid mathematical singularities when the scale approaches zero.

5. The intelligent control method of the zinc ash-containing tail gas purification system according to claim 3, wherein The specific steps for analyzing the nucleation rate of steam condensation to form solid particles under the detection window to generate the reference value of the average charge change rate of particles are as follows: First, calculate the instantaneous particle collision charge transfer rate, which is used to measure the charge exchange rate caused by particle collision and aggregation in a high-concentration environment after steam condensation forms solid particles. The calculation expression of the instantaneous particle collision charge transfer rate is as follows: ， where Q c is the instantaneous particle collision charge transfer rate, ε0 is the vacuum permittivity, E is the local electrostatic field strength, A p is the average particle surface area, is the exponential decay factor, which describes the degree of reduction of the single-particle charge exchange rate when the particle concentration N p increases, e is the natural base, ω is the empirical adjustment parameter, K p is the particle kinetic energy, is the kinetic energy influence factor, which is used to adjust the influence degree of kinetic energy on the charge exchange rate, F c is the Coulomb force between particles, which describes the electrostatic force between charged particles, λ is the correction factor for particle concentration influence, and θ is the adjustment parameter of the concentration exponent term; Obtain the instantaneous particle collision charge transfer rate Q c After that, calculate the reference value of the average charge change rate of the particles to quantify the net charge growth trend of the particles within the entire detection window. The calculation expression is as follows: ， Wherein, PMCVI is the reference value of the average charge change rate of particles, μ is the spatial region within the detection window, η is the charge exchange efficiency factor between particles, is the power scaling of the instantaneous particle collision charge transfer rate, and δ reflects the non-linear growth of the particle charge exchange rate, is the potential inhibition factor, σ is the adjustment parameter, φ p is the surface potential of the particle, e is the natural base, ρ p is the mass density of the particle, is the local pressure gradient of the particle, ψ is the particle charge polarization influence factor, τ p is the particle polarization relaxation time, κ is the non-linear scaling exponent of the polarization relaxation time, which is used to adjust the influence degree of the polarization relaxation time on the overall charge change, is the high-concentration correction factor, ξ represents the exponential influence of the particle concentration on the correction term, and v is the high-concentration correction factor.

6. The intelligent control method of the zinc ash-containing tail gas purification system according to claim 3, characterized in that, The analyzed turbulence vortex scale offset reference value and the reference value of the average charge change rate of particles are input into a pre-trained machine learning model. The zinc ash particle concentration risk coefficient is generated through the machine learning model, and whether the current zinc ash particle concentration shows a significant upward trend is judged based on the zinc ash particle concentration risk coefficient.

7. The intelligent control method of the zinc ash-containing tail gas purification system according to claim 6, characterized in that, The zinc ash particle concentration risk coefficient generated when judging whether the current zinc ash particle concentration shows a significant upward trend through a pre-trained machine learning model is compared with the pre-set reference threshold of the zinc ash particle concentration risk coefficient to judge whether the current zinc ash particle concentration shows a significant upward trend. The specific process is as follows: If the zinc ash particle concentration risk coefficient is greater than the pre-set reference threshold of the zinc ash particle concentration risk coefficient, it is judged that the current zinc ash particle concentration shows a significant upward trend; if the zinc ash particle concentration risk coefficient is less than the pre-set reference threshold of the zinc ash particle concentration risk coefficient, it is judged that the current zinc ash particle concentration does not show an upward trend.

8. The intelligent control method of the zinc ash-containing tail gas purification system according to claim 7, characterized in that, When the machine learning model real-time identifies a significant increase in the zinc ash particle concentration, according to the amplitude of the increase in particle concentration, the rotation speed of the centrifugal separator is dynamically increased to increase the centrifugal force. At the same time, pulse backwashing and dust cleaning are started. The specific steps for removing the zinc ash particles that have rapidly accumulated inside the filter unit due to the sudden increase in particle concentration through high-frequency and short-period pulsed airflows are as follows: When the machine learning model real-time identifies a significant increase in the zinc ash particle concentration, immediately adjust the rotation speed of the centrifugal separator to enhance the centrifugal force and improve the particle separation efficiency. The calculation expression for dynamically adjusting the rotation speed is as follows: ， Where, Δω is the rotational speed adjustment increment of the centrifugal separator, A is the centrifugal force gain coefficient, ZAPCR is the zinc ash particle concentration risk coefficient, and ZAPCR thr is the reference threshold of the zinc ash particle concentration risk coefficient, e is the natural base, H is the nonlinear adjustment exponent, R is the exponent adjustment parameter, κ i is the weight coefficient, representing the contribution of the historical time window i to the current adjustment, and n is the number of historical detection windows. is the weighted historical zinc ash particle concentration risk coefficient, representing the weighted value of the zinc ash particle concentration risk coefficient at each moment in the past i time windows, and is adjusted using the square root exponent i / 2. δ i is the adjustment stability parameter; After adjusting the rotation speed of the centrifugal separator, at the same time start pulse backwashing and dust cleaning to ensure that the zinc ash particles that have entered the filter unit will not quickly accumulate and cause blockage due to the sudden increase in concentration. The calculation expression for the frequency of pulse backwashing is as follows: ， where f p is the adjusted pulse backflush frequency, f p0 is the initial flow rate scanning frequency, E is the frequency gain adjustment coefficient, D is the adjustment smoothing coefficient, B is the exponential adjustment parameter, m is the historical detection window size, indicating the historical detection window size used to calculate the pulse jet frequency, μ j is the influence degree of the j-th historical detection window on the calculation of the current jet frequency, is the exponential decay term, θ j is the exponential decay factor, used to control the influence degree of the risk coefficient of the past zinc ash particle concentration on the current pulse jet frequency, φ j is the feedback adjustment sensitivity parameter; Calculate the backwashing air pressure, and the calculation expression is as follows: ， Where P p is the adjusted pulse jet pressure, P p0 is the initial jet pressure, T is the pressure regulation gain coefficient, X is the nonlinear regulation exponent, and L is the pressure response sensitivity control parameter; Complete the rotational speed adjustment increment Δω of the centrifugal separator, the pulse back-blowing frequency f after adjustment p and the pulse jetting pressure P after adjustment p After calculation, establish a closed-loop feedback control, and continuously optimize the centrifugal separation and pulse dust cleaning strategies to ensure dynamic stability under different concentration states. The adjustment calculation expression of the real-time feedback control is as follows: ， where K adj is the adjustment coefficient, determining the correction amounts of the rotational speed and the backflush frequency in the next cycle, ζ is the feedback adjustment gain coefficient, U is the nonlinear adjustment exponent, controlling the change amplitude, G is the flow weight coefficient, Q is the flow rate, ψ f is the weight of the f-th time window, υ f is the smoothing adjustment factor.

Images