Intelligent desulfurization control method, device, medium and product based on dynamic data

Abstract

An intelligent desulfurization control method, device, medium and product based on dynamic data. In the method, the flue gas flow, SO2 concentration and slurry pH value data at the inlet are first obtained, the effective data are obtained after denoising and outlier processing, and then the time synchronization is realized by adjusting the sliding window length according to the instantaneous change rate of the flue gas flow. Then, combined with the correlation between historical data and desulfurization efficiency, the influence weight of each data on the desulfurization efficiency is obtained, the credibility score is calculated and compared with the threshold value, and the slurry circulating pump flow and limestone slurry supply rate are dynamically adjusted according to the high credibility data. The scheme effectively overcomes the problem of response lag of the traditional static control method, can accurately obtain real-time synchronous data, quantifies the influence of each parameter on the desulfurization efficiency, quickly and accurately adjusts the equipment operation parameters according to the dynamic working condition, and improves the desulfurization control precision and stability.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of industrial flue gas treatment, and particularly relates to an intelligent desulfurization control method and device based on dynamic data, a medium and a product. BACKGROUND

[0002] With the acceleration of industrialization, the emission of sulfur dioxide in industrial flue gas has become one of the main factors of serious environmental pollution. In order to meet the increasingly stringent environmental regulations, flue gas desulfurization technology has been widely used, and the wet flue gas desulfurization technology has become the current mainstream desulfurization method due to its high desulfurization efficiency, mature operation and other advantages. In the wet desulfurization process, by adjusting the slurry circulating pump flow rate and limestone slurry supply rate in the desulfurization tower, the concentration of sulfur dioxide in the flue gas can be effectively reduced.

[0003] In related technologies, in order to solve the problem of wet desulfurization efficiency, a control method based on static parameter setting is usually used. This method controls the flow rate of the slurry circulating pump and the limestone slurry supply rate by using a pre-set fixed value or a proportional relationship to maintain the pH value and the reactant concentration of the slurry. In this method, the control system mainly formulates a parameter setting curve according to historical experience or experimental data, and adjusts the flow rate of the slurry circulating pump and the limestone slurry supply rate to meet the basic requirements of desulfurization.

[0004] However, the static parameter control method of the prior art has obvious response lag problem when facing dynamic working conditions. When the flue gas flow or the concentration of sulfur dioxide changes rapidly, the static parameter setting cannot timely adjust the flow rate of the slurry circulating pump or the limestone slurry supply rate, resulting in that the control system reacts slowly to the working conditions. This hysteresis may cause insufficient desulfurization reaction or excessive supply of slurry, and ultimately affects the desulfurization efficiency and the stable operation of the equipment. SUMMARY

[0005] The present application provides an intelligent desulfurization control method and device based on dynamic data, a medium and a product, which are used to solve the problem of lag in adjusting the flow rate of the slurry circulating pump and the limestone slurry supply under dynamic working conditions, and to adapt to the rapid changes of flue gas flow and sulfur dioxide concentration, thereby improving the control accuracy of desulfurization and the stability of operation.

[0006] In a first aspect, the application provides an intelligent desulfurization control method based on dynamic data, comprising: obtaining flue gas flow, SO2 concentration and slurry pH value data at the inlet of a desulfurization device; performing preprocessing operations on the flue gas flow, SO2 concentration and slurry pH value data to obtain effective data, the preprocessing operations including removing high-frequency noise and processing outliers based on a sliding window; dynamically adjusting the length of the sliding window according to the instantaneous change rate of the flue gas flow in the effective data to obtain time-synchronized flue gas flow, SO2 concentration and slurry pH value; based on the correlation between historical flue gas flow, SO2 concentration, slurry pH value data and actual desulfurization efficiency, combining the time-synchronized flue gas flow, SO2 concentration and slurry pH value, obtaining the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on desulfurization efficiency; calculating the credibility score of the flue gas flow, SO2 concentration and slurry pH value data according to the influence weight; obtaining high-credibility flue gas flow, SO2 concentration and slurry pH value data by comparing the credibility score with a preset credibility threshold; and dynamically adjusting the slurry circulating pump flow and limestone slurry supply rate in the desulfurization device according to the high-credibility flue gas flow, SO2 concentration and slurry pH value data.

[0007] By using the above technical solution, the obtained flue gas flow, SO2 concentration and slurry pH value data are preprocessed to remove high-frequency noise and outliers, eliminate interference factors, and restore the true state of the data. The length of the sliding window is dynamically adjusted based on the instantaneous change rate of the flue gas flow, the window is shortened when the working condition changes dramatically to quickly capture data characteristics, and the window is lengthened when the working condition is stable to enhance data stability, adaptively adjust the data processing period, and ensure that appropriate sampling intervals are obtained under different working conditions. The correlation between historical data and desulfurization efficiency is analyzed, the influence weight of each parameter on desulfurization efficiency is calculated based on time-synchronized real-time data, and the data credibility is evaluated accordingly to select high-credibility data as the input of the control strategy. Based on these high-quality data, the slurry circulating pump flow and limestone slurry supply rate are dynamically adjusted to realize accurate control of the desulfurization process, significantly improve the response speed to changes in working conditions and the stability of desulfurization efficiency, and effectively overcome the response lag problem of traditional static control methods.

[0008] In some embodiments of the first aspect, in some embodiments, the length of the sliding window is dynamically adjusted according to the instantaneous change rate of the flue gas flow in the effective data to obtain time-synchronized flue gas flow, SO2 concentration and slurry pH value, specifically comprising: calculating the flue gas flow change rate of the continuous data points in the effective data; comparing the flue gas flow change rate with a preset change rate threshold to obtain the fluctuation of the flue gas flow change rate; dynamically adjusting the length of the sliding window according to the fluctuation of the flue gas flow change rate to obtain an adjusted sliding window length; and recalculating the time stamp of the effective data according to the adjusted sliding window length to obtain time-synchronized flue gas flow, SO2 concentration and slurry pH value.

[0009] By using the above technical solution, the flue gas flow change rate is calculated and compared with the threshold value, and the degree of flow fluctuation can be captured in real time. According to the fluctuation, the length of the sliding window is dynamically adjusted, which can reduce the window when the flow suddenly changes, enhance the sensitivity to sudden changes, and make the data processing more consistent with the actual working condition changes. Recalculating the time stamp realizes time synchronization, ensures that each parameter is analyzed under the same time reference, avoids the deviation of control decision caused by different time synchronization, and improves the accuracy of subsequent parameter correlation analysis and control adjustment.

[0010] In some embodiments of the first aspect, in some embodiments, the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency is obtained based on the correlation between the historical flue gas flow, SO2 concentration, slurry pH value data and the actual desulfurization efficiency, and the time-synchronized flue gas flow, SO2 concentration and slurry pH value, specifically comprising: time series segmentation of the historical flue gas flow, SO2 concentration, slurry pH value data to obtain a plurality of time window sequences, the time window sequence containing the flue gas flow, SO2 concentration and slurry pH value and the actual desulfurization efficiency in the corresponding period; parameter correlation calculation of the flue gas flow, SO2 concentration and slurry pH value in the time window sequence to obtain a parameter correlation degree matrix; constructing a parameter contribution degree evaluation function according to the parameter correlation degree matrix and the actual desulfurization efficiency to obtain a contribution weight coefficient of the flue gas flow, SO2 concentration and slurry pH value to the desulfurization efficiency; and based on the contribution weight coefficient, combining the change characteristics of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data to obtain the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency.

[0011] By adopting the technical solution, the time window sequence is obtained by segmenting the historical data time sequence, and different working condition stages can be clearly divided. The parameter correlation matrix is calculated to clearly show the mutual influence relationship between parameters, and the parameter contribution evaluation function is constructed to combine the actual desulfurization efficiency to quantize the contribution of each parameter to the desulfurization effect. Based on the contribution weight coefficient, the time synchronization data change characteristics are combined, the dynamic nature of the influence of real-time working conditions on parameters is considered, the influence weight is more consistent with the current working condition, and a scientific basis is provided for accurate control.

[0012] In combination with some embodiments of the first aspect, in some embodiments, based on the contribution weight coefficient, the change characteristics of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data are combined to obtain the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency, specifically including: based on the contribution weight coefficient, the parameter synergy matrix is constructed in combination with the normalized values of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data; the eigenvalues of the parameter synergy matrix are calculated; the contribution weight coefficient is corrected based on the size of the eigenvalue to obtain a corrected weight coefficient; the corrected weight coefficient and the normalized value are combined by weighting to obtain the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency.

[0013] By adopting the technical solution, the parameter synergy matrix is constructed based on the contribution weight coefficient and the normalized value, which can comprehensively reflect the synergy of each parameter at different levels. The eigenvalue is calculated to correct the contribution weight coefficient, which highlights the significant parameter changes affecting the desulfurization efficiency and suppresses the interference of secondary parameters. The normalized value and the corrected weight coefficient are combined by weighting, so that the influence weight more accurately reflects the actual influence of each parameter on the desulfurization efficiency under the current working condition, providing a reliable basis for subsequent credibility score calculation and improving the scientificity of control decision.

[0014] In combination with some embodiments of the first aspect, in some embodiments, according to the influence weight, the credibility score of the flue gas flow, SO2 concentration and slurry pH value data is calculated, specifically including: based on the influence weight, the time-synchronized flue gas flow, SO2 concentration and slurry pH value, the weighted data value is calculated; the dynamic mean value of the weighted data value in a preset time period is calculated by a sliding exponential smoothing method; based on the dynamic mean value, the dynamic variance of the weighted data value is calculated by using an adaptive variance; according to the deviation degree of the weighted data value and the dynamic mean value, in combination with the dynamic variance, the credibility score of the flue gas flow, SO2 concentration and slurry pH value data is calculated.

[0015] By adopting the technical scheme, the weighted data value is calculated based on the influence weight, and the key parameter effect is highlighted. The dynamic mean value is calculated by using the sliding exponential smoothing method, which can adapt to the dynamic change of data and track the data trend in real time. The self-adaptive variance calculation considers the dynamic characteristics of data distribution, and more accurately reflects the data dispersion degree. The credibility score is calculated in combination with the dynamic mean value and variance, which can effectively identify the reliability of data, filter abnormal or unreliable data, and retain high credibility data for control adjustment, thereby improving the accuracy and stability of control decision.

[0016] In combination with some embodiments of the first aspect, in some embodiments, according to the high-credibility flue gas flow, SO2 concentration and slurry pH value data, the slurry circulating pump flow and limestone slurry supply rate in the desulfurization device are dynamically adjusted, specifically including: calculating a real-time deviation value and a historical deviation cumulative value of the high-credibility SO2 concentration from a preset SO2 emission standard value; calculating a deviation weighted score according to the real-time deviation value and the historical deviation cumulative value; setting an adaptive adjustment coefficient based on the deviation weighted score, the adaptive adjustment coefficient increasing with the increase of the deviation weighted score; performing multi-parameter coupling calculation on the adaptive adjustment coefficient, the high-credibility flue gas flow data and the slurry pH value data to obtain a flow adjustment increment and a slurry supply adjustment increment; and calculating the slurry circulating pump flow and the limestone slurry supply rate in the desulfurization device according to the flow adjustment increment and the slurry supply adjustment increment.

[0017] By adopting the technical scheme, the real-time deviation value and the historical deviation cumulative value are calculated to comprehensively measure the difference between the current and long-term desulfurization effect and the standard. The deviation weighted score comprehensively considers the immediate and historical situations to avoid misjudgment caused by short-term fluctuations. The adaptive adjustment coefficient increases with the increase of the deviation, so that the system increases the adjustment strength when the deviation is large, and quickly responds to abnormal working conditions. The multi-parameter coupling calculation considers the complexity of the desulfurization process in combination with factors such as flow and pH value, so that the adjustment increment is more in line with the actual demand, and precise dynamic adjustment is realized.

[0018] In combination with some embodiments of the first aspect, in some embodiments, according to the flow adjustment increment and the slurry supply adjustment increment, the slurry circulating pump flow and the limestone slurry supply rate in the desulfurization device are calculated, specifically including: performing trend analysis on the flow adjustment increment and the slurry supply adjustment increment to obtain the change trend characteristics and the dynamic adjustment step of the adjustment parameters; generating a stage adjustment target value and an adjustment execution time sequence according to the dynamic adjustment step, the flow adjustment increment and the slurry supply adjustment increment; and adjusting the slurry circulating pump flow and the limestone slurry supply rate in the desulfurization device according to the adjustment execution time sequence to realize the stage adjustment target value.

[0019] By adopting the technical scheme, the trend of the adjustment increment is analyzed, the parameter change trend characteristics are identified, and a reasonable dynamic adjustment step is determined to avoid over-adjustment or under-adjustment. The phase adjustment target value and the execution time sequence are generated, the overall adjustment is decomposed into ordered phases, and the system is smoothly transitioned to the target state. The phase target is realized according to the execution time sequence, the system shock is reduced, the slurry circulating pump flow and the limestone slurry supply rate are smoothly adjusted, the adaptability and stability of the desulfurization system to dynamic working conditions are improved, and efficient desulfurization is realized.

[0020] In a second aspect, the present application provides a server, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprising computer instructions, and the one or more processors invoke the computer instructions to enable the server to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0021] In a third aspect, the present application provides a computer readable storage medium, comprising instructions, when the instructions are run on a server, enabling the server to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, when the computer program product is run on a server, enabling the server to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0024] 1. Since the dynamic data of the desulfurization device inlet is acquired, high-frequency noise is removed, the sliding window abnormal value processing is based on, and the sliding window length is dynamically adjusted according to the instantaneous change rate of the flue gas flow to realize data time synchronization, the data is first removed from the high-frequency noise to avoid unnecessary interference fluctuations, the abnormal value processing based on the sliding window can eliminate accidental error data to ensure that the data is real and reliable. Then, the sliding window length is flexibly adjusted according to the instantaneous change rate of the flue gas flow, the window is shortened when the flow changes sharply to quickly capture the changes, the window is lengthened when the flow is stable to improve the data smoothness, and the time synchronization of the multiple parameters is realized. The technical effect of obtaining more accurate, real-time and synchronized effective data is realized, which lays a foundation for subsequent desulfurization efficiency improvement and accurate control.

[0025] 2、Due to the adoption of the technical means of time series segmentation of historical data, calculation of parameter correlation matrix, construction of parameter contribution degree evaluation function, and determination of influence weight combined with time synchronization data change characteristics, the historical data is first time series segmented to form a time window sequence of different working condition stages, the parameter correlation matrix is calculated to determine the mutual influence relationship of each parameter, and the parameter contribution degree evaluation function is constructed to quantify the contribution of each parameter combined with the actual desulfurization efficiency. Then combined with the change characteristics of time synchronization data, the dynamic nature of the influence of real-time working conditions on parameters is considered, and the weight is further optimized. Effectively solve the problem that the prior art cannot accurately measure the actual influence of each parameter on the desulfurization efficiency, and further realize the technical effect of accurately quantifying the influence weight of each dynamic parameter on the desulfurization efficiency, providing a scientific basis for data-based intelligent desulfurization control.

[0026] 3、Due to the adoption of the technical means of calculating real-time and historical deviation values, setting adaptive adjustment coefficients, and performing multi-parameter coupling calculation to determine the adjustment increment, the real-time deviation value and the historical deviation cumulative value are first calculated to comprehensively reflect the gap between the current and long-term desulfurization effect and the standard, and the deviation weighted score is used to avoid misjudgment caused by short-term fluctuations. The adaptive adjustment coefficient is set to increase with the increase of the deviation, so that the system increases the adjustment effort when the deviation is large. Multi-parameter coupling calculation comprehensively considers factors such as flow and pH value, and fully considers the complexity of the desulfurization process. Effectively solve the problem that the existing static parameter control method cannot timely and reasonably adjust the slurry circulating pump flow and limestone slurry supply rate under dynamic working conditions, and further realize the technical effect of quickly and accurately adjusting the equipment operating parameters according to the dynamic working conditions, improving the desulfurization efficiency and system stability. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 is a flowchart of using the intelligent desulfurization control method based on dynamic data in the embodiment of the present application;

[0028] Figure 2 is another flowchart of using the intelligent desulfurization control method based on dynamic data in the embodiment of the present application;

[0029] Figure 3 is a hardware structure diagram of an electronic device in the embodiment of the present application. DETAILED DESCRIPTION

[0030] The terminology used in the following description of the embodiments herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the description of the embodiments and the appended claims herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It also will be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0031] Hereinafter, the terms "first", "second", "third", "fourth", "fifth", "sixth", "seventh" and "eighth" are used only for the purpose of description, and are not intended to imply or indicate relative importance or imply a specific number of the technical features indicated. Therefore, the features defined with "first", "second", "third", "fourth", "fifth", "sixth", "seventh" and "eighth" can explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0032] The present application aims to solve the problem that the control system response is slow under the complex working conditions of rapid fluctuation of flue gas flow and sulfur dioxide concentration, dynamic change of slurry pH value, etc. in the industrial desulfurization process, and the static parameter setting cannot timely adjust the slurry circulating pump flow and limestone slurry supply rate, which leads to insufficient desulfurization reaction, excessive supply of slurry, and ultimately low desulfurization efficiency.

[0033] In order to solve the problem of desulfurization efficiency in the prior art, a control method based on static parameter setting is usually used. This method controls the flow of the slurry circulating pump and the limestone slurry supply rate through a pre-set fixed value or proportional relationship to maintain the pH value of the slurry and the concentration of the reactants. In this method, the control system mainly formulates a parameter setting curve according to historical experience or experimental data, and controls the flow of the slurry circulating pump and the limestone slurry supply rate to meet the basic needs of desulfurization.

[0034] The intelligent desulfurization control method based on dynamic data in the embodiment of the application first acquires real-time data of flue gas flow, SO2 concentration and slurry pH value at the inlet of a desulfurization device. The data is subjected to high-frequency noise removal and outlier processing based on a dynamic sliding window to obtain effective data. The length of the sliding window is dynamically adjusted according to the instantaneous change rate of the flue gas flow to realize time synchronization of the data. Then, the influence weight of each parameter on the desulfurization efficiency is calculated based on the correlation analysis of historical data and actual desulfurization efficiency. Through credibility score evaluation and threshold screening, high-credibility monitoring data is obtained. Finally, according to the high-credibility data, multi-parameter coupling calculation and adaptive adjustment are adopted to dynamically optimize the control parameters of the slurry circulating pump flow and the limestone slurry supply rate. The method significantly improves the response speed and control accuracy of the desulfurization equipment to the change of flue gas working conditions by means of data preprocessing, dynamic time window, parameter weight calculation and adaptive control, and overcomes the lag problem of the traditional static control method.

[0035] For ease of understanding, the intelligent desulfurization control method based on dynamic data provided in the embodiments of the application is described as follows: first, inlet flue gas flow, SO2 concentration and slurry pH value data are acquired, and effective data is obtained through denoising and outlier processing. Then, the length of the sliding window is adjusted according to the instantaneous change rate of the flue gas flow to realize time synchronization. Then, the influence weight of each data on the desulfurization efficiency is obtained in combination with the correlation of historical data and desulfurization efficiency, the credibility score is calculated and compared with the threshold value, and the slurry circulating pump flow and the limestone slurry supply rate are dynamically adjusted according to the high-credibility data.

[0036] Figure 1 is a flowchart of using the intelligent desulfurization control method based on dynamic data in the embodiments of the application.

[0037] Please refer to Figure 1 , the specific description of the intelligent desulfurization control method based on dynamic data is as follows: 101, acquire flue gas flow, SO2 concentration and slurry pH value data at the inlet of a desulfurization device.

[0038] The flue gas flow data is usually acquired by means of a flow sensor installed at a specific position of the inlet pipeline of the desulfurization device. For example, a commonly used vortex flowmeter utilizes fluid oscillation principle. When flue gas passes through, it will alternately generate vortexes on both sides of the vortex generator of the flowmeter, and the frequency of the vortexes is linearly related to the flow rate (i.e. flue gas flow). By detecting the vortex frequency, the flue gas flow can be accurately calculated.

[0039] For measuring SO2 concentration, non-dispersive infrared absorption sensors are commonly used. Their working principle is based on the strong absorption characteristic of SO2 gas by infrared light of a specific wavelength. When flue gas containing SO2 passes through the measuring chamber, the infrared light of that specific wavelength is absorbed by the flue gas. By detecting the change in infrared intensity before and after absorption, the SO2 concentration can be calculated. Taking a chemical plant as an example, the flue gas emitted during its production process contains different concentrations of SO2. Installing such a sensor at the inlet of the desulfurization unit allows for timely acquisition of dynamic changes in SO2 concentration.

[0040] The pH value of the slurry is obtained using a pH sensor. It consists of a reference electrode and a measuring electrode. When the sensor is immersed in the desulfurization slurry, it generates a corresponding potential difference based on the hydrogen ion concentration in the slurry. By measuring this potential difference and performing calculations, the pH value of the slurry can be determined. In the desulfurization process, the pH value of the slurry is crucial to the desulfurization reaction. For example, in the desulfurization system of a certain smelter, if the pH value is too high, it will lead to excessively rapid consumption of limestone and may also cause scaling on the equipment; if the pH value is too low, the desulfurization efficiency will decrease significantly.

[0041] 102. Perform preprocessing operations on the flue gas flow rate, SO2 concentration and slurry pH value data to obtain valid data. The preprocessing operations include removing high-frequency noise and handling outliers based on a sliding window.

[0042] High-frequency noise was removed from the flue gas flow rate, SO2 concentration, and slurry pH data to obtain denoised flue gas flow rate, SO2 concentration, and slurry pH data. High-frequency noise is usually generated by factors such as equipment vibration and electromagnetic interference, which can cause unstable fluctuations in the data and affect the accuracy of subsequent analysis and control. A common noise reduction method is to use digital filters, such as low-pass filters. A low-pass filter can be set with a cutoff frequency, allowing only signals below that frequency to pass through, while high-frequency noise signals above the cutoff frequency are filtered out. For example, in a desulfurization unit of a factory, electromagnetic interference caused by the operation of a large nearby motor caused high-frequency fluctuations in the collected flue gas flow rate data. By setting a low-pass filter with an appropriate cutoff frequency in the data processing stage, these high-frequency noises were successfully removed, making the flue gas flow rate data smooth and stable.

[0043] Based on the denoised flue gas flow, SO2 concentration and slurry pH value data, a sliding window is set; the median of the data points in the sliding window is compared with each data point in the sliding window to obtain abnormal points; the median of the data points in the sliding window is used to replace the value of the abnormal points to obtain the effective data in the sliding window. The sliding window is a fixed length data subset sliding on the data sequence. Taking the flue gas flow data as an example, assuming that the sliding window length is set to 5 data points, when the window moves on the data sequence, the statistical characteristics of the data in the window are calculated, such as mean and standard deviation. If the deviation of a data point from the mean value in the window exceeds a certain multiple of the standard deviation (usually set to 3 times the standard deviation), the data point is determined to be an abnormal value. For example, in a set of continuously collected flue gas flow data, most of the data fluctuate between 500-600 cubic meters / hour, but a 1000 cubic meters / hour data point suddenly appears. Through sliding window calculation, it is found that the point deviates from the mean value in the window by more than 3 times the standard deviation, which can be determined as an abnormal value. For abnormal values, the common method is to replace the median value in the window.

[0044] 103、According to the instantaneous change rate of the flue gas flow in the effective data, the length of the sliding window is dynamically adjusted to obtain time-synchronized flue gas flow, SO2 concentration and slurry pH value.

[0045] The instantaneous change rate of flue gas flow reflects the change of flue gas flow in a very short time. When calculating the instantaneous change rate, the difference between two adjacent data points is usually divided by the time interval. For example, the flue gas flow collected at time t1 is F1, and the flue gas flow collected at the next time t2 is F2, the time interval Δt is (t2-t1), and the instantaneous change rate of flue gas flow in this time period is (F2-F1) / Δt.

[0046] According to the calculated instantaneous change rate to dynamically adjust the length of the sliding window, the data change trend can be better captured. When the instantaneous change rate of flue gas flow is large, it means that the working condition is in a state of rapid change, at this time the length of the sliding window should be shortened. For example, in the desulfurization process of a certain steel plant, at specific production links such as blast furnace tapping, it will cause the flue gas flow to increase sharply in a short time, at this time the instantaneous change rate increases. If a longer sliding window is still used, the data in the window will contain more data under different working conditions, and cannot accurately reflect the current rapid change. After shortening the length of the sliding window, the rapid change of the flue gas flow can be tracked more timely and carefully, making the subsequent analysis and control more targeted.

[0047] On the contrary, when the instantaneous change rate of flue gas flow is small, it indicates that the working condition is relatively stable, and at this time the sliding window length can be appropriately lengthened. Taking the stable power generation stage of a certain thermal power plant as an example, the flue gas flow changes relatively gently, and lengthening the sliding window length can include more data in the analysis range, enhance the stability and representativeness of the data, and reduce the influence of accidental factors on data analysis.

[0048] After adjusting the sliding window length, time synchronization of data needs to be realized. Time synchronization is crucial for accurately analyzing the relationship between flue gas flow, SO2 concentration, and slurry pH value. Assuming that the original sliding window length is fixed at 10 data points, corresponding to a time span of 1 minute, and now the window length is adjusted to 5 data points according to the instantaneous change rate, the time span becomes 0.5 minutes. At this time, the time label of each data point needs to be re-determined to ensure that the time reference of each data point is consistent under the new window length.

[0049] 104、Based on the correlation between historical flue gas flow, SO2 concentration, slurry pH value data and actual desulfurization efficiency, combined with the time-synchronized flue gas flow, SO2 concentration and slurry pH value, the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on desulfurization efficiency is obtained.

[0050] First, collect the flue gas flow, SO2 concentration, slurry pH value and corresponding desulfurization efficiency data within a period of time. These data should cover different working conditions to ensure the comprehensiveness and accuracy of the analysis results. For example, in the desulfurization system of a certain thermal power plant, the above data is continuously collected every hour within a month, including data under different working conditions such as unit load change and coal quality fluctuation.

[0051] According to historical data, when the flue gas flow suddenly increases, if the slurry circulating pump flow and limestone slurry supply rate cannot be adjusted in time, the desulfurization efficiency will often decrease. This indicates that there is a close correlation between flue gas flow and desulfurization efficiency. For example, when the slurry pH value is in a certain specific interval, the desulfurization reaction is more complete and the desulfurization efficiency is higher, which reveals the important influence of slurry pH value on desulfurization efficiency.

[0052] When combining historical data with time-synchronized real-time data, the changes of each parameter need to be considered comprehensively. Assuming that at a certain time, the time-synchronized flue gas flow, SO2 concentration and slurry pH value show that the current working condition is similar to a certain high-efficiency desulfurization period in history, but there are some subtle differences, at this time, historical data cannot be simply applied to the weight, but the characteristics of the current real-time data need to be adjusted. If the current SO2 concentration is slightly higher than the historical data, while the flue gas flow and slurry pH value are similar, then when calculating the influence weight, the weight of SO2 concentration needs to be appropriately increased to reflect its greater influence on desulfurization efficiency under the current working condition.

[0053] The calculation of the influence weight needs to be adjusted according to the dynamic changes of real-time data. In actual operation, the desulfurization process is changing all the time and may be disturbed by various factors. For example, the replacement of fuel may cause changes in flue gas composition, thereby affecting the role of each parameter on the desulfurization efficiency. By continuously adjusting the influence weight combined with real-time data, it can be more in line with the actual situation and improve the accuracy and adaptability of control.

[0054] 105、According to the influence weight, the reliability score of the flue gas flow, SO2 concentration and slurry pH value data is calculated.

[0055] The influence weight reflects the importance of each parameter in the desulfurization process, and based on this, the reliability score is calculated, which can highlight the role of key parameters. For example, in the desulfurization system of a certain chemical enterprise, it was found through analysis that the influence weight of SO2 concentration on desulfurization efficiency was larger, which means that the accuracy and stability of SO2 concentration data have a more significant impact on the overall reliability when calculating the reliability score.

[0056] Combining dynamic mean and variance to calculate the reliability score can comprehensively evaluate the reliability of the data. For example, when the deviation of SO2 concentration data at a certain time from the dynamic mean is small, and the variance is also small, it means that the data is within the normal fluctuation range and has high reliability; on the contrary, if the deviation is large and the variance is also large, the data may be abnormal and has low reliability.

[0057] 106、By comparing the reliability score with the preset reliability threshold, the flue gas flow, SO2 concentration and slurry pH value data with high reliability are obtained.

[0058] The preset reliability threshold is determined according to the actual needs and experience in the desulfurization process. Due to different process requirements and expectations for data accuracy, the set reliability threshold will also vary. For example, in the power industry which has very high requirements for desulfurization precision, in order to ensure that the emissions meet the standards, the reliability threshold may be set relatively high, only the data with high reliability score will be recognized; while in some small enterprises which have relatively low requirements for desulfurization efficiency but pay more attention to cost control, the reliability threshold may be relatively low.

[0059] The process of comparing the credibility score with the threshold value is a strict screening of the data. For example, in a desulfurization system of a certain steel plant, if the credibility score of the flue gas flow at a certain time is 0.8 and the preset credibility threshold value is 0.7, it means that the credibility of the flue gas flow data is high and meets the requirements of data quality, and it will be retained as the basis for subsequent control. On the contrary, if the credibility score of the slurry pH value at a certain time is 0.6, which is lower than the preset threshold value, the reliability of the data is questionable and needs to be further processed, such as re-collected or corrected by combining other data.

[0060] For data that does not meet the threshold value, there are many ways to handle it. One common method is to estimate by interpolation according to the data of the previous and subsequent time. For example, if the SO2 concentration data at a certain time has low credibility, and the data of the previous and subsequent time has high credibility, then the reasonable SO2 concentration value at that time can be estimated by linear interpolation. In addition, other related parameters can be combined to make a comprehensive judgment and correction.

[0061] Through this screening process, the high credibility data obtained has higher accuracy and reliability.

[0062] 107、According to the high credibility flue gas flow, SO2 concentration and slurry pH value data, dynamically adjust the slurry circulating pump flow and limestone slurry supply rate in the desulfurization device.

[0063] The high credibility flue gas flow, SO2 concentration and slurry pH value data provide a reliable basis for adjustment. For example, when the high credibility data shows that the current flue gas flow increases, the SO2 concentration exceeds the emission standard, and the slurry pH value is low, it indicates that the reaction needs to be intensified to reduce SO2 emission. At this time, the slurry circulating pump flow needs to be increased to make more slurry participate in the reaction, and the limestone slurry supply rate needs to be increased to supplement the alkaline substances needed for the desulfurization reaction, thereby enhancing the desulfurization effect.

[0064] If the dynamic adjustment process is simply based on the current data for one-time large adjustment, it may overreact and cause slurry waste. Therefore, the adjustment process needs to be carried out gradually, and the effect after adjustment needs to be monitored in real time. For example, after increasing the slurry circulating pump flow, the change of desulfurization efficiency and the fluctuation of slurry pH value need to be closely observed, and the flow and slurry supply rate need to be further adjusted according to the actual feedback.

[0065] The intelligent desulfurization control method based on dynamic data in the embodiment of the application is adopted, the flue gas flow, SO2 concentration and slurry pH value data at the inlet of the desulfurization device are acquired and pretreated, high-frequency noise and abnormal values are removed, the length of the sliding window is dynamically adjusted according to the instantaneous change rate of the flue gas flow to realize time synchronization, the influence weight of each parameter on the desulfurization efficiency is determined in combination with historical data, the high-confidence data is screened out by calculating the confidence score, and finally the slurry circulating pump flow and the limestone slurry supply rate in the desulfurization device are dynamically adjusted according to the data, so that the desulfurization process is accurately controlled. Not only the problem of response lag of the traditional static parameter control method under dynamic working conditions is effectively solved, but also the stability of the desulfurization efficiency is enhanced, so that the desulfurization process can stably and efficiently run under complex and changeable working conditions, the operation cost is reduced, the environmental pollution is reduced, and the increasingly strict environmental protection regulations are met.

[0066] Another method provided by the embodiment of the application is described below: first, the flue gas flow change rate is calculated, the length of the sliding window is dynamically adjusted, and the time stamp is recalculated to realize data synchronization; second, the historical data time sequence is segmented, the influence weight is determined by correlation calculation and construction of an evaluation function, and the weight is corrected; third, the confidence score is calculated based on the influence weight; and finally, the deviation is calculated based on the high-confidence data, the adaptive adjustment coefficient is set, the slurry circulating pump flow and the limestone slurry supply rate are accurately and dynamically adjusted through multi-parameter coupling and trend analysis.

[0067] Figure 2 Another flowchart of using the intelligent desulfurization control method based on dynamic data in the embodiment of the application is shown in FIG. 4.

[0068] Referring to FIG. 4, Figure 2 Another method of the intelligent desulfurization control based on dynamic data is specifically described as follows: 201, the flue gas flow, SO2 concentration and slurry pH value data at the inlet of the desulfurization device are acquired (this step has been described in 101, and will not be repeated here).

[0069] 202, the flue gas flow, SO2 concentration and slurry pH value data are pretreated to obtain effective data, and the pretreatment operation includes removing high-frequency noise and abnormal value processing based on a sliding window (this step has been described in 102, and will not be repeated here).

[0070] 203, the flue gas flow change rate of the continuous data points in the effective data is calculated.

[0071] First, continuous data points are read from the database or cache that stores valid data. Assuming that the obtained flue gas flow data is a time series, for example, the flue gas flow collected at a certain time t1 is F1, and the flue gas flow collected at the next time t2 immediately after t1 is F2, the time interval Δt is (t2-t1), and the instantaneous change rate of the flue gas flow in this time period is (F2-F1) / Δt.

[0072] During the calculation process, the validity of the data and abnormal situations also need to be considered. If a certain data point deviates significantly from the normal range, such as a sudden change in data due to sensor failure, the server needs to handle it according to the preset rules. For example, a data smoothing algorithm can be used to correct abnormal data, or the abnormal point can be skipped when calculating the change rate, to ensure that the calculated change rate can truly reflect the change of the flue gas flow. In addition, the server also stores the calculated change rate data for subsequent analysis and use.

[0073] 204、Compare the flue gas flow change rate with the preset change rate threshold to obtain the fluctuation of the flue gas flow change rate.

[0074] The preset change rate threshold is determined comprehensively according to historical operation data of the desulfurization device, equipment performance, process requirements and other factors. Generally, two thresholds, an upper threshold Vmax and a lower threshold Vmin, are set. For example, for a certain desulfurization device, after analyzing a large amount of historical data and experimental verification, the upper threshold Vmax is determined to be 2000 cubic meters / (hour·minute), and the lower threshold Vmin is determined to be -1500 cubic meters / (hour·minute).

[0075] Each calculated change rate data is compared with the two thresholds. When the calculated change rate Vi is greater than Vmax, it indicates that the flue gas flow is in a state of rapid and violent fluctuation. For example, during the desulfurization process in a certain steel plant, when the blast furnace starts to tap, a large amount of high-temperature flue gas rapidly flows into the desulfurization device, causing the flue gas flow to increase rapidly. Assuming that the calculated change rate at this time is 2500 cubic meters / (hour·minute), which is greater than the preset upper threshold 2000 cubic meters / (hour·minute), the server determines that the flue gas flow change is in a state of violent fluctuation.

[0076] When the change rate Vi is less than Vmin, it indicates that the flue gas flow is rapidly decreasing, and is also in a state of violent fluctuation. For example, during the shutdown stage of the production equipment, the flue gas flow will rapidly decrease, and if the calculated change rate is -1800 cubic meters / (hour·minute), which is less than the lower threshold -1500 cubic meters / (hour·minute), the server will identify this rapid and violent fluctuation.

[0077] If the change rate Vi is between Vmin and Vmax, the flue gas flow rate changes relatively smoothly. For example, during stable power generation in a certain thermal power plant, the flue gas flow rate change rate is always maintained between -500 cubic meters / (hour·minute) and 1000 cubic meters / (hour·minute), and the server will determine that the flue gas flow rate is in a state of smooth fluctuation at this time.

[0078] 205、According to the fluctuation of the flue gas flow rate change rate, the length of the sliding window is dynamically adjusted to obtain an adjusted sliding window length.

[0079] When the flue gas flow rate change rate is in a state of severe fluctuation, i.e., the change rate is greater than the upper threshold or less than the lower threshold, the server will shorten the length of the sliding window. This is because in the case of rapid change of working conditions, a shorter sliding window can more timely and accurately capture the instantaneous change of data. For example, when the furnace is fed in a certain smelting plant, a large amount of flue gas is generated, resulting in a large instantaneous increase in the flue gas flow rate at the inlet of the desulfurization device, and the change rate far exceeds the upper threshold. At this time, the server shortens the sliding window from 10 data points to 5 data points, and the data in the window can more closely surround the current rapidly changing working conditions, avoiding the inclusion of too much data under different working conditions due to the length of the window, making the subsequent analysis and processing of data more targeted, and being able to quickly respond to the change of flue gas flow rate.

[0080] On the contrary, if the flue gas flow rate change rate is in a relatively stable state, i.e., the change rate is between the upper and lower thresholds, the server will appropriately lengthen the length of the sliding window. For example, during stable operation in a certain thermal power plant, the flue gas flow rate change rate is relatively stable and always fluctuates within the preset threshold range. At this time, the server increases the sliding window length from 5 data points to 10 data points. A longer sliding window can include more data, enhancing the stability and representativeness of the data and reducing the influence of accidental factors on data analysis. Because in the stable working condition, the fluctuation of data is small, by increasing the amount of data, the overall trend and characteristics of the data can be more accurately reflected.

[0081] 206、According to the adjusted sliding window length, the time stamp of the effective data is recalculated to obtain time-synchronized flue gas flow rate, SO2 concentration and slurry pH value.

[0082] First, the adjusted sliding window length information is obtained. Assuming that the sliding window length before adjustment is fixed at 10 data points, corresponding to a time span of 1 minute, after adjustment according to the flue gas flow rate change rate, the window length becomes 5 data points. At this time, the server needs to determine the time mark of each data point according to the new window length.

[0083] Certain rules must be followed when recalculating timestamps. If the original data collection time intervals are uniform, then when shortening the window, data points can be selected proportionally and the time remarked. When lengthening the window, it may be necessary to supplement some data points using an interpolation algorithm and allocate timestamps appropriately. For example, when the window is lengthened, the server can use linear interpolation to determine the timestamps for the newly added data points. Assuming the original window length was 5 points with a time interval of 0.5 minutes, and it is now lengthened to 10 points, 5 new points need to be inserted between the original 1st and 2nd points. The server will calculate the timestamps and corresponding data values ​​of these 5 new points using linear interpolation based on the time and data characteristics of the original two points.

[0084] By recalculating the timestamp, it can be ensured that the three sets of data—flue gas flow rate, SO2 concentration, and slurry pH value—are completely synchronized in time.

[0085] 207. The historical flue gas flow rate, SO2 concentration, and slurry pH value data are segmented over time to obtain multiple time window sequences. The time window sequences include the flue gas flow rate, SO2 concentration, slurry pH value, and actual desulfurization efficiency within the corresponding time period.

[0086] First, a large amount of historical data was read from the database, covering information about the desulfurization unit at different operating stages. For example, flue gas flow rate, SO2 concentration, slurry pH value, and corresponding actual desulfurization efficiency data were obtained, collected every 15 minutes over the past year.

[0087] The historical data is segmented into time-series segments according to preset rules. The length of the time window for each segment can be set according to actual conditions, commonly 5 minutes, 10 minutes, 30 minutes, etc. Assuming the server sets the time window length to 10 minutes, the data is divided into 10-minute intervals starting from the start time of the historical data. For example, the data from minutes 1 to 10 is divided into the first time window sequence, which includes the flue gas flow rate, SO2 concentration, slurry pH value data at each collection moment within these 10 minutes, as well as the actual desulfurization efficiency of the desulfurization unit within these 10 minutes. Then, the data from minutes 11 to 20 is divided into the second time window sequence, and so on.

[0088] During the segmentation process, it is essential to ensure the integrity and continuity of data within each time window sequence. If data is missing at a certain point in time, the server will employ appropriate methods to supplement or process it, based on the characteristics of the data and its relationship with preceding and following data. For example, for missing flue gas flow data, if the changes in preceding and following data are relatively stable, the server may use linear interpolation to estimate the missing value; if the data fluctuates significantly, it may combine data from other relevant parameters for a comprehensive estimation.

[0089] Through such time segmentation operation, the server obtains multiple time window sequences. These sequences are like individual data "slices", each of which represents the running state of the desulfurization device in a specific time period.

[0090] 208、performing parameter correlation calculation on the flue gas flow, SO2 concentration and slurry pH value in the time window sequence to obtain a parameter correlation matrix.

[0091] The server performs calculation for each time window sequence. Taking one of the time window sequences as an example, suppose that the sequence contains data of n collection time points, i.e. there are n groups of flue gas flow data (F1, F2, …, Fn), SO2 concentration data (C1, C2, …, Cn) and slurry pH value data (P1, P2, …, Pn). The server will use a suitable algorithm to calculate the correlation between parameters, and the commonly used method is the Pearson correlation coefficient algorithm.

[0092] Taking the correlation between flue gas flow and SO2 concentration as an example, the calculation formula of the Pearson correlation coefficient r is:

[0093] The r FC is the Pearson correlation coefficient of the correlation between flue gas flow and SO2 concentration;

[0094] is the average value of the flue gas flow in the time window;

[0095] is the average value of the SO2 concentration.

[0096] The correlation between flue gas flow, SO2 concentration, flue gas flow and slurry pH value, and SO2 concentration and slurry pH value is calculated in turn. For example, after calculation, in a certain time window sequence, the Pearson correlation coefficient of flue gas flow and SO2 concentration is 0.8, which indicates that there is a strong positive correlation between them, i.e. when the flue gas flow increases, the SO2 concentration also tends to increase. The correlation coefficient of flue gas flow and slurry pH value is -0.5, which indicates that there is a certain negative correlation between them, i.e. when the flue gas flow increases, the slurry pH value may decrease.

[0097] After completing the correlation calculation between parameters in each time window sequence, the server arranges these correlation values into a parameter correlation matrix.

[0098] 1. According to the parameter correlation matrix and the actual desulfurization efficiency, a parameter contribution degree evaluation function is constructed to obtain the contribution weight coefficient of the flue gas flow, SO2 concentration and slurry pH value to the desulfurization efficiency.

[0099] In constructing the evaluation function, the server comprehensively considers the relationship between the correlation degree of each parameter and the desulfurization efficiency. Assuming that the flue gas flow is x1, the SO2 concentration is x2, the slurry pH value is x3, the actual desulfurization efficiency is y, the function y = β0 + β1x1 + β2x2 + β3x3 + ∈ is preliminarily constructed, β0 is a constant term, β1, β2, β3 are weight coefficients to be determined, and ∈ is an error term.

[0100] The least square method optimization algorithm is used to continuously adjust the β value according to the historical data, so that the error sum of squares of the function prediction value and the actual desulfurization efficiency is minimized. For example, in the data of the thermal power plant, after multiple iterations, β1 = 0.3, β2 = 0.5, and β3 = 0.2 are obtained. These β values are the contribution weight coefficients of each parameter to the desulfurization efficiency, indicating that in this period, the SO2 concentration has the greatest influence on the desulfurization efficiency, followed by the flue gas flow, and the slurry pH value is relatively small, but all have important contribution to the desulfurization efficiency.

[0101] 210, based on the contribution weight coefficients, the normalized values of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data are combined to construct a parameter synergy matrix.

[0102] First, the time-synchronized flue gas flow, SO2 concentration and slurry pH value data are normalized. The purpose of normalization is to unify data of different magnitudes and ranges to a standard scale for fair comparison and analysis. For example, in the desulfurization system of a certain thermal power plant, the flue gas flow may range from a few hundred to a few thousand cubic meters per hour, the SO2 concentration may range from a few dozen to a few hundred ppm, and the slurry pH value is within a certain pH range. Through normalization, the server converts these data to a standard interval such as [0, 1] to obtain normalized flue gas flow data.

[0103] The server constructs a parameter synergy matrix based on the contribution weight coefficients and the normalized data. Assuming that the contribution weight coefficients are a (flue gas flow), b (SO2 concentration), and c (slurry pH value), and the normalized flue gas flow, SO2 concentration and slurry pH value data are F norm , C norm , P norm respectively. The parameter synergy matrix constructed by the server may be a three-dimensional matrix, and its elements can represent the interaction relationship of each parameter under different weights. For example, an element in the matrix may represent the influence degree of the synergistic action of flue gas flow and SO2 concentration on desulfurization efficiency under the current flue gas flow weight a, SO2 concentration weight b and slurry pH value weight c.

[0104] 211, calculate the eigenvalues of the parameter synergy matrix.

[0105] The constructed parameter synergy matrix is subjected to eigenvalue calculation. During the calculation process, the server employs specific algorithms, such as the power method, QR algorithm, etc. These algorithms can accurately solve the eigenvalues of the matrix. These algorithms can accurately solve the eigenvalues of the matrix. Suppose the calculated eigenvalues are λ1, λ2, λ3 (for a three-order parameter synergy matrix).

[0106] The size and nature of the eigenvalues contain rich information. Larger eigenvalues usually correspond to more important eigenvectors in the matrix, and these eigenvectors are closely related to the synergy relationship between parameters. For example, if λ1 is the largest eigenvalue, then the parameter combination represented by the corresponding eigenvector may play a dominant role in affecting desulfurization efficiency. This means that in this combination, the synergistic effect of the parameters on desulfurization efficiency is most significant.

[0107] For example, the positive and negative of the eigenvalues can also reflect the direction of the parameter synergy. Positive eigenvalues may indicate that the synergy between parameters has a positive promoting effect on desulfurization efficiency, while negative eigenvalues may mean that the synergy under certain parameter combinations will inhibit desulfurization efficiency. By analyzing these eigenvalues, the server can more clearly understand the trend of desulfurization efficiency under different parameter synergy conditions.

[0108] 212、Based on the size of the eigenvalues, the contribution weight coefficients are modified to obtain modified weight coefficients.

[0109] The server first analyzes the size relationship of the eigenvalues. Taking the desulfurization system of a certain steel plant as an example, suppose the three calculated eigenvalues are λ1> λ2> λ3. The larger eigenvalue λ1 corresponds to an eigenvector that reflects a stronger synergy mode between parameters, and this mode has a more prominent impact on desulfurization efficiency. The server will adjust the contribution weight coefficients of each parameter accordingly based on the size of the eigenvalues.

[0110] For the parameters associated with the largest eigenvalue λ1, the server will appropriately increase their contribution weight coefficients. For example, if the synergy between flue gas flow and SO2 concentration is more significant in this eigenvector, the server may increase the weight coefficients of these two parameters. Conversely, for parameters associated with smaller eigenvalues, the server will appropriately reduce their weight coefficients. For example, if the slurry pH value accounts for a large proportion in the eigenvector corresponding to the smaller eigenvalue λ3, and the synergy represented by this eigenvector has a relatively weak impact on desulfurization efficiency, the server will reduce the contribution weight coefficient of the slurry pH value.

[0111] Through such modification of the contribution weight coefficients based on the size of the eigenvalues, the server obtains modified weight coefficients.

[0112] 213、weighting and combining the correction weight coefficient and the normalized value to obtain the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency.

[0113] The correction weight coefficient calculated before and the normalized value of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data are obtained. Taking the desulfurization system of a certain thermal power plant as an example, the correction weight coefficient of the flue gas flow is 0.45, the correction weight coefficient of the SO2 concentration is 0.38, and the correction weight coefficient of the slurry pH value is 0.17 after the previous calculation. At the same time, the normalized values of the time-synchronized flue gas flow, SO2 concentration and slurry pH value at a certain time are 0.6, 0.7 and 0.5 respectively.

[0114] When weighting and combining, corresponding calculations are performed according to these data. The correction weight coefficient of each parameter is multiplied by the corresponding normalized value, and then the product results are considered comprehensively to determine the influence weight. For the flue gas flow, the influence weight on the desulfurization efficiency is part of the correction weight coefficient 0.45 multiplied by the normalized value 0.6; for the SO2 concentration, it is the correction weight coefficient 0.38 multiplied by the normalized value 0.7; for the slurry pH value, it is the correction weight coefficient 0.17 multiplied by the normalized value 0.5.

[0115] Through such a weighting and combining method, the weight of each parameter and the state of the current real-time data can be fully considered. If the correction weight coefficient of a certain parameter is high, it means that it is usually important in the desulfurization process; and its normalized value reflects the actual level of the parameter at the current time. For example, if the normalized value of the SO2 concentration at a certain time is high and its correction weight coefficient is also large, then in the calculation of the influence weight, the role of the SO2 concentration parameter will be highlighted, which means that the SO2 concentration is more critical to the desulfurization efficiency under the current working condition.

[0116] 214、based on the influence weight, the time-synchronized flue gas flow, SO2 concentration and slurry pH value, calculating the weighted data value.

[0117] After determining the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency, based on these influence weights and the corresponding time-synchronized data, the weighted data value is calculated. Taking the desulfurization system of a certain chemical enterprise as an example, the server obtains the time-synchronized flue gas flow of 800 cubic meters / hour, the SO2 concentration of 300 ppm and the slurry pH value of 5.5 at a certain time, and the influence weights of the three parameters on the desulfurization efficiency are 0.4, 0.35 and 0.25 respectively through the previous calculation.

[0118] When calculating the weighted data values, each parameter value is multiplied by its corresponding influence weight. For flue gas flow rate, the weighted value is 800 cubic meters per hour multiplied by 0.4; for SO2 concentration, it is 300 ppm multiplied by 0.35; and for slurry pH value, it is 5.5 multiplied by 0.25. This calculation highlights the importance of parameters with larger influence weights in the data. For example, if analysis shows that SO2 concentration has a larger influence weight on desulfurization efficiency under a certain operating condition, then the value of SO2 concentration will contribute more to the final result when calculating the weighted data values, better reflecting the key role of this parameter in the current desulfurization process.

[0119] This calculation method considers the varying degrees of importance of different parameters in the desulfurization process, making the results more representative of the overall impact of the data on desulfurization efficiency. Without weighted calculations, directly using the raw data would fail to reflect the different impacts of each parameter in the desulfurization process, potentially leading to inaccurate data assessments.

[0120] 215. Calculate the dynamic mean of the weighted data values ​​over a preset time period using the sliding exponential smoothing method.

[0121] After obtaining the weighted data values, the server uses a moving exponential smoothing method to calculate its dynamic mean over a preset time period. Taking the desulfurization system of a steel plant as an example, the server obtains a series of weighted data values. Assuming a preset time period of 10 minutes, data is collected every minute, resulting in 10 weighted data values. The core idea of ​​the moving exponential smoothing method is to assign different weights to data from different times, with newer data having higher weights, thereby highlighting real-time changes in the data.

[0122] When applying the sliding exponential smoothing method, a smoothing coefficient is first set. This coefficient is typically between 0 and 1, for example, set to 0.3. For the first data point, the dynamic mean is equal to the weighted value of that data point. Starting from the second data point, the server calculates the dynamic mean based on the smoothing coefficient. Specifically, the new dynamic mean equals the smoothing coefficient multiplied by the current weighted data value, plus (1 - smoothing coefficient) the previously calculated dynamic mean.

[0123] Assuming the first weighted data value is 100, the dynamic mean at the first time point is 100. When the second data point's weighted data value is 110, the dynamic mean = 0.3*110 + (1-0.3)*100 = 103. As the data is continuously collected, the server continuously updates the dynamic mean according to this rule. The dynamic mean will continuously adjust with the addition of new data, and can quickly respond to changes in data. If the weighted data value suddenly increases, due to the larger weight of the new data, the dynamic mean will quickly rise; conversely, if the data value decreases, the dynamic mean will also decrease, but the decrease will be affected by the previous data, and will not be too drastic.

[0124] 216、Based on the dynamic mean, the dynamic variance of the weighted data value is calculated using adaptive variance.

[0125] After obtaining the dynamic mean of the weighted data value through the moving exponential smoothing method, adaptive variance is used to calculate the dynamic variance of these data values. Taking a desulfurization system of a certain cement plant as an example, the server has calculated the dynamic mean of the weighted data value within a certain time period. The calculation of adaptive variance takes into account the dynamic characteristics of the data, and adjusts the calculation method flexibly as the data changes. During the calculation process, the server compares the difference between each weighted data value and the dynamic mean.

[0126] If the data fluctuation is relatively stable, the calculation method of adaptive variance will focus on reflecting this stable dispersion. Assuming that the weighted data value fluctuates around the dynamic mean within a certain time period, the server will calculate the variance according to specific adaptive rules based on the deviation of these data points from the dynamic mean. For example, when the data fluctuation is small, the calculation of adaptive variance will appropriately reduce the weight of individual data points with large deviations, in order to avoid the excessive influence of these abnormal points on the overall variance, and thus more accurately reflect the stable fluctuation state of the data.

[0127] When the data fluctuation is relatively stable, the calculation method of adaptive variance will focus on reflecting this stable dispersion. Assuming that the weighted data value fluctuates around the dynamic mean within a certain time period, the server will calculate the variance according to specific adaptive rules based on the deviation of these data points from the dynamic mean. For example, when the data fluctuation is small, the calculation of adaptive variance will appropriately reduce the weight of individual data points with large deviations, in order to avoid the excessive influence of these abnormal points on the overall variance, and thus more accurately reflect the stable fluctuation state of the data.

[0128] 217、According to the degree of deviation of the weighted data value from the dynamic mean, combined with the dynamic variance, the credibility score of the flue gas flow, SO2 concentration and slurry pH value data is calculated.

[0129] First, the degree of deviation between the weighted data value and the dynamic average value is calculated. This degree of deviation reflects the deviation of the current data from the average level. If the degree of deviation is small, it means that the data is relatively stable and consistent with the overall trend; on the contrary, a larger degree of deviation indicates that the data deviates from the normal range, which may be an abnormal situation.

[0130] Then, a comprehensive analysis is conducted in combination with the dynamic variance. The dynamic variance reflects the dispersion degree of the data. The larger the variance, the more dispersed the distribution of the data, and the poorer the stability of the data. For example, if the dynamic variance of a certain parameter is large, it means that the data of the parameter fluctuates greatly, and its credibility may be relatively low.

[0131] When calculating the credibility score, the deviation degree and the dynamic variance are integrated. According to the size of the deviation degree and the dynamic variance, appropriate weights are assigned to them. For data with a large deviation degree and a large dynamic variance, a lower credibility score is given, because such data deviates from the average level and has a large fluctuation, and its reliability is low. On the contrary, for data with a small deviation degree and a small dynamic variance, a higher credibility score is given, indicating that these data are stable and reliable.

[0132] 218、By comparing the credibility score with the preset credibility threshold, high-credibility flue gas flow, SO2 concentration and slurry pH value data are obtained (this step has been described in 106, and will not be repeated here).

[0133] 219、Calculate the real-time deviation value and the historical deviation cumulative value of the high-credibility SO2 concentration from the preset SO2 emission standard value.

[0134] Read the high-credibility SO2 concentration data and the preset SO2 emission standard value. The preset SO2 emission standard value is determined according to environmental protection regulations, enterprise production requirements, etc., and is an important benchmark for measuring desulfurization effect. For example, the environmental protection regulations of a certain region stipulate that the SO2 emission limit value of a certain type of enterprise is 100 mg / m 3 , which is the preset SO2 emission standard value of the desulfurization system of this enterprise.

[0135] The real-time deviation value reflects the gap between the high-credibility SO2 concentration at the current time and the emission standard value. Through simple subtraction operation, the real-time deviation value is obtained by subtracting the preset SO2 emission standard value from the current high-credibility SO2 concentration value.

[0136] The historical deviation cumulative value is a cumulative record of the deviation of SO2 concentration from the emission standard value over a period of time. The server reads the high-credibility SO2 concentration data at each time from the storage device in the past, calculates the deviation of each time from the emission standard value, and accumulates it. Assuming that the deviations of the past 5 times are 5 mg / m3 8 mg / m 3 - 3 mg / m 3 (Indicates below standard), 10 mg / m 3 12 mg / m 3 The historical deviation cumulative value is 5 + 8 - 3 + 10 + 12 = 32 mg / m 3 In this way, the server can comprehensively understand the overall situation of the deviation of the SO2 concentration from the standard over a period of time.

[0137] The real-time deviation value and the historical deviation cumulative value provide different dimensions of information for the server. The real-time deviation value allows the server to promptly perceive whether the current running state of the desulfurization system meets the standard, while the historical deviation cumulative value helps the server analyze the long-term stability and trends of the desulfurization system. If the real-time deviation value is small but the historical deviation cumulative value is large, it indicates that although the current desulfurization effect is close to the standard, there are some unstable factors in the long term, and the desulfurization process needs to be further optimized; conversely, if the real-time deviation value is large and the historical deviation cumulative value is small, it may be that the current desulfurization effect is poor due to a sudden situation, and emergency adjustment measures need to be taken in time.

[0138] 220. According to the real-time deviation value and the historical deviation cumulative value, a deviation weighted score is calculated.

[0139] In calculating the deviation weighted score, different weights are assigned to the real-time deviation value and the historical deviation cumulative value according to actual conditions. This is because the real-time deviation value reflects the immediate state of the current desulfurization equipment, while the historical deviation cumulative value embodies stability, and the importance of the two for evaluating the desulfurization effect is different. The real-time deviation value can better reflect the current working condition and may be given a relatively high weight; the historical deviation cumulative value helps to grasp the long-term trend and also has an important role that cannot be ignored. For example, the server can set the weight of the real-time deviation value to 0.6 and the weight of the historical deviation cumulative value to 0.4.

[0140] The process of calculating the deviation weighted score is a weighted sum process. The server multiplies the real-time deviation value by its corresponding weight, and adds the historical deviation cumulative value multiplied by its weight to obtain the final deviation weighted score. Assuming that the real-time deviation value is 20 mg / m 3 , the historical deviation cumulative value is 30 mg / m 3 , and according to the above weight setting, the deviation weighted score is 20 x 0.6 + 30 x 0.4 = 12 + 12 = 24.

[0141] 221. Based on the deviation weighted score, an adaptive adjustment coefficient is set, which increases with the increase of the deviation weighted score.

[0142] First, establish the mapping relationship between the deviation-weighted score and the adaptive adjustment coefficient. Since the adaptive adjustment coefficient is required to increase with the deviation-weighted score, a linear function is used to achieve this relationship. The adaptive adjustment coefficient is set as deviation-weighted score × 0.1 (here, 0.1 is a proportional coefficient set based on actual conditions and experience; it may vary for different desulfurization equipment). If the deviation-weighted score is 20, then the adaptive adjustment coefficient is 20 × 0.1 = 2.

[0143] In addition to linear relationships, the server can also employ nonlinear functions based on the characteristics of the desulfurization system. For example, using an exponential function, the adaptive adjustment coefficient increases slowly when the deviation weighted score is small, but increases rapidly when the deviation weighted score is large. Such a nonlinear relationship can better adapt to the adjustment needs of the desulfurization equipment under different deviation levels.

[0144] 222. Perform multi-parameter coupling calculations on the adaptive adjustment coefficient, the high-reliability flue gas flow data, and the slurry pH data to obtain the flow adjustment increment and the slurry supply adjustment increment.

[0145] In multi-parameter coupled calculations, the calculation is constructed based on the inherent principles of the desulfurization process and historical operating data. Adaptive adjustment coefficients, flue gas flow data, and slurry pH data are organically combined. For example, a multivariate function incorporating these parameters is used for the calculation; the form of the function and the weights of the parameters are determined through analysis of a large amount of historical data and simulation experiments.

[0146] Assuming the adaptive adjustment coefficient is K, the high-confidence flue gas flow rate is F, and the slurry pH is P, the server-built calculation might resemble the following form: Flow rate adjustment increment ΔQ = K × a × F + b × P + c, Slurry supply adjustment increment ΔM = K × d × F + e × P + f. Here, a, b, c, d, e, and f are coefficients fitted based on the characteristics of the desulfurization equipment and historical data. These coefficients reflect the degree of influence of each parameter on the flow rate adjustment increment and the slurry supply adjustment increment.

[0147] In actual calculations, the server will substitute the real-time adaptive adjustment coefficient, flue gas flow rate data, and slurry pH value data. For example, if the current adaptive adjustment coefficient K = 1.5, the high-confidence flue gas flow rate F = 800 cubic meters / hour, and the slurry pH value P = 5.8, and the calculated values ​​are a = 0.001, b = 10, c = -5, d = 0.002, e = 8, and f = -3, then the flow rate adjustment increment ΔQ = 1.5 × 0.001 × 800 + 10 × 5.8 - 5 = 59 cubic meters / hour, and the slurry supply adjustment increment ΔM = 1.5 × 0.002 × 800 + 8 × 5.8 - 3 = 2.4 + 46.4 - 3 = 45.8.

[0148] 223. Calculate the slurry circulating pump flow rate and the limestone supply rate in the desulfurization device according to the flow adjustment increment and the slurry supply adjustment increment.

[0149] Perform trend analysis on the flow adjustment increment and the slurry supply adjustment increment to obtain the change trend characteristics of the adjustment parameters and the dynamic adjustment step. By analyzing the changes of these increments over time, the change trend characteristics of the adjustment parameters are obtained. For example, if the flow adjustment increment shows a gradually increasing trend at consecutive time points, it indicates that the flow of the slurry circulating pump needs to be continuously increased to cope with changes in SO2 concentration in the flue gas or other changes in working conditions. At the same time, by determining the dynamic adjustment step, which determines the magnitude of each adjustment, a variety of factors are considered, such as the response speed of the equipment, stability requirements, and the adjustable range of the equipment. If the device has a higher response requirement to changes and allows rapid adjustment, the dynamic adjustment step can be appropriately increased; on the contrary, if the device focuses more on stability and avoids fluctuations caused by excessive adjustment, the dynamic adjustment step will be relatively small.

[0150] According to the dynamic adjustment step, the flow adjustment increment, and the slurry supply adjustment increment, generate phase adjustment target values and adjustment execution timing. The phase adjustment target value is to divide the overall adjustment task into multiple small phase targets, so that the device can smoothly transition to the final target state. For example, assuming that the current slurry circulating pump flow is 500 cubic meters / hour, the flow adjustment increment is 50 cubic meters / hour, and the dynamic adjustment step is 20 cubic meters / hour. Then, the server may set the phase adjustment target value as follows: adjust the flow to 520 cubic meters / hour in the first step, to 540 cubic meters / hour in the second step, and to 550 cubic meters / hour (close to the final target of 550 cubic meters / hour) in the third step. At the same time, the server determines the execution timing of each phase adjustment target, clearly specifying when the corresponding adjustment operation is performed.

[0151] According to the adjustment execution timing, the phase adjustment target value is realized, the slurry circulating pump flow rate in the desulfurization device and the limestone slurry supply rate are adjusted. During the execution, the server sends control instructions to the related equipment, accurately controls the slurry circulating pump to adjust the flow rate, and controls the conveying speed of the limestone slurry supply equipment to adjust the slurry supply rate. During the adjustment, the server also monitors the running state of the desulfurization system in real time, including the desulfurization efficiency, the SO2 concentration, the slurry pH value and other key indicators. If it is found that the actual adjustment effect does not match the expectation, the server will timely adjust the subsequent adjustment strategy, such as recalculating the adjustment increment, adjusting the dynamic adjustment step or modifying the phase adjustment target value, to ensure that the adjustment of the slurry circulating pump flow rate and the limestone slurry supply rate can be accurately and smoothly carried out, so that the desulfurization system can be efficiently and stably operated, the requirements of the desulfurization process can be met, the sulfur dioxide emission can be reduced, and the environmental protection standard can be reached.

[0152] By adopting the intelligent desulfurization control method based on dynamic data in the embodiments of the present application, the flue gas flow rate, the SO2 concentration and the slurry pH value data at the inlet of the desulfurization device are acquired and preprocessed to remove high-frequency noise and abnormal values, the length of the sliding window is dynamically adjusted according to the instantaneous change rate of the flue gas flow rate to realize data time synchronization, the influence weight of each parameter on the desulfurization efficiency is determined in combination with the historical data, the high-confidence data is screened out by calculating the confidence score, the deviation is calculated according to the high-confidence data, the adaptive adjustment coefficient is set, the adjustment increment is determined and the precise dynamic adjustment is realized through the multi-parameter coupling and trend analysis, the accurate control of the desulfurization process is realized, not only the problem of response lag of the traditional static parameter control method under dynamic working conditions is effectively solved, but also the stability of the desulfurization efficiency is enhanced, so that the desulfurization process can be stably and efficiently operated under complex and variable working conditions, the environmental pollution is reduced, and the increasingly strict environmental protection regulations are met.

[0153] The intelligent desulfurization control method based on dynamic data provided in the above embodiments can be executed by a server composed of an electronic device. The electronic device in the embodiments of the present application is described from the perspective of hardware processing as follows: Figure 3 , which is a hardware structure schematic diagram of the electronic device in the embodiments of the present application.

[0154] It should be noted that, Figure 3 The structure of the electronic device shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0155] As Figure 3As shown, the electronic device includes a central processing unit (CPU) 301 which can perform various appropriate actions and processes in accordance with a program stored in a read-only memory (ROM) 302 or a program loaded from a storage section 308 into a random access memory (RAM) 303, such as performing the methods described in the above embodiments. In the random access memory (RAM) 303, various programs and data required for system operation are also stored. The central processing unit (CPU) 301, the read-only memory (ROM) 302, and the random access memory (RAM) 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0156] Connected to the input / output (I / O) interface 305 are an input section 306 including an audio input device, a button switch, and the like; an output section 307 including a display, an audio output device, an indicator, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the input / output (I / O) interface 305 as necessary. A removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 310 as necessary, so that a computer program read therefrom is installed in the storage section 308 as necessary.

[0157] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program in accordance with embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing a computer program for performing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 309 and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present application are performed.

[0158] Note that specific examples of computer-readable storage media can include but are not limited to an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, computer-readable storage media can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0159] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functional processes, and operational processes, according to various embodiments of the present application. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or the block diagrams, can be implemented by computer readable program instructions such as program code. Such computer readable program instructions can be provided to a processor of a computer, or other programmable data processing apparatus, to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flow diagrams and / or block diagrams. These computer readable program instructions can also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and the other

[0160] In particular, the electronic device of the embodiment includes a processor and a memory coupled with the one or more processors, the memory configured to store computer program code comprising computer instructions that, when executed by the one or more processors, cause the electronic device to perform the method provided by the above embodiment.

[0161] As another aspect, the present disclosure also provides a computer readable storage medium, which can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device. The storage medium carries one or more computer programs, which, when executed by a processor of the electronic device, cause the electronic device to implement the method provided in the above embodiments.

[0162] The above embodiments are only used to illustrate the technical solutions of the present disclosure, but not limit the present disclosure; even though the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present disclosure.

[0163] In the above embodiments, the term "when" can be interpreted as meaning "if" or "after" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "on determining" or "if detecting (a stated condition or event)" can be interpreted as meaning "if determining" or "in response to determining" or "on detecting (a stated condition or event)" or "in response to detecting (a stated condition or event)" depending on the context.

[0164] In the above embodiments, all or some of the flowcharts or functions can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or some of the flowcharts or functions can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or some of the flowcharts or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as DVD), or semiconductor media (such as solid state disk), etc.

[0165] A person of ordinary skill in the art can understand that all or part of the flow of the above-mentioned embodiment method can be instructed by a computer program to complete the relevant hardware, and the program can be stored in a computer readable storage medium, and the program can include the flow of each method embodiment as described above when executed. The aforementioned storage medium includes ROM or random access memory (RAM), magnetic disk or optical disk, and various program code storage media.

Claims

1. A dynamic data-based intelligent desulfurization control method, characterized in that, The method comprises the following steps: acquiring flue gas flow, SO2 concentration and slurry pH value data at the inlet of a desulfurization device; performing preprocessing operations on the flue gas flow, SO2 concentration and slurry pH value data to obtain effective data, the preprocessing operations including removing high-frequency noise and performing outlier processing based on a sliding window; dynamically adjusting the length of the sliding window according to the instantaneous change rate of the flue gas flow in the effective data to obtain time-synchronized flue gas flow, SO2 concentration and slurry pH value; based on the correlation between historical flue gas flow, SO2 concentration, slurry pH value data and actual desulfurization efficiency, combining the time-synchronized flue gas flow, SO2 concentration and slurry pH value, obtaining the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency; calculating the credibility score of the flue gas flow, SO2 concentration and slurry pH value data according to the influence weight; by comparing the credibility score with a preset credibility threshold, obtaining high-credibility flue gas flow, SO2 concentration and slurry pH value data; based on the high-credibility flue gas flow, SO2 concentration and slurry pH value data, dynamically adjusting the slurry circulating pump flow and the limestone slurry supply rate in the desulfurization device.

2. The method of claim 1, wherein, dynamically adjusting the length of the sliding window according to the instantaneous change rate of the flue gas flow in the effective data to obtain time-synchronized flue gas flow, SO2 concentration and slurry pH value, specifically including: calculating the flue gas flow change rate of consecutive data points in the effective data; comparing the flue gas flow change rate with a preset change rate threshold to obtain the fluctuation of the flue gas flow change rate; dynamically adjusting the length of the sliding window according to the fluctuation of the flue gas flow change rate to obtain an adjusted sliding window length; recomputing the time stamp of the effective data according to the adjusted sliding window length to obtain time-synchronized flue gas flow, SO2 concentration and slurry pH value.

3. The method of claim 1, wherein, based on the correlation between historical flue gas flow, SO2 concentration, slurry pH value data and actual desulfurization efficiency, combining the time-synchronized flue gas flow, SO2 concentration and slurry pH value, obtaining the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency, specifically including: performing time sequence segmentation on historical flue gas flow, SO2 concentration, slurry pH value data to obtain a plurality of time window sequences, the time window sequence containing flue gas flow, SO2 concentration and slurry pH value and actual desulfurization efficiency within the corresponding time period; performing parameter correlation calculation on the flue gas flow, SO2 concentration and slurry pH value in the time window sequence to obtain a parameter correlation degree matrix; based on the parameter correlation degree matrix and the actual desulfurization efficiency, constructing a parameter contribution degree evaluation function to obtain the contribution weight coefficient of the flue gas flow, SO2 concentration and slurry pH value to the desulfurization efficiency; based on the contribution weight coefficient, combining the change characteristics of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data to obtain the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency.

4. The method of claim 3, wherein, Based on the contribution weight coefficient, combined with the change characteristics of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data, the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency is obtained, specifically including: Based on the contribution weight coefficient, combined with the change characteristics of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data, the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency is obtained, specifically including: Based on the contribution weight coefficient, combined with the change characteristics of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data, the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency is obtained, specifically including: Based on the contribution weight coefficient, combined with the change characteristics of the time-synchronized flue gas flow, SO2 concentration and slurry pH value data, the influence weight of the time-synchronized flue gas flow, SO2 concentration and slurry pH value on the desulfurization efficiency is obtained, specifically including: According to the influence weight, the reliability score of the flue gas flow, SO2 concentration and slurry pH value data is calculated, specifically including:

5. The method of claim 1, wherein, Based on the influence weight, the time-synchronized flue gas flow, SO2 concentration and slurry pH value, the weighted data value is calculated; The dynamic mean value of the weighted data value in the preset time period is calculated by the sliding exponential smoothing method; Based on the dynamic mean value, the dynamic variance of the weighted data value is calculated by using adaptive variance; According to the deviation degree of the weighted data value and the dynamic mean value, combined with the dynamic variance, the reliability score of the flue gas flow, SO2 concentration and slurry pH value data is calculated. According to the high reliability of the flue gas flow, SO2 concentration and slurry pH value data, the slurry circulating pump flow and limestone slurry supply rate in the desulfurization device are dynamically adjusted, specifically including:

6. The method of claim 1, wherein, The real-time deviation value and historical deviation cumulative value of the high reliability SO2 concentration and the preset SO2 emission standard value are calculated; According to the real-time deviation value and historical deviation cumulative value, the deviation weighted score is calculated; Based on the deviation weighted score, the adaptive adjustment coefficient is set, which increases with the increase of the deviation weighted score; The adaptive adjustment coefficient, the high reliability of the flue gas flow data and the slurry pH value data are coupled and calculated to obtain the flow adjustment increment and the slurry supply adjustment increment; According to the flow adjustment increment and the slurry supply adjustment increment, the slurry circulating pump flow and the limestone slurry supply rate in the desulfurization device are calculated. According to the flow adjustment increment and the slurry supply adjustment increment, the slurry circulating pump flow and the limestone slurry supply rate in the desulfurization device are calculated, specifically including:

7. The method of claim 6, wherein, The trend analysis is performed on the flow adjustment increment and the slurry supply adjustment increment to obtain the change trend characteristics and dynamic adjustment step of the adjustment parameters; According to the dynamic adjustment step, the flow adjustment increment and the slurry supply adjustment increment, the stage adjustment target value and the adjustment execution time sequence are generated; According to the adjustment execution time sequence, the stage adjustment target value is realized, and the slurry circulating pump flow and the limestone slurry supply rate in the desulfurization device are adjusted. The server comprises:

8. A server, characterized by One or more processors and memories; ​ The memory is coupled with the one or more processors, and is configured to store computer program codes, the computer program codes comprising computer instructions, which are invoked by the one or more processors to cause the server to perform the method according to any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, The instructions, when executed on a server, cause the server to perform the method according to any one of claims 1-7.

10. A computer program product, characterised in that, The computer program product, when executed on a server, causes the server to perform the method according to any one of claims 1-7.

Images