De-nitration control method, device, storage medium, electronic equipment and system

Abstract

The present disclosure relates to a denitration control method, device, storage medium, electronic equipment and system, the method comprising: obtaining operation data of a denitration system, the operation data comprising flue gas volume, denitration temperature and opening value of an ammonia injection control valve; inputting the operation data into a pre-trained denitration prediction model to obtain a denitration prediction result output by the denitration prediction model, the denitration prediction result comprising a target nitrogen oxide concentration of a next time period corresponding to a denitration outlet of the denitration system; determining a target opening value of the ammonia injection control valve according to the target nitrogen oxide concentration; and controlling the ammonia injection control valve according to the target opening value so that the denitration system performs denitration.

Description

Technical Field

[0001] This disclosure relates to the field of denitrification control technology, specifically to a denitrification control method, apparatus, storage medium, electronic device, and system. Background Technology

[0002] Nitrogen oxides are one of the main pollutants emitted by thermal power plants, and their emissions need to be strictly controlled. Therefore, it is necessary to propose corresponding control strategies for denitrification equipment and its corresponding denitrification control system.

[0003] Currently, most flue gas purification equipment in thermal power plants uses Selective Catalytic Reduction (SCR) reactors to remove NOx from the flue gas. The basic principle is that ammonia (NH3) is injected into the flue gas, and the NOx reacts with it under the condition of a catalyst. In actual operation, large fluctuations in the NOx concentration at the SCR reactor outlet are common, and the ammonia injection rate is often excessive, leading to air preheater blockage and affecting production efficiency. Summary of the Invention

[0004] To address the technical problems existing in related technologies, this disclosure provides a denitrification control method, apparatus, storage medium, electronic device, and system.

[0005] According to a first aspect of the present disclosure, a denitrification control method is provided, comprising:

[0006] Acquire the operating data of the denitrification system, including flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve;

[0007] The running data is input into a pre-trained denitrification prediction model to obtain the denitrification prediction result output by the denitrification prediction model. The denitrification prediction result includes the target nitrogen oxide concentration at the denitrification outlet of the denitrification system for the next time period.

[0008] The target opening value of the ammonia injection control valve is determined based on the target nitrogen oxide concentration.

[0009] The ammonia injection valve is controlled according to the target opening value so that the denitrification system can perform denitrification.

[0010] Optionally, the denitrification prediction model includes a prediction module, an iteration module, and a memory module;

[0011] The prediction module is used to predict the target nitrogen oxide concentration for the next time period corresponding to the denitrification outlet based on the operational data.

[0012] The iterative module is used to perform multiple iterative calculations based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module to obtain the target control quantity;

[0013] The memory module is used to store the historical prediction data of the prediction module and the historical iteration data of the iteration module, so as to provide the iteration module with iterative data for the next iteration calculation.

[0014] Optionally, the step of iteratively calculating the target control quantity based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module includes:

[0015] A step response experiment was conducted based on the initial denitrification prediction model to obtain a transfer function model in the frequency domain.

[0016] Transform the frequency domain transfer function model into a time domain state-space model;

[0017] The expression for the transfer function model is:

[0018] y(s)=G(s)·u(s)

[0019] Where u(s) represents the opening value of the ammonia injection regulating valve, y(s) represents the nitrogen oxide concentration at the denitrification outlet, and G(s) represents the transfer function;

[0020] The expression for the state-space model is:

[0021]

[0022] Wherein, A, B, and C are preset variable matrices that affect the nitrogen oxide concentration at the denitrification outlet, u(t) represents the input of the denitrification system at time t, x(t) represents the state of the denitrification system at time t, and y(t) represents the output of the denitrification system at time t.

[0023] Optionally, the target control quantity is calculated based on the performance index function of the optimal control algorithm, and the expression of the performance index function of the optimal control algorithm is:

[0024] J=[Δy(t) T RΔy(t)+Δu(t) T SΔu(t)+δΔu(t) T QδΔu(t)]

[0025] Where Q, R, and S represent the preset weight matrices of the variable matrix, Δy() represents the output change of the denitrification system at time t, Δu() represents the input change of the denitrification system at time t, and δ represents the preset time change operator.

[0026] Optionally, the target control quantity is obtained by iterative calculation based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module, including:

[0027] Determine the minimum function of the performance index function;

[0028] The target input change is calculated based on the minimum function.

[0029] Optionally, determining the target opening value of the ammonia injection control valve based on the target nitrogen oxide concentration includes:

[0030] Determine the correspondence between the nitrogen oxide concentration at the denitrification outlet and the opening value of the ammonia injection control valve;

[0031] The target opening value is calculated based on the correspondence and the target nitrogen oxide concentration.

[0032] According to a second aspect of the present disclosure, a denitrification control device is provided, comprising:

[0033] The acquisition module is used to acquire the operating data of the denitrification system, including the flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve.

[0034] The prediction module is used to input the running data into a pre-trained denitrification prediction model to obtain the denitrification prediction result output by the denitrification prediction model. The denitrification prediction result includes the target nitrogen oxide concentration at the denitrification outlet of the denitrification system for the next time period.

[0035] The determination module is used to determine the target opening value of the ammonia injection control valve based on the target nitrogen oxide concentration;

[0036] The control module is used to control the ammonia injection valve according to the target opening value so that the denitrification system can perform denitrification.

[0037] According to a third aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method described in any of the first aspects.

[0038] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising:

[0039] A memory on which computer programs are stored;

[0040] A processor for executing the computer program in the memory to implement the steps of the method of any one of the first aspects.

[0041] According to a fifth aspect of the present disclosure, a denitrification system is provided, including the electronic equipment described in the fourth aspect.

[0042] The above technical solution involves inputting real-time operational data from the denitrification system, including flue gas volume, denitrification temperature, and ammonia injection valve opening, into a pre-trained denitrification prediction model. This model determines the target nitrogen oxide concentration (NOx) at the denitrification outlet for the next time period. Based on this target NOx concentration, the target opening value of the ammonia injection valve is then determined, allowing the denitrification system to control the valve accordingly. This method predicts the target NOx concentration at the denitrification outlet based on existing real-time operational data, enabling the ammonia injection valve to operate proactively. This improves the speed and stability of the denitrification control system, solves the problem of large fluctuations in NOx concentration at the SCR reactor outlet and frequent excessive ammonia injection, thereby preventing air preheater blockage and improving production efficiency.

[0043] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0044] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0045] Figure 1 This is a flowchart illustrating a denitrification control method according to an exemplary embodiment.

[0046] Figure 2 This is a block diagram illustrating a denitrification control device according to an exemplary embodiment.

[0047] Figure 3 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0048] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0049] Figure 1 This is a flowchart illustrating a denitrification control method according to an exemplary embodiment, including the following steps:

[0050] In step S101, the operating data of the denitrification system is acquired, including flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve.

[0051] In step S102, the running data is input into the pre-trained denitrification prediction model to obtain the denitrification prediction result output by the denitrification prediction model. The denitrification prediction result includes the target nitrogen oxide concentration at the denitrification outlet of the denitrification system for the next time period.

[0052] In step S103, the target opening value of the ammonia injection control valve is determined based on the target nitrogen oxide concentration;

[0053] In step S104, the ammonia injection valve is controlled according to the target opening value so that the denitrification system can perform denitrification.

[0054] It should be understood that since the nitrogen oxide concentration at the denitrification outlet is related to parameters such as flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve, the target nitrogen oxide concentration for the next time period at the denitrification outlet can be predicted based on operating data including flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve. Of course, the operating data of the denitrification system may also include other parameters affecting the nitrogen oxide concentration at the denitrification outlet during the denitrification process; this disclosure does not limit this. The operating data of the denitrification system can be obtained directly from the denitrification system, or it can be obtained by setting corresponding sensors to acquire the operating data of the denitrification system; this disclosure also does not limit this.

[0055] It should also be understood that the next time period corresponding to the denitrification outlet can be calculated based on factors such as the time for completing the operation data, determining the target nitrogen oxides, determining the target opening value, and the control time of the denitrification system.

[0056] The above technical solution involves inputting real-time operational data from the denitrification system, including flue gas volume, denitrification temperature, and ammonia injection valve opening, into a pre-trained denitrification prediction model. This model determines the target nitrogen oxide concentration (NOx) at the denitrification outlet for the next time period. Based on this target NOx concentration, the target opening value of the ammonia injection valve is then determined, allowing the denitrification system to control the valve accordingly. This method predicts the target NOx concentration at the denitrification outlet based on existing real-time operational data, enabling the ammonia injection valve to operate proactively. This improves the speed and stability of the denitrification control system, solves the problem of large fluctuations in NOx concentration at the SCR reactor outlet and frequent excessive ammonia injection, thereby preventing air preheater blockage and improving production efficiency.

[0057] In some possible ways, the denitrification prediction model includes a prediction module, an iteration module, and a memory module;

[0058] The prediction module is used to predict the target nitrogen oxide concentration at the denitrification outlet for the next time period based on operational data;

[0059] The iterative module is used to perform multiple iterative calculations based on the target nitrogen oxide concentration predicted by the optimal control algorithm and the prediction module to obtain the target control quantity;

[0060] The memory module stores historical prediction data from the prediction module and historical iteration data from the iteration module, providing iteration data for the next iteration calculation in order to support the iteration module.

[0061] It should be understood that the training process of the denitrification prediction model includes multiple rounds of iterative training. Each training round is based on the predicted value obtained from the previous round of iterative training (i.e., the target nitrogen oxide concentration for the next time period corresponding to the denitrification outlet). The iterative module is used to perform multiple iterative calculations based on the optimal control algorithm and the predicted values ​​output by the prediction module. Through multiple iterative calculations, the predicted values ​​of the prediction module of the denitrification prediction model are made closer to the true values. The memory module is used to store data information, including historical prediction data from the prediction module and historical iteration data from the iterative module, to provide iterative data for the next iteration calculation of the iterative module.

[0062] The target control quantity refers to the target concentration of nitrogen oxides output from the current denitrification port. The target concentration of nitrogen oxides is fed back to the control system so that the target opening value of the ammonia injection valve corresponding to the target concentration can be calculated based on the target concentration of nitrogen oxides.

[0063] In one possible approach, the target control variable can be obtained by iterative calculation based on the target nitrogen oxide concentration predicted by the optimal control algorithm and the prediction module:

[0064] A step response experiment was conducted based on the initial denitrification prediction model to obtain a transfer function model in the frequency domain.

[0065] Transform the frequency domain transfer function model into a time domain state-space model;

[0066] The expression for the transfer function model is:

[0067] y(s)=G(s)·u(s)

[0068] Where u(s) represents the opening value of the ammonia injection control valve, which is the input quantity, y(s) represents the nitrogen oxide concentration at the denitrification outlet, which is the output quantity, and G(s) represents the transfer function.

[0069] The expression for the state-space model is:

[0070]

[0071] Where A, B, and C are preset variable matrices that affect the nitrogen oxide concentration at the denitrification outlet, u(t) represents the input of the denitrification system at time t, x(t) represents the state of the denitrification system at time t, and y(t) represents the output of the denitrification system at time t.

[0072] It should be understood that in this system composed of the opening value of the ammonia injection control valve and the nitrogen oxide concentration at the denitrification outlet, since the input and output quantities are measurable and known, the system transfer function is unknown. Therefore, the system transfer function can be determined by introducing known input quantities and studying the system output quantities through experimental methods. That is, by conducting step response tests based on the initial denitrification prediction model, the system transfer function can be determined to describe the dynamic characteristics of this system composed of the opening value of the ammonia injection control valve and the nitrogen oxide concentration at the denitrification outlet.

[0073] For example, matrices A, B, and C can represent the flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve. At time t, the output of the denitrification system is based on the input at time t. However, at time t+1, since the state of the denitrification system varies at different times during operation, the state variables are based on the input and state variables at time t. The predicted NOx concentration at the denitrification outlet based on the denitrification system can be specifically expressed as:

[0074]

[0075] It can be written as:

[0076]

[0077] Right now Where N denotes the prediction time domain.

[0078] In one possible approach, the target control quantity is calculated based on the performance index function of the optimal control algorithm, which is expressed as follows:

[0079] J=[Δy(t) T RΔy(t)+Δu(t) T SΔu(t)+δΔu(t) T QδΔu(t)]

[0080] Where Q, R, and S represent the weight matrices of the preset variable matrices, Δy(t) represents the output change of the denitrification system at time t, Δu(t) represents the input change of the denitrification system at time t, and δ represents the preset time change operator.

[0081] For example, since factors such as flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve have varying degrees of influence on the nitrogen oxide concentration at the denitrification inlet during the operation of the denitrification system, weights can be added to each influencing factor to adjust its influence on the nitrogen oxide concentration at the denitrification inlet. That is, the weight matrices Q, R, and S can correspond to the preset variable matrices A, B, and C, and the influence of each factor in variable matrices A, B, and C on the nitrogen oxide concentration at the denitrification inlet can be adjusted through the weight matrices Q, R, and S.

[0082] In one possible approach, the target control variable can be obtained by iterative calculation based on the target nitrogen oxide concentration predicted by the optimal control algorithm and the prediction module:

[0083] Determine the minimum function of the performance index function;

[0084] Calculate the change in the target input based on the minimum function.

[0085] For example, the minimum performance metric function can be:

[0086] J = min[Δy(t)] T RΔy(t)+Δu(t) T SΔu(t)+δΔu(t) T QδΔu(t)]

[0087] The change in the target input can then be calculated using the following formula:

[0088] Δu(t)=(E T RE+S+Q) -1 E T R(Δy(t)-Dx(t)-Qδu(t))

[0089] After calculating the target input change Δu(t) at time t, the target control quantity can be calculated based on the target input change Δu(t). Then, based on the target control quantity (i.e., the target concentration of nitrogen oxides output from the current denitrification port), the target opening value of the ammonia injection valve corresponding to achieving this target concentration can be calculated. Finally, the ammonia injection valve is controlled to perform denitrification based on the target opening value. Simultaneously, during this process, the memory module stores information such as the input quantity, output quantity, input change quantity, and state change quantity of the denitrification system at time t, providing historical data for the next round of iterative calculations.

[0090] Among the possible methods, determining the target opening value of the ammonia injection control valve based on the target nitrogen oxide concentration can be as follows:

[0091] Determine the correspondence between the nitrogen oxide concentration at the denitrification outlet and the opening value of the ammonia injection control valve;

[0092] The target opening value is calculated based on the corresponding relationship and the target nitrogen oxide concentration.

[0093] For example, since the basic principle of selective catalysis is that ammonia (NH3) injected into the flue gas reacts with NOx under catalytic conditions, we can pre-store the correspondence between the NOx concentration at the denitrification outlet and the opening value of the ammonia injection control valve. After determining the target NOx concentration, the target opening value can be calculated based on the detectable target NOx concentration using the preset correspondence or calculation method. This disclosure does not specifically limit the correspondence or calculation method between the NOx concentration at the denitrification outlet and the opening value of the ammonia injection control valve.

[0094] The above technical solution involves inputting real-time operational data from the denitrification system, including flue gas volume, denitrification temperature, and ammonia injection valve opening, into a pre-trained denitrification prediction model. This model determines the target nitrogen oxide concentration (NOx) at the denitrification outlet for the next time period. Based on this target NOx concentration, the target opening value of the ammonia injection valve is then determined, allowing the denitrification system to control the valve accordingly. This allows for prediction of the target NOx concentration at the denitrification outlet based on existing real-time operational data, enabling the ammonia injection valve to operate ahead of time. This improves the speed and stability of the denitrification control system, solves the problem of large fluctuations in NOx concentration at the SCR reactor outlet and frequent excessive ammonia injection, thus preventing air preheater blockage and improving production efficiency. Furthermore, the denitrification prediction model is obtained through multiple iterative calculations based on the optimal control algorithm and the predicted values ​​output by the prediction module. These iterations further refine the model's predictions, bringing them closer to the actual values ​​and improving the accuracy of the predicted target NOx concentration at the denitrification outlet for the next time period, thereby enhancing the overall accuracy of the denitrification control system.

[0095] For example, by applying the above technical solution to the denitrification control system of a power plant, the control system parameter tuning results are shown in Table 1. The operating curves of the unit during the load change phase (401MW-516MW-365MW) with simultaneous changes in the desulfurization outlet setpoint are shown. Based on the operating curves over approximately 2 hours, it can be observed that after the denitrification optimization control system was put into operation, the inlet concentrations on both sides (A and B) remained stable. The desulfurization outlet setpoints changed from 40 mg / Nm3 to 45 mg / Nm3 and 40 mg / Nm3, respectively. The NOx concentration control at the desulfurization outlet remained stable, with a maximum positive deviation of +2.5 mg / Nm3 and a maximum negative deviation of -3.9 mg / Nm3. The control target was ±5 mg / Nm3, significantly improving the operational quality of the denitrification control system.

[0096] Table 1

[0097] parameter Setting value Iterative time domain N 80 Control weight matrix Q 50I Control weight matrix R 20I Control weight matrix S 5I

[0098] Where I represents the identity matrix.

[0099] Figure 2 This is a block diagram illustrating a denitrification control device according to an exemplary embodiment. (Refer to...) Figure 2 The denitrification control device 200 includes an acquisition module 201, a prediction module 202, a determination module 203, and a control module 204.

[0100] The acquisition module 201 is used to acquire the operating data of the denitrification system, including the flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve.

[0101] Prediction module 202 is used to input the running data into a pre-trained denitrification prediction model to obtain the denitrification prediction result output by the denitrification prediction model. The denitrification prediction result includes the target nitrogen oxide concentration of the next time period corresponding to the denitrification outlet of the denitrification system.

[0102] The determining module 203 is used to determine the target opening value of the ammonia injection control valve based on the target nitrogen oxide concentration;

[0103] The control module 204 is used to control the ammonia injection valve according to the target opening value so that the denitrification system can perform denitrification.

[0104] Optionally, the denitrification prediction model includes a prediction module, an iteration module, and a memory module;

[0105] The prediction module is used to predict the target nitrogen oxide concentration for the next time period corresponding to the denitrification outlet based on the operational data.

[0106] The iterative module is used to perform multiple iterative calculations based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module to obtain the target control quantity;

[0107] The memory module is used to store the historical prediction data of the prediction module and the historical iteration data of the iteration module, so as to provide the iteration module with iterative data for the next iteration calculation.

[0108] Optionally, the step of iteratively calculating the target control quantity based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module includes:

[0109] A step response experiment was conducted based on the initial denitrification prediction model to obtain a transfer function model in the frequency domain.

[0110] Transform the frequency domain transfer function model into a time domain state-space model;

[0111] The expression for the transfer function model is:

[0112] y(s)=G(s)·u(s)

[0113] Where u(s) represents the opening value of the ammonia injection regulating valve, y(s) represents the nitrogen oxide concentration at the denitrification outlet, and G(s) represents the transfer function;

[0114] The expression for the state-space model is:

[0115]

[0116] Wherein, A, B, and C are preset variable matrices that affect the nitrogen oxide concentration at the denitrification outlet, u(t) represents the input of the denitrification system at time t, x(t) represents the state of the denitrification system at time t, and y(t) represents the output of the denitrification system at time t.

[0117] Optionally, the target control quantity is calculated based on the performance index function of the optimal control algorithm, and the expression of the performance index function of the optimal control algorithm is:

[0118] J=[Δy(t) T RΔy(t)+Δu(t) T SΔu(t)+δΔu(t) T QδΔu(t)]

[0119] Where Q, R, and S represent the preset weight matrices of the variable matrix, Δy(t) represents the output change of the denitrification system at time t, Δu(t) represents the input change of the denitrification system at time t, and δ represents the preset time change operator.

[0120] Optionally, the target control quantity is obtained by iterative calculation based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module, including:

[0121] Determine the minimum function of the performance index function;

[0122] The target input change is calculated based on the minimum function.

[0123] Optionally, the determining module 203 is used to:

[0124] Determine the correspondence between the nitrogen oxide concentration at the denitrification outlet and the opening value of the ammonia injection control valve;

[0125] The target opening value is calculated based on the correspondence and the target nitrogen oxide concentration.

[0126] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0127] Figure 3 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Figure 3 As shown, the electronic device 300 may include a processor 301 and a memory 302. The electronic device 300 may also include one or more of a multimedia component 303, an input / output (I / O) interface 304, and a communication component 305.

[0128] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps in the aforementioned denitrification control method. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 302 or transmitted via communication component 305. The audio component also includes at least one speaker for outputting audio signals. I / O interface 304 provides an interface between processor 301 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 305 is used for wired or wireless communication between electronic device 300 and other electronic devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 305 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0129] In an exemplary embodiment, the electronic device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the denitrification control method described above.

[0130] In another exemplary embodiment, a computer-readable medium including program instructions is also provided, which, when executed by a processor, implement the steps of the denitrification control method described above. For example, the computer-readable medium may be the memory 302 including the program instructions described above, which may be executed by the processor 301 of the electronic device 300 to complete the denitrification control method described above.

[0131] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described denitrification control method when executed by the programmable device.

[0132] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0133] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0134] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A denitrification control method, characterized in that, include: Acquire the operating data of the denitrification system, including flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve; The running data is input into a pre-trained denitrification prediction model to obtain the denitrification prediction result output by the denitrification prediction model. The denitrification prediction result includes the target nitrogen oxide concentration at the denitrification outlet of the denitrification system for the next time period. The target opening value of the ammonia injection control valve is determined based on the target nitrogen oxide concentration. The ammonia injection valve is controlled according to the target opening value so that the denitrification system can perform denitrification. The denitrification prediction model includes a prediction module, an iteration module, and a memory module; The prediction module is used to predict the target nitrogen oxide concentration for the next time period corresponding to the denitrification outlet based on the operational data. The iterative module is used to perform multiple iterative calculations based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module to obtain the target control quantity; The memory module is used to store the historical prediction data of the prediction module and the historical iteration data of the iteration module, so as to provide the iteration module with iterative data for the next iteration calculation. The step of iteratively calculating the target control quantity based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module includes: A step response experiment was conducted based on the initial denitrification prediction model to obtain a transfer function model in the frequency domain. Transform the frequency domain transfer function model into a time domain state-space model; The expression for the transfer function model is: in, This indicates the opening value of the ammonia injection control valve. This indicates the nitrogen oxide concentration at the denitrification outlet. Represents the transfer function; The expression for the state-space model is: in, A , B , C This is a preset variable matrix that affects the nitrogen oxide concentration at the denitrification outlet. This indicates that the denitrification system is in t Input volume at any given time This indicates that the denitrification system is in t State quantity at any given time. This indicates that the denitrification system is in t Output at any given moment.

2. The method according to claim 1, characterized in that, The target control quantity is calculated based on the performance index function of the optimal control algorithm, and the expression of the performance index function of the optimal control algorithm is as follows: in, Q , R , S This represents the weight matrix of the preset variable matrix. This indicates that the denitrification system is in t The change in output at any given time. This indicates that the denitrification system is in t The change in input at any given time. This represents a preset time change operator.

3. The method according to claim 2, characterized in that, The target control quantity is obtained by iterative calculation based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module, including: Determine the minimum function of the performance index function; The target input change is calculated based on the minimum function.

4. The method according to claim 1, characterized in that, Determining the target opening value of the ammonia injection control valve based on the target nitrogen oxide concentration includes: Determine the correspondence between the nitrogen oxide concentration at the denitrification outlet and the opening value of the ammonia injection control valve; The target opening value is calculated based on the correspondence and the target nitrogen oxide concentration.

5. A denitrification control device, characterized in that, include: The acquisition module is used to acquire the operating data of the denitrification system, including the flue gas volume, denitrification temperature, and the opening value of the ammonia injection control valve. The prediction module is used to input the running data into a pre-trained denitrification prediction model to obtain the denitrification prediction result output by the denitrification prediction model. The denitrification prediction result includes the target nitrogen oxide concentration at the denitrification outlet of the denitrification system for the next time period. The determination module is used to determine the target opening value of the ammonia injection control valve based on the target nitrogen oxide concentration; The control module is used to control the ammonia injection valve according to the target opening value so that the denitrification system can perform denitrification. The denitrification prediction model includes a prediction module, an iteration module, and a memory module; The prediction module is used to predict the target nitrogen oxide concentration for the next time period corresponding to the denitrification outlet based on the operational data. The iterative module is used to perform multiple iterative calculations based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module to obtain the target control quantity; The memory module is used to store the historical prediction data of the prediction module and the historical iteration data of the iteration module, so as to provide the iteration module with iterative data for the next iteration calculation. The step of iteratively calculating the target control quantity based on the optimal control algorithm and the target nitrogen oxide concentration predicted by the prediction module includes: A step response experiment was conducted based on the initial denitrification prediction model to obtain a transfer function model in the frequency domain. Transform the frequency domain transfer function model into a time domain state-space model; The expression for the transfer function model is: in, This indicates the opening value of the ammonia injection control valve. This indicates the nitrogen oxide concentration at the denitrification outlet. Represents the transfer function; The expression for the state-space model is: in, A , B , C This is a preset variable matrix that affects the nitrogen oxide concentration at the denitrification outlet. This indicates that the denitrification system is in t Input volume at any given time This indicates that the denitrification system is in t State quantity at any given time. This indicates that the denitrification system is in t Output at any given moment.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method described in any one of claims 1-4.

7. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-4.

8. A denitrification system, characterized in that, Includes the electronic device as described in claim 7.

Images