Control Method for Full-Operating Condition Denitration System Based on Generalized Predictive Control and Intelligent Feedforward

Abstract

The present invention provides a control method for a full-condition denitration system based on generalized predictive control and intelligent feedforward, which includes the following steps: Using a neural network algorithm, a transfer function model is obtained according to a historical data set and input into a generalized predictive controller to obtain a main-loop controller. The main-loop controller is used for main-loop control to obtain a denitration inlet concentration prediction instruction, an ammonia injection amount prediction instruction, and a denitration outlet concentration; According to the ammonia injection amount prediction instruction, the denitration inlet concentration prediction instruction combined with an inlet concentration compensation algorithm, the denitration outlet concentration combined with a deviation protection logic, and the current ammonia injection amount combined with the historical optimal ammonia injection amount, a feedforward total controller is jointly obtained to control the feedforward loop and update the current ammonia injection amount. The control method provided by the present invention has good stability, reliability, strong prediction ability and self-adaptability, good control quality, and can achieve the optimal balance between denitration efficiency and economy.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal power generation, and particularly to a control method for a full-condition denitration system based on generalized predictive control and intelligent feedforward. Background Art

[0002] With the increasingly strict environmental protection regulations, thermal power units face higher requirements for nitrogen oxide (NOx) emission control. Selective catalytic reduction (SCR) denitration technology has been widely used due to its high efficiency. However, traditional control methods rely on fixed parameters or simple feedback, making it difficult to adapt to complex working conditions such as load fluctuations and fuel changes, resulting in fluctuations in denitration efficiency, increased ammonia slip, and rising operating costs. Existing methods have limitations in response speed and economy, and cannot balance environmental compliance and economic operation. Summary of the Invention

[0003] Aiming at the problems existing in the prior art, the present invention provides an intelligent denitration control method based on generalized predictive control and multiple feedforward control methods, aiming to improve the denitration efficiency and operating economy of thermal power generating units under full conditions.

[0004] To achieve the above object, the technical solution adopted by the present invention is as follows: A control method for a full-condition denitration system based on generalized predictive control and intelligent feedforward, comprising the following steps: obtaining a historical data set, a current input command, and a current ammonia injection amount based on a thermal power generating unit;

[0005] Using a neural network algorithm to obtain a transfer function model according to the historical data set;

[0006] Inputting the transfer function model into a generalized predictive controller to obtain a main loop controller; the optimization objective function of the main loop controller is:

[0007] ;

[0008] In the formula, is the optimization objective function, is the set value of the denitration outlet concentration, is the time, is the denitration outlet concentration, is the weight coefficient, is the change amount of the control variable;

[0009] Based on the main loop controller, obtaining a prediction command according to the current input command; the prediction command at least includes a denitration inlet concentration prediction command and an ammonia injection amount prediction command;

[0010] Controlling the main loop of the thermal power generating unit according to the prediction command to obtain at least current output data, the current output data at least including the denitration outlet concentration;

[0011] Based on the denitration inlet concentration prediction instruction, a first feedforward control is obtained according to the inlet concentration compensation algorithm;

[0012] Based on the denitration outlet concentration, a second feedforward control is obtained according to the deviation protection logic;

[0013] The historical optimal ammonia injection amount is obtained according to the historical data set;

[0014] A third feedforward control is obtained according to the current ammonia injection amount and the historical optimal ammonia injection amount;

[0015] A feedforward total controller is obtained according to the ammonia injection amount prediction instruction, the first feedforward control, the second feedforward control and the third feedforward control;

[0016] The feedforward loop of the thermal power generating unit is controlled according to the feedforward total controller and the current ammonia injection amount is updated.

[0017] In some embodiments, the historical data set includes a first historical data set and a second historical data set;

[0018] The first historical data set is used to obtain the transfer function model by using a neural network algorithm;

[0019] The second historical data set is used to obtain the historical optimal ammonia injection amount.

[0020] In some embodiments, the first historical data set includes a set of historical input data and a set of historical output data;

[0021] The historical input data includes historical load, historical coal feeding amount, historical ammonia injection flow rate, historical primary air damper opening and historical secondary air damper opening;

[0022] The historical output data includes historical denitration inlet concentration and historical denitration outlet concentration.

[0023] In some embodiments, the current input instruction includes a load instruction and a coal feeding amount instruction.

[0024] In some embodiments, the formula of the inlet concentration compensation algorithm is:

[0025] ;

[0026] In the formula, is the feedforward channel compensation value based on the prediction instruction, is the delay time from judging the change trend of the denitration inlet concentration to the change of the denitration outlet concentration, is a function related to both the load instruction and the coal feeding amount instruction, is the coal feeding amount command, is the load command.

[0027] In some embodiments, the step of obtaining the second feedforward control based on the denitration outlet concentration according to the deviation protection logic is as follows:

[0028] Obtain the sensitivity coefficient, the deviation protection threshold, and the outlet concentration set value;

[0029] Obtain the concentration change rate according to the denitration outlet concentration;

[0030] Judge whether the first condition is established according to the denitration outlet concentration, the deviation protection threshold, and the outlet concentration set value; the first condition is that the denitration outlet concentration is greater than the sum of the deviation protection threshold and the outlet concentration set value;

[0031] Judge whether the second condition is established according to the concentration change rate, the sensitivity coefficient, and the deviation protection threshold; the second condition is that the concentration change rate is greater than the product of the sensitivity coefficient and the deviation protection threshold;

[0032] When both the first condition and the second condition are established, trigger the emergency control strategy;

[0033] When the first condition is not established or the second condition is not established, do not trigger the emergency control strategy.

[0034] In some embodiments, the correction formula of the third feedforward control is:

[0035] ;

[0036] In the formula, is the correction signal, is the economic feedforward gain coefficient, is the historical optimal ammonia injection amount, is the current ammonia injection amount.

[0037] In some embodiments, the feedforward total controller is a weighted superposition of the ammonia injection amount prediction command, the output signal of the first feedforward control, the output signal of the second feedforward control, and the output signal of the third feedforward control.

[0038] In some embodiments, the second historical data set includes a set of operating parameters of the thermal power generation unit system under different operating conditions, and the historical transient ammonia injection amounts under different operating conditions.

[0039] In some embodiments, the feedforward total controller is used to control the ammonia injection regulating valve.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] 1. The present invention takes Generalized Predictive Control (GPC) as the core, and constructs a multi-level collaborative control system by combining inlet concentration compensation that fully considers the complex working conditions and dynamic characteristics of thermal power generating units, outlet concentration deviation protection based on the safety requirements of environmental protection indicators of thermal power generating units, and economic feedforward based on historical ammonia injection data. System identification is carried out through operating historical data modeling and neural network algorithms to form an accurate transfer function model, ensuring that the control system has good prediction ability and self-adaptability.

[0042] 2. The present invention ensures the precise control of the ammonia injection regulating valve through the weighted superposition of multiple control signals, ensuring that the environmental protection denitration control system can achieve good control quality under all working conditions, and achieving the optimal balance between denitration efficiency and economy.

[0043] 3. The present invention is applicable to the denitration control under the complex working conditions of thermal power units, and has good stability, reliability and popularization and application value. Description of the Drawings

[0044] Figure 1 It is a schematic diagram of the principle of the full-condition denitration system control method based on generalized predictive control and intelligent feedforward of the present invention. Detailed Embodiments

[0045] To clearly illustrate the technical characteristics of this solution, the following will combine the drawings and embodiments to detail the implementation manner of this application, so as to fully understand how this application uses technical means to solve technical problems and the implementation process of achieving corresponding technical effects and implement accordingly. Each feature in the embodiments of this application and in the embodiments can be combined with each other without conflict, and the formed technical solutions are all within the protection scope of this application.

[0046] In order to achieve the purpose of ensuring the economy of the power plant while meeting environmental friendliness, it is urgent to develop a denitration control method that adapts to all working conditions, has prediction ability and intelligent adjustment function, so as to improve the environmental protection performance and operation economy of thermal power units.

[0047] See Figure 1 , the embodiment of the present invention provides a full-condition denitration system control method based on generalized predictive control and intelligent feedforward, including the following steps: respectively obtaining a first historical data set, a second historical data set, a current input instruction and a current ammonia injection amount based on a thermal power generating unit;

[0048] The first historical dataset is a collection of historical data of the operation of a thermal power generation unit; in some embodiments, the first historical dataset includes a collection of historical input data and a collection of historical output data; the historical input data includes, but is not limited to, historical load, historical coal feeding amount, historical ammonia injection flow rate, historical primary air damper opening degree, and historical secondary air damper opening degree; the historical output data includes historical denitration inlet concentration and historical denitration outlet concentration;

[0049] Preprocess the first historical dataset to obtain a standard dataset; the preprocessing is used to eliminate industrial noise and gross value data to ensure the accuracy and reliability of the data;

[0050] First, remove industrial noise through wavelet packet processing, and then perform gross value data processing through the quartile method;

[0051] The steps of removing industrial noise by wavelet packet processing are as follows: for the collected data containing multi-dimensional operation parameters such as historical load, historical coal feeding amount, historical ammonia injection flow rate, historical primary air damper opening degree, historical secondary air damper opening degree, historical denitration inlet concentration, and historical denitration outlet concentration, decompose the signal into different frequency bands by wavelet packet decomposition, filter out high-frequency noise components through the threshold denoising algorithm, and then perform wavelet packet reconstruction on the signal to retain the effective information as the intermediate dataset. The method of removing industrial noise by wavelet packet processing can more accurately separate noise from useful signals compared with traditional filtering techniques, reduce data distortion, and ensure the high reliability and accuracy of the data in the model identification stage.

[0052] The steps of performing gross value data processing by the quartile method are as follows: calculate the first quartile (Q1) and the third quartile (Q3) of the intermediate dataset, determine the interquartile range (IQR = Q3 - Q1), and set 1.5 times IQR as the outlier detection threshold. Any data in the intermediate dataset that is lower than Q1 - 1.5IQR or higher than Q3 + 1.5IQR is determined as a gross value and removed. The method of performing gross value data processing by the quartile method does not require assumptions about the data distribution, is applicable to the variable working conditions of the operation data of the thermal power generation unit, effectively improves the data quality, and ensures the stability and generalization ability of the subsequent transfer function model.

[0053] Classify the standard dataset according to the input-output relationship to obtain a training dataset; the training dataset includes a standard input dataset and a standard output dataset. The standard input dataset is a collection of preprocessed historical input data, and the standard output dataset is a collection of preprocessed historical output data;

[0054] The neural network algorithm is adopted to obtain the transfer function model according to the training data set; the neural network algorithm is used for the model identification of the transfer function of the system (thermal power generating unit), and a transfer function model that can characterize the dynamic characteristics of the system is established. The model identification process includes selecting a suitable network structure, determining the learning rate, and training and validating the transfer function model to ensure that the transfer function model has good generalization ability under different working conditions; the neural network algorithm is adopted to model according to the transfer function of the training data set, so that the finally obtained transfer function model can effectively reflect the dynamic behavior of the thermal power generating unit and provide a reliable mathematical basis for the design of the overall control.

[0055] The transfer function model is input into the generalized predictive controller to obtain the main loop controller. The denitration outlet concentration is set as the feedback value of the main loop controller, and the denitration outlet concentration set value is the target value of the main loop controller; the main loop controller realizes the preliminary control of the main loop of the thermal power generating unit through key links such as the transfer function model, rolling optimization, and feedback correction in the generalized predictive controller; the optimization objective function of the main loop controller is:

[0056] ;

[0057] In the formula, is the optimization objective function, is the denitration outlet concentration set value, is the time, is the denitration outlet concentration, is the weight coefficient, is the change amount of the control variable, and the control variable is the ammonia injection amount.

[0058] Based on the main loop controller, a prediction instruction is obtained according to the current input instruction; the prediction instruction at least includes the denitration inlet concentration prediction instruction and the ammonia injection amount prediction instruction, and the prediction instruction also includes the denitration outlet concentration instruction; in some embodiments, the current input instruction includes the load instruction and the coal feeding amount instruction, and the control performance is optimized by adjusting the prediction time domain and control time domain parameters to ensure the system response speed and stability; the thermal power generating unit at least includes an instruction input unit, a denitration outlet, and an ammonia injection regulating valve, and the instruction input unit is used to input current input instructions such as the load instruction and the coal feeding amount instruction.

[0059] Controlling the main loop of the thermal power generating unit according to the prediction instruction to obtain at least the current output data, and the current output data at least includes the denitration outlet concentration, and the denitration outlet concentration monitored at the denitration outlet is controlled by the denitration outlet concentration instruction;

[0060] Based on the denitration inlet concentration and the denitration inlet concentration prediction instruction, the first feedforward control is obtained according to the inlet concentration compensation algorithm;

[0061] Considering the complex working conditions and dynamic characteristics of a thermal power generating unit, a first feed-forward control based on the predicted instruction of the denitration inlet concentration is added. The load instruction and the coal feeding amount instruction of the thermal power generating unit are used as input instructions, and the predicted instruction of the denitration inlet concentration is obtained through the main loop controller to judge the change trend of the denitration inlet concentration in advance; when the denitration inlet concentration has not changed significantly and the instrument calibration measurement data is inaccurate, a signal for adjusting the action of the ammonia injection regulating valve is output in advance to reduce the fluctuation of the denitration outlet concentration; in the inlet concentration compensation algorithm, a delay constant is set to adapt to the working conditions to suppress the sudden increase of the denitration outlet concentration. The formula of the inlet concentration compensation algorithm is:

[0062] ;

[0063] In the formula, is the feed-forward channel compensation value based on the predicted instruction, is the delay constant adapting to the working conditions, representing the delay time from judging the change trend of the denitration inlet concentration to the change of the denitration outlet concentration, is a function related to both the load instruction and the coal feeding amount instruction, is the coal feeding amount instruction, is the load instruction.

[0064] The delay constant adapting to the working conditions is identified by the neural network algorithm. This delay constant represents the advance time for the algorithm to predict the change of the denitration outlet concentration. Since this delay time is different under different working conditions, adjusting this delay constant can ensure that the algorithm performs excellently under all working conditions. When the predicted instruction of the denitration inlet concentration surges, a compensation value for the opening of the ammonia injection regulating valve is converted according to the predicted instruction of the denitration inlet concentration.

[0065] Based on the denitration outlet concentration, a second feed-forward control is obtained according to the deviation protection logic;

[0066] To ensure the safety of environmental protection indicators, a deviation protection mechanism based on the correction feedback of the denitration outlet concentration is designed as the second feed-forward control. By real-time monitoring the differential value of the denitration outlet concentration, that is, the concentration change rate, and judging the change trend of the denitration outlet concentration. When the denitration outlet concentration is greater than the sum of the deviation protection threshold and the outlet concentration set value, and the concentration change rate is greater than the product of the sensitivity coefficient and the deviation protection threshold, an emergency control strategy is triggered, that is, a signal for quickly adjusting the opening of the ammonia injection regulating valve is output to prevent the denitration outlet concentration from exceeding the standard. In some of these embodiments, the steps of obtaining the second feed-forward control based on the denitration outlet concentration according to the deviation protection logic are:

[0067] Obtain the sensitivity coefficient, the deviation protection threshold and the outlet concentration set value;

[0068] Obtain the rate of change of concentration based on the denitrification outlet concentration;

[0069] When the denitrification outlet concentration is greater than the sum of the deviation protection threshold and the outlet concentration set value, and the rate of change of concentration is greater than the product of the sensitivity coefficient and the deviation protection threshold, trigger the emergency control strategy;

[0070] Otherwise, do not trigger the emergency control strategy;

[0071] The deviation protection logic is:

[0072] ;

[0073] In the formula, is the rate of change of concentration, is the sensitivity coefficient, is the deviation protection threshold, is the denitrification outlet concentration, is the outlet concentration set value, is the emergency control strategy;

[0074] Obtain the historical optimal ammonia injection amount according to the second historical data set; In some embodiments, the second historical data set is historical ammonia injection data, and the second historical data set includes a set of operating parameters of the thermal power generation unit system under different working conditions, and the historical transient ammonia injection amounts under different working conditions.

[0075] Obtain the third feedforward control according to the current ammonia injection amount and the historical optimal ammonia injection amount; To improve the economy of the thermal power generation unit system, an economic feedforward control based on historical ammonia injection data is added. By analyzing the second historical data set, the historical optimal ammonia injection amount is calculated . In real-time control, compare the current ammonia injection amount with the historical optimal ammonia injection amount . After the error ( ) is weighted, it is output as a correction signal to avoid economic losses caused by too much or too little current ammonia injection amount. In some embodiments, the correction formula for the third feedforward control is:

[0076] ;

[0077] In the formula, is the correction signal, is the economic feedforward ammonia injection amount based on historical ammonia injection data, is the economic feedforward gain coefficient, is the historical optimal ammonia injection amount, is the current ammonia injection amount.

[0078] Obtain a feedforward total controller based on the ammonia injection amount prediction instruction, the first feedforward control, the second feedforward control, and the third feedforward control; in some embodiments, the feedforward total controller is a weighted superposition of the ammonia injection amount prediction instruction, the output signal of the first feedforward control, the output signal of the second feedforward control, and the output signal of the third feedforward control; the weighted superposition formula is:

[0079] ;

[0080] In the formula, is the final output ammonia injection amount, , , , are adjustable weighting coefficients respectively, is the ammonia injection amount prediction instruction, is the feedforward channel compensation value based on the prediction instruction, represents the output signal of the first feedforward control, is the deviation protection ammonia injection amount based on the correction feedback of the denitration outlet concentration, represents the output signal of the second feedforward control, is the economic feedforward ammonia injection amount based on historical ammonia injection data, represents the output signal of the third feedforward control;

[0081] Control the feedforward loop of the thermal power generating unit according to the feedforward total controller and update the current ammonia injection amount; in some embodiments, the feedforward total controller is used to control the ammonia injection regulating valve.

[0082] Perform weighted superposition on the output signals of the above-mentioned ammonia injection amount prediction instruction, the first feedforward control, the second feedforward control, and the third feedforward control, and finally act on the ammonia injection regulating valve. By reasonably configuring the weights of each control method, ensure that the thermal power generating unit system has good control quality under all working conditions, achieve the optimal balance between denitration efficiency and economy, meet the environmental protection emission standards, and reduce the operation cost.

[0083] Calculation example:

[0084] Put the full-condition denitration system control method based on generalized predictive control and intelligent feedforward of the present disclosure into a certain power plant, and the control target is to ensure that the hourly average value of the NOx concentration discharged from the thermal power generating unit meets the environmental protection requirement of 30 mg / m 3 while ensuring a certain economy.

[0085] Before the input, the hourly average value of the NOx concentration discharged from the thermal power generating unit was 15.7 mg / m 3 , and the dynamic fluctuation range of the NOx concentration was about 50 mg / m 3 ; after the input, the NOx concentration discharged from the unit was 25.6 mg / m3 , the dynamic fluctuation range is about 20 mg / m 3 , significantly reducing the ammonia injection volume. While ensuring environmental friendliness, the economy of the power plant is guaranteed.

[0086] Finally, it should be noted that the above content is only used to illustrate the technical solution of the present invention, rather than limiting the protection scope of the present invention. Any simple modification or equivalent replacement made by those of ordinary skill in the art to the technical solution of the present invention shall not depart from the essence and scope of the technical solution of the present invention.

Claims

1. A full-condition denitrification system control method based on generalized predictive control and intelligent feedforward, characterized in that: The following steps are involved: Based on the thermal power generating units, historical data sets, current input instructions and current ammonia injection amount are respectively obtained; Using a neural network algorithm, a transfer function model is obtained based on the historical data set; The transfer function model is input into the generalized predictive controller to obtain the main loop controller; the optimization objective function of the main loop controller is: ； In the formula, To optimize the objective function, the optimization objective function is to minimize the function. is the set value of denitrification outlet concentration, For time, is the denitrification outlet concentration, is the weight coefficient, is the change of the controlled variable, the controlled variable is the amount of ammonia injection; Based on the main loop controller, a prediction instruction is obtained according to the current input instruction; the prediction instruction at least includes a denitration inlet concentration prediction instruction and an ammonia injection amount prediction instruction; Control the main circuit of the thermal power generating set according to the prediction instruction to at least obtain current output data, wherein the current output data at least includes a denitration outlet concentration; Based on the denitration inlet concentration prediction instruction, a first feedforward control is obtained according to an inlet concentration compensation algorithm; Based on the denitration outlet concentration, obtaining a second feedforward control according to a deviation protection logic; Obtaining a historical optimal ammonia injection amount according to the historical data set; Obtaining a third feedforward control according to the current ammonia injection amount and the historical optimal ammonia injection amount; Obtaining a feedforward master controller according to the ammonia injection amount prediction instruction, the first feedforward control, the second feedforward control and the third feedforward control; The feedforward loop of the thermal power generator set is controlled according to the feedforward master controller and the current ammonia injection amount is updated.

2. The full-operating-condition denitration system control method based on generalized predictive control and intelligent feedforward according to claim 1 is characterized in that: The historical data set includes a first historical data set and a second historical data set; The first historical data set is used to obtain the transfer function model using a neural network algorithm; The second historical data set is used to obtain the historical optimal ammonia injection amount.

3. The full-condition denitration system control method based on generalized predictive control and intelligent feedforward according to claim 2 is characterized in that: The first historical data set includes a set of historical input data and a set of historical output data; The historical input data includes historical load, historical coal feed rate, historical ammonia injection flow rate, historical primary air door opening and historical secondary air door opening; The historical output data includes historical denitrification inlet concentration and historical denitrification outlet concentration.

4. The full-operating-condition denitration system control method based on generalized predictive control and intelligent feedforward according to claim 3 is characterized in that: The current input command includes a load command and a coal supply quantity command.

5. The full-operating-condition denitration system control method based on generalized predictive control and intelligent feedforward according to claim 4 is characterized in that: The formula of the inlet concentration compensation algorithm is: ； In the formula, is the feedforward channel compensation value based on the predicted instruction, It is the delay time from judging the concentration change trend of denitrification inlet to the change of denitrification outlet concentration. is a function related to both load command and coal supply command. For coal feeding quantity instruction, For load instructions.

6. The full-operating-condition denitration system control method based on generalized predictive control and intelligent feedforward according to claim 5 is characterized in that: Based on the denitration outlet concentration, the steps of obtaining the second feedforward control according to the deviation protection logic are: Obtain sensitivity coefficient, deviation protection threshold and outlet concentration setting value; Obtaining a concentration change rate according to the denitration outlet concentration; Determine whether a first condition is met according to the denitration outlet concentration, the deviation protection threshold and the outlet concentration setting value; the first condition is that the denitration outlet concentration is greater than the sum of the deviation protection threshold and the outlet concentration setting value; Determining whether a second condition is met is obtained according to the concentration change rate, the sensitivity coefficient and the deviation protection threshold; the second condition is that the concentration change rate is greater than the product of the sensitivity coefficient and the deviation protection threshold; When both the first condition and the second condition are met, triggering an emergency control strategy; When the first condition is not met or the second condition is not met, the emergency control strategy is not triggered.

7. The full-operating-condition denitration system control method based on generalized predictive control and intelligent feedforward according to claim 6 is characterized in that: The correction formula of the third feedforward control is: ； In the formula, To correct the signal, is the economic feedforward gain coefficient, The best ammonia injection amount in history. is the current ammonia injection amount.

8. The method for controlling a denitration system under all operating conditions based on generalized predictive control and intelligent feedforward according to claim 1 is characterized in that: The feedforward master controller is a weighted superposition of the ammonia injection amount prediction instruction, the output signal of the first feedforward control, the output signal of the second feedforward control, and the output signal of the third feedforward control.

9. The method for controlling a denitration system under all operating conditions based on generalized predictive control and intelligent feedforward according to claim 2 is characterized in that: The second historical data set includes a set of system operating parameters of the thermal power generating set under different operating conditions, and historical transient ammonia injection amounts under different operating conditions.

10. The method for controlling a denitration system under all operating conditions based on generalized predictive control and intelligent feedforward according to claim 1, characterized in that: The feedforward master controller is used to control the ammonia injection regulating valve.

Images