Denitrification control method and related device

Abstract

The invention provides a denitration control method and a related device, and relates to the field of denitration. In the application, an ammonia injection amount prediction strategy is determined, the ammonia injection amount prediction strategy represents a logic relationship between a target parameter and an ammonia injection amount, and based on parameter information of the target parameter and the ammonia injection amount prediction strategy, an ammonia injection amount prediction operation is performed to obtain a target ammonia injection amount at a next moment. And performing ammonia spraying control operation at the next moment according to the target ammonia spraying amount. Namely, the future ammonia spraying amount is determined in advance through a prediction mode, so that the ammonia spraying control operation can be directly performed based on the ammonia spraying amount when the next moment arrives, compared with a mode of calculating the ammonia spraying amount and performing ammonia spraying control when the next moment arrives, the ammonia spraying control can be performed in advance, the hysteresis of the ammonia spraying control is avoided, and the ammonia spraying control efficiency is improved. The denitration efficiency is met.

Description

Technical Field

[0001] The present application relates to the field of denitrification, and more specifically, to a denitrification control method and related devices. Background Art

[0002] When the SCR (Selective Catalytic Reduction) system of a thermal power plant performs automatic control of flue gas denitrification, it is necessary to spray ammonia to achieve the purpose of denitrification.

[0003] At present, there is a lag in the ammonia injection operation, which cannot meet the destocking efficiency. Summary of the invention

[0004] In view of this, the present application provides a destocking control method and related devices to solve the problem of hysteresis and inability to meet the destocking efficiency during ammonia injection operation.

[0005] In order to solve the above technical problems, this application adopts the following technical solutions:

[0006] A method for controlling out-of-stock, comprising:

[0007] Obtain parameter information of target parameters affecting ammonia injection amount;

[0008] Determining an ammonia injection amount prediction strategy, wherein the ammonia injection amount prediction strategy represents a logical relationship between the target parameter and the ammonia injection amount;

[0009] Based on the parameter information of the target parameter and the ammonia injection amount prediction strategy, an ammonia injection amount prediction operation is performed to obtain a target ammonia injection amount at the next moment;

[0010] The ammonia injection control operation at the next moment is performed according to the target ammonia injection amount.

[0011] Optionally, the process of determining the target parameter includes:

[0012] Acquire historical out-of-stock data; the historical out-of-stock data includes parameter values ​​of an ammonia injection amount parameter and parameter values ​​of candidate parameters;

[0013] Based on the historical out-of-stock data, a target parameter related to the ammonia injection amount parameter is screened out from the candidate parameters.

[0014] Optionally, based on the historical out-of-stock data, a target parameter related to the ammonia injection amount parameter is screened out from the candidate parameters, including:

[0015] For each of the candidate parameters, based on the parameter value of the ammonia injection amount parameter and the parameter value of the candidate parameter, calculating the correlation between the ammonia injection amount parameter and the candidate parameter;

[0016] According to the correlation, a target parameter related to the ammonia injection amount parameter is screened out from the candidate parameters.

[0017] Optionally, determining an ammonia injection amount prediction strategy includes:

[0018] For each of the target parameters, based on the parameter value of the ammonia injection amount parameter and the parameter value of the target parameter, determining the function content of the candidate function;

[0019] Selecting a target function of the target parameter from the plurality of candidate functions based on function contents of the candidate functions;

[0020] Based on the objective function of the target parameter, an ammonia injection amount prediction strategy is determined.

[0021] Optionally, selecting a target function of the target parameter from the multiple candidate functions based on function contents of the candidate functions comprises:

[0022] Based on the function contents of the candidate functions, a candidate function corresponding to the minimum mean square error is selected from the multiple candidate functions using a particle swarm algorithm, and is used as the target function of the target parameter.

[0023] Optionally, based on the objective function of the target parameter, determining the ammonia injection amount prediction strategy includes:

[0024] Determining a weighted value of an objective function of the objective parameter;

[0025] Using the weighted value, weighted summation is performed on the objective function of the target parameter to obtain an ammonia injection amount prediction formula;

[0026] The ammonia injection amount prediction formula is used as the ammonia injection amount prediction strategy.

[0027] Optionally, performing an ammonia injection control operation at the next moment according to the target ammonia injection amount includes:

[0028] Obtaining the reference ammonia injection amount at the next moment obtained through a preset operation logic;

[0029] determining a minimum value between the reference ammonia injection amount and the target ammonia injection amount;

[0030] The minimum value is used to perform the ammonia injection control operation at the next moment.

[0031] A stock-out control device, comprising:

[0032] An information acquisition module, used to acquire parameter information of target parameters affecting the amount of ammonia injection;

[0033] A strategy determination module, used to determine an ammonia injection amount prediction strategy, wherein the ammonia injection amount prediction strategy represents a logical relationship between the target parameter and the ammonia injection amount;

[0034] A prediction module, configured to perform an ammonia injection amount prediction operation based on the parameter information of the target parameter and the ammonia injection amount prediction strategy to obtain a target ammonia injection amount at the next moment;

[0035] A control module is used to perform an ammonia injection control operation at a next moment according to the target ammonia injection amount.

[0036] An electronic device comprises at least one processor and a memory connected to the processor, wherein:

[0037] The memory is used to store computer programs;

[0038] The processor is used to execute the computer program so that the electronic device can implement the out-of-stock control method.

[0039] A computer storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the out-of-stock control method.

[0040] The present application provides a method and related device for controlling a stock out of stock. In the present application, an ammonia injection amount prediction strategy is determined. The ammonia injection amount prediction strategy characterizes the logical relationship between the target parameter and the ammonia injection amount. Based on the parameter information of the target parameter and the ammonia injection amount prediction strategy, an ammonia injection amount prediction operation is performed to obtain the target ammonia injection amount at the next moment, and an ammonia injection control operation at the next moment is performed according to the target ammonia injection amount. That is, the present invention determines the future ammonia injection amount in advance by prediction, so that when the next moment arrives, the ammonia injection control operation can be performed directly based on the ammonia injection amount. Compared with the method of calculating the ammonia injection amount and performing ammonia injection control when the next moment arrives, the ammonia injection control can be performed in advance, avoiding the hysteresis of the ammonia injection control and satisfying the denitrification efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0042] Figure 1 A flow chart of a method for controlling out-of-stock situations provided by an embodiment of the present invention;

[0043] Figure 2A flow chart of a parameter screening method provided by an embodiment of the present invention;

[0044] Figure 3 A flow chart of a strategy determination method provided by an embodiment of the present invention;

[0045] Figure 4 A flow chart of an ammonia injection control method provided by an embodiment of the present invention;

[0046] Figure 5 A schematic diagram of a scenario of an ammonia injection control method provided by an embodiment of the present invention;

[0047] Figure 6 A schematic structural diagram of a stock-out control device provided by an embodiment of the present invention;

[0048] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] When the SCR of a thermal power plant is performing automatic control of flue gas denitrification, it is necessary to spray ammonia to achieve the purpose of denitrification. At present, when performing ammonia spraying operation, in order to meet the denitrification efficiency, the SCR flue gas denitrification automatic control must accurately control the amount of ammonia sprayed. For this reason, the basic control method used for the denitrification ammonia flow control is the constant mole ratio control method (Constant Mole Ratio Control). This control method is based on the denitrification efficiency and the catalyst denitrification capacity. Under this control method, the system removes nitrogen oxides NOx from the flue gas according to a fixed ammonia nitrogen molar ratio. This control method is a single-loop control system with adjustable denitrification efficiency. The control loop is simple and easy to debug and adjust. However, this method requires real-time detection of the NOx content and then controls the amount of ammonia spraying based on the content. When ammonia is sprayed, the NOx content has changed, which causes control lag and control delay in the SCR, resulting in excessive denitrification and increased operating costs.

[0051] In order to solve this problem, in an embodiment of the present invention, the ammonia injection amount at the next moment is predicted in real time, so that when the next moment arrives, the ammonia injection operation is directly performed according to the ammonia injection amount, eliminating the process of detecting the NOx content and calculating the ammonia injection amount based on the NOx content, thereby avoiding ammonia injection lag and delay.

[0052] Based on the above content, an embodiment of the present invention provides a method for controlling out-of-stock, and the execution subject may be an out-of-stock controller. Figure 1 , out-of-stock control methods may include:

[0053] S11. Obtain parameter information of target parameters that affect the amount of ammonia injection.

[0054] In actual scenarios, when SCR is in the destocking operation, there will be a large number of operating parameters, such as unit load command, total coal supply, total air volume, (A side, B side) SCR inlet concentration, (A side, B side) SCR outlet concentration, (A side, B side) ammonia escape, (A side, B side) ammonia supply flow parameters, etc. Some of these parameters have an impact on the ammonia injection amount, while others have no impact on the ammonia injection amount. Therefore, it is necessary to select the parameters that affect the ammonia injection amount from a large number of operating parameters. These parameters are called target parameters.

[0055] For the current moment, the historical parameter information of the target parameter can be used to predict the ammonia injection amount at the next moment. The historical parameter information can be parameter information of the previous week, the previous month, the previous few months, etc. The time period can be specifically configured according to the actual scenario.

[0056] S12. Determine the ammonia injection amount prediction strategy.

[0057] The ammonia injection amount prediction strategy represents the logical relationship between the target parameter and the ammonia injection amount. In actual scenarios, the logical relationship between the target parameter and the ammonia injection amount can be implemented using a formula, which includes the operational relationship between each target parameter and the ammonia injection amount.

[0058] S13: Based on the parameter information of the target parameter and the ammonia injection amount prediction strategy, an ammonia injection amount prediction operation is performed to obtain a target ammonia injection amount at a next moment.

[0059] Specifically, the parameter information of the target parameter can be put into the above formula to obtain the target ammonia injection amount at the next moment.

[0060] S14. Performing ammonia injection control operation at the next moment according to the target ammonia injection amount.

[0061] In this embodiment, since the ammonia injection amount at the next moment has been predicted, the ammonia injection operation can be performed using the ammonia injection amount when the next moment arrives, and the ammonia supply flow rate can be adjusted so that the ammonia injection amount at the next moment is the ammonia injection amount calculated in step S13.

[0062] In this embodiment, an ammonia injection amount prediction strategy will be determined, and the ammonia injection amount prediction strategy characterizes the logical relationship between the target parameter and the ammonia injection amount. Based on the parameter information of the target parameter and the ammonia injection amount prediction strategy, an ammonia injection amount prediction operation is performed to obtain the target ammonia injection amount at the next moment, and an ammonia injection control operation at the next moment is performed according to the target ammonia injection amount. That is, the present invention determines the future ammonia injection amount in advance by prediction, so that when the next moment arrives, the ammonia injection control operation can be performed directly based on the ammonia injection amount. Compared with the method of calculating the ammonia injection amount and performing ammonia injection control when the next moment arrives, the ammonia injection control can be performed in advance, avoiding the hysteresis of the ammonia injection control and satisfying the denitrification efficiency.

[0063] The above embodiment mentioned that the target parameters need to be determined. The embodiment of the present invention introduces the process of determining the target parameters. Figure 2 , which may include:

[0064] S21. Obtain historical out-of-stock data.

[0065] The historical out-of-stock data includes parameter values ​​of an ammonia injection amount parameter and parameter values ​​of candidate parameters.

[0066] Specifically, historical data related to the amount of ammonia injection in the SCR flue gas denitrification automatic control is retrieved from the DCS (Distributed Control System) of the power plant control system or the SIS (Supervisory Information System) system that communicates with the DCS, including the amount of ammonia injection in different time periods and units, load, total coal feed, total air volume, (A side, B side) SCR inlet concentration, (A side, B side) SCR outlet concentration, (A side, B side) ammonia escape, (A side, B side) ammonia supply flow rate and other data.

[0067] Among them, the ammonia injection amount is the parameter value of the ammonia injection amount parameter, and the operating parameters such as load, total coal feed, total air volume, (A side, B side) SCR inlet concentration, (A side, B side) SCR outlet concentration, (A side, B side) ammonia escape amount, (A side, B side) ammonia supply flow rate can be called candidate parameters, and it is necessary to screen out the target parameters related to the ammonia injection amount parameter from these candidate parameters.

[0068] After obtaining the parameter values ​​of the candidate parameters and the ammonia injection amount parameter, in order to ensure that the correlation between the candidate parameters and the ammonia injection amount parameter can be accurately calculated later, the obtained historical data can be cleaned in MATLAB.

[0069] S22. Based on the historical out-of-stock data, select a target parameter related to the ammonia injection amount parameter from the candidate parameters.

[0070] Specifically, due to the large number of candidate parameters, too many parameters will increase the complexity of calculation and the calculation accuracy cannot be guaranteed. Therefore, in the embodiment of the present invention, the cleaned historical data will be subjected to Pearson correlation analysis in MATLAB. Pearson correlation analysis is a statistical method for quantifying the degree of linear correlation between two variables. The value range of the Pearson correlation coefficient is between -1 and 1, where 1 represents a perfect positive correlation, -1 represents a perfect negative correlation, and 0 represents no linear relationship.

[0071] In the specific correlation analysis, the correlation between each candidate parameter and the ammonia injection amount parameter is calculated respectively. At this time, the correlation between the ammonia injection amount parameter and the candidate parameter can be calculated by using Pearson correlation analysis based on the parameter value of the ammonia injection amount parameter and the parameter value of the candidate parameter.

[0072] Subsequently, the target parameter related to the ammonia injection amount parameter may be screened out from the candidate parameters according to the correlation.

[0073] For example, based on the correlation, candidate parameters with correlation greater than a certain threshold can be screened out, and these parameters can be used as target parameters.

[0074] For another example, the larger the correlation value is, the higher the correlation between the candidate parameter and the ammonia injection amount parameter is. The candidate parameters can be sorted from large to small according to the correlation, and a preset number of candidate parameters can be screened out and used as target parameters.

[0075] For example, the target parameters ultimately determined may include unit load instructions, total coal feed, total air volume, (A side, B side) SCR inlet concentration, (A side, B side) SCR outlet concentration, (A side, B side) ammonia slip, (A side, B side) ammonia supply flow, etc.

[0076] In this embodiment, through correlation analysis, target parameters with a high degree of correlation with the ammonia injection amount parameter are screened out from a large number of candidate parameters, so that when predicting the ammonia injection amount, only parameters with a greater impact on the ammonia injection amount are considered, and parameters with a smaller impact on the ammonia injection amount can be ignored, thereby reducing the calculation complexity. In addition, since parameters that have no relationship with the ammonia injection amount are eliminated, the influence of irrelevant parameters on the ammonia injection amount prediction can be avoided, and the calculation accuracy can be improved.

[0077] Through the above steps, the target parameters affecting the ammonia injection amount can be obtained, and then the ammonia injection amount prediction strategy for predicting the ammonia injection amount can be determined according to the target parameters and the ammonia injection amount parameters. Figure 3 , determine the ammonia injection prediction strategy, including:

[0078] S31. For each of the target parameters, determine the function content of the candidate function based on the parameter value of the ammonia injection amount parameter and the parameter value of the target parameter.

[0079] In practical applications, different objective functions may have different effects on the amount of ammonia injection. Therefore, in the embodiment of the present invention, for each objective function, the relationship between it and the amount of ammonia injection may adopt different function forms, and each function form may be called a candidate function. Among them, the candidate function may include a linear function, a quadratic polynomial, a cubic polynomial, a power function, etc., which may be specifically configured according to the actual scenario.

[0080] In order to select a function suitable for the target parameter from a variety of different candidate functions, in an embodiment of the present invention, for each target parameter, the function content of each candidate function can be determined, taking the linear function y=ax+b as an example, wherein y is the independent variable, specifically the amount of ammonia injection, x is the dependent variable, specifically the target parameter, such as the SCR outlet concentration on the A side, a is the slope, and b is the intercept. For this linear function, after determining the values ​​of a and b, the function content of the linear function can be determined. At this time, the parameter value of the ammonia injection parameter in the historical data and the parameter value of the target parameter can be fitted to obtain the values ​​of a and b, thereby obtaining the function formula of y=ax+b.

[0081] Similarly, for quadratic polynomials, cubic polynomials, power functions, etc., the function content of each candidate function is determined in the same way.

[0082] S32: Selecting a target function of the target parameter from the multiple candidate functions based on the function contents of the candidate functions.

[0083] Specifically, for a target parameter, the function contents of multiple candidate functions are determined for it. However, in actual applications, the relationship between the target parameter and the ammonia injection amount parameter is unique. Therefore, although multiple candidate functions are constructed, it is necessary to select a function that best meets the relationship between the target parameter and the ammonia injection amount parameter from the multiple candidate functions. This function is called the target function.

[0084] In an implementation of the present invention, based on the function content of the candidate function, a particle swarm algorithm can be used to select a candidate function corresponding to the minimum mean square error from the multiple candidate functions and use it as the target function of the target parameter.

[0085] For example, for the SCR outlet concentration and ammonia injection amount on the A side, multiple candidate functions such as linear function, quadratic polynomial, cubic polynomial, power function, etc. are configured, and the function content of each candidate function is determined. Subsequently, the particle swarm algorithm programming in MATLAB can be used, such as particle swarm optimization (PSO) to select the function form that satisfies the minimum mean square error from the candidate functions such as linear function, quadratic polynomial, cubic polynomial, power function, etc., and use this function form as the objective function.

[0086] When using the PSO algorithm, firstly, based on the parameter value of the ammonia injection amount parameter and the parameter of the target parameter, the actual curves of the two are determined, and then compared with the function curve of the candidate function mentioned above, and the mean square error of the two curves is calculated using the PSO algorithm. The larger the mean square error, the greater the difference between the two curves, and the more dissimilar the curves are; the smaller the mean square error, the smaller the difference between the two curves, and the more similar the curves are. Therefore, the candidate function corresponding to the minimum mean square error can be selected and used as the target function, so that the determined target function is closest to the functional relationship between the two parameters in the actual scene.

[0087] S33. Determine an ammonia injection amount prediction strategy based on the objective function of the target parameter.

[0088] Specifically, through the above steps, the objective function of each target parameter can be obtained. In actual scenarios, at the same time, the amount of ammonia injection is jointly affected by multiple target parameters, that is, multiple target parameters simultaneously determine the amount of ammonia injection. Therefore, the objective function of each target parameter can be weighted and summed to obtain a total formula, which characterizes the influence of different target parameters on the amount of ammonia injection. In one implementation, the formula can be:

[0089] K1f(x1)+K2f(x2)+K3f(x3)…+ Knf(xn). Where n is the total number of target parameters, x1, x2, xn are different target parameters, f(x1), f(x2), f(xn) are the target functions of different target parameters, and K1, K2…Kn are the weights of different target functions.

[0090] Since different target parameters have different effects on the ammonia injection amount, the weight values ​​of the objective functions for different target parameters are different, so it is necessary to determine the weighted value of the objective function of the target parameter.

[0091] When determining the weighted value, the Lasso (Least absolute shrinkage and selection operator) algorithm can be used in MATLAB to train the training samples, such as the above-mentioned historical out-of-stock data, to obtain the optimal combination of weights, that is, to obtain the above-mentioned K1, K2...Kn. After K1, K2...Kn are determined, the weighted value is used to perform weighted summation on the objective function of the target parameter to obtain the ammonia injection amount prediction formula. The ammonia injection amount prediction formula can be as described above K1f(x1)+K2f(x2)+K3f(x3)...+ Knf(xn).

[0092] Since the out-of-stock process is divided into side A and side B, the corresponding ammonia injection amount prediction formulas can be configured for side A and side B respectively. When obtaining the ammonia injection amount prediction formulas for different sides, the historical out-of-stock data of this side is used. For example, when configuring the ammonia injection amount prediction formula for side A, the formula is determined using data such as the SCR inlet concentration on side A and the SCR outlet concentration on side A; when configuring the ammonia injection amount prediction formula for side B, the formula is determined using data such as the SCR inlet concentration on side B and the SCR outlet concentration on side B.

[0093] The ammonia injection amount prediction formula can be used as a formula in the ammonia demand prediction model and applied to the automatic control configuration of SCR flue gas denitrification in DCS power plants.

[0094] Subsequently, the ammonia injection amount prediction formula is used as an ammonia injection amount prediction strategy. Specifically, by inputting the parameter value of the target parameter, the ammonia injection amount at the next moment can be predicted. The parameter value of the target parameter in the embodiment of the present invention can be the parameter value of the current moment, or it can be the parameter value of a certain moment in history. For example, if the ammonia injection amounts at different moments are similar, the parameter value of the target parameter at the current moment can be used to predict the ammonia injection amount at the next moment. If the ammonia injection amounts at different moments are quite different, such as the ammonia injection amounts from Monday to Friday are different from those on weekends, taking the prediction of the ammonia injection amount on Saturday as an example, the parameter value of the target parameter at the current moment of last Saturday can be used to predict the ammonia injection amount at the next moment of this Saturday, and the ammonia injection amount is the target ammonia injection amount.

[0095] In this embodiment, the parameter value of the target parameter is used to predict the future ammonia injection amount of SCR flue gas denitrification under different unit loads, coal volume changes, and boiler air volume changes. The future change trend of the ammonia injection amount can be predicted in advance, and control and adjustment can be performed according to the future change in the ammonia injection amount, thereby improving the closed-loop stability and anti-disturbance capability of the denitrification system.

[0096] In addition, the embodiment of the present invention uses a particle swarm algorithm to solve the main function form of the target parameter affecting the amount of ammonia injection in a large amount of SCR flue gas denitrification operation data, and then uses the Lasso regression algorithm to determine the weight value of each function, and finally obtains the ammonia supply demand prediction model, which can be conveniently applied to various control DCS systems of power plants, overcome the problems of large inertia, large delay and poor control stability in the denitrification control system, and the entire SCR flue gas denitrification control is easy to debug and apply. Improve denitrification efficiency and economy.

[0097] In addition, in the present invention, the self-developed ammonia demand prediction model is used to avoid the problems of high introduction cost, inconvenient maintenance, unstable control effect, etc. caused by purchasing ammonia injection prediction controllers from other manufacturers.

[0098] It should be noted that, in the embodiment of the present invention, the ammonia injection amount prediction technology is used to avoid the lag and delay problems. In addition, the lag and delay problems can also be solved by using the fusion-improved state variable control, phase compensation control technology, etc.

[0099] After the target ammonia injection amount is obtained through the above embodiment, the ammonia injection control operation at the next moment can be performed according to the target ammonia injection amount. For example, the ammonia injection operation at the next moment is performed directly according to the target ammonia injection amount. In addition, the target ammonia injection amount and the reference ammonia injection amount obtained by PID calculation can be compared with each other to obtain the optimal ammonia injection amount.

[0100] Specifically, refer to Figure 4 , performing an ammonia injection control operation at the next moment according to the target ammonia injection amount may include:

[0101] S41. Obtain a reference ammonia injection amount at the next moment obtained through a preset operation logic.

[0102] Specifically, the preset operation logic may be a PID (proportional-integral-derivative control) control logic.

[0103] like Figure 5As shown, the environmental protection total outlet NOx set value and the environmental protection total outlet NOx measurement value (the measurement value is an hourly average) are obtained, the environmental protection total outlet NOx set value is used as the set value S, and the environmental protection total outlet NOx measurement value is used as the detection value P to be input into the PID controller, the PID controller includes a proportion K, an integral ∫ and a differential d / dt, and the PID controller is used to obtain a first intermediate value, and the first intermediate value is summed with the A side outlet NOx set value offset and the B side outlet NOx set value offset to obtain a second intermediate value, and the second intermediate value and the A side outlet NOx (after purging and holding processing) are input into the PID controller to obtain the reference ammonia injection amount of the A side and the B side.

[0104] S42: Determine the minimum value between the reference ammonia injection amount and the target ammonia injection amount.

[0105] Specifically, in order to save ammonia, a minimum value between the reference ammonia injection amount and the target ammonia injection amount can be obtained by performing a small selection operation on the reference ammonia injection amount and the target ammonia injection amount. Figure 5 As shown, the ammonia injection amount prediction formula of side A is configured in the ammonia supply demand prediction model, and the target ammonia injection amount of side A is obtained by using the ammonia injection amount prediction formula. Similarly, the ammonia supply demand prediction model of side B is configured with the ammonia injection amount prediction formula of side B, and the target ammonia injection amount of side B is obtained by using the ammonia injection amount prediction formula. For the target ammonia injection amount of each side, it is compared with the reference ammonia injection amount to obtain the minimum value.

[0106] S43. Use the minimum value to perform ammonia injection control operation at the next moment.

[0107] Specifically, taking side A as an example, the minimum value and the ammonia supply flow rate of side A are input into the PID control to obtain the ammonia supply regulating valve of side A, and the current ammonia supply amount is made the above minimum value by adjusting the valve opening. The same operation is performed on side B.

[0108] In this embodiment, the minimum value between the reference ammonia injection amount and the target ammonia injection amount is used, so that the destocking operation can be achieved with less ammonia gas, thereby saving costs. In addition, in the embodiment of the present invention, the minimum value between the reference ammonia injection amount and the target ammonia injection amount is determined to achieve mutual correction between the reference ammonia injection amount and the target ammonia injection amount, which can avoid the problem of low accuracy of ammonia injection amount caused by inaccurate prediction of the target ammonia injection amount, thereby affecting the destocking efficiency.

[0109] Based on the above-mentioned out-of-stock control method embodiment, another embodiment of the present invention provides an out-of-stock control device, referring to Figure 6 , which may include:

[0110] An information acquisition module 11 is used to acquire parameter information of target parameters affecting the amount of ammonia injection;

[0111] A strategy determination module 12, for determining an ammonia injection amount prediction strategy, wherein the ammonia injection amount prediction strategy represents a logical relationship between the target parameter and the ammonia injection amount;

[0112] A prediction module 13 is used to perform an ammonia injection amount prediction operation based on the parameter information of the target parameter and the ammonia injection amount prediction strategy to obtain a target ammonia injection amount at the next moment;

[0113] The control module 14 is used to perform an ammonia injection control operation at a next moment according to the target ammonia injection amount.

[0114] In one implementation, a parameter determination module is further included, and the parameter determination module includes:

[0115] A data acquisition submodule, used to acquire historical out-of-stock data; the historical out-of-stock data includes parameter values ​​of an ammonia injection amount parameter and parameter values ​​of candidate parameters;

[0116] A screening submodule is used to screen out a target parameter related to the ammonia injection amount parameter from the candidate parameters based on the historical out-of-stock data.

[0117] In one implementation, the screening submodule includes:

[0118] a correlation calculation unit, configured to calculate, for each of the candidate parameters, a correlation between the ammonia injection amount parameter and the candidate parameter based on a parameter value of the ammonia injection amount parameter and a parameter value of the candidate parameter;

[0119] A screening unit is used to screen out a target parameter related to the ammonia injection amount parameter from the candidate parameters according to the correlation.

[0120] In one implementation, the policy determination module 12 includes:

[0121] a content determination submodule, for determining, for each of the target parameters, the function content of the candidate function based on the parameter value of the ammonia injection amount parameter and the parameter value of the target parameter;

[0122] A function selection submodule, configured to select a target function of the target parameter from the plurality of candidate functions based on function contents of the candidate functions;

[0123] The strategy determination submodule is used to determine the ammonia injection amount prediction strategy based on the objective function of the target parameter.

[0124] In one implementation, the function selection submodule is specifically used for:

[0125] Based on the function contents of the candidate functions, a candidate function corresponding to the minimum mean square error is selected from the multiple candidate functions using a particle swarm algorithm, and is used as the target function of the target parameter.

[0126] In one implementation, the policy determination submodule includes:

[0127] A weighted value determination unit, used to determine a weighted value of an objective function of the objective parameter;

[0128] A formula determination unit, configured to perform weighted summation on the objective function of the objective parameter using the weighted value to obtain an ammonia injection amount prediction formula;

[0129] A strategy determination unit is used to use the ammonia injection amount prediction formula as an ammonia injection amount prediction strategy.

[0130] In one implementation, the control module 14 includes:

[0131] The ammonia injection amount acquisition submodule is used to obtain the reference ammonia injection amount at the next moment obtained by a preset operation logic;

[0132] a numerical value determination submodule, used to determine the minimum value between the reference ammonia injection amount and the target ammonia injection amount;

[0133] The control submodule is used to use the minimum value to perform an ammonia injection control operation at the next moment.

[0134] In this embodiment, an ammonia injection amount prediction strategy will be determined, and the ammonia injection amount prediction strategy characterizes the logical relationship between the target parameter and the ammonia injection amount. Based on the parameter information of the target parameter and the ammonia injection amount prediction strategy, an ammonia injection amount prediction operation is performed to obtain the target ammonia injection amount at the next moment, and an ammonia injection control operation at the next moment is performed according to the target ammonia injection amount. That is, the present invention determines the future ammonia injection amount in advance by prediction, so that when the next moment arrives, the ammonia injection control operation can be performed directly based on the ammonia injection amount. Compared with the method of calculating the ammonia injection amount and performing ammonia injection control when the next moment arrives, the ammonia injection control can be performed in advance, avoiding the hysteresis of the ammonia injection control and satisfying the denitrification efficiency.

[0135] It should be noted that, for the working process of each module, sub-module and unit in this embodiment, please refer to the corresponding description in the above embodiment, which will not be repeated here.

[0136] An embodiment of the present application also provides an electronic device, including at least one processor and a memory connected to the processor, wherein:

[0137] The memory is used to store computer programs;

[0138] The processor is used to execute the computer program so that the electronic device can implement the out-of-stock control method.

[0139] refer to Figure 7 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 7 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0140] like Figure 7 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0141] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0142] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any out-of-stock control method provided in the embodiment of the present application.

[0143] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any out-of-stock control method provided in the embodiment of the present application.

[0144] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling out-of-stock, characterized in that: include: Obtain parameter information of target parameters affecting ammonia injection amount; Determining an ammonia injection amount prediction strategy, wherein the ammonia injection amount prediction strategy represents a logical relationship between the target parameter and the ammonia injection amount; Based on the parameter information of the target parameter and the ammonia injection amount prediction strategy, an ammonia injection amount prediction operation is performed to obtain a target ammonia injection amount at the next moment; The ammonia injection control operation at the next moment is performed according to the target ammonia injection amount.

2. The out-of-stock control method according to claim 1, characterized in that: The process of determining the target parameters includes: Acquire historical out-of-stock data; the historical out-of-stock data includes parameter values ​​of an ammonia injection amount parameter and parameter values ​​of candidate parameters; Based on the historical out-of-stock data, a target parameter related to the ammonia injection amount parameter is screened out from the candidate parameters.

3. The out-of-stock control method according to claim 2, characterized in that: Based on the historical out-of-stock data, target parameters related to the ammonia injection amount parameter are screened out from the candidate parameters, including: For each of the candidate parameters, based on the parameter value of the ammonia injection amount parameter and the parameter value of the candidate parameter, calculating the correlation between the ammonia injection amount parameter and the candidate parameter; According to the correlation, a target parameter related to the ammonia injection amount parameter is screened out from the candidate parameters.

4. The out-of-stock control method according to claim 2, characterized in that: Determine the ammonia injection prediction strategy, including: For each of the target parameters, based on the parameter value of the ammonia injection amount parameter and the parameter value of the target parameter, determining the function content of the candidate function; Selecting a target function of the target parameter from the plurality of candidate functions based on function contents of the candidate functions; Based on the objective function of the target parameter, an ammonia injection amount prediction strategy is determined.

5. The out-of-stock control method according to claim 4, characterized in that: Selecting a target function of the target parameter from the plurality of candidate functions based on function contents of the candidate functions comprises: Based on the function contents of the candidate functions, a candidate function corresponding to the minimum mean square error is selected from the multiple candidate functions using a particle swarm algorithm and used as the target function of the target parameter.

6. The out-of-stock control method according to claim 4, characterized in that: Based on the objective function of the target parameter, an ammonia injection amount prediction strategy is determined, including: Determining a weighted value of an objective function of the objective parameter; Using the weighted value, weighted summation is performed on the objective function of the target parameter to obtain an ammonia injection amount prediction formula; The ammonia injection amount prediction formula is used as the ammonia injection amount prediction strategy.

7. The out-of-stock control method according to claim 1, characterized in that: Performing an ammonia injection control operation at the next moment according to the target ammonia injection amount includes: Obtaining the reference ammonia injection amount at the next moment obtained through a preset operation logic; determining a minimum value between the reference ammonia injection amount and the target ammonia injection amount; The minimum value is used to perform the ammonia injection control operation at the next moment.

8. A stock-out control device, characterized in that: include: An information acquisition module, used to acquire parameter information of target parameters affecting the amount of ammonia injection; A strategy determination module, used to determine an ammonia injection amount prediction strategy, wherein the ammonia injection amount prediction strategy represents a logical relationship between the target parameter and the ammonia injection amount; A prediction module, configured to perform an ammonia injection amount prediction operation based on the parameter information of the target parameter and the ammonia injection amount prediction strategy to obtain a target ammonia injection amount at the next moment; A control module is used to perform an ammonia injection control operation at a next moment according to the target ammonia injection amount.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the out-of-stock control method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the out-of-stock control method as described in any one of claims 1 to 7.

Images