Determination Method, Device, and Equipment for Ammonia Injection Strategy Model of SCR System Reactor

Abstract

An embodiment of the present invention discloses a method, device, and equipment for determining an ammonia injection strategy model of an SCR system reactor. First, obtain the thermal parameters of the SCR system reactor, where the thermal parameters include distribution parameters of the flue gas flow rate at the first preset section and / or the second preset section, distribution parameters of the flue gas temperature at the first preset section and / or the second preset section, and at least one of the operating parameters of the boiler; then train the first sub-model in the preset model according to the thermal parameters to obtain the first target sub-model; then train the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain the second target sub-model; finally, determine the ammonia injection strategy model according to the first target sub-model and the second target sub-model for outputting the ammonia injection strategy. It solves the problem in the existing technical solution that it is difficult to accurately determine the ammonia injection strategy during the partitioned ammonia injection process, and realizes accurately determining the ammonia injection strategy during the partitioned ammonia injection process.

Description

Technical Field

[0001] The present invention relates to the technical field of flue gas denitrification, and in particular to a method, device, and equipment for determining an ammonia injection strategy model of an SCR system reactor. Background Art

[0002] The process of removing flue gas pollutants is a key link in controlling emissions from thermal power plants and has important social significance in reducing air pollution and protecting the human living environment.

[0003] The Selective Catalytic Reduction (SCR) technology widely used at home and abroad is an effective means to reduce nitrogen oxide emissions from thermal power plants, and the ammonia injection amount is the core parameter in the operation process of the SCR system.

[0004] In the prior art, nitrogen oxides are mainly reduced by methods such as sectional ammonia injection to control nitrogen oxide emissions. However, in the process of sectional ammonia injection, when using machine learning methods to analyze and model the ammonia injection amount and ammonia injection method based on operation history data, conventional machine learning modeling means are limited in the application of sectional ammonia injection, and it is often difficult to accurately determine the ammonia injection strategy in the process of sectional ammonia injection.

[0005] Therefore, in the existing technical solutions, there is a problem that it is difficult to accurately determine the ammonia injection strategy in the process of sectional ammonia injection. Summary of the Invention

[0006] Embodiments of the present invention provide a method for determining an ammonia injection strategy model of an SCR system reactor, a method for determining an ammonia injection strategy of an SCR system reactor, a device, equipment, and a storage medium, which solve the problem in the existing technical solutions that it is difficult to accurately determine the ammonia injection strategy in the process of sectional ammonia injection, and realize accurately determining the ammonia injection strategy in the process of sectional ammonia injection.

[0007] To solve the above technical problems, the present invention:

[0008] In a first aspect, a method for determining an ammonia injection strategy model of an SCR system reactor is provided, and the method includes:

[0009] Obtain the thermal parameters of the SCR system reactor, where the thermal parameters include at least one of the distribution parameters of the flue gas flow rate on the first preset section and / or the second preset section, the distribution parameters of the flue gas temperature on the first preset section and / or the second preset section, and obtain the operation parameters of the boiler;

[0010] Train the first sub-model in the preset model according to the thermal parameters to obtain a first target sub-model;

[0011] Train the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain the second target sub-model;

[0012] Determine the ammonia injection strategy model according to the first target sub-model and the second target sub-model.

[0013] In some implementation manners of the first aspect, training the first sub-model in the preset model according to the thermal parameters to obtain the first target sub-model includes:

[0014] Determine the transport relationship of the mass-energy conservation and the first parameter in the SCR system reactor according to the thermal parameters and the first sub-model, where the first parameter includes at least one of mass, momentum, and energy;

[0015] Train the transport relationship according to the thermal parameters to obtain the first target sub-model.

[0016] In some implementation manners of the first aspect, the first sub-model includes a preset flow reaction control equation; determining the transport relationship of the mass-energy conservation and the first parameter in the SCR system reactor according to the thermal parameters and the first sub-model includes:

[0017] Divide the SCR system reactor into multiple calculation units in the preset flue gas flow direction;

[0018] Determine the mass-energy conservation of each unit in the SCR system reactor and the transport relationship of the first parameter between units according to the thermal parameters and the preset flow reaction control equation.

[0019] In some implementation manners of the first aspect, training the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain the second target sub-model includes:

[0020] Determine the concentration distribution parameter of nitrogen oxides upstream of the ammonia injection grid in the SCR system reactor at the third preset section according to the first target sub-model and the thermal parameters;

[0021] Use the second sub-model to determine the ammonia injection strategy according to the concentration distribution parameter, the pre-stored outlet flue gas nitrogen oxide concentration, the pre-stored outlet ammonia concentration, and the pre-stored ammonia injection amount;

[0022] Train the second sub-model according to the ammonia injection strategy and the first target sub-model to obtain the second target sub-model.

[0023] In some implementation manners of the first aspect, training the second sub-model according to the ammonia injection strategy and the first target sub-model to obtain the second target sub-model includes:

[0024] Determine the concentration of nitrogen oxides in the outlet flue gas and the concentration of ammonia in the outlet corresponding to the ammonia injection strategy according to the ammonia injection strategy and the first target sub-model;

[0025] Adjust the parameters of the second sub-model according to the concentration of nitrogen oxides in the outlet flue gas and the concentration of ammonia in the outlet corresponding to the ammonia injection strategy to obtain the second target sub-model.

[0026] In a second aspect, a method for determining the ammonia injection strategy of an SCR system reactor is provided. The method includes:

[0027] Obtain the target thermal parameters of the SCR system reactor, where the target thermal parameters include at least one of the distribution parameters of the flue gas flow rate on the first preset cross-section, the distribution parameters of the flue gas temperature on the second preset cross-section, and the operating parameters of the boiler obtained;

[0028] Obtain the ammonia injection strategy according to the target thermal parameters and the ammonia injection strategy model, where the ammonia injection strategy model is obtained based on the first aspect and the method for determining the ammonia injection strategy model of the SCR system reactor in some implementation manners of the first aspect.

[0029] In a third aspect, a device for determining the ammonia injection strategy model of an SCR system reactor is provided. The device includes:

[0030] An acquisition module, configured to acquire the thermal parameters of the SCR system reactor, where the thermal parameters include at least one of the distribution parameters of the flue gas flow rate on the first preset cross-section and / or the second preset cross-section, the distribution parameters of the flue gas temperature on the first preset cross-section and / or the second preset cross-section, and the operating parameters of the boiler obtained;

[0031] A processing module, configured to train the first sub-model in the preset model according to the thermal parameters to obtain the first target sub-model;

[0032] The processing module is further configured to train the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain the second target sub-model;

[0033] The processing module is further configured to determine the ammonia injection strategy model according to the first target sub-model and the second target sub-model.

[0034] In a fourth aspect, a device for determining the ammonia injection strategy of an SCR system reactor is provided. The device includes:

[0035] An acquisition module, configured to acquire the target thermal parameters of the SCR system reactor, where the target thermal parameters include at least one of the distribution parameters of the flue gas flow rate on the first preset cross-section, the distribution parameters of the flue gas temperature on the second preset cross-section, and the operating parameters of the boiler obtained;

[0036] A processing module is configured to obtain an ammonia injection strategy according to a target thermotechnical parameter and an ammonia injection strategy model, where the ammonia injection strategy model is obtained based on the first aspect and the method for determining the ammonia injection strategy model of the SCR system reactor in some implementation manners of the first aspect.

[0037] In a fifth aspect, an electronic device is provided, which includes: a processor and a memory storing computer program instructions;

[0038] When the processor executes the computer program instructions, it implements the method for determining the ammonia injection strategy model of the SCR system reactor in the first aspect and some implementation manners of the first aspect, or implements the method for determining the ammonia injection strategy of the SCR system reactor in the second aspect.

[0039] In a sixth aspect, a computer storage medium is provided, which is characterized in that computer program instructions are stored on the computer storage medium, and when the computer program instructions are executed by a processor, they implement the method for determining the ammonia injection strategy model of the SCR system reactor in the first aspect and some implementation manners of the first aspect, or implement the method for determining the ammonia injection strategy of the SCR system reactor in the second aspect.

[0040] Embodiments of the present invention provide a method for determining an ammonia injection strategy model of an SCR system reactor, a method for determining an ammonia injection strategy of an SCR system reactor, a device, a device and a storage medium. First, obtain the thermotechnical parameters of the SCR system reactor, where the thermotechnical parameters include at least one of the distribution parameters of the flue gas velocity at a first preset section, the distribution parameters of the flue gas temperature at a second preset section, and the operating parameters of the boiler; then train a first sub-model in a preset model according to the thermotechnical parameters to obtain a first target sub-model; then train a second sub-model in the preset model according to the first target sub-model and the thermotechnical parameters to obtain a second target sub-model; finally, determine an ammonia injection strategy model according to the first target sub-model and the second target sub-model for outputting an ammonia injection strategy. Because in the process of determining the ammonia injection strategy model of the SCR system reactor, thermotechnical parameters including at least one of the distribution parameters of the flue gas velocity at a first preset section, the distribution parameters of the flue gas temperature at a second preset section, and the operating parameters of the boiler are used, considering that there is a strong correlation between the flue gas velocity and the flue gas temperature and the distribution of nitrogen oxides, by training the preset model according to the above thermotechnical parameters, the trained ammonia injection strategy model can take into account the distribution of nitrogen oxides, so as to accurately determine the ammonia injection strategy in the process of sectional ammonia injection. Description of the Drawings

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a schematic flowchart of a method for determining an ammonia injection strategy model of an SCR system reactor provided by an embodiment of the present invention;

[0043] Figure 2 It is a schematic flowchart of a method for determining an ammonia injection strategy of an SCR system reactor provided by an embodiment of the present invention;

[0044] Figure 3 It is a schematic structural diagram of a device for determining an ammonia injection strategy model of an SCR system reactor provided by an embodiment of the present invention;

[0045] Figure 4 It is a schematic structural diagram of a device for determining an ammonia injection strategy of an SCR system reactor provided by an embodiment of the present invention;

[0046] Figure 5 It is a structural diagram of a computing device provided by an embodiment of the present invention. Detailed Embodiments

[0047] The following will describe in detail the features and exemplary embodiments of various aspects of the present invention. To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present invention by showing examples of the present invention.

[0048] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise", or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or device including a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. Without further limitation, the elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article, or device including the said elements.

[0049] The process of removing flue gas pollutants is a key link in controlling emissions from thermal power plants and has important social significance in reducing air pollution and protecting the human living environment. In recent years, with the continuous upgrading of national requirements for pollutant emissions, the pollutant emission limits have gradually decreased. In the "50355" ultra-low emission project, it is clearly required that the concentration of nitric oxides (NOx) in the flue gas emitted by thermal power plants shall not be higher than 50 mg / m3.

[0050] The selective catalytic reduction (SCR) technology widely used at home and abroad is an effective means to reduce NOx emissions from thermal power plants, and the ammonia injection rate is the core parameter during the operation of the SCR system. When the ammonia injection rate is too low, it cannot meet the national requirements for NOx emission limits; when the ammonia injection rate is too high, the escaped NH3 not only harms the surrounding environment, but also reacts with sulfur oxides to form ammonium bisulfate, which adheres to the surface of the air preheater with a lower temperature, forms a viscous liquid and absorbs a large amount of dust in the flue gas, resulting in the blockage of the air preheater and affecting the safe operation of the power plant.

[0051] At present, for the problem of controlling the ammonia injection rate of the SCR system, the flue gas online monitoring system is mainly used to collect the NOx concentration value in the inlet flue gas, and then the ammonia injection rate is adjusted through the feedback control system. However, this method has problems in terms of accuracy and timeliness. In addition, there is a problem of improper matching of ammonia-nitrogen concentration in the reactor during the actual operation of the SCR system, specifically manifested as uneven distribution of the NOx concentration in the flue gas on the cross-section perpendicular to the mainstream direction, while the ammonia injection grid (AIG) mostly performs uniform ammonia injection operations, resulting in high local NOx concentration and a large amount of local NH3 escape at the reactor outlet.

[0052] In the existing technology, the main solutions include flow optimization and sectional ammonia injection, etc. The flow optimization method is to add a rectifying structure upstream of the reactor to strengthen the flue gas flow mixing and make the distribution of flue gas parameters on the cross-section more uniform. However, this method cannot completely avoid the uneven distribution of flue gas components on the cross-section. The sectional ammonia injection method is to transform the structure of the original ammonia injection grid to achieve the effect of separately controlling each spray head according to the incoming flue gas concentration distribution and realizing non-uniform ammonia injection. Formulating a reasonable non-uniform ammonia injection strategy is the key issue of the sectional ammonia injection technology.

[0053] In recent years, under the policy guidance of the country's full promotion of the intelligentization of the production process, the concept of "intelligent power plant" has been continuously infiltrated in the power industry, and the full intelligentization of power plants based on data and with self-learning ability has become an inevitable trend in the industry development.

[0054] By using machine learning methods and analyzing and modeling based on operation history data, more accurate calculation of ammonia injection volume can be achieved. However, conventional machine learning modeling methods highly depend on the quality of the training dataset. When the dataset quality is poor, the model prediction accuracy is low and the practical effect is poor. In addition, parameters such as the flue gas component concentration and its distribution are difficult to measure in real time, and conventional machine learning modeling means are limited in the application of sectional ammonia injection, and it is often difficult to accurately determine the ammonia injection strategy during the sectional ammonia injection process.

[0055] Therefore, in the existing technical solutions, there is a problem that it is difficult to accurately determine the ammonia injection strategy during the sectional ammonia injection process.

[0056] To solve the problem that it is difficult to accurately determine the ammonia injection strategy during the sectional ammonia injection process in the current technical solutions, the embodiments of the present invention provide a method for determining the ammonia injection strategy model of the SCR system reactor, a method for determining the ammonia injection strategy of the SCR system reactor, a device, equipment, and storage medium. First, obtain the thermal parameters of the SCR system reactor, where the thermal parameters include at least one of the distribution parameters of the flue gas flow rate at the first preset section, the distribution parameters of the flue gas temperature at the second preset section, and obtain the operation parameters of the boiler; then train the first sub-model in the preset model according to the thermal parameters to obtain the first target sub-model; then train the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain the second target sub-model; finally, determine the ammonia injection strategy model according to the first target sub-model and the second target sub-model for outputting the ammonia injection strategy. Because in the process of determining the ammonia injection strategy model of the SCR system reactor, thermal parameters including at least one of the distribution parameters of the flue gas flow rate at the first preset section, the distribution parameters of the flue gas temperature at the second preset section, and obtain the operation parameters of the boiler are used. Considering that there is a strong correlation between the flue gas flow rate and the flue gas temperature and the distribution of nitrogen oxides, by training the preset model according to the above thermal parameters, the trained ammonia injection strategy model can take into account the distribution of nitrogen oxides, so as to accurately determine the ammonia injection strategy during the sectional ammonia injection process.

[0057] The technical solutions provided by the embodiments of the present invention will be described below with reference to the accompanying drawings.

[0058] Figure 1 It is a schematic flow chart of a method for determining the ammonia injection strategy model of the SCR system reactor provided by the embodiments of the present invention. The execution subject of this method can be based on a processor, and this processor refers to an SCR controller.

[0059] As Figure 1 shown, the method for determining the ammonia injection strategy model of the SCR system reactor may include:

[0060] S101: Obtain the thermal parameters of the SCR system reactor.

[0061] Among them, the thermal parameters may include at least one of the distribution parameters of the flue gas velocity on the first preset cross-section and / or the second preset cross-section, the distribution parameters of the flue gas temperature on the first preset cross-section and / or the second preset cross-section, and the operating parameters of the boiler. The first preset cross-section refers to the cross-section at the inlet of the SCR system reactor, and the second preset cross-section refers to the cross-section at the outlet of the SCR system reactor.

[0062] In one embodiment, the distribution parameter of the flue gas velocity on the first preset cross-section and / or the second preset cross-section may be the velocity distribution parameter measured by a thermal ball anemometer on the first preset cross-section and / or the second preset cross-section; the distribution parameter of the flue gas temperature on the first preset cross-section and / or the second preset cross-section may be the temperature distribution parameter measured by the acoustic wave temperature measurement method on the first preset cross-section and / or the second preset cross-section; the operating parameters of the boiler specifically refer to the boiler load and the boiler flue gas volume parameter value.

[0063] After obtaining the thermal parameters, the preset model can be trained according to the obtained thermal parameters to generate an ammonia injection strategy model, that is, S102 - S104 are executed.

[0064] S102: Train the first sub-model in the preset model according to the thermal parameters to obtain the first target sub-model.

[0065] Optionally, the first sub-model may include a preset flow reaction control equation, which refers to a one-dimensional, two-dimensional or three-dimensional flow reaction control equation.

[0066] In this training process, for the convenience of data calculation and processing, the thermal parameters can be preprocessed first, and the SCR system reactor can be divided into multiple calculation units in the preset flue gas flow direction. Considering the correlation between the thermal parameters including the distribution parameter of the flue gas velocity and the distribution parameter of the flue gas temperature and the distribution of nitrogen oxides (NOx), this process can also use the mechanism analysis method to determine the mass and energy conservation of each unit in the SCR system reactor and the transport relationship of the first parameter between units according to the preprocessed thermal parameters and the above-mentioned preset flow reaction control equation, so as to obtain the mapping relationship between the cross-section flue gas parameter distribution of the SCR system reactor and the non-uniformity of the nitrogen oxides (NOx) concentration distribution upstream of the grid, where the first parameter includes at least one of mass, momentum, and energy.

[0067] Optionally, the above preprocessing process may specifically be to convert the parameter values of the obtained thermal parameters to the interval [0, 1] using the maximum-minimum normalization method, perform data clustering using the k-means algorithm, and reduce the ammonia injection amount, flue gas component concentration, flue gas physical property parameters, and flue gas flow parameters to one or several intermediate variables such as ammonia-nitrogen ratio, Reynolds number, and Nusselt number according to the flue gas flow reaction mechanism. Missing values of each parameter can be found in the time domain and interpolated using the maximum likelihood estimation method, and noise can be reduced using the extended Kalman filter in the frequency domain to obtain an operating parameter dataset for training the first sub-model, that is, the preprocessed thermal parameters. Among them, time domain analysis mainly includes data clustering and quality screening in time series, while frequency domain analysis mainly includes noise suppression and capturing of system dynamic response characteristics, which are used to distinguish different operating conditions and filter out low-quality data to make each parameter match in time series.

[0068] In one embodiment, after obtaining the transport relationship, one or several methods such as a preset neural network and a support vector machine can be used to correct and adjust the convective diffusion coefficient and component diffusion coefficient in the transport relationship according to the preset convective diffusion coefficient and preset component diffusion coefficient included in the thermal parameters to obtain the first target sub-model, that is, the trained NOx concentration distribution non-uniformity prediction model, so as to predict the non-uniformity of the NOx concentration distribution.

[0069] After obtaining the first target sub-model, that is, the trained NOx concentration distribution non-uniformity prediction model, S103 can be entered, that is, continue to train the second sub-model in the preset model according to the first target sub-model.

[0070] S103: Train the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain the second target sub-model.

[0071] In this process, the concentration distribution parameters of nitrogen oxides upstream of the ammonia injection grid of the SCR system reactor at the third preset section can be determined according to the first target sub-model, that is, the trained NOx concentration distribution non-uniformity prediction model and the thermal parameters; then the ammonia injection strategy can be determined using the second sub-model according to the concentration distribution parameters, the pre-stored outlet flue gas nitrogen oxide concentration, the pre-stored outlet ammonia concentration, and the pre-stored ammonia injection amount; then the outlet flue gas nitrogen oxide concentration and outlet ammonia concentration corresponding to the ammonia injection strategy can be determined according to the ammonia injection strategy and the first target sub-model; finally, the parameters of the second sub-model are adjusted according to the preset target outlet flue gas nitrogen oxide concentration, the preset target outlet ammonia concentration, the outlet flue gas nitrogen oxide concentration corresponding to the ammonia injection strategy, and the outlet ammonia concentration to obtain the second target sub-model.

[0072] It should be noted that since the concentration distribution parameters of nitrogen oxides upstream of the ammonia injection grid at the third preset cross-section are considered in the process of determining the ammonia injection strategy, this ammonia injection strategy is for the ammonia injection process in the sectional ammonia injection.

[0073] In one embodiment, the training process in S103 can use a neural network combined with a particle swarm optimization (PSO) algorithm to adjust the parameters of the second sub-model. Among them, the parameters of the second sub-model refer to the inertia weight, learning factor, speed position limit, and population size. Before iterative calculation, the population needs to be randomly initialized. When adjusting the parameters of the second sub-model, the fitness value of each particle needs to be calculated, and then the particle velocity and position are updated according to the fitness value to iteratively update the parameters of the second sub-model. When the NOx concentration and ammonia (NH3) concentration of the outlet flue gas obtained by inputting the ammonia injection strategy determined by the second sub-model with updated parameters into the first target sub-model meet the preset target outlet flue gas nitrogen oxide concentration and the preset target outlet ammonia concentration, that is, it meets the global optimal position, the update is stopped, and the second sub-model with adjusted parameters is used as the above-mentioned second target sub-model.

[0074] Optionally, in one embodiment, when iteratively updating the parameters of the second sub-model according to the preset target outlet flue gas nitrogen oxide concentration, the preset target outlet ammonia concentration, the outlet flue gas nitrogen oxide concentration corresponding to the ammonia injection strategy, and the outlet ammonia concentration to achieve adjustment, when the number of iterations meets the preset maximum value, the update can be stopped, and the second sub-model with updated parameters is used as the above-mentioned second target sub-model.

[0075] In addition, in one embodiment, the above-mentioned preset maximum value and the preset target outlet flue gas nitrogen oxide concentration, the preset target outlet ammonia concentration can be used as the stop conditions for parameter update. When the number of iterations first meets the preset maximum value, the update is stopped, and the second sub-model with updated parameters is used as the above-mentioned second target sub-model; it can also be when the number of iterations has not met the preset maximum value, but when the NOx concentration and ammonia (NH3) concentration of the outlet flue gas obtained by inputting the ammonia injection strategy determined by the second sub-model with updated parameters into the first target sub-model meet the preset target outlet flue gas nitrogen oxide concentration and the preset target outlet ammonia concentration, the update is stopped, and the second sub-model with adjusted parameters is used as the above-mentioned second target sub-model.

[0076] After obtaining the first target sub-model and the second target sub-model, the ammonia injection strategy model can be determined according to the first target sub-model and the second target sub-model, that is, S104 is executed.

[0077] S104: Determine the ammonia injection strategy model according to the first target sub-model and the second target sub-model.

[0078] Since the modeling method of coupling mechanism analysis and machine learning is adopted in the process of determining the ammonia injection strategy model, the obtained ammonia injection strategy model has strong interpretability, and the provided sectional ammonia injection strategy is also more accurate.

[0079] The method for determining the ammonia injection strategy model of the SCR system reactor provided in the embodiment of the present invention first obtains the thermal parameters of the SCR system reactor, where the thermal parameters include at least one of the distribution parameters of the flue gas flow rate on the first preset section, the distribution parameters of the flue gas temperature on the second preset section, and the operating parameters of the boiler; then trains the first sub-model in the preset model according to the thermal parameters to obtain the first target sub-model; then trains the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain the second target sub-model; finally, determines the ammonia injection strategy model according to the first target sub-model and the second target sub-model for outputting the ammonia injection strategy. Since in the process of determining the ammonia injection strategy model of the SCR system reactor, thermal parameters including at least one of the distribution parameters of the flue gas flow rate on the first preset section, the distribution parameters of the flue gas temperature on the second preset section, and the operating parameters of the boiler are used, considering that there is a strong correlation between the flue gas flow rate and the flue gas temperature and the distribution of nitrogen oxides, by training the preset model according to the above thermal parameters, the trained ammonia injection strategy model can take into account the distribution of nitrogen oxides, so as to accurately determine the ammonia injection strategy in the sectional ammonia injection process. In addition, in the process of determining the ammonia injection strategy model, the modeling method of coupling mechanism analysis and machine learning is also adopted, so that the obtained ammonia injection strategy model has strong interpretability and the provided sectional ammonia injection strategy is more accurate, thus solving the problem that it is difficult to accurately determine the ammonia injection strategy in the sectional ammonia injection process in the existing technical solutions, and realizing the accurate determination of the ammonia injection strategy in the sectional ammonia injection process.

[0080] Figure 2 It is a schematic flow chart of a method for determining the ammonia injection strategy of an SCR system reactor provided in an embodiment of the present invention. The execution subject of this method can be based on a processor, and this processor refers to an SCR controller.

[0081] As Figure 2 shown, the method for determining the ammonia injection strategy of the SCR system reactor may include:

[0082] S201: Obtain the target thermal parameters of the SCR system reactor.

[0083] Among them, the target thermal parameters include at least one of the distribution parameters of the flue gas flow rate on the first preset section, the distribution parameters of the flue gas temperature on the second preset section, and the operating parameters of the boiler;

[0084] S202: Obtain the ammonia injection strategy according to the target thermal parameters and the ammonia injection strategy model.

[0085] Among them, the ammonia injection strategy model is obtained based on Figure 1 the determination method of the ammonia injection strategy model of the SCR system reactor in

[0086] In the determination method of the ammonia injection strategy of the SCR system reactor provided in the embodiments of the present invention, the ammonia injection strategy is determined using a pre-determined ammonia injection strategy model. When determining the ammonia injection strategy model, first obtain the thermal parameters of the SCR system reactor. Among them, the thermal parameters include at least one of the distribution parameters of the flue gas velocity at the first preset section, the distribution parameters of the flue gas temperature at the second preset section, and the operating parameters of the boiler; then train the first sub-model in the preset model according to the thermal parameters to obtain the first target sub-model; then train the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain the second target sub-model; finally, determine the ammonia injection strategy model according to the first target sub-model and the second target sub-model for outputting the ammonia injection strategy. Because in the process of determining the ammonia injection strategy model of the SCR system reactor, thermal parameters including at least one of the distribution parameters of the flue gas velocity at the first preset section, the distribution parameters of the flue gas temperature at the second preset section, and the operating parameters of the boiler are used. Considering that there is a strong correlation between the flue gas velocity and the flue gas temperature and the distribution of nitrogen oxides, by training the preset model according to the above thermal parameters, the trained ammonia injection strategy model can take into account the distribution of nitrogen oxides, so as to accurately determine the ammonia injection strategy in the process of sectional ammonia injection. In addition, in the process of determining the ammonia injection strategy model, a modeling method combining mechanism analysis and machine learning is also adopted, so that the obtained ammonia injection strategy model has strong interpretability and the provided sectional ammonia injection strategy is more accurate. Therefore, the problem that it is difficult to accurately determine the ammonia injection strategy in the process of sectional ammonia injection in the existing technical solutions is solved, and the accurate determination of the ammonia injection strategy in the process of sectional ammonia injection is realized.

[0087] Corresponding to Figure 1 the flowchart of the determination method of the ammonia injection strategy model of the SCR system reactor in

[0088] Figure 3 FIG. is a schematic structural diagram of a device for determining an ammonia injection strategy model of an SCR system reactor provided in an embodiment of the present invention. As Figure 3 shown, the determination device may include:

[0089] An acquisition module 301 can be used to acquire the thermal parameters of the SCR system reactor. Among them, the thermal parameters include at least one of the distribution parameters of the flue gas flow rate on the first preset section and / or the second preset section, the distribution parameters of the flue gas temperature on the first preset section and / or the second preset section, and the operating parameters of the boiler obtained;

[0090] A processing module 302 can be used to train a first sub-model in a preset model according to the thermal parameters to obtain a first target sub-model;

[0091] The processing module 302 can also be used to train a second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain a second target sub-model;

[0092] The processing module 302 can also be used to determine an ammonia injection strategy model according to the first target sub-model and the second target sub-model.

[0093] In one embodiment, the processing module 302 can also be used to determine the material energy conservation and the transport relationship of the first parameter in the SCR system reactor according to the thermal parameters and the first sub-model. Among them, the first parameter includes at least one of mass, momentum, and energy. Then, the transport relationship is trained according to the thermal parameters to obtain a first target sub-model.

[0094] In one embodiment, the first sub-model includes a preset flow reaction control equation.

[0095] The processing module 302 can also be used to divide the SCR system reactor into multiple calculation units in the preset flue gas flow direction. Then, according to the thermal parameters and the preset flow reaction control equation, the material energy conservation of each unit in the SCR system reactor and the transport relationship of the first parameter between units are determined.

[0096] In one embodiment, the thermal parameters further include a preset convective diffusion coefficient and a preset component diffusion coefficient.

[0097] The processing module 302 can also be used to use a preset neural network to adjust the transport relationship according to the preset convective diffusion coefficient and the preset component diffusion coefficient to obtain a first target sub-model.

[0098] In one embodiment, the processing module 302 can also be used to determine the concentration distribution parameter of nitrogen oxides upstream of the ammonia injection grid in the SCR system reactor on the third preset section according to the first target sub-model and the thermal parameters. Then, the second sub-model is used to determine the ammonia injection strategy according to the concentration distribution parameter, the pre-stored outlet flue gas nitrogen oxide concentration, the pre-stored outlet ammonia concentration, and the pre-stored ammonia injection amount. Then, the second sub-model is trained according to the ammonia injection strategy and the first target sub-model to obtain a second target sub-model.

[0099] In one embodiment, the processing module 302 may further be configured to determine the concentration of nitrogen oxides in the outlet flue gas and the concentration of ammonia in the outlet corresponding to the ammonia injection strategy according to the ammonia injection strategy and the first target sub-model, and adjust the parameters of the second sub-model according to the concentration of nitrogen oxides in the outlet flue gas and the concentration of ammonia in the outlet corresponding to the ammonia injection strategy to obtain a second target sub-model.

[0100] In one embodiment, the processing module 302 may further be configured to adjust the parameters of the second sub-model according to the preset target concentration of nitrogen oxides in the outlet flue gas, the preset target concentration of ammonia in the outlet, the concentration of nitrogen oxides in the outlet flue gas corresponding to the ammonia injection strategy, and the concentration of ammonia in the outlet to obtain a second target sub-model.

[0101] In the determining device for the ammonia injection strategy model of the SCR system reactor provided in the embodiments of the present invention, first, an acquisition module acquires the thermal parameters of the SCR system reactor, where the thermal parameters include at least one of the distribution parameters of the flue gas flow rate at a first preset cross-section, the distribution parameters of the flue gas temperature at a second preset cross-section, and the operating parameters of the boiler; then the processing module trains the first sub-model in the preset model according to the thermal parameters to obtain a first target sub-model; then trains the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain a second target sub-model; finally, determines the ammonia injection strategy model according to the first target sub-model and the second target sub-model for outputting the ammonia injection strategy. Because in the process of determining the ammonia injection strategy model of the SCR system reactor, thermal parameters including at least one of the distribution parameters of the flue gas flow rate at a first preset cross-section, the distribution parameters of the flue gas temperature at a second preset cross-section, and the operating parameters of the boiler are used, considering that there is a strong correlation between the flue gas flow rate and the flue gas temperature and the distribution of nitrogen oxides, by training the preset model according to the above thermal parameters, the trained ammonia injection strategy model can take into account the distribution of nitrogen oxides, so as to accurately determine the ammonia injection strategy in the process of sectional ammonia injection. In addition, in the process of determining the ammonia injection strategy model, a modeling method combining mechanism analysis and machine learning is adopted, so that the obtained ammonia injection strategy model has strong interpretability and the provided sectional ammonia injection strategy is more accurate. Therefore, the problem in the existing technical solution that it is difficult to accurately determine the ammonia injection strategy in the process of sectional ammonia injection is solved, and the accurate determination of the ammonia injection strategy in the process of sectional ammonia injection is realized.

[0102] Corresponding to Figure 2 the flowchart of the method for determining the ammonia injection strategy of the SCR system reactor in [reference], the embodiments of the present invention further provide a device for determining the ammonia injection strategy of the SCR system reactor.

[0103] Figure 4This is a schematic structural diagram of a device for determining the ammonia injection strategy of an SCR system reactor provided by an embodiment of the present invention. As Figure 4 shown, the determining device may include:

[0104] An acquisition module 401, which can be used to acquire the target thermal parameters of the SCR system reactor, where the target thermal parameters include at least one of the distribution parameters of the flue gas flow rate on the first preset cross-section, the distribution parameters of the flue gas temperature on the second preset cross-section, and the operating parameters of the boiler obtained;

[0105] A processing module 402, which can be used to obtain the ammonia injection strategy according to the target thermal parameters and the ammonia injection strategy model.

[0106] Among them, the ammonia injection strategy model is obtained based on Figure 1 the method for determining the ammonia injection strategy model of the SCR system reactor in

[0107] For the device for determining the ammonia injection strategy of the SCR system reactor provided by the embodiment of the present invention, the ammonia injection strategy is determined using a pre-determined ammonia injection strategy model. When determining the ammonia injection strategy model, first, the thermal parameters of the SCR system reactor are acquired, where the thermal parameters include at least one of the distribution parameters of the flue gas flow rate on the first preset cross-section, the distribution parameters of the flue gas temperature on the second preset cross-section, and the operating parameters of the boiler obtained; then, the first sub-model in the preset model is trained according to the thermal parameters to obtain the first target sub-model; then, the second sub-model in the preset model is trained according to the first target sub-model and the thermal parameters to obtain the second target sub-model; finally, the ammonia injection strategy model is determined according to the first target sub-model and the second target sub-model for outputting the ammonia injection strategy. Because in the process of determining the ammonia injection strategy model of the SCR system reactor, thermal parameters including at least one of the distribution parameters of the flue gas flow rate on the first preset cross-section, the distribution parameters of the flue gas temperature on the second preset cross-section, and the operating parameters of the boiler obtained are used, considering that there is a strong correlation between the flue gas flow rate and the flue gas temperature and the distribution of nitrogen oxides, by training the preset model according to the above thermal parameters, the trained ammonia injection strategy model can take into account the distribution of nitrogen oxides, so as to accurately determine the ammonia injection strategy in the process of sectional ammonia injection. In addition, in the process of determining the ammonia injection strategy model, a modeling method combining mechanism analysis and machine learning is also adopted, so that the obtained ammonia injection strategy model has strong interpretability and the provided sectional ammonia injection strategy is more accurate. Therefore, the problem in the existing technical solution that it is difficult to accurately determine the ammonia injection strategy in the process of sectional ammonia injection is solved, and the accurate determination of the ammonia injection strategy in the process of sectional ammonia injection is realized.

[0108] Figure 5 This is a structural diagram of the hardware architecture of a computing device provided by an embodiment of the present invention. As Figure 5As shown, the computing device 500 includes an input device 501, an input interface 502, a central processing unit 503, a memory 504, an output interface 505, and an output device 506. Among them, the input interface 502, the central processing unit 503, the memory 504, and the output interface 505 are interconnected through a bus 510. The input device 501 and the output device 506 are respectively connected to the bus 510 through the input interface 502 and the output interface 505, and then connected to other components of the computing device 500.

[0109] Specifically, the input device 501 receives input information from the outside and transmits the input information to the central processing unit 503 through the input interface 502; the central processing unit 503 processes the input information based on computer-executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 through the output interface 505; the output device 506 outputs the output information to the outside of the computing device 500 for user use.

[0110] That is to say, Figure 5 the computing device shown can also be implemented as a determining device for the SCR system reactor ammonia injection strategy model or a determining device for the SCR system reactor ammonia injection strategy. The determining device may include: a processor and a memory storing computer-executable instructions; when the processor executes the computer-executable instructions, it can implement the method for determining the SCR system reactor ammonia injection strategy model provided by the embodiments of the present invention, or the method for determining the SCR system reactor ammonia injection strategy.

[0111] The embodiments of the present invention also provide a computer-readable storage medium, on which computer program instructions are stored; when the computer program instructions are executed by a processor, they implement the method for determining the SCR system reactor ammonia injection strategy model provided by the embodiments of the present invention, or the method for determining the SCR system reactor ammonia injection strategy.

[0112] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions after understanding the spirit of the present invention, or change the order between steps.

[0113] The functional blocks shown in the above-described structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present invention are programs or code segments for performing the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0114] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, can be different from the order in the embodiments, or several steps can be executed simultaneously.

[0115] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block in the flowcharts and / or block diagrams, and the combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more blocks of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It is also understood that each block in the block diagram and / or flowchart, and the combinations of blocks in the block diagram and / or flowchart, can also be implemented by dedicated hardware performing the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0116] As described above, the foregoing are only specific embodiments of the present invention. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules, and units described above may refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present invention.

Claims

1. A method for determining an ammonia injection strategy model of an SCR system reactor, characterized in that, The method includes: Obtaining the thermal parameters of the SCR system reactor, where the thermal parameters include at least one of the distribution parameters of the flue gas velocity on the first preset cross-section and / or the second preset cross-section, the distribution parameters of the flue gas temperature on the first preset cross-section and / or the second preset cross-section, and the operating parameters of the boiler; Training the first sub-model in the preset model according to the thermal parameters to obtain a first target sub-model; Training the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain a second target sub-model; Determining an ammonia injection strategy model according to the first target sub-model and the second target sub-model; The training the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain a second target sub-model includes: Determining the concentration distribution parameters of nitrogen oxides upstream of the ammonia injection grid of the SCR system reactor on the third preset cross-section according to the first target sub-model and the thermal parameters; Using the second sub-model to determine an ammonia injection strategy according to the concentration distribution parameters, the pre-stored outlet flue gas nitrogen oxide concentration, the pre-stored outlet ammonia concentration, and the pre-stored ammonia injection amount; Training the second sub-model according to the ammonia injection strategy and the first target sub-model to obtain a second target sub-model; the training the second sub-model according to the ammonia injection strategy and the first target sub-model to obtain a second target sub-model includes: Determining the outlet flue gas nitrogen oxide concentration and the outlet ammonia concentration corresponding to the ammonia injection strategy according to the ammonia injection strategy and the first target sub-model; Adjusting the parameters of the second sub-model according to the outlet flue gas nitrogen oxide concentration and the outlet ammonia concentration corresponding to the ammonia injection strategy to obtain a second target sub-model.

2. The method according to claim 1, characterized in that, The training the first sub-model in the preset model according to the thermal parameters to obtain a first target sub-model includes: Determining the material energy conservation and the transport relationship of the first parameter in the SCR system reactor according to the thermal parameters and the first sub-model, where the first parameter includes at least one of mass, momentum, and energy; Training the transport relationship according to the thermal parameters to obtain a first target sub-model.

3. The method according to claim 2, characterized in that, The first sub-model includes a preset flow reaction control equation; the determining the material energy conservation and the transport relationship of the first parameter in the SCR system reactor according to the thermal parameters and the first sub-model includes: Dividing the SCR system reactor into a plurality of calculation units in the preset flue gas flow direction; Determining the material energy conservation of each unit in the SCR system reactor and the transport relationship of the first parameter between units according to the thermal parameters and the preset flow reaction control equation.

4. A method for determining an ammonia injection strategy of an SCR system reactor, characterized in that, The method includes: Obtaining the target thermal parameters of the SCR system reactor, where the target thermal parameters include at least one of the distribution parameters of the flue gas velocity on the first preset cross-section, the distribution parameters of the flue gas temperature on the second preset cross-section, and the operating parameters of the boiler; Based on the target thermal parameters and the ammonia injection strategy model, an ammonia injection strategy is obtained, where the ammonia injection strategy model is obtained based on the method for determining the ammonia injection strategy model of the SCR system reactor according to any one of claims 1 to 3.

5. A device for determining an ammonia injection strategy model of an SCR system reactor, characterized in that, The device includes: An acquisition module, configured to acquire the thermal parameters of the SCR system reactor, where the thermal parameters include at least one of the distribution parameters of the flue gas flow rate at the first preset section and / or the second preset section, the distribution parameters of the flue gas temperature at the first preset section and / or the second preset section, and the operating parameters of the boiler. A processing module, configured to train the first sub-model in the preset model according to the thermal parameters to obtain a first target sub-model. The processing module is further configured to train the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain a second target sub-model. The processing module is further configured to determine an ammonia injection strategy model according to the first target sub-model and the second target sub-model. The training of the second sub-model in the preset model according to the first target sub-model and the thermal parameters to obtain a second target sub-model includes: Determining the concentration distribution parameters of nitrogen oxides upstream of the ammonia injection grid of the SCR system reactor at the third preset section according to the first target sub-model and the thermal parameters. Using the second sub-model to determine an ammonia injection strategy according to the concentration distribution parameters, the pre-stored outlet flue gas nitrogen oxide concentration, the pre-stored outlet ammonia concentration, and the pre-stored ammonia injection amount. Training the second sub-model according to the ammonia injection strategy and the first target sub-model to obtain a second target sub-model; the training of the second sub-model according to the ammonia injection strategy and the first target sub-model to obtain a second target sub-model includes: Determining the outlet flue gas nitrogen oxide concentration and the outlet ammonia concentration corresponding to the ammonia injection strategy according to the ammonia injection strategy and the first target sub-model. Adjusting the parameters of the second sub-model according to the outlet flue gas nitrogen oxide concentration and the outlet ammonia concentration corresponding to the ammonia injection strategy to obtain a second target sub-model.

6. A device for determining an ammonia injection strategy of an SCR system reactor, characterized in that, The device includes: An acquisition module, configured to acquire the target thermal parameters of the SCR system reactor, where the target thermal parameters include at least one of the distribution parameters of the flue gas flow rate at the first preset section, the distribution parameters of the flue gas temperature at the second preset section, and the operating parameters of the boiler. A processing module, configured to obtain an ammonia injection strategy according to the target thermal parameters and the ammonia injection strategy model, where the ammonia injection strategy model is obtained based on the method for determining the ammonia injection strategy model of the SCR system reactor according to any one of claims 1 to 3.

7. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions. When the processor executes the computer program instructions, it implements the method for determining the ammonia injection strategy model of the SCR system reactor according to any one of claims 1 to 3, or when the processor executes the computer program instructions, it implements the method for determining the ammonia injection strategy of the SCR system reactor according to claim 4.

8. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, which, when executed by a processor, implement the method for determining the ammonia injection strategy model of the SCR system reactor as described in any one of claims 1-3, or, when executed by a processor, implement the method for determining the ammonia injection strategy of the SCR system reactor as described in claim 4.

Images