Thermal power generating unit SO2 emission automatic control system based on historical operation data

Abstract

The invention relates to the technical field of desulfurization of coal-fired power generating units, in particular to a thermal power generating unit SO2 emission automatic control system based on historical operation data, which comprises a detection subsystem, a prediction control subsystem, a historical data analysis subsystem, a correction subsystem, a main control subsystem and a driving subsystem, historical data are classified and screened by adopting the historical data analysis subsystem, so that classification of operation combinations of slurry circulating pumps can be determined, optimal combination operation of the slurry circulating pump set can be realized by adopting a clustering algorithm, and the SO2 content is predicted in advance by adopting the prediction control subsystem. The PH value of the desulfurization absorption tower is accurately controlled through the control subsystem, the flue gas flow is corrected through the correction subsystem, distortion of test point data due to temperature influence can be avoided, and automatic, efficient, safe, environment-friendly and stable operation of the desulfurization system is achieved through accurate control of the PH value of the desulfurization absorption tower and optimal combination of the slurry circulating pump set.

Description

Technical Field

[0001] The invention relates to the technical field of desulfurization of coal-fired power generation units, and in particular to an automatic control system for SO2 emission of thermal power generation units based on historical operation data. Background Art

[0002] The air pollution caused by coal burning in my country, especially the pollution caused by SO2 emissions, has seriously affected people's normal production and life. Therefore, in order to protect the environment, it is necessary to control the SO2 emissions of coal-fired power plants. At present, there are three main ways to control SO2 emissions from coal-fired power plants: desulfurization before combustion, desulfurization during combustion, and desulfurization after combustion. Among them, post-combustion desulfurization, namely flue gas desulfurization, is currently the most effective way to control and is also a method commonly used internationally. Among the flue gas desulfurization methods, limestone-gypsum wet flue gas desulfurization is currently a commonly used technology.

[0003] The limestone-gypsum wet flue gas desulfurization process uses limestone as the alkaline desulfurization absorbent. The limestone blocks are pre-crushed and mixed with water in a ball mill to form a slurry. The slurry is pumped to the desulfurization absorption tower. The fresh desulfurizer enters the slurry pool of the absorption tower and mixes with the circulating slurry. The circulating slurry is pumped to the spray layer on the top of the tower and dispersed into mist droplets by the nozzle. The mist slurry droplets mix and contact with the acidic flue gas during the falling process. The calcium carbonate in the slurry droplets undergoes a series of physical and chemical absorption reactions with the SO2 in the flue gas to generate calcium sulfite. At the same time, as the pH value decreases, the calcium sulfite further reacts with the oxygen in the oxidizing air in the absorption tower slurry pool to generate calcium sulfate. After the calcium sulfate reaches a certain saturation, it crystallizes and precipitates to eventually generate gypsum (CaSO4·H2O). The flue gas after desulfurization is discharged into the chimney after the fine droplets carried by the flue gas are removed by the demister. The gypsum slurry discharged from the absorption tower is concentrated and dehydrated by the dehydration system, and the gypsum is sold as a by-product. The wastewater is partially reused after simple treatment, and the discharged wastewater is discharged after treatment. The whole process mainly includes the absorption tower system, limestone slurry preparation system, and gypsum dehydration treatment system. The absorption tower has two outlets, one for the gypsum slurry outlet, which detects the real-time pH, that is, the pH of the gypsum slurry outlet; the other outlet is the clean flue gas outlet, which detects the concentration of SO2, that is, the concentration of SO2 at the clean flue gas outlet.

[0004] There are two main methods for controlling pH value of the absorption tower. One is the most common cascade control system, where the main loop is pH value control and the inner loop is limestone slurry flow control; the other is the most basic single closed-loop PID control. Due to the large delay and large inertia of pH value changes in the absorption tower, the above two conventional control methods have poor automatic control effects and weak anti-disturbance capabilities during actual operation, and even cannot be put into automatic operation. After the unit is put into AGC, there are problems such as frequent load changes and large amplitude changes, resulting in a large change in flue gas flow, which makes it impossible for the desulfurization system to track the changes in flue gas flow well, resulting in lag in automatic control of pH value and large fluctuations.

[0005] At the same time, the current combined operation mode of the slurry circulation pump mostly relies on the manual start and stop of the operator. In order to ensure that the outlet SO2 emission concentration does not exceed the set value, more slurry replenishment, multiple pump start-up, and multiple high-power pump start-up methods are used to ensure that the outlet SO2 emission concentration is at a low level, which leads to high energy consumption operation of the desulfurization system and affects the economy of the unit.

[0006] To sum up, in the process of controlling SO2 emissions by flue gas desulfurization, the desulfurization system has the problem that the automatic control of SO2 emissions cannot be put into use, the limestone consumption is large, the slurry circulation pump is frequently started and stopped manually, the desulfurization system has high energy consumption, and the operating personnel have a large workload to manually operate the desulfurization system equipment. At the same time, the existing control methods such as cascade control and single closed-loop PID control cannot cope with the characteristics of large delay and large inertia of the pH value of the absorption tower. The pH value of the absorption tower cannot be accurately controlled, resulting in excessive SO2 emissions, causing environmental problems. Summary of the invention

[0007] The purpose of the present invention is to provide an automatic control system for SO2 emissions from thermal power units based on historical operating data, which solves the technical problems of the existing desulfurization system, namely, the inability to put SO2 emission automatic control into operation, large limestone consumption, frequent manual start and stop of the slurry circulation pump, high energy consumption of the desulfurization system, large workload for operators to manually operate the desulfurization system equipment, and inability to cope with the large inertia and hysteresis of the pH value of the absorption tower and poor anti-disturbance ability.

[0008] To achieve the above-mentioned object, the present invention provides an automatic control system for SO2 emission of thermal power units based on historical operation data, comprising a detection subsystem, a prediction control subsystem, a historical data analysis subsystem, a correction subsystem, a main control subsystem and a drive subsystem, wherein the prediction control subsystem, the historical data analysis subsystem and the correction subsystem are respectively connected to the main control subsystem, and the detection subsystem, the main control subsystem and the drive subsystem are connected in sequence;

[0009] The detection subsystem is used to detect the pH value and SO2 concentration at the outlet of the absorption tower in real time, and transmit the detection results to the main control subsystem;

[0010] The predictive control subsystem is used to analyze and obtain the three parameters of flue gas flow, inlet SO2 concentration, and outlet SO2 concentration according to the calcium-sulfur ratio principle, so as to predict the SO2 content in advance;

[0011] The historical data analysis subsystem is used to classify and screen the historical data to determine the classification of the operation combination of the slurry circulation pump;

[0012] The correction subsystem is used to correct the smoke flow rate to prevent the test point from being distorted;

[0013] The main control subsystem is used to receive the detection results of the detection subsystem, analyze and compare the detection results with the analysis results, calculate the optimal combination of the slurry circulation pump under the current working conditions, and control the start and stop of the driving subsystem;

[0014] The driving subsystem is used to automatically discharge SO2 and control the emission amount of SO2.

[0015] The detection subsystem measures the SO2 concentration by volume flow measurement.

[0016] Among them, the working mode of the predictive control subsystem is: select the dynamic inverse of the model, add a suitable differential algorithm when the model is accurate, and analyze the three parameters of flue gas flow, inlet SO2 concentration, and outlet SO2 concentration based on the calcium-sulfur ratio principle.

[0017] Wherein, the historical data analysis subsystem includes an expert library module and an algorithm analysis module, and the algorithm analysis module is connected to the expert library module;

[0018] The expert database module is used to export the historical operation data of the main control subsystem for one year and create an expert database based on the data;

[0019] The algorithm analysis module is used to classify the data in the expert database according to different slurry circulation pump operation combinations, while paying attention to eliminating the import and export SO2 meter calibration data, PH meter calibration, flushing and other data in the data, to determine the classification of the slurry circulation pump operation combination.

[0020] Among them, the characteristic parameters included in the operation combination of the slurry circulation pump are flue gas flow rate, inlet SO2 concentration, outlet SO2 concentration, and absorption tower pH value.

[0021] Among them, there is a qualitative and quantitative relationship between the flue gas flow rate, inlet SO2 concentration, and outlet SO2 concentration in the characteristic parameters included in the operation combination of the slurry circulation pump, that is: flue gas flow rate*(inlet SO2 concentration-outlet SO2 concentration)=SO2 flow rate.

[0022] The correction subsystem uses an ambient temperature compensation coefficient to correct the measured value of the flue gas flow rate.

[0023] The present invention discloses an automatic control system for SO2 emission of thermal power units based on historical operation data. The present invention classifies and screens historical data by using the historical data analysis subsystem, thereby determining the classification of the operation combination of the slurry circulation pump, so that the clustering algorithm can be used to achieve the optimal combination operation of the slurry circulation pump group. The prediction control subsystem is used to predict the SO2 content in advance, thereby achieving precise control of the pH value of the desulfurization absorption tower. The correction subsystem is used to correct the flue gas flow rate, thereby avoiding distortion of the test point data due to temperature. The precise control of the pH value of the desulfurization absorption tower and the optimal combination of the slurry circulation pump group achieve automatic, efficient, safe, environmentally friendly and stable operation of the desulfurization system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0025] Figure 1 It is a control principle diagram of the automatic control system for SO2 emission of thermal power units based on historical operation data according to the first embodiment of the present invention.

[0026] Figure 2 It is a normal distribution diagram of the 2 / 4 pump combination mode of the first embodiment of the present invention.

[0027] Figure 3 It is a variation trend diagram of the induced draft fan current and the flue gas flow rate according to the first embodiment of the present invention.

[0028] In the figure: 101 - detection subsystem, 102 - prediction control subsystem, 103 - historical data analysis subsystem, 104 - correction subsystem, 105 - main control subsystem, 106 - driving subsystem, 107 - expert library module, 108 - algorithm analysis module. DETAILED DESCRIPTION

[0029] Embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0030] First embodiment:

[0031] See also Figures 1 to 3The present invention provides an automatic control system for SO2 emissions from thermal power units based on historical operating data, including a detection subsystem, a prediction control subsystem, a historical data analysis subsystem, a correction subsystem, a main control subsystem and a drive subsystem. The historical data analysis subsystem includes an expert library module and an algorithm analysis module.

[0032] In this embodiment, the present invention classifies and screens historical data by using the historical data analysis subsystem, thereby determining the classification of the operating combination of the slurry circulation pump, so that the clustering algorithm can be used to achieve the optimal combination operation of the slurry circulation pump group, and the predictive control subsystem is used to predict the SO2 content in advance, thereby achieving precise control of the pH value of the desulfurization absorption tower, and the correction subsystem is used to correct the flue gas flow rate, thereby avoiding the distortion of the test point data due to temperature, and through the precise control of the pH value of the desulfurization absorption tower and the optimal combination of the slurry circulation pump group, the automatic, efficient, safe, environmentally friendly and stable operation of the desulfurization system is achieved.

[0033] Wherein, the prediction control subsystem, the historical data analysis subsystem, and the correction subsystem are respectively connected to the main control subsystem, and the detection subsystem, the main control subsystem, and the driving subsystem are connected in sequence;

[0034] The detection subsystem is used to detect the pH value and SO2 concentration at the outlet of the absorption tower in real time, and transmit the detection results to the main control subsystem;

[0035] The predictive control subsystem is used to analyze and obtain the three parameters of flue gas flow, inlet SO2 concentration, and outlet SO2 concentration according to the calcium-sulfur ratio principle, so as to predict the SO2 content in advance;

[0036] The historical data analysis subsystem is used to classify and screen the historical data to determine the classification of the operation combination of the slurry circulation pump;

[0037] The correction subsystem is used to correct the smoke flow rate to prevent the test point from being distorted;

[0038] The main control subsystem is used to receive the detection results of the detection subsystem, analyze and compare the detection results with the analysis results, calculate the optimal combination of the slurry circulation pump under the current working conditions, and control the start and stop of the driving subsystem;

[0039] The driving subsystem is used to automatically discharge SO2 and control the emission amount of SO2.

[0040] Secondly, the detection subsystem measures the SO2 concentration by volume flow measurement.

[0041] Again, the working mode of the predictive control subsystem is: select the dynamic inverse of the model, add a suitable differential algorithm when the model is accurate, and analyze the parameters of flue gas flow, inlet SO2 concentration, and outlet SO2 concentration based on the calcium-sulfur ratio principle. The predictive control subsystem uses a low-pass filter to improve the robustness of the subsystem, thereby reducing the adverse effects caused by external disturbances and improving a certain degree of adaptability.

[0042] At the same time, the algorithm analysis module is connected to the expert library module;

[0043] The expert database module is used to export the historical operation data of the main control subsystem for one year and create an expert database based on the data;

[0044] The algorithm analysis module is used to classify the data in the expert database according to different slurry circulation pump operation combinations, while paying attention to eliminating the import and export SO2 meter calibration data, PH meter calibration, flushing and other data in the data, to determine the classification of the slurry circulation pump operation combination.

[0045] In addition, the operation combinations of the slurry circulation pump are specifically classified into eight types, and the eight combinations cover all the operation load sections of the unit, as shown in the following table.

[0046]

[0047] In addition, the characteristic parameters included in the operating combination of the slurry circulation pump are flue gas flow rate, inlet SO2 concentration, outlet SO2 concentration, and absorption tower pH value. There is a qualitative and quantitative relationship between the flue gas flow rate, inlet SO2 concentration, and outlet SO2 concentration among the characteristic parameters included in the operating combination of the slurry circulation pump, namely: flue gas flow rate*(inlet SO2 concentration-outlet SO2 concentration)=SO2 flow rate.

[0048] Finally, the correction subsystem uses the ambient temperature compensation coefficient to correct the measured value of the flue gas flow rate.

[0049] When using an automatic control system for SO2 emissions from thermal power plants based on historical operating data of this embodiment, the detection subsystem is used to detect the pH value and SO2 concentration at the outlet of the absorption tower in real time, and the detection results are transmitted to the main control subsystem, so that the main control subsystem can receive the detection results of the detection subsystem, and transmit the detection results to the prediction control subsystem, the historical data analysis subsystem and the correction subsystem respectively, so that the prediction control subsystem can analyze the three parameters of flue gas flow, inlet SO2 concentration and outlet SO2 concentration according to the calcium-sulfur ratio principle to predict the SO2 content in advance, so that the main control subsystem can receive the detection results of the detection subsystem, and transmit the detection results to the prediction control subsystem, the historical data analysis subsystem and the correction subsystem respectively, so that the prediction control subsystem can analyze the three parameters of flue gas flow, inlet SO2 concentration and outlet SO2 concentration according to the calcium-sulfur ratio principle to predict the SO2 content in advance, so that the main control subsystem can receive the detection results of the detection subsystem, and transmit the detection results to the prediction control subsystem, the historical data analysis subsystem and the correction subsystem respectively, so that the main ..., so as to predict the SO2 content in advance, so The historical data analysis subsystem classifies and screens the historical data, determines the classification of the operating combination of the slurry circulation pump, and allows the correction subsystem to correct the flue gas flow to prevent test point distortion. Afterwards, the predictive control subsystem, the historical data analysis subsystem and the correction subsystem respectively feed back the analysis results to the main control subsystem, so that the main control subsystem will analyze and compare the test results with the analysis results, calculate the optimal combination of the slurry circulation pump under the current working conditions, and control the start and stop of the drive subsystem. When the drive subsystem is started, SO2 can be automatically discharged and the emission of SO2 can be controlled.

[0050] The specific working mode of the above control process is as follows:

[0051] 1. Introduce the predictive control subsystem into the main control subsystem, so that the matrix operation can be converted into transfer function calculation, reducing the resource occupancy rate of the main control subsystem. The essence of the internal model control (IMC) idea is to realize the structure of parallel connection and combination of the internal model and the actual controlled object. By allowing the predictive control subsystem to select the dynamic inverse of the model, when the model is accurate, the entire control subsystem is equivalent to an open-loop following system. At the same time, a suitable differential action is added, which is equivalent to the reference trajectory of the predictive control, so that the performance of the closed-loop system is satisfied as much as possible, and then a low-pass filter is used to improve the robustness of the system, thereby reducing the adverse effects caused by external disturbances and improving a certain degree of adaptability.

[0052] The simulation program of the predictive control subsystem is as follows:

[0053] e=R-(y-y0);

[0054] E0(i) = e;

[0055] ximc1=Af*ximc1+Bf / K1*e;

[0056] f1=ximc1+T0 / Tf / K1*e;

[0057] ximc2 = Af*ximc2 + Bf*f1;

[0058] f2 = ximc2 + T0 / Tf*f1;

[0059] u=f2;

[0060] U0(i)=u;

[0061] x01=A0*x01+K1*B0*u;

[0062] x02=A0*x02+B0*x01;

[0063] y0=x02;

[0064] Y0(i)=y0;

[0065] When the model object adopts the first order, the pure delay time is identified as 130 seconds according to the actual situation on site, the inertia time is 16 minutes, the object gain is 1.6, and the filter time parameter is 450 seconds. After simulation, the controller output basically meets the actual needs of the site.

[0066] 2. Use historical data to create the expert library module to guide operators in real time, and use normal distribution calculation method to clean historical data to prevent extreme working conditions.

[0067] Parameters were adjusted based on the main basis provided by the operation, and dimensionality reduction processing was performed. It was found that due to the changes in coal quality, parameters such as load and coal combustion amount could not truly reflect the actual SO2 content in the flue gas. At the same time, according to the calcium-sulfur ratio principle, it was analyzed that the three parameters of flue gas flow, inlet SO2 concentration, and outlet SO2 concentration can basically reflect the SO2 content in the actual system. At the same time, combined with different PH values ​​under different slurry circulation pump combinations, the desulfurization capacity of the absorption tower is basically reflected.

[0068] In summary, under different working conditions, the cluster center characteristic parameters of different combinations of slurry circulation pumps are: flue gas flow rate, inlet SO2 concentration, outlet SO2 concentration, and absorption tower pH value. There is a qualitative and quantitative relationship between the first three parameters, namely: flue gas flow rate*(inlet SO2 concentration-outlet SO2 concentration)=SO2 flow rate. Therefore, the cluster characteristic parameters are two parameters, namely: SO2 flow rate and absorption tower pH value.

[0069] One year of DCS historical operation data was exported, and the data was classified according to different slurry circulation pump operation combinations. At the same time, the import and export SO2 instrument calibration data, PH instrument calibration, flushing data and other data were eliminated. After screening the above data, eight slurry circulation pump operation combinations were determined. These eight combinations cover all operating load sections of the unit, as shown in the following table.

[0070] Serial number Combination PH Center <![CDATA[SO2 Flow Center (mg / h)]]> 1 21 / 22 5.35 1154676028.12 2 21 / 24 5.30 1465335442.56 3 22 / 23 5.49 1442111076.48 4 21 / 22 / 23 5.19 1680252212.54 5 21 / 22 / 24 5.30 1887181494.29 6 21 / 23 / 24 5.13 2149831246.31 7 21 / 22 / 23 / 24 5.22 2635834727.10 8 21 / 22 / 23 / 24 / 25 5.19 2900553916.82

[0071] In order to prevent the existence of extreme distribution in classified data, a normal distribution graph is drawn for each combination of data. The normal distribution formula is shown below, where the mean is the cluster center of the data.

[0072]

[0073] Take the SO2 flow rate as an example for calculation: The normal distribution diagram of the 2 / 4 pump combination is as follows: Figure 2 As shown, the center of the data is 1.47*109. By comparing the center value with the normal distribution graph, it can be seen that the center of the data is consistent with the actual situation and there is no extreme distribution. The same applies to other combinations.

[0074] 3. Use soft measurement to correct the flue gas flow rate to prevent distortion of the measuring point. The flue gas flow rate is measured by volume flow rate. The measured values ​​in winter and summer are greatly affected by the ambient temperature, which leads to deviations in the measured data and the combination method does not conform to the actual situation. It was found in the simulation that the measured data of the flue gas flow rate in summer is too large, but the actual data is too small, which leads to a larger calculated output of the slurry circulation pump combination; similarly, the measured data of the flue gas flow rate in winter is too small, but the actual data is too large, which leads to the slurry circulation pump combination derived from the historical data in summer not conforming to the actual operating conditions in winter. Based on the above problems, the ambient temperature compensation coefficient is used to correct the measured values, which are described in detail as follows:

[0075] Through correlation analysis of related variables, we can find out the related variables that are not affected by ambient temperature and can reflect the influence of ambient temperature for soft measurement correction. Through curve analysis, we can find that the trend of changes in induced draft fan current, flue gas flow rate, etc. are consistent and have strong correlation, such as Figure 3 As shown. At the same time, the induced draft fan current reflects the impact of coal type changes on flue gas flow to a certain extent. At the same time, under the same working conditions in winter and summer, the induced draft fan current in summer is about 20A greater than that in winter. This result also verifies the results of the above analysis: the measured data of flue gas flow in summer is too large, but the actual data is too small (low density); the measured data of flue gas flow in winter is too small, but the actual data is too large (high density).

[0076] Based on this, the magnitude of the induced draft fan current in winter and summer under the same load is found out respectively, and the coefficient correction is performed as shown in the following table. The corrected data can not only optimize the combination of the slurry circulation pump group, but also improve the pH control accuracy of the desulfurization absorption tower, making SO2 emission control more refined.

[0077] Serial number load Summer induced draft fan current Winter induced draft fan current Correction factor 1 350MW 270A 235A 1.15 2 300MW 232A 205A 1.13 3 250MW 190A 178A 1.07 4 200MW 160A 150A 1.07 5 175MW 153A 140A 1.09

[0078] 4. Use mature clustering big data calculation methods to calculate the optimal combination of slurry circulation pumps under current working conditions.

[0079] According to the calculated characteristic data center value, clustering is used in different working conditions in real time.

[0080] The center distance minimum method determines the optimal slurry circulation pump combination and recommends it to the pre-disk operator. The center calculation formula uses the Euclidean distance formula, as shown in the following formula 1:

[0081]

[0082] What is disclosed above is only one or more preferred embodiments of the present application, and cannot be used to limit the scope of rights of the present application. Ordinary technicians in this field can understand that all or part of the processes of implementing the above embodiments and equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. An automatic control system for SO2 emissions from thermal power plants based on historical operating data, characterized in that: It includes a detection subsystem, a prediction control subsystem, a historical data analysis subsystem, a correction subsystem, a main control subsystem and a drive subsystem, wherein the prediction control subsystem, the historical data analysis subsystem and the correction subsystem are respectively connected to the main control subsystem, and the detection subsystem, the main control subsystem and the drive subsystem are connected in sequence; The detection subsystem is used to detect the pH value and SO2 concentration at the outlet of the absorption tower in real time, and transmit the detection results to the main control subsystem; The predictive control subsystem is used to analyze and obtain the three parameters of flue gas flow, inlet SO2 concentration, and outlet SO2 concentration according to the calcium-sulfur ratio principle, so as to predict the SO2 content in advance; The historical data analysis subsystem is used to classify and screen the historical data to determine the classification of the operation combination of the slurry circulation pump; The correction subsystem is used to correct the smoke flow rate to prevent the test point from being distorted; The main control subsystem is used to receive the detection results of the detection subsystem, analyze and compare the detection results with the analysis results, calculate the optimal combination of the slurry circulation pump under the current working conditions, and control the start and stop of the driving subsystem; The driving subsystem is used to automatically discharge SO2 and control the emission amount of SO2.

2. The automatic control system for SO2 emission from thermal power plants based on historical operation data according to claim 1, characterized in that: The detection subsystem measures the SO2 concentration by volume flow measurement.

3. The automatic control system for SO2 emission from thermal power plants based on historical operation data according to claim 1, characterized in that: The working mode of the predictive control subsystem is: select the dynamic inverse of the model, add a suitable differential algorithm when the model is accurate, and analyze and obtain the parameters of flue gas flow, inlet SO2 concentration and outlet SO2 concentration based on the calcium-sulfur ratio principle.

4. The automatic control system for SO2 emission from thermal power plants based on historical operation data according to claim 1, characterized in that: The historical data analysis subsystem includes an expert library module and an algorithm analysis module, and the algorithm analysis module is connected to the expert library module; The expert database module is used to export the historical operation data of the main control subsystem for one year and create an expert database based on the data; The algorithm analysis module is used to classify the data in the expert database according to different slurry circulation pump operation combinations, while paying attention to eliminating the import and export SO2 meter calibration data, PH meter calibration, flushing and other data in the data, to determine the classification of the slurry circulation pump operation combination.

5. The automatic control system for SO2 emission from thermal power plants based on historical operation data according to claim 4, characterized in that: The characteristic parameters included in the operation combination of the slurry circulation pump are flue gas flow rate, inlet SO2 concentration, outlet SO2 concentration, and absorption tower pH value.

6. The automatic control system for SO2 emission from thermal power plants based on historical operation data according to claim 5, characterized in that: There is a qualitative and quantitative relationship between the flue gas flow rate, inlet SO2 concentration, and outlet SO2 concentration in the characteristic parameters included in the operation combination of the slurry circulation pump, that is: flue gas flow rate*(inlet SO2 concentration-outlet SO2 concentration)=SO2 flow rate.

7. The automatic control system for SO2 emission from thermal power plants based on historical operation data according to claim 1, characterized in that: The correction subsystem uses the ambient temperature compensation coefficient to correct the measured value of the flue gas flow rate.

Images