A circulating fluidized bed boiler SNCR system denitration monitoring system and use method

Abstract

The present application belongs to the field of circulating fluidized bed boiler flue gas denitration treatment technology, and discloses a circulating fluidized bed boiler SNCR system denitration monitoring system and use method; the system comprises: a separator and an air preheater, a flue gas sampling device is connected between the inlet of the separator and the inlet of the air preheater; the flue gas sampling device is a pipeline with a sampling grid at the inlet; the inlet end of the flue gas sampling device is arranged upstream of the SNCR lance, a first monitoring system is arranged in the pipeline of the flue gas sampling device, and a second monitoring system is arranged at the inlet of the air preheater; the first monitoring system comprises a first oxygen monitoring device and a first NOx monitoring device; the second monitoring system comprises a second oxygen monitoring device, a second NOx monitoring device and an NH3 monitoring device. By additionally arranging a flue gas sampling grid in front of the lance at the inlet of the separator, the problem of insufficient urea solution injection control precision caused by large model error and lagging measurement data in the prior art is solved.

Description

Technical Field

[0001] This invention belongs to the field of flue gas denitrification treatment technology for circulating fluidized bed boilers, specifically relating to a denitrification monitoring system and its usage method for SNCR systems in circulating fluidized bed boilers. Background Technology

[0002] Currently, SNCR (Selective Non-Catalytic Reduction) is the most commonly used method for nitrogen oxide (NOx) treatment in circulating fluidized bed (CFB) boilers. Typically, several SNCR nozzles are placed at the separator inlet flue gas duct, allowing NOx in the boiler flue gas to undergo a redox reaction with ammonia without a catalyst, producing nitrogen and water that have no environmental impact. The biggest problems currently existing in the operation of SNCR systems in CFB boilers are: firstly, the high temperature of the flue gas at the separator inlet, and the lack of a suitable flue gas CEMS (Continuous Emission Monitoring System) to monitor the original NOx concentration of the boiler; secondly, the NOx concentration after NOx removal by the SNCR system is monitored using a CEMS system at the chimney inlet, resulting in significant data lag; furthermore, due to the absence of a catalyst, the NOx removal efficiency of the SNCR system is closely related to the separator inlet flue gas temperature, the ammonia-to-nitrogen molar ratio (NSR) of the SNCR, and the urea solution concentration. Due to the combined effects of factors such as the lack of original NOx concentration values, the severe lag in outlet NOx concentration values, the inlet flue gas temperature of the separator, and the ammonia-nitrogen molar ratio (NSR), the automatic control of the SNCR system is far more difficult than that of the SCR system for pulverized coal boilers.

[0003] Currently, most circulating fluidized bed (SNCR) boiler systems use PID control systems to control the real-time flow of urea solution. This involves calculating the error between the target NOx concentration at the chimney inlet and the real-time measured value using proportional, integral, and derivative methods, and then controlling the opening of a pneumatic regulating valve to control the real-time flow of urea solution. Furthermore, based on the set urea solution concentration, the real-time flow of dilution water is controlled by adjusting the opening of the pneumatic regulating valve, ensuring that the urea solution concentration meets operational requirements and ultimately achieving NOx concentration at the chimney inlet that meets emission standards. Currently, the most commonly used parameter determination method is the engineering correction method, which requires repeated experiments by engineers. Due to the system's significant inertia and time delay characteristics, it is overly dependent on the experience and technical skills of personnel. However, in actual operation, changes in boiler load and operating conditions mean that the urea solution flow is related to multiple factors such as flue gas volume and ammonia-nitrogen molar ratio. Therefore, it is necessary for the PID control parameters to have adaptive correction capabilities.

[0004] Chinese patent publication number CN115253636A, entitled "A Wide-Load Denitrification System for a Circulating Fluidized Bed Boiler," includes a hot air generation system, a urea solution supply system, a urea pyrolysis furnace, a cyclone separator, and a control system connected by pipelines. The hot air generated by the hot air generation system and the urea solution supplied by the urea solution supply system enter the urea pyrolysis furnace, where the urea solution is pyrolyzed to generate a reducing agent mixture containing ammonia. This reducing agent mixture is split into multiple branches and mixed with the raw flue gas from the furnace outlet, then enters the independent cyclone separators for denitrification reactions, and finally discharged through the chimney. The control system determines the urea solution supply by collecting and testing the composition of the raw flue gas entering the cyclone separator, the composition of the flue gas after denitrification by the cyclone separator, and the composition of the flue gas at the chimney's main outlet. This patent application fails to address the problem of insufficient accuracy in controlling the urea solution injection rate caused by measurement data lag and large model errors. Summary of the Invention

[0005] In order to overcome the problems existing in the prior art, the purpose of this invention is to provide a denitrification monitoring system and its usage method for a circulating fluidized bed boiler SNCR system. By adding a flue gas sampling grid before the separator inlet spray gun, the problem of insufficient control accuracy of urea solution injection caused by measurement data lag and large model error in the prior art is solved.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] In a first aspect, the present invention provides a denitrification monitoring system for a circulating fluidized bed boiler SNCR system, comprising: a separator and an air preheater, wherein the outlet of the separator is connected to the inlet of the air preheater, and an SNCR spray gun is provided at the inlet of the separator; a flue gas sampling device is connected between the inlet of the separator and the inlet of the air preheater; the flue gas sampling device is a pipe with a sampling grid at its inlet; the inlet end of the flue gas sampling device is located upstream of the SNCR spray gun, a first monitoring system is provided inside the pipe of the flue gas sampling device, and a second monitoring system is provided at the inlet of the air preheater; the first monitoring system includes a first oxygen monitoring device and a first NOx monitoring device; the second monitoring system includes a second oxygen monitoring device, a second NOx monitoring device, and an NH3 monitoring device.

[0008] Optionally, the flue gas sampling device is connected to a compressed air pipeline.

[0009] Optionally, an overheater is provided between the outlet of the separator and the inlet of the air preheater.

[0010] Optionally, a reheater and an economizer are provided between the inlet of the superheater and the air preheater.

[0011] Optionally, the flue gas sampling device is positioned within a range of 1.5m to 2m upstream of the SNCR spray gun.

[0012] Secondly, the present invention provides a method for using the denitrification monitoring system of a circulating fluidized bed boiler SNCR system, characterized by comprising the following steps:

[0013] S1: Set the initial NSR design value based on the inlet NOx concentration value obtained from the first monitoring system;

[0014] S2: According to the NO monitored by the first monitoring system X Urea consumption is calculated from concentration and flue gas flow rate;

[0015] S3: Calculate the dilution water consumption based on the urea consumption;

[0016] S4: Conduct field tests to determine the optimal urea solution concentration under different loads and obtain the fitting curve of the optimal urea solution concentration.

[0017] S5: Obtain historical operating data and train NOx generation prediction regression model and NSR prediction regression model on the historical operating data.

[0018] Optionally, a virtual SCR reactor model is established, the reaction loss function of the SNCR system is established, and the optimal solution is obtained through the differential evolution algorithm to obtain the SNCR denitrification reaction model;

[0019] The NOx concentration at the separator inlet is predicted using a NOx generation prediction regression model. The urea solution consumption of the SNCR system is calculated and controlled using the NSR prediction regression model. The NOx concentration at the air preheater inlet is predicted using a virtual SCR reactor model of the SNCR system. The dilution water volume is controlled by the fitted curve of the optimal urea solution concentration value.

[0020] Optionally, in step S2, the formula for calculating urea consumption is: In the formula: Urea consumption, kg / h; : Flue gas flow rate at the separator inlet at a 6% O2 concentration, m3 / h; : Average NOx concentration at the separator inlet section at 6% O2 concentration, mg / m3; NO2 molar mass, g / mol; NSR: NH3 / NOx molar ratio; Molar mass of NH3, g / mol.

[0021] Optionally, in step S3, the formula for calculating the dilution water consumption is: ; In the formula: : Mass of urea solution; The concentration of the urea solution prepared by the power plant; The optimal urea solution concentration for the SNCR system, determined experimentally; The amount of dilution water required by the SNCR system to dilute the urea solution to the optimal concentration.

[0022] Optionally, in step S5, the specific process of building a NOx generation prediction model using a gated recurrent neural network is as follows: by setting the parameters of the activation function, learning rate, batch size, number of iterations, and weight decay coefficient for the NOx generation prediction model, a gated recurrent neural network structure is used to build the NOx generation prediction model network structure; wherein: the expression of the activation function is... , The NOx generation prediction model is obtained by training the network structure of the NOx generation prediction model using the training dataset. The expression of the NOx generation prediction model is as follows: In the formula: X1 is the dependent variable of the NOx generation prediction model, and X2 is the normalized independent variable of the NOx generation prediction model.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] This invention adds a flue gas sampling grid before the separator inlet spray gun and uses the differential pressure between the separator and the air preheater inlet to allow a small proportion of flue gas to automatically flow into the air preheater inlet. A first monitoring system is installed on the pipeline; simultaneously, the flue gas dissipates heat to the environment during flow, preventing high temperatures from damaging the flue gas monitoring instruments. A second monitoring system is installed at the air preheater inlet to monitor the concentration of nitrogen oxides after denitrification. By selecting boiler operating data to predict the initial NOx concentration at the separator inlet and the optimal NSR value, and combining this with the loss function of the virtual SCR reactor to predict the NOx content at the air preheater inlet, the urea solution consumption is adjusted after comparing the predicted values ​​with the actual values ​​from the second monitoring system.

[0025] This addresses the problem of insufficient accuracy in controlling the amount of urea solution injected, caused by lag in measurement data and large model errors in existing technologies. Attached Figure Description

[0026] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of the invention in any way. Furthermore, the shapes and proportions of the components in the drawings are merely schematic to aid in understanding the invention and do not specifically limit the shapes and proportions of the components. In the drawings:

[0027] Figure 1 This is a schematic diagram of NOx monitoring at the inlet and outlet of the SNCR system of the present invention;

[0028] Figure 2 This is a schematic diagram of the grid sampling of the inlet and outlet positions in this invention;

[0029] Figure 3 This is a diagram of the SNCR system according to Embodiment 1 of the present invention;

[0030] Among them, 1. Boiler furnace; 2. Cyclone separator; 3. Flue gas sampling device; 4. Air preheater; 21. SNCR spray gun; 31. Compressed air pipeline; 32. First oxygen monitoring device; 33. First NOx monitoring device; 41. Superheater; 42. Reheater; 43. Economizer; 44. Second oxygen monitoring device; 45. Second NOx monitoring device; 46. Flow monitoring device; 47. NH3 monitoring device; 101. Self-compressed air header; 102. Self-urea solution transfer pump; 103. Self-dilution water pump. Detailed Implementation

[0031] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0032] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0033] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper", "lower", "horizontal", "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of the invention is usually placed during use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0034] When an element is referred to as being "set on" another element, it can be directly on the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only embodiments. The use of the term "horizontal" does not imply that the component is required to be absolutely horizontal, but rather that it may be slightly tilted. "Horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but rather that it may be slightly tilted.

[0035] It should be noted that similar reference numerals and letters in the following figures denote similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the specification of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification and appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0037] The present invention will now be described in detail with reference to the accompanying drawings.

[0038] A denitrification monitoring system for a circulating fluidized bed boiler SNCR system is characterized by comprising: a separator 2 and an air preheater 4, wherein the outlet of the separator 2 is connected to the inlet of the air preheater 4, and an SNCR spray gun 21 is provided at the inlet of the separator 2; a flue gas sampling device 3 is connected between the inlet of the separator 2 and the inlet of the air preheater 4; the flue gas sampling device 3 is a pipe with a sampling grid at its inlet; the inlet end of the flue gas sampling device 3 is located upstream of the SNCR spray gun 21, a first monitoring system is provided inside the pipe of the flue gas sampling device 3, and a second monitoring system is provided at the inlet of the air preheater 4; the first monitoring system includes a first oxygen monitoring device 32 and a first NOx monitoring device 33; the second monitoring system includes a second oxygen monitoring device 44, a second NOx monitoring device 45, and an NH3 monitoring device 47.

[0039] The method of using the denitrification monitoring system of the circulating fluidized bed boiler SNCR system includes the following steps:

[0040] S1: Set the initial NSR design value based on the inlet NOx concentration value obtained from the first monitoring system;

[0041] S2: According to the NO monitored by the first monitoring system X Urea consumption is calculated from concentration and flue gas flow rate;

[0042] S3: Calculate the dilution water consumption based on the urea consumption;

[0043] S4: Conduct field tests to determine the optimal urea solution concentration under different loads and obtain the fitting curve of the optimal urea solution concentration.

[0044] S5: Obtain historical operating data and train NOx generation prediction regression model and NSR prediction regression model on the historical operating data.

[0045] This invention adds a flue gas sampling grid before the inlet spray gun of the separator, and uses the differential pressure between the cyclone separator 2 and the air preheater 4 inlet to allow a small proportion of flue gas to automatically flow into the air preheater 4 inlet. A first monitoring system is installed on the pipeline; simultaneously, the flue gas dissipates heat to the environment during flow, preventing high-temperature damage to the flue gas monitoring instruments. A second monitoring system is installed at the air preheater 4 inlet to monitor the nitrogen oxide concentration after denitrification. By selecting boiler operating data to predict the initial NOx concentration and the optimal NSR value at the separator inlet, and combining the loss function of the virtual SCR reactor to predict the NOx content at the air preheater inlet, the urea solution consumption is adjusted after comparing with the measured values ​​of the second monitoring system. This solves the problem of insufficient accuracy in controlling the urea solution injection rate caused by measurement data lag and large model errors.

[0046] Example 1

[0047] like Figure 3 As shown, in this embodiment, the SNCR system includes a self-compressed air header 101, a self-urea solution delivery pump 102, and a self-dilution water pump 103. The self-compressed air header 101 is used to atomize air. The self-compressed air header 101 is connected to the compressed air pipeline 31.

[0048] This embodiment of a circulating fluidized bed boiler SNCR system denitrification monitoring system includes: a separator 2 and an air preheater 4. The outlet of the separator 2 is connected to the inlet of the air preheater 4, and an SNCR spray gun 21 is installed at the inlet of the separator 2. The boiler furnace 1 is connected upstream of the separator 2, and a superheater 41, a reheater 42, an economizer 43, and the air preheater 4 are connected downstream in sequence.

[0049] To prevent the injected urea solution from affecting the original NOx concentration test, a flue gas sampling device 3 is connected between the inlet of the separator 2 and the inlet of the air preheater 4. The flue gas sampling device 3 is a pipe with a sampling grid at the inlet. The inlet end of the flue gas sampling device 3 is located upstream of the SNCR spray gun 21. The flue gas is guided to the inlet of the air preheater 4 by the pressure difference between the inlet of the separator 2 and the inlet of the air preheater 4.

[0050] The flue gas sampling device 3 is equipped with a first monitoring system in its pipeline, and the air preheater 4 is equipped with a second monitoring system at its inlet, for monitoring the original NOx concentration value produced by the boiler.

[0051] The first monitoring system includes a first oxygen monitoring device 32 and a first NOx monitoring device 33 connected to the flue gas sampling device 3 via pipelines. The second monitoring system includes a second oxygen monitoring device 44, a second NOx monitoring device 45, a flow monitoring device 46, and an NH3 monitoring device 47 connected to the inlet of the air preheater 4 via pipelines.

[0052] Optionally, compressed air conduit 31 connects to the power plant's miscellaneous compressed air.

[0053] Optionally, the flue gas sampling device 3 is a grid-based flue gas sampling device, where flue gas is collected into a DN25 pipe and introduced into the inlet of the air preheater 4 through a flue gas sampling grid. Since the flue gas temperature at the sampling point is as high as 850~950℃, the steel pipe used for sampling in the flue gas sampling device 3 needs to be made of high-temperature resistant stainless steel. Optionally, the pipe of the flue gas sampling device 3 is made of 310S stainless steel. To ensure that the flue gas temperature reaching the inlet of the air preheater 4 is reduced to below 400℃, the DN25 stainless steel flue gas pipe does not require insulation and is allowed to dissipate heat naturally.

[0054] Preferably, the flue gas sampling device 3 is located within a range of 1.5m to 2m upstream of the SNCR spray gun 21.

[0055] Optionally, the flue gas sampling device 3 is connected to a compressed air pipe 31. To prevent dust in the flue gas from clogging the pipe and the sampling port of the flue gas sampling grid during long-term operation, a compressed air pipe 31 is installed on the pipe for backflushing, and the backflushing frequency is determined according to the dust concentration in the flue gas.

[0056] Optionally, the second monitoring system is a CEMS (Continuous Emission Monitoring System), used to monitor the composition of flue gas after denitrification, and to guide the power plant's combustion control and adjust the operating oxygen level.

[0057] Example 2

[0058] Since the SCR system has a catalytic effect, provided that the catalyst activity meets the performance requirements, the NSR can be directly calculated from the denitrification efficiency and ammonia slip. Therefore, the urea consumption of the SCR system can be directly calculated from the flue gas volume, NSR, and inlet NOx concentration.

[0059] In actual operation, the specific NSR is related to factors such as boiler load (flue gas volume), flue gas temperature at the inlet of separator 2, concentration of diluted urea solution, and original NOx concentration. Once the specific NSR value is obtained, the consumption of urea solution is directly calculated using the boiler load (flue gas volume) and the original NOx concentration.

[0060] The dosage of urea granules is calculated using the following method:

[0061]

[0062] In the formula:

[0063] Urea consumption, kg / h;

[0064] Flue gas flow rate at the inlet of separator 2 at 6% O2 concentration, in m³ 3 / h;

[0065] NO at the inlet cross section of separator 2 at 6% O2 concentration X Average concentration, mg / m³ 3 ;

[0066] Molar mass of NO2, g / mol;

[0067] NSR NH3 / NO X molar ratio;

[0068] Molar mass of NH3, g / mol.

[0069] The urea consumption is calculated using the above formula. The power plant first prepares the urea granules into a 40%~50% urea solution for storage.

[0070]

[0071] In the formula: This refers to the urea solution of a certain concentration that needs to be consumed by the power plant, with a mass concentration of 40% to 50%, which is also the mass of urea solution measured by the electromagnetic flowmeter in the SNCR system. : Concentration of urea solution prepared by the power plant.

[0072] The SNCR system dilutes a 40%–50% urea solution to the required concentration using dilution water, controlling the concentration to 8%–12%, which needs to be confirmed through on-site testing. The dilution water consumption is then:

[0073]

[0074] In the formula:

[0075] The optimal urea solution concentration for the SNCR system, determined experimentally.

[0076] The amount of dilution water required by the SNCR system to dilute the urea solution to the optimal concentration is also the amount of dilution water measured by the turbine flow meter set in the SNCR system.

[0077] The effect of diluted urea solution concentration on NSR value was determined through field tests.

[0078] Taking a stable load as an example, power plant operators stabilize the unit's operating load, ensuring stable coal quality and parameters such as oxygen levels. They maintain a constant 50% concentration of urea solution, adjusting the dilution water flow rate to adjust the concentration of the diluted urea solution. Based on the NOx concentrations from the newly added first and second monitoring systems, they calculate the denitrification efficiency and find the dilute urea solution concentration corresponding to the highest denitrification efficiency. The concentration of the diluted urea solution is between 5% and 15%.

[0079] By adjusting the dilution water flow rate under certain stable load, operating oxygen content, coal quality, and urea solution flow rate, urea solutions of different concentrations were obtained. The changes in NOx concentration at the inlet of air preheater 4 were observed, and the optimal urea solution concentration for the corresponding load was selected.

[0080] On-site tests were conducted to determine the optimal urea solution concentration values ​​under boiler loads of 50%, 60%, 70%, 80%, 90%, and 100%.

[0081] Under stable load, stable coal quality, and stable operating oxygen content, the initial NOx concentration of production can be considered to be at the basic temperature. The optimal urea solution concentration value refers to the highest denitrification efficiency when the flow rate of 50% urea solution is constant, and the lowest NOx concentration in the second monitoring system. Based on the optimal urea solution concentration values ​​determined by the above 6 boiler loads, the relationship curve between boiler load and optimal urea solution concentration is fitted and input into the denitrification DCS system.

[0082] Obtain historical boiler operation data, determine the dependent variable y and independent variable x of the NOx generation prediction model, and obtain the training dataset;

[0083] Among them, boiler load, coal feed rate, primary air volume, secondary air volume, boiler operating oxygen content, furnace temperature, and amount of limestone for dry desulfurization in the furnace are used as independent variables in the NOx generation prediction model; the NOx concentration at the separator inlet is used as the dependent variable in the NOx generation prediction model.

[0084] Specifically, the independent variables need to be normalized before the NOx generation prediction model can be trained.

[0085] The normalization formula is shown below:

[0086]

[0087] In the formula: Let X be the minimum value of the independent variable X. Let X be the maximum value of the independent variable X. The data is modeled after the independent variables are normalized.

[0088] A gated recurrent neural network model was used to build the network structure of the NOx generation prediction model. After training the network structure of the NOx generation prediction model with the training dataset, a NOx generation prediction regression model was obtained.

[0089] Preferably, the specific process of building a NOx generation prediction model using a gated recurrent neural network is as follows:

[0090] By setting the parameters of the activation function, learning rate, sample batch size, number of iterations and weight decay coefficient for the NOx generation prediction model, a gated recurrent neural network structure is used to build the NOx generation prediction model network structure.

[0091] Where: the expression for the activation function is , ;

[0092] Preferably, the NOx generation prediction model is obtained by training the network structure of the NOx generation prediction model using the training dataset. The expression of the NOx generation prediction model is as follows:

[0093]

[0094] In the formula: The dependent variable and the NOx generation prediction model X 1 represents the normalized independent variable of the NOx generation prediction model.

[0095] The historical operating data of the boiler includes: boiler load, coal feed rate, primary air volume, secondary air volume, flue gas oxygen content, furnace temperature, amount of limestone for dry desulfurization in the furnace, and NOx concentration at the inlet of separator 2.

[0096] Historical boiler operation data was obtained to determine the dependent and independent variables of the NSR prediction model and to acquire the training dataset. A gated recurrent neural network was used to build the NSR prediction model network structure, and the NSR prediction regression model was obtained by training the NSR prediction model network structure with the training dataset.

[0097] Among them, boiler load, coal feed amount, primary air volume, secondary air volume, boiler operating oxygen content, furnace temperature, amount of limestone for dry desulfurization in the furnace, and NOx concentration at the separator inlet are used as independent variables in the NSR prediction model; the mass of a certain concentration of urea solution prepared by the power plant required for this project is used as the dependent variable in the NSR prediction model.

[0098] Among these: the independent variables need to be normalized before the NSR prediction model can be trained;

[0099] The normalization formula is shown below:

[0100] ;

[0101] In the formula: Let X be the minimum value of the independent variable X. Let X be the maximum value of the independent variable X. The data is modeled after the independent variables are normalized.

[0102] A gated recurrent neural network model was used to build the NSR prediction model network structure, and the NSR prediction regression model was obtained by training the NSR prediction model network structure with the training dataset.

[0103] Preferably, the specific process of building an NSR prediction model using a gated recurrent neural network is as follows:

[0104] By setting the parameters of activation function, learning rate, batch size, number of iterations and weight decay coefficient for the NSR prediction model, a gated recurrent neural network structure is used to build the NSR prediction model network structure.

[0105] Where: the expression for the activation function is , ;

[0106] Preferably, the NSR prediction model is obtained by training the NSR prediction model network structure using the training dataset. The expression of the NSR prediction model is:

[0107]

[0108] In the formula: The dependent variable and the NSR prediction model X 2 represents the normalized independent variables of the NSR prediction model.

[0109] By using the independent and dependent variables of the virtual SCR reactor model of the SNCR system, the reaction loss function of the SNCR system is established, and the optimal solution of the loss function is solved by the differential evolution algorithm, thereby establishing the SNCR denitrification reaction model.

[0110] The specific process for establishing a virtual SCR reactor model of an SNCR system is as follows:

[0111] A loss function is established using the independent and dependent variables of a virtual SCR reactor denitrification reaction model. The expression is as follows:

[0112]

[0113] in: For random terms that follow a standard normal distribution, For variables The reaction coefficient, For variables The reaction coefficient,

[0114] The loss function is expressed as follows:

[0115] ;

[0116] Where: e represents the value derived from boiler load s, separator inlet temperature T, and ammonia-nitrogen molar ratio. The efficiency of the denitrification reaction is determined by SR. , , These are, respectively, boiler load s, reactor inlet flue gas temperature T, and ammonia-nitrogen molar ratio. Contribution of SR to denitrification reaction efficiency;

[0117] The parameters in the loss function are solved using the differential evolution algorithm. The parameters obtained from the optimization result can be used to establish a denitrification reaction model for a virtual SCR reactor. The expression for the SCR denitrification reaction model is as follows:

[0118] ;

[0119] In the formula: is the dependent variable in the SCR denitrification reaction model.

[0120] Preferably, the specific process of predicting nitrogen oxides at the separator inlet using a NOx generation prediction regression model is as follows:

[0121] Data on the current boiler operating status, including boiler load, coal feed rate, primary air volume, secondary air volume, boiler operating oxygen content, furnace temperature, and amount of limestone used for dry desulfurization, are obtained and normalized to form the prediction independent variable X1. The NOx generation prediction regression model is used to predict the NOx concentration at the separator inlet, and its expression is as follows:

[0122]

[0123] Preferably, the specific process by which the SCR denitrification reaction model predicts nitrogen oxides at the reactor outlet is as follows:

[0124] Based on the current boiler load s, separator inlet flue gas temperature T, and separator inlet NOx molar concentration... Utilizing the current urea capacity flow rate Calculate the molar concentration of NH3. ammonia nitrogen molar ratio SR; then, the NOx molar concentration at the reactor outlet is predicted using a virtual SCR reactor. Its expression is:

[0125]

[0126] Preferably, the specific process for controlling the ammonia injection flow rate in the reactor is as follows:

[0127] NOx control target at reactor outlet Controlling tolerance deviation If the predicted value The current urea volumetric flow rate is determined if the following conditions are met. This is the recommended value:

[0128] ;

[0129] If not satisfied, adjust and update urea capacity and flow rate with a fixed step size. The process of predicting nitrogen oxides and NOx generation at the inlet of the air preheater using a virtual SCR reactor reaction model was repeated until the conditions were met.

[0130] Based on the determined urea volume flow rate The dilution water flow rate is controlled in conjunction with the previously selected optimal concentration of the diluted urea solution.

[0131] Based on the current operating status of the virtual SCR reactor in the SNCR system, the NOx concentration at the inlet of separator 2 is predicted using the NOx generation prediction regression model of S4.

[0132] The urea solution consumption of the SNCR system was calculated and controlled using an NSR predictive regression model and model 4. The NOx concentration at the inlet of the air preheater 4 was predicted using a virtual SCR reactor model of the SNCR system. The dilution water volume was controlled by the curve fitted to the optimal urea solution concentration under different loads determined by the aforementioned field tests.

[0133] Unless otherwise specified, the equipment components involved in the above embodiments are all conventional equipment components, and the structural settings, working methods or control methods involved are all conventional settings, working methods or control methods in the art unless otherwise specified.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Any other modifications or equivalent substitutions made by those skilled in the art to the technical solutions of the present invention, as long as they do not depart from the spirit and scope of the technical solutions of the present invention, should be covered within the scope of the claims of the present invention.

Claims

1. A method for using a circulating fluidized bed boiler SNCR denitrification monitoring system, characterized in that, The circulating fluidized bed boiler SNCR denitrification monitoring system includes: a separator (2) and an air preheater (4). The outlet of the separator (2) is connected to the inlet of the air preheater (4). An SNCR spray gun (21) is installed at the inlet of the separator (2). A flue gas sampling device (3) is connected between the inlet of the separator (2) and the inlet of the air preheater (4). The flue gas sampling device (3) is a pipe with a sampling grid at the inlet. The inlet end of the flue gas sampling device (3) is located upstream of the SNCR spray gun (21). A first monitoring system is installed inside the pipe of the flue gas sampling device (3), and a second monitoring system is installed at the inlet of the air preheater (4). The first monitoring system includes a first oxygen monitoring device (32) and a first NO monitoring device (32). X Monitoring device (33); the second monitoring system includes a second oxygen monitoring device (44) and a second NO monitoring device (44). X Monitoring device (45) and NH3 monitoring device (47); The method of using the SNCR denitrification monitoring system for a circulating fluidized bed boiler includes the following steps: S1: Based on the entry NO obtained from the first monitoring system X The concentration value is set as the initial NSR design value; S2: According to the NO monitored by the first monitoring system X Urea consumption is calculated from concentration and flue gas flow rate; S3: Calculate the dilution water consumption based on the urea consumption; S4: Conduct field tests to determine the optimal urea solution concentration under different loads and obtain the fitting curve of the optimal urea solution concentration. S5: Obtain historical operational data and train the NO algorithm based on the historical operational data. X Genetic quantity prediction regression model and NSR prediction regression model; A virtual SCR reactor model was established, and the reaction loss function of the SNCR system was established. The optimal solution was obtained through the differential evolution algorithm, and the SNCR denitrification reaction model was obtained. Through NO X Generation quantity prediction regression model prediction separator (2) inlet NO X The concentration of urea solution in the SNCR system was calculated and controlled using the NSR prediction regression model; the NO inlet concentration of the air preheater (4) was predicted using the virtual SCR reactor model of the SNCR system. X The concentration and dilution volume are controlled by the fitted curve of the optimal urea solution concentration value; In step S5, a gated recurrent neural network is used to build NO X The specific process of the NO generation prediction model is as follows: by establishing the NO generation prediction model... X The activation function, learning rate, batch size, number of iterations, and weight decay coefficient of the generation prediction model are set, and a gated recurrent neural network structure is used to build the NO model. X The network structure of the generation prediction model; where: the expression for the activation function is... , ; By training the dataset on NO X After training the network structure of the generation prediction model, NO is obtained. X Generation prediction model, NO X The expression for the generation prediction model is: In the formula: NO X The dependent variable and X1 of the generation prediction model are NO. X The normalized independent variables of the generation prediction model.

2. The method of using the SNCR denitrification monitoring system for a circulating fluidized bed boiler according to claim 1, characterized in that, The flue gas sampling device (3) is connected to a compressed air pipeline (31).

3. The method of using the SNCR denitrification monitoring system for a circulating fluidized bed boiler according to claim 1, characterized in that, An overheater (41) is provided between the outlet of the separator (2) and the inlet of the air preheater (4).

4. The method of using the SNCR denitrification monitoring system for a circulating fluidized bed boiler according to claim 3, characterized in that, A reheater (42) and an economizer (43) are provided between the inlet of the superheater (41) and the air preheater (4).

5. The method of using the SNCR denitrification monitoring system for a circulating fluidized bed boiler according to claim 1, characterized in that, The flue gas sampling device (3) is located 1.5m to 2m upstream of the SNCR spray gun (21).

6. The method of using the SNCR denitrification monitoring system for a circulating fluidized bed boiler according to claim 1, characterized in that, In step S2, the formula for calculating urea consumption is: In the formula: Urea consumption, kg / h; : Separator (2) inlet flue gas flow rate at 6% O2 concentration, m 3 / h; Separator (2) inlet cross-section NO at 6% O2 concentration X Average concentration, mg / m³ 3 ; NO2 molar mass, g / mol; NSR: NH3 / NO X molar ratio; Molar mass of NH3, g / mol.

7. The method of using the SNCR denitrification monitoring system for a circulating fluidized bed boiler according to claim 1, characterized in that, In step S3, the formula for calculating the dilution water consumption is: ; In the formula: : Urea solution quality; The concentration of the urea solution prepared by the power plant; The optimal urea solution concentration for the SNCR system, determined experimentally; The amount of dilution water required by the SNCR system to dilute the urea solution to the optimal concentration.

Images