A garbage incineration SNCR and SCR denitration synergistic control method fusing model prediction and expert evaluation

By integrating model prediction and expert evaluation methods during waste incineration, the ammonia injection flow rate or valve opening of SNCR and SCR denitrification systems was optimized, solving the problem of coordinated control of SNCR and SCR denitrification systems, achieving efficient and stable NOx emission control, and improving the operation and management level of waste incineration enterprises.

CN122386689APending Publication Date: 2026-07-14SOUTH CHINA UNIV OF TECH +1

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SOUTH CHINA UNIV OF TECH
Filing Date
2026-04-22
Publication Date
2026-07-14

Smart Images

  • Figure CN122386689A_ABST
    Figure CN122386689A_ABST
Patent Text Reader

Abstract

The application discloses a garbage incineration SNCR and SCR denitration synergic control method combining model prediction and expert evaluation, and comprises the following steps: establishing a NOx emission concentration trend prediction model and predicting the NOx emission concentration at a future time; calculating the ammonia injection flow or valve opening value of the SNCR denitration system based on the model prediction; calculating the weight of the ammonia injection flow or valve opening adjustment of the SNCR denitration system; calculating the final ammonia injection flow or valve opening adjustment value of the SNCR denitration system; calculating the ammonia injection flow or valve opening value of the SCR denitration system based on the model prediction; calculating the weighted ammonia injection flow or valve opening adjustment value of the SCR denitration system; calculating the ammonia injection flow or valve opening adjustment amount of the SCR denitration system based on the feedback adjustment; calculating the weight of the ammonia injection flow or valve opening adjustment of the SCR denitration system; calculating the final ammonia injection flow or valve opening adjustment value of the SCR denitration system; and controlling the ammonia injection flow or valve opening of the SNCR and SCR denitration systems. The application can realize the efficient synergy of the two systems.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention belongs to the field of waste incineration, and specifically relates to a method for synergistic control of SNCR and SCR denitrification in waste incineration that integrates model prediction and expert evaluation. Background Technology

[0002] The massive amount of municipal solid waste, if not treated promptly and effectively, will not only pollute water, soil, and air, but also seriously affect people's health and living environment. Therefore, the reduction, resource recovery, and harmless treatment of municipal solid waste are crucial links in the sustainable development of the ecological environment. Waste-to-energy incineration technology involves burning municipal solid waste in an incinerator and using the generated heat to generate electricity, making it an important means of achieving waste reduction, resource recovery, and harmless treatment. However, while vigorously developing municipal solid waste incineration technology, we also face the environmental pollution problems caused by the waste incineration process. Among these, nitrogen oxides (NOx) are one of the main pollutants, and their large-scale emissions exacerbate the formation of acid rain, photochemical smog, regional fine particulate matter pollution, and haze, posing a significant threat to human health and survival.

[0003] To reduce the impact of NOx emissions from waste-to-energy incineration on the ecological environment, my country has formulated and implemented stringent environmental emission standards. In recent years, local governments have also actively promoted ultra-low NOx emissions from waste incineration processes. Selective non-catalytic reduction (SNCR) denitrification technology, characterized by low initial investment and low operating costs, has been widely applied in flue gas denitrification processes during waste incineration. However, with the deepening of ecological civilization construction and increasingly stringent environmental emission standards, SNCR technology alone is no longer sufficient to meet the higher requirements for ultra-low NOx emissions. Against this backdrop, selective catalytic reduction (SCR) technology, due to its higher denitrification efficiency and more stable operating performance, will become an important technical means for waste incineration plants to further achieve deep denitrification. However, due to the complex variations in waste characteristics, the reliance on manual or traditional PID control methods, and the lack of effective synergy between SNCR and SCR denitrification systems, coupled with the significant delay and strong hysteresis characteristics of the denitrification process, the NOx emission control accuracy of the SNCR and SCR dual denitrification system is low, with large fluctuations, high material consumption, and significant ammonia slip, seriously affecting the safety and economy of the unit operation. Therefore, researching intelligent control methods for synergistic denitrification of SNCR and SCR in waste incineration processes is of great significance for improving the safe, stable, economical, and environmentally friendly operation and management of NOx emissions from waste incineration plants.

[0004] Zhou Hongqiang disclosed an intelligent control system and method for ammonia injection in SNCR denitrification of cement kilns in Chinese invention patent CN111665711A. This invention includes a host computer, alarm system, PLC controller, data acquisition module, output control module, frequency converter, and ammonia spraying pump. The main control scheme involves collecting and analyzing the changing trends of relevant parameters such as NOx emission feedback values, frequency converter frequency feedback values, ammonia pump flow feedback values, decomposer coal feed feedback values, and sludge feed feedback values ​​to calculate and adjust the frequency converter frequency, thereby regulating the ammonia spraying volume. This invention is applicable to SNCR denitrification systems in dry-process cement kilns.

[0005] Yang Ming et al. disclosed an automatic control method for the ammonia water spray volume of SNCR denitrification in a kiln in Chinese invention patent CN106178908A. The basic principle is to calculate the output value using a PID control algorithm based on the emission concentration detection feedback value and the concentration target value, and at the same time automatically calculate the output compensation value based on the temperature of the spray zone.

[0006] Sun Yangyang et al. disclosed a control device for an SNCR denitrification system of a coal-fired boiler in Chinese invention patent CN107670474B. The device mainly includes a reducing agent injection device, a denitrification device, and a PID control device. The denitrification control principle of this device is mainly to detect the NOx concentration at the economizer outlet and calculate the deviation from the NOx control target value. Based on the range of the deviation, proportional control, proportional-derivative control, and proportional-derivative-integral control are selected.

[0007] Liao Yanfen et al. disclosed an SNCR denitrification control system for an industrial boiler in Chinese invention patent CN111459109A. The system mainly comprises an execution layer, a sensing layer, and a control layer. The execution layer includes an ammonia injection regulating valve, an electromagnetic flowmeter, a spray gun, and an air compressor. The sensing layer includes a dynamic flue gas volume measurement module, primarily used to collect the NO and O2 content within the furnace. The control layer is connected to the ammonia injection regulating valve, electromagnetic flowmeter, spray gun, air compressor, and sensing layer, and is used to control the spray gun to inject reducing agent into the furnace. The main control principle is to collect the NO and O2 content and flue gas flow information within the furnace to calculate the amount of reducing agent to be injected.

[0008] Liu Depeng et al. disclosed an automatic control method and system for SNCR denitrification in Chinese invention patent CN111135683B, which mainly includes a control module, an ammonia pump, a nitrogen oxide acquisition module, and a PID function module. The control approach is to first adjust the ammonia flow rate until the nitrogen oxide concentration reaches the standard. Then, in ammonia control mode, this adjusted ammonia flow rate serves as the target value for the PID control of the ammonia injection valve. In nitrogen oxide control mode, it is determined whether the deviation between the NOx setpoint and the emission value is within the fluctuation range. If it is within the range, the ammonia injection quantity is controlled near the previous injection quantity value through the PID control of the ammonia injection valve. If it is not within the fluctuation range, the ammonia flow rate setpoint is calculated and controlled by the PID regulation of the ammonia injection valve.

[0009] Zhu Liang et al. disclosed a model-based SNCR control system in Chinese Invention Publication Patent CN110652856A. The system mainly includes a data acquisition device for collecting process data related to the SNCR reaction process; and a model parameter optimization unit, comprising a model processing unit and a parameter optimization unit. The model processing unit uses a dynamic flue gas treatment model to calculate output variables related to the control parameters of the SNCR using the process data as input variables. The parameter optimization unit calculates the optimized control parameters of the SNCR based on the output variables, thereby achieving automatic control of the SNCR.

[0010] Fan Wanmei et al. disclosed a highly efficient method for precise control of ammonia flow rate in Chinese invention patent CN109833773A. The main control idea is to determine the boiler operating status based on the unit load command and the variable load rate: when the unit is running in a variable load state, the fuzzy control system is called; when the unit is running in a constant load state, the improved cascade PID control system is called.

[0011] Dong Chen et al. disclosed a control method for an SNCR denitrification system in a coal-fired power unit in Chinese Invention Publication Patent CN112516767A. The control approach involves acquiring the urea solution flow rate and diluted demineralized water pressure values ​​in each metering module under different loads, as well as the NOx concentration at the SNCR outlet, and constructing a database based on this data. During actual unit operation, based on the current unit load, the corresponding urea solution flow rate and diluted demineralized water pressure values ​​are retrieved from the database. Then, the urea solution flow rate and diluted demineralized water pressure values ​​in the metering modules are adjusted to match the values ​​retrieved from the database. Furthermore, the urea solution flow rate in the metering modules is corrected based on the currently measured NOx concentration at the SNCR outlet, ensuring that the measured NOx concentration at the SNCR outlet matches the NOx concentration at the SNCR outlet corresponding to the current load in the database.

[0012] Hong Yizhou et al. disclosed a fuzzy control method and system for denitrification of flue gas from waste incineration in Chinese invention patent CN106054608A. The main control idea is to use the deviation between the NOx concentration detection value and the given value and the rate of change of the deviation as fuzzy input variables for fuzzy control. Based on the fuzzy input, fuzzy reasoning, decision-making and defuzzification are performed to obtain the control output. The output is output to the ammonia water distribution controller to control the flow rate of the upper and lower layers of ammonia water.

[0013] Dong Changliang et al. disclosed a precise control method for non-nitrification reaction (SNCR) in waste incineration based on pre-dynamic prediction using a mechanistic model in Chinese invention patent CN120180770B. The main idea is to establish a thermodynamic-combustion coupled model of the incinerator by running big data, and then use the energy conservation equation, radiation transfer equation, and CFD inverse solution to invert the flue gas temperature and flow field velocity vectors to achieve three-dimensional flow field reconstruction and axial temperature field estimation. Subsequently, the spray gun parameters are optimized using a particle swarm optimization algorithm to achieve a multi-objective balance between denitrification efficiency and ammonia slip. Finally, the spray gun flow rate, angle, and layout are dynamically adjusted based on the optimized parameters.

[0014] Yang Jing et al. disclosed a reinforcement learning-based collaborative control method for incineration pollution in Chinese invention patent CN120650717A. The main idea is to establish a multi-objective prediction model by real-time collection of data such as combustion temperature, flue gas residence time, denitrification agent injection rate, fly ash metal content, and dioxin / polycyclic aromatic hydrocarbon concentration. With the objectives of minimizing pollutant emissions, maximizing fly ash metal content, and minimizing resource recovery costs, a reinforcement learning algorithm is used to determine the optimal combustion air ratio, secondary air velocity, and denitrification injection timing, thereby guiding the operation of the incinerator.

[0015] Sun Hongzuo et al. disclosed a dynamic collaborative optimization control method for denitrification in a waste incinerator in Chinese invention patent CN120361695B. The main idea is to identify the stable operating conditions, variable load conditions, and waste composition fluctuation conditions of the waste incinerator through membership functions. Simultaneously, based on different operating conditions, a predictive model based on sliding autoregression is established, and corresponding model predictive control strategies are developed.

[0016] Yang Hong et al. disclosed an automatic ammonia injection adjustment boiler SNCR denitrification control method and system in Chinese invention patent CN120644046A. The main idea is to dynamically adjust the spray gun flow rate by monitoring the temperature and humidity gradient and real-time temperature value of the longitudinal section of the furnace. Simultaneously, the atomization pressure and injection angle of the spray gun are optimized based on the inlet / outlet NOx concentration and ammonia slip detection values.

[0017] Zou Tingbiao et al. disclosed an automatic adjustment method and system for SNCR denitrification based on multi-parameter coupling optimization in Chinese invention patent CN120669535A. The main idea is to establish a multi-parameter coupling relationship model based on historical operating data and machine learning algorithms to predict denitrification efficiency and ammonia consumption. Simultaneously, based on the predicted denitrification efficiency and ammonia consumption, as well as preset denitrification efficiency targets and ammonia consumption constraints, optimization algorithms such as particle swarm optimization and genetic algorithms are used, along with the multi-parameter coupling relationship model, to obtain the currently predicted optimal ammonia injection rate, ammonia injection temperature, and ammonia injection angle. Furthermore, the ammonia injection angle is automatically adjusted based on the obtained flue gas flow rate change rate, NOx concentration distribution standard deviation, and ammonia slip exceedance value.

[0018] Zhou Bihua disclosed a predictive control method for denitrification based on LSTM and PINN in Chinese invention patent CN120502228A. The main idea is to collect operational data from the SCR denitrification system for sintering waste gas in the steel industry, including inlet NOx concentration, outlet NOx concentration, inlet flue gas flow rate, oxygen content, ammonia injection rate, catalyst activity, reactor temperature, dilution air flow fluctuation, and hot blast furnace heating efficiency. This data is then combined with a long short-term memory neural network and a PINN network to predict the outlet NOx concentration and ammonia slip for the next 2-3 minutes. Based on this, an intelligent control strategy based on reinforcement learning is developed.

[0019] From the perspective of control methods, the existing denitrification control strategies mainly include the following two types: (1) Operators adjust the ammonia injection rate by observing the NOx emission concentration value and combining their own experience, so as to improve the economic efficiency of the denitrification system operation while ensuring that the NOx emission concentration meets the environmental emission standards. (2) Cascade PID control, which calculates the ammonia injection rate setting value by using the deviation between the actual value of the NOx emission concentration and the target set value. At the same time, combined with the PID of the ammonia injection valve, the actual ammonia flow rate is controlled near the ammonia injection rate setting value. (3) Model prediction-based optimization control method, which predicts the future NOx emission concentration by introducing a mathematical model and combining it with the corresponding optimization control strategy to achieve accurate and efficient operation control of the denitrification system. From the perspective of control mode, the existing SNCR and SCR denitrification systems operate independently and there is no corresponding collaborative control method.

[0020] Due to the complex variations in waste characteristics and the significant delays and hysteresis inherent in denitrification, denitrification control in waste incinerators, primarily relying on manual control and traditional PID control, yields poor results. While model-based predictive optimization control methods can improve control performance to some extent, they are only applied to single denitrification systems such as SNCR or SCR, with limited research and application in dual denitrification systems. Furthermore, the lack of effective synergy between SNCR and SCR denitrification leads to problems such as low control accuracy, large fluctuations in NOx emissions, and significant material waste. Summary of the Invention

[0021] The purpose of this invention is to solve the problems of low control synergy, poor economy, and large fluctuations in waste incineration SNCR and SCR dual denitrification systems that rely mainly on manual control and traditional PID control. This invention provides a waste incineration SNCR and SCR denitrification synergistic control method that integrates model prediction and expert evaluation. It uses model prediction for proactive regulation to eliminate the effects of large delays and lags, and dynamically optimizes the adjustment weight of ammonia injection for both systems by evaluating the ammonia consumption and NOx emission status of the SNCR and SCR denitrification systems in real time. This achieves efficient synergy between the two systems, thereby effectively improving the safety, economy, and environmental protection of the waste incinerator dual denitrification system.

[0022] To achieve the objectives of this invention, the present invention provides a method for the synergistic control of SNCR and SCR denitrification in waste incineration, which integrates model prediction and expert evaluation, comprising the following steps: Step 1: First, obtain The system collects operational parameters from prior time points, including grate air volume, secondary air volume, furnace temperature, furnace oxygen content, ammonia flow rate in the SNCR and SCR denitrification systems, inlet and outlet temperatures of the SCR denitrification system, and NOx emission concentration. Then, it reconstructs the time series of these parameters using a mutual information algorithm. Finally, it establishes a NOx emission concentration trend prediction model based on linear algorithms such as partial least squares or nonlinear algorithms such as neural networks, enabling predictions for future NOx emission concentrations. +1、 +2 and Accurate prediction of NOx emission concentration at +3 time.

[0023] Step 2: Calculate the model predictions +1、 +2 and Average NOx emission concentration at +3 time and calculate With control target value Deviation between Based on piecewise functions Calculate the ammonia injection flow rate or valve opening value of the SNCR denitrification system. ; Step 3: Expert evaluation calculates the weight of ammonia injection flow rate or valve opening adjustment in the SNCR denitrification system. This involves calculating the hourly average NOx emission concentration relative to the control target value. G Deviation between Combined with piecewise functions Obtain the ammonia injection flow rate or valve opening adjustment weight of the SNCR denitrification system. .

[0024] Step 4: Calculate the final ammonia injection flow rate or valve opening adjustment value for the SNCR denitrification system; Step 5: Calculate the model predictions respectively. +1、 +2 and The deviation between NOx emission concentration and control target value at time +3 , and Combining piecewise nonlinear functions , , , Calculate the ammonia injection flow rate or valve opening value of the three SCR denitrification systems. , and The weighted calculation is based on model predictions of ammonia injection flow rate or valve opening adjustment value in the SCR denitrification system.

[0025] Step 6: Calculate the average actual NOx emission concentration from the chimney within a certain time window and the control target value. Average deviation between Combined with PID1, calculate the ammonia injection flow rate or valve opening adjustment amount of the SCR denitrification system based on feedback control. ; Step 7: Expert evaluation calculates the weight of ammonia injection flow rate or valve opening adjustment in the SCR denitrification system. This involves calculating the average actual ammonia injection flow rate or valve opening of the SCR denitrification system within a certain time window. Total ammonia consumption , combined Based on piecewise nonlinear functions Calculate the ammonia injection flow rate or valve opening adjustment weight of the SCR denitrification system. .

[0026] Step 8: Calculate the final ammonia injection flow rate or valve opening adjustment value of the SCR denitrification system in real time; Step 9: Real-time calculation The difference between the actual ammonia injection flow rate or valve opening of the SNCR denitrification system and the actual ammonia injection flow rate or valve opening. The difference between the actual ammonia injection flow rate or valve opening of the SCR denitrification system and the actual ammonia injection flow rate or valve opening is used in conjunction with PID2 and PID3 to control the ammonia injection flow rate or valve opening of the SNCR and SCR denitrification systems.

[0027] The present invention also provides a waste incineration SNCR and SCR denitrification synergistic control system that integrates model prediction and expert evaluation.

[0028] The present invention also provides a computer device.

[0029] The present invention also provides a computer-readable storage medium.

[0030] Compared with the prior art, the present invention can achieve at least the following beneficial effects: This invention, by comprehensively considering the economic efficiency, environmental friendliness, and synergy of SNCR and SCR denitrification, develops an adaptive synergistic composite control strategy that combines model-predictive advance control with dynamic optimization of SNCR and SCR ammonia injection weights based on real-time expert evaluation. This strategy effectively eliminates the large delay and inertia effects of the denitrification system in the waste incineration process, while fully realizing the synergistic operation of SNCR and SCR, thereby improving the intelligent operation and management level of the enterprise's denitrification system. Attached Figure Description

[0031] Figure 1 This is a schematic diagram of the structure of an embodiment of the present invention.

[0032] Figure 2 This is a block diagram of the components of an embodiment of the present invention.

[0033] Figure 3 This is a diagram illustrating the implementation steps of an embodiment of the present invention. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0035] Please see Figure 1 The present invention provides a method for synergistic control of SNCR and SCR denitrification in waste incineration by integrating model prediction and expert evaluation, comprising the following steps: Step 1: First, obtain The operating parameters before the specified time point are then analyzed. Subsequently, the operating parameters are reconstructed into a time series based on the mutual information algorithm. Finally, a NOx emission concentration trend prediction model is established based on linear algorithms such as partial least squares or nonlinear algorithms such as neural networks, and predictions are made for future NOx emissions. +1、 +2 and Accurate prediction of NOx emission concentration at +3 time.

[0036] In one embodiment, the operating variables selected in step 1 for constructing the NOx emission concentration trend prediction model include, but are not limited to, the exhaust air volume at each stage of the incinerator, the secondary air volume, the furnace temperature, the oxygen content in the furnace, the ammonia flow rate of the SNCR denitrification system, the ammonia flow rate of the SCR denitrification system, the inlet and outlet temperatures of the SCR denitrification system, and the NOx emission concentration value.

[0037] In one embodiment, the NOx emission concentration trend prediction model construction process in step 1 is as follows: Step 1.1: Obtain The following data were collected before the specified time: incinerator drying grate air volume (No. 1), combustion grate 1 air volume (No. 2), combustion grate 2 air volume (No. 3), burnout grate air volume (No. 4), secondary air volume (No. 5), furnace average temperature (No. 6), furnace oxygen content (No. 7), SNCR denitrification system ammonia flow rate (No. 8), SCR denitrification system ammonia flow rate (No. 9), SCR denitrification system inlet and outlet temperatures (Nos. 10 and 11), and NOx emission concentration (No. 12). One running variable, setting the time series reconstruction length of the running variable. The upcoming Each running variable Time's up Data at each time point is used as input to the NOx emission concentration trend prediction model. Based on the mutual information nonlinear correlation analysis algorithm, the operating variables after time series reconstruction are calculated with... The correlation between NOx emission concentrations at time +1 is calculated, and the time series with the highest correlation is reconstructed to its length. The optimal time series reconstruction length is determined by the above-mentioned operating variables. =2, =2, =2, =2, =2, =3, =3, =3, =1, =1, =1, =2. The time series reconstruction of the obtained runtime variables is shown below:

[0038] , These are the time series representations of the running variables numbered 1 to 12. These represent the runtime variables numbered 1 through 12, respectively.

[0039] Step 1.3: Use the Z-score algorithm to normalize the runtime variables after time reconstruction, as shown below.

[0040]

[0041] In the formula, Represented as normalized data, This represents the original data after time series reconstruction. and These are the mean and standard deviation of the data, respectively: Step 1.4: Model and train the NOx emission trend prediction model based on linear algorithms such as partial least squares or nonlinear algorithms such as neural networks to achieve future... +1、 +2 and Accurate prediction of NOx emission concentration at +3 time.

[0042] Step 1.5: Perform inverse normalization on the prediction results to obtain... +1、 +2 and Predicted NOx emission concentration at time +3.

[0043] Step 2: Calculate the NOx emission concentration trend prediction model's predictions. +1、 +2 and Average NOx emission concentration at +3 time And calculate the average value. With control target value Deviation between Based on piecewise functions Calculate the ammonia injection flow rate or valve opening value of the SNCR denitrification system. Its expression is shown below.

[0044]

[0045] Piecewise function in step 2 Its input is the NOx emission concentration trend prediction model. +1、 +2 and The average NOx emission concentration at +3 time point and the control target value Deviation between The output is the ammonia injection flow rate or valve opening value of the SNCR denitrification system, as shown below.

[0046]

[0047] In the formula, All are constants. , ... This represents a range of non-overlapping values. , , ... The value is initially set based on the experience of operation experts, and then iteratively corrected and optimized based on the results of on-site debugging.

[0048] In one embodiment, and The values ​​are shown in Table 1. In practical applications, the values ​​can be obtained through the experience of operation experts and on-site debugging and correction.

[0049] Table 1 Function parameter value table

[0050] Step 3: Calculate the weight of ammonia injection flow rate or valve opening adjustment in the SNCR denitrification system through expert evaluation. This involves obtaining the hourly average NOx emission concentration at the waste-to-energy power plant chimney (using a one-hour time window, calculate the average of all measured NOx concentrations at the chimney within that window), and comparing this value with the control target value. Deviation between Combined with piecewise functions Obtain the ammonia injection flow rate or valve opening adjustment weight of the SNCR denitrification system. .

[0051]

[0052] Piecewise function in step 3 Its inputs are the hourly average NOx value and the control target value from the real-time environmental monitoring of the waste incineration power plant's chimney. Deviation between The output is the ammonia injection flow rate or valve opening adjustment weight of the SNCR denitrification system, as shown in the following figure.

[0053]

[0054] In the formula, All are constants. , This represents a range of non-overlapping values. , The value can be initially set based on the experience of operation experts, and then iteratively corrected and optimized in combination with the results of on-site debugging.

[0055] In one embodiment, and , The values ​​are shown in Table 2. In practical applications, the values ​​can be obtained through the experience of operation experts and on-site debugging and correction.

[0056] Table 2 Function parameter value table

[0057] Step 4: Calculate the final ammonia injection flow rate or valve opening adjustment value for the SNCR denitrification system, expressed as follows:

[0058] Step 5: Calculate the NOx emission concentration trend predictions from the model. +1、 +2 and NOx emission concentration and control target value at +3 time Deviation between , and Combining piecewise nonlinear functions , , , Calculate the ammonia injection flow rate or valve opening value of the three SCR denitrification systems. , and .

[0059]

[0060] In the formula, These represent the NOx emission concentration trend prediction models. +1、 +2 and NOx emission concentration at +3 time.

[0061] Weighted calculation of ammonia injection flow rate or valve opening adjustment value in SCR denitrification system Its expression is shown below.

[0062]

[0063] In the formula, , and These are the weighting coefficients. In one embodiment, the values ​​are shown in Table 3, and in practical applications, they can be obtained from the experience of operation experts or through on-site debugging.

[0064] Table 3 Value table

[0065] Piecewise nonlinear function Its expression is shown below.

[0066]

[0067] In the formula, These are nonlinear functions, such as polynomials, sigmoid functions, and logarithms. , ... This represents a range of non-overlapping values. Function selection and , ... The value can be initially set based on the experience of operation experts, and then iteratively corrected and optimized in combination with the results of on-site debugging.

[0068] In one embodiment, The specific expression is shown below.

[0069]

[0070] Step 6: Calculate the time window Average actual NOx emission concentration from internal chimneys compared to control target value Average deviation between Using Proportional-Integral-Derivative (PID) module 1 (PID1 for short), the ammonia injection flow rate or valve opening adjustment of the SCR denitrification system based on feedback control is calculated. .

[0071] Step 7: Calculate the weighting of ammonia injection flow rate or valve opening adjustment in the SCR denitrification system through expert evaluation. .

[0072] Calculation time window Average ammonia injection flow rate or valve opening of the internal SNCR denitrification system and ammonia consumption Combined with the average deviation Based on piecewise nonlinear functions Calculate the ammonia injection flow rate or valve opening adjustment weight of the SCR denitrification system. .

[0073]

[0074] In the formula, and For the weighting coefficient, we can take... , This can be obtained through the experience of operation experts and on-site debugging and correction.

[0075] Let be a piecewise function, expressed as follows.

[0076]

[0077] In the formula, It is a constant. , This represents a range of non-overlapping values. The value can be initially set based on the experience of operation experts, and then iteratively corrected and optimized in combination with the results of on-site commissioning. In one embodiment, its value is shown in Table 4.

[0078] Table 4 Function parameter value table

[0079] Step 8: Calculate the final ammonia injection flow rate or valve opening adjustment value of the SCR denitrification system in real time. The calculation formula is shown below.

[0080]

[0081] In the formula, and These are weighting coefficients; in one embodiment, =0.6, =0.4, which can be obtained through the experience of operation experts and on-site debugging and correction in practical applications.

[0082] Step 9: Calculate the ammonia injection flow rate or valve opening adjustment value of the SNCR denitrification system. The difference between the actual ammonia injection flow rate or valve opening of the SNCR denitrification system and the adjusted ammonia injection flow rate or valve opening of the SCR denitrification system. The difference between the actual ammonia injection flow rate or valve opening of the SCR denitrification system and the actual ammonia injection flow rate or valve opening is used in conjunction with PID2 (PID module 2, hereinafter referred to as PID2) and PID3 (PID module 3, hereinafter referred to as PID3) to control the ammonia injection flow rate or valve opening of the SNCR and SCR denitrification systems.

[0083] In steps 6 and 9, PID1, PID2, and PID3 are configured with upper and lower limits and dead zones. PID is a common control module in the industry, and will not be elaborated upon here.

[0084] In one embodiment, a waste incineration SNCR and SCR denitrification synergistic control system integrating model prediction and expert evaluation is provided, characterized in that, for implementing the method described in the foregoing embodiment, the system includes the following modules: The data acquisition module is used to acquire... The runtime parameters before the specified time; The prediction model module is used to reconstruct time series data from operating parameters, establish NOx emission concentration trend prediction models using linear or nonlinear algorithms, and predict future NOx emission concentrations. +1、 +2 and Predict NOx emission concentration at time +3; The expert evaluation module for calculating the weights of SNCR denitrification systems is used to calculate the weights of ammonia injection flow rate or valve opening adjustments in the SNCR denitrification system through expert evaluation. ; The SNCR denitrification system ammonia injection flow rate or valve opening calculation module is used to calculate the NOx emission concentration trend prediction model. +1、 +2 and Average NOx emission concentration at +3 time Calculate the average value With control target value Deviation between Based on piecewise functions Calculate the ammonia injection flow rate or valve opening value of the SNCR denitrification system. Based on the ammonia injection flow rate or valve opening value of the SNCR denitrification system and weight Calculate the final ammonia injection flow rate or valve opening adjustment value for the SNCR denitrification system. ; The expert evaluation module for calculating the weights of SCR denitrification system weights is used to calculate the weights of ammonia injection flow rate or valve opening adjustments in the SCR denitrification system through expert evaluation. ; The SCR denitrification system ammonia injection flow rate or valve opening calculation module calculates the NOx emission concentration trend prediction model. +1、 +2 and NOx emission concentration and control target value at +3 time Deviation between , and Combining piecewise nonlinear functions , , , Calculate the corresponding ammonia injection flow rate or valve opening value for the SCR denitrification system. , and Based on the ammonia injection flow rate or valve opening value of the SCR denitrification system , and Weighted calculations are performed to obtain the ammonia injection flow rate or valve opening adjustment value of the SCR denitrification system. ;Calculation time window Average actual NOx emission concentration from internal chimneys compared to control target value Average deviation between By combining the proportional-integral-derivative module, the ammonia injection flow rate or valve opening adjustment amount of the SCR denitrification system based on feedback regulation is calculated. Based on the ammonia injection flow rate or valve opening adjustment value of the SCR denitrification system Ammonia injection flow rate or valve opening adjustment amount in SCR denitrification system and weight Calculate the final ammonia injection flow rate or valve opening adjustment value for the SCR denitrification system. ; The SNCR ammonia injection flow rate or valve opening PID control module is used to calculate the ammonia injection flow rate or valve opening adjustment value of the SNCR denitrification system. The difference between the actual ammonia injection flow rate or valve opening of the SNCR denitrification system and the corresponding proportional-integral-derivative module is used to control the ammonia injection flow rate or valve opening of the SNCR denitrification system. The SCR ammonia injection flow or valve opening PID control module is used to calculate the ammonia injection flow or valve opening adjustment value of the SCR denitrification system. The difference between the actual ammonia injection flow rate or valve opening of the SCR denitrification system and the actual ammonia injection flow rate or valve opening is used to control the ammonia injection flow rate or valve opening of the SCR denitrification system in conjunction with the corresponding proportional-integral-derivative module.

[0085] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the methods described in the foregoing embodiments.

[0086] In one embodiment, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described in the foregoing embodiments.

[0087] The system, device, and medium described herein possess the technical effects achievable by the method described in the foregoing embodiments.

[0088] The above description is merely one embodiment of the present invention and should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A method for synergistic control of SNCR and SCR denitrification in waste incineration, integrating model prediction and expert evaluation, characterized in that, Includes the following steps: Get The operating parameters before a certain time are analyzed and reconstructed into a time series. A NOx emission concentration trend prediction model is established using linear or nonlinear algorithms, and the future... +1、 +2 and Predict NOx emission concentration at time +3; The calculation of NOx emission concentration trend prediction model prediction +1、 +2 and Average NOx emission concentration at +3 time Calculate the average value With control target value Deviation between Based on piecewise functions Calculate the ammonia injection flow rate or valve opening value of the SNCR denitrification system. ; The weighting of ammonia injection flow rate or valve opening adjustment in the SNCR denitrification system was calculated through expert evaluation. ; Based on the ammonia injection flow rate or valve opening value of the SNCR denitrification system and weight Calculate the final ammonia injection flow rate or valve opening adjustment value for the SNCR denitrification system. ; Calculate the NOx emission concentration trend prediction model for each. +1、 +2 and NOx emission concentration and control target value at +3 time Deviation between , and Combining piecewise nonlinear functions , , , Calculate the corresponding ammonia injection flow rate or valve opening value for the SCR denitrification system. , and ; Based on the ammonia injection flow rate or valve opening value of the SCR denitrification system , and Weighted calculations are performed to obtain the ammonia injection flow rate or valve opening adjustment amount of the SCR denitrification system. ; Calculation time window Average actual NOx emission concentration from internal chimneys compared to control target value Average deviation between By combining the proportional-integral-derivative module, the ammonia injection flow rate or valve opening adjustment amount of the SCR denitrification system based on feedback regulation is calculated. ; The weighting of ammonia injection flow rate or valve opening adjustment in the SCR denitrification system was calculated through expert evaluation. ; Based on the ammonia injection flow rate or valve opening adjustment value of the SCR denitrification system Ammonia injection flow rate or valve opening adjustment amount in SCR denitrification system and weight Calculate the final ammonia injection flow rate or valve opening adjustment value for the SCR denitrification system. ; Calculate the ammonia injection flow rate or valve opening adjustment value of the SNCR denitrification system and the SCR denitrification system respectively. Ammonia injection flow rate or valve opening adjustment value of SCR denitrification system The difference between the actual ammonia injection flow rate and the valve opening is used to control the ammonia injection flow rate or valve opening of the SNCR and SCR denitrification systems, in conjunction with the corresponding proportional-integral-derivative modules.

2. The collaborative control method according to claim 1, characterized in that, The operating parameters include, but are not limited to, the grate air volume at each stage of the incinerator, the secondary air volume, the furnace temperature, the oxygen content in the furnace, the ammonia flow rate of the SNCR denitrification system, the ammonia flow rate of the SCR denitrification system, the inlet and outlet temperatures of the SCR denitrification system, and the NOx emission concentration.

3. The collaborative control method according to claim 1, characterized in that, Time series reconstruction is performed, and a NOx emission concentration trend prediction model is established using linear or nonlinear algorithms, including: Set the time series reconstruction length as a runtime variable. Based on the mutual information nonlinear correlation analysis algorithm, the running variables after time series reconstruction are calculated with... The correlation between NOx emission concentrations at time +1 is calculated, and the time series with the highest correlation is reconstructed to its length. As the optimal time series reconstruction length; Normalize the runtime variables after time reconstruction; A NOx emission trend prediction model is established by modeling and training based on linear or nonlinear algorithms.

4. The collaborative control method according to claim 1, characterized in that, The weighting of ammonia injection flow rate or valve opening adjustment in the SNCR denitrification system was calculated through expert evaluation. ,include: Obtain the hourly average NOx emission concentration at the chimney of the waste-to-energy incineration plant, and calculate the hourly average NOx emission concentration relative to the control target value. Deviation between Combined with piecewise functions Obtain the ammonia injection flow rate or valve opening adjustment weight of the SNCR denitrification system. ,in, .

5. The collaborative control method according to claim 1, characterized in that, The weighting of ammonia injection flow rate or valve opening adjustment in the SCR denitrification system was calculated through expert evaluation. ,include: Calculation time window Average ammonia injection flow rate or valve opening of the internal SNCR denitrification system and ammonia consumption ; Combined deviation average Based on piecewise nonlinear functions Calculate the ammonia injection flow rate or valve opening adjustment weight of the SCR denitrification system. .

6. The cooperative control method according to claim 1, characterized in that, SCR denitrification system ammonia injection flow rate or valve opening adjustment value The calculation formula is: , and These are the weighting coefficients.

7. The cooperative control method according to any one of claims 1-6, characterized in that, SCR denitrification system ammonia injection flow rate or valve opening adjustment value The calculation formula is: and These are the weighting coefficients.

8. A waste incineration SNCR and SCR denitrification synergistic control system integrating model prediction and expert evaluation, characterized in that, The system for implementing the method according to any one of claims 1-7 includes the following modules: The data acquisition module is used to acquire... The runtime parameters before the specified time; The prediction model module is used to reconstruct time series data from operating parameters, establish NOx emission concentration trend prediction models using linear or nonlinear algorithms, and predict future NOx emission concentrations. +1、 +2 and Predict NOx emission concentration at time +3; The expert evaluation module for calculating the weights of SNCR denitrification systems is used to calculate the weights of ammonia injection flow rate or valve opening adjustments in the SNCR denitrification system through expert evaluation. ; The SNCR denitrification system ammonia injection flow rate or valve opening calculation module is used to calculate the NOx emission concentration trend prediction model. +1、 +2 and Average NOx emission concentration at +3 time Calculate the average value With control target value Deviation between Based on piecewise functions Calculate the ammonia injection flow rate or valve opening value of the SNCR denitrification system. Based on the ammonia injection flow rate or valve opening value of the SNCR denitrification system and weight Calculate the final ammonia injection flow rate or valve opening adjustment value for the SNCR denitrification system. ; The expert evaluation module for calculating the weights of SCR denitrification systems is used to calculate the weights of ammonia injection flow rate or valve opening adjustments in the SCR denitrification system through expert evaluation. ; The SCR denitrification system ammonia injection flow rate or valve opening calculation module calculates the NOx emission concentration trend prediction model. +1、 +2 and NOx emission concentration and control target value at +3 time Deviation between , and Combining piecewise nonlinear functions , , , Calculate the corresponding ammonia injection flow rate or valve opening value for the SCR denitrification system. , and Based on the ammonia injection flow rate or valve opening value of the SCR denitrification system , and Weighted calculations are performed to obtain the ammonia injection flow rate or valve opening adjustment value of the SCR denitrification system. ;Calculation time window Average actual NOx emission concentration from internal chimneys compared to control target value Average deviation between By combining the proportional-integral-derivative module, the ammonia injection flow rate or valve opening adjustment amount of the SCR denitrification system based on feedback regulation is calculated. Based on the ammonia injection flow rate or valve opening adjustment value of the SCR denitrification system Ammonia injection flow rate or valve opening adjustment amount in SCR denitrification system and weight Calculate the final ammonia injection flow rate or valve opening adjustment value for the SCR denitrification system. ; The SNCR ammonia injection flow rate or valve opening PID control module is used to calculate the ammonia injection flow rate or valve opening adjustment value of the SNCR denitrification system. The difference between the actual ammonia injection flow rate or valve opening of the SNCR denitrification system and the actual ammonia injection flow rate or valve opening is used to control the ammonia injection flow rate or valve opening of the SNCR denitrification system in combination with the corresponding proportional-integral-derivative module; The SCR ammonia injection flow or valve opening PID control module is used to calculate the ammonia injection flow or valve opening adjustment value of the SCR denitrification system. The difference between the actual ammonia injection flow rate or valve opening of the SCR denitrification system and the actual ammonia injection flow rate or valve opening is used to control the ammonia injection flow rate or valve opening of the SCR denitrification system in conjunction with the corresponding proportional-integral-derivative module.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-7.