CN114089636A - SCR denitration external hanging type intelligent ammonia spraying closed-loop control method and equipment - Google Patents
SCR denitration external hanging type intelligent ammonia spraying closed-loop control method and equipment Download PDFInfo
- Publication number
- CN114089636A CN114089636A CN202210058608.4A CN202210058608A CN114089636A CN 114089636 A CN114089636 A CN 114089636A CN 202210058608 A CN202210058608 A CN 202210058608A CN 114089636 A CN114089636 A CN 114089636A
- Authority
- CN
- China
- Prior art keywords
- scr denitration
- prediction model
- time
- ammonia
- feedforward
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Treating Waste Gases (AREA)
Abstract
The invention discloses an SCR denitration external hanging type intelligent ammonia spraying closed-loop control method and equipment, wherein the method comprises the following steps of S100: acquiring operation data of a boiler system and a denitration system, connecting the operation data with an OPC communication protocol to establish a database, and S200: processing the operating data; s300: constructing a time-varying feed-forward prediction model of the concentration of nitrogen oxides at the inlet of the SCR denitration reactor, and predicting the concentration of the nitrogen oxides at the inlet of the SCR denitration reactor in real time; s400: constructing an SCR denitration ammonia injection amount feedback correction model by adopting a classification algorithm with a time-varying function, calculating an ammonia consumption correction coefficient of an SCR denitration reactor, and correcting a calculated value of the ammonia injection amount output by a feedforward prediction model according to a final calculation result; s500: the communication module of the external hanging control system is transmitted to the DCS control system, and finally the DCS control system adjusts the ammonia spraying regulating valve in real time to control the ammonia spraying amount, so that intelligent ammonia spraying closed-loop control is realized. The invention reduces the total ammonia injection amount, reduces the ammonia escape rate and realizes intelligent ammonia injection closed-loop control.
Description
Technical Field
The invention belongs to the technical field of thermal power denitration, and particularly relates to an external hanging type intelligent ammonia injection closed-loop control method and equipment for SCR denitration.
Background
In ultra low emission standards for coal fired power plant pollutants, NOXThe discharge amount of (A) is an important environmental index. At present, a coal-fired power plant aims to remove NO in flue gasXTechniques commonly used are Selective Catalytic Reduction (SCR), selective non-catalytic reduction (SNCR) and a combination of selective and selective catalytic reduction (SNCR/SCR hybrid). Wherein, the domestic technology mature device generally adopts Selective Catalytic Reduction (SCR), namely NO in the smoke gas in a certain temperature rangeXUnder the action of catalyst, reacting with reducing agent (usually NH)3) Reacting to produce harmless N2And H20, thereby removing NO in the flue gasXThe purpose of (1).
The SCR denitration technology is the most effective flue gas denitration technology applied in the world at present, and can reach 80-90% of NO under reasonable arrangement and temperature rangeXAnd (4) removing rate. However, there are many problems with the conventional SCR denitration ammonia injection control: (1) the technological principle of the denitration reaction process is simple, but the influence factors are more, and the flue gas temperature, the smoke dust, the SO2 concentration, the inlet NOx concentration, the denitration efficiency, the flue gas flow field and the form of the catalyst have great influence on the performance of the denitration reactor; (2) parameters such as NOx at an inlet and an outlet of the SCR denitration reactor are important measurement parameters in ammonia injection amount control of the SCR denitration system, and are acquired and measured through a continuous flue gas emission monitoring system (CEMS). In practical application, sampling pipes from a sampling extraction opening to a small CEMS analysis room of each CEMS brand can reach more than 60m, so that the extraction time of flue gas is very long, generally 60-120 s, and some flue gas even reaches more than 180s, and therefore the CEMS data acquisition has large hysteresis. The measurement hysteresis of the inlet and outlet NOx makes the ammonia injection amount control process of the denitration system become a large delay link, so that the automatic control is difficult to obtain a good effect. In addition, existing CEMS must intermittently purge the sampling lines to ensure that the lines do not clog. Normal measurement cannot be realized during CEMS purging, and the measured value needs to be kept in a state before purging, so that the effective time of measurement is shortened, and the CEMS purging is close to a non-control state. In addition, the ammonia supply regulating valve has large regulation dead zone, idle stroke and serious nonlinearity, and impurities are deposited and measured in the ammonia flowmeterThe equipment problems such as inaccurate quantity all can influence denitration control effect. (3) At present, most of traditional SCR denitration closed-loop control strategies are designed into a fixed molar ratio control mode, the control method is over simple in design, only static characteristics of objects are considered, a self-adaptive mechanism is lacked, local excessive ammonia is often caused by non-uniform flow fields, ammonia escape often exceeds the standard, and the operation of a control system excessively depends on the accuracy of all measured values. (4) The denitration reactor operation condition deterioration caused by the nonlinear change of the denitration system monitoring equipment and the catalyst activity is considered, along with the increase of the operation time of the denitration reactor, the denitration reactor operation condition deterioration, the deviation between the calculated ammonia injection amount and the actually required ammonia injection amount of the traditional intelligent ammonia injection control system is larger and larger, and the automatic correction cannot be carried out, so the traditional intelligent ammonia injection control system has poor self-adaptability.
Disclosure of Invention
Aiming at the defects or the improvement requirements of the prior art, the invention provides an external hanging type intelligent ammonia spraying closed-loop control method and equipment for SCR denitration, which combine prediction feedforward control with discharge port feedback control, realize external hanging type intelligent ammonia spraying closed-loop control by adding a time-varying function method in both feedforward control and feedback control, stabilize the NOx discharge concentration at the outlet of an SCR denitration reactor near a set value, reduce the total ammonia spraying amount and reduce the ammonia escape rate.
In order to achieve the above object, according to one aspect of the present invention, there is provided an external hanging type intelligent ammonia injection closed-loop control method for SCR denitration, comprising the following steps:
s100: acquiring operation data of a boiler system and a denitration system, connecting the operation data with an OPC communication protocol to establish a database, and storing the operation data into the database;
s200: performing steady state detection, abnormal data processing and vacancy value filling on the operating data;
s300: constructing a time-varying feed-forward prediction model of the concentration of nitrogen oxides at the inlet of the SCR denitration reactor, training and updating the prediction model by taking the processed operation data as input variables to obtain a final prediction model, and predicting the concentration of the nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model;
s400: on the basis of a nitrogen oxide concentration set value at an SCR outlet, an SCR denitration ammonia injection amount feedback correction model is constructed by adopting a classification algorithm with a time-varying function, the feedback correction model is updated in real time on the basis of the load of an SCR denitration operation parameter unit, an ammonia consumption correction coefficient of an SCR denitration reactor is calculated, and a final calculation result is used for correcting an ammonia injection amount calculation value output by a feedforward prediction model;
s500: the feedforward control signal and the feedback control signal are combined and transmitted to the communication module of the externally-mounted control system, the communication module of the externally-mounted control system is transmitted to the DCS control system, and finally the ammonia spraying amount is controlled by adjusting the ammonia spraying adjusting valve in real time through the DCS control system, so that intelligent ammonia spraying closed-loop control is realized.
Further, in S300, the constructing of the time-varying feedforward prediction model includes the following steps:
s301: determining input and output variables of a feedforward prediction model, acquiring operation data of a plurality of boilers and an SCR denitration system according to the requirements of the input variables, and performing data preprocessing;
s302: the method comprises the steps of constructing a feedforward prediction model by adopting a classification algorithm based on data driving, and adopting a regularization parameter with a large influence on the performance of the model by adopting a queue competition algorithm
And kernel function width
Optimizing, determining the optimal values of the two parameters, minimizing the error of the model, and improving the prediction accuracy of the model; adding a time-varying function into the feedforward prediction model to obtain the nitrogen oxide concentration prediction results under different lag time lengths, and updating the feedforward prediction model in real time by adopting a sliding window technology by taking the time length corresponding to the minimum root mean square error in the prediction results as the lag time length;
s303: and training and testing the updated feedforward prediction model to obtain a final feedforward prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final feedforward prediction model.
Further, in step S302, the building a prediction model by using a classification algorithm includes:
wherein the content of the first and second substances,
is the minimum value of the objective function;
is composed of
The vector coefficients of (a);
is a non-linear transformation;
is the nth element of the vector coefficient;
is the norm of the vector coefficient;
is a regularization parameter;
predicting an error vector for the ith training set; n is the number of prediction error vectors of the training set; b is a prediction model parameter;
is the ith Lagrangian multiplier; k is a kernel function; x is an input vector;
is the ith input vector;
is a prediction model;
is the ith output vector;
are constraints.
Further, in step S302, the time-varying function is:
wherein z is a time-varying function;
is the parameter value at the time t;
the input vector at the k-th moment is;
the output quantity of the time-varying function at the kth moment;fis a time-varying function expression.
Further, in step S302, the minimum root mean square error is:
wherein RMSE is the root mean square error; m is the number of samples;
is the ith predicted value;
is the ith true value.
Further, in S300, the constructing of the time-varying feedforward prediction model further includes:
s304: and calculating the theoretical ammonia spraying amount through the inlet flue gas amount of the SCR denitration reactor, a NOx predicted value, the oxygen content of the flue gas, the flue gas humidity and the NOx concentration set value at the outlet of the SCR denitration reactor.
Further, S400 further includes:
s401: and extracting the flue gas amount, the flue gas humidity, the oxygen content, the NOx concentration and the unit load operation data at the discharge ports of the chimneys of the boiler systems from the database, and preprocessing the data.
According to another aspect of the invention, an external intelligent ammonia injection closed-loop control device for SCR denitration is provided, which comprises:
the database module is used for acquiring operation data of the boiler system and the denitration system, establishing a database by connecting with an OPC communication protocol, and storing the operation data into the database;
the data processing module is used for performing steady state detection, abnormal data processing and vacancy value filling on the operating data;
the time-varying feedforward prediction module is used for constructing a time-varying feedforward prediction model of the concentration of the nitrogen oxide at the inlet of the SCR denitration reactor, training and updating the prediction model by taking the processed operation data as input variables to obtain a final prediction model, and predicting the concentration of the nitrogen oxide at the inlet of the SCR denitration reactor in real time by adopting the final prediction model;
the time-varying feedback correction module is used for constructing an SCR denitration ammonia injection amount feedback correction model by adopting a classification algorithm with a time-varying function according to a nitrogen oxide concentration set value at an SCR outlet, updating the feedback correction model in real time based on the load of an SCR denitration operation parameter unit, calculating an ammonia consumption correction coefficient of the SCR denitration reactor, and correcting a final calculation result for an ammonia injection amount calculation value output by the feedforward prediction model;
the intelligent ammonia spraying control module is used for combining a feedforward control signal with a feedback control signal, transmitting the feedforward control signal to the communication module of the externally-hung control system, transmitting the feedforward control signal to the DCS control system through the communication module of the externally-hung control system, and finally adjusting the ammonia spraying regulating valve in real time through the DCS control system to control the ammonia spraying amount so as to realize intelligent ammonia spraying closed-loop control.
According to a third aspect of the present invention, there is provided an electronic apparatus comprising:
a memory for storing a computer program;
and the processor is used for realizing the steps in the SCR denitration external intelligent ammonia injection closed-loop control method when executing the computer program.
According to a fourth aspect of the invention, a readable storage medium is provided, and the readable storage medium stores a computer program, and the computer program realizes the steps of the SCR denitration externally-hung intelligent ammonia injection closed-loop control method after being executed by a processor.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
1. the method combines the predictive feedforward control with the SCR discharge outlet denitration ammonia injection amount feedback control, so that the model adapts to the characteristic change of the SCR denitration process, and the ammonia injection amount which is used as the feedforward control and is adapted to the current SCR denitration system is output. Meanwhile, the ammonia injection amount correction model with time variation for SCR denitration is analyzed and calculated in real time to obtain the ammonia consumption deviation coefficient of the SCR denitration reactor in the current state, and the ammonia injection amount correction value of the SCR denitration system which is used as feedback control and adapts to the current working condition is output; the feedforward control signal and the feedback control signal are combined and transmitted to the communication module of the external hanging type control system, and then the communication module of the external hanging type control system is transmitted to the DCS control system, so that the external hanging type intelligent ammonia spraying closed-loop control is realized, the NOx emission concentration at the outlet of the SCR denitration reactor is stabilized near a set value, the total ammonia spraying amount is reduced, and the ammonia escape rate is reduced.
2. The method has the advantages that the feedforward control model and the feedback control model with the time changes have the functions of continuous learning and real-time updating, so that the feedforward control model and the feedback control model in the externally-hung control system have good adaptability to the deterioration of the operation condition of the SCR denitration reactor caused by the increase of the operation time.
3. According to the method, the time-varying feedback control model analyzes and calculates the NOx concentration of the total denitration discharge outlet and the operation data of the denitration system, and corrects the ammonia injection amount output by the feedforward control model of the SCR denitration reactor.
4. According to the method, an externally-hung control scheme is that a feedforward signal and a feedback signal are combined and transmitted to a DCS control system through a communication module in an externally-hung mode to control the ammonia spraying flow of an ammonia spraying adjusting valve, the problems that the traditional PID control cannot be normally used and the fluctuation of the NOx emission concentration at an outlet is large are solved, and the purpose of accurately spraying ammonia is achieved.
Drawings
FIG. 1 is a schematic flow chart of an SCR denitration externally-hung intelligent ammonia injection closed-loop control method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a data preprocessing flow according to an embodiment of the present invention;
FIG. 3 is a flow chart of a feedforward control system with time variation according to an embodiment of the present invention;
FIG. 4 is a block diagram of the control logic of a feedforward control system with time varying in accordance with an embodiment of the present invention;
FIG. 5 is a block diagram of feedback control logic with time varying according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating the configuration of an external hanging type intelligent ammonia injection closed-loop control system for SCR denitration according to an embodiment of the present invention;
fig. 7 is a logic structure diagram of an externally-hung closed-loop control system with an adaptive function according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1, an embodiment of the present invention provides an external-hanging intelligent ammonia injection closed-loop control method for SCR denitration, which includes the following steps:
the method comprises the following steps: building a system database
Establishing a MYSQL database by acquiring the connection between the boiler system and an OPC Server port of a denitration system and OPC, and establishing different database tables according to data types; and storing the collected boiler system operation data and denitration system operation data in a MYSQL database in real time through a programming language.
Step two: data pre-processing
The collected data are processed, and the method mainly comprises the following steps:
(1) steady state detection
And (3) performing steady state detection by adopting a sliding window method: firstly, determining a certain window length, then calculating the fluctuation condition of data in the window, if the fluctuation condition is larger, considering that the data in the window is in an unsteady state, otherwise, considering that the data is in a steady state. And after the last window is judged, moving the window backwards, and continuously judging the next group of data until all the data are judged.
(2) Culling anomalous data
A statistical identification method is used, a confidence probability is given according to a statistical rule, and a confidence limit is determined, and a more common method is a Laja criterion: let sample data X = (X1, X2... Xn), the average of the samples is
Deviation of some sample data from the average value is Vi = Xi-
(i =1, 2.., n). The standard deviation of the sample is calculated according to equation (1):
if the sample data deviation satisfies:
the sample is considered as abnormal data and is eliminated.
The data vacancy exists after the abnormal data are removed, and the data vacancy can be filled by the following method.
(3) Filling of vacancy values
And filling the vacancy value by adopting a one-dimensional piecewise linear interpolation method, namely predicting a function value at the interpolation point by a linear function connecting two nearest side points of the interpolation point.
Step three: establishing a feed forward prediction with time variation
As shown in fig. 4, firstly, determining input and output variables of a feedforward prediction model, and acquiring operation data of a plurality of boilers and SCR denitration reactors according to the requirements of the input variables and performing data preprocessing; the method comprises the steps of constructing a prediction model by adopting a classification algorithm based on data driving, and adopting a regularization parameter with a large influence on the performance of the model by adopting a queue competition algorithm
And kernel function width
Optimizing, determining the optimal values of the two parameters, minimizing the error of the model, and improving the prediction accuracy of the model; adding a time-varying function into the prediction model to obtain the prediction results of the concentration of nitrogen oxides (NOx) under different delay time lengths, and updating the prediction model in real time by adopting a sliding window technology by taking the time length corresponding to the minimum root mean square error in the prediction results as the delay time length to enable the model to adapt to the characteristic variation of the denitration process; and training and testing the updated prediction model to obtain a final prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model. And calculating the theoretical ammonia spraying amount through the inlet flue gas amount of the SCR denitration reactor, a NOx predicted value, the oxygen content of the flue gas, the flue gas humidity and the NOx concentration set value at the outlet of the SCR denitration reactor.
The method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor adopts a classification algorithm to construct a prediction model, and comprises the following steps:
wherein the content of the first and second substances,
is the minimum value of the objective function;
is composed of
The vector coefficients of (a);
is a non-linear transformation;
is the nth element of the vector coefficient;
is the norm of the vector coefficient;
is a regularization parameter;
predicting an error vector for the ith training set; n is the number of prediction error vectors of the training set; b is a prediction model parameter;
is the ith Lagrangian multiplier; k is a kernel function; x is an input vector;
is the ith input vector;
is a prediction model;
is the ith output vector;
are constraints.
The time-varying function added into the model for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor is as follows:
wherein z is a time-varying function;
is the parameter value at the time t;
the input vector at the k-th moment is;
the output quantity of the time-varying function at the kth moment;fis a time-varying function expression.
The minimum root mean square error in the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor is as follows:
wherein RMSE is the root mean square error; m is the number of samples;
is the ith predicted value;
is the ith true value.
Step four: establishing a feedback control model with time variation
As shown in fig. 5, the operation data such as the flue gas amount, the flue gas humidity, the oxygen content, the NOx concentration, the unit load and the like at the discharge ports of a plurality of chimneys are taken from the database and are subjected to data preprocessing; based on a concentration set value of nitrogen oxides (NOx) at an SCR outlet, an SCR denitration ammonia injection amount correction model is constructed by adopting a classification algorithm with a time-varying function, based on the load of an SCR denitration operation parameter unit, the model is updated in real time by adopting a sliding window technology, an ammonia consumption correction coefficient of an SCR denitration reactor is calculated, and a final calculation result is used for correcting an ammonia injection amount calculation value output by a feedforward control model.
Step five: external hanging type closed-loop control system with self-adaptive function
As shown in fig. 6, the feedforward control model with time variation is calculated by real-time prediction, and the model is learned and updated in real time by adopting a sliding window technology, so that the model adapts to the characteristic change of the SCR denitration process, and the ammonia injection amount which is used as feedforward control and adapts to the current SCR denitration system is output. Meanwhile, the ammonia injection amount correction model with time variation for SCR denitration is analyzed and calculated in real time to obtain the ammonia consumption deviation coefficient of the SCR denitration reactor in the current state, and the ammonia injection amount correction value of the SCR denitration system which is used as feedback control and adapts to the current working condition is output; the feedforward control signal and the feedback control signal are combined and transmitted to a communication module of the external hanging type control system, then the communication module of the external hanging type control system is transmitted to the DCS control system, and finally the ammonia spraying amount is controlled by adjusting the ammonia spraying adjusting valve in real time through the DCS control system.
As shown in fig. 7, a logic structure diagram of an externally-hung type closed-loop control system with a self-adaptive function, according to the SCR denitration externally-hung type intelligent ammonia spraying closed-loop control method and device with a self-adaptive function, when the method and device are specifically operated, the operation data of a boiler system and a denitration system are collected through a communication module of the externally-hung type control system, a feedforward control model and a feedback control model are established by using a classification algorithm with time varying, and the feedforward model and the feedback model have the functions of continuous learning and updating, so that the feedforward control model and the feedback control model in the externally-hung type control system have good adaptability to the operation condition deterioration of an SCR denitration reactor generated along with the increase of operation time; the externally-hung control scheme is that a feedforward signal and a feedback signal are combined and transmitted to the DCS control system through the externally-hung communication module to control the ammonia spraying flow of the ammonia spraying adjusting valve, the problems that the traditional PID control cannot be normally put into use and the fluctuation of the outlet NOx emission concentration is large are solved, the purpose of accurately spraying ammonia is achieved, the NOx concentration of a main discharge port is finally stabilized near the NOx emission concentration set value, the total ammonia consumption of the denitration system is reduced, and the ammonia escape is reduced.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. An external hanging type intelligent ammonia spraying closed-loop control method for SCR denitration is characterized by comprising the following steps:
s100: acquiring operation data of a boiler system and a denitration system, connecting the operation data with an OPC communication protocol to establish a database, and storing the operation data into the database;
s200: performing steady state detection, abnormal data processing and vacancy value filling on the operating data;
s300: constructing a time-varying feed-forward prediction model of the concentration of nitrogen oxides at the inlet of the SCR denitration reactor, training and updating the prediction model by taking the processed operation data as input variables to obtain a final prediction model, and predicting the concentration of the nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model;
s400: on the basis of a nitrogen oxide concentration set value at an SCR outlet, an SCR denitration ammonia injection amount feedback correction model is constructed by adopting a classification algorithm with a time-varying function, the feedback correction model is updated in real time on the basis of the load of an SCR denitration operation parameter unit, an ammonia consumption correction coefficient of an SCR denitration reactor is calculated, and a final calculation result is used for correcting an ammonia injection amount calculation value output by a feedforward prediction model;
s500: the feedforward control signal and the feedback control signal are combined and transmitted to the communication module of the externally-mounted control system, the communication module of the externally-mounted control system is transmitted to the DCS control system, and finally the ammonia spraying amount is controlled by adjusting the ammonia spraying adjusting valve in real time through the DCS control system, so that intelligent ammonia spraying closed-loop control is realized.
2. The SCR denitration externally-hung intelligent ammonia injection closed-loop control method according to claim 1, wherein in S300, the construction of the time-varying feedforward prediction model comprises the following steps:
s301: determining input and output variables of a feedforward prediction model, acquiring operation data of a plurality of boilers and an SCR denitration system according to the requirements of the input variables, and performing data preprocessing;
s302: the method comprises the steps of constructing a feedforward prediction model by adopting a classification algorithm based on data driving, and adopting a regularization parameter with a large influence on the performance of the model by adopting a queue competition algorithm
And kernel function width
Optimizing, determining the optimal values of the two parameters, minimizing the error of the model, and improving the prediction accuracy of the model; adding a time-varying function into the feedforward prediction model to obtain the nitrogen oxide concentration prediction results under different lag time lengths, and updating the feedforward prediction model in real time by adopting a sliding window technology by taking the time length corresponding to the minimum root mean square error in the prediction results as the lag time length;
s303: and training and testing the updated feedforward prediction model to obtain a final feedforward prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final feedforward prediction model.
3. The SCR denitration externally-hung type intelligent ammonia injection closed-loop control method as claimed in claim 2, wherein in step S302, the building of the prediction model by using the classification algorithm comprises:
4. The SCR denitration externally-hung intelligent ammonia injection closed-loop control method as claimed in claim 3, wherein in step S302, the time-varying function is:
wherein z is a time-varying function;
is the parameter value at the time t;
the input vector at the k-th moment is;
the output quantity of the time-varying function at the kth moment;fis a time-varying function expression.
5. The SCR denitration externally-hung intelligent ammonia injection closed-loop control method as claimed in claim 2, wherein in step S302, the minimum root mean square error is as follows:
wherein RMSE is the root mean square error; m is the number of samples;
is the ith predicted value;
is the ith true value.
6. The SCR denitration externally-hung intelligent ammonia injection closed-loop control method according to any one of claims 1 to 5, wherein in S300, the construction of the time-varying feedforward prediction model further comprises:
s304: and calculating the theoretical ammonia spraying amount through the inlet flue gas amount of the SCR denitration reactor, a NOx predicted value, the oxygen content of the flue gas, the flue gas humidity and the NOx concentration set value at the outlet of the SCR denitration reactor.
7. The SCR denitration externally-hung intelligent ammonia injection closed-loop control method according to any one of claims 1 to 5, wherein S400 further comprises:
s401: and extracting the flue gas amount, the flue gas humidity, the oxygen content, the NOx concentration and the unit load operation data at the discharge ports of the chimneys of the boiler systems from the database, and preprocessing the data.
8. The utility model provides a SCR denitration externally hung type intelligence spouts ammonia closed-loop control equipment which characterized in that includes:
the database module is used for acquiring operation data of the boiler system and the denitration system, establishing a database by connecting with an OPC communication protocol, and storing the operation data into the database;
the data processing module is used for performing steady state detection, abnormal data processing and vacancy value filling on the operating data;
the time-varying feedforward prediction module is used for constructing a time-varying feedforward prediction model of the concentration of the nitrogen oxide at the inlet of the SCR denitration reactor, training and updating the prediction model by taking the processed operation data as input variables to obtain a final prediction model, and predicting the concentration of the nitrogen oxide at the inlet of the SCR denitration reactor in real time by adopting the final prediction model;
the time-varying feedback correction module is used for constructing an SCR denitration ammonia injection amount feedback correction model by adopting a classification algorithm with a time-varying function according to a nitrogen oxide concentration set value at an SCR outlet, updating the feedback correction model in real time based on the load of an SCR denitration operation parameter unit, calculating an ammonia consumption correction coefficient of the SCR denitration reactor, and correcting a final calculation result for an ammonia injection amount calculation value output by the feedforward prediction model;
the intelligent ammonia spraying control module is used for combining a feedforward control signal with a feedback control signal, transmitting the feedforward control signal to the communication module of the externally-hung control system, transmitting the feedforward control signal to the DCS control system through the communication module of the externally-hung control system, and finally adjusting the ammonia spraying regulating valve in real time through the DCS control system to control the ammonia spraying amount so as to realize intelligent ammonia spraying closed-loop control.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the SCR denitration hanging type intelligent ammonia injection closed-loop control method according to any one of claims 1 to 7 when executing the computer program.
10. A readable storage medium, wherein the readable storage medium stores thereon a computer program, and the computer program, when executed by a processor, implements the steps of the SCR denitration externally-hung intelligent ammonia injection closed-loop control method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210058608.4A CN114089636A (en) | 2022-01-19 | 2022-01-19 | SCR denitration external hanging type intelligent ammonia spraying closed-loop control method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210058608.4A CN114089636A (en) | 2022-01-19 | 2022-01-19 | SCR denitration external hanging type intelligent ammonia spraying closed-loop control method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114089636A true CN114089636A (en) | 2022-02-25 |
Family
ID=80308583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210058608.4A Pending CN114089636A (en) | 2022-01-19 | 2022-01-19 | SCR denitration external hanging type intelligent ammonia spraying closed-loop control method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114089636A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114870626A (en) * | 2022-04-28 | 2022-08-09 | 安徽工业大学 | Ammonia injection denitration control system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104850008A (en) * | 2015-03-17 | 2015-08-19 | 厦门奥普拓自控科技有限公司 | Multivariate control and real-time optimization method for layer-burning boiler |
| CN106873381A (en) * | 2017-04-10 | 2017-06-20 | 内蒙古瑞特优化科技股份有限公司 | Spray ammonia control system |
| CN108837699A (en) * | 2018-07-02 | 2018-11-20 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and PREDICTIVE CONTROL |
| CN109343349A (en) * | 2018-11-01 | 2019-02-15 | 大唐环境产业集团股份有限公司 | A kind of SCR denitrating flue gas Optimal Control System and method based on ammonia spraying amount compensator |
| CN113592163A (en) * | 2021-07-22 | 2021-11-02 | 汉谷云智(武汉)科技有限公司 | Method and equipment for predicting concentration of nitrogen oxide at inlet of SCR (Selective catalytic reduction) denitration reactor |
| CN113578006A (en) * | 2021-07-02 | 2021-11-02 | 大唐东北电力试验研究院有限公司 | SCR (selective catalytic reduction) denitration control method based on control strategy optimization |
-
2022
- 2022-01-19 CN CN202210058608.4A patent/CN114089636A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104850008A (en) * | 2015-03-17 | 2015-08-19 | 厦门奥普拓自控科技有限公司 | Multivariate control and real-time optimization method for layer-burning boiler |
| CN106873381A (en) * | 2017-04-10 | 2017-06-20 | 内蒙古瑞特优化科技股份有限公司 | Spray ammonia control system |
| CN108837699A (en) * | 2018-07-02 | 2018-11-20 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and PREDICTIVE CONTROL |
| CN109343349A (en) * | 2018-11-01 | 2019-02-15 | 大唐环境产业集团股份有限公司 | A kind of SCR denitrating flue gas Optimal Control System and method based on ammonia spraying amount compensator |
| CN113578006A (en) * | 2021-07-02 | 2021-11-02 | 大唐东北电力试验研究院有限公司 | SCR (selective catalytic reduction) denitration control method based on control strategy optimization |
| CN113592163A (en) * | 2021-07-22 | 2021-11-02 | 汉谷云智(武汉)科技有限公司 | Method and equipment for predicting concentration of nitrogen oxide at inlet of SCR (Selective catalytic reduction) denitration reactor |
Non-Patent Citations (1)
| Title |
|---|
| 王伟: "SCR脱硝***前馈-反馈控制策略", 《中国科技信息》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114870626A (en) * | 2022-04-28 | 2022-08-09 | 安徽工业大学 | Ammonia injection denitration control system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109343349B (en) | SCR flue gas denitration optimal control system and method based on ammonia injection amount compensator | |
| CN107561941B (en) | Full-working-condition standard-reaching emission control method for thermal power generating unit denitration system | |
| CN109062053B (en) | Denitration ammonia injection control method based on multivariate correction | |
| CN112580250A (en) | Thermal power generating unit denitration system based on deep learning and optimization control method | |
| CN105629736B (en) | The fired power generating unit SCR denitration Disturbance Rejection forecast Control Algorithm of data-driven | |
| CN105786035B (en) | Fired power generating unit SCR denitration Optimal Control System based on heuristic Prediction and Control Technology | |
| CN112619394B (en) | Denitration ammonia injection self-adaptive control method and device and denitration system | |
| CN111897373B (en) | Model prediction-based ammonia injection flow adjusting method for SCR denitration device | |
| CN111624876B (en) | Intelligent ammonia injection optimization control system | |
| CN111841276B (en) | SNCR denitration control method and device for circulating fluidized bed unit and storage medium | |
| CN110368808A (en) | A kind of the ammonia spraying amount control method and system of SCR flue gas denitrification system | |
| CN111522290A (en) | Denitration control method and system based on deep learning method | |
| CN111489605B (en) | Ammonia spraying optimization control simulation system based on Simulink and WinCC | |
| CN114089636A (en) | SCR denitration external hanging type intelligent ammonia spraying closed-loop control method and equipment | |
| CN116688754A (en) | Ship flue gas desulfurization automatic control system and method thereof | |
| CN111399458A (en) | SCR denitration system design method based on disturbance suppression generalized predictive control | |
| CN115245735A (en) | Cement kiln flue gas iSNCR control method based on predictive control model | |
| CN109833773B (en) | Efficient denitration ammonia flow accurate control method | |
| CN109046021B (en) | SCR system accurate ammonia injection control method with strong self-adaptive capacity | |
| CN109107360B (en) | Ammonia injection control method and device based on denitration system | |
| CN113488111B (en) | Ammonia injection amount optimization modeling method for SCR denitration system | |
| CN113970937A (en) | SCR denitration accurate ammonia injection control method | |
| CN117270387A (en) | SCR denitration system low ammonia escape control method and system based on deep learning | |
| CN113952838A (en) | Ammonia spraying grid automatic optimization and adjustment device and method for SCR flue gas denitration system | |
| CN109933884B (en) | Neural network inverse control method for SCR denitration system of coal-fired unit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220225 |