Fine ammonia injection control system for coal-fired power plant

Abstract

The invention discloses a refined ammonia injection control system for a coal-fired power plant, and relates to the technical field of ammonia injection control systems for power plants. The real-time monitoring module is used for monitoring NOx concentration, oxygen content and temperature parameters in flue gas in real time and transmitting data to the central processing unit; and the prediction model construction module is used for constructing an NOx generation prediction model by utilizing a machine learning algorithm according to the historical data and the real-time monitoring data. Through the real-time monitoring module, the system can continuously track key parameters such as NOx concentration, oxygen content and temperature in flue gas; the control decision is ensured to be based on the latest environmental condition, so that the response speed and accuracy of the ammonia spraying system are improved; the NOx generation prediction model constructed by using a machine learning algorithm not only considers historical data, but also integrates real-time monitoring data, so that the model can accurately predict the NOx concentration change trend in a period of time in the future; and the system can predict and adapt to the future emission condition.

Description

Technical Field

[0001] The present invention relates to the technical field of ammonia injection control systems for power plants, and in particular to a refined ammonia injection control system for coal-fired power plants. Background Art

[0002] In the flue gas treatment process of coal-fired power plants, selective catalytic reduction (SCR) technology is widely used to reduce nitrogen oxides (NO x ) emissions. This technology uses ammonia or urea as a reducing agent to react with NO under the action of a catalyst. x A reaction occurs, converting it into harmless nitrogen and water vapor, thereby reducing pollution to the atmospheric environment. However, the traditional SCR system has problems such as low precision and slow response speed in ammonia injection control, resulting in a large amount of ammonia escape, which not only increases operating costs but may also cause secondary pollution.

[0003] After searching, the application scheme of Chinese patent application number CN202210600752.6 discloses a coal-fired power plant SCR denitrification ammonia injection measurement control system and method, the control system includes, a static mixer, an ammonia injection grid and a first partition mixer arranged in sequence in the horizontal section of the economizer outlet flue; the ammonia injection grid is arranged in one-to-one correspondence with the flue partition, and several ammonia injection grids are connected to the ammonia injection mother pipe through corresponding ammonia injection partition regulating valves, and the ammonia injection mother pipe is provided with an ammonia injection master regulating valve; the economizer outlet flue measurement system is arranged on the economizer outlet flue, and the inlet partition sampling tube is arranged at the denitrification inlet flue. The control system in the above patent has the following deficiencies: the real-time control capability is still insufficient and needs to be improved. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a refined ammonia injection control system for a coal-fired power plant.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A refined ammonia injection control system for a coal-fired power plant, comprising:

[0007] Real-time monitoring module: real-time monitoring of NO in flue gas x concentration, oxygen content, temperature parameters, and transmit the data to the central processing unit;

[0008] Prediction model building module: Based on historical data and real-time monitoring data, a machine learning algorithm is used to build a NOx generation prediction model to predict NOx in the future. x Concentration trend;

[0009] Dynamic adjustment module: The central processing unit dynamically adjusts the amount of ammonia injection according to the output results of the prediction model to ensure the balance of ammonia and NO x The best molar ratio of

[0010] Closed-loop control module: Through the feedback regulation mechanism, the ammonia injection strategy is adjusted in real time according to the NOx emission data provided by the downstream monitoring equipment to form a closed-loop control;

[0011] Safety protection module: When the system detects abnormal operating conditions, it automatically cuts off the ammonia supply and activates the emergency plan.

[0012] Preferably, the control method of the ammonia injection control system comprises the following steps:

[0013] S1: First, establish NO x Generate a prediction model, whose mathematical expression is:

[0014] NOx pred (t) = f(NOx past ,O2,T,Δt)

[0015] in, is the predicted NOx concentration, NO for history x Concentration data, O2 is oxygen content, T is temperature, Δt is the prediction time interval;

[0016] S2: Secondly, calculate the optimal ammonia injection amount, the calculation formula is:

[0017]

[0018] in, is the optimal ammonia injection amount, a is the ammonia nitrogen ratio, MW NOx NO x The molar mass, Q is the flue gas flow rate, η is the SCR reaction efficiency;

[0019] S3: Determine the ammonia injection position, considering the active temperature window of the catalyst, and its mathematical model is:

[0020]

[0021] in, and are the lowest and highest activity temperatures of the catalyst, is the reaction enthalpy change of ammonia, C p is the specific heat capacity of flue gas, Q in and Q out are the flue gas flow rates before and after ammonia injection, respectively;

[0022] S4: Implement closed-loop control, the control logic is:

[0023]

[0024] in, is the amount of ammonia injected after feedback adjustment, K p , K i , K d are proportional, integral, and differential gains respectively, For the setting of NO x Emission target value, is the actual measured NO x Emission value.

[0025] Preferably: the real-time monitoring module comprises:

[0026] Data acquisition unit: responsible for collecting NO in flue gas from sensors x Concentration, oxygen content, temperature data;

[0027] Data transmission unit: ensures that the collected data can be transmitted to the central processing unit in real time and accurately;

[0028] Data preprocessing unit: performs cleaning and normalization preprocessing operations on the original data to improve data quality.

[0029] Preferably: the prediction model building module comprises:

[0030] Historical data analysis unit: Analyze historical operation data and identify the impact of NO x Key factors for generation;

[0031] Model training unit: Use machine learning algorithms to train NO x Generate a predictive model;

[0032] Model Validation Unit: The accuracy and generalization ability of the model are evaluated through cross-validation method.

[0033] Preferably: the dynamic adjustment module comprises:

[0034] Parameter calculation unit: calculates the required optimal ammonia injection amount according to the output of the prediction model;

[0035] Position optimization unit: determines the best ammonia injection position to adapt to the active temperature window of the catalyst;

[0036] Strategy implementation unit: converts the calculated ammonia injection amount and position into control instructions and sends them to the actuator.

[0037] Preferably: the closed-loop control module comprises:

[0038] Feedback regulation unit: According to the NO provided by the downstream monitoring equipment xEmission data, real-time adjustment of ammonia injection strategy;

[0039] Performance evaluation unit: Regularly evaluate denitrification efficiency and ammonia escape, and optimize control parameters;

[0040] Adaptive adjustment unit: automatically adjusts the parameters of the PID controller according to changes in system performance.

[0041] Preferably: the security protection module comprises:

[0042] Abnormal detection unit: monitors the system operation status in real time and detects abnormal conditions in time;

[0043] Emergency response unit: automatically initiates emergency response plan when abnormality is detected;

[0044] Recording and reporting unit: records the occurrence and handling process of abnormal events and reports to relevant personnel.

[0045] Preferably, it also includes:

[0046] The backup route planning module automatically switches to the backup control strategy when the main control system fails or is abnormal, ensuring the continuous and stable operation of the ammonia injection system;

[0047] The intelligent optimization algorithm module performs global optimization on key parameters such as ammonia injection amount and ammonia injection position.

[0048] Preferably: the backup route planning module comprises:

[0049] Scenario analysis unit: Analyzes different control scenarios and parameters to provide a basis for the selection of backup routes;

[0050] Route selection unit: Based on intelligent algorithms, it selects the most suitable solution for the current working conditions from the preset alternative routes;

[0051] Switching execution unit: when the main control system fails, quickly switch to the backup route to ensure stable operation of the system;

[0052] The backup route planning selects the backup plan that best suits the current working conditions based on the preset control scenarios and parameters, specifically:

[0053]

[0054] Among them, R backup is the selected alternative route, R is the set of all available alternative routes, and T target Target NO x concentration and temperature, β is the weight coefficient used to balance the importance of NOx concentration and temperature.

[0055] Preferably: the intelligent optimization algorithm module comprises:

[0056] Parameter optimization unit: Use intelligent optimization algorithms to globally optimize key parameters;

[0057] Result evaluation unit: evaluate the optimized control effect to ensure that environmental protection requirements are met;

[0058] The optimization objective function of the intelligent optimization algorithm module is expressed as:

[0059]

[0060] Among them, w1, w2, and w3 are the weights of each item. is the actual NOx emission concentration, is the target NOx concentration setting value, For the cost of ammonia, Penalty emission Penalty costs for exceeding emission standards.

[0061] The beneficial effects of the present invention are:

[0062] 1. The present invention uses a real-time monitoring module, and the system can continuously track NO in the flue gas. x concentration, oxygen content, and temperature; ensuring that control decisions are based on the latest environmental conditions, thereby improving the response speed and accuracy of the ammonia injection system; using machine learning algorithms to build NO x The prediction model is generated by taking into account not only historical data but also real-time monitoring data, so that the model can accurately predict NO in the future. x Trending concentrations; enabling the system to anticipate and adapt to future emissions rather than just reacting to current conditions.

[0063] 2. The dynamic adjustment module of the present invention allows the system to adjust the amount and position of ammonia injection in real time according to the output results of the prediction model; ensuring the x The optimal molar ratio of the catalyst and the active temperature window of the catalyst are taken into consideration to optimize the ammonia injection position; this not only improves the denitrification efficiency, but also reduces ammonia escape and reduces operating costs.

[0064] 3. The closed-loop control module of the present invention uses a feedback adjustment mechanism to adjust the NO x Emissions data allows real-time adjustments to ammonia injection strategies; enabling the system to continuously optimize performance and maintain high efficiency even when external conditions change. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 The present invention provides a flow chart of a control method for a refined ammonia injection control system in a coal-fired power plant. DETAILED DESCRIPTION

[0066] The technical solution of the present invention is further described in detail below in conjunction with specific implementation methods.

[0067] Embodiment 1:

[0068] A refined ammonia injection control system for a coal-fired power plant, comprising:

[0069] Real-time monitoring module: This module is responsible for real-time monitoring of NO in flue gas x concentration, oxygen content, temperature and other key parameters, and transmit the data to the central processing unit;

[0070] Prediction model building module: Based on historical data and real-time monitoring data, machine learning algorithms are used to build NO x Generate a prediction model to predict NO in the future x Concentration trend;

[0071] Dynamic adjustment module: The central processing unit dynamically adjusts the amount of ammonia injection according to the output results of the prediction model to ensure the balance of ammonia and NO x The best molar ratio of , while taking into account the active temperature window of the catalyst, optimize the ammonia injection position;

[0072] Closed-loop control module: Through the feedback adjustment mechanism, according to the NO x Emission data, real-time adjustment of ammonia injection strategy to form a closed-loop control;

[0073] Safety protection module: When the system detects abnormal conditions, such as ammonia leakage, over-temperature, etc., it automatically cuts off the ammonia supply and activates the emergency plan.

[0074] The control method of the ammonia injection control system comprises the following steps:

[0075] S1: First, establish NO x Generate a prediction model, whose mathematical expression is:

[0076] NOx pred (t) = f(NOx past ,O2,T,Δt)

[0077] in, is the predicted NOx concentration, NO for history x Concentration data, O2 is oxygen content, T is temperature, Δt is the prediction time interval;

[0078] S2: Secondly, calculate the optimal ammonia injection amount, the calculation formula is:

[0079]

[0080] in, is the optimal ammonia injection amount, a is the ammonia nitrogen ratio, MW NOx NO x The molar mass, Q is the flue gas flow rate, η is the SCR reaction efficiency;

[0081] S3: Determine the ammonia injection position, considering the active temperature window of the catalyst, and its mathematical model is:

[0082]

[0083] in, and are the lowest and highest activity temperatures of the catalyst, is the reaction enthalpy change of ammonia, C p is the specific heat capacity of flue gas, Q in and Q out are the flue gas flow rates before and after ammonia injection, respectively;

[0084] S4: Implement closed-loop control, the control logic is:

[0085]

[0086] in, is the amount of ammonia injected after feedback adjustment, K p , K i , K d are proportional, integral and differential gains respectively, For the setting of NO x Emission target value, is the actual measured NO x Emission value.

[0087] Wherein, the real-time monitoring module includes:

[0088] Data acquisition unit: responsible for collecting NO in flue gas from sensors x Concentration, oxygen content, temperature and other data;

[0089] Data transmission unit: ensures that the collected data can be transmitted to the central processing unit in real time and accurately;

[0090] Data preprocessing unit: performs preprocessing operations such as cleaning and normalization on the original data to improve data quality.

[0091] Wherein, the prediction model building module includes:

[0092] Historical data analysis unit: Analyze historical operation data and identify the impact of NO x Key factors for generation;

[0093] Model training unit: Use machine learning algorithms (such as neural networks, support vector machines) to train NO x Generate a predictive model;

[0094] Model validation unit: Evaluate the accuracy and generalization ability of the model through methods such as cross-validation.

[0095] Wherein, the dynamic adjustment module includes:

[0096] Parameter calculation unit: calculates the required optimal ammonia injection amount according to the output of the prediction model;

[0097] Position optimization unit: determines the best ammonia injection position to adapt to the active temperature window of the catalyst;

[0098] Strategy implementation unit: converts the calculated ammonia injection amount and position into control instructions and sends them to the actuator.

[0099] Wherein, the closed-loop control module comprises:

[0100] Feedback regulation unit: According to the NO provided by the downstream monitoring equipment x Emission data, real-time adjustment of ammonia injection strategy;

[0101] Performance evaluation unit: Regularly evaluate denitrification efficiency and ammonia escape, and optimize control parameters;

[0102] Adaptive adjustment unit: automatically adjusts the parameters of the PID controller according to changes in system performance.

[0103] Wherein, the security protection module includes:

[0104] Abnormal detection unit: monitors the system operation status in real time and detects abnormal conditions in time;

[0105] Emergency response unit: automatically initiates emergency plans when an abnormality is detected, such as cutting off the ammonia supply;

[0106] Recording and reporting unit: records the occurrence and handling process of abnormal events and reports to relevant personnel.

[0107] Embodiment 2:

[0108] A refined ammonia injection control system for a coal-fired power plant, comprising:

[0109] Real-time monitoring module: This module is responsible for real-time monitoring of NO in flue gas x concentration, oxygen content, temperature and other key parameters, and transmit the data to the central processing unit;

[0110] Prediction model building module: Based on historical data and real-time monitoring data, machine learning algorithms are used to build NO xGenerate a prediction model to predict NO in the future x Concentration trend;

[0111] Dynamic adjustment module: The central processing unit dynamically adjusts the amount of ammonia injection according to the output results of the prediction model to ensure the balance of ammonia and NO x The best molar ratio of , while taking into account the active temperature window of the catalyst, optimize the ammonia injection position;

[0112] Closed-loop control module: Through the feedback adjustment mechanism, according to the NO x Emission data, real-time adjustment of ammonia injection strategy to form a closed-loop control;

[0113] Safety protection module: When the system detects abnormal conditions, such as ammonia leakage, over-temperature, etc., it automatically cuts off the ammonia supply and activates the emergency plan.

[0114] Also includes:

[0115] The backup route planning module automatically switches to the backup control strategy when the main control system fails or is abnormal, ensuring the continuous and stable operation of the ammonia injection system;

[0116] The intelligent optimization algorithm module globally optimizes key parameters such as ammonia injection amount and ammonia injection position.

[0117] Wherein, the backup route planning module includes:

[0118] Scenario analysis unit: Analyzes different control scenarios and parameters to provide a basis for the selection of backup routes;

[0119] Route selection unit: Based on intelligent algorithms, it selects the most suitable solution for the current working conditions from the preset alternative routes;

[0120] Switching execution unit: When the main control system fails, quickly switch to the backup route to ensure stable operation of the system.

[0121] The backup route planning is based on the preset control scenarios and parameters, and selects the backup solution that best suits the current working conditions, specifically:

[0122]

[0123] Among them, R backup is the selected alternative route, R is the set of all available alternative routes, and T target Target NO x concentration and temperature, β is the weight coefficient used to balance the importance of NOx concentration and temperature.

[0124] Wherein, the intelligent optimization algorithm module includes:

[0125] Parameter optimization unit: Use intelligent optimization algorithms to globally optimize key parameters;

[0126] Result evaluation unit: Evaluate the optimized control effect to ensure that environmental protection requirements are met.

[0127] The optimization objective function of the intelligent optimization algorithm module is expressed as:

[0128]

[0129] Among them, w1, w2, and w3 are the weights of each item. is the actual NOx emission concentration, is the target NOx concentration setting value, For the cost of ammonia, Penalty emission Penalty costs for exceeding emission standards.

[0130] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A refined ammonia injection control system for a coal-fired power plant, characterized in that: include: Real-time monitoring module: real-time monitoring of NO in flue gas x concentration, oxygen content, temperature parameters, and transmit the data to the central processing unit; Prediction model building module: Based on historical data and real-time monitoring data, a machine learning algorithm is used to build a NOx generation prediction model to predict NOx in the future. x Concentration trend; Dynamic adjustment module: The central processing unit dynamically adjusts the amount of ammonia injection according to the output results of the prediction model to ensure the balance of ammonia and NO x The best molar ratio of Closed-loop control module: Through the feedback regulation mechanism, the ammonia injection strategy is adjusted in real time according to the NOx emission data provided by the downstream monitoring equipment to form a closed-loop control; Safety protection module: When the system detects abnormal operating conditions, it automatically cuts off the ammonia supply and activates the emergency plan.

2. A refined ammonia injection control system for a coal-fired power plant according to claim 1, characterized in that: The control method of the ammonia injection control system comprises the following steps: S1: First, establish NO x Generate a prediction model, whose mathematical expression is: NOx pred (t)=f(NOx past ,O2,T,Δt) in, is the predicted NOx concentration, NO for history x Concentration data, O2 is oxygen content, T is temperature, Δt is the prediction time interval; S2: Secondly, calculate the optimal ammonia injection amount, the calculation formula is: in, is the optimal ammonia injection amount, a is the ammonia nitrogen ratio, MW NOx NO x The molar mass, Q is the flue gas flow rate, η is the SCR reaction efficiency; S3: Determine the ammonia injection position, considering the active temperature window of the catalyst, and its mathematical model is: in, and are the lowest and highest activity temperatures of the catalyst, is the reaction enthalpy change of ammonia, C p is the specific heat capacity of flue gas, Q in and Q out are the flue gas flow rates before and after ammonia injection, respectively; S4: Implement closed-loop control, the control logic is: in, is the amount of ammonia injected after feedback adjustment, K p , K i , K d are proportional, integral, and differential gains respectively, For the setting of NO x Emission target value, is the actual measured NO x Emission value.

3. A refined ammonia injection control system for a coal-fired power plant according to claim 2, characterized in that: The real-time monitoring module comprises: Data acquisition unit: responsible for collecting NO in flue gas from sensors x Concentration, oxygen content, temperature data; Data transmission unit: ensures that the collected data can be transmitted to the central processing unit in real time and accurately; Data preprocessing unit: performs cleaning and normalization preprocessing operations on the original data to improve data quality.

4. A refined ammonia injection control system for a coal-fired power plant according to claim 3, characterized in that: The prediction model building module includes: Historical data analysis unit: Analyze historical operation data and identify the impact of NO x Key factors for generation; Model training unit: Use machine learning algorithms to train NO x Generate a predictive model; Model Validation Unit: The accuracy and generalization ability of the model are evaluated through cross-validation method.

5. A refined ammonia injection control system for a coal-fired power plant according to claim 4, characterized in that: The dynamic adjustment module includes: Parameter calculation unit: calculates the required optimal ammonia injection amount according to the output of the prediction model; Position optimization unit: determines the best ammonia injection position to adapt to the active temperature window of the catalyst; Strategy implementation unit: converts the calculated ammonia injection amount and position into control instructions and sends them to the actuator.

6. A refined ammonia injection control system for a coal-fired power plant according to claim 5, characterized in that: The closed-loop control module comprises: Feedback regulation unit: According to the NO provided by the downstream monitoring equipment x Emission data, real-time adjustment of ammonia injection strategy; Performance evaluation unit: Regularly evaluate denitrification efficiency and ammonia escape, and optimize control parameters; Adaptive adjustment unit: automatically adjusts the parameters of the PID controller according to changes in system performance.

7. A refined ammonia injection control system for a coal-fired power plant according to claim 6, characterized in that: The security protection module comprises: Abnormal detection unit: monitors the system operation status in real time and detects abnormal conditions in time; Emergency response unit: automatically initiates emergency response plan when abnormality is detected; Recording and reporting unit: records the occurrence and handling process of abnormal events and reports to relevant personnel.

8. A refined ammonia injection control system for a coal-fired power plant according to claim 7, characterized in that: Also includes: The backup route planning module automatically switches to the backup control strategy when the main control system fails or is abnormal, ensuring the continuous and stable operation of the ammonia injection system; The intelligent optimization algorithm module performs global optimization on key parameters such as ammonia injection amount and ammonia injection position.

9. A refined ammonia injection control system for a coal-fired power plant according to claim 8, characterized in that: The backup route planning module comprises: Scenario analysis unit: Analyzes different control scenarios and parameters to provide a basis for the selection of backup routes; Route selection unit: Based on intelligent algorithms, it selects the most suitable solution for the current working conditions from the preset alternative routes; Switching execution unit: when the main control system fails, quickly switch to the backup route to ensure stable operation of the system; The backup route planning selects the backup plan that best suits the current working conditions based on the preset control scenarios and parameters, specifically: Among them, R backup is the selected alternative route, R is the set of all available alternative routes, and T target Target NO x concentration and temperature, β is the weight coefficient used to balance the importance of NOx concentration and temperature.

10. A refined ammonia injection control system for a coal-fired power plant according to claim 9, characterized in that: The intelligent optimization algorithm module includes: Parameter optimization unit: Use intelligent optimization algorithms to globally optimize key parameters; Result evaluation unit: evaluate the optimized control effect to ensure that environmental protection requirements are met; The optimization objective function of the intelligent optimization algorithm module is expressed as: Among them, w1, w2, and w3 are the weights of each item. is the actual NOx emission concentration, is the target NOx concentration setting value, For the cost of ammonia, Penalty emission Penalty costs for exceeding emission standards.

Images