Control method and device for selective non-catalytic reduction of nitrogen oxides

Abstract

The invention discloses a control method and device for selective non-catalytic reduction of nitric oxide, and relates to the field of emission treatment. In the method, production condition data are collected, and the production condition data comprise reaction temperature, flue gas flow, oxygen concentration and first nitrogen oxide concentration; predicting a second nitrogen oxide concentration at a future preset moment by using a preset prediction model according to the production condition data; a preset control model is used for calculating control data according to the second nitrogen oxide concentration and the production working condition data, and the control data comprise the ammonia water demand quantity, the compressed air demand quantity and the optimal ammonia spraying position; and controlling the flow and the position of the spray gun at each point location according to the control data. By implementing the technical scheme provided by the invention, the technical effect of accurately predicting and controlling nitrogen oxide emission is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of emission treatment, and in particular to a control method and device for selective non-catalytic reduction of nitrogen oxides. Background Art

[0002] The emission control of nitrogen oxides (NOx) has attracted more and more attention. It is not only related to environmental protection, but also an important factor in the sustainable development of enterprises. This is mainly because the nitrogen oxides produced in industrial processes such as coal burning and waste incineration will seriously affect the air quality, increase the probability of acid rain, photochemical smog and other problems, and thus affect human health and the ecological environment.

[0003] At present, common solutions mainly include the use of indirect measurement and empirical control to control nitrogen oxide emissions, including the following solutions: The first solution is to monitor the nitrogen oxide concentration in the flue gas under the existing working conditions and adjust the amount of ammonia added according to empirical data; the second solution is to directly adjust the opening or closing of the spray gun and the increase or decrease of the ammonia injection amount according to the pre-set proportional parameters during the production process. These conventional means can achieve the initial goal of reducing nitrogen oxide emissions. However, these traditional control methods have certain limitations in practical applications. For example, it is difficult to achieve precise control based on empirical control methods, which may lead to excessive or insufficient use of reducing agents, thereby affecting conversion efficiency and economic benefits.

[0004] Therefore, a method for reducing nitrogen oxides with higher efficiency is needed. Summary of the invention

[0005] The present application provides a control method and device for selective non-catalytic reduction of nitrogen oxides, which has the technical effect of accurately predicting and controlling nitrogen oxide emissions.

[0006] In a first aspect of the present application, a control method for selective non-catalytic reduction of nitrogen oxides is provided, which is applied to a selective non-catalytic reduction control platform, and the method comprises: Collecting production condition data, wherein the production condition data includes reaction temperature, flue gas flow rate, oxygen concentration and first nitrogen oxide concentration; Predicting a second nitrogen oxide concentration at a preset time in the future according to the production condition data using a preset prediction model; Calculating control data using a preset control model according to the second nitrogen oxide concentration and the production condition data, the control data including ammonia water demand, compressed air demand and an optimal ammonia injection position; The flow rate and position of the spray gun at each point are controlled according to the control data.

[0007] By adopting the above technical solution, real-time production condition data (such as reaction temperature, flue gas flow, oxygen concentration and first nitrogen oxide concentration) are collected, and the nitrogen oxide concentration at the preset time in the future is predicted by using the preset prediction model. This method can predict the generation trend of NOx in advance, so as to formulate a control strategy more accurately. Compared with the traditional hysteresis control, this method significantly improves the accuracy and timeliness of control. Using the predicted second nitrogen oxide concentration and production condition data, the control data such as ammonia demand, compressed air demand and optimal ammonia injection position are calculated through the preset control model. This optimization calculation based on real-time data and prediction results can ensure the accurate addition of reducing agents such as ammonia, avoid excessive or insufficient, thereby optimizing resource utilization and reducing operating costs. By accurately controlling the flow and position of the spray gun, it is ensured that reducing agents such as ammonia react with NOx in the flue gas under optimal conditions, thereby effectively reducing NOx emissions. This method not only meets environmental protection requirements, but also helps enterprises improve their social image and competitiveness. By integrating the prediction model and the control model, intelligent control of the SNCR system is realized. This automated and intelligent control method can reduce human intervention, reduce operational difficulty and error rate, and thus improve the stability and reliability of the system. By accurately controlling the amount of ammonia added and the ammonia injection position, unnecessary energy consumption and ammonia escape can be reduced, further promoting the realization of energy conservation and emission reduction goals. This is of great significance for alleviating energy pressure and improving environmental quality.

[0008] Optionally, the using a preset prediction model to predict the second nitrogen oxide concentration at a preset time in the future according to the production condition data includes: Acquire historical production condition data, and extract correlation features of nitrogen oxide concentration from the historical production condition data, wherein the correlation features include an average value, a change rate, and a ratio of flue gas flow rate to oxygen concentration within a temperature window; Associating the associated features with corresponding nitrogen oxide concentration data to form a data set, and training and validating an initial model through the data set to obtain a preset prediction model; The production condition data is input into the preset prediction model to obtain a second nitrogen oxide concentration at a preset time in the future.

[0009] By adopting the above technical solution, the key factors affecting the change of NOx concentration are captured through the correlation features (such as the average value, change rate, ratio of flue gas flow rate to oxygen concentration, etc. within the temperature window). The data set formed by associating these correlation features with the corresponding NOx concentration data provides rich and high-quality information for the training of the prediction model. This enables the trained preset prediction model to more accurately capture the complex relationship between NOx concentration and production conditions, thereby improving the accuracy and reliability of the prediction. Training and validating the initial model using historical production condition data is a key step. This process not only optimizes the parameters of the model, but also enables the model to learn the ability to extract useful information from the data and make predictions. More importantly, through the verification process, the performance of the model under different conditions can be evaluated and adjusted to improve the generalization ability. This means that the preset prediction model can better adapt to various production condition changes that may be encountered in the future, ensuring the stability and accuracy of the prediction results. By inputting real-time production condition data into the preset prediction model, the enterprise can quickly obtain the predicted value of NOx concentration at a preset time in the future. This real-time prediction capability enables enterprises to understand the trend of NOx emissions in a timely manner and formulate corresponding control strategies or adjust production parameters based on the prediction results. This helps companies better meet environmental protection requirements, reduce the risk of excessive emissions, and optimize resource utilization. The integration of preset prediction models into the SNCR control system enables intelligent prediction and control of NOx emissions. This increase in intelligence not only improves the automation and operating efficiency of the system, but also reduces the need for human intervention and the error rate. At the same time, the intelligent control system can also automatically adjust the control strategy based on real-time data and prediction results to ensure that the system is always in the optimal operating state.

[0010] Optionally, the calculating control data by using a preset control model according to the second nitrogen oxide concentration and the production condition data includes: Calculating the mass flow rate of the second nitrogen oxide according to the flue gas flow rate and the second nitrogen oxide concentration in the production condition data; The required molar amount of ammonia is determined according to the mass flow rate of the second nitrogen oxide, and the required amount of ammonia water is determined according to the concentration of ammonia water, the molar amount of ammonia gas and the injection efficiency.

[0011] By adopting the above technical solution, the mass flow rate of the second nitrogen oxide is calculated according to the flue gas flow rate in the production condition data and the predicted concentration of the second nitrogen oxide. This step ensures accurate calculation based on the actual working conditions and predicted results, and provides an accurate basis for the subsequent determination of the ammonia demand. The required molar amount of ammonia is determined according to the mass flow rate of nitrogen oxides and the chemical reaction equation. This ensures the stoichiometric relationship between ammonia and nitrogen oxides, laying the foundation for achieving efficient NOx reduction reaction. The required ammonia demand is calculated according to the concentration of ammonia, the molar amount of ammonia and the injection efficiency. This step comprehensively considers the physical properties of ammonia (such as concentration) and actual operating conditions (such as injection efficiency) of ammonia, ensuring the accuracy and effectiveness of ammonia addition. By accurately calculating the ammonia demand, it is possible to ensure that the ammonia dosage is increased when the NOx concentration is high, thereby achieving higher emission reduction efficiency. The preset control model is integrated into the SNCR control system to realize the automatic control of the ammonia dosage. This reduces the need for human intervention and the error rate, and improves the stability and reliability of the system. The system can automatically adjust the control strategy according to real-time data and predicted results to ensure that the optimal emission reduction effect can be achieved under different working conditions. This improves the intelligence level and adaptive ability of the system. By accurately controlling the amount of ammonia added, unnecessary waste and additional processing costs are avoided. This helps companies reduce operating costs and improve economic benefits. At the same time, good emission reduction effects also help companies establish a good environmental image and lay a good foundation for their long-term development.

[0012] Optionally, the calculating control data using a preset control model according to the second nitrogen oxide concentration and the production condition data further includes: The proportionality coefficient is obtained by experimentally measuring the compressed air flow rate corresponding to different ammonia water injection amounts, and the compressed air demand is determined according to the proportionality coefficient and the ammonia water demand.

[0013] By adopting the above technical solution, the proportional coefficient obtained by experimental measurement can ensure that the ammonia water and compressed air maintain the best proportional relationship during the injection process. This optimization not only helps to improve the atomization effect of ammonia water, so that ammonia water can more fully contact and react with NOx in the flue gas, thereby improving the NOx reduction efficiency, but also reduces unnecessary compressed air consumption and energy consumption. The compressed air demand calculation based on the proportional coefficient and the ammonia water demand can achieve accurate control of the compressed air dosage. This helps to avoid problems caused by excessive or insufficient compressed air, such as excessive may lead to increased energy consumption, and insufficient may affect the atomization effect of ammonia water and the NOx reduction efficiency. By accurately controlling the demand for compressed air, the impact of unstable compressed air supply on system performance can be reduced. This helps to maintain the stability and reliability of system operation and improve the overall performance of the system. Integrating this calculation process into the preset control model can realize automatic calculation and adjustment of compressed air demand. This further improves the intelligence level of the system and reduces the need for manual intervention and error rate.

[0014] Optionally, the calculating control data using a preset control model according to the second nitrogen oxide concentration and the production condition data further includes: In the numerical simulation software, establish the geometric model, boundary conditions and initial conditions of the furnace or flue; Start numerical simulation to calculate the flow characteristics of flue gas in the furnace or flue, including temperature distribution and velocity distribution, and identify the target area where the flue gas mixing degree, velocity and temperature meet the preset conditions; A reaction temperature window of the selective non-catalytic reduction reaction is determined according to the type of ammonia water and the second nitrogen oxide concentration, and an ammonia water injection position is selected within the target area in combination with the flow characteristics within the reaction temperature window.

[0015] By adopting the above technical solution, the geometric model, boundary conditions and initial conditions established by the numerical simulation software can accurately simulate the flow characteristics of flue gas in the furnace or flue, including temperature distribution, flow velocity distribution, etc. This helps to identify the target area where the mixing degree, flow velocity and temperature meet the preset conditions, so as to select the ammonia injection position in these areas. Such precise positioning can ensure that ammonia and NOx in the flue gas are fully in contact and react, thereby improving the reduction efficiency of NOx. According to the reaction temperature window of the selective non-catalytic reduction reaction determined by the type of ammonia and the concentration of the second nitrogen oxide, the injection position is selected in combination with the flow characteristics, which can avoid injecting ammonia in an unsuitable temperature area, thereby reducing the waste of ammonia and unnecessary emissions. At the same time, the precise injection position can also ensure the effective use of ammonia and improve the utilization efficiency of resources. The ammonia injection position determined by numerical simulation can maintain the stable operation of the system. An unreasonable injection position may lead to excessive or insufficient local ammonia, thereby affecting the overall performance of the system. The injection position optimized by numerical simulation can avoid these problems and improve the stability and reliability of the system. The automatic optimization of the ammonia injection position is achieved by combining the numerical simulation software with the preset control model. This process reduces the need for manual intervention and the error rate, and improves the intelligence and automation level of the system. At the same time, through continuous iteration and optimization, the system can continue to adapt to changes in production conditions and maintain an efficient and stable operating state.

[0016] Optionally, the calculating control data by using a preset control model according to the second nitrogen oxide concentration and the production condition data includes: A preset number of control strategies are randomly generated as an initial population, and a fitness function is determined according to an objective function, wherein the control strategy includes encoding control variables, and the control variables include spray gun flow, pressure, and position; and the objective function is a weighted sum of nitrogen oxide emissions and ammonia consumption; The fitness of each control strategy is calculated by the fitness function, a target control strategy is selected by a selection operation to perform a crossover operation to obtain a sub-control strategy, the sub-control strategy is randomly mutated, and the number of iterations is increased by one; Repeat the previous step until the maximum number of iterations is reached or the target control strategy remains unchanged, and output the control data according to the final target control strategy.

[0017] By adopting the above technical solutions, the genetic algorithm generates the initial population randomly and evolves continuously through operations such as selection, crossover and mutation in each iteration, and has a strong global search capability. This helps to find the optimal or near-optimal control strategy in a complex and changing environment and achieve the best balance between nitrogen oxide emissions and ammonia consumption. The optimized control strategy can more accurately control the flow, pressure and position of the spray gun, thereby improving the performance of the SNCR system. This includes improving the NOx reduction efficiency, reducing ammonia escape, and reducing unnecessary ammonia consumption. By optimizing the amount of ammonia used and the injection position, excessive ammonia consumption and unnecessary emissions can be avoided, thereby reducing operating costs. This is particularly important for large-scale industrial equipment that needs to operate for a long time. The optimization process of the genetic algorithm can automatically adjust the control strategy according to real-time data and system status to adapt to changes in production conditions. This adaptive adjustment capability enables the system to maintain efficient and stable operation under different conditions. The integration of the genetic algorithm into the preset control model realizes the automatic optimization and decision-making of the control strategy. This reduces the need for manual intervention and the error rate, and improves the intelligence level and automation level of the system. Genetic algorithms continuously approach the optimal solution through an efficient iterative process, and can complete a large amount of calculation and optimization work in a short period of time. This helps to shorten the optimization cycle and improve production efficiency.

[0018] Optionally, controlling the flow rate and position of the spray gun at each point according to the control data includes: A spray gun number in the control data and target spray data corresponding to the spray gun number are acquired from the control data, the target spray data is transmitted to a corresponding target spray gun according to the spray gun number, and the target spray data is executed by the target spray gun.

[0019] By adopting the above technical solution, by obtaining the spray gun number and its corresponding target injection data from the control data, it can be ensured that each spray gun can receive accurate control instructions. This point-to-point control method avoids possible misoperation or instruction confusion in traditional control methods, and ensures the accurate execution of the control strategy. When the optimized control data is generated, the target injection data can be immediately transmitted to the corresponding target spray gun according to the spray gun number. This instant transmission mechanism reduces the delay of data transmission, improves the response speed of the system, and enables the system to adapt to changes in production conditions more quickly. The target injection data in the control data includes parameters such as the flow rate and position of the spray gun, which are the optimal solutions calculated according to the optimization algorithm. By allocating these parameters to each spray gun, the reasonable allocation and utilization of resources can be ensured, and the waste and unnecessary consumption of resources can be avoided. The entire control process is automated and intelligent, reducing the need for manual intervention and the error rate. This helps to reduce the system fluctuations and failure risks caused by improper human operation and enhance the stability and reliability of the system. By accurately controlling parameters such as the flow rate and position of the spray gun, the reduction effect of the SNCR system can be optimized, the NOx reduction efficiency can be improved, and the ammonia slip can be reduced. This helps reduce the emission of harmful substances, improve environmental benefits and corporate social responsibility. The spray guns at various points work together according to the optimized control data to achieve efficient reduction of NOx. This collaborative working mode helps improve production efficiency and product quality, and reduce production costs and energy consumption.

[0020] In a second aspect of the present application, a control system for selective non-catalytic reduction of nitrogen oxides is provided, comprising a collection module, a prediction module, a calculation module and a control module, wherein: A collection module configured to collect production condition data, wherein the production condition data includes reaction temperature, flue gas flow, oxygen concentration and first nitrogen oxide concentration; A prediction module, configured to predict a second nitrogen oxide concentration at a preset time in the future according to the production condition data using a preset prediction model; a calculation module configured to calculate control data using a preset control model according to the second nitrogen oxide concentration and the production condition data, the control data including ammonia water demand, compressed air demand and an optimal ammonia injection position; The control module is configured to control the flow rate and position of the spray gun at each point according to the control data.

[0021] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Predict the second nitrogen oxide concentration at a preset time in the future based on the current production condition data (such as reaction temperature, flue gas flow, oxygen concentration and first nitrogen oxide concentration) through a preset prediction model. This step can predict the system status in advance and provide a basis for subsequent precise control. Based on the predicted second nitrogen oxide concentration and production condition data, the preset control model can calculate accurate control data, including ammonia demand, compressed air demand and optimal ammonia injection position. This precise control ensures the effectiveness and efficiency of the SNCR system; 2. By accurately calculating the demand for ammonia water and compressed air, we can avoid waste and unnecessary consumption of resources and improve resource utilization efficiency; determining the best ammonia injection position can ensure that ammonia water is fully in contact with nitrogen oxides in the flue gas, improve reduction efficiency, reduce ammonia escape, and further improve system efficiency; 3. Based on the real-time collected production condition data and the predicted future nitrogen oxide concentration, the system can adjust the control strategy in real time to adapt to the changes in production conditions and maintain the stable operation of the system; accurate control data and timely adjustment mechanism can reduce the fluctuation of system operation and ensure the stability and reliability of the system; 4. By optimizing the amount of ammonia used and the location of ammonia injection, the SNCR system can more effectively reduce nitrogen oxides, reduce emissions, and meet more stringent environmental protection requirements; the entire control process is automated and intelligent, reducing the need for manual intervention and the error rate, and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic flow chart of a control method for selective non-catalytic reduction of nitrogen oxides disclosed in an embodiment of the present application; Figure 2 It is a process flow diagram of a control method for selective non-catalytic reduction of nitrogen oxides disclosed in an embodiment of the present application; Figure 3 is a communication topology diagram of the selective non-catalytic reduction control platform disclosed in the embodiment of the present application; Figure 4 It is a module schematic diagram of a control system for selective non-catalytic reduction of nitrogen oxides disclosed in an embodiment of the present application; Figure 5 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0025] Explanation of the reference numerals: 401, acquisition module; 402, prediction module; 403, calculation module; 404, control module; 501, processor; 502, communication bus; 503, user interface; 504, network interface; 505, memory. DETAILED DESCRIPTION

[0026] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0028] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0029] This embodiment discloses a control method for selective non-catalytic reduction of nitrogen oxides, which is applied to a selective non-catalytic reduction control platform. Figure 1 is a flow chart of a control method for selective non-catalytic reduction of nitrogen oxides disclosed in an embodiment of the present application, such as Figure 1 As shown, the control method includes the following steps: S110, collecting production condition data, wherein the production condition data includes reaction temperature, flue gas flow rate, oxygen concentration and first nitrogen oxide concentration; SNCR technology, or selective non-catalytic reduction technology, is a clean denitrification technology that sprays an amino-containing reducing agent (ammonia water or urea, etc.) into the furnace within a reaction temperature window of 850 to 1100°C to reduce and remove NOx in the flue gas to generate nitrogen and water.

[0030] Reaction temperature is one of the key factors of SNCR technology. The reaction efficiency of the reducing agent and nitrogen oxides is highly dependent on temperature. Generally speaking, the suitable temperature range of SNCR reaction is 950℃~1050℃, but the specific optimal temperature may vary depending on different working conditions and types of reducing agents. When the temperature is below 800℃, the reaction rate is very slow; when the temperature is above 1100℃, the reducing agent may react with oxygen to generate new nitrogen oxides instead of undergoing a reduction reaction with nitrogen oxides. The reaction temperature window using ammonia water as the reducing agent is 850~1050℃, and the reaction window temperature using urea as the reducing agent is 950~1100℃. The reaction temperature can be measured in real time by a temperature sensor arranged in the flue gas channel. These temperature data are crucial for adjusting the injection amount and position of the reducing agent to ensure that the reaction is carried out within the optimal temperature window. The flue gas flow rate directly affects the residence time of the flue gas in the reaction area and the mixing effect of the reducing agent and nitrogen oxides. High flow rate may lead to incomplete reaction, while low flow rate may increase the consumption of reducing agent and ammonia slip. The flue gas flow rate can be measured by devices such as flow meters or differential pressure gauges. These data are critical for evaluating the reaction efficiency and adjusting the injection rate of the reducing agent. The oxygen concentration also has a significant effect on the SNCR reaction. Although oxygen is one of the necessary conditions for the reaction, an excessively high oxygen concentration may promote the direct reaction of the reducing agent with oxygen to generate new nitrogen oxides, thereby reducing the denitrification efficiency. A trace amount of O2 is conducive to the SNCR reaction, and the increase in oxygen concentration moves the reaction temperature window toward the low temperature. The O2 concentration of the decomposition furnace should be controlled at 1.5-2%. The oxygen concentration can be measured in real time in the flue gas channel by an oxygen analyzer. These data help to optimize the injection amount and timing of the reducing agent to balance the relationship between nitrogen oxide reduction and oxygen consumption. The first nitrogen oxide concentration refers to the concentration of nitrogen oxides in the flue gas before entering the SNCR reaction zone. This is the basic data for evaluating the denitrification effect and an important basis for adjusting the amount of reducing agent injection. The first nitrogen oxide concentration can be measured by installing a nitrogen oxide analyzer in the flue gas channel upstream of the reaction zone. These data, combined with the nitrogen oxide concentration after the reaction, can calculate the denitrification efficiency of the SNCR technology.

[0031] S120, predicting a second nitrogen oxide concentration at a preset time in the future according to the production condition data using a preset prediction model; The selection of prediction models depends on the characteristics of the data and the accuracy of the prediction requirements. Common prediction models include machine learning models (such as random forests, extreme gradient boosting trees, neural networks, etc.), statistical models (such as time series analysis, regression analysis, etc.) and hybrid models. These models can capture complex relationships in the data and make predictions based on them. The construction of the model needs to be based on a large amount of historical data and prior knowledge. In the SNCR system, these data include production condition data such as reaction temperature, flue gas flow, oxygen concentration, and first nitrogen oxide concentration. By training these data, the model can learn the mapping relationship between nitrogen oxide concentration and production conditions and make predictions based on this. Input the production condition data at the current moment or in the recent period into the preset prediction model. These data should include all factors that affect the nitrogen oxide concentration to ensure the accuracy and reliability of the prediction. The prediction model uses internal algorithms and parameters to calculate based on the input production condition data. This process may involve steps such as data preprocessing (such as data cleaning, feature selection, etc.), model reasoning (such as using a trained model for prediction), and post-processing (such as result verification, outlier processing, etc.). After the model calculation, the second nitrogen oxide concentration prediction value at a preset time in the future is output. This prediction value reflects the possible situation of nitrogen oxide concentration at a certain time in the future under given production conditions. Alternatively, the second nitrogen oxide concentration is determined by directly fitting the historical data.

[0032] Optionally, the using a preset prediction model to predict the second nitrogen oxide concentration at a preset time in the future according to the production condition data includes: Acquire historical production condition data, and extract correlation features of nitrogen oxide concentration from the historical production condition data, wherein the correlation features include an average value, a change rate, and a ratio of flue gas flow rate to oxygen concentration within a temperature window; Associating the associated features with corresponding nitrogen oxide concentration data to form a data set, and training and validating an initial model through the data set to obtain a preset prediction model; The production condition data is input into the preset prediction model to obtain a second nitrogen oxide concentration at a preset time in the future.

[0033] Collect and organize the production condition data of the SNCR system in the past period of time. The production condition data include key parameters such as reaction temperature, flue gas flow rate, oxygen concentration, etc., which have an important impact on the change of nitrogen oxide concentration. In order to build an effective prediction model, it is necessary to extract features closely related to nitrogen oxide concentration from the historical production condition data. The associated features include the average value, change rate, and ratio of flue gas flow rate to oxygen concentration within the temperature window. The average value within the temperature window: reflects the stability and change trend of the reaction temperature over a period of time, which is crucial for evaluating the efficiency of the SNCR reaction. Change rate: may refer to the rate of change of temperature, flue gas flow rate or oxygen concentration. These rates of change can capture the dynamic changes of the system state and have reference value for predicting future changes in nitrogen oxide concentration. The ratio of flue gas flow rate to oxygen concentration: This ratio may reflect the relationship between the oxygen content and the total volume in the flue gas. The extracted associated features are associated with the corresponding nitrogen oxide concentration data to form a data set for model training and verification. This data set contains rich information and can reveal the complex relationship between production conditions and nitrogen oxide concentration. The initial prediction model is trained and verified using the above data set. The training process aims to optimize the parameters and structure of the model so that the model can accurately learn the changing pattern of nitrogen oxide concentration from the production condition data. The verification process is used to evaluate the predictive performance of the model to ensure the reliability and accuracy of its prediction results on unknown data. After training and verification, a preset prediction model with good predictive performance is obtained. This model can receive the current production condition data as input and output the second nitrogen oxide concentration prediction value at a preset time in the future. In actual applications, the real-time or recent production condition data is input into the preset prediction model, and the model calculates the second nitrogen oxide concentration prediction value at a preset time in the future based on these data. This prediction value can provide an important reference for production control and help enterprises adjust process parameters in advance to optimize the denitrification effect.

[0034] By extracting the associated features of NOx concentration from historical production condition data (such as the average value, rate of change, and ratio of flue gas flow rate to oxygen concentration within the temperature window), these features can more comprehensively reflect the relationship between production conditions and NOx concentration. This refined feature extraction helps to improve the accuracy of the prediction model. Using a data set containing these associated features to train and verify the initial model can ensure that the model can learn the complex relationship between production conditions and NOx concentration. Through continuous iteration and optimization, the final preset prediction model will have higher prediction accuracy. The prediction model not only considers a single production condition parameter, but also comprehensively considers multiple associated features, such as temperature, flue gas flow rate, oxygen concentration and their mutual relationship. This multi-factor consideration approach enables the model to better adapt to the prediction of NOx concentration under different conditions, and improves the adaptability and generalization ability of the model. As new data is continuously added, the preset prediction model can be regularly updated and optimized to reflect the latest production conditions and NOx concentration change trends. This real-time update mechanism helps to maintain the accuracy and effectiveness of the model.

[0035] S130, using a preset control model to calculate control data according to the second nitrogen oxide concentration and the production condition data, the control data including ammonia water demand, compressed air demand and optimal ammonia injection position; The required amount of ammonia is calculated based on the parameters such as the second nitrogen oxide concentration, the utilization efficiency of ammonia, the target NOx emission concentration and the mass concentration of ammonia. The required amount of ammonia is calculated by mathematical calculation using the preset relationship model or algorithm. The amount of compressed air required for ammonia atomization is usually proportional to the ammonia demand, and is also affected by factors such as the performance of the atomizing nozzle and the pipeline resistance. The relationship between the amount of compressed air and the amount of ammonia is determined by experiments or empirical formulas, and then the required amount of compressed air is calculated. According to production operating data, flue gas flow characteristics and SNCR reaction mechanism. Analyze the flue gas temperature distribution and determine the temperature window of the SNCR reaction (usually 850-1100°C). Considering the flue gas flow velocity, turbulence intensity and mixing effect, select an area where the reductant and flue gas can be fully mixed and the residence time meets the reaction requirements. Combined with actual operating data (such as cyclone temperature, dust concentration, etc.), the optimal ammonia injection position is determined by simulation calculation or field test.

[0036] Optionally, the calculating control data by using a preset control model according to the second nitrogen oxide concentration and the production condition data includes: Calculating the mass flow rate of the second nitrogen oxide according to the flue gas flow rate and the second nitrogen oxide concentration in the production condition data; The required molar amount of ammonia is determined according to the mass flow rate of the second nitrogen oxide, and the required amount of ammonia water is determined according to the concentration of ammonia water, the molar amount of ammonia gas and the injection efficiency.

[0037] Get the current flue gas flow rate (usually expressed as volume flow rate, such as cubic meters per hour) and the second nitrogen oxide concentration (usually expressed as volume fraction or ppm) from the monitoring system. Make sure all parameters use the same unit system, such as the International System of Units (SI). Use the formula to convert the volume concentration of the second nitrogen oxide to mass flow rate. This usually involves multiplying the volume concentration by the flue gas flow rate and taking into account the density of nitrogen oxides (which may be adjusted with temperature and pressure changes) or using approximate values ​​for calculation. However, when directly calculating the mass flow rate of nitrogen oxides, it is more common to assume that the flue gas is mainly nitrogen and oxygen, and convert based on the average molecular weight of these gases. The specific formula may vary depending on the actual application, but the basic principle is to convert the volume flow rate to mass flow rate. Formula example: The second nitrogen oxide mass flow rate = flue gas flow rate × the second nitrogen oxide volume concentration × the nitrogen oxide molecular weight / flue gas average molecular weight.

[0038] The formula here is simplified. In practical applications, more factors may need to be considered, such as the specific proportion of flue gas components, temperature, pressure, etc.

[0039] Based on the calculated mass flow rate of the second nitrogen oxide, the molar amount of ammonia required to completely reduce these nitrogen oxides is calculated according to the molar ratio of nitrogen oxides to ammonia in the chemical equation (usually determined according to the SNCR reaction principle). The concentration of ammonia water refers to the mass fraction or mole fraction of ammonia in the ammonia solution. The injection efficiency indicates the degree of effective utilization of ammonia water during the injection process, that is, the ratio of the amount of ammonia actually participating in the reaction to the total amount of ammonia injected. Calculate the amount of ammonia water required: Combine the molar amount of ammonia, the concentration of ammonia water and the injection efficiency, and calculate the required volume or mass of ammonia water through mathematical operations. Formula example: Ammonia demand = required ammonia molar amount / (ammonia concentration × injection efficiency × molar mass of ammonia).

[0040] The term "molar mass of ammonia" here refers to the molar mass of ammonia gas (NH3) and is used to convert molar quantities to mass or volume (depending on how the ammonia concentration is expressed).

[0041] By directly calculating the mass flow rate of the second nitrogen oxide based on the flue gas flow rate and the second nitrogen oxide concentration, this step ensures the accuracy of the input data and provides a solid foundation for subsequent calculations. The required molar amount of ammonia is determined based on the mass flow rate of nitrogen oxides, and the ammonia demand is further calculated based on the concentration of ammonia water, the molar amount of ammonia gas and the injection efficiency. This process fully considers the stoichiometric relationship of the chemical reaction and the efficiency loss in the actual injection process, thereby improving the accuracy of the control data. By accurately calculating the ammonia demand, ammonia escape and waste caused by excessive injection can be avoided, and potential pollution to the environment can be reduced. Under the premise of ensuring the denitrification effect, reasonable control of the use of ammonia water can help reduce production costs and improve economic benefits. According to the real-time monitoring of the second nitrogen oxide concentration and production condition data, the control model can quickly calculate the required ammonia demand and adjust the injection amount accordingly, thereby realizing real-time control of nitrogen oxide emissions. According to the characteristics of nitrogen oxide emissions under different working conditions, the control model can flexibly adjust the control strategy, improve the adaptability and pertinence of the denitrification system, and ensure that good denitrification effects can be achieved under various working conditions.

[0042] Optionally, the calculating control data using a preset control model according to the second nitrogen oxide concentration and the production condition data further includes: The proportionality coefficient is obtained by experimentally measuring the compressed air flow rate corresponding to different ammonia water injection amounts, and the compressed air demand is determined according to the proportionality coefficient and the ammonia water demand.

[0043] In a laboratory or actual production environment, a series of experiments are conducted to measure the corresponding compressed air flow rate under different ammonia injection amounts. These experiments are aimed at finding the relationship between the ammonia injection amount and the compressed air flow rate. During the experiment, other conditions (such as nozzle type, pipeline resistance, gas pressure, etc.) need to be kept relatively stable in order to accurately measure the corresponding relationship between the two. By analyzing the experimental data, one or more proportional coefficients can be obtained, which reflect the proportional relationship between the ammonia injection amount and the compressed air flow rate. The specific value of the proportional coefficient depends on many factors such as experimental conditions, equipment performance, and actual working conditions. In actual applications, after the ammonia demand is calculated by the preset control model, these proportional coefficients can be used to calculate the corresponding compressed air demand. This step is a mathematical calculation based on experimental data, which aims to ensure that the ammonia can be fully atomized during the injection process.

[0044] Sufficient compressed air flow is the key to ensure good ammonia atomization. By accurately calculating the compressed air demand, it can be ensured that the ammonia forms fine droplets during the injection process, thereby increasing the contact area with the flue gas and improving the denitrification efficiency. Excessive compressed air will increase energy consumption and costs, while too little compressed air will affect the atomization effect. By accurately calculating the compressed air demand, unnecessary waste can be avoided and production costs can be reduced. Accurate calculation of compressed air demand helps to maintain stable operation of the system. When production conditions change, the system can adjust the compressed air flow in time according to the new ammonia demand to keep the atomization effect unchanged. Different production conditions and equipment conditions may require different compressed air flow rates. Through experimental measurement and the application of proportional coefficients, this method can adapt to different production environments and equipment requirements, and has strong flexibility and adaptability.

[0045] Optionally, the calculating control data using a preset control model according to the second nitrogen oxide concentration and the production condition data further includes: In the numerical simulation software, establish the geometric model, boundary conditions and initial conditions of the furnace or flue; Start numerical simulation to calculate the flow characteristics of flue gas in the furnace or flue, including temperature distribution and velocity distribution, and identify the target area where the flue gas mixing degree, velocity and temperature meet the preset conditions; A reaction temperature window of the selective non-catalytic reduction reaction is determined according to the type of ammonia water and the second nitrogen oxide concentration, and an ammonia water injection position is selected in the target area within the reaction temperature window in combination with the flow characteristics.

[0046] In the numerical simulation software, a geometric model of the furnace or flue is established. This model should reflect the shape, size and internal structure of the actual furnace or flue as accurately as possible, so that the subsequent flow simulation can be close to the actual situation. Boundary conditions include parameters such as flue gas temperature, pressure, velocity, composition, etc. at the inlet and outlet of the furnace or flue; initial conditions refer to the state inside the furnace or flue at the beginning of the simulation, such as temperature distribution, velocity field, etc. The setting of these conditions is crucial to the accuracy of the simulation results. After the model is established and the boundary conditions and initial conditions are set, the numerical simulation program is started for calculation. During the simulation, the software will gradually calculate the flow characteristics of the flue gas in the furnace or flue according to the set physical model and algorithm. The flow characteristics mainly include temperature distribution, flow velocity distribution, etc. These characteristics reflect the movement state of the flue gas in the furnace or flue, which is crucial for the subsequent determination of the ammonia injection position. At the same time, the simulation will also identify the target areas where the flue gas mixing degree, flow velocity and temperature meet the preset conditions. These areas are ideal locations for SNCR reactions. According to the type of ammonia and the concentration of the second nitrogen oxide, the optimal temperature range (i.e., reaction temperature window) of the SNCR reaction can be determined. This window is one of the key conditions for the effective reaction between ammonia and nitrogen oxides. Within the reaction temperature window, the optimal ammonia injection position is selected in the target area in combination with the flow characteristics obtained by numerical simulation (such as temperature distribution, flow velocity distribution, mixing degree, etc.). This position should ensure that ammonia can quickly mix with flue gas and react at a suitable temperature, thereby improving denitrification efficiency and reducing ammonia escape.

[0047] By determining the ammonia injection position through numerical simulation, it can be ensured that ammonia is mixed and reacted with flue gas under optimal conditions, thereby improving the denitrification efficiency. Reasonable injection position can reduce the excessive use of ammonia, reduce the risk of ammonia escape, and avoid secondary pollution to the environment. By accurately controlling the amount of ammonia used and the injection position, the operating cost of the denitrification system can be optimized and the economic benefits can be improved. The numerical simulation method can be adjusted and optimized according to different furnace or flue structures and operating conditions, and has strong adaptability and flexibility.

[0048] Optionally, the calculating control data by using a preset control model according to the second nitrogen oxide concentration and the production condition data includes: A preset number of control strategies are randomly generated as an initial population, and a fitness function is determined according to an objective function, wherein the control strategy includes encoding control variables, and the control variables include spray gun flow, pressure, and position; and the objective function is a weighted sum of nitrogen oxide emissions and ammonia consumption; The fitness of each control strategy is calculated by the fitness function, a target control strategy is selected by a selection operation to perform a crossover operation to obtain a sub-control strategy, the sub-control strategy is randomly mutated, and the number of iterations is increased by one; Repeat the previous step until the maximum number of iterations is reached or the target control strategy remains unchanged, and output the control data according to the final target control strategy.

[0049] A certain number of control strategies are randomly generated as the initial population. Each control strategy represents a possible solution, which contains the coding form of control variables such as spray gun flow, pressure, and position. These control variables are the key factors that directly affect nitrogen oxide emissions and ammonia consumption. The objective function is set as the weighted sum of nitrogen oxide emissions and ammonia consumption. This setting reflects the core goal of the optimization problem, that is, while ensuring that nitrogen oxide emissions are as low as possible, ammonia consumption must also be controlled to achieve a balance between economic and environmental benefits. According to the objective function, a fitness function is defined to evaluate the pros and cons of each control strategy. The fitness function usually transforms the objective function in some way (such as negating it) so that the control strategy with a higher fitness value is closer to the optimal solution. After calculating the fitness of each control strategy through the fitness function, a selection operation is performed. The selection operation simulates the process of natural selection, that is, a control strategy with a high fitness is more likely to be selected for subsequent genetic operations. The selected control strategy (called the parent generation) undergoes a crossover operation (also called hybridization or genetic recombination) to produce a new control strategy (called the offspring). Specifically, for strategies such as single-point crossover and double-point crossover, one or more crossover points need to be randomly selected on the encoding string of the parent individual. These crossover points divide the parent individual into two parts, and the crossover operation will be performed between these two parts. The crossover operation is the main way to generate new solutions in genetic algorithms, which helps to explore different areas of the solution space. The offspring control strategy is randomly mutated, that is, the values ​​of some of its control variables are changed with a certain probability. The mutation operation increases the diversity of the population and helps to avoid the algorithm from falling into a local optimal solution. The number of iterations is increased by one, and the above selection, crossover and mutation operations are repeated until the preset maximum number of iterations is reached or the target control strategy (i.e., the control strategy with the highest fitness) remains unchanged in multiple consecutive iterations. This indicates that the algorithm has converged to or is close to the optimal solution. According to the target control strategy obtained in the final iteration, the specific control data such as the flow rate, pressure, and position of the spray gun are decoded. These data will be used in the actual production process to guide the operation of the spray gun, so as to optimize the nitrogen oxide emissions and ammonia consumption.

[0050] Through the optimization process of genetic algorithms, the optimal or near-optimal control strategy can be automatically searched, thereby ensuring that nitrogen oxide emissions meet standards while reducing ammonia consumption. Genetic algorithms do not depend on the specific form of the problem and can handle complex, nonlinear optimization problems, so they have strong adaptability. Because genetic algorithms use mechanisms such as population search and random mutation, they have good global search capabilities and robustness, and can avoid falling into local optimal solutions to a certain extent.

[0051] S140, controlling the flow rate and position of the spray gun at each point according to the control data.

[0052] Parse the calculated control data. The control data usually includes the optimal flow value for each spray gun point, the optimal spray position (which may be the distance or angle relative to a reference point), and possibly other related parameters (such as spray angle, spray time, etc.). Depending on the specific configuration of the spray gun system, ensure that each spray gun can independently receive and respond to control signals. This may involve programming the spray gun controller so that it can recognize and apply the control data from the optimization algorithm. Flow control is usually achieved by adjusting the flow control valve on the spray gun. Based on the flow value in the control data, the spray gun controller sends a corresponding signal to the flow control valve to adjust the flow of ammonia or other reducing agent through the spray gun. This process requires precise control to ensure that each spray gun can spray at the preset flow rate. Position control may involve a robotic arm, a sliding track, or other type of positioning mechanism. Based on the position information in the control data, the spray gun system needs to be able to accurately adjust the position of the spray gun in the furnace or flue. This usually requires the spray gun system to have high-precision positioning and movement capabilities to ensure that the spray gun can accurately point to the predetermined spray point. In actual operation, it may be necessary to fine-tune the control parameters of the spray gun according to real-time operating data (such as flue gas temperature, flow rate, NOx concentration, etc.). This can be achieved through sensors integrated in the spray gun system, which can monitor relevant parameters in real time and feed the data back to the control system. The control system can adjust the flow, position or other parameters of the spray gun based on these data to achieve more precise control. Throughout the control process, the safe and stable operation of the spray gun system must be ensured. This includes preventing the spray gun from overheating, preventing ammonia leakage, and ensuring the stability of the spray gun during movement. To this end, the spray gun system needs to be equipped with corresponding safety protection devices and fault monitoring mechanisms. Finally, the operating data of the spray gun system needs to be recorded and analyzed. This helps to evaluate the effectiveness of the control strategy and provide data support for future optimization. Through continuous data collection and analysis, the control strategy can be continuously improved, the denitrification efficiency can be improved, and the operating cost can be reduced.

[0053] Optionally, controlling the flow rate and position of the spray gun at each point according to the control data includes: A spray gun number in the control data and target spray data corresponding to the spray gun number are acquired from the control data, the target spray data is transmitted to a corresponding target spray gun according to the spray gun number, and the target spray data is executed by the target spray gun.

[0054] The system needs to obtain control data from some form of data source (such as a database, file, real-time data stream, etc.). These control data contain specific instructions on how to operate each spray gun and are the basis for subsequent control operations. After obtaining the control data, the system will parse the data and identify the number (or identifier) ​​of each spray gun and the corresponding target spray data. The target spray data is the key information to guide how the spray gun works. It may include multiple parameters, but in this scenario, the main focus is on the amount of ammonia sprayed and the spray pressure. According to the spray gun number, the system accurately transmits the corresponding target spray data to the corresponding target spray gun. This step usually relies on a reliable communication network that can ensure that the data is accurately transmitted from the control system to each spray gun. After receiving the target spray data, the spray gun will perform the spray operation according to this data. This includes adjusting the amount of ammonia sprayed and the spray pressure to ensure that the spraying is carried out according to the preset specifications and requirements. In some advanced systems, the spray gun may also be fine-tuned based on real-time feedback (such as sensor data) to further improve the accuracy and efficiency of the spraying. Position control of the spray gun is also very important, which usually involves the precise positioning and movement of the spray gun in space to ensure that the spray pattern, thickness or coverage meets the design requirements. Position control may be achieved by a robotic arm, rail system or other automated mechanical device that moves the spray gun according to a preset path or real-time instructions.

[0055] By obtaining the gun number and the corresponding target injection data (such as ammonia volume and pressure) from the control data, the system can ensure that each gun receives its own injection instruction. This one-to-one matching method significantly improves the accuracy of gun control. The system can receive and process control data in real time, and then adjust the injection parameters of the gun (such as ammonia volume and pressure). This real-time adjustment capability enables the system to quickly respond to changes in operating conditions such as production load and flue gas composition, and optimize the denitrification effect. By accurately controlling the injection amount of ammonia, the system can avoid excessive or insufficient ammonia, thereby improving the utilization efficiency of ammonia and reducing waste. Accurately controlling the injection parameters of the gun helps to achieve full reaction of the reducing agent at the optimal window temperature, thereby improving the removal rate of NOx. By optimizing parameters such as injection angle and atomization effect, the system can reduce the situation where ammonia escapes directly without reacting with NOx, reducing secondary pollution to the environment. Accurately controlling the injection parameters of the gun helps to reduce the overall energy consumption and material consumption (such as ammonia) of the system, thereby reducing operating costs.

[0056] Figure 2 is a process flow diagram of a control method for selective non-catalytic reduction of nitrogen oxides disclosed in an embodiment of the present application, such as Figure 2As shown, the upper left end of the valve group is an ammonia water source (the specific line is not shown). The ammonia water of the denitration valve group is replenished in real time through the ammonia water pump and the ammonia tank storing the ammonia water reducing agent provided by the factory, so as to meet the ammonia water pressure requirement of the main pipeline inlet of the valve group. The lower left end of the valve group is a compressed air source (the specific line is not shown). The compressed air is provided by the air compressor of the factory, and finally connected to the compressed air main pipeline of the valve group after entering the air storage tank and the filter, so as to meet the compressed air pressure requirement of the valve group. The rightmost side of the valve group is a denitration spray gun. Each spray gun is connected to an ammonia water pipe and a compressed air hose of the corresponding branch hard pipeline. The connection is equipped with a valve and an ammonia water filter. The 4500t / d production line is equipped with 8 spray guns, and each two spray guns use independent intelligent regulating valves and flow rates for reducing agent control. Precise control of independent partitions can be achieved.

[0057] Figure 3 is a schematic diagram of the communication topology of the selective non-catalytic reduction control platform disclosed in the embodiment of the present application, such as Figure 3 As shown, the denitration valve group of this project is in frame 301. The denitration valve group control cabinet leads an ammonia pressure signal to the ammonia zone system, and the ammonia zone uses the pressure signal to stabilize the ammonia pressure demand of the valve group inlet. The factory DCS transmits the field working condition data and chimney environmental emission data required by the denitration system to the gateway module and valve group PLC in the valve group through Profibus DP communication, and then transmits the data to the server of the denitration system through the gateway module through Modbus transmission through optical fiber. In addition, the data of the denitration valve group PLC is also transmitted to the server of the denitration system through optical fiber. The denitration control software in the denitration server realizes the functions of controlling each actuator of the denitration valve group, monitoring environmental data, and monitoring hardware equipment through the read data, and finally realizes the control of nitrogen oxide emissions and reasonable adjustment of ammonia consumption by controlling the spraying of ammonia of each spray gun. The mini computer ThinkClient is connected to the denitration server through a network cable as a function of displaying the human-computer interaction control interface.

[0058] The SNCR system of the embodiment of the present application uses a neural network tool to predict the NOx generation concentration by more extensively monitoring data of the production process and real-time tracking of changes in production conditions, and can usually achieve a prediction of 3 minutes in advance; the relatively flat spray gun arrangement of the traditional SNCR denitrification technology is changed, and the spray guns are arranged in a wider temperature window range. A hierarchical installation of independently controllable spray gun groups is adopted to track the working conditions in real time, and timely adjust and control the injection position and injection amount of ammonia water respectively, so as to achieve the purpose of improving denitrification efficiency, reducing ammonia water consumption, and reducing ammonia escape; through the extensive data information collected, input parameters are formed, and through the control strategy, the priority of the control scheme under the working condition is found, and the spray guns at each point, the flow rate and pressure of each spray gun, and the flow rate and pressure of compressed air are flexibly allocated to achieve precise ammonia injection; the traditional SNCR denitrification working condition changes often require manual control optimization. The SNCR system of the embodiment of the present application actively optimizes the reducing agent to find the best distribution ratio, continuously self-optimizes the injection priority, and the longer the system is put into use, the more stable the system operation.

[0059] This embodiment also discloses a control system for selective non-catalytic reduction of nitrogen oxides. Figure 4 is a schematic diagram of a module of a control system for selective non-catalytic reduction of nitrogen oxides disclosed in an embodiment of the present application, such as Figure 4 As shown, the system includes a collection module 401, a prediction module 402, a calculation module 403 and a control module 404, wherein: The acquisition module 401 is configured to collect production condition data, wherein the production condition data includes reaction temperature, flue gas flow rate, oxygen concentration and first nitrogen oxide concentration; A prediction module 402, configured to predict a second nitrogen oxide concentration at a preset time in the future according to the production condition data using a preset prediction model; A calculation module 403 is configured to calculate control data using a preset control model according to the second nitrogen oxide concentration and the production condition data, wherein the control data includes ammonia water demand, compressed air demand and an optimal ammonia injection position; The control module 404 is configured to control the flow rate and position of the spray gun at each point according to the control data.

[0060] Optionally, the prediction module 402 is configured to: Acquire historical production condition data, and extract correlation features of nitrogen oxide concentration from the historical production condition data, wherein the correlation features include an average value, a change rate, and a ratio of flue gas flow rate to oxygen concentration within a temperature window; Associating the associated features with corresponding nitrogen oxide concentration data to form a data set, and training and validating an initial model through the data set to obtain a preset prediction model; The production condition data is input into the preset prediction model to obtain a second nitrogen oxide concentration at a preset time in the future.

[0061] Optionally, the calculation module 403 is configured to: Calculating the mass flow rate of the second nitrogen oxide according to the flue gas flow rate and the second nitrogen oxide concentration in the production condition data; The required molar amount of ammonia is determined according to the mass flow rate of the second nitrogen oxide, and the required amount of ammonia water is determined according to the concentration of ammonia water, the molar amount of ammonia gas and the injection efficiency.

[0062] Optionally, the calculation module 403 is further configured to: The proportionality coefficient is obtained by experimentally measuring the compressed air flow rate corresponding to different ammonia water injection amounts, and the compressed air demand is determined according to the proportionality coefficient and the ammonia water demand.

[0063] Optionally, the calculation module 403 is further configured to: In the numerical simulation software, establish the geometric model, boundary conditions and initial conditions of the furnace or flue; Start numerical simulation to calculate the flow characteristics of flue gas in the furnace or flue, including temperature distribution and velocity distribution, and identify the target area where the flue gas mixing degree, velocity and temperature meet the preset conditions; A reaction temperature window of the selective non-catalytic reduction reaction is determined according to the type of ammonia water and the second nitrogen oxide concentration, and an ammonia water injection position is selected in the target area within the reaction temperature window in combination with the flow characteristics.

[0064] Optionally, the calculation module 403 is configured to: A preset number of control strategies are randomly generated as an initial population, and a fitness function is determined according to an objective function, wherein the control strategy includes encoding control variables, and the control variables include spray gun flow, pressure, and position; and the objective function is a weighted sum of nitrogen oxide emissions and ammonia consumption; The fitness of each control strategy is calculated by the fitness function, a target control strategy is selected by a selection operation to perform a crossover operation to obtain a sub-control strategy, the sub-control strategy is randomly mutated, and the number of iterations is increased by one; Repeat the previous step until the maximum number of iterations is reached or the target control strategy remains unchanged, and output the control data according to the final target control strategy.

[0065] Optionally, the control module 404 is configured to: A spray gun number in the control data and target spray data corresponding to the spray gun number are acquired from the control data, the target spray data is transmitted to a corresponding target spray gun according to the spray gun number, and the target spray data is executed by the target spray gun.

[0066] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0067] This embodiment also discloses an electronic device, referring to Figure 5 The electronic device may include: at least one processor 501 , at least one communication bus 502 , a user interface 503 , a network interface 504 , and at least one memory 505 .

[0068] The communication bus 502 is used to realize the connection and communication between these components.

[0069] The user interface 503 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 503 may also include a standard wired interface and a wireless interface.

[0070] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0071] Among them, the processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 501 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501, and it can be implemented separately through a chip.

[0072] Among them, the memory 505 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 505 may also be optionally at least one storage device located away from the aforementioned processor 501. As Figure 5 As shown, the memory 505 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of the control method for selective non-catalytic reduction of nitrogen oxides.

[0073] exist Figure 5In the electronic device shown, the user interface 503 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 501 can be used to call the application program of the control method for selective non-catalytic reduction of nitrogen oxides stored in the memory 505. When executed by one or more processors 501, the electronic device executes one or more methods in the above-mentioned embodiments.

[0074] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0075] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0077] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0079] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory 505, including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory 505 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0080] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A control method for selective non-catalytic reduction of nitrogen oxides, characterized in that: Applied to a selective non-catalytic reduction control platform, the method comprises: Collecting production condition data, wherein the production condition data includes reaction temperature, flue gas flow rate, oxygen concentration and first nitrogen oxide concentration; Predicting a second nitrogen oxide concentration at a preset time in the future according to the production condition data using a preset prediction model; Calculating control data using a preset control model according to the second nitrogen oxide concentration and the production condition data, the control data including ammonia water demand, compressed air demand and an optimal ammonia injection position; The flow rate and position of the spray gun at each point are controlled according to the control data.

2. The control method for selective non-catalytic reduction of nitrogen oxides according to claim 1, characterized in that: The method of using a preset prediction model to predict a second nitrogen oxide concentration at a preset time in the future according to the production condition data includes: Acquire historical production condition data, and extract correlation features of nitrogen oxide concentration from the historical production condition data, wherein the correlation features include an average value, a change rate, and a ratio of flue gas flow rate to oxygen concentration within a temperature window; Associating the associated features with corresponding nitrogen oxide concentration data to form a data set, and training and validating an initial model through the data set to obtain a preset prediction model; The production condition data is input into the preset prediction model to obtain a second nitrogen oxide concentration at a preset time in the future.

3. The control method for selective non-catalytic reduction of nitrogen oxides according to claim 1, characterized in that: The calculating control data by using a preset control model according to the second nitrogen oxide concentration and the production condition data comprises: Calculating the mass flow rate of the second nitrogen oxide according to the flue gas flow rate and the second nitrogen oxide concentration in the production condition data; The required molar amount of ammonia is determined according to the mass flow rate of the second nitrogen oxide, and the required amount of ammonia water is determined according to the concentration of ammonia water, the molar amount of ammonia gas and the injection efficiency.

4. The control method for selective non-catalytic reduction of nitrogen oxides according to claim 3, characterized in that: The calculating control data by using a preset control model according to the second nitrogen oxide concentration and the production condition data further includes: The proportionality coefficient is obtained by experimentally measuring the compressed air flow rate corresponding to different ammonia water injection amounts, and the compressed air demand is determined according to the proportionality coefficient and the ammonia water demand.

5. The control method for selective non-catalytic reduction of nitrogen oxides according to claim 4, characterized in that: The calculating control data by using a preset control model according to the second nitrogen oxide concentration and the production condition data further includes: In the numerical simulation software, establish the geometric model, boundary conditions and initial conditions of the furnace or flue; Start numerical simulation to calculate the flow characteristics of flue gas in the furnace or flue, including temperature distribution and velocity distribution, and identify the target area where the flue gas mixing degree, velocity and temperature meet the preset conditions; A reaction temperature window of the selective non-catalytic reduction reaction is determined according to the type of ammonia water and the second nitrogen oxide concentration, and an ammonia water injection position is selected in the target area within the reaction temperature window in combination with the flow characteristics.

6. The control method for selective non-catalytic reduction of nitrogen oxides according to claim 1, characterized in that: The calculating control data by using a preset control model according to the second nitrogen oxide concentration and the production condition data comprises: A preset number of control strategies are randomly generated as an initial population, and a fitness function is determined according to an objective function, wherein the control strategy includes encoding control variables, and the control variables include spray gun flow, pressure, and position; and the objective function is a weighted sum of nitrogen oxide emissions and ammonia consumption; The fitness of each control strategy is calculated by the fitness function, a target control strategy is selected by a selection operation to perform a crossover operation to obtain a sub-control strategy, the sub-control strategy is randomly mutated, and the number of iterations is increased by one; Repeat the previous step until the maximum number of iterations is reached or the target control strategy remains unchanged, and output the control data according to the final target control strategy.

7. The control method for selective non-catalytic reduction of nitrogen oxides according to claim 6, characterized in that: The control of the flow rate and position of the spray gun at each point according to the control data includes: A spray gun number in the control data and target spray data corresponding to the spray gun number are acquired from the control data, the target spray data is transmitted to a corresponding target spray gun according to the spray gun number, and the target spray data is executed by the target spray gun.

8. A control system for selective non-catalytic reduction of nitrogen oxides, characterized in that: It includes acquisition module, prediction module, calculation module and control module, among which: A collection module configured to collect production condition data, wherein the production condition data includes reaction temperature, flue gas flow, oxygen concentration and first nitrogen oxide concentration; A prediction module, configured to predict a second nitrogen oxide concentration at a preset time in the future according to the production condition data using a preset prediction model; a calculation module configured to calculate control data using a preset control model according to the second nitrogen oxide concentration and the production condition data, the control data including ammonia water demand, compressed air demand and an optimal ammonia injection position; The control module is configured to control the flow rate and position of the spray gun at each point according to the control data.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images