CN116036849A - CFB boiler flue gas denitration automatic control method and system - Google Patents
CFB boiler flue gas denitration automatic control method and system Download PDFInfo
- Publication number
- CN116036849A CN116036849A CN202211565197.4A CN202211565197A CN116036849A CN 116036849 A CN116036849 A CN 116036849A CN 202211565197 A CN202211565197 A CN 202211565197A CN 116036849 A CN116036849 A CN 116036849A
- Authority
- CN
- China
- Prior art keywords
- denitration
- model
- ammonia injection
- control
- cfb boiler
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/74—General processes for purification of waste gases; Apparatus or devices specially adapted therefor
- B01D53/77—Liquid phase processes
- B01D53/79—Injecting reactants
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/30—Controlling by gas-analysis apparatus
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/46—Removing components of defined structure
- B01D53/54—Nitrogen compounds
- B01D53/56—Nitrogen oxides
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2251/00—Reactants
- B01D2251/20—Reductants
- B01D2251/206—Ammonium compounds
- B01D2251/2062—Ammonia
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2258/00—Sources of waste gases
- B01D2258/02—Other waste gases
- B01D2258/0283—Flue gases
Abstract
The invention discloses an automatic control method for flue gas denitration of a CFB boiler, which comprises the following steps: s1, collecting and recording reaction parameters in CFB boilers at different moments in real time as measurement data; s2, substituting the measured data into a denitration control model to predict and output denitration control quantity; s3, adjusting and controlling the actual ammonia injection amount of the ammonia injection regulating valve according to the denitration control amount; s4, measuring actual denitration efficiency as a basis to optimize and correct the denitration control model; the invention also discloses an automatic control system for the denitration of the CFB boiler flue gas. According to the method, the gray model is utilized to model the historical denitration big data, the Markov prediction model is combined, the data in a future monitoring period can be accurately predicted, and meanwhile, the accurate denitration control quantity is obtained by calculating the adaptive denitration control model, so that the ammonia injection quantity is accurately regulated and controlled, and the denitration efficiency quality is ensured.
Description
Technical Field
The invention relates to the technical field of flue gas denitration, in particular to an automatic control method and system for CFB boiler flue gas denitration.
Background
Coal is used as main primary energy, and is used as energy source for power station boilers, industrial boilers, power equipment in various related industrial fields, resident life and the likeThe consumption is a large proportion. Particularly, with the development of economy in China in recent years, the demand for electricity is greatly increased, and the consumption of coal is greatly increased. Due to the release of SO during combustion of large amounts of coal 2 、NO 2 And the like brings serious environmental pollution and ecological damage to reduce the life quality of residents.
With increasingly strict environmental protection requirement standards, the Circulating Fluidized Bed (CFB) boiler is insufficient to meet the requirements of the flue gas emission standard by virtue of the characteristics of the boiler, and the selective non-catalytic reduction (SNCR) denitration process has the advantages of low cost, small occupied area, simple facilities and the like, and is suitable for denitration reconstruction of old power plants and small and medium-sized units. The comprehensive denitration efficiency of the SNCR denitration system of the circulating fluidized bed boiler can reach 50% -70%, and the requirements of the existing environmental protection standards are met. However, due to the influence of factors such as fluctuation of coal quality conditions, unstable operation conditions, insufficient operation and the like, various problems exist in actual operation, and standard emission is difficult to realize.
The selective non-catalytic reduction (SNCR) technology is characterized by that in the range of 800-1100 deg.C of boiler furnace a reducing agent (such as ammonia water, liquid ammonia or urea) is sprayed, and under the condition of high-temp., said reducing agent can be quickly decomposed into NH 3 And with NO in the flue gas x Reduction reaction is carried out to generate harmless N 2 And H 2 Denitration technology of the O. The SNCR system consists of a reducing agent storage tank, a plurality of layers of reducing agent spraying devices and corresponding control systems. In order to ensure that the denitration reaction can achieve the best reduction effect with the least ammonia injection amount, the reducing agent is well mixed with the flue gas, the probability of blocking and corroding the rotary air preheater is reduced, and the injected NH is caused 3 The reducing agent is sprayed to the most effective part in the hearth by multiple points according to the principle that the boiler load changes and the temperature changes.
But the accurate and reasonable control of the ammonia injection flow is a precondition for the efficient operation of the SNCR process. Due to NH 3 With NO x Is a delayed, large inertia process, combined with NO x The filtration-continuous sampling-condensation-secondary filtration-chemical analysis process of the on-line monitoring instrument CEMS also has significant delay inIn such a delayed system, after the ammonia injection flow regulating gate is changed, a long delay time is always required to pass the NO x The monitored amount changes, so that the traditional PID control always has obvious hysteresis overshoot and even has divergent characteristics. Furthermore, the boiler exhaust gas NO x The content change is a complex process, is greatly affected by parameters such as unit load, air quantity, coal type, the opening of a SOFA air door of the over-fire air at the top of the low-nitrogen burner and the like, has different delay characteristics, and is difficult to solve the industrial control problems by the traditional field control means such as manual control, PID automatic control and the like.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides an automatic control method and system for flue gas denitration of a CFB boiler, which are used for overcoming the technical problems existing in the related art.
For this purpose, the invention adopts the following specific technical scheme:
according to one aspect of the invention, there is provided an automatic control method for flue gas denitration of a CFB boiler, the method comprising the steps of:
s1, collecting and recording reaction parameters in CFB boilers at different moments in real time as measurement data;
s2, substituting the measured data into a denitration control model to predict and output denitration control quantity;
s3, adjusting and controlling the actual ammonia injection amount of the ammonia injection regulating valve according to the denitration control amount;
and S4, measuring actual denitration efficiency as a basis to optimize and correct the denitration control model.
Further, the step of collecting and recording the reaction parameters in the CFB boiler at different moments in real time as measured data comprises the following steps:
s11, setting and monitoring the CFB boiler in real time according to a monitoring period;
s12, measuring bed temperature, air quantity and coal supply quantity parameters in the CFB boiler to determine the boiler load;
s13, measuring NO in flue gas in CFB boiler x The concentration of the gas as an initial concentration;
s14, acquiring the opening and closing degree of the ammonia injection regulating valve in the current monitoring period;
s15, acquiring and recording the ammonia spraying amount under the premise of the current monitoring period and the current opening and closing degree, and taking the ammonia spraying amount as an initial ammonia spraying amount;
s16, taking the boiler load, the initial concentration, the opening and closing degree and the initial ammonia injection amount in the same monitoring period as measurement data of a certain monitoring period.
Further, substituting the measured data into a denitration control model to predict and output a denitration control amount includes the following steps:
s21, constructing a gray Markov prediction model by combining the historical denitration concentration big data;
s22, constructing an ammonia injection regulation model by combining a brain model neural network of the big data of the historical ammonia injection quantity;
s23, constructing a denitration control model meeting a denitration control strategy by the gray Markov prediction model and the denitration control neural network;
s24, substituting the measured data into the denitration control model in sequence, and outputting denitration control quantity.
Further, the construction of the gray Markov prediction model by combining the historical denitration concentration big data comprises the following steps:
s211, constructing a gray prediction model by taking the historical denitration concentration big data as basic data;
s212, inputting a simulation data set into the gray model to carry out simulation prediction, and outputting a simulation prediction result;
s213, calculating a relative error between the true value and the predicted value according to the simulation predicted result, and dividing a state interval through an error range;
s214, combining probabilities of transferring the current state to the next state through a plurality of steps to form a state transfer probability matrix;
s215, predicting the state at the next moment according to the current state and the state transition matrix.
Further, the construction of the ammonia injection regulation model by combining the historical ammonia injection amount big data cerebellum model neural network comprises the following steps:
s221, constructing an initial model by using a Gaussian function as a basis function of a cerebellum model neural network;
s222, expanding the historical ammonia injection amount big data and dividing the data into a training set and a testing set;
s223, substituting the training set into the initial model to train so as to obtain an ammonia injection regulation model;
s223, performing test training and verification on the ammonia injection regulation model by using the test set.
Further, substituting the measured data into the denitration control model in sequence, and outputting the denitration control amount includes the following steps:
s241, substituting the boiler load, the initial concentration and the opening degree in the measured data of the current monitoring period into the ammonia injection regulation model to output a result as a basic ammonia injection quantity;
s242, substituting the initial concentration in the measured data of the current monitoring period into the gray Markov prediction model to predict to obtain a concentration prediction result of the next monitoring period;
s243, calculating a difference value between the concentration prediction result and the initial concentration in the current monitoring period, and calculating by combining working condition parameters of the CFB boiler to obtain a corresponding compensation ammonia injection amount;
s244, multiplying the sum of the basic ammonia injection amount and the compensation ammonia injection amount by a correction coefficient and a correction coefficient to obtain the actual ammonia injection amount in the next monitoring period, and taking the actual ammonia injection amount as the denitration control amount.
Furthermore, the actual ammonia injection amount is regulated and controlled by the ammonia injection regulating valve according to the denitration control amount by adopting a cascade control strategy, wherein the main parameter of control is the initial concentration, the auxiliary parameter is the opening and closing degree, and the reference amount is the denitration control amount.
Further, the measuring the actual denitration efficiency as a basis to perform optimization correction on the denitration control model includes the following steps:
s41, measuring NO at actual outlet in real time x The concentration of the gas is used for calculating the actual denitration efficiency;
s42, substituting the actual denitration efficiency of the current monitoring period into a correction formula to calculate and obtain a correction coefficient of the next monitoring period;
s43, substituting the correction coefficient into the denitration control model to calculate the denitration control quantity of the next monitoring period;
s44, when the actual denitration efficiency of a plurality of continuous monitoring periods is lower than a preset safety threshold, the system sends out an early warning, and the denitration process is manually checked and the correction coefficient is modified.
Further, the correction formula is:
wherein η represents a correction coefficient;
s represents the actual denitration efficiency of the current monitoring period;
S min representing a minimum value of a preset denitration efficiency standard;
S max representing the maximum value of the preset denitration efficiency standard.
According to another aspect of the present invention, there is also provided an automatic control system for denitration of CFB boiler flue gas, the system comprising: the CFB boiler comprises a CFB boiler main body, a real-time monitoring unit, an automatic control unit, an ammonia injection regulating valve and a supervision control center;
the CFB boiler body is used for providing a denitration and reduction environment for flue gas;
the real-time monitoring unit is used for acquiring boiler parameters and NO in the flue gas in real time x A gas concentration;
the automatic control unit is used for realizing the self-adaptive regulation control of ammonia injection according to the monitoring data;
the ammonia injection regulating valve is used for changing the opening and closing degree to control the ammonia injection amount;
the supervision and control center is used for realizing remote supervision and parameter adjustment input of the system.
The beneficial effects of the invention are as follows: the historical denitration big data is modeled by utilizing a gray model, and the data in a future monitoring period can be accurately predicted by combining with a Markov prediction model, and meanwhile, an accurate denitration control quantity is obtained by calculating by matching with a self-adaptive denitration control model, so that the ammonia injection quantity is accurately regulated and controlled, the influence of time delay of monitoring signals, reaction delay and the like on reduction denitration of SNCR technology in the CFB boiler is eliminated, and the denitration efficiency and denitration quality are further ensured; at the same time, according to the real-time monitoring of the running parameters in the CFB boiler and the NO of the smoke inlet and outlet x The gas concentration is calculated in real time, the actual denitration efficiency inputs a feedback correction instruction to a denitration control model, the accuracy of automatic control is further improved, self-adaptive dynamic adjustment can be carried out according to the actual running condition, and the reduction denitration efficiency and effect caused by sudden change of a certain parameter in a boiler are avoided; by adding the automatic early warning system, under the condition of automatic control errors in the long-term operation process, the system can prompt the manual maintenance and investigation in time, so that the loss and harm of the system are reduced to the greatest extent, and the safety and stability of the automatic control system are improved; in addition, the system has the advantages that the signal feedback instruction transmission efficiency is rapid in time, and the problem of large signal lag and inertia in the traditional denitration process is effectively solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for automatically controlling flue gas denitration of a CFB boiler according to an embodiment of the present invention;
fig. 2 is a system block diagram of an automatic control system for flue gas denitration of a CFB boiler according to an embodiment of the present invention.
In the figure:
1. a CFB boiler body; 2. a real-time monitoring unit; 3. an automatic control unit; 4. an ammonia injection regulating valve; 5. and (5) supervising the control center.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used to illustrate the embodiments and, together with the description, serve to explain the principles of the embodiments, and with reference to these descriptions, one skilled in the art will recognize other possible implementations and advantages of the present invention, wherein elements are not drawn to scale, and like reference numerals are generally used to designate like elements.
According to the embodiment of the invention, an automatic control method for flue gas denitration of a CFB boiler is provided.
The invention will be further described with reference to the accompanying drawings and detailed description, as shown in fig. 1, a method for automatically controlling denitration of flue gas of a CFB boiler according to an embodiment of the invention, the method comprising the steps of:
s1, collecting and recording reaction parameters in CFB boilers at different moments in real time as measurement data;
the method for acquiring and recording the reaction parameters in the CFB boiler at different moments in real time as measured data comprises the following steps:
s11, setting and monitoring the CFB boiler in real time according to a monitoring period;
s12, measuring bed temperature, air quantity and coal supply quantity parameters in the CFB boiler to determine the boiler load;
s13, measuring NO in flue gas in CFB boiler x The concentration of the gas as an initial concentration;
s14, acquiring the opening and closing degree of the ammonia injection regulating valve in the current monitoring period;
s15, acquiring and recording the ammonia spraying amount under the premise of the current monitoring period and the current opening and closing degree, and taking the ammonia spraying amount as an initial ammonia spraying amount;
s16, taking the boiler load, the initial concentration, the opening and closing degree and the initial ammonia injection amount in the same monitoring period as measurement data of a certain monitoring period.
S2, substituting the measured data into a denitration control model to predict and output denitration control quantity;
wherein substituting the measured data into a denitration control model to predict and output a denitration control amount comprises the following steps:
s21, constructing a gray Markov prediction model by combining the historical denitration concentration big data;
in the denitration process of the CFB boiler with the historic denitration concentration big data selection by utilizing the SNCR technology, NO at the inlet inside the boiler x The change data of the gas concentration is also set to be sequentially arranged in a periodically changing sequence.
Markov (Markov) prediction is a probabilistic prediction method regarding the occurrence of events. It is a prediction method for predicting the change condition of each time (or period) in the future according to the current condition of an event. The state of future things is predicted by an initial probability of different states of the things and transition probabilities of the states.
The method for constructing the gray Markov prediction model by combining the historical denitration concentration big data comprises the following steps of:
s211, constructing a gray prediction model by taking the historical denitration concentration big data as basic data;
setting the historical denitration concentration big data in a certain time period as an original sequence, wherein the expression is as follows:
and the number sequence is negative, a data sequence is generated by one accumulation according to the original sequence, namely +.>
The first order linear differential equation of the gray prediction model can be expressed as:
wherein a represents a development coefficient, the size and sign of a reflect the development situation of the original sequence and the one-time accumulated data sequence,b represents the ash application amount.
The values of a and b can be obtained by a least square method and a construction matrix, and a gray prediction model is constructed by the method
S212, inputting a simulation data set into the gray model to carry out simulation prediction, and outputting a simulation prediction result;
s213, calculating a relative error between the true value and the predicted value according to the simulation predicted result, and dividing a state interval through an error range;
the state interval can be expressed as: e (E) i ＝[L i ,H i ]Wherein L is i Represents the lower limit, H i The upper limit is indicated.
S214, combining probabilities that the current state is transferred to the next state through a plurality of steps (k steps) to form a state transfer probability matrix;
set sequence x t In state E i The state probability of (2) is p i (t)＝p(x t =i), if the sequence x t From state E i Transition to the next time state E j Is p ij Then p ij ＝p(x t+1 ＝j|x t =i), is the probability of transition to state j to time t+1 under the condition that time t is in state i. If the value at time t+1 depends only on the value at time t and the transition probability, then this time series is called a Markov chain. P is p ij Is the probability of one-step transition of the Markov chain at time t.
State E i Transition to State E j The number of times of m ij State E i The number of occurrences is M i State E i Transfer to E j The probability of p ij The transition probability of k steps is then called the probability of the state j being reached from state i through k steps at time t. Thus, the k-step transition probability matrix is a matrix formed by combining the k-step transition probabilities.
S215, predicting the state at the next moment according to the current state and the state transition matrix. S22, constructing an ammonia injection regulation model by combining a brain model neural network of the big data of the historical ammonia injection quantity;
the historical ammonia injection amount big data comprises specific ammonia injection amount and NO corresponding to each ammonia injection amount x The initial concentration of the gas and the load and other parameters of the CFB boiler, different boiler environments need to be sprayed with reducing agents with different dosages for denitration, so that parameters corresponding to different ammonia spraying amounts are different.
The method for constructing the ammonia spraying regulation model by combining the historical ammonia spraying amount big data cerebellum model neural network comprises the following steps of:
s221, constructing an initial model by using a Gaussian function as a basis function of a cerebellum model neural network;
the expression of the initial model is:
wherein N is x Representing input x j Dimension of u k,j Representing the center, sigma, of the basis function k,j The variance of the basis function is represented, and k represents the input quantization technique for determining the mapping accuracy.
S222, expanding the historical ammonia injection amount big data and dividing the data into a training set and a testing set;
s223, substituting the training set into the initial model to train so as to obtain an ammonia injection regulation model;
s223, performing test training and verification on the ammonia injection regulation model by using the test set.
S23, constructing a denitration control model meeting a denitration control strategy by the gray Markov prediction model and the denitration control neural network;
s24, substituting the measured data into the denitration control model in sequence, and outputting denitration control quantity.
Wherein, substituting the measured data into the denitration control model in turn, outputting a denitration control amount includes the following steps:
s241, substituting the boiler load, the initial concentration and the opening degree in the measured data of the current monitoring period into the ammonia injection regulation model to output a result as a basic ammonia injection quantity;
s242, substituting the initial concentration in the measured data of the current monitoring period into the gray Markov prediction model to predict to obtain a concentration prediction result of the next monitoring period;
s243, calculating a difference value between the concentration prediction result and the initial concentration in the current monitoring period, and calculating by combining working condition parameters of the CFB boiler to obtain a corresponding compensation ammonia injection amount;
s244, multiplying the sum of the basic ammonia injection amount and the compensation ammonia injection amount by a correction coefficient and a correction coefficient to obtain the actual ammonia injection amount in the next monitoring period, and taking the actual ammonia injection amount as the denitration control amount.
S3, adjusting and controlling the actual ammonia injection amount of the ammonia injection regulating valve according to the denitration control amount;
and regulating and controlling the actual ammonia injection amount of the ammonia injection regulating valve according to the denitration control amount by adopting a cascade control strategy, wherein the main parameter of control is the initial concentration, the auxiliary parameter is the opening and closing degree, and the reference amount is the denitration control amount.
And S4, measuring actual denitration efficiency as a basis to optimize and correct the denitration control model.
Wherein, the measurement of the actual denitration efficiency is used as a basis to carry out optimization correction on the denitration control model, and the optimization correction comprises the following steps:
s41, measuring NO at actual outlet in real time x The concentration of the gas is used for calculating the actual denitration efficiency;
s42, substituting the actual denitration efficiency of the current monitoring period into a correction formula to calculate and obtain a correction coefficient of the next monitoring period;
wherein, the correction formula is:
wherein η represents a correction coefficient;
s represents the actual denitration efficiency of the current monitoring period;
S min representing a minimum value of a preset denitration efficiency standard;
S max representing the maximum value of the preset denitration efficiency standard.
S43, substituting the correction coefficient into the denitration control model to calculate the denitration control quantity of the next monitoring period;
s44, when the actual denitration efficiency of a plurality of continuous monitoring periods is lower than a preset safety threshold, the system sends out an early warning, and the denitration process is manually checked and the correction coefficient is modified.
When continuous deviation occurs in actual denitration efficiency, abnormality of certain parameters may exist at this time, so that manual troubleshooting and maintenance are required, effective operation of the system is ensured, and main factors affecting denitration efficiency of the SNCR flue gas denitration system are as follows:
1) Boiler excess air factor: NO of excess air ratio to CFB boiler x The generation and emission effects are larger, and the larger the air excess coefficient is, the generated NO x The more the excess air ratio is properly reduced, the NO can be greatly reduced x Is generated; however, the excess air ratio is influenced by a plurality of factors such as boiler load, furnace temperature, fuel combustion condition and the like.
2) Unit load: unit load vs. NO x The generation of (a) plays a main role, and the larger the load is, the more the fuel amount is, NO x The higher the mass concentration; at present, the power grid load distribution adopts the regional control deviation (ACE) technology, so that the load change of a unit is large, the combustion system of a boiler is unstable, the changes of fuel quantity, air quantity, excess air coefficient and the like are large, and NO x The emission mass concentration fluctuates drastically.
3) Measuring point mounting position: NO (NO) x The analyzer is generally installed behind the induced draft fan at the inlet of the desulfurizing tower. Through field practical tests, when the load of the unit changes, NO x The delay time of the corresponding change of the measured value is between 2 and 3 minutes, and the delay is quite large.
4) Furnace temperature: NH is aggravated by high furnace temperatures 3 Reducing the reducing agent and increasing ammonia slip at the same time; too low a furnace temperature will reduce NH 3 Is a reduction reaction rate of (a).
According to another embodiment of the present invention, as shown in fig. 2, there is also provided an automatic control system for denitration of CFB boiler flue gas, the system comprising: the CFB boiler comprises a CFB boiler main body 1, a real-time monitoring unit 2, an automatic control unit 3, an ammonia injection regulating valve 4 and a supervision control center 5;
the CFB boiler comprises a CFB boiler main body 1, a smoke gas sensor and a smoke gas sensor, wherein the CFB boiler main body 1 is used for providing a denitration and reduction environment of smoke gas;
the real-time monitoring unit 2 is used for acquiring boiler parameters and NO in the flue gas in real time x A gas concentration;
the automatic control unit 3 is used for realizing the self-adaptive regulation control of ammonia injection according to the monitoring data;
the ammonia injection regulating valve 4 is used for changing the opening and closing degree to control the ammonia injection amount;
the supervision and control center 5 is used for realizing remote supervision and parameter adjustment input of the system.
In summary, by means of the technical scheme, the historical denitration big data is modeled by utilizing the gray model, and the data in a future monitoring period can be accurately predicted by combining with the Markov prediction model, and meanwhile, the accurate denitration control quantity is obtained by calculating by matching with the adaptive denitration control model, so that the ammonia injection quantity is accurately regulated and controlled, the influence of time lag such as monitoring signals, reaction delay and the like on reduction denitration of SNCR technology in the CFB boiler is eliminated, and the denitration efficiency and denitration quality are further ensured; at the same time, according to the real-time monitoring of the running parameters in the CFB boiler and the NO of the smoke inlet and outlet x The gas concentration is calculated in real time, the actual denitration efficiency inputs a feedback correction instruction to a denitration control model, the accuracy of automatic control is further improved, self-adaptive dynamic adjustment can be carried out according to the actual running condition, and the reduction denitration efficiency and effect caused by sudden change of a certain parameter in a boiler are avoided; by adding an automatic early warning system, the system can operate for a long timeUnder the condition of automatic control errors, the system timely reminds people to overhaul and check, so that the loss and harm of the system are reduced to the greatest extent, and the safety and stability of the automatic control system are improved; in addition, the system has the advantages that the signal feedback instruction transmission efficiency is rapid in time, and the problem of large signal lag and inertia in the traditional denitration process is effectively solved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. The automatic control method for the denitration of the CFB boiler flue gas is characterized by comprising the following steps of:
s1, collecting and recording reaction parameters in CFB boilers at different moments in real time as measurement data;
s2, substituting the measured data into a denitration control model to predict and output denitration control quantity;
s3, adjusting and controlling the actual ammonia injection amount of the ammonia injection regulating valve according to the denitration control amount;
s4, measuring actual denitration efficiency as a basis to optimize and correct the denitration control model; the method for collecting and recording the reaction parameters in the CFB boiler at different moments in real time as measured data comprises the following steps:
s11, setting and monitoring the CFB boiler in real time according to a monitoring period;
s12, measuring bed temperature, air quantity and coal supply quantity parameters in the CFB boiler to determine the boiler load;
s13, measuring NO in flue gas in CFB boiler x The concentration of the gas as an initial concentration;
s14, acquiring the opening and closing degree of the ammonia injection regulating valve in the current monitoring period;
s15, acquiring and recording the ammonia spraying amount under the premise of the current monitoring period and the current opening and closing degree, and taking the ammonia spraying amount as an initial ammonia spraying amount;
s16, taking the boiler load, the initial concentration, the opening and closing degree and the initial ammonia injection amount in the same monitoring period as measurement data of a certain monitoring period;
substituting the measured data into a denitration control model to predict and output denitration control quantity comprises the following steps:
s21, constructing a gray Markov prediction model by combining the historical denitration concentration big data;
s22, constructing an ammonia injection regulation model by combining a brain model neural network of the big data of the historical ammonia injection quantity;
s23, constructing a denitration control model meeting a denitration control strategy by the gray Markov prediction model and the denitration control neural network;
s24, substituting the measured data into the denitration control model in sequence, and outputting denitration control quantity; the construction of the gray Markov prediction model by combining the historical denitration concentration big data comprises the following steps:
s211, constructing a gray prediction model by taking the historical denitration concentration big data as basic data;
s212, inputting a simulation data set into the gray model to carry out simulation prediction, and outputting a simulation prediction result;
s213, calculating a relative error between the true value and the predicted value according to the simulation predicted result, and dividing a state interval through an error range;
s214, combining probabilities of transferring the current state to the next state through a plurality of steps to form a state transfer probability matrix;
s215, predicting the state at the next moment according to the current state and the state transition matrix;
the construction of the ammonia spraying regulation model by combining the brain model neural network with the historical ammonia spraying amount big data comprises the following steps:
s221, constructing an initial model by using a Gaussian function as a basis function of a cerebellum model neural network;
s222, expanding the historical ammonia injection amount big data and dividing the data into a training set and a testing set;
s223, substituting the training set into the initial model to train so as to obtain an ammonia injection regulation model;
s223, performing test training and verification on the ammonia injection regulation model by using the test set.
2. The automatic control method for denitration of CFB boiler flue gas according to claim 1, wherein substituting the measurement data into the denitration control model in sequence, and outputting the denitration control amount comprises the steps of:
s241, substituting the boiler load, the initial concentration and the opening degree in the measured data of the current monitoring period into the ammonia injection regulation model to output a result as a basic ammonia injection quantity;
s242, substituting the initial concentration in the measured data of the current monitoring period into the gray Markov prediction model to predict to obtain a concentration prediction result of the next monitoring period;
s243, calculating a difference value between the concentration prediction result and the initial concentration in the current monitoring period, and calculating by combining working condition parameters of the CFB boiler to obtain a corresponding compensation ammonia injection amount;
s244, multiplying the sum of the basic ammonia injection amount and the compensation ammonia injection amount by a correction coefficient and a correction coefficient to obtain the actual ammonia injection amount in the next monitoring period, and taking the actual ammonia injection amount as the denitration control amount.
3. The automatic control method for flue gas denitration of the CFB boiler according to claim 2, wherein a cascade control strategy is adopted for adjusting and controlling the actual ammonia injection amount of the ammonia injection regulating valve according to the denitration control amount, the main parameter to be controlled is the initial concentration, the auxiliary parameter is the opening and closing degree, and the reference amount is the denitration control amount.
4. A method for automatically controlling denitration of flue gas in a CFB boiler according to claim 3, wherein the measuring actual denitration efficiency includes the following steps:
s41, measuring NO at actual outlet in real time x The concentration of the gas is used for calculating the actual denitration efficiency;
s42, substituting the actual denitration efficiency of the current monitoring period into a correction formula to calculate and obtain a correction coefficient of the next monitoring period;
s43, substituting the correction coefficient into the denitration control model to calculate the denitration control quantity of the next monitoring period;
s44, when the actual denitration efficiency of a plurality of continuous monitoring periods is lower than a preset safety threshold, the system sends out an early warning, and the denitration process is manually checked and the correction coefficient is modified.
5. The automatic control method for flue gas denitration of a CFB boiler according to claim 4, wherein the correction formula is:
wherein η represents a correction coefficient;
s represents the actual denitration efficiency of the current monitoring period;
S min representing a minimum value of a preset denitration efficiency standard;
S max representing the maximum value of the preset denitration efficiency standard.
6. An automatic control system for denitration of CFB boiler flue gas, for implementing the automatic control method for denitration of CFB boiler flue gas according to any one of claims 1 to 5, characterized in that the system comprises: the CFB boiler comprises a CFB boiler main body, a real-time monitoring unit, an automatic control unit, an ammonia injection regulating valve and a supervision control center;
the CFB boiler body is used for providing a denitration and reduction environment for flue gas;
the real-time monitoring unit is used for acquiring boiler parameters and NO in the flue gas in real time x A gas concentration;
the automatic control unit is used for realizing the self-adaptive regulation control of ammonia injection according to the monitoring data;
the ammonia injection regulating valve is used for changing the opening and closing degree to control the ammonia injection amount;
the supervision and control center is used for realizing remote supervision and parameter adjustment input of the system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211565197.4A CN116036849A (en) | 2022-12-07 | 2022-12-07 | CFB boiler flue gas denitration automatic control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211565197.4A CN116036849A (en) | 2022-12-07 | 2022-12-07 | CFB boiler flue gas denitration automatic control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116036849A true CN116036849A (en) | 2023-05-02 |
Family
ID=86120812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211565197.4A Pending CN116036849A (en) | 2022-12-07 | 2022-12-07 | CFB boiler flue gas denitration automatic control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116036849A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117452829A (en) * | 2023-12-25 | 2024-01-26 | 北京可视化智能科技股份有限公司 | Denitration intelligent decision method, system, terminal and storage medium |
-
2022
- 2022-12-07 CN CN202211565197.4A patent/CN116036849A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117452829A (en) * | 2023-12-25 | 2024-01-26 | 北京可视化智能科技股份有限公司 | Denitration intelligent decision method, system, terminal and storage medium |
| CN117452829B (en) * | 2023-12-25 | 2024-02-27 | 北京可视化智能科技股份有限公司 | Denitration intelligent decision method, system, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112580250A (en) | Thermal power generating unit denitration system based on deep learning and optimization control method | |
| CN106681381A (en) | SCR denitration system ammonia spraying quantity optimal control system and method based on intelligent feedforward signals | |
| CN104826492B (en) | Improvement method for selective catalytic reduction flue gas denitrification and ammonia injection control system | |
| CN104826493B (en) | A kind of control method of selective catalytic reduction flue gas denitrification system | |
| CN113433911B (en) | Accurate control system and method for ammonia spraying of denitration device based on accurate concentration prediction | |
| CN102778538B (en) | Soft measuring method based on improved SVM (Support Vector Machine) for measuring boiler unburned carbon content in fly ash | |
| CN105629736B (en) | The fired power generating unit SCR denitration Disturbance Rejection forecast Control Algorithm of data-driven | |
| RU2013130996A (en) | OPTIMIZED INTEGRATED CONTROL FOR A POWER PLANT OPERATING OXYGEN FUEL COMBUSTION | |
| CN111624876B (en) | Intelligent ammonia injection optimization control system | |
| CN105069185A (en) | Method for establishing air pre-heater clean factor calculation model by using smoke pressure difference, and application | |
| CN103759277A (en) | Intelligent soot blowing closed-loop control method, device and system for coal-fired power station boiler | |
| CN116036849A (en) | CFB boiler flue gas denitration automatic control method and system | |
| CN111829003A (en) | Power plant combustion control system and control method | |
| CN111897373A (en) | Model prediction-based ammonia injection flow adjusting method for SCR denitration device | |
| CN110263452A (en) | Flue gas Annual distribution characteristic analysis method, system and denitrating system in a kind of flue | |
| CN113359425A (en) | Thermal power plant boiler main steam temperature intelligent control system based on LSTM neural network PID optimization | |
| CN112742187A (en) | Method and device for controlling pH value in desulfurization system | |
| CN112613237B (en) | CFB unit NOx emission concentration prediction method based on LSTM | |
| CN112329959A (en) | Intelligent operation and maintenance system and method for thermal equipment | |
| CN109933884B (en) | Neural network inverse control method for SCR denitration system of coal-fired unit | |
| CN112783115A (en) | Online real-time optimization method and device for steam power system | |
| CN117270387A (en) | SCR denitration system low ammonia escape control method and system based on deep learning | |
| CN113488111B (en) | Ammonia injection amount optimization modeling method for SCR denitration system | |
| CN116776770A (en) | CFD numerical simulation coupling BP neural network based method for relieving high-temperature corrosion of boiler | |
| Fu et al. | Prediction model of desulfurization efficiency of coal-fired power plants based on long short-term memory neural network |
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 |