Wet desulfurization mist eliminator flushing control method, device and computer equipment

Abstract

The present invention provides a wet flue gas desulfurization mist eliminator flushing control method, device, and computer equipment, relating to the field of intelligent desulfurization system technology. The method comprises: collecting the actual differential pressure value of the mist eliminator at the current moment; obtaining a first correlation factor correlated with the mist eliminator differential pressure, screening a first characteristic variable from the first correlation factor, inputting the first characteristic variable into a differential pressure prediction model, and predicting the normal differential pressure value at the current moment; calculating the blocking process coefficient based on the normal differential pressure value and the actual differential pressure value; obtaining a second correlation factor correlated with the mist eliminator blocking risk, screening a second characteristic variable from the second correlation factor, inputting the second characteristic variable into a blocking risk calculation model, and calculating the blocking risk coefficient of the mist eliminator at the current moment; if it is determined that the blocking process coefficient and the blocking risk coefficient meet the flushing start condition, then starting the flushing of the mist eliminator. The above method realizes on-demand flushing of the mist eliminator, taking into account both reliability and economy.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent desulfurization system, and specifically relates to a wet desulfurization demister flushing control method, a wet desulfurization demister flushing control device, a computer device and a machine-readable storage medium. Background Art

[0002] As a crucial component of wet flue gas desulfurization systems, demisters are primarily used to remove solid particles and tiny droplets from post-desulfurization flue gas, preventing them from entering the chimney with the flue gas and causing chimney corrosion. This also reduces environmental pollution caused by the flue gas after discharge. During the demisting process, solid particles and tiny droplets can deposit on the demister walls, causing blockage. This, in turn, increases flue gas flow resistance and fan power consumption in the air-smoke system. Furthermore, the cumulative blockage effect can cause the demister to collapse, forcing unplanned unit shutdowns.

[0003] At present, in order to slow down the clogging process of the demister, regular or continuous flushing is used for daily maintenance of the demister. Regular and continuous flushing methods are only carried out according to the operating system of the wet flue gas desulfurization system and the liquid level of the absorber. Among them, the regular flushing method is based on the operating system of the wet flue gas desulfurization system, and the demister is flushed at fixed time intervals. If the liquid level of the absorber exceeds the operating limit during the flushing process, the flushing is suspended. After the liquid level of the absorber returns to the normal range, the flushing process is continued until the current flushing is completed. The continuous flushing method is based on the operating system of the wet flue gas desulfurization system, and the demister is continuously flushed. If the liquid level of the absorber exceeds the operating limit during the flushing process, the flushing is suspended. After the liquid level of the absorber returns to the normal range, the flushing process is continued. After the current flushing is completed, the next flushing round will be directly entered.

[0004] Therefore, neither periodic nor continuous flushing methods pay attention to the system's operating characteristics and cannot effectively reduce the risk of blockage. Continuous flushing also results in a certain degree of resource waste. Targeted, on-demand flushing of demisters is of great significance to the safe, stable, and economical operation of wet flue gas desulfurization systems. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a wet desulfurization demister flushing control method, a wet desulfurization demister flushing control device, a computer device and a machine-readable storage medium to overcome one or more defects of the periodic flushing and continuous flushing methods in the prior art.

[0006] In order to achieve the above-mentioned object, a first aspect of an embodiment of the present invention provides a wet desulfurization mist eliminator flushing control method, the method comprising:

[0007] Collect the actual differential pressure value of the demister at the current moment;

[0008] Obtaining a first correlation factor correlated with the demister differential pressure under the demister's current operating conditions, screening a first characteristic variable from the first correlation factor based on the correlation with the demister differential pressure, inputting the first characteristic variable into a differential pressure prediction model derived from historical data-driven modeling, and predicting a normal differential pressure value of the demister at the current moment;

[0009] Calculating a blocking process coefficient of the demister at the current moment according to the normal differential pressure value and the actual differential pressure value, wherein the blocking process coefficient represents a degree of change of the actual differential pressure value relative to the normal differential pressure value;

[0010] Obtaining a second correlation factor correlated with the defogger blockage risk under the defogger's current operating conditions, screening a second characteristic variable from the second correlation factor based on the correlation with the defogger blockage risk, inputting the second characteristic variable into the established blockage risk calculation model, and calculating the blockage risk coefficient of the defogger at the current moment;

[0011] If it is determined that the blocking process coefficient and the blocking risk coefficient both meet the flushing start conditions, the flushing of the demister is started.

[0012] Optionally, the functional expressions of the second correlation factor and the blocking risk calculation model are determined based on expert knowledge and the fouling reaction mechanism of the demister.

[0013] Optionally, in the process of obtaining the differential pressure prediction model based on historical data driven modeling, the training samples used are constructed based on the historical operating condition data and historical demister differential pressure collection data within the first preset time period after the demister system unit overhaul.

[0014] Optionally, the method further includes:

[0015] The predicted normal differential pressure value is corrected using a compensation factor, wherein the compensation factor is determined based on the product of the demister differential pressure change caused by one overhaul of the demister system unit and the number of overhauls that have occurred to the demister unit at the current moment.

[0016] Optionally, the method further includes:

[0017] Calculate the blocking process coefficients at other times within the preset time window including the current time;

[0018] The blocking process coefficient at the current moment is updated to the sliding average of the blocking process coefficients calculated at each moment within the preset time window, so as to determine whether the blocking process coefficient and blocking risk coefficient at the current moment meet the flushing start condition.

[0019] Optionally, the method further includes:

[0020] The blocking process of the demister is graded and warned based on the blocking process coefficient.

[0021] Optionally, the method further includes:

[0022] The blockage risk of the demister is graded and alarmed according to the blockage risk coefficient.

[0023] Optionally, the flushing start condition is: the sum of the blocking process coefficient and the blocking risk coefficient at the current moment is greater than a first threshold.

[0024] Optionally, the flushing start condition is: the blockage process coefficient is greater than the second threshold and the blockage risk coefficient is greater than the third threshold.

[0025] Optionally, the flushing start condition is that a flushing demand coefficient obtained by weighted summation of the blocking process coefficient and the blocking risk coefficient at the current moment is greater than a fourth threshold.

[0026] Optionally, the first associated factors include raw flue gas flow, raw flue gas temperature, dust content, slurry circulation pump flow, slurry density, slurry pH value, raw flue gas SO2 concentration, and net flue gas SO2 concentration.

[0027] Optionally, the second correlation factor includes raw flue gas flow, raw flue gas temperature, raw flue gas SO2 concentration, slurry pH value, slurry circulation pump flow and process water main pressure.

[0028] A second aspect of an embodiment of the present invention provides a wet desulfurization mist eliminator flushing control device, the device comprising:

[0029] The actual differential pressure acquisition module is used to collect the actual differential pressure value of the demister at the current moment;

[0030] A differential pressure prediction module is configured to obtain a first correlation factor correlated with the demister differential pressure under the demister's current operating conditions, select a first characteristic variable from the first correlation factor based on the correlation with the demister differential pressure, input the first characteristic variable into a differential pressure prediction model derived from historical data-driven modeling, and predict a normal differential pressure value of the demister at the current moment;

[0031] a blockage process coefficient determination module, configured to calculate a blockage process coefficient of the defogger at a current moment based on the normal differential pressure value and the actual differential pressure value, wherein the blockage process coefficient represents a degree of change of the actual differential pressure value relative to the normal differential pressure value;

[0032] a blocking risk calculation module for obtaining a second correlation factor correlated with the blocking risk of the defogger under the current operating conditions of the defogger, screening a second characteristic variable from the second correlation factor based on the correlation with the blocking risk of the defogger, inputting the second characteristic variable into the constructed blocking risk calculation model, and calculating the blocking risk coefficient of the defogger at the current moment;

[0033] The flushing control module is used to start flushing of the demister when it is determined that the blocking process coefficient and the blocking risk coefficient both meet the flushing start conditions.

[0034] A third aspect of an embodiment of the present invention provides a computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the wet desulfurization demister flushing control method described in the first aspect of an embodiment of the present invention is implemented.

[0035] A fourth aspect of an embodiment of the present invention provides a machine-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the wet desulfurization demister flushing control method described in the first aspect of the embodiment of the present invention is implemented.

[0036] In the above technical solution, the blockage process and blockage risk of the demister are predicted, and a flushing strategy is formulated based on the above prediction content, thereby realizing on-demand flushing of the demister, effectively balancing the energy waste caused by continuous flushing of the demister and the problem that the low flushing frequency accelerates the blockage process of the demister. While ensuring the safe operation capability of the demister system, the flushing process is more economical.

[0037] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0039] Figure 1 A flow chart of a wet desulfurization mist eliminator flushing control method according to an embodiment of the present invention is schematically shown;

[0040] Figure 2 The block diagram schematically shows the composition of a wet desulfurization demister flushing control device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0042] Method Example

[0043] See Figure 1 The embodiment of the present invention provides a wet desulfurization mist eliminator flushing control method, comprising the following implementation steps:

[0044] Step S100: collecting the actual differential pressure value of the demister at the current moment.

[0045] Step S200: obtain a first correlation factor that is correlated with the defogger differential pressure under the current operating conditions of the defogger, select a first characteristic variable from the first correlation factor based on the correlation with the defogger differential pressure, input the first characteristic variable into a differential pressure prediction model obtained based on historical data-driven modeling, and predict the normal differential pressure value of the defogger at the current moment.

[0046] It can be known that the demister differential pressure is the most important parameter for judging the demister blockage process. It refers to the pressure loss generated by the flue gas passing through the demister. Under normal circumstances, the greater the flue gas flow rate, the higher the demister differential pressure. At the same time, as the demister fouling process develops, the demister differential pressure also tends to gradually increase. Therefore, within the normal life cycle of the demister, the factors that determine its differential pressure value include flue gas flow rate, flue gas velocity, flue gas SO2 concentration and other operating factors. These operating factors are the first associated factors that are correlated with the demister differential pressure. In addition, there are usually many first associated factors, and the main factors need to be screened out from the first associated factors based on the correlation with the demister differential pressure. For example, the first associated factors can be reduced in dimension by principal component analysis to obtain the first characteristic variable. The principal component analysis can use PCA analysis method, etc. This embodiment does not describe this part in detail. In addition, it is also possible to select multiple first characteristic variables that have a strong correlation with the demister differential pressure from the first associated factors by combining expert knowledge.

[0047] In a specific embodiment, the first correlation factor includes raw flue gas flow, raw flue gas temperature, dust content, slurry circulation pump flow, slurry density, slurry pH value, raw flue gas SO2 concentration, and clean flue gas SO2.

[0048] In a specific embodiment, based on expert knowledge, the first characteristic variables selected from the first correlation factors include raw flue gas flow, raw flue gas temperature, slurry circulation pump flow, and slurry density.

[0049] In a specific embodiment, the historical data driven modeling method may be an artificial neural network, partial least squares, support vector machine, multivariate linear regression, polynomial fitting and other modeling methods.

[0050] For example: Based on expert knowledge, the first characteristic variable is selected and used as the input data of the differential pressure prediction model obtained by historical data-driven modeling. The normal differential pressure value is used as the output data of the differential pressure prediction model. The differential pressure prediction model is selected as a single hidden layer BP neural network with 5 nodes. In order to ensure the generalization ability of the differential pressure prediction model and overcome the gradient vanishing and explosion problems during the training process, the input data and output data of the differential pressure prediction model are normalized, and the selected normalization method can be the minimum-maximum normalization method. The ratio of training samples to test samples is set to 7:3. It should be noted that the differential pressure prediction model is equipped with an anti-normalization link to restore the output of the differential pressure prediction model to the actual differential pressure range.

[0051] In a specific embodiment, in the process of obtaining a differential pressure prediction model based on historical data-driven modeling, the training samples used are constructed based on the historical operating condition data and historical demister differential pressure collection data within the first preset time period after the demister system unit is overhauled. Within a certain period of time after the demister system unit is overhauled, the operating condition of the demister is relatively good. At this time, the demister differential pressure value reflected by the demister differential pressure collection data is close to the differential pressure value within the normal life cycle of the demister. Therefore, the historical operating condition data within the first preset time period after the demister system unit is overhauled is selected to construct sample data for inputting the initial differential pressure prediction model, and the historical demister differential pressure collection data within the first preset time period is used to construct label data for training the differential pressure prediction model. Based on the construction of the above-mentioned training samples, the accuracy of the constructed differential pressure prediction model is improved.

[0052] Step S300 , calculating the demister blocking coefficient based on the predicted normal differential pressure value at the current moment and the collected actual differential pressure value of the demister, where the blocking coefficient represents the degree of change of the actual differential pressure value relative to the normal differential pressure value.

[0053] In step S300, the blocking process coefficient characterizes the degree of change of the actual differential pressure value relative to the normal differential pressure value, and reflects the speed of the blocking process of the defogger. It can be known that in order to reflect the degree of change of the actual differential pressure value relative to the normal differential pressure value, it is possible to obtain the difference, the ratio, etc. Therefore, for ordinary technicians in this field, they can know one or more methods for calculating the blocking process coefficient of the defogger based on the normal differential pressure value and the actual differential pressure value. For example, the ratio of the actual differential pressure value to the normal differential pressure value is determined as the blocking process coefficient, or the difference between the actual differential pressure value and the normal differential pressure value is determined as the blocking process coefficient.

[0054] Step S400: Obtain a second correlation factor that is correlated with the defogger blocking risk under the current operating conditions of the defogger, select a second characteristic variable from the second correlation factor based on the correlation with the defogger blocking risk, input the second characteristic variable into the constructed blocking risk calculation model, and calculate the blocking risk coefficient of the defogger at the current moment.

[0055] It can be known that, according to the fouling reaction mechanism of the demister, the size of the flue gas flow rate, the size of the flue gas SO2 concentration, the size of the process water pipe pressure, etc. all largely determine the degree of fouling of the demister. It can be seen that the differences in flue gas flow rate, flue gas SO2 concentration and process water pipe pressure indicate different degrees of demister blockage risk. Therefore, the flue gas flow rate, flue gas SO2 concentration, process water pipe pressure, etc. are the second related factors that are correlated with the demister blockage risk. In addition, there are usually many second related factors, and it is necessary to screen out the main factors from the second related factors based on the correlation with the demister blockage risk. For example, the second related factors can be reduced in dimension by principal component analysis to obtain the second characteristic variable. The principal component analysis can adopt PCA analysis method, etc. This embodiment does not describe this part in detail. In addition, it is also possible to select multiple second characteristic variables that have a strong correlation with the demister blockage risk from the second related factors by combining expert knowledge.

[0056] In a specific embodiment, the second correlation factors determined based on expert knowledge and scaling reaction mechanism include raw flue gas flow rate, raw flue gas temperature, raw flue gas SO2 concentration, slurry pH value, slurry circulation pump flow rate and process water main pressure.

[0057] In a specific embodiment, in combination with expert knowledge, the second characteristic variables selected from the second correlation factors include raw flue gas SO2 concentration, raw flue gas flow rate, raw flue gas temperature and process water main pressure.

[0058] In one specific embodiment, a functional expression for the blockage risk calculation model is determined based on expert knowledge and the fouling reaction mechanism. It is understood that calculating an accurate blockage risk coefficient based on the second characteristic variables requires considering the degree of impact of each second characteristic variable on demister fouling. This impact is closely related to the fouling reaction mechanism. Therefore, by combining expert knowledge and the fouling reaction mechanism, the contribution of each second characteristic variable to the demister blockage risk can be analyzed and determined. Based on this contribution, weighted coefficients for each second characteristic variable can then be derived.

[0059] For example, the functional expression of the blockage risk calculation model can be the weighted sum of each second characteristic variable. When the raw flue gas SO2 concentration, raw flue gas flow rate, raw flue gas temperature, and process water pipe pressure are used as the second characteristic variables, the functional expression of the blockage risk calculation model determined based on expert knowledge and the fouling reaction mechanism under a specific demister system operating condition is:

[0060]

[0061] In formula 1, R(t) represents the blocking risk coefficient at the current time t, T flow Indicates the original flue gas flow rate, D SO2 Indicates the original flue gas SO2 concentration, p water Indicates the process water pipe pressure, T gas Represents the original flue gas temperature, and abs() represents the absolute value.

[0062] It should be understood that Formula 1 is only a functional expression determined in combination with the specific operating conditions of the demister system. In practical applications, the functional expression of the blockage risk calculation model can be determined in combination with the specific operating conditions of the demister system.

[0063] Step S500: After the demister system is automatically put into operation, if it is determined that the current blocking process coefficient and blocking risk coefficient meet the flushing start conditions, the flushing of the demister is started. During the flushing process, if it is monitored that the absorption tower liquid level exceeds the limit, the flushing is suspended. When the absorption tower liquid level returns to the normal level, the flushing is started again.

[0064] It is known that the demister flushing process also needs to consider the liquid level of the wet flue gas desulfurization absorption tower. For example, during the flushing process, if the absorption tower liquid level is detected to be over the limit, the flushing will be suspended. When the absorption tower liquid level returns to the normal level, the flushing will be restarted. The specific implementation process includes the following:

[0065] Monitor the absorber liquid level during flushing;

[0066] If the liquid level in the absorption tower exceeds the first limit, the flushing is immediately suspended. When the liquid level in the absorption tower returns to below the second limit, the demister flushing is restarted. When the demister flushing is restarted, the flushing starts from the spray layer where the flushing was suspended. The first limit is greater than the second limit.

[0067] For example, if the flushing stops at the second spray layer, restarting the system from the second spray layer will avoid uneven flushing compared to restarting the system from the first spray layer.

[0068] It should be understood that because both the blocking progress coefficient and the blocking risk coefficient represent the need for defogger flushing, the flushing initiation conditions are determined in conjunction with the blocking progress coefficient and the blocking risk coefficient. Preferably, to facilitate determining the degree of blockage risk of the defogger based on the blocking risk coefficient, the blocking risk coefficient calculated by the blocking risk calculation model is typically normalized or output range-adjusted, and the normalized or output range-adjusted blocking risk coefficient is used to determine the flushing initiation conditions.

[0069] For example, in a specific embodiment, the flushing start condition is: the flushing demand coefficient at the current moment is greater than a first threshold, and the flushing demand coefficient at the current moment is the sum of the blocking process coefficient and the blocking risk coefficient at the current moment.

[0070] For example, in a specific embodiment, the flushing start condition is: the blockage process coefficient is greater than the second threshold and the blockage risk coefficient is greater than the third threshold.

[0071] For example, in a specific embodiment, the flushing start condition is: a flushing demand coefficient obtained by weighted summing the blocking process coefficient and the blocking risk coefficient at the current moment is greater than a fourth threshold.

[0072] As an improvement to the above embodiment, after predicting the normal differential pressure value of the demister at the current moment, the predicted normal differential pressure value is corrected using a compensation factor, wherein the compensation factor is determined by multiplying the change in the demister differential pressure due to a single overhaul of the demister system unit by the number of overhauls that have occurred on the demister unit at the current moment. The change in the demister differential pressure due to a single overhaul of the demister system unit refers to the difference between the full-load demister differential pressure before the unit is shut down for the overhaul and the full-load demister differential pressure after the overhaul.

[0073] Because during the operation of the demister system, the demister system needs to be overhauled regularly or periodically, the overhaul of the unit will bring about changes in the demister differential pressure, which usually improves the demister differential pressure. Based on this principle, it can be seen that the normal differential pressure value of the demister predicted at the current moment is lower than the true value of the normal life cycle differential pressure. By using the compensation factor to correct the predicted normal differential pressure value, the corrected normal differential pressure value is closer to the true value of the normal life cycle differential pressure, thereby improving the accuracy of the blocking process coefficient. After the accuracy of the blocking process coefficient is improved, the flushing control process based on the blocking process coefficient is more accurate.

[0074] For example, the normal differential pressure value at the current moment predicted by the differential pressure prediction model is expressed as m(t′), and the compensation factor is expressed as C(t′). Then, the corrected normal differential pressure value M(t′) can be calculated by the following formula:

[0075] M(t′)=C(t′)+m(t′) (Formula 2);

[0076] Where t′ represents the natural operating time of the demister system at the current moment, and the compensation factor C(t′) can be calculated by the following formula:

[0077]

[0078] Among them, L p It represents the difference between the full-load demister differential pressure before the unit is shut down for overhaul and the full-load demister differential pressure after the overhaul. N() represents the rounding function. T m Indicates the overhaul time interval of the demister system unit.

[0079] As another improvement of the above embodiment, before determining whether the current blocking process coefficient and blocking risk coefficient meet the flushing start condition, the wet desulfurization mist eliminator flushing control method further includes the following implementation process:

[0080] Calculate the blocking process coefficients at other times within the preset time window including the current time;

[0081] The blocking process coefficient at the current moment is updated to the sliding average of the blocking process coefficients calculated at each moment within the preset time window.

[0082] Because the obtained operating condition data of the defogger system is often subject to various external interferences, resulting in errors in the obtained first correlation factor data, the existence of the first correlation factor error may cause errors in the normal differential pressure value predicted by the differential pressure prediction model. By predicting the normal differential pressure values ​​at multiple moments in a preset time window including the current moment, the corresponding blocking process coefficient is obtained, and the blocking process coefficient at the current moment is determined as the sliding average of each blocking process coefficient in the preset time window, thereby overcoming the blocking process coefficient error caused by external interference and improving the accuracy of the blocking process coefficient. After the accuracy of the blocking process coefficient is improved, the flushing control process based on the blocking process coefficient is more accurate.

[0083] For example, the current blocking process coefficient calculated by the differential pressure prediction model is expressed as p, and the current blocking process coefficient re-determined by sliding average can be calculated by the following formula:

[0084]

[0085] Among them, s represents the number of blocking process coefficients in the preset time window, that is, the number of data; i represents the number of the blocking process coefficient, k represents the moment number of the current moment, p(k-i+1) represents the blocking process coefficient numbered i, and P(k) represents the blocking process coefficient of the current moment re-determined by sliding average.

[0086] As another improvement of the above embodiments, in one or more specific embodiments, a blocking process grading warning mechanism is also introduced. Accordingly, the wet desulfurization demister flushing control method further includes: grading and warning the blocking process of the demister according to the blocking process coefficient.

[0087] In the above embodiments, through the grading warning for the blocking process, the operator can know whether the real-time blocking process is accelerating, or too fast, or beyond the reasonable range, etc., and can carry out targeted operation and maintenance and troubleshooting in combination with the warning signal, thereby improving the reliability of the demister system.

[0088] For example, when calculating the blocking process coefficient by the method of finding the ratio, three levels of warnings are set for the blocking process of the demister. Accordingly, three warning thresholds are set, which are P1, P2, and P3 respectively, and P1 < P2 < P3. When the blocking process coefficient is higher than the warning threshold P1, a warning signal of "the blocking process of the demister is accelerating" is issued. When the blocking process coefficient is higher than the warning threshold P2, a warning signal of "the blocking process of the demister is too fast" is issued. When the blocking process coefficient is higher than the warning threshold P3, a warning signal of "the blocking of the demister exceeds the reasonable range, please check and repair in time" is issued.

[0089] As another improvement of the above embodiments, in one or more specific embodiments, a blocking risk grading alarm mechanism is also introduced. Accordingly, the wet desulfurization demister flushing control method further includes: grading and alarming the blocking risk of the demister according to the blocking risk coefficient.

[0090] In the above embodiments, through the grading alarm for the blocking risk, the operator can know the level of the real-time blocking risk, and can carry out targeted operation and maintenance and troubleshooting in combination with the alarm signal, thereby improving the reliability of the demister system.

[0091] For example, three levels of alarms are set for the blocking risk of the demister. Accordingly, three alarm thresholds are set, which are R1, R2, and R3 respectively, and R1 < R2 < R3. When the blocking risk coefficient R is higher than the alarm threshold R1, an alarm signal of "there is a certain blocking risk in the current working condition of the demister, please adjust the spraying frequency in time" is issued. When the blocking risk coefficient R is higher than the alarm threshold R2, an alarm signal of "the blocking risk in the current working condition of the demister is relatively high, please adjust the spraying frequency in time and check whether there is any abnormality in the spraying system in time" is issued. When the blocking risk coefficient R is higher than the alarm threshold R3, an alarm signal of "the blocking risk in the current working condition of the demister is high, please check whether there is any abnormality in the spraying system in time and make adjustments in time" is issued. It should be understood that the above "adjust the spraying frequency in time, check the spraying system in time", etc. are to notify the operator and let the operator carry out manual flushing when the demister system is not in automatic mode according to the alarm signal.

[0092] Under the blockage risk calculation model based on Formula 1, the three-level alarm for blockage risk can be: when the blockage risk coefficient R is greater than 0.9, it prompts: there is a certain blockage risk in the current working condition of the demister, please adjust the spraying frequency in time; when the blockage risk coefficient R is greater than 1.2, it prompts: the current working condition of the demister has a high blockage risk, please adjust the spraying frequency in time and check whether there is any abnormality in the spraying system in time; when the blockage risk coefficient R is greater than 1.4, it prompts: the blockage risk of the demister is high, please check whether there is any abnormality in the spraying system in time and make timely adjustments.

[0093] Based on the above embodiments, in a specific application, the wet desulfurization mist eliminator flushing control method includes the following implementation process:

[0094] Step SS1: collecting the actual differential pressure value of the demister at the current moment.

[0095] Step SS2: Obtain a first correlation factor under the current operating conditions of the demister, and based on expert knowledge, select a first characteristic variable from the first correlation factor. Input the first characteristic variable into the established differential pressure prediction model to predict the normal differential pressure value of the demister at the current moment. The predicted normal differential pressure value is corrected using the compensation factor determined by Equation 3. A sliding average of the corrected normal differential pressure value is then performed within a preset time window, and the sliding average calculated according to Equation 4 is used as the final normal differential pressure value of the demister at the current moment. The differential pressure prediction model is a BP neural network model.

[0096] Step SS3, calculating the ratio of the actual differential pressure value to the corrected normal differential pressure value at the current moment, and defining the ratio as the blocking process coefficient of the defogger at the current moment.

[0097] Step SS4: Obtain the second correlation factor for the current operating conditions of the demister. Based on expert knowledge and the demister fouling reaction mechanism, select a second characteristic variable from the second correlation factor. The selected second characteristic variables include four dimensions: raw flue gas SO2 concentration, raw flue gas flow rate, raw flue gas temperature, and process water pipe pressure. Input the second characteristic variable into the established blocking risk calculation model to calculate the blocking risk coefficient of the demister at the current moment. The calculated blocking risk coefficient is then normalized or output range adjusted. The functional expression of the blocking risk calculation model is shown in Equation 1.

[0098] Step SS5, determine whether the blocking process coefficient and blocking risk coefficient at the current moment after normalization or output interval adjustment meet the preset flushing start conditions. If so, start the flushing of the demister. Otherwise, do not start the flushing of the demister. During the flushing process of the demister, monitor whether the liquid level of the absorption tower exceeds the limit. If so, suspend the flushing. When the liquid level of the absorption tower returns to the normal level, start the flushing again.

[0099] Step SS6: Performing graded early warning on the blocking process of the demister according to the blocking process coefficient and performing graded alarm on the blocking risk of the demister according to the blocking risk coefficient.

[0100] Device embodiment

[0101] See Figure 2 The embodiment of the present invention provides a wet flue gas desulfurization mist eliminator flushing control device, comprising an actual differential pressure acquisition module, a differential pressure prediction module, a blocking process coefficient determination module, a blocking risk calculation module, and a flushing control module, wherein:

[0102] The actual differential pressure acquisition module is used to collect the actual differential pressure value of the demister at the current moment;

[0103] A differential pressure prediction module is configured to obtain a first correlation factor correlated with the demister differential pressure under the demister's current operating conditions, select a first characteristic variable from the first correlation factor based on the correlation with the demister differential pressure, input the first characteristic variable into a differential pressure prediction model derived from historical data-driven modeling, and predict a normal differential pressure value of the demister at the current moment;

[0104] A blockage process coefficient determination module is used to calculate the blockage process coefficient of the defogger at the current moment based on the normal differential pressure value and the actual differential pressure value. The blockage process coefficient represents the degree of change of the actual differential pressure value relative to the normal differential pressure value.

[0105] a blocking risk calculation module for obtaining a second correlation factor correlated with the blocking risk of the defogger under the current operating conditions of the defogger, screening a second characteristic variable from the second correlation factor based on the correlation with the blocking risk of the defogger, inputting the second characteristic variable into the constructed blocking risk calculation model, and calculating the blocking risk coefficient of the defogger at the current moment;

[0106] The flushing control module is used to start flushing of the demister when it is determined that the blocking process coefficient and the blocking risk coefficient meet the flushing start condition.

[0107] In a specific embodiment, the second correlation factor and the functional expression of the blockage risk calculation model are determined based on expert knowledge and the fouling reaction mechanism of the demister.

[0108] In a specific embodiment, in the process of obtaining the differential pressure prediction model based on historical data driven modeling, the training samples used are constructed based on the historical operating condition data and historical demister differential pressure collection data within the first preset time period after the demister system unit is overhauled.

[0109] In a specific embodiment, the wet desulfurization demister flushing control device also includes a correction module, which is used to correct the predicted normal differential pressure value using a compensation factor. The compensation factor is determined based on the product of the demister differential pressure change caused by an overhaul of the demister system unit and the number of overhauls that have occurred to the demister unit at the current moment.

[0110] In a specific embodiment, the wet flue gas desulfurization mist remover flushing control device also includes a sliding average module, which is used to calculate the blocking process coefficients at other moments within a preset time window including the current moment, and update the blocking process coefficient at the current moment to the sliding average of the blocking process coefficients calculated at each moment within the preset time window, so as to determine whether the blocking process coefficient and blocking risk coefficient at the current moment meet the flushing start conditions.

[0111] In a specific embodiment, the wet flue gas desulfurization demister flushing control device further includes an early warning module, which is used to provide graded early warnings on the demister's blocking process according to the blocking process coefficient and graded alarms on the demister's blocking risk according to the blocking risk coefficient.

[0112] In a specific embodiment, the flushing start condition is: the sum of the blocking process coefficient and the blocking risk coefficient at the current moment is greater than a first threshold.

[0113] In a specific embodiment, the flushing start condition is: the blockage process coefficient is greater than the second threshold and the blockage risk coefficient is greater than the third threshold.

[0114] In a specific embodiment, the flushing start condition is: a flushing demand coefficient obtained by weighted summing the blocking process coefficient and the blocking risk coefficient at the current moment is greater than a fourth threshold.

[0115] In a specific embodiment, the first correlation factor includes raw flue gas flow, raw flue gas temperature, dust content, slurry circulation pump flow, slurry density, slurry pH value, raw flue gas SO2 concentration, and net flue gas SO2 concentration.

[0116] In a specific embodiment, the second correlation factor includes raw flue gas flow rate, raw flue gas temperature, raw flue gas SO2 concentration, slurry pH value, slurry circulation pump flow rate and process water main pressure.

[0117] On the other hand, an embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, it implements any one of the wet desulfurization demister flushing control methods described in the above method embodiments.

[0118] On the other hand, an embodiment of the present invention further provides a machine-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any one of the wet desulfurization demister flushing control methods described in the above method embodiments.

[0119] On the other hand, an embodiment of the present invention further provides a processor, which is used to run a program, wherein when the program is run, any one of the wet desulfurization demister flushing control methods described in the above method embodiments is executed.

[0120] In another aspect, an embodiment of the present invention further provides a computer program product, which, when executed on a data processing device, is adapted to execute a program for initializing the following method steps:

[0121] Collect the actual differential pressure value of the demister at the current moment;

[0122] Obtaining a first correlation factor correlated with the demister differential pressure under the demister's current operating conditions, screening a first characteristic variable from the first correlation factor based on the correlation with the demister differential pressure, inputting the first characteristic variable into a differential pressure prediction model derived from historical data-driven modeling, and predicting a normal differential pressure value of the demister at the current moment;

[0123] Calculate the blocking process coefficient of the defogger at the current moment based on the normal differential pressure value and the actual differential pressure value, where the blocking process coefficient represents the degree of change of the actual differential pressure value relative to the normal differential pressure value;

[0124] Obtaining a second correlation factor correlated with the defogger blockage risk under the defogger's current operating conditions, screening a second characteristic variable from the second correlation factor based on the correlation with the defogger blockage risk, inputting the second characteristic variable into the established blockage risk calculation model, and calculating the blockage risk coefficient of the defogger at the current moment;

[0125] If it is determined that the blocking process coefficient and the blocking risk coefficient meet the flushing start conditions, the flushing of the demister is started.

[0126] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0127] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0128] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0130] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0131] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0132] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0133] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0134] The above are merely embodiments of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A wet desulfurization mist eliminator flushing control method, characterized in that: The method comprises: Collect the actual differential pressure value of the demister at the current moment; Obtaining a first correlation factor correlated with the demister differential pressure under the demister's current operating conditions, screening a first characteristic variable from the first correlation factor based on the correlation with the demister differential pressure, inputting the first characteristic variable into a differential pressure prediction model derived from historical data-driven modeling, and predicting a normal differential pressure value of the demister at the current moment; The predicted normal differential pressure value is corrected using a compensation factor, where the compensation factor is determined by multiplying the change in the demister differential pressure caused by a major overhaul of the demister system unit by the number of overhauls that have occurred to the demister unit at the current moment; Calculating a blocking process coefficient of the demister at the current moment according to the normal differential pressure value and the actual differential pressure value, wherein the blocking process coefficient represents a degree of change of the actual differential pressure value relative to the normal differential pressure value; Obtaining a second correlation factor correlated with the defogger blockage risk under the defogger's current operating conditions, screening a second characteristic variable from the second correlation factor based on the correlation with the defogger blockage risk, inputting the second characteristic variable into the established blockage risk calculation model, and calculating the blockage risk coefficient of the defogger at the current moment; If it is determined that the blocking process coefficient and the blocking risk coefficient both meet the flushing start conditions, the flushing of the demister is started.

2. The wet desulfurization demister flushing control method according to claim 1, characterized in that: The functional expressions of the second correlation factor and the blocking risk calculation model are determined based on expert knowledge and the fouling reaction mechanism of the demister.

3. The wet desulfurization demister flushing control method according to claim 1, characterized in that: In the process of obtaining the differential pressure prediction model based on historical data-driven modeling, the training samples used are constructed based on the historical operating condition data and historical demister differential pressure collection data within the first preset time period after the demister system unit overhaul.

4. The wet desulfurization demister flushing control method according to claim 1, characterized in that: The method further comprises: Calculate the blocking process coefficients at other times within the preset time window including the current time; The blocking process coefficient at the current moment is updated to the sliding average of the blocking process coefficients calculated at each moment within the preset time window, so as to determine whether the blocking process coefficient and blocking risk coefficient at the current moment meet the flushing start condition.

5. The wet desulfurization demister flushing control method according to claim 1, characterized in that: The method further comprises: The blocking process of the demister is graded and warned based on the blocking process coefficient.

6. The wet desulfurization demister flushing control method according to claim 1, characterized in that: The method further comprises: The blockage risk of the demister is graded and alarmed according to the blockage risk coefficient.

7. The wet desulfurization demister flushing control method according to claim 1, characterized in that: The flushing start condition is that the sum of the blocking process coefficient and the blocking risk coefficient at the current moment is greater than a first threshold.

8. The wet desulfurization demister flushing control method according to claim 1, characterized in that: The flushing start condition is: the blocking process coefficient is greater than the second threshold and the blocking risk coefficient is greater than the third threshold.

9. The wet desulfurization mist eliminator flushing control method according to claim 1, characterized in that: The flushing start condition is that a flushing demand coefficient obtained by weighted summation of the blocking process coefficient and the blocking risk coefficient at the current moment is greater than a fourth threshold.

10. The wet desulfurization mist eliminator flushing control method according to claim 1, characterized in that: The first correlation factors include raw flue gas flow, raw flue gas temperature, dust content, slurry circulation pump flow, slurry density, slurry pH value, raw flue gas SO2 concentration, and net flue gas SO2 concentration.

11. The wet desulfurization demister flushing control method according to claim 1, characterized in that: The second correlation factors include raw flue gas flow, raw flue gas temperature, raw flue gas SO2 concentration, slurry pH value, slurry circulation pump flow and process water main pressure.

12. A wet desulfurization mist eliminator flushing control device, characterized in that: The device comprises: The actual differential pressure acquisition module is used to collect the actual differential pressure value of the demister at the current moment; A differential pressure prediction module is configured to obtain a first correlation factor correlated with the demister differential pressure under the demister's current operating conditions, select a first characteristic variable from the first correlation factor based on the correlation with the demister differential pressure, input the first characteristic variable into a differential pressure prediction model derived from historical data-driven modeling, and predict a normal differential pressure value of the demister at the current moment; A correction module is used to correct the predicted normal differential pressure value using a compensation factor, where the compensation factor is determined by multiplying the change in the demister differential pressure caused by an overhaul of the demister system unit by the number of overhauls that have occurred to the demister unit at the current moment; a blockage process coefficient determination module, configured to calculate a blockage process coefficient of the defogger at a current moment based on the normal differential pressure value and the actual differential pressure value, wherein the blockage process coefficient represents a degree of change of the actual differential pressure value relative to the normal differential pressure value; a blocking risk calculation module for obtaining a second correlation factor correlated with the blocking risk of the defogger under the current operating conditions of the defogger, screening a second characteristic variable from the second correlation factor based on the correlation with the blocking risk of the defogger, inputting the second characteristic variable into the constructed blocking risk calculation model, and calculating the blocking risk coefficient of the defogger at the current moment; The flushing control module is used to start flushing of the demister when it is determined that the blocking process coefficient and the blocking risk coefficient both meet the flushing start conditions.

13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the wet desulfurization mist eliminator flushing control method according to any one of claims 1 to 11 is implemented.

14. A machine-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the wet desulfurization mist eliminator flushing control method according to any one of claims 1 to 11 is implemented.

Images