Method for determining control parameters of ammonia-coal mixed combustion system and related device and system

Abstract

The invention discloses a method for determining control parameters of an ammonia-coal mixed combustion system and a related device and system, and relates to the field of ammonia-coal mixed combustion systems.The method comprises the steps that the actual value of the ammonia input flow, the actual value of the air input flow, the actual value of the nitrogen oxide content and the actual value of the ammonia remaining amount are collected; utilizing the mechanism model to obtain a predicted value of the nitrogen oxide content and a predicted value of the residual ammonia gas; determining the range of the nitrogen oxide content and the range of the residual amount of ammonia gas; training the neural network model by using the range of the nitrogen oxide content and the range of the residual ammonia gas to obtain an optimal excess air coefficient determined by the neural network model; obtaining a target ammonia gas input flow and a target air input flow corresponding to the optimal excess air coefficient; and determining the target ammonia gas input flow and the target air input flow as control parameters of the ammonia-coal mixed combustion system. The control parameters of the ammonia-coal mixed combustion system can be quickly and accurately determined, and emission of nitric oxide and ammonia gas is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of ammonia-coal mixed combustion systems, and in particular to a method for determining control parameters of an ammonia-coal mixed combustion system and related devices and systems. Background Art

[0002] Ammonia-coal co-combustion is a fuel supply method that mixes ammonia (NH3) with pulverized coal to partially replace traditional pulverized coal combustion.

[0003] Ammonia as a fuel is not completely decomposed or oxidized during the combustion process, which will cause unreacted ammonia to be emitted from the flue gas, which is called ammonia escape. The problem of ammonia escape will affect pollutant emissions, for example: ammonia in flue gas is easy to react with NO x The reaction generates ammonium salt particles, which cause particulate matter emissions. It also affects the reaction efficiency of the denitrification device (such as the selective catalytic reduction reactor SCR) and causes corrosion of downstream equipment. Summary of the invention

[0004] In view of the above problems, the present application provides a method for determining control parameters of an ammonia-coal mixed combustion system and related devices and systems to achieve the purpose of quickly and accurately determining the control parameters of the ammonia-coal mixed combustion system and reducing the emission of nitrogen oxides and ammonia. The specific scheme is as follows:

[0005] The first aspect of the present application provides a method for determining control parameters of an ammonia-coal mixed combustion system, comprising:

[0006] Collect multiple sets of parameter values ​​of the ammonia-coal mixed combustion system under the current excess air coefficient, each set of parameter values ​​at least includes: the current excess air coefficient, ammonia input flow rate, air input flow rate, actual value of nitrogen oxide content and actual value of ammonia residual amount;

[0007] The ammonia input flow rate and the air input flow rate are processed using a mechanism model of ammonia-coal mixed combustion to obtain a predicted value of nitrogen oxide content and a predicted value of ammonia residual amount;

[0008] Determine the range of the nitrogen oxide content and the range of the residual ammonia of the ammonia-coal mixed combustion system at a current excess air coefficient based on the actual value of the nitrogen oxide content, the actual value of the residual ammonia, the predicted value of the nitrogen oxide content and the predicted value of the residual ammonia;

[0009] The neural network model is trained using the range of the nitrogen oxide content, the range of the residual ammonia, and the ammonia input flow rate, the current excess air coefficient, and the air input flow rate in each group of parameter values ​​to obtain an optimal excess air coefficient determined by the trained neural network model;

[0010] Calculating a target ammonia input flow rate and a target air input flow rate corresponding to the optimal excess air coefficient according to the optimal excess air coefficient;

[0011] At least the target ammonia input flow rate and the target air input flow rate are determined as control parameters of the ammonia-coal mixed combustion system.

[0012] In a possible implementation, the input of the neural network model includes: ammonia input flow rate, air input flow rate and excess air coefficient, and the output of the neural network model includes: nitrogen oxide content and ammonia residual amount.

[0013] The method of training a neural network model by using the range of the nitrogen oxide content, the range of the residual ammonia, the ammonia input flow rate, the current excess air coefficient, and the air input flow rate in each group of parameter values ​​to obtain an optimal excess air coefficient determined by the trained neural network model includes:

[0014] Determine the minimum value between the actual value of the nitrogen oxide content and the predicted value of the nitrogen oxide content as a first reference value, and determine the minimum value between the actual value of the remaining ammonia amount and the predicted value of the remaining ammonia amount as a second reference value;

[0015] The neural network model is trained using the first reference value, the second reference value, the range of the nitrogen oxide content, the range of the residual ammonia, and the ammonia input flow, the current excess air coefficient, and the air input flow in each group of parameter values. When the nitrogen oxide content output by the neural network model for N consecutive times is lower than the first reference value and the residual ammonia output by the neural network model for N consecutive times is lower than the second reference value, the training of the neural network model is terminated to obtain the trained neural network model, and the optimal excess air coefficient is determined based on the trained neural network model.

[0016] In a possible implementation, determining the optimal excess air ratio based on the trained neural network model includes:

[0017] Determine the output nitrogen oxide content and ammonia residual amount when the trained neural network model inputs different excess air coefficients;

[0018] The nitrogen oxide content and the residual ammonia output by the trained neural network model are calculated based on the preset calculation method to obtain a comprehensive emission evaluation value;

[0019] The excess air coefficient corresponding to the minimum comprehensive emission evaluation value is determined as the optimal excess air coefficient.

[0020] In a possible implementation, the method further includes:

[0021] The ammonia input flow and air input flow of the ammonia-coal mixed combustion system are controlled by the control parameters, the optimal excess air coefficient is determined as the current excess air coefficient, and the step of collecting multiple groups of parameter values ​​of the ammonia-coal mixed combustion system under the current excess air coefficient is returned to execute.

[0022] In a possible implementation, the boiler of the ammonia-coal mixed combustion system has a main combustion zone, a reburning zone and a burnout zone.

[0023] The ammonia input flow rate includes: the ammonia input flow rate of the main combustion zone, the ammonia input flow rate of the reburning zone and the ammonia input flow rate of the burnout zone;

[0024] The air input flow rate includes: the air input flow rate of the main combustion zone, the air input flow rate of the reburning zone and the air input flow rate of the burnout zone;

[0025] The target ammonia input flow rate includes: a target ammonia input flow rate in the main combustion zone, a target ammonia input flow rate in the reburning zone, and a target ammonia input flow rate in the burnout zone;

[0026] The target air input flow rate includes: a main combustion zone target air input flow rate, a reburning zone target air input flow rate and a burnout zone target air input flow rate.

[0027] A second aspect of the present application provides a control parameter determination device for an ammonia-coal mixed combustion system, comprising:

[0028] A collection unit is used to collect multiple sets of parameter values ​​of the ammonia-coal mixed combustion system under the current excess air coefficient, each set of parameter values ​​at least including: the current excess air coefficient, ammonia input flow rate, air input flow rate, actual value of nitrogen oxide content and actual value of ammonia residual amount;

[0029] A mechanism model unit, used to process the ammonia input flow rate and the air input flow rate using a mechanism model of ammonia-coal mixed combustion to obtain a predicted value of nitrogen oxide content and a predicted value of ammonia residual amount;

[0030] a range determination unit, for determining a range of the nitrogen oxide content and a range of the residual ammonia amount of the ammonia-coal mixed combustion system at a current excess air coefficient based on an actual value of the nitrogen oxide content, an actual value of the residual ammonia amount, a predicted value of the nitrogen oxide content and a predicted value of the residual ammonia amount;

[0031] A model training unit, configured to train a neural network model using the range of the nitrogen oxide content, the range of the residual ammonia, and the ammonia input flow rate, the current excess air coefficient, and the air input flow rate in each group of parameter values, to obtain an optimal excess air coefficient determined by the trained neural network model;

[0032] a flow determination unit, configured to calculate, according to the optimal excess air coefficient, a target ammonia input flow rate and a target air input flow rate corresponding to the optimal excess air coefficient;

[0033] The parameter determination unit is used to determine at least the target ammonia input flow rate and the target air input flow rate as control parameters of the ammonia-coal mixed combustion system.

[0034] The third aspect of the present application provides an ammonia-coal mixed combustion control system, comprising: an ammonia flow meter, an air flow meter, a flue gas analyzer and a control device,

[0035] The ammonia flowmeter is arranged on the ammonia delivery pipeline of the ammonia-coal mixed combustion system, the air flowmeter is arranged on the air delivery pipeline of the ammonia-coal mixed combustion system, the flue gas analyzer is arranged in the flue gas emission pipeline of the ammonia-coal mixed combustion system, the first signal input end of the control device is connected to the ammonia flowmeter, the second signal input end of the control device is connected to the air flowmeter, the third signal input end of the control device is connected to the flue gas analyzer, the first control signal output end of the control device is connected to the ammonia supply regulating device of the ammonia-coal mixed combustion system, and the second control signal output end of the control device is connected to the air supply regulating device of the ammonia-coal mixed combustion system.

[0036] The control device obtains the current excess air coefficient, the ammonia input flow rate collected by the ammonia flowmeter, the air input flow rate collected by the air flowmeter, and the actual value of the nitrogen oxide content and the actual value of the ammonia residual amount collected by the flue gas analyzer; the control device processes the ammonia input flow rate and the air input flow rate using the mechanism model of ammonia-coal mixed combustion to obtain the predicted value of the nitrogen oxide content and the predicted value of the ammonia residual amount; the control device determines the range of the nitrogen oxide content and the range of the ammonia residual amount of the ammonia-coal mixed combustion system under the current excess air coefficient based on the actual value of the nitrogen oxide content, the actual value of the ammonia residual amount, the predicted value of the nitrogen oxide content and the predicted value of the ammonia residual amount; the control device uses the nitrogen oxide content to process the ammonia input flow rate and the air input flow rate to obtain the predicted value of the nitrogen oxide content and the predicted value of the ammonia residual amount. The neural network model is trained according to the range of the compound content, the range of the residual ammonia, and the ammonia input flow, the current excess air coefficient, and the air input flow in each group of parameter values ​​to obtain the optimal excess air coefficient determined by the trained neural network model; the control device calculates the target ammonia input flow and the target air input flow corresponding to the optimal excess air coefficient according to the optimal excess air coefficient; the control device at least determines the target ammonia input flow and the target air input flow as control parameters of the ammonia-coal mixed combustion system, the control device controls the working state of the ammonia supply regulating device according to the target ammonia input flow, and the control device controls the working state of the air supply regulating device according to the target air input flow.

[0037] The fourth aspect of the present application provides an ammonia-coal mixed combustion system, comprising: the ammonia-coal mixed combustion control system of the third aspect, the ammonia-coal mixed combustion system also comprising: a first ammonia storage device, an air conveyor, a boiler and an exhaust gas treatment unit, the first ammonia storage device conveys ammonia to the boiler through an ammonia conveying pipeline, the air conveyor conveys air to the boiler through an air conveying pipeline, and the flue gas analyzer is arranged behind the exhaust gas treatment unit in the flue gas emission pipeline.

[0038] In a possible implementation, the boiler has a main combustion zone, a reburning zone and a burnout zone.

[0039] The first ammonia storage device delivers ammonia to the main combustion zone through a first ammonia delivery pipeline, the first ammonia storage device delivers ammonia to the reburning zone through a second ammonia delivery pipeline, and the first ammonia storage device delivers ammonia to the burnout zone through a third ammonia delivery pipeline;

[0040] The air conveyor conveys air to the main combustion zone through a first air conveying pipeline, the air conveyor conveys air to the reburning zone through a second air conveying pipeline, and the air conveyor conveys air to the burnout zone through a third air conveying pipeline.

[0041] In a possible implementation, the exhaust gas treatment unit includes: a second ammonia storage device, a selective catalytic reduction reactor and an atomizer, wherein the second ammonia storage device is connected to the inlet of the atomizer, and the outlet of the atomizer is connected to the selective catalytic reduction reactor through a pipeline.

[0042] By means of the above technical scheme, the present invention provided by the present application aims at the failure to accurately control the ammonia injection amount and the air distribution method during ammonia slip, collects the ammonia input flow rate and the air input flow rate and controls the ammonia input flow rate and the air input flow rate, and the present application also monitors the nitrogen oxide content and the residual ammonia. In order to ensure that a suitable ammonia input amount is taken in the selective catalytic reduction reactor, so that the selective catalytic reduction reactor will not cause waste of ammonia and secondary ammonia slip; the mechanism model quickly calculates the ammonia input flow rate and the air input flow rate, and can quickly calculate the predicted value of the nitrogen oxide content and the predicted value of the residual ammonia. Through the actual value of the nitrogen oxide content, the actual value of the residual ammonia, the predicted value of the nitrogen oxide content and the predicted value of the residual ammonia, the present application can determine the range of the nitrogen oxide content and the range of the residual ammonia, which is an approximate range. These two ranges are input into the neural network model for training. Since the data range is greatly reduced, the operating efficiency of the neural network model is significantly improved, and the results can be calculated faster. Through repeated training, within the range of input nitrogen oxide content and the range of residual ammonia, the neural network model can find the optimal excess air coefficient that comprehensively considers the influence of the two, and then calculate the target ammonia input flow rate and target air input flow rate corresponding to the optimal excess air coefficient based on the optimal excess air coefficient.

[0043] By executing the above process multiple times, the present application can use the neural network model to gradually iterate the optimal operating conditions, the present application realizes a rapid response to pollutant emissions, the present application can dynamically adjust parameters, monitor the ammonia input flow, air input flow, nitrogen oxide content, and ammonia residual in real time, reduce the nitrogen oxide content and ammonia residual emissions to the lowest value, optimize the combustion organization mode of the main combustion zone, reburning zone, and burnout zone, and reduce the secondary pollution to the environment caused by ammonia and nitrogen oxide emissions.

[0044] The present invention makes up for the defects of poor prediction accuracy of the mechanism model and slow convergence speed of the neural network model. It uses the mechanism model to calculate an approximate range, and then uses the range to control the training process of the neural network model, effectively improving the calculation speed of the neural network model. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0046] Figure 1 A flow chart of a method for determining control parameters of an ammonia-coal mixed combustion system provided in this application;

[0047] Figure 2 A schematic diagram of the structure of a control parameter determination device for an ammonia-coal mixed combustion system provided in the present application;

[0048] Figure 3 A structural schematic diagram of an ammonia-coal mixed combustion system provided in this application. DETAILED DESCRIPTION

[0049] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0050] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0051] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0052] The embodiment of the present application provides a method for determining control parameters of an ammonia-coal mixed combustion system. The method for determining control parameters of an ammonia-coal mixed combustion system of the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0053] Reference Figure 1 , Figure 1 A flow chart of a method for determining control parameters of an ammonia-coal mixed combustion system provided in an embodiment of the present application is shown as follows: Figure 1As shown, a method for determining control parameters of an ammonia-coal mixed combustion system provided in an embodiment of the present application may include steps S100 to S600, and these steps are described in detail below.

[0054] S100, collecting multiple groups of parameter values ​​of the ammonia-coal mixed combustion system under the current excess air coefficient, each group of parameter values ​​at least includes: the current excess air coefficient, ammonia input flow rate, air input flow rate, actual value of nitrogen oxide content and actual value of residual ammonia.

[0055] The excess air coefficient is also called "excess air coefficient" or "excess air coefficient". It refers to the ratio of the actual amount of air supplied to fuel combustion to the theoretical amount of air. It is an important parameter that reflects the fuel-air ratio. In various furnaces or combustion chambers, in order to make the fuel burn as completely as possible, the actual amount of air supplied must always be greater than the theoretical amount of air (the excess part is called "excess air"), that is, the excess air coefficient must be greater than 1. However, combustion theory and operating experience show that too large or too small excess air coefficient is not conducive to combustion. If the optimal excess air coefficient can be determined, the combustion effect can be effectively improved, thereby reducing the problem of ammonia slip.

[0056] In practical applications, the ammonia input flow rate can be obtained by collecting through an ammonia flow meter, the air input flow rate can be obtained by collecting through an air flow meter, and the actual value of the nitrogen oxide content and the actual value of the remaining ammonia can be obtained by collecting through a flue gas analyzer.

[0057] Optionally, the current excess air coefficient may be an excess air coefficient set by a user.

[0058] At each current excess air coefficient, the ammonia-coal mixed combustion system can operate for a period of time. During this period of time, the present application can collect multiple sets of parameter values ​​of the ammonia-coal mixed combustion system at different times.

[0059] Optionally, the same set of parameter values ​​are collected or obtained at the same time or in the same time period.

[0060] S200, using the mechanism model of ammonia-coal mixed combustion to process the ammonia input flow rate and the air input flow rate to obtain a predicted value of the nitrogen oxide content and a predicted value of the ammonia residual amount.

[0061] Among them, the mechanism model of ammonia-coal mixed combustion refers to a mathematical model that describes and simulates the chemical reaction path, reaction equation, reaction kinetics, and main physical and chemical phenomena involved in the mixed combustion of ammonia and coal.

[0062] The mechanism model of ammonia-coal mixed combustion in the present application may be an existing mechanism model, and the present application does not limit it.

[0063] Specifically, the mechanism model of ammonia-coal mixed combustion may include: a main combustion zone mathematical model, a reburning zone mathematical model and a burnout zone mathematical model.

[0064] The mechanism model of ammonia-coal mixed combustion has the characteristics of fast calculation speed but low accuracy. If the mechanism model of ammonia-coal mixed combustion is used alone to obtain the control parameters of the ammonia-coal mixed combustion system, due to its low accuracy, it is often impossible to achieve a good combustion effect, which leads to a large amount of nitrogen oxides and residual ammonia in the flue gas. In order to solve this problem, the present application uses a mechanism model and a neural network model in combination, and comprehensively utilizes the characteristics of fast calculation speed of the mechanism model and high accuracy of the neural network model, so that the present application can determine the optimal excess air coefficient relatively quickly, thereby reducing the nitrogen oxide content and residual ammonia in the flue gas.

[0065] S300. Based on the actual value of the nitrogen oxide content, the actual value of the remaining ammonia, the predicted value of the nitrogen oxide content and the predicted value of the remaining ammonia, determine the range of the nitrogen oxide content and the range of the remaining ammonia in the ammonia-coal mixed combustion system at the current excess air coefficient.

[0066] The present application can determine a minimum range including the actual value of the nitrogen oxide content and the predicted value of the nitrogen oxide content as the range of the nitrogen oxide content, and at the same time determine a minimum range including the actual value of the ammonia remaining amount and the predicted value of the ammonia remaining amount as the range of the ammonia remaining amount.

[0067] Of course, the present application can also determine the range in other ways, for example: determining the actual value of the nitrogen oxide content, the actual value of the remaining ammonia, the predicted value of the nitrogen oxide content and the abnormal values ​​in the predicted value of the remaining ammonia according to the variance, and after removing the abnormal values, determining the range of the nitrogen oxide content according to the actual value of the remaining nitrogen oxide content and the predicted value of the remaining nitrogen oxide content, and determining the range of the remaining ammonia according to the actual value of the remaining ammonia and the predicted value of the remaining ammonia.

[0068] Optionally, each current excess air coefficient may correspond to a range of the nitrogen oxide content and a range of the residual ammonia content.

[0069] S400, training a neural network model using the range of the nitrogen oxide content, the range of the residual ammonia, and the ammonia input flow, the current excess air coefficient, and the air input flow in each group of parameter values ​​to obtain an optimal excess air coefficient determined by the trained neural network model.

[0070] In an optional embodiment, the user can set multiple excess air coefficients, and then use these excess air coefficients as the current excess air coefficients, and perform the processing from step S100 to step S300. In this way, the present application can determine the range of the nitrogen oxide content and the range of the residual ammonia in the ammonia-coal mixed combustion system under multiple excess air coefficients. Next, step S400 of the present application uses the range of nitrogen oxide content, the range of residual ammonia, and the ammonia input flow rate in each group of parameter values, each current excess air coefficient, and the air input flow rate to train the neural network model. The input of the neural network model includes: excess air coefficient, ammonia input flow rate and air input flow rate, and the output includes: nitrogen oxide content and ammonia residual amount. The training data used in the present application when training the neural network model may include: the range of nitrogen oxide content, the range of residual ammonia, and the ammonia input flow rate in each group of parameter values, each current excess air coefficient, and the air input flow rate. In another optional embodiment, the training data may also include: the actual value of the nitrogen oxide content and the actual value of the residual ammonia in each group of parameter values. Among them, the range of nitrogen oxide content and the range of ammonia residual amount can be used to constrain and guide the training of the neural network model and speed up the training speed. The trained neural network model can output its predicted nitrogen oxide content and ammonia residual amount according to the input excess air coefficient, ammonia input flow rate and air input flow rate. Since the change of the excess air coefficient will affect the predicted nitrogen oxide content and ammonia residual amount, the present application can find the optimal excess air coefficient that makes its predicted nitrogen oxide content and ammonia residual amount the lowest according to the trained neural network model.

[0071] Optionally, the optimal excess air coefficient refers to the best excess air coefficient determined by the trained neural network model, but in actual applications, the optimal excess air coefficient is not necessarily the best excess air coefficient. This application can be executed multiple times Figure 1 The method shown, for example: in executing once Figure 1 After obtaining the control parameters of the ammonia-coal mixed combustion system according to the optimal excess air coefficient, the combustion of the ammonia-coal mixed combustion system is controlled by the control parameters, and then the optimal excess air coefficient is used as the current excess air coefficient, and the method is executed again. Figure 1 In this way, through the iterative process, the best can be selected and the combustion effect can be further improved.

[0072] S500. Calculate a target ammonia input flow rate and a target air input flow rate corresponding to the optimal excess air coefficient according to the optimal excess air coefficient.

[0073] Optionally, the specific calculation process of step S500 may include:

[0074] According to the equation: 4NH3+3O2→2N2+6H2O and the theoretical air volume = 3 / 4 ammonia volume, As the ammonia flow rate, As other fuel flow, As the total theoretical air requirement for fuel, then:

[0075] = + .

[0076] in, = , = , where α is the optimal excess air coefficient.

[0077] According to the ammonia mixing ratio and the excess air coefficient, the theoretical air requirement for the combustion reaction is calculated by the following formula:

[0078] =

[0079] If the total air flow rate is known, the mixing ratio of ammonia can be inferred:

[0080] = ,

[0081] = .

[0082] Fuel flow The theoretical air demand of the fuel is fixed and the coal powder flow rate is not controlled in this application. It can be calculated. According to the actual air supply volume The value of , plus the excess air coefficient α obtained by feedback, can calculate the ammonia flow rate Then calculate the ammonia blending ratio in each area .

[0083] S600. Determine at least the target ammonia input flow rate and the target air input flow rate as control parameters of the ammonia-coal mixed combustion system.

[0084] The present application can comprehensively utilize the mechanism model and the neural network model to obtain the control parameters of the ammonia-coal mixed combustion system, which can effectively improve the control speed and improve the accuracy, thereby reducing the emission of nitrogen oxides and ammonia and reducing the ammonia escape phenomenon.

[0085] In an optional embodiment, since carbon monoxide is also one of the emissions, the present application can also monitor and predict the carbon monoxide content. Specifically, Figure 1The method shown also includes: collecting the actual value of the carbon monoxide content of the ammonia-coal mixed combustion system at the current excess air coefficient. Step S200 also obtains the predicted value of the carbon monoxide content after processing the ammonia input flow rate and the air input flow rate using the mechanism model of the ammonia-coal mixed combustion. Step S300 can also determine the range of the carbon monoxide content based on the predicted value of the carbon monoxide content and the actual value of the carbon monoxide content. Step S400 also uses the range of the carbon monoxide content when training the neural network model.

[0086] Optionally, the input of the neural network model includes: ammonia input flow rate, air input flow rate and excess air coefficient, and the output of the neural network model includes: nitrogen oxide content and ammonia residual amount,

[0087] The method of training a neural network model by using the range of the nitrogen oxide content, the range of the residual ammonia, the ammonia input flow rate, the current excess air coefficient, and the air input flow rate in each group of parameter values ​​to obtain an optimal excess air coefficient determined by the trained neural network model includes:

[0088] Determine the minimum value between the actual value of the nitrogen oxide content and the predicted value of the nitrogen oxide content as a first reference value, and determine the minimum value between the actual value of the remaining ammonia amount and the predicted value of the remaining ammonia amount as a second reference value;

[0089] The neural network model is trained using the first reference value, the second reference value, the range of the nitrogen oxide content, the range of the residual ammonia, and the ammonia input flow, the current excess air coefficient, and the air input flow in each group of parameter values. When the nitrogen oxide content output by the neural network model for N consecutive times is lower than the first reference value and the residual ammonia output by the neural network model for N consecutive times is lower than the second reference value, the training of the neural network model is terminated to obtain the trained neural network model, and the optimal excess air coefficient is determined based on the trained neural network model.

[0090] Optionally, when the nitrogen oxide content output by the neural network model for M consecutive times is not lower than the first reference value and the residual ammonia output by the neural network model for M consecutive times is not lower than the second reference value, the training of the neural network model can be stopped. This situation represents a problem in the training of the neural network model, and the training should not be continued.

[0091] By utilizing the above parameter ratio, the training accuracy of the neural network model can be effectively improved.

[0092] Optionally, determining the optimal excess air coefficient based on the trained neural network model includes:

[0093] Determine the output nitrogen oxide content and ammonia residual amount when the trained neural network model inputs different excess air coefficients;

[0094] The nitrogen oxide content and the residual ammonia output by the trained neural network model are calculated based on the preset calculation method to obtain a comprehensive emission evaluation value;

[0095] The excess air coefficient corresponding to the minimum comprehensive emission evaluation value is determined as the optimal excess air coefficient.

[0096] The comprehensive emission evaluation value can comprehensively evaluate the nitrogen oxide content and the residual ammonia content. Specifically, the preset calculation method can be a weighted calculation method.

[0097] Optional, Figure 1 The method shown also includes:

[0098] The ammonia input flow and air input flow of the ammonia-coal mixed combustion system are controlled by the control parameters, the optimal excess air coefficient is determined as the current excess air coefficient, and the step of collecting multiple groups of parameter values ​​of the ammonia-coal mixed combustion system under the current excess air coefficient is returned to execute.

[0099] Specifically, the present application can control the ammonia input flow rate and air input flow rate of the ammonia-coal mixed combustion system by controlling the ammonia valve and air valve in the ammonia-coal mixed combustion system. The present application can also control the air input flow rate by controlling the working state of the air conveyor.

[0100] Optionally, the boiler of the ammonia-coal mixed combustion system has a main combustion zone, a reburning zone and a burnout zone.

[0101] The ammonia input flow rate includes: the ammonia input flow rate of the main combustion zone, the ammonia input flow rate of the reburning zone and the ammonia input flow rate of the burnout zone;

[0102] The air input flow rate includes: the air input flow rate of the main combustion zone, the air input flow rate of the reburning zone and the air input flow rate of the burnout zone;

[0103] The target ammonia input flow rate includes: a target ammonia input flow rate in the main combustion zone, a target ammonia input flow rate in the reburning zone, and a target ammonia input flow rate in the burnout zone;

[0104] The target air input flow rate includes: a main combustion zone target air input flow rate, a reburning zone target air input flow rate and a burnout zone target air input flow rate.

[0105] Through the above-mentioned division of the main combustion zone, the reburning zone and the burnout zone, the present application can more accurately control the combustion process of the ammonia-coal mixed combustion system. It can be understood that through the division of the main combustion zone, the reburning zone and the burnout zone, the parameters input when the present application trains the neural network model are also divided into different parameters of the main combustion zone, the reburning zone and the burnout zone.

[0106] The present invention aims at the failure to accurately control the ammonia injection amount and the air distribution method during ammonia slip, collects the ammonia input flow rate and the air input flow rate and controls the ammonia input flow rate and the air input flow rate, and the present application also monitors the nitrogen oxide content and the residual ammonia. In order to ensure that the appropriate ammonia input amount is taken in the selective catalytic reduction reactor, so that the selective catalytic reduction reactor will not cause waste of ammonia and secondary ammonia slip; the mechanism model quickly calculates the ammonia input flow rate and the air input flow rate, and can quickly calculate the predicted value of the nitrogen oxide content and the predicted value of the residual ammonia. Through the actual value of the nitrogen oxide content, the actual value of the residual ammonia, the predicted value of the nitrogen oxide content and the predicted value of the residual ammonia, the present application can determine the range of the nitrogen oxide content and the range of the residual ammonia, which is an approximate range. These two ranges are input into the neural network model for training. Since the data range is greatly reduced, the operating efficiency of the neural network model is significantly improved, and the results can be calculated faster. Through repeated training, within the range of input nitrogen oxide content and the range of residual ammonia, the neural network model can find the optimal excess air coefficient that comprehensively considers the influence of the two, and then calculate the target ammonia input flow rate and target air input flow rate corresponding to the optimal excess air coefficient based on the optimal excess air coefficient.

[0107] By executing the above process multiple times, the present application can use the neural network model to gradually iterate the optimal operating conditions, the present application realizes a rapid response to pollutant emissions, the present application can dynamically adjust parameters, monitor the ammonia input flow, air input flow, nitrogen oxide content, and ammonia residual in real time, reduce the nitrogen oxide content and ammonia residual emissions to the lowest value, optimize the combustion organization mode of the main combustion zone, reburning zone, and burnout zone, and reduce the secondary pollution to the environment caused by ammonia and nitrogen oxide emissions.

[0108] The present invention makes up for the defects of poor prediction accuracy of the mechanism model and slow convergence speed of the neural network model. It uses the mechanism model to calculate an approximate range, and then uses the range to control the training process of the neural network model, effectively improving the calculation speed of the neural network model.

[0109] Optional, on first execution Figure 1When using the method shown, the following settings can be made: fix the pulverized coal flow rate, set the ammonia blending ratio to 20% to 30%, initially set the excess air coefficient, set the combustion temperature of the main combustion zone to 1200℃ to 1600℃, set the combustion temperature of the reburning zone to 1000℃ to 1400℃, and set the combustion temperature of the burnout zone to 800℃ to 1000℃.

[0110] and Figure 1 Corresponding to the method shown, the present application also provides a control parameter determination device for an ammonia-coal mixed combustion system, such as Figure 2 As shown, the device may include:

[0111] The collection unit 210 is used to collect multiple sets of parameter values ​​of the ammonia-coal mixed combustion system under the current excess air coefficient, each set of parameter values ​​at least including: the current excess air coefficient, ammonia input flow rate, air input flow rate, actual value of nitrogen oxide content and actual value of ammonia residual amount;

[0112] The mechanism model unit 220 is used to process the ammonia input flow rate and the air input flow rate using the mechanism model of ammonia-coal mixed combustion to obtain a predicted value of nitrogen oxide content and a predicted value of ammonia residual amount;

[0113] A range determination unit 230, configured to determine a range of the nitrogen oxide content and a range of the residual ammonia amount of the ammonia-coal mixed combustion system at a current excess air coefficient based on an actual value of the nitrogen oxide content, an actual value of the residual ammonia amount, a predicted value of the nitrogen oxide content, and a predicted value of the residual ammonia amount;

[0114] A model training unit 240 is used to train a neural network model using the range of the nitrogen oxide content, the range of the residual ammonia, and the ammonia input flow rate, the current excess air coefficient, and the air input flow rate in each group of parameter values ​​to obtain an optimal excess air coefficient determined by the trained neural network model;

[0115] A flow determination unit 250, configured to calculate, according to the optimal excess air coefficient, a target ammonia input flow rate and a target air input flow rate corresponding to the optimal excess air coefficient;

[0116] The parameter determination unit 260 is used to determine at least the target ammonia input flow rate and the target air input flow rate as control parameters of the ammonia-coal mixed combustion system.

[0117] The present application also provides an ammonia-coal mixed combustion control system, including: an ammonia flow meter, an air flow meter, a flue gas analyzer and a control device,

[0118] The ammonia flowmeter is arranged on the ammonia delivery pipeline of the ammonia-coal mixed combustion system, the air flowmeter is arranged on the air delivery pipeline of the ammonia-coal mixed combustion system, the flue gas analyzer is arranged in the flue gas emission pipeline of the ammonia-coal mixed combustion system, the first signal input end of the control device is connected to the ammonia flowmeter, the second signal input end of the control device is connected to the air flowmeter, the third signal input end of the control device is connected to the flue gas analyzer, the first control signal output end of the control device is connected to the ammonia supply regulating device of the ammonia-coal mixed combustion system, and the second control signal output end of the control device is connected to the air supply regulating device of the ammonia-coal mixed combustion system.

[0119] The control device obtains the current excess air coefficient, the ammonia input flow rate collected by the ammonia flowmeter, the air input flow rate collected by the air flowmeter, and the actual value of the nitrogen oxide content and the actual value of the ammonia residual amount collected by the flue gas analyzer; the control device processes the ammonia input flow rate and the air input flow rate using the mechanism model of ammonia-coal mixed combustion to obtain the predicted value of the nitrogen oxide content and the predicted value of the ammonia residual amount; the control device determines the range of the nitrogen oxide content and the range of the ammonia residual amount of the ammonia-coal mixed combustion system under the current excess air coefficient based on the actual value of the nitrogen oxide content, the actual value of the ammonia residual amount, the predicted value of the nitrogen oxide content and the predicted value of the ammonia residual amount; the control device uses the nitrogen oxide content to process the ammonia input flow rate and the air input flow rate to obtain the predicted value of the nitrogen oxide content and the predicted value of the ammonia residual amount. The neural network model is trained according to the range of the compound content, the range of the residual ammonia, and the ammonia input flow, the current excess air coefficient, and the air input flow in each group of parameter values ​​to obtain the optimal excess air coefficient determined by the trained neural network model; the control device calculates the target ammonia input flow and the target air input flow corresponding to the optimal excess air coefficient according to the optimal excess air coefficient; the control device at least determines the target ammonia input flow and the target air input flow as control parameters of the ammonia-coal mixed combustion system, the control device controls the working state of the ammonia supply regulating device according to the target ammonia input flow, and the control device controls the working state of the air supply regulating device according to the target air input flow.

[0120] Figure 3 An optional structural schematic diagram of an ammonia-coal mixed combustion system is shown. Figure 3 As can be seen in the figure, the first ammonia storage device 8 is connected to the main combustion zone ammonia nozzle 6-1 through a pipeline, and a main combustion zone ammonia flowmeter 7-1 is arranged on the pipeline. An ammonia valve 9 is arranged on one side of the first ammonia storage device 8. Figure 3There are also a reburning zone ammonia nozzle 11-1-1 and a burnout zone ammonia nozzle 12-1-1. Ammonia can be injected into the main combustion zone, the reburning zone and the burnout zone respectively through the main combustion zone ammonia nozzle 6-1, the reburning zone ammonia nozzle 11-1-1 and the burnout zone ammonia nozzle 12-1-1. Figure 3 There are also main combustion zone air nozzles 6-2, reburning zone air nozzles 11-1-2 and burnout zone air nozzles 12-1-2 to inject air into the main combustion zone, reburning zone and burnout zone respectively.

[0121] Optionally, the number of each of the above nozzles may be one or more.

[0122] Optionally, a flow meter is provided on the pipeline of each of the above-mentioned nozzles.

[0123] For convenience, Figure 3 In the figure, only the first ammonia storage device 8 is shown on the connecting pipe of the ammonia nozzle 6-1 in the main combustion zone, but it can be understood that the ammonia nozzle 11-1-1 in the reburning zone and the ammonia nozzle 12-1-1 in the burnout zone also need to be connected to an ammonia storage device. The ammonia storage device connected to the ammonia nozzle 11-1-1 in the reburning zone and the ammonia nozzle 12-1-1 in the burnout zone can be the first ammonia storage device 8 or other ammonia storage devices.

[0124] Accordingly, Figure 3 Only the air conveyor connected to the main combustion zone air nozzle 6-2 is shown. The reburning zone air nozzle 11-1-2 and the burnout zone air nozzle 12-1-2 also need to be connected to an air conveyor, and the air conveyors they are connected to can be the same or different.

[0125] exist Figure 3 Also shown is the main combustion zone air flow meter 7-2 located on the pipeline of the main combustion zone air nozzle 6-2 and the main combustion zone ammonia flow meter 7-1 located on the pipeline of the main combustion zone ammonia nozzle 6-1. It can be understood that ammonia flow meters and air flow meters can also be set on the pipelines of the reburning zone ammonia nozzle 11-1-1, the burnout zone ammonia nozzle 12-1-1, the reburning zone air nozzle 11-1-2 and the burnout zone air nozzle 12-1-2.

[0126] The main combustion zone is located in the burner area and its function is to ignite coal powder, precipitate and burn volatiles. The main combustion zone ammonia nozzle 6-1 and the main combustion zone air nozzle 6-2 are arranged on the inner wall of the main burner, wherein along the vertical wall direction of the main burner, the main combustion zone ammonia nozzle 6-1 and the main combustion zone air nozzle 6-2 are alternately arranged on the vertical walls of the two main burners to provide ammonia and air to the main burner. The main function of ammonia is to burn as fuel to release energy, and at the same time react chemically with oxygen in the air to generate water and nitrogen, thereby realizing energy conversion and utilization. In this embodiment, two main combustion zone ammonia nozzles 6-1 and two main combustion zone air nozzles 6-2 are alternately arranged on the vertical walls on both sides of the main combustion zone.

[0127] The reburning zone is located between the upper area of ​​the burner and the burnout zone. The fuel in the reburning zone is injected into the downstream of the main combustion zone under the condition of insufficient air to form a reducing atmosphere (α<1), which is beneficial to the NO generated in the main combustion zone. x In addition, the reburning zone not only makes the generated NO x is restored, while also inhibiting the generation of new NO x The generation of NO x Emission, in the present embodiment, the number of the reburning zone ammonia nozzle 11-1-1 and the reburning zone air nozzle 11-1-2 are both one, and the reburning zone ammonia nozzle 11-1-1 and the reburning zone air nozzle 11-1-2 are symmetrically arranged on the vertical wall of the reburning zone.

[0128] The burnout zone is located at the uppermost part of the furnace of the boiler 10 to ensure the completeness of combustion and reduce the generation of incomplete combustion products. In this embodiment, the number of the burnout zone ammonia nozzle 12-1-1 and the burnout zone air nozzle 12-1-2 are both one, and the burnout zone ammonia nozzle 12-1-1 and the burnout zone air nozzle 12-1-2 are symmetrically arranged on the vertical wall of the burnout zone.

[0129] Optionally, all the main combustion zone ammonia nozzles 6-1, all the reburning zone ammonia nozzles 11-1-1 and all the burnout zone ammonia nozzles 12-1-1 are connected to a first ammonia storage device 8, on which an ammonia valve 9 is provided, and all the main combustion zone air nozzles 6-2, the reburning zone air nozzles 11-1-2 and the burnout zone air nozzles 12-1-2 are connected to an air conveyor, on which an air valve is provided. The first ammonia storage device 8 is used to provide the ammonia required for ammonia blending; the air conveyor is an air delivery pump, which can be composed of a nitrogen gas storage cylinder and an oxygen gas storage cylinder, which are proportioned to deliver gas similar to air to the device. The advantage of this is to avoid the influence of dust, other gases or other particulate matter in the air on combustion, and to control the stability of air distribution.

[0130] In a specific embodiment, each main combustion zone ammonia nozzle 6-1 is provided with a main combustion zone ammonia flowmeter 7-1, and each main combustion zone air nozzle 6-2 is provided with a main combustion zone air flowmeter 7-2. Each reburning zone ammonia nozzle 11-1-1 is provided with a reburning zone ammonia flowmeter, and each reburning zone air nozzle 11-1-2 is provided with a reburning zone air flowmeter. Each burnout zone ammonia nozzle 12-1-1 is provided with a burnout zone ammonia flowmeter, and each burnout zone air nozzle 12-1-2 is provided with a burnout zone air flowmeter.

[0131] The main combustion zone ammonia flowmeter 7-1, the reburning zone ammonia flowmeter and the burnout zone ammonia flowmeter are used to monitor and collect the ammonia flow on the main combustion zone ammonia nozzle 6-1, the reburning zone ammonia nozzle 11-1-1 and the burnout zone ammonia nozzle 12-1-1 respectively. The main combustion zone air flowmeter 7-2, the reburning zone air flowmeter and the reburning zone air flowmeter are used to monitor and collect the air flow of the main combustion zone air nozzle 6-2, the reburning zone air nozzle 11-1-2 and the burnout zone air nozzle 12-1-2 respectively.

[0132] Optional, such as Figure 3 As shown, the ammonia-coal mixed combustion system further includes: a temperature sensor 15. Specifically, the temperature sensor 15 is arranged on the selective catalytic reduction reactor to detect the temperature of the selective catalytic reduction reactor.

[0133] The temperature collected by the temperature sensor 15 can be sent to the control device of the ammonia-coal mixed combustion control system. The control device can determine the optimal excess air coefficient while referring to the temperature of the selective catalytic reduction reactor during the execution of the control parameter determination method of the ammonia-coal mixed combustion system of the present application, thereby further improving the accuracy.

[0134] The control device can compare the temperature collected by the temperature sensor 15 with the preset temperature range. If it exceeds the preset temperature range, the flow rate of ammonia gas input to the selective catalytic reduction reactor can be controlled by controlling the valve 17, so that the temperature of the selective catalytic reduction reactor can be maintained within the above-mentioned preset temperature range. Of course, the control device can also control the valve 17 according to the nitrogen oxide content. For example, when the actual value of the nitrogen oxide content is large, more ammonia gas can be input into the selective catalytic reduction reactor by controlling the valve 17 to reduce the nitrogen oxide content.

[0135] The temperature range of the selective catalytic reduction reaction in the selective catalytic reduction reactor is between 300°C and 450°C. When the temperature is too low, the reaction rate is slow and NO xThe removal efficiency is low and the activity of the catalyst may be insufficient. When the temperature is too high, it may lead to excessive use of ammonia (ammonia escape problem) and the catalyst is easily deactivated. Therefore, the temperature of the selective catalytic reduction reaction must be strictly controlled. The main reasons for introducing high-temperature ammonia vapor into the selective catalytic reduction reaction are as follows: because the gaseous form of ammonia is easier to contact and react with the catalyst surface than the liquid form, ammonia vapor is easier to react with NO than liquid ammonia. x The introduction of high-temperature ammonia vapor can better disperse the ammonia and accelerate the reaction process. The reaction rate of ammonia is increased, thereby reducing the ammonia escape of the selective catalytic reduction reaction. At the same time, high temperature can also promote the activity of the catalyst, which can more effectively reduce NO x If ammonia is in a low temperature environment, it may cause solid deposits or carbon deposition on the surface of some catalysts, reducing the reactivity of the catalyst. High temperature can avoid these problems and maintain the long-term activity of the catalyst.

[0136] The present application also provides an ammonia-coal mixed combustion system, which may include: an ammonia-coal mixed combustion control system provided in an embodiment of the present application, such as Figure 3 As shown, the ammonia-coal mixed combustion system also includes: a first ammonia storage device 8, an air conveyor, a boiler 10 and an exhaust gas treatment unit. The first ammonia storage device conveys ammonia to the boiler through an ammonia conveying pipeline, the air conveyor conveys air to the boiler through an air conveying pipeline, and the flue gas analyzer 14 is arranged behind the exhaust gas treatment unit in the flue gas emission pipeline.

[0137] Optionally, the boiler has a main combustion zone, a reburning zone and a burnout zone.

[0138] The first ammonia storage device delivers ammonia to the main combustion zone through a first ammonia delivery pipeline, the first ammonia storage device delivers ammonia to the reburning zone through a second ammonia delivery pipeline, and the first ammonia storage device delivers ammonia to the burnout zone through a third ammonia delivery pipeline;

[0139] The air conveyor conveys air to the main combustion zone through a first air conveying pipeline, the air conveyor conveys air to the reburning zone through a second air conveying pipeline, and the air conveyor conveys air to the burnout zone through a third air conveying pipeline.

[0140] Optionally, the combustion temperature of the main combustion zone is 1200°C to 1600°C, the combustion temperature of the reburning zone is 1000°C to -1400°C, and the combustion temperature of the burnout zone is 800°C to 1000°C.

[0141] Optionally, when the boiler 10 is burning, the ammonia blending ratio is 20% to 30%.

[0142] Optional, such as Figure 3 As shown, the tail gas treatment unit includes: a second ammonia storage device 16, a selective catalytic reduction reactor 13 and an atomizer 18, wherein the second ammonia storage device is connected to the inlet of the atomizer, and the outlet of the atomizer is connected to the selective catalytic reduction reactor through a pipeline.

[0143] Figure 3 The exhaust gas treatment ammonia nozzle 19 and valve 17 are also provided. The exhaust gas treatment ammonia nozzle 19 is used to spray ammonia into the selective catalytic reduction reactor, and the valve 17 is used to control the flow rate of ammonia.

[0144] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0145] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for determining control parameters of an ammonia-coal mixed combustion system, characterized in that: include: Collect multiple sets of parameter values ​​of the ammonia-coal mixed combustion system under the current excess air coefficient, each set of parameter values ​​at least includes: the current excess air coefficient, ammonia input flow rate, air input flow rate, actual value of nitrogen oxide content and actual value of ammonia residual amount; The ammonia input flow rate and the air input flow rate are processed using a mechanism model of ammonia-coal mixed combustion to obtain a predicted value of nitrogen oxide content and a predicted value of ammonia residual amount; Determine the range of the nitrogen oxide content and the range of the residual ammonia of the ammonia-coal mixed combustion system at a current excess air coefficient based on the actual value of the nitrogen oxide content, the actual value of the residual ammonia, the predicted value of the nitrogen oxide content and the predicted value of the residual ammonia; The neural network model is trained using the range of the nitrogen oxide content, the range of the residual ammonia, and the ammonia input flow rate, the current excess air coefficient, and the air input flow rate in each group of parameter values ​​to obtain an optimal excess air coefficient determined by the trained neural network model; Calculating a target ammonia input flow rate and a target air input flow rate corresponding to the optimal excess air coefficient according to the optimal excess air coefficient; At least the target ammonia input flow rate and the target air input flow rate are determined as control parameters of the ammonia-coal mixed combustion system.

2. The method according to claim 1, characterized in that The input of the neural network model includes: ammonia input flow rate, air input flow rate and excess air coefficient, and the output of the neural network model includes: nitrogen oxide content and ammonia residual amount, The method of training a neural network model by using the range of the nitrogen oxide content, the range of the residual ammonia, the ammonia input flow rate, the current excess air coefficient, and the air input flow rate in each group of parameter values ​​to obtain an optimal excess air coefficient determined by the trained neural network model includes: Determine the minimum value between the actual value of the nitrogen oxide content and the predicted value of the nitrogen oxide content as a first reference value, and determine the minimum value between the actual value of the remaining ammonia amount and the predicted value of the remaining ammonia amount as a second reference value; The neural network model is trained using the first reference value, the second reference value, the range of the nitrogen oxide content, the range of the residual ammonia, and the ammonia input flow, the current excess air coefficient, and the air input flow in each group of parameter values. When the nitrogen oxide content output by the neural network model for N consecutive times is lower than the first reference value and the residual ammonia output by the neural network model for N consecutive times is lower than the second reference value, the training of the neural network model is terminated to obtain the trained neural network model, and the optimal excess air coefficient is determined based on the trained neural network model.

3. The method according to claim 2, characterized in that The method of determining the optimal excess air coefficient based on the trained neural network model comprises: Determine the output nitrogen oxide content and ammonia residual amount when the trained neural network model inputs different excess air coefficients; The nitrogen oxide content and the residual ammonia output by the trained neural network model are calculated based on the preset calculation method to obtain a comprehensive emission evaluation value; The excess air coefficient corresponding to the minimum comprehensive emission evaluation value is determined as the optimal excess air coefficient.

4. The method according to claim 1, characterized in that: Also includes: The ammonia input flow and air input flow of the ammonia-coal mixed combustion system are controlled by the control parameters, the optimal excess air coefficient is determined as the current excess air coefficient, and the step of collecting multiple groups of parameter values ​​of the ammonia-coal mixed combustion system under the current excess air coefficient is returned to execute.

5. The method according to claim 1, characterized in that The boiler of the ammonia-coal mixed combustion system has a main combustion zone, a reburning zone and a burnout zone. The ammonia input flow rate includes: the ammonia input flow rate of the main combustion zone, the ammonia input flow rate of the reburning zone and the ammonia input flow rate of the burnout zone; The air input flow rate includes: the air input flow rate of the main combustion zone, the air input flow rate of the reburning zone and the air input flow rate of the burnout zone; The target ammonia input flow rate includes: a target ammonia input flow rate in the main combustion zone, a target ammonia input flow rate in the reburning zone, and a target ammonia input flow rate in the burnout zone; The target air input flow rate includes: a main combustion zone target air input flow rate, a reburning zone target air input flow rate and a burnout zone target air input flow rate.

6. A control parameter determination device for an ammonia-coal mixed combustion system, characterized in that: include: A collection unit is used to collect multiple sets of parameter values ​​of the ammonia-coal mixed combustion system under the current excess air coefficient, each set of parameter values ​​at least including: the current excess air coefficient, ammonia input flow rate, air input flow rate, actual value of nitrogen oxide content and actual value of ammonia residual amount; A mechanism model unit, used to process the ammonia input flow rate and the air input flow rate using a mechanism model of ammonia-coal mixed combustion to obtain a predicted value of nitrogen oxide content and a predicted value of ammonia residual amount; a range determination unit, for determining a range of the nitrogen oxide content and a range of the residual ammonia amount of the ammonia-coal mixed combustion system at a current excess air coefficient based on an actual value of the nitrogen oxide content, an actual value of the residual ammonia amount, a predicted value of the nitrogen oxide content and a predicted value of the residual ammonia amount; A model training unit, configured to train a neural network model using the range of the nitrogen oxide content, the range of the residual ammonia, and the ammonia input flow rate, the current excess air coefficient, and the air input flow rate in each group of parameter values, to obtain an optimal excess air coefficient determined by the trained neural network model; a flow determination unit, configured to calculate, according to the optimal excess air coefficient, a target ammonia input flow rate and a target air input flow rate corresponding to the optimal excess air coefficient; The parameter determination unit is used to determine at least the target ammonia input flow rate and the target air input flow rate as control parameters of the ammonia-coal mixed combustion system.

7. An ammonia-coal mixed combustion control system, characterized in that: include: Ammonia flowmeter, air flowmeter, flue gas analyzer and control equipment, The ammonia flowmeter is arranged on the ammonia delivery pipeline of the ammonia-coal mixed combustion system, the air flowmeter is arranged on the air delivery pipeline of the ammonia-coal mixed combustion system, the flue gas analyzer is arranged in the flue gas emission pipeline of the ammonia-coal mixed combustion system, the first signal input end of the control device is connected to the ammonia flowmeter, the second signal input end of the control device is connected to the air flowmeter, the third signal input end of the control device is connected to the flue gas analyzer, the first control signal output end of the control device is connected to the ammonia supply regulating device of the ammonia-coal mixed combustion system, and the second control signal output end of the control device is connected to the air supply regulating device of the ammonia-coal mixed combustion system. The control device obtains the current excess air coefficient, the ammonia input flow rate collected by the ammonia flowmeter, the air input flow rate collected by the air flowmeter, and the actual value of the nitrogen oxide content and the actual value of the ammonia residual amount collected by the flue gas analyzer; the control device processes the ammonia input flow rate and the air input flow rate using the mechanism model of ammonia-coal mixed combustion to obtain the predicted value of the nitrogen oxide content and the predicted value of the ammonia residual amount; the control device determines the range of the nitrogen oxide content and the range of the ammonia residual amount of the ammonia-coal mixed combustion system under the current excess air coefficient based on the actual value of the nitrogen oxide content, the actual value of the ammonia residual amount, the predicted value of the nitrogen oxide content and the predicted value of the ammonia residual amount; the control device trains the neural network model using the range of the nitrogen oxide content, the range of the ammonia residual amount, and the ammonia input flow rate, the current excess air coefficient, and the air input flow rate in each group of parameter values ​​to obtain the optimal excess air coefficient determined by the trained neural network model; The control device calculates a target ammonia input flow rate and a target air input flow rate corresponding to the optimal excess air coefficient according to the optimal excess air coefficient; The control device at least determines the target ammonia input flow rate and the target air input flow rate as control parameters of the ammonia-coal mixed combustion system, and the control device controls the working state of the ammonia supply regulating device according to the target ammonia input flow rate, and the control device controls the working state of the air supply regulating device according to the target air input flow rate.

8. An ammonia-coal mixed combustion system, characterized in that: include: The ammonia-coal mixed combustion control system as described in claim 7, wherein the ammonia-coal mixed combustion system also includes: a first ammonia storage device, an air conveyor, a boiler and an exhaust gas treatment unit, wherein the first ammonia storage device conveys ammonia to the boiler through an ammonia conveying pipeline, the air conveyor conveys air to the boiler through an air conveying pipeline, and the flue gas analyzer is arranged behind the exhaust gas treatment unit in the flue gas emission pipeline.

9. The ammonia-coal mixed combustion system according to claim 8, characterized in that: The boiler has a main combustion zone, a reburning zone and a burnout zone. The first ammonia storage device delivers ammonia to the main combustion zone through a first ammonia delivery pipeline, the first ammonia storage device delivers ammonia to the reburning zone through a second ammonia delivery pipeline, and the first ammonia storage device delivers ammonia to the burnout zone through a third ammonia delivery pipeline; The air conveyor conveys air to the main combustion zone through a first air conveying pipeline, the air conveyor conveys air to the reburning zone through a second air conveying pipeline, and the air conveyor conveys air to the burnout zone through a third air conveying pipeline.

10. The ammonia-coal mixed combustion system according to claim 8, characterized in that: The tail gas treatment unit comprises: a second ammonia storage device, a selective catalytic reduction reactor and an atomizer, wherein the second ammonia storage device is connected to the inlet of the atomizer, and the outlet of the atomizer is connected to the selective catalytic reduction reactor through a pipeline.

Images