A control method of a semi-dry deacidification process and related equipment

Abstract

The application provides a kind of semi-dry deacidification process control method and related equipment, obtain pollutant real-time concentration and flue gas real-time temperature;With the conversion value of pollutant real-time concentration as key parameter;Predict the first state signal representing whether the future pollutant concentration exceeds the standard;Second state signal and third state signal representing whether slurry valve and cooling water valve are in dead zone are identified;Based on pollutant real-time concentration, the first state signal and the second state signal, generate fusion state value and opening compensation value;Based on the first controller, each key parameter, fusion state value and opening compensation value, generate the first target opening;Match opening value is calculated based on third state signal and opening compensation value;Based on the second controller, flue gas real-time temperature and matching opening value, generate the second target opening;Based on the first target opening and the second target opening control corresponding valve, so as to realize multivariable intelligent decision, and actively eliminate the influence of dead zone on control effectiveness.

Description

Technical Field

[0001] This invention relates to the field of emission control technology, specifically to a control method and related equipment for a semi-dry desulfurization process. Background Technology

[0002] The rotary spray semi-dry acid removal process (SDA) is a core component of waste-to-energy flue gas purification systems. It primarily uses atomizers to finely atomize lime slurry, which then reacts efficiently with acidic gases (such as HCl and SO2) in the flue gas within a reaction tower. This process is widely used in the industry due to its advantages in construction and operating costs. However, the complex composition and large fluctuations in calorific value of the waste fed into the furnace result in highly nonlinear, long-time-delay, and strongly coupled characteristics in the flue gas parameters (flow rate, temperature, and acid gas concentration), posing significant challenges to the stable, economical, and environmentally friendly operation of the acid removal system. The main control targets for the semi-dry acid removal process are SO2 and HCl emission concentrations, which need to be kept below a certain level, such as an hourly average of 60 mg / m³. 3 And the daily average is 40 mg / m³ 3 This places high demands on the overall control system. Balancing economy and deacidification effect is a key challenge. Simultaneously, the flue gas temperature after the reaction tower must not be too low and must be maintained within a reasonable range. Therefore, conventional control equipment consists of slurry valves and cooling water valves. The slurry valves control the flow rate of the deacidification agent, while the cooling water valves control the total water volume.

[0003] Existing control methods for semi-dry deacidification processes lack multivariate intelligent decision-making capabilities. Most existing control methods are single-loop or simple cascade PID controllers, lacking the ability to comprehensively analyze and predict multiple key parameters and make collaborative optimization decisions. Furthermore, existing control methods are prone to flow dead zones when switching between open and closed states of the slurry valve and the cooling water valve; the flow rate remains unchanged for a significant range, affecting the effectiveness of control. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a control method and related equipment for a semi-dry deacidification process, so as to achieve multivariate intelligent decision-making and actively eliminate the impact of dead zones on control effectiveness.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] The first aspect of this invention discloses a method for controlling a semi-dry deacidification process, the method comprising:

[0007] Obtain the real-time concentration of pollutants and the real-time temperature of flue gas at the chimney outlet;

[0008] Based on the real-time concentration of the pollutant, multiple conversion values ​​are obtained, and the real-time concentration of the pollutant and each of the conversion values ​​are used as key parameters.

[0009] The first state signal is predicted to characterize whether the pollutant concentration at the chimney outlet exceeds the standard in the future period.

[0010] The second state signal characterizing whether the slurry valve is in the dead zone and the third state signal characterizing whether the cooling water valve is in the dead zone are identified.

[0011] A fusion state value is generated using the real-time concentration of the pollutant and the first state signal, and an opening compensation value is generated using the real-time concentration of the pollutant, the first state signal, and the second state signal.

[0012] Based on the preset first controller, each of the key parameters, the fusion state value, and the opening compensation value, a first target opening is generated;

[0013] Based on the third state signal and the opening compensation value, the matching opening value is calculated;

[0014] A second target opening is generated based on the preset second controller, the real-time temperature of the flue gas, and the matching opening value;

[0015] The slurry valve is controlled based on the first target opening degree, and the cooling water valve is controlled based on the second target opening degree.

[0016] Optionally, the prediction obtains a first state signal characterizing whether the pollutant concentration at the chimney outlet exceeds the standard in a future period, including:

[0017] Obtain real-time operating parameters of the flue gas generation system;

[0018] The real-time concentration of the pollutants and the real-time operating parameters are input into a pre-trained prediction model to obtain a first state signal characterizing whether the pollutant concentration at the chimney outlet exceeds the standard in a future period.

[0019] Optionally, the identification of a second state signal characterizing whether the slurry valve is in a dead zone and a third state signal characterizing whether the cooling water valve is in a dead zone includes:

[0020] The first opening change value and the first flow rate change value of the slurry valve are obtained, and based on the first opening change value and the first flow rate change value, a second state signal characterizing whether the slurry valve is in the dead zone is identified.

[0021] The second opening change value and the second flow rate change value of the cooling water valve are obtained, and based on the second opening change value and the second flow rate change value, a third state signal characterizing whether the cooling water valve is in the dead zone is identified.

[0022] Optionally, the real-time concentration of the pollutants includes: real-time concentration of SO2 and real-time concentration of HCl;

[0023] The step of generating a fusion state value using the real-time pollutant concentration and the first state signal, and generating an aperture compensation value using the real-time pollutant concentration, the first state signal, and the second state signal, includes:

[0024] Using the formula: Generate fusion state values;

[0025] Using the formula: Generate opening compensation values; where, The real-time concentration of SO2, S is the preset value for SO2 concentration. HCl S represents the real-time concentration of HCl. HCl_set The HCl concentration is a preset value, T1 is the first state signal, T2 is the second state signal, D1 is the first opening change value, and k1, k2, and k3 are weighting coefficients. Optionally, generating the first target opening based on the preset first controller, each of the key parameters, the fusion state value, and the opening compensation value includes:

[0026] For each of the key parameters, calculate the deviation value between it and the corresponding preset value of the key parameter;

[0027] Select target deviation values ​​that meet the preset activation conditions from the various deviation values;

[0028] Using the formula: sum(max(-10,min(ki*(SS)) set )*S i ,10)))+S7, calculate the control target; where ki is the weight coefficient, S is each of the key parameters, S set Each of the aforementioned key parameters corresponds to a preset value for that key parameter, S. i For the activation state of each of the aforementioned deviation values, (SS) set )*S i S7 represents the fusion state value, where each target deviation value represents a different value; the activation state of each deviation value is determined by the formula... Calculate, where K is a constant coefficient;

[0029] The control target is input into a preset first controller to obtain the opening degree to be compensated;

[0030] The opening value is used to compensate the opening to be compensated, thereby generating a first target opening.

[0031] Optionally, calculating the matching opening value based on the third state signal and the opening compensation value includes:

[0032] The matching opening value is calculated using the formula: k4*T3*D2-k5*K2; where k4 and k5 are constant coefficients, T3 is the third state signal, K2 is the opening compensation value, and D2 is the second opening change value.

[0033] Optionally, generating the second target opening based on the preset second controller, the real-time flue gas temperature, and the matching opening value includes:

[0034] The real-time flue gas temperature is used as the preset PV value of the second controller, and the matching opening value is used as the feedforward value of the second controller to generate the second target opening.

[0035] A second aspect of this invention discloses a control device for a semi-dry deacidification process, the device comprising:

[0036] The acquisition unit is used to acquire the real-time concentration of pollutants and the real-time temperature of flue gas at the chimney outlet.

[0037] The conversion unit is used to convert the real-time concentration of the pollutant into multiple conversion values, and to use the real-time concentration of the pollutant and each of the conversion values ​​as key parameters.

[0038] The prediction unit is used to predict a first state signal that characterizes whether the pollutant concentration at the chimney outlet exceeds the standard in a future period.

[0039] The identification unit is used to identify the second state signal characterizing whether the slurry valve is in the dead zone and the third state signal characterizing whether the cooling water valve is in the dead zone.

[0040] The first generation unit is used to generate a fusion state value and an opening compensation value based on the real-time concentration of the pollutant, the first state signal and the second state signal;

[0041] The second generation unit is used to generate a first target opening based on a preset first controller, each of the key parameters, the fusion state value, and the opening compensation value.

[0042] The calculation unit is used to calculate the matching opening value based on the third state signal and the opening compensation value;

[0043] The third generation unit is used to generate a second target opening based on the preset second controller, the real-time temperature of the flue gas, and the matching opening value;

[0044] The control unit is used to control the slurry valve based on the first target opening degree and to control the cooling water valve based on the second target opening degree.

[0045] A third aspect of this invention discloses an electronic device, comprising:

[0046] Memory, used to store computer programs;

[0047] A processor is configured to execute the computer program to implement the control method for any of the semi-dry deacidification processes described in the first aspect of the present invention.

[0048] A fourth aspect of the present invention discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements a control method for any of the semi-dry deacidification processes described in the first aspect of the present invention.

[0049] Based on the control method and related equipment for a semi-dry desulfurization process provided by the above embodiments of the present invention, the following steps are taken: Real-time pollutant concentration and flue gas temperature at the chimney outlet are obtained; multiple conversion values ​​are calculated based on the real-time pollutant concentration, and the real-time pollutant concentration and each of the conversion values ​​are used as key parameters; a first state signal characterizing whether the pollutant concentration at the chimney outlet exceeds the standard in a future period is predicted; a second state signal characterizing whether the slurry valve is in a dead zone and a third state signal characterizing whether the cooling water valve is in a dead zone are identified; a fusion state value is generated using the real-time pollutant concentration and the first state signal, and an opening compensation value is generated using the real-time pollutant concentration, the first state signal, and the second state signal; a first target opening is generated based on a preset first controller, each of the key parameters, the fusion state value, and the opening compensation value; a matching opening value is calculated based on the third state signal and the opening compensation value; a second target opening is generated based on a preset second controller, the flue gas temperature, and the matching opening value; the slurry valve is controlled based on the first target opening, and the cooling water valve is controlled based on the second target opening. In this solution, real-time pollutant values ​​are collected synchronously and converted into multiple key parameters. The solution also predicts future risks of exceeding standards, identifies the dead zone state of dual valves, and dynamically generates fusion state values ​​and compensation values ​​to drive the coordinated adjustment of slurry valves and cooling water valves. This upgrades traditional single-loop control to multi-variable intelligent decision-making and actively eliminates the impact of dead zones on control effectiveness. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0051] Figure 1 This is a partial architecture diagram of a control system for a conventional semi-dry deacidification process disclosed in an embodiment of the present invention;

[0052] Figure 2 This is a flowchart of a control method for a semi-dry deacidification process disclosed in an embodiment of the present invention;

[0053] Figure 3 This is a control effect diagram of a semi-dry deacidification process disclosed in an embodiment of the present invention;

[0054] Figure 4 This is a structural diagram of a control device for a semi-dry deacidification process disclosed in an embodiment of the present invention;

[0055] Figure 5 This is a structural diagram of an electronic device disclosed in an embodiment of the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0058] As the background technology indicates, the main control target of the semi-dry desulfurization process is the emission concentration of SO2 and HCl, which needs to be controlled below a certain concentration, such as an hourly average of 60 mg / m³. 3 And the daily average is 40 mg / m³ 3This places high demands on the overall control system. Balancing economy and deacidification effect is a key challenge. Simultaneously, the flue gas temperature after the reaction tower must not be too low and must be maintained within a reasonable range. Therefore, conventional control equipment consists of slurry valves and cooling water valves. The slurry valves control the flow rate of the deacidification agent, while the cooling water valves control the total water volume.

[0059] like Figure 1 The diagram shown is a partial architecture diagram of a control system for a conventional semi-dry deacidification process disclosed in an embodiment of the present invention.

[0060] Existing control methods for semi-dry deacidification processes lack multivariate intelligent decision-making capabilities. Most existing control methods are single-loop or simple cascaded PID controllers, lacking the ability to comprehensively analyze and predict multiple key parameters and make collaborative optimization decisions. Furthermore, existing control methods are prone to flow dead zones when switching between open and closed states of the slurry valve and the cooling water valve; the flow rate remains unchanged for a significant range, affecting the effectiveness of control.

[0061] Therefore, this invention discloses a control method and related equipment for a semi-dry deacidification process. In this solution, by synchronously collecting real-time pollutant values ​​and converting them into multiple key parameters, predicting future exceedance risks, identifying the dead zone state of dual valves, and then dynamically generating fusion state values ​​and compensation values ​​to drive the coordinated adjustment of slurry valves and cooling water valves, the traditional single-loop control is upgraded to multi-variable intelligent decision-making, and the impact of dead zones on control effectiveness is actively eliminated.

[0062] like Figure 2 The diagram shows a flowchart of a control method for a semi-dry deacidification process disclosed in an embodiment of the present invention, including the following steps:

[0063] Step S101: Obtain the real-time concentration of pollutants and the real-time temperature of flue gas at the chimney outlet.

[0064] In step S101, the real-time concentrations of pollutants include: the real-time concentration of SO2 and the real-time concentration of HCl.

[0065] Step S102: Based on the real-time concentration of pollutants, multiple conversion values ​​are obtained, and the real-time concentration of pollutants and each conversion value are used as key parameters.

[0066] In the specific implementation of step S102, based on the real-time concentration of pollutants, multiple conversion values, including but not limited to hourly average and daily average, are calculated, and then the real-time concentration of pollutants and each conversion value are used as key parameters.

[0067] Step S103: Predict and obtain the first state signal that characterizes whether the pollutant concentration at the chimney outlet exceeds the standard in the future period.

[0068] In the specific implementation of step S103, the real-time operating parameters of the flue gas generation system are obtained; the real-time pollutant concentration and real-time operating parameters are input into the pre-trained prediction model to obtain the first state signal characterizing whether the pollutant concentration at the chimney outlet exceeds the standard in the future period.

[0069] The real-time operating parameters of the flue gas generation system include, but are not limited to: the flow rate and frequency of the primary air fan, secondary air fan and recirculation fan, the oxygen concentration at the economizer outlet, and the main steam flow rate.

[0070] Specifically, the prediction model is a pre-trained classification model. Based on real-time input data (real-time pollutant concentrations and real-time operating parameters), the classification model generates a first state signal T1 indicating whether the HCl or SO2 emission concentration at the chimney outlet exceeds the emission standard after a certain period of time.

[0071] Optionally, the classification model is a pre-trained LightGBM machine learning model. The first state signal output by the classification model can be a value of 0 or 1. 0 indicates that the emission concentrations of HCl and SO2 will not exceed the standard in the next 60 seconds, and 1 indicates that the emission concentrations of HCl and SO2 will exceed the standard in the next 60 seconds.

[0072] It should be noted that traditional control strategies heavily rely on online monitoring data at the chimney outlet. From the addition of lime slurry to the reaction of flue gas inside the tower, through bag filter dust collection, and finally to chimney detection, there is a lag of several minutes throughout the entire process. This causes feedback control to be unable to respond promptly to drastic changes in the inlet flue gas, easily leading to fluctuations in emission indicators or overdosing of reagents.

[0073] This invention constructs a pollutant state prediction model (LightGBM) based on real-time operating parameters such as the primary air fan, economizer outlet oxygen concentration, and main steam flow rate. It predicts whether the pollutant concentration at the chimney outlet exceeds the standard 60 seconds in advance, generates a first state signal T1, and drives the dynamic target strategy module to generate an opening compensation value K2 in advance. Thus, when the inlet flue gas parameters change drastically but have not yet affected the outlet emissions, the opening of the slurry valve is actively adjusted. This upgrades the traditional post-event feedback to pre-event prediction and active compensation, fundamentally overcoming the problem of untimely response caused by a delay of several minutes.

[0074] Step S104: Identify the second state signal characterizing whether the slurry valve is in the dead zone and the third state signal characterizing whether the cooling water valve is in the dead zone.

[0075] In step S104, the dead zone identification algorithm identifies a second state signal characterizing whether the slurry valve is in the dead zone and a third state signal characterizing whether the cooling water valve is in the dead zone.

[0076] The process of determining whether the slurry valve is in the dead zone and obtaining the second state signal is as follows:

[0077] The first opening change value and the first flow rate change value of the slurry valve are obtained, and based on the first opening change value and the first flow rate change value, a second state signal characterizing whether the slurry valve is in the dead zone is identified.

[0078] In other words, the valve opening and the corresponding flow rate change (i.e., the first opening change value and the first flow rate change value) are monitored in real time to determine whether the slurry valve is in the dead zone and to give the corresponding second state signal T2.

[0079] Optionally, the second state signal T2 can be calculated using the formula max(-1,min(k*D1*F1,1)), where k is a constant coefficient, D1 is the change in the opening degree of the slurry valve within 20s, and F1 is the change in the flow rate of the slurry valve within 30s.

[0080] The process of determining whether the cooling water valve is in the dead zone and obtaining the third state signal is as follows:

[0081] The second opening change value and the second flow rate change value of the cooling water valve are obtained, and based on the second opening change value and the second flow rate change value, a third state signal characterizing whether the cooling water valve is in the dead zone is identified.

[0082] In other words, the valve opening and corresponding flow rate changes are monitored in real time (i.e., the second opening change value and the second flow rate change value) to determine whether the cooling water valve is in the dead zone and to give the corresponding third state signal T3.

[0083] Optionally, the third state signal T3 can be calculated using the formula max(-1,min(k*D2*F2,1)), where k is a constant coefficient, D2 is the change in the opening degree of the cooling water valve within 20s, and F2 is the change in the flow rate of the cooling water valve within 30s.

[0084] Step S105: Generate a fusion state value using the real-time pollutant concentration and the first state signal, and generate an opening compensation value using the real-time pollutant concentration, the first state signal, and the second state signal.

[0085] In step S105, according to the dynamic target strategy, when the first state signal or the second state signal is greater than 0, a fusion state value S7 and an opening compensation value K2 are generated based on the real-time pollutant concentration, the first state signal, and the second state signal.

[0086] Specifically, a timer is used to activate the system. The activation condition is that either the first state signal T1 or the second state signal T2 is greater than 0. When T1 is activated (i.e., greater than 0), it will be set to 1 for 1 minute. When T2 is activated (i.e., greater than 0), it will be set to 1 for 1 minute. If it is not activated, the output will be 0.

[0087] Among them, the opening compensation value is a combination of pollutant excess compensation and slurry valve dead zone compensation.

[0088] In the specific implementation of step S105, the following formula is used: Dynamically generate fusion state values; using the formula: Generate opening compensation values; where, This represents the real-time concentration of SO2. S is the preset value for SO2 concentration. HCl S represents the real-time concentration of HCl. HCl_set The HCl concentration is a preset value, T1 is the first state signal, T2 is the second state signal, D1 is the first opening change value, and k1, k2 and k3 are weighting coefficients.

[0089] It should be noted that the values ​​of k1, k2, and k3 are determined by two factors: first, the sensitivity and importance attached to the control of different pollutants (such as SO2 and HCl) in actual production; and second, the concentration fluctuation range of each pollutant in actual operation. k1 is usually taken as 1, and the values ​​of k2 and k3 are usually between 0 and 10.

[0090] For example: In 38, S HCl_set When the value is 8, k1 is taken as the conventional value of 1. Since the concentrations of SO2 and HCl fluctuate significantly, this effect needs to be eliminated. Similarly .

[0091] In addition, if the incinerated waste has a high sulfur content, the SO2 concentration fluctuates more than that of HCl. In this case, a trial-and-error method is used to adjust k1, k2 and k3. For example, based on the original values, k1=2, k2=4.75 and k3=4.75 to improve the response to SO2 concentration control.

[0092] Step S106: Generate the first target opening based on the preset first controller, various key parameters, fusion state value and opening compensation value.

[0093] The first target opening degree is applied to the slurry valve.

[0094] The specific implementation of step S106 includes the following steps:

[0095] 1. For each key parameter, calculate the deviation value between it and the corresponding preset value of the key parameter; select the target deviation values ​​that meet the preset activation conditions from the various deviation values.

[0096] It should be noted that, based on the preset target activation strategy, the deviation value between each key parameter and its corresponding preset value is used to determine whether to activate the deviation value (the activated deviation value is used as the target deviation value) and proceed to the next step of calculation.

[0097] For example, assuming the key parameters are the real-time values, hourly average values, and daily average values ​​of HCl and SO2 concentrations, then there are 6 corresponding deviation values.

[0098] The activation state of each deviation value is determined by the formula. calculate.

[0099] Taking real-time SO2 concentration as an example, through the formula Calculate the activation state of the real-time SO2 concentration, where This represents the real-time concentration of SO2. The preset value corresponding to the real-time SO2 concentration is K, which is a constant coefficient and is set to 0. For example, when the real-time SO2 concentration is 42, the preset value corresponding to the real-time SO2 concentration is 38, then the activation state is 1.

[0100] 2. Using the formula: sum(max(-10,min(ki*(SS)) set )*S i ,10)))+S7, calculate the control target.

[0101] Where ki is the weight coefficient, and S represents each key parameter. set The preset values ​​of each key parameter, S i For the activation state of each deviation value, (SS) set )*S i S7 represents the deviation value of each target, and S8 represents the fusion state value.

[0102] It should be noted that, according to the preset multi-objective fusion optimization algorithm, based on the deviation values ​​of each objective and the fusion state value S7, each value is dynamically optimized and merged into a final value, which is used as the preset first controller control target input (i.e. control target).

[0103] 3. Input the control target into the preset first controller to obtain the opening degree to be compensated K1; use the opening degree compensation value K2 to compensate the opening degree to be compensated K1 to generate the first target opening degree K3.

[0104] In the specific implementation, K3 = K1 + T_max(K2), where T_max(K2) is the maximum value of the opening compensation value K2 within 1 minute.

[0105] Optionally, the first controller is a PID controller or other conventional controller.

[0106] Step S107: Calculate the matching opening value based on the third state signal and the opening compensation value.

[0107] In the specific implementation of step S107, the matching opening value is calculated using the formula: k4*T3*D2-k5*K2; where k4 and k5 are constant coefficients, T3 is the third state signal, K2 is the opening compensation value, and D2 is the second opening change value.

[0108] Wherein, k4*T3*D2 is the dead zone opening compensation of the cooling water valve. The dead zone opening compensation of the cooling water valve is dynamically matched and merged with the opening compensation value K2 to obtain the matched opening value K4.

[0109] It should be noted that the values ​​of k4 and k5 range from 0 to 2, with a common value of 1. k4 can be adjusted based on the actual site conditions. For example, if the pipe diameter corresponding to the slurry valve is DN20 (i.e., nominal diameter of 20 mm), and the pipe diameter corresponding to the cooling water valve is DN15 (i.e., nominal diameter of 15 mm), then k4 = 15 / 20 = 0.75. k4 and k5 can be adjusted using a trial-and-error method. If, during on-site commissioning, it is found that the opening of the slurry valve suddenly increases and the opening of the cooling water valve cannot be closed in time, k5 can be increased, such as k5 = 1.2.

[0110] Step S108: Generate a second target opening based on the preset second controller, real-time flue gas temperature, and matching opening value.

[0111] In the specific implementation of step S108, the real-time flue gas temperature is used as the preset PV value of the second controller, and the matching opening value is used as the feedforward value of the second controller to generate the second target opening.

[0112] It should be noted that the real-time flue gas temperature at the outlet of the reaction tower chimney is used as the PV value of the second controller, the preset value of the flue gas temperature at the outlet of the chimney is used as the SV value of the second controller, and K4 is used as the feedforward value of the second controller to obtain the second target opening degree K5 of the second controller output, which acts on the cooling water valve.

[0113] Optionally, the second controller is a PID controller or other conventional controller.

[0114] Step S109: Control the slurry valve based on the first target opening degree, and control the cooling water valve based on the second target opening degree.

[0115] In step S109, the calculated first target opening degree is sent as an instruction to the slurry valve to precisely control the amount of lime slurry added; at the same time, the second target opening degree is sent as an instruction to the cooling water valve to precisely control the flow rate of the cooling water, thereby realizing the coordinated linkage of the two valves.

[0116] It should be noted that in existing technologies, lime slurry is both a reactant and its moisture evaporation also has a cooling effect. The dosage of both affects each other. If excessive lime slurry is added solely to ensure emissions, it will excessively lower the tower outlet temperature, resulting in resource waste, increased fly ash, and the risk of equipment condensation and corrosion. If controlled separately, it is difficult to achieve optimal synergy.

[0117] In this embodiment of the invention, by introducing the slurry valve opening compensation value K2 as a feedforward signal into the cooling water valve control process, the matching opening K4 is dynamically calculated, enabling the cooling water valve to sense the adjustment action of the slurry valve in advance and compensate in the reverse: when the slurry valve opens larger (K2 increases), K4 automatically reduces the opening of the cooling water valve to offset the excessive cooling effect caused by the evaporation of lime slurry water, thereby breaking the isolated control mode of the two valves acting independently, achieving the optimal synergy between emission compliance and temperature stability, and avoiding resource waste and equipment risks caused by excessive addition of lime slurry.

[0118] like Figure 3 The diagram shown illustrates the control effect of a semi-dry deacidification process disclosed in an embodiment of the present invention.

[0119] Figure 3 The figure shows the trend of slurry valve opening and real-time pollutant concentration (taking SO2 as an example) after applying the new control method. As can be seen from the figure, when the real-time SO2 concentration fluctuates, the slurry valve opening can be adjusted in a timely manner to respond to changes in the real-time pollutant concentration, thereby effectively controlling the real-time pollutant concentration within the desired range.

[0120] in addition, Figure 3 It also demonstrated that the valves could act in advance under certain operating conditions, i.e., the valve opening was increased in advance in anticipation of an increase in the real-time SO2 concentration. This advance response mechanism significantly reduced the fluctuation range of the real-time SO2 concentration, thereby effectively controlling the real-time concentration of pollutants within the expected range.

[0121] Based on the control method of the semi-dry deacidification process disclosed in the above embodiments of the present invention, in this solution, the real-time value of pollutants is collected synchronously and converted into multiple key parameters, and the future risk of exceeding the standard is predicted and the dead zone state of the dual valves is identified. Then, the fusion state value and compensation value are dynamically generated to drive the slurry valve and the cooling water valve to adjust in a coordinated manner, thereby upgrading the traditional single-loop control to multi-variable intelligent decision-making and actively eliminating the impact of the dead zone on the control effectiveness.

[0122] Corresponding to the control method of the semi-dry deacidification process disclosed in the above embodiments of the present invention, such as... Figure 4The diagram shown is a structural diagram of a control device for a semi-dry deacidification process disclosed in an embodiment of the present invention, including: an acquisition unit 401, a conversion unit 402, a prediction unit 403, an identification unit 404, a first generation unit 405, a second generation unit 406, a calculation unit 407, a third generation unit 408, and a control unit 409.

[0123] The acquisition unit 401 is used to acquire the real-time concentration of pollutants and the real-time temperature of flue gas at the chimney outlet.

[0124] The conversion unit 402 is used to convert multiple conversion values ​​based on the real-time concentration of pollutants, and uses the real-time concentration of pollutants and each conversion value as key parameters.

[0125] Prediction unit 403 is used to predict the first state signal that characterizes whether the pollutant concentration at the chimney outlet exceeds the standard in the future period.

[0126] The identification unit 404 is used to identify the second state signal characterizing whether the slurry valve is in the dead zone and the third state signal characterizing whether the cooling water valve is in the dead zone.

[0127] The first generation unit 405 is used to generate a fusion state value using the real-time concentration of pollutants and the first state signal, and to generate an opening compensation value using the real-time concentration of pollutants, the first state signal and the second state signal.

[0128] The second generation unit 406 is used to generate a first target opening based on a preset first controller, various key parameters, fusion state value and opening compensation value;

[0129] Calculation unit 407 is used to calculate the matching opening value based on the third state signal and the opening compensation value;

[0130] The third generation unit 408 is used to generate a second target opening based on a preset second controller, real-time flue gas temperature and matching opening value;

[0131] Control unit 409 is used to control the slurry valve based on a first target opening degree and to control the cooling water valve based on a second target opening degree.

[0132] Optionally, prediction unit 403 is specifically used for:

[0133] Obtain real-time operating parameters of the flue gas generation system;

[0134] By inputting real-time pollutant concentrations and real-time operating parameters into a pre-trained prediction model, a first-state signal is obtained that characterizes whether the pollutant concentration at the chimney outlet will exceed the standard in the future.

[0135] Optionally, the identification unit 404 is specifically used for:

[0136] The first opening change value and the first flow rate change value of the slurry valve are obtained, and based on the first opening change value and the first flow rate change value, a second state signal characterizing whether the slurry valve is in the dead zone is identified.

[0137] The second opening change value and the second flow rate change value of the cooling water valve are obtained, and based on the second opening change value and the second flow rate change value, a third state signal characterizing whether the cooling water valve is in the dead zone is identified.

[0138] Optionally, the real-time concentrations of pollutants include: real-time SO2 concentration and real-time HCl concentration; the first generation unit 405 is specifically used for:

[0139] Using the formula: Generate fusion state values;

[0140] Using the formula: Generate opening compensation values; where, This represents the real-time concentration of SO2. S is the preset value for SO2 concentration. HCl S represents the real-time concentration of HCl. HCl_set The HCl concentration is a preset value, T1 is the first state signal, T2 is the second state signal, D1 is the first opening change value, and k1, k2 and k3 are weighting coefficients.

[0141] Optionally, the second generation unit 406 is specifically used for:

[0142] For each key parameter, calculate the deviation value between it and the corresponding preset value of the key parameter;

[0143] Select the target deviation values ​​that meet the preset activation conditions from the various deviation values;

[0144] Using the formula: sum(max(-10,min(ki*(SS)) set )*S i ,10)))+S7, the control target is calculated; where ki is the weight coefficient, S is the key parameter, and S set The preset values ​​of each key parameter, S i SS represents the activation state of each deviation value. set *S i S7 represents the fusion state value, where each target deviation value is represented by a formula. Calculate, where K is a constant coefficient;

[0145] The control target is input into the preset first controller to obtain the opening degree to be compensated;

[0146] The opening compensation value is used to compensate the opening to be compensated, and the first target opening is generated.

[0147] Optionally, computing unit 407 is specifically used for:

[0148] The matching opening value is calculated using the formula: k4*T3*D2-k5*K2; where k4 and k5 are constant coefficients, T3 is the third state signal, K2 is the opening compensation value, and D2 is the second opening change value.

[0149] Optionally, the third generation unit 408 is specifically used for:

[0150] The real-time flue gas temperature is used as the preset PV value of the second controller, and the matching opening value is used as the feedforward value of the second controller to generate the second target opening.

[0151] Based on the control device for a semi-dry deacidification process disclosed in the above embodiments of the present invention, this solution synchronously collects real-time pollutant values ​​and converts them into multiple key parameters, predicts future risks of exceeding standards, identifies the dead zone state of dual valves, and then dynamically generates fusion state values ​​and compensation values ​​to drive the slurry valve and cooling water valve to adjust in a coordinated manner. This upgrades the traditional single-loop control to multi-variable intelligent decision-making and actively eliminates the impact of dead zones on control effectiveness.

[0152] This invention also provides an electronic device, please refer to... Figure 5 The electronic device includes a memory 501 and a processor 502.

[0153] Among them, memory 501 is used to store computer programs;

[0154] The processor 502 is used to execute computer programs, specifically to implement the control method for the semi-dry deacidification process provided in any embodiment of this application.

[0155] This application also provides a computer storage medium for storing a computer program, which, when executed, is specifically used to implement the control method for the semi-dry deacidification process provided in any embodiment of this application.

[0156] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, for system or system embodiments, since they are fundamentally similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. Components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0157] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0158] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of controlling a semi-dry deacidification process, characterized in that, The method comprises: acquiring a real-time concentration of pollutants and a real-time temperature of flue gas at an outlet of a chimney; based on the real-time concentration of pollutants, converting a plurality of conversion values, taking the real-time concentration of pollutants and each of the conversion values as key parameters; the conversion values include hourly average and daily average; predicting a first state signal representing whether the concentration of pollutants at the outlet of the chimney exceeds the standard in the future period; acquiring a first opening change value and a first flow change value of a slurry valve, and identifying a second state signal representing whether the slurry valve is in a dead zone; acquiring a second opening change value and a second flow change value of a cooling water valve, and identifying a third state signal representing whether the cooling water valve is in a dead zone; using the real-time concentration of pollutants and the first state signal to generate a fusion state value, and using the real-time concentration of pollutants, the first opening change value, the first state signal and the second state signal to generate an opening compensation value; for each of the key parameters, calculating a deviation value between the corresponding key parameter and a preset value; selecting each target deviation value from each of the deviation values that meets a preset activation condition, and calculating a control target; inputting the control target into a preset first controller to obtain a to-be-compensated opening; compensating the to-be-compensated opening by using the opening compensation value to generate a first target opening; based on the third state signal and the opening compensation value, calculating a matching opening value; based on a preset second controller, the real-time temperature of flue gas and the matching opening value, generating a second target opening; controlling the slurry valve based on the first target opening, and controlling the cooling water valve based on the second target opening.

2. The method of claim 1, wherein, The prediction of the first state signal representing whether the concentration of pollutants at the outlet of the chimney exceeds the standard in the future period comprises: acquiring real-time operating parameters of a flue gas generating system; inputting the real-time concentration of pollutants and the real-time operating parameters into a pre-trained prediction model to obtain a first state signal representing whether the concentration of pollutants at the outlet of the chimney exceeds the standard in the future period.

3. The method of claim 1, wherein, The real-time concentration of pollutants includes a real-time concentration of SO2 and a real-time concentration of HCl; The use of the real-time concentration of pollutants and the first state signal to generate a fusion state value, and the use of the real-time concentration of pollutants, the first opening change value, the first state signal and the second state signal to generate an opening compensation value, comprise: The fusion state value is generated using the formula: , The opening degree compensation value is generated by using the formula: wherein, is the SO2 real-time concentration, is the SO2 concentration preset value, is the SO2 concentration preset value, HCl is the HCl real-time concentration, HCl_set is the HCl concentration preset value, T1 is the first state signal, T2 is the second state signal, D1 is the first opening degree change value, and k1, k2, and k3 are weight coefficients.

4. The method of claim 1, wherein, The calculation of the control target comprises: Using the formula: sum(max(-10,min(ki*(SS)) set )*S i ,10)))+S7, calculate the control target; where ki is the weight coefficient, S is each of the key parameters, S set Each of the aforementioned key parameters corresponds to a preset value for that key parameter, S. i For the activation state of each of the aforementioned deviation values, (SS) set )*S i S7 represents the fusion state value, where each target deviation value represents a different value; the activation state of each deviation value is determined by the formula... Calculate, where K is a constant coefficient.

5. The method of claim 1, wherein, The calculation of the matching opening value based on the third state signal and the opening compensation value comprises: using the formula: k4*T3*D2-k5*K2 to calculate the matching opening value; wherein k4 and k5 are constant coefficients, T3 is the third state signal, K2 is the opening compensation value, and D2 is the second opening change value.

6. The method according to any one of claims 1 to 5, characterized in that, The generation of the second target opening based on the preset second controller, the real-time temperature of flue gas and the matching opening value comprises: taking the real-time temperature of flue gas as the PV value of the preset second controller, and taking the matching opening value as the feedforward value of the second controller to generate a second target opening.

7. A control device for a semi-dry deacidification process, characterized in that The device is used for executing the control method of the semi-dry deacidification process as claimed in any one of claims 1 to 6, and the device comprises: An acquisition unit is configured to acquire a real-time concentration of pollutants and a real-time temperature of flue gas at an outlet of a chimney; A conversion unit is configured to convert the real-time concentration of pollutants to obtain a plurality of conversion values, and take the real-time concentration of pollutants and each conversion value as a key parameter; A prediction unit is configured to predict a first state signal representing whether the concentration of pollutants at the outlet of the chimney exceeds a standard in a future period; An identification unit is configured to identify a second state signal representing whether a slurry valve is in a dead zone and a third state signal representing whether a cooling water valve is in a dead zone; A first generation unit is configured to generate a fusion state value and an opening compensation value based on the real-time concentration of pollutants, the first state signal, and the second state signal; A second generation unit is configured to generate a first target opening based on a preset first controller, each key parameter, the fusion state value, and the opening compensation value; A calculation unit is configured to calculate a matching opening value based on the third state signal and the opening compensation value; A third generation unit is configured to generate a second target opening based on a preset second controller, the real-time temperature of flue gas, and the matching opening value; A control unit is configured to control the slurry valve based on the first target opening and control the cooling water valve based on the second target opening.

8. An electronic device, comprising: The device comprises: A memory configured to save a computer program; A processor configured to execute the computer program to implement the control method of the semi-dry deacidification process as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A memory configured to save a computer program; wherein the computer program is executed by a processor to implement the control method of the semi-dry deacidification process as claimed in any one of claims 1 to 6.

Images