Method and system for regulating NOx concentration of flue gas at SCR inlet of coal-fired unit with green ammonia blending combustion

Abstract

The embodiment of the present application provides a kind of method and system for regulating and controlling NOx concentration of SCR inlet flue gas of coal-fired unit with green ammonia combustion, belong to clean emission technical field.The method comprises: based on the design information of coal-fired unit, the reaction mechanism model corresponding to the reaction of ammonia and coal combustion is constructed;Based on the reaction mechanism model, the optimization problem is constructed with the minimum proportion of NOx concentration of SCR inlet flue gas as the target, and the constraint function is added to the optimization problem to obtain the optimization model;Based on the optimization model and long short-term memory network, the influence degree of each operating parameter of coal-fired unit on NOx concentration of SCR inlet flue gas is analyzed to obtain the NOx concentration prediction model of coal-fired unit;Based on the real-time operating parameters of coal-fired unit and the NOx concentration prediction model, real-time optimization control of coal-fired unit is carried out to ensure that coal-fired unit maintains the lowest NOx concentration emission.The present application solves the problem of difficult ammonia flow control and large NOx concentration fluctuation in traditional method, thereby improving the environmental performance and operating efficiency of coal-fired unit.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of clean emission, in particular to a method for regulating NOx concentration of SCR inlet flue gas of a green ammonia blended coal-fired unit and a system for regulating NOx concentration of SCR inlet flue gas of a green ammonia blended coal-fired unit. BACKGROUND

[0002] With the increasing intensification of global climate change, the impact on the environment and society is becoming more and more significant, and countries have made carbon peak and carbon neutrality as important goals. In this context, the energy industry, especially the coal-fired power generation industry dominated by coal, is under great pressure and needs to reduce greenhouse gas emissions and improve energy efficiency through technological innovation and industrial transformation.

[0003] Although new energy technologies have made significant progress in recent years, due to the instability of natural conditions (such as solar and wind energy), China's power supply is still mainly based on thermal power generation, and coal is the main energy source. Therefore, how to reduce the impact on the environment on the basis of coal-fired power generation has become a problem that needs to be solved in the current energy industry. The boiler of a coal-fired power plant as a core device produces a large amount of nitrogen oxides (NOx) during the combustion process, which is one of the main air pollutants, causing serious threats to air quality and human health. The control of NOx emissions is not only closely related to environmental protection policies, but also has an important impact on the economy and thermal efficiency of coal-fired units.

[0004] Currently, blending green ammonia as a potential solution has attracted attention. Green ammonia is a carbon-free fuel produced by renewable energy, which can reduce carbon emissions and reduce the generation of NOx. However, existing solutions still face multiple challenges in practical application, especially in the combustion process, it is difficult to control the opening of the ammonia valve, and it is easy to appear the phenomenon of excessive escape or insufficient reaction of ammonia. In addition, the NOx concentration of the SCR inlet flue gas is difficult to accurately control, mainly due to the influence of multiple disturbance factors and system dynamic characteristics on the combustion system. The existing technology lacks effective means to deal with these complex factors, making it difficult to ensure NOx emission compliance while maintaining the stability and economy of the combustion system. Therefore, how to achieve real-time and accurate control of the NOx concentration of the SCR inlet under complex working conditions and effectively control the flow of ammonia has become a technical problem that needs to be solved. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a method and system for regulating NOx concentration of SCR inlet flue gas of a green ammonia blended coal-fired unit to at least solve the problem that it is difficult to achieve real-time and accurate control of the NOx concentration of the SCR inlet under complex working conditions.

[0006] In order to achieve the above object, the present application provides a method for regulating NOx concentration of SCR inlet flue gas of a coal-fired unit mixed with green ammonia, which is applied to the prediction and control of NOx concentration of SCR inlet flue gas of a coal-fired unit mixed with green ammonia, and comprises the following steps: constructing a reaction mechanism model of ammonia and coal combustion reaction based on design information of the coal-fired unit; constructing an optimization problem with the minimum proportion of NOx concentration of SCR inlet flue gas as the target based on the reaction mechanism model, and adding a constraint function to the optimization problem to obtain an optimization model; analyzing the influence degree of each operating parameter of the coal-fired unit on the NOx concentration of SCR inlet flue gas based on the optimization model and a long short-term memory network to obtain a NOx concentration prediction model of the coal-fired unit; and performing real-time optimization control of the coal-fired unit based on real-time operating parameters of the coal-fired unit and the NOx concentration prediction model to ensure that the coal-fired unit maintains the lowest NOx emission; wherein the real-time optimization control of the coal-fired unit at least includes opening size control of a green ammonia supply valve.

[0007] Optionally, the reaction mechanism model of ammonia and coal combustion reaction based on the design information of the coal-fired unit comprises: constructing a green ammonia production model based on the design information of the coal-fired unit; and constructing a reaction mechanism model of ammonia and coal combustion reaction in the furnace based on the green ammonia production model; wherein the green ammonia production model is constructed by a synthetic ammonia device, a renewable energy power generation device and a water electrolysis hydrogen production device.

[0008] Optionally, the reaction mechanism model of ammonia and coal combustion reaction is as follows:

[0009]

[0010] wherein, is the generation rate of NOx; is the generation rate constant of NOx; is the mass flow rate of coal; is the mass fraction of nitrogen in coal; is the mass fraction of unburned nitrogen; is the reduction rate of NOx; is the process efficiency value; is the mass flow rate of green ammonia; is the concentration of NOx.

[0011] Optionally, the optimization problem is expressed as:

[0012]

[0013] wherein, The NOx concentration of the SCR inlet flue gas accounts for the proportion; the constraint function includes any one or more of the following: energy balance constraint, total fuel blending green ammonia proportion constraint, boiler outlet ammonia escape amount constraint, boiler outlet flue gas oxygen content concentration constraint, unit output constraint and non-negative constraint.

[0014] Optionally, the influence degree of each operating parameter of the coal-fired unit on the NOx concentration of the SCR inlet flue gas is analyzed based on the optimization model and the long short-term memory network to obtain a NOx concentration prediction model of the coal-fired unit, including: constructing a long short-term memory network based on the optimization model, wherein the long short-term memory network includes memory cells, input gates, forget gates and output gates, and a linear regression layer at the end; based on the long short-term memory network, the influence degree of each parameter on the NOx concentration of the SCR inlet under different working conditions is simulated, and the parameters with an influence degree greater than a preset influence degree threshold are taken as key parameters; and a NOx concentration prediction model of the coal-fired unit is constructed based on the key parameters.

[0015] Optionally, the NOx concentration prediction model of the coal-fired unit is constructed based on the key parameters, including: based on the selected key parameters, an initial framework of the NOx concentration prediction model is constructed to clarify the input and output of the model; based on the existing historical data and the initial framework of the NOx concentration prediction model, the NOx concentration prediction model is trained to obtain an initial NOx concentration prediction model; and based on the unused data set, the prediction model is verified and tested, and the model that passes the verification is taken as the NOx concentration prediction model.

[0016] Optionally, real-time optimization control of the coal-fired unit is performed based on the real-time operating parameters of the coal-fired unit and the NOx concentration prediction model to ensure that the coal-fired unit maintains the lowest NOx concentration emission, including: collecting real-time operating parameters of the coal-fired unit, and taking the real-time operating parameters as input parameters of the NOx concentration prediction model, and outputting a predicted value of the NOx concentration of the SCR inlet based on the model; wherein, in the process of outputting the predicted value of the NOx concentration of the SCR inlet based on the model, a disturbance compensation based on an extended state observer is added; based on the predicted value of the NOx concentration of the SCR inlet, it is judged whether the predicted value is the minimum value of the NOx concentration under the corresponding working condition; if not, a current optimal control strategy is generated based on a generalized predictive control model; and an adjustment scheme of each execution component is generated based on the optimal control strategy as an optimization control scheme.

[0017] Optionally, the extended state observer is represented as:

[0018]

[0019] wherein, and is the derivative of the extended state variable of the extended state observer; and is a measurement gain parameter; is an observer bandwidth; is a state variable of the coal-fired unit; is a control gain coefficient; is an input parameter of the extended state observer; is an output parameter after additional disturbance compensation.

[0020] Optionally, the generalized predictive control model is:

[0021]

[0022] wherein, is a control increment such that the target function is minimized; is a predicted value of the NOx concentration; is an expected value of the NOx concentration; T is a matrix; is a weight of the control increment.

[0023] The second aspect of the present application provides a green ammonia blending coal-fired unit SCR inlet flue gas NOx concentration regulation system, which is applied to the prediction and control of the SCR inlet flue gas NOx concentration of the green ammonia blending coal-fired unit. The system comprises: an initial unit configured to construct a reaction mechanism model of ammonia and coal combustion reaction based on design information of the coal-fired unit; a model construction unit configured to construct an optimization problem based on the reaction mechanism model, with the minimum SCR inlet flue gas NOx concentration ratio as the target, and to obtain an optimization model by adding a constraint function to the optimization problem; a prediction unit configured to analyze the influence degree of each operating parameter of the coal-fired unit on the SCR inlet flue gas NOx concentration based on the optimization model and a long short-term memory network, and to obtain a NOx concentration prediction model of the coal-fired unit; and a control unit configured to perform real-time optimization control of the coal-fired unit based on real-time operating parameters of the coal-fired unit and the NOx concentration prediction model, so as to ensure that the coal-fired unit maintains the lowest NOx concentration emission.

[0024] In another aspect, the present application provides a computer readable storage medium having instructions stored thereon, which, when executed on a computer, cause the computer to perform the above-mentioned green ammonia blending coal-fired unit SCR inlet flue gas NOx concentration regulation method.

[0025] By the technical scheme, the application scheme constructs a reaction mechanism model of ammonia and coal combustion reaction, accurately describes the generation mechanism of nitrogen oxides (NOx) in the combustion process, and establishes an optimization problem with the minimum SCR inlet flue gas NOx concentration as the target. By adding a constraint function, an optimization model is generated, which can identify key operating parameters under complex conditions. Then, the long short-term memory network (LSTM) is combined to analyze the operating parameters of the coal-fired unit, and the change of the SCR inlet NOx concentration under different operating conditions is predicted. Based on the prediction model, the system can optimize the real-time operating data of the coal-fired unit, especially adjust the opening of the green ammonia supply valve, to ensure that the NOx emission concentration always maintains at the lowest level. This technology can realize dynamic adjustment of the combustion process, solve the problems of difficult ammonia flow control and large NOx concentration fluctuation in the traditional method, and improve the environmental protection performance and operating efficiency of the coal-fired unit.

[0026] Other features and advantages of the present application will be described in detail in the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0027] The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:

[0028] Figure 1 is a step flow chart of the method for adjusting and controlling the SCR inlet flue gas NOx concentration of the coal-fired unit mixed with green ammonia provided by an embodiment of the application;

[0029] Figure 2 is a manufacturing flow chart of green ammonia provided by an embodiment of the application;

[0030] Figure 3 is a flow chart of the control and optimization design of the coal-fired unit provided by an embodiment of the application;

[0031] Figure 4 is a schematic diagram of the coal-fired unit outlet NOx model based on LSTM provided by an embodiment of the application;

[0032] Figure 5 is a schematic diagram of the SCR inlet flue gas NOx concentration optimization process provided by an embodiment of the application;

[0033] Figure 6 is a control structure block diagram provided by an embodiment of the application;

[0034] Figure 7 is a control effect comparison diagram of the IPC and TRD control strategy under different flue gas NOx concentration set values provided by an embodiment of the application;

[0035] Figure 8 is a comparative diagram of the NOx concentration of the SCR inlet flue gas under different load conditions provided by an embodiment of the present application;

[0036] Figure 9 is a system structure diagram of the NOx concentration regulation system of the SCR inlet flue gas of the green ammonia blending combustion coal-fired unit provided by an embodiment of the present application. DETAILED DESCRIPTION

[0037] The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application.

[0038] Figure 1 is a method flow chart of the NOx concentration regulation method of the green ammonia blending combustion coal-fired unit provided by an embodiment of the present application. As shown in Figure 1 , the embodiment of the present application provides a method, which comprises the following steps:

[0039] Step S10: constructing a reaction mechanism model corresponding to the ammonia and coal combustion reaction based on the coal-fired unit design information.

[0040] Specifically, a green ammonia production model is constructed based on the coal-fired unit design information; a reaction mechanism model corresponding to the ammonia and coal combustion reaction in the furnace is constructed based on the green ammonia production model; wherein the green ammonia production model is constructed by a synthetic ammonia device, a renewable energy power generation device and an electrolytic water hydrogen production device.

[0041] In the embodiment of the present application, as shown in Figure 2 , the green ammonia production adopts three major types of core process paths: traditional Haber-Bosch method, flexible process and new type of photocatalysis, plasma or electrochemical process. Among them, the Haber-Bosch method generates green hydrogen and nitrogen gas through thermal catalysis, high temperature and high pressure conditions of iron-based catalyst, and generates green ammonia by coupling renewable energy. The reaction conditions of this process are high pressure of 20~50MPa and high temperature of 350~500℃. The upper part of the device is a contact chamber containing iron-based catalyst, and the lower part is a heat exchanger. Hydrogen and nitrogen gas complete preheating, reaction and cooling in this system, and finally generate liquid ammonia. The unreacted hydrogen and ammonia are recycled into the synthesis tower for repeated use.

[0042] Further, on this basis, the green ammonia production model combines renewable energy power generation devices (such as wind or solar energy) and water electrolysis hydrogen production devices, and uses green electricity to drive the water electrolysis reaction to generate green hydrogen, ensuring that the carbon footprint in the ammonia production process is minimized. Through the cooperation of energy storage facilities, the stability of production is ensured, and the influence of new energy fluctuations on hydrogen generation and ammonia synthesis is avoided. The completed green ammonia production model is then used for the reaction mechanism modeling of the ammonia and coal combustion reaction in the furnace, and in-depth research is conducted on the combustion process of ammonia and coal and its reaction characteristics in a high-temperature environment. Through this model, the influence of ammonia and coal on the generation and reduction of NOx in the combustion process can be accurately analyzed, and further precise data support is provided for the control of NOx emissions of coal-fired units.

[0043] Based on the scheme of the present application, the scheme of the present application integrates the production process of green ammonia, which not only meets the demand for clean production of ammonia, but also provides low-carbon fuel for coal-fired units, effectively reducing the emission of greenhouse gases. At the same time, the efficient production and application of green ammonia can reduce the generation of NOx and achieve precise control of NOx emissions.

[0044] Further, in the furnace, the combustion reaction of ammonia and coal can be described by the following chemical reactions to produce and reduce NOx:

[0045]

[0046]

[0047]

[0048]

[0049]

[0050] The output in the furnace includes the heat energy generated by combustion, nitrogen in the flue gas, water vapor, unreacted ammonia, remaining NOx and other combustion products. In order to convert these chemical reactions into physical expressions, the following aspects are considered:

[0051] 1) The heat balance in the furnace can be described by the energy conservation equation:

[0052]

[0053] where, the heat input by fuel combustion, the heat lost through flue gas and furnace wall, the heat stored in water and steam.

[0054] Further, the mass flow rate is represented as:

[0055]

[0056] wherein, represents the mass flow rate, and the subscript represents different substances.

[0057] Based on this, the reaction mechanism model of the reaction of the ammonia gas with the coal combustion is:

[0058]

[0059] wherein, is the generation rate of the NOx; is the generation rate constant of the NOx; is the mass flow rate of the coal; is the mass fraction of the nitrogen in the coal; is the mass fraction of the unburned nitrogen; is the reduction rate of the NOx; is the process efficiency value; is the mass flow rate of the green ammonia; is the concentration of the NOx.

[0060] Step S20: Based on the reaction mechanism model, an optimization problem is constructed with the minimum SCR inlet flue gas NOx concentration ratio as the target, and a constraint function is added to the optimization problem to obtain an optimization model.

[0061] Specifically, the optimization problem is represented as:

[0062]

[0063] wherein, is the SCR inlet flue gas NOx concentration ratio; the constraint function includes any one or more of the following: an energy balance constraint, a total fuel blending green ammonia ratio constraint, a boiler outlet ammonia escape amount constraint, a boiler outlet flue gas oxygen content concentration constraint, a unit output constraint and a non-negative constraint.

[0064] In the embodiment of the present application, the minimum SCR inlet flue gas NOx concentration ratio is taken as the criterion. That is, the total fuel blending green ammonia ratio, the boiler outlet ammonia escape amount, the boiler outlet flue gas oxygen content concentration and the unit output are known, the various constraint conditions are satisfied, and the flue gas outlet NOx in the control period is minimized. Specifically, each constraint is represented as:

[0065] 1) Energy balance constraint:

[0066] ;

[0067] 2) Total fuel blending green ammonia ratio constraint:

[0068] ;

[0069] 3) Boiler outlet ammonia escape amount constraint:

[0070] ;

[0071] 4) Boiler outlet flue gas oxygen content concentration constraint

[0072] ;

[0073] 5) Unit output constraint:

[0074] ;

[0075] 6) Non-negative constraint:

[0076] The above variables are non-negative.

[0077] wherein, and are the coal ammonia combustion heat; and the coal combustion heat; is the green ammonia blending ratio; and are the boiler outlet ammonia escape amount and the maximum value allowed; , and are the mass of coal, air and ammonia respectively; is the boiler outlet flue gas oxygen content concentration; , and are the unit output and the allowed constraint value size range respectively.

[0078] SCR (flue gas denitration technology) inlet flue gas NOx content set value: boiler outlet flue gas amount = SCR inlet flue gas amount, expressed as:

[0079]

[0080] wherein, total SCR inlet flue gas amount.

[0081] Step S30: Based on the optimization model and the long short-term memory network, the influence degree of each operating parameter of the coal-fired unit on the SCR inlet flue gas NOx concentration is analyzed to obtain a NOx concentration prediction model of the coal-fired unit.

[0082] Specifically, a long short-term memory network is constructed based on the optimization model, wherein the long short-term memory network comprises a memory unit, an input gate, a forgetting gate, and an output gate, and a linear regression layer at the end; based on the long short-term memory network, simulation of the influence degree of each parameter on the SCR inlet NOx concentration under different working conditions is performed, and the parameter with an influence degree greater than a preset influence degree threshold is taken as a key parameter; and a NOx concentration prediction model of the coal-fired unit is constructed based on the key parameter.

[0083] In the embodiment of the application, the LSTM (Long Short-Term Memory Network) is a special RNN that learns long-term dependencies while avoiding the problem of gradient disappearance. In the neurons of the hidden layer of the RNN, a structure called memory cell (Memory Cell) is added to memorize past information, and three gate structures (input gate, forgetting gate, and output gate) are added to control the use of historical information.

[0084] Let the input sequence be , the hidden layer state be , and at time t, there are:

[0085]

[0086]

[0087]

[0088]

[0089]

[0090] wherein, represents a sigmoid activation function, represents a gate activation function (usually tanh), represents a Hadamard product (element-wise multiplication), and W and b represent weights and biases, respectively. represents a hidden state, represents an input, , , and represent an update gate, a forgetting gate, an output gate, and a cell state, respectively. In order to make the LSTM meet the prediction purpose, a linear regression layer needs to be added, that is:

[0091]

[0092] wherein, represents an output of the final prediction result; represents a threshold value of the linear regression layer.

[0093] In the application scenario of NOx concentration prediction, the long short-term memory network (LSTM) can effectively process the time series data of the operation parameters of the coal-fired unit, especially the problem of NOx concentration change in a complex dynamic system. By introducing the memory unit and the structures of the input gate, the forgetting gate and the output gate, the LSTM can avoid the problem of gradient disappearance while maintaining the memory of historical data.

[0094] In the application process, first, the operation parameters of the coal-fired unit are input, such as the combustion temperature of the boiler, the oxygen concentration, the fuel flow and the like. These parameters are input into the LSTM network as time series, and the input of each time step is combined with the hidden state of the previous time. The LSTM determines how much information of the current input is updated into the memory unit through the input gate, and controls whether the past information needs to be discarded through the forgetting gate. The memory unit can effectively process the long-term dependent input through the dynamic adjustment of these gates.

[0095] Next, the LSTM processes the hidden state of each time step according to the prediction task, and outputs the predicted value of the NOx concentration. The output gate plays a key role in this process, which determines how much of the hidden state of the current time step can affect the predicted value. In order to make the model more suitable for prediction requirements, a linear regression layer is added at the end of the LSTM network to map the processed hidden state to the predicted output of the NOx concentration.

[0096] Based on the application scheme of the present application, the application of LSTM in NOx concentration prediction can effectively predict the trend of the change of the NOx concentration at the inlet of the SCR by capturing the dynamic changes of various operation parameters in the coal-fired unit. Compared with the traditional linear model or simple time series model, the LSTM has stronger ability to learn complex time-dependent relationships, can process information over a long time span, and effectively avoids the gradient disappearance problem in the traditional recurrent neural network (RNN). In this way, the LSTM can accurately predict the NOx concentration, thereby providing an important decision basis for the optimization control of the coal-fired unit, helping to minimize the NOx emission and meet the environmental protection standard requirements.

[0097] Step S40: Based on the real-time operation parameters of the coal-fired unit and the NOx concentration prediction model, real-time optimization control of the coal-fired unit is performed to ensure that the coal-fired unit maintains the lowest NOx concentration emission.

[0098] Specifically, real-time operation parameters of the coal-fired unit are collected, and the real-time operation parameters are taken as input parameters of a NOx concentration prediction model, and a prediction value of NOx concentration at an SCR inlet is output based on the model; in the process of outputting the prediction value of NOx concentration at the SCR inlet based on the model, a disturbance compensation based on an extended state observer is added; whether the prediction value is a minimum value of NOx concentration under a corresponding working condition is determined based on the prediction value of NOx concentration at the SCR inlet; if not, a current optimal control strategy is generated based on a generalized predictive control model; and an adjustment scheme of each execution component is generated based on the optimal control strategy, as an optimal control scheme.

[0099] In the embodiment of the present application, as Figure 4 , first, real-time parameters of the coal-fired unit are collected, including a combustion temperature of a boiler, air and fuel flow, and the like. The parameters are taken as input to a NOx concentration prediction model, and the model predicts a NOx concentration at an SCR (selective catalytic reduction) inlet by combining historical data and real-time data.

[0100] In the prediction process, an extended state observer (ESO) is introduced to compensate for disturbances and dynamic changes not considered in the model. ESO monitors changes in external disturbances in real time and compensates for them, ensuring that the prediction result is more accurate and robust. At this time, the system will determine whether the prediction value of NOx concentration output by the model is the minimum value of NOx under the current working condition. If the prediction value is not the optimal value, a generalized predictive control (GPC) model is introduced to generate an optimal control strategy based on the current system state.

[0101] Further, the generalized predictive control predicts future working conditions by combining current state and historical data, and calculates an optimal control scheme that minimizes the NOx concentration. The control scheme generates a specific adjustment plan for the execution components, adjusts the combustion conditions in the boiler, such as fuel input, air volume, ammonia flow, and the like, thereby achieving minimization of NOx emissions.

[0102] Based on the scheme of the present application, as Figure 5 , by combining the NOx concentration prediction model, the extended state observer, and the generalized predictive control (GPC), real-time optimal control of the coal-fired unit under complex working conditions is achieved. First, the extended state observer effectively compensates for the influence of external disturbances on the prediction model, ensuring the accuracy and stability of the prediction. Second, the generalized predictive control generates an optimal control strategy based on the prediction result, ensuring that the NOx concentration is always at the lowest level under various working conditions. Through this real-time optimal control, not only can NOx emissions be effectively reduced to meet environmental protection requirements, but also the overall operation efficiency of the coal-fired unit can be optimized, and the economic efficiency and stability of the system can be improved.

[0103] In one possible implementation, the extended state observer strategy is as follows:

[0104] The first-order form reorganization of an uncertain system is expressed as:

[0105]

[0106] Where: g is unknown dynamic characteristics; b is a key gain, indicating the strength of the control quantity u on the controlled quantity y.

[0107] In modeling, b is difficult to obtain accurately, and the formula is as follows:

[0108]

[0109] Where: b0 is the approximation of b; Total disturbance, including unknown external disturbance and internal dynamic characteristics.

[0110] Let y=x1, f=x2, and the extended state space expression is:

[0111]

[0112] Its extended state observer (ESO) can be designed as:

[0113]

[0114] Where: ωo is the observer bandwidth, the larger the ωo, the closer the observed value of the system to the actual value, but too large will produce noise effect, and the setting should be considered comprehensively.

[0115] Further, the controlled autoregressive integral moving average (CARIMA) model of generalized predictive control (GPC) describes the controlled object as:

[0116]

[0117] Where, and are the control quantity and output of the system at time t, respectively; and represent the and polynomials of the backward shift operator , respectively, and is the first-order polynomial; is a white noise with zero mean and bounded variance; k is the minimum time delay of the system; is the difference operator.

[0118] According to the principle of GPC, based on Diophantine equation and the controlled object, the optimal prediction of the system output at t+k+i time in the future from the output at t time can be obtained as follows:

[0119]

[0120] The known quantity part in the optimal prediction is:

[0121]

[0122] wherein, and are the polynomials of Diophantine equation, and p is the prediction step length, for the range of 0 is the lth coefficient of the step response of the object, which can be written in the matrix form as and the actual output is , and E is the error vector, which is determined by and Diophantine equation.

[0123] The set value is softened according to the following formula:

[0124]

[0125] wherein, is the set value at t time, is the softened set value, is the softening factor, .

[0126] The optimal control strategy adopted by GPC is to minimize the following quadratic objective function:

[0127]

[0128] wherein, , is the control step length, , is the weight of the control increment.

[0129] ​Preferably, during the boiler combustion process, the emission of nitrogen oxides (NOx) not only has a significant impact on the environment, but also relates to the operational efficiency of the boiler. Therefore, in order to reduce the emission of NOx and improve the combustion efficiency, a comprehensive intelligent control and optimization system is introduced. The core of the system is an optimization model based on the long short-term memory network (LSTM), which can effectively process complex time series data during the operation of the boiler. The LSTM network accurately predicts the amount of NOx emission under different working conditions by memorizing and analyzing the trend of historical operating parameters. Its unique input gate, forget gate and output gate structure enables LSTM to handle long-term dependencies and avoid gradient disappearance, thereby accurately predicting NOx emissions. Through the LSTM model, the system can identify and establish a mathematical model of the boiler combustion process, accurately simulating the influence of boiler operating parameters on NOx generation. This mathematical model provides a basis for subsequent controller and control method design, and the controller adjusts the operating parameters of the boiler in real time, such as fuel input, air flow and ammonia flow, to optimize the combustion process.

[0130] Based on the scheme of the present application, by introducing the LSTM model, the accurate prediction and control of NOx emission during the operation of the boiler are realized, and the amount of NOx emission is significantly reduced. At the same time, the optimization control process also improves the combustion efficiency, so that the boiler can save fuel while maintaining environmental performance. Through the establishment of the mathematical model, the control strategy of the whole system is more flexible and efficient, which can adapt to the changes of various working conditions and provide protection for the stability and economy of the boiler operation.

[0131] Preferably, in the control strategy, an intelligent feedforward controller uses the set value and measured value of the inlet NOx content to adjust the opening of the green ammonia control valve in real time through an extended state observer and a NOx concentration prediction model. This feedforward control strategy ensures accurate control of the NOx concentration at the outlet of the boiler. At the same time, the generalized predictive control (GPC) controller optimizes the control strategy based on the information of the prediction model and the observer to adapt to different working conditions and maintain low NOx emission.

[0132] In the embodiment of the present application, in the control strategy, the intelligent feedforward controller accurately controls the opening of the green ammonia valve by real-time use of the NOx set value and actual measured value at the inlet of the SCR, combined with the extended state observer (ESO) and the NOx concentration prediction model. The role of this feedforward controller is to predict and compensate for external disturbances and system dynamic characteristics in advance, so that the system can still maintain the stability of NOx concentration when facing complex operating environments. The extended state observer can detect unmodeled disturbances in real time and compensate for the influence of NOx concentration changes through dynamic adjustment, further improving the robustness of the system.

[0133] In addition, the generalized predictive control (GPC) controller also plays a crucial role in this strategy. GPC optimizes the calculation of the trend of NOx concentration under different working conditions based on the output of the prediction model and the feedback information of ESO, ensuring that the system can maintain low NOx emissions under different loads and combustion conditions. Through the combination of feedforward control and GPC control, this double control strategy ensures the system's rapid response ability and prediction ability to disturbances.

[0134] Based on the scheme of the present application, precise control and optimization of the NOx concentration of the coal-fired boiler are achieved. The intelligent feedforward controller reduces the fluctuation of NOx concentration by predicting and adjusting the green ammonia valve in advance, and maintains stability under dynamic working conditions. The extended state observer further enhances the anti-disturbance ability of the system to external disturbances, making the control more accurate. The generalized predictive control (GPC) continuously optimizes the control strategy according to the actual operating conditions, ensuring that the system always maintains the lowest NOx emission level under different conditions. This scheme not only improves environmental benefits, but also improves combustion efficiency and system operation stability.

[0135] Preferably, as Figure 6 , the NOx concentration controller works with the generalized predictive control (GPC) controller to form an intelligent and automated coal-fired boiler control system. The NOx concentration controller monitors the NOx concentration at the boiler outlet in real time, adjusts the system's operating parameters in real time by comparing the actual emissions with the set environmental standards. In particular, the controller dynamically adjusts the opening size of the gaseous green ammonia valve according to the actual working conditions to ensure that the NOx emissions remain within the specified range. At the same time, the GPC controller further optimizes the control strategy based on the prediction model of the combustion process and the data feedback from the extended state observer (ESO), ensuring that the combustion system can adapt to changing operating conditions. Through the close cooperation of the NOx concentration controller and the GPC controller, not only can the NOx emissions be precisely controlled, but also the various parameters in the combustion process can be optimized, improving energy utilization efficiency. The control system uses advanced control algorithms and observers to intelligently manage the boiler's combustion process, achieving real-time monitoring and adjustment, so that the boiler can maintain the best operating state under different loads and combustion conditions.

[0136] Based on the scheme of the present application, by integrating the NOx concentration controller and the GPC controller, the environmental and energy efficiency performance of the coal-fired boiler is significantly improved. It can precisely control NOx emissions under dynamic conditions, ensure that the boiler meets environmental standards, and improve energy utilization efficiency. The system design realizes efficient combustion and stable operation of the boiler by intelligently adjusting the opening of the green ammonia valve, reduces energy waste, and significantly reduces environmental pollution. This integrated control system has strong adaptability and can cope with various combustion challenges under different working conditions, ensuring the best results in energy saving and environmental protection.

[0137] Embodiment:

[0138] This example is aimed at different load conditions on the 600 MW supercritical boiler of the coal-fired unit of the thermal power plant. Through the LSTM model, the model information is obtained under the conditions of coal powder mixed with ammonia and without ammonia, which is brought into the ammonia mixed combustion control method based on intelligent prediction and control (IPC), and compared with the traditional coal powder mixed ammonia combustion. The control effect comparison results of the two control strategies are shown in Figure 7 The corresponding control indicators are given, including the rise time tr, the regulation time ts, the decay rate φd and the overshoot σ. The control algorithm performance index comparison under different set values is shown in Table 1. Through the table, it can be seen that the control and comparison of the SCR inlet flue gas NOx concentration under two different set values are superior to TRD.

[0139] Table 1 Comparison of control algorithm performance index under different set values

[0140]

[0141] Test two: this example takes a 600 MW supercritical coal-fired boiler as the object of control and optimization design research, and compares the intelligent prediction and control (IPC) ammonia mixed combustion and the traditional coal powder (TRD) combustion to measure and compare the SCR inlet flue gas NOx concentration. With the increase of load, the coal powder ratio increases, and the SCR inlet flue gas NOx concentration of the two presents different trends, and the overall ammonia mixed combustion is lower than the traditional coal powder combustion flue gas concentration NOx, as shown in Figure 8 When ammonia is mixed with coal powder for combustion, the presence of ammonia can inhibit the generation of thermal NOx and react with fuel NOx, thereby reducing the NOx concentration in the flue gas. The mixing ratio and combustion conditions of ammonia need to be carefully controlled to ensure effective reduction of NOx while avoiding excessive ammonia escaping into the flue gas. This usually involves real-time monitoring of NOx and ammonia concentrations, as well as adjusting the mixing ratio to optimize reaction efficiency.

[0142] Figure 9 The system structure diagram of the ammonia mixed green ammonia coal-fired unit SCR inlet flue gas NOx concentration regulation system provided by an embodiment of the present application is shown in Figure 9As shown, the embodiment of the present application provides a NOx concentration regulation system for SCR inlet flue gas of a coal-fired unit with mixed combustion of green ammonia, which comprises: an initial unit configured to construct a reaction mechanism model of ammonia and coal combustion reaction based on design information of the coal-fired unit; a model construction unit configured to construct an optimization problem based on the reaction mechanism model, with the minimum proportion of NOx concentration of SCR inlet flue gas as the target, and to obtain an optimization model by adding a constraint function to the optimization problem; a prediction unit configured to analyze the influence degree of each operating parameter of the coal-fired unit on the NOx concentration of the SCR inlet flue gas based on the optimization model and a long short-term memory network, and to obtain a NOx concentration prediction model of the coal-fired unit; and a control unit configured to perform real-time optimization control of the coal-fired unit based on real-time operating parameters of the coal-fired unit and the NOx concentration prediction model, so as to ensure that the coal-fired unit maintains the lowest NOx emission concentration.

[0143] The embodiment of the present application also provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to perform the above-mentioned NOx concentration regulation method for SCR inlet flue gas of a coal-fired unit with mixed combustion of green ammonia.

[0144] Those skilled in the art can understand that all or part of the steps of the method for implementing the above-mentioned embodiment can be completed by a program instructing related hardware, the program being stored in a storage medium and including a plurality of instructions for causing a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk and various storage medium capable of storing program codes.

[0145] The above describes optional embodiments of the present application in detail in combination with the drawings, but the embodiments of the present application are not limited to the specific details in the above-mentioned embodiments. Within the technical concept range of the embodiments of the present application, the technical solutions of the embodiments of the present application can be subjected to various simple modifications, and these simple modifications all belong to the protection range of the embodiments of the present application. In addition, it should be noted that each specific technical feature described in the above-mentioned specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present application do not further describe various possible combination manners.

[0146] In addition, various different embodiments of the present application can also be combined in any manner, as long as they do not deviate from the idea of the embodiments of the present application, and they should also be considered as disclosed by the embodiments of the present application.

Claims

1. A method for regulating the NOx concentration of the SCR inlet flue gas of a coal-fired unit with green ammonia blending, the method being applied to the prediction and control of the NOx concentration of the SCR inlet flue gas of a coal-fired unit with green ammonia blending, characterized in that, The method comprises: constructing a reaction mechanism model of ammonia and coal combustion reaction based on coal-fired unit design information; based on the reaction mechanism model, constructing an optimization problem with the minimum SCR inlet flue gas NOx concentration ratio as the target, and adding a constraint function to the optimization problem to obtain an optimization model; based on the optimization model and the long short-term memory network, analyzing the influence degree of each operating parameter of the coal-fired unit on the SCR inlet flue gas NOx concentration to obtain a NOx concentration prediction model of the coal-fired unit; based on the real-time operating parameters of the coal-fired unit and the NOx concentration prediction model, performing real-time optimization control of the coal-fired unit to ensure that the coal-fired unit maintains the lowest NOx concentration emission; wherein the real-time optimization control of the coal-fired unit based on the real-time operating parameters of the coal-fired unit and the NOx concentration prediction model to ensure that the coal-fired unit maintains the lowest NOx concentration emission comprises: collecting real-time operating parameters of the coal-fired unit, and taking the real-time operating parameters as input parameters of the NOx concentration prediction model to output the predicted value of the NOx concentration at the SCR inlet; wherein, in the process of outputting the predicted value of the NOx concentration at the SCR inlet, a disturbance compensation based on an extended state observer is added; based on the predicted value of the NOx concentration at the SCR inlet, it is judged whether the predicted value is the minimum NOx concentration under the corresponding working condition; if not, a current optimal control strategy is generated based on a generalized predictive control model; based on the optimal control strategy, an adjustment scheme for each execution component is generated as an optimization control scheme; The real-time optimization control of the coal-fired unit at least includes the opening size control of the green ammonia supply valve.

2. The method of claim 1, wherein, The reaction mechanism model of ammonia and coal combustion reaction based on the coal-fired unit design information comprises: constructing a green ammonia production model based on the coal-fired unit design information; based on the green ammonia production model, constructing a reaction mechanism model of ammonia and coal combustion reaction in the furnace; wherein the green ammonia production model is constructed by an ammonia synthesis device, a renewable energy power generation device and an electrolytic water hydrogen production device.

3. The method of claim 1, wherein, The reaction mechanism model of ammonia and coal combustion reaction is: wherein, is the rate of generation of NOx; KNOx is the rate constant for the production of NOx; Qcoal is the mass flow rate of coal; wherein w is the mass fraction of nitrogen in the coal; unburnt nitrogen mass fraction; the rate of reduction of NOx; ProcessEfficiencyValue is the process efficiency value; G is the mass flow rate of green ammonia; the concentration of NOx.

4. The method of claim 1, wherein, The optimization problem is represented as: wherein, is the SCR inlet flue gas NOx concentration ratio; The constraint function includes: any one or more of energy balance constraint, total fuel blending green ammonia ratio constraint, boiler outlet ammonia escape amount constraint, boiler outlet flue gas oxygen content concentration constraint, unit output constraint and non-negative constraint.

5. The method of claim 1, wherein, The influence degree analysis of each operating parameter of the coal-fired unit on the SCR inlet flue gas NOx concentration based on the optimization model and the long short-term memory network to obtain the NOx concentration prediction model of the coal-fired unit comprises: constructing a long short-term memory network based on the optimization model, wherein the long short-term memory network comprises memory cells, input gates, forget gates and output gates, and a linear regression layer at the end; based on the long short-term memory network, simulating the influence degree of each parameter on the SCR inlet NOx concentration under different working conditions, and taking the parameters with an influence degree greater than a preset influence degree threshold as key parameters; constructing a NOx concentration prediction model of the coal-fired unit based on the key parameters.

6. The method of claim 1, wherein, The NOx concentration prediction model of the coal-fired unit based on the key parameters comprises: Based on the selected key parameters, an initial framework of the NOx concentration prediction model is constructed to clarify the input and output of the model; Based on the existing historical data and the initial framework of the NOx concentration prediction model, the NOx concentration prediction model is trained to obtain an initial NOx concentration prediction model; Based on the unused data set, the prediction model is verified and tested, and the model that passes the verification is used as the NOx concentration prediction model.

7. The method of claim 1, wherein, The expansion state observer is represented as: wherein and is the derivative of the extended state variable of the extended state observer; and meter gain parameter; for the observer bandwidth; are state variables of the coal-fired unit; to control the gain coefficient; are input parameters for the extended state observer; is the output parameter after additional disturbance compensation.

8. The method of claim 1, wherein, The generalized predictive control model is: wherein, represents an increment of the control quantity such that the objective function is minimized; NOx concentration prediction value; NOx concentration desired value; T is a matrix; To control the weight of the increment.

9. A system for regulating the NOx concentration of the flue gas at the inlet of the SCR of a coal-fired unit with green ammonia blending, applied to the prediction and control of the NOx concentration of the flue gas at the inlet of the SCR of a coal-fired unit with green ammonia blending, characterized in that, The system comprises: An initial unit configured to construct a reaction mechanism model of ammonia and coal combustion reaction based on coal-fired unit design information; A model construction unit configured to construct an optimization problem based on the reaction mechanism model, with the minimum SCR inlet flue gas NOx concentration ratio as the target, and to obtain an optimization model by adding a constraint function to the optimization problem; A prediction unit configured to analyze the influence of each operating parameter of the coal-fired unit on the SCR inlet flue gas NOx concentration based on the optimization model and the long short-term memory network, and to obtain a NOx concentration prediction model of the coal-fired unit; A control unit configured to perform real-time optimization control of the coal-fired unit based on the real-time operating parameters of the coal-fired unit and the NOx concentration prediction model, so as to ensure that the coal-fired unit maintains the lowest NOx concentration emission; wherein The real-time optimization control of the coal-fired unit based on the real-time operating parameters of the coal-fired unit and the NOx concentration prediction model to ensure that the coal-fired unit maintains the lowest NOx concentration emission comprises: collecting real-time operating parameters of the coal-fired unit, taking the real-time operating parameters as input parameters of the NOx concentration prediction model, and outputting a predicted value of the NOx concentration at the SCR inlet based on the model; wherein, in the process of outputting the predicted value of the NOx concentration at the SCR inlet based on the model, a disturbance compensation based on the expansion state observer is added; based on the predicted value of the NOx concentration at the SCR inlet, it is determined whether the predicted value is the minimum NOx concentration under the corresponding working condition; if not, a current optimal control strategy is generated based on the generalized predictive control model; and an adjustment scheme of each execution component is generated based on the optimal control strategy as an optimization control scheme.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions, which when executed on a computer, cause the computer to perform the method for adjusting and controlling the NOx concentration of the SCR inlet flue gas of the coal-fired unit with mixed green ammonia combustion according to any one of claims 1-8.

Images