CN112418284B - Control method and system of SCR denitration system of all-condition power station - Google Patents
Control method and system of SCR denitration system of all-condition power station Download PDFInfo
- Publication number
- CN112418284B CN112418284B CN202011276325.4A CN202011276325A CN112418284B CN 112418284 B CN112418284 B CN 112418284B CN 202011276325 A CN202011276325 A CN 202011276325A CN 112418284 B CN112418284 B CN 112418284B
- Authority
- CN
- China
- Prior art keywords
- scr denitration
- individual
- predicted
- denitration system
- ammonia injection
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 claims abstract description 335
- 229910021529 ammonia Inorganic materials 0.000 claims abstract description 164
- 238000002347 injection Methods 0.000 claims abstract description 111
- 239000007924 injection Substances 0.000 claims abstract description 111
- 230000002068 genetic effect Effects 0.000 claims abstract description 34
- 238000005457 optimization Methods 0.000 claims abstract description 18
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 24
- 239000003546 flue gas Substances 0.000 claims description 24
- 210000002569 neuron Anatomy 0.000 claims description 18
- 238000003062 neural network model Methods 0.000 claims description 16
- 238000005507 spraying Methods 0.000 claims description 14
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 7
- 230000005611 electricity Effects 0.000 claims description 7
- 239000001301 oxygen Substances 0.000 claims description 7
- 229910052760 oxygen Inorganic materials 0.000 claims description 7
- 239000007789 gas Substances 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 6
- 230000006798 recombination Effects 0.000 claims description 6
- 238000005215 recombination Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010531 catalytic reduction reaction Methods 0.000 claims description 3
- 208000011580 syndromic disease Diseases 0.000 claims description 3
- 108700018263 Brassica oleracea SCR Proteins 0.000 claims 3
- 230000008859 change Effects 0.000 abstract description 6
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 230000004044 response Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 59
- 230000008569 process Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 239000003054 catalyst Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003638 chemical reducing agent Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 231100000252 nontoxic Toxicity 0.000 description 1
- 230000003000 nontoxic effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- B01D53/86—Catalytic processes
- B01D53/8621—Removing nitrogen compounds
- B01D53/8625—Nitrogen oxides
- B01D53/8631—Processes characterised by a specific device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Chemical & Material Sciences (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Environmental & Geological Engineering (AREA)
- Computing Systems (AREA)
- Analytical Chemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Treating Waste Gases (AREA)
Abstract
The invention discloses a control method and a control system of an SCR denitration system of an all-condition power station, wherein the control method comprises the following steps: adding denitration cost into an optimization objective function, adopting a predictive control structure, and carrying out model establishment and control quantity optimization by combining a neural network and a genetic algorithm, thereby realizing the optimal control of the ammonia injection quantity. The method can well overcome the defects of large inertia and large delay of the SCR denitration system, improve the response speed of ammonia injection quantity control to unit load change and improve the dynamic regulation quality of the SCR denitration system.
Description
Technical Field
The invention relates to the technical field of optimal control of coal-fired power plants, in particular to a control method and a control system of an SCR denitration system of an all-condition power plant.
Background
In the energy structure transformation process, the large-scale access of new energy power to the power grid brings forward the operation flexibility requirement to the coal-fired unit. The rapid deep load change means that the operation working condition of the unit is rapidly changed in a large range, and the fluctuation of NO x generated by combustion is aggravated by the change of the working condition of the boiler, so that the difficulty of realizing ultralow emission of NO x of the unit is definitely increased. SCR (SELECTIVE CATALYTIC Reduction), the selective catalytic Reduction method, is the most mature and widely used flue gas denitration technology in the world at present. SCR is a catalyst, and a reducing agent NH 3 and the like are utilized to selectively react with NO x in flue gas to generate non-toxic and pollution-free N 2 and H 2 O. SCR denitration is a mainstream flue gas denitration technology at present, and its reaction is a complicated physicochemical process, spouts ammonia volume more and can reduce NO x emission, but can increase economic cost to lead to ammonia escape increase, influence unit safe operation.
The existing SCR control system applied on site is mainly divided into two types, wherein one type is a fixed molar ratio control mode, and the mode belongs to open loop control and cannot meet the ultra-low emission requirement; the other is a fixed outlet NO x concentration control mode, a cascade PID control system is adopted at present on site, parameters of the cascade PID control system are set according to the characteristics of a reactor under a designed (rated) working condition, when the working condition of a unit is changed greatly, if the SCR system cannot be controlled effectively, denitration efficiency is low or ammonia escape phenomenon is serious, optimal control is difficult to realize, and the system is very unfavorable for economic and environment-friendly operation of a thermal power plant. Therefore, it is often difficult to obtain a good control effect by adopting an open loop control and a cascade PID control method.
Therefore, how to optimally control the denitration system, and realize the economic operation of the unit while ensuring the standard emission is a problem to be solved in the coal-fired power plant.
Disclosure of Invention
The invention aims to provide a control method and a control system for an SCR denitration system of an all-condition power station, so as to realize the optimal control of the denitration system, ensure the standard emission and realize the economic operation of a unit.
In order to achieve the above object, the present invention provides the following solutions:
a control method of an SCR denitration system of an all-condition power station comprises the following steps:
acquiring historical operation data of an SCR denitration system;
dividing the historical operation data into a plurality of load intervals by adopting a clustering algorithm to obtain the historical operation data of the load intervals;
Training a neural network model by utilizing historical operation data of each load interval respectively to obtain an SCR denitration system output prediction model of each load interval; the SCR denitration system outputs a prediction model for predicting the concentration of the outlet NO x and the escape of the outlet ammonia of the SCR denitration system at each prediction time point in the prediction time period according to the current working state data of the SCR denitration system and the ammonia spraying amount of each control time point in the prediction time period; the working state data comprise unit load, NO x concentration at an inlet of the SCR denitration system and flue gas flow;
According to a load instruction of the SCR denitration system, obtaining an SCR denitration system output prediction model of a load section where a unit load corresponding to the load instruction is located;
According to an output prediction model of the SCR denitration system in a load zone where a unit load corresponding to a load instruction is located, determining the ammonia injection quantity which is optimal for a multi-objective optimization function by adopting a genetic algorithm, and taking the ammonia injection quantity as the optimal ammonia injection quantity;
and controlling the SCR denitration system according to the optimal ammonia injection amount.
Optionally, the neural network model includes an input layer, an output layer, and an hidden layer, the input layer includes 4 neurons, the output layer includes 2 neurons, and the output layer includes 5 neurons.
Optionally, the output prediction model of the SCR denitration system according to the load interval where the unit load corresponding to the load instruction is located adopts a genetic algorithm to determine the ammonia injection amount that optimizes the multi-objective optimization function, and the method specifically includes:
initializing a population of a genetic algorithm by taking the ammonia spraying amount of each control time point in a predicted time period as an individual;
Judging whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount of each individual control time point in the population is between the lower limit value and the upper limit value of the valve opening or not, and obtaining a first judgment result;
If the first judgment result shows that the ammonia injection amount in the individual with the valve opening of the SCR denitration system smaller than the lower limit value of the valve opening is replaced by the ammonia injection amount corresponding to the lower limit value of the valve opening, and the ammonia injection amount in the individual with the valve opening of the SCR denitration system larger than the upper limit value of the valve opening is replaced by the ammonia injection amount corresponding to the upper limit value of the valve opening;
inputting each individual in the population into an SCR denitration system to output a prediction model, and obtaining predicted outlet NO x concentration and predicted outlet ammonia escape quantity of each predicted time point in a predicted time period corresponding to each individual;
Using the formula Correcting the predicted outlet NO x concentration of each predicted time point in the predicted time period corresponding to each individual to obtain corrected predicted outlet NO x concentration of each predicted time point in the predicted time period corresponding to each individual; wherein,The predicted outlet NO x concentration corrected for the time k+i.s 1,The predicted outlet NO x concentration at time k+i.s 1,For a predicted outlet NO x concentration at time k,The concentration of the actual outlet NO x of the SCR denitration system at the moment k is i, i represents the ith prediction time point, s 1 is the prediction step length, and r is the correction coefficient;
Calculating a first objective function value and a second objective function value of each individual by using the first objective function and the second objective function respectively according to the predicted outlet NO x concentration, the predicted outlet ammonia escape amount and the corrected predicted outlet NO x concentration at each predicted time point in the predicted time period corresponding to each individual;
Determining an individual with the smallest first objective function in the individuals meeting the second objective function in the population as an optimal individual of the L-th iteration, and setting an individual with larger first objective function value in the optimal individual of the L-th iteration and the global optimal individual of the L-1-th iteration as a global optimal individual of the L-th iteration;
Judging whether the iteration times are larger than an iteration times threshold value or not, and obtaining a second judgment result;
If the second judgment result indicates no, increasing the number of iterations by 1, updating the population by adopting genetic, mutation and recombination modes in a genetic algorithm, and returning to the step of judging whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount at each control time point in each individual in the population is between the lower limit value and the upper limit value of the valve opening or not to obtain a first judgment result;
And if the second judgment result shows that the overall optimal individual in the L-th iteration is output as the optimal ammonia injection amount.
Optionally, the first objective function is:
wherein J 1 denotes a first objective function value, For the predicted outlet ammonia slip at time k+i.s 1, M 2 is the liquid ammonia price, P is the number of predicted time points in the predicted time period, Q gas is the flue gas flow,M 1 is the oxygen content of the flue gas, M 1 is the pollution discharge cost,The ammonia spraying amount at the moment k+j.s 2 is j, the j is the j-th control time point, s 2 is the control step length, M is the number of the control time points in the prediction time period, N is the generating capacity of the unit, M 3 is the electricity price patch price, omega 1 is a first weight coefficient, and omega 2 is a second weight coefficient;
optionally, the second objective function is:
Wherein J 2 is the second objective function value, P is the number of predicted time points in the predicted time period, r (k+i·s 1) is the expected value of the concentration of the outlet NO x at the time of k+i·s 1, ||Δu (k+j·s 2) || is the difference between the ammonia injection amount at the time of k+j·s 2 and the expected ammonia injection amount, J is the jth control time point, s 2 is the control step length, M is the number of control time points in the predicted time period, ω 3 is the third weight coefficient.
A control system for an all-condition power station SCR denitration system, the control system comprising:
the historical operation data acquisition module is used for acquiring historical operation data of the SCR denitration system;
the clustering module is used for dividing the historical operation data into a plurality of load intervals by adopting a clustering algorithm to obtain the historical operation data of the load intervals;
The training module is used for training the neural network model by utilizing the historical operation data of each load interval respectively to obtain an SCR denitration system output prediction model of each load interval; the SCR denitration system output prediction model is used for predicting the outlet NOx concentration and outlet ammonia escape of the SCR denitration system at each prediction time point in the prediction time period according to the current working state data of the SCR denitration system and the ammonia injection amount of each control time point in the prediction time period; the working state data comprise unit load, NOx concentration at an inlet of the SCR denitration system and flue gas flow;
The SCR denitration system output prediction model selection module is used for acquiring an SCR denitration system output prediction model of a load section where a unit load corresponding to a load instruction is located according to the load instruction of the SCR denitration system;
The optimal ammonia injection amount determining module is used for determining the ammonia injection amount which is optimal for a multi-objective optimization function by adopting a genetic algorithm according to an output prediction model of the SCR denitration system in a load zone where the unit load corresponding to the load instruction is located, and the ammonia injection amount is used as the optimal ammonia injection amount;
and the control module is used for controlling the SCR out-of-stock system according to the optimal ammonia injection amount.
Optionally, the neural network model includes an input layer, an output layer, and an hidden layer, the input layer includes 4 neurons, the output layer includes 2 neurons, and the output layer includes 5 neurons.
Optionally, the optimal ammonia injection amount determining module specifically includes:
The initialization submodule is used for initializing the population of the genetic algorithm by taking the ammonia spraying amount of each control time point in the prediction time period as an individual;
The first judging submodule is used for judging whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount of each individual control time point in the population is between the lower limit value and the upper limit value of the valve opening or not, and obtaining a first judging result;
An individual updating sub-module, configured to replace, if the first determination result indicates no, an ammonia injection amount in an individual having a valve opening of the SCR denitration system smaller than a lower limit value of the valve opening with an ammonia injection amount corresponding to the lower limit value of the valve opening, and replace an ammonia injection amount in an individual having a valve opening of the SCR denitration system larger than an upper limit value of the valve opening with an ammonia injection amount corresponding to the upper limit value of the valve opening;
the prediction submodule is used for inputting each individual in the population into the SCR denitration system to output a prediction model, and obtaining the predicted outlet NOx concentration and the predicted outlet ammonia escape amount of each predicted time point in the prediction time period corresponding to each individual;
A syndrome module for using the formula Correcting the predicted outlet NOx concentration of each predicted time point in the predicted time period corresponding to each individual to obtain corrected predicted outlet NOx concentration of each predicted time point in the predicted time period corresponding to each individual; wherein,For the predicted outlet NOx concentration corrected at time k + i-s 1,For a predicted outlet NOx concentration at time k + i-s 1,For a predicted outlet NOx concentration at time k,The actual outlet NOx concentration of the SCR denitration system at the moment k is i, i represents the ith prediction time point, s 1 is the prediction step length, and r is the correction coefficient;
an objective function value calculation sub-module, configured to calculate a first objective function value and a second objective function value of each individual by using the first objective function and the second objective function, respectively, according to the predicted outlet NOx concentration, the predicted outlet ammonia slip amount, and the corrected predicted outlet NOx concentration at each predicted time point in the predicted time period corresponding to each individual;
The optimal individual determining sub-module is used for determining an individual with the smallest first objective function in the individuals meeting the second objective function in the population as an optimal individual of the L-th iteration, and setting the optimal individual of the L-th iteration and an individual with larger first objective function value in the global optimal individual of the L-1-th iteration as the global optimal individual of the L-th iteration;
The second judging sub-module is used for judging whether the iteration times are larger than the iteration times threshold value or not, and obtaining a second judging result;
A population updating sub-module, configured to increase the number of iterations by 1 if the second determination result indicates no, update the population by adopting a genetic, mutation and recombination method in a genetic algorithm, and return to the step of determining whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount at each control time point in each individual in the population is between the lower limit value and the upper limit value of the valve opening, thereby obtaining a first determination result;
And the optimal ammonia injection quantity output sub-module is used for outputting a global optimal individual of the L-th iteration as the optimal ammonia injection quantity if the second judgment result shows that the global optimal individual is the optimal ammonia injection quantity.
Optionally, the first objective function is:
wherein J 1 denotes a first objective function value, For the predicted outlet ammonia slip at time k+i.s 1, M 2 is the liquid ammonia price, P is the number of predicted time points in the predicted time period, Q gas is the flue gas flow,M 1 is the oxygen content of the flue gas, M 1 is the pollution discharge cost,The ammonia spraying amount at the moment k+j.s 2 is j, the j is the j-th control time point, s 2 is the control step length, M is the number of the control time points in the prediction time period, N is the generating capacity of the unit, M 3 is the electricity price patch price, omega 1 is a first weight coefficient, and omega 2 is a second weight coefficient;
optionally, the second objective function is:
Wherein J 2 is the second objective function value, P is the number of predicted time points in the predicted time period, r (k+i·s 1) is the expected value of the outlet NOx concentration at the time of k+i·s 1, ||Δu (k+j·s 2) ||is the difference between the ammonia injection amount at the time of k+j·s 2 and the expected ammonia injection amount, J is the jth control time point, s 2 is the control step length, M is the number of control time points in the predicted time period, ω 3 is the third weight coefficient.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
The invention discloses a control method and a control system of an SCR denitration system of an all-condition power station, wherein the control method comprises the following steps: adding denitration cost into an optimization objective function, adopting a predictive control structure, and carrying out model establishment and control quantity optimization by combining a neural network and a genetic algorithm, thereby realizing the optimal control of the ammonia injection quantity. The method can well overcome the defects of large inertia and large delay of the SCR denitration system, improve the response speed of ammonia injection quantity control to unit load change and improve the dynamic regulation quality of the SCR denitration system.
By adopting a multi-target control mode, the upper and lower limit of the valve opening degree, the emission concentration of the outlet NO x, the ammonia escape and the economic index of the denitration system are considered in the prediction control, the influence on the system performance due to the saturation of an actuating mechanism is avoided, the ammonia injection amount can be reduced as much as possible on the basis that the concentration of the outlet NO x reaches the target value, and the running cost and the ammonia escape rate are effectively reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that 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 control method of an SCR denitration system of an all-condition power station;
FIG. 2 is a schematic diagram of a control method of an SCR denitration system of an all-condition power station;
FIG. 3 is a schematic diagram of the method for determining the ammonia injection amount for optimizing the multi-objective optimization function by adopting the genetic algorithm
FIG. 4 is a flow chart of determining the amount of ammonia injection that optimizes the multi-objective optimization function using a genetic algorithm in accordance with the present invention.
Detailed Description
The invention aims to provide a control method and a control system for an SCR denitration system of an all-condition power station, so as to realize the optimal control of the denitration system, ensure the standard emission and realize the economic operation of a unit.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
1-2, The invention provides a control method of an SCR denitration system of an all-condition power station, which comprises the following steps:
Step 101, acquiring historical operation data of an SCR denitration system.
The historical operation data comprise the unit load, the NOx concentration at the inlet of the SCR denitration system, the flue gas flow rate, the ammonia injection amount, the NOx concentration at the outlet of the SCR denitration system and ammonia slip.
The frequency of the invention when historical operating data is collected is once every 2 minutes.
And step 101, dividing the historical operation data into a plurality of load sections by adopting a clustering algorithm to obtain the historical operation data of the plurality of load sections.
The historical data is divided according to the load section through a clustering algorithm and respectively marked as a high load section, a medium load section and a low load section.
Step 102, training a neural network model by using historical operation data of each load interval respectively to obtain an SCR denitration system output prediction model of each load interval; the SCR denitration system outputs a prediction model for predicting the concentration of the outlet NO x and the escape of the outlet ammonia of the SCR denitration system at each prediction time point in the prediction time period according to the current working state data of the SCR denitration system and the ammonia spraying amount of each control time point in the prediction time period; the working state data comprise unit load, NO x concentration at an inlet of the SCR denitration system and flue gas flow.
The neural network models are respectively trained according to the historical data of different load intervals, different neural network models are selected according to the real-time input data of the SCR denitration system in the process of running the control algorithm, the model prediction accuracy is remarkably improved, and the model prediction method can be better adapted to the background of wide-range change of the working conditions of the unit.
The neural network model is an LSTM neural network and comprises an input layer, an output layer and an implicit layer, wherein the input layer comprises 4 neurons, the output layer comprises 2 neurons, and the output layer comprises 5 neurons.
Before training, the invention also carries out normalization pretreatment on the historical operation data. During training, the training frequency of the neural network model is set to be 1000 times, the learning rate is set to be 0.05, and the minimum error is set to be 10 -3.
And step 103, acquiring an SCR denitration system output prediction model of a load section where the unit load corresponding to the load instruction is located according to the load instruction of the SCR denitration system.
And 104, determining the ammonia injection quantity which is optimal for the multi-objective optimization function by adopting a genetic algorithm according to an output prediction model of the SCR denitration system in a load zone where the unit load corresponding to the load instruction is located, and taking the ammonia injection quantity as the optimal ammonia injection quantity.
The multi-objective optimization function of the invention ensures that the concentration of the NO x at the outlet of the SCR in the denitration control system meets the requirement, and the outlet NO x, ammonia escape and related economic cost are taken into account, so that the unit can safely and economically operate on the premise of standard emission. And adding the upper and lower limits of the valve opening to the constraint objective function.
According to the invention, online rolling optimization is performed in a prediction time domain, and a control quantity sequence is determined by optimizing in an objective function by using a genetic algorithm, so that the predicted output of the neural network model can be maximally close to the concentration of NO x at an outlet and the expected value of ammonia escape.
Compared with the traditional iterative algorithm, the genetic algorithm of the invention can well avoid the phenomenon of dead loop caused by trapping in a local minimum trap, and is a global optimization algorithm.
As shown in fig. 3 and 4, in step 103, according to the output prediction model of the SCR denitration system in the load zone where the unit load corresponding to the load command is located, a genetic algorithm is adopted to determine the ammonia injection amount that optimizes the multi-objective optimization function, and the method specifically includes:
Step 401, initializing a population of a genetic algorithm by taking the ammonia spraying amount of each control time point in a predicted time period as an individual; the population size of the genetic algorithm is set to be 300, the maximum iteration number (iteration number threshold) is 100, the mating probability is 0.85, and the variation probability is 0.2.
Step 402, judging whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount at each control time point in each individual in the population is between the lower limit value and the upper limit value of the valve opening, and obtaining a first judgment result.
If the first determination result indicates no, step 403 is performed, in which the ammonia injection amount in the individual having the valve opening of the SCR denitration system smaller than the lower limit value of the valve opening is replaced with the ammonia injection amount corresponding to the lower limit value of the valve opening, and the ammonia injection amount in the individual having the valve opening of the SCR denitration system larger than the upper limit value of the valve opening is replaced with the ammonia injection amount corresponding to the upper limit value of the valve opening. The invention considers the upper and lower limit of the valve opening, the emission concentration of the NO x at the outlet, the ammonia escape and the economic index of the denitration system, avoids influencing the system performance due to the saturation of an actuating mechanism, reduces the ammonia spraying amount as much as possible on the basis of ensuring that the concentration of the NO x at the outlet reaches the target value, and effectively reduces the running cost and the ammonia escape rate.
And step 404, inputting each individual in the population into the SCR denitration system to output a prediction model, and obtaining the predicted outlet NO x concentration and the predicted outlet ammonia escape amount of each predicted time point in the prediction time period corresponding to each individual. According to the method, the output value of the output prediction model of the SCR denitration system is subjected to inverse normalization treatment, so that the predicted value of the concentration of the NOx and the ammonia slip of the outlet of the SCR denitration system at each predicted time point is obtained.
Step 405, using the formulaCorrecting the predicted outlet NO x concentration of each predicted time point in the predicted time period corresponding to each individual to obtain corrected predicted outlet NO x concentration of each predicted time point in the predicted time period corresponding to each individual; wherein,The predicted outlet NO x concentration corrected for the time k+i.s 1,The predicted outlet NO x concentration at time k+i.s 1,For a predicted outlet NO x concentration at time k,The actual outlet NO x concentration of the SCR denitration system at the moment k is i, i represents the ith prediction time point, s 1 is a prediction step length, and r is a correction coefficient. The number of predicted time points of the present invention is 10, and the number of control time points is 3. The invention comprises the following steps: at time k, the ammonia injection amount obtained by optimizing is recorded as u (k-1), and the actual output y m (k-1) of the system and the output y (k-1) of the prediction model can be obtained. Accordingly, y m (k) and y (k+1) can be obtained by u (k). Since there is an inevitable deviation between the prediction model and the actual system, the deviation between the actual output y m (k) at time k and the model output y (k) at time k is regarded as an estimated value of the prediction error at time k, and is compensated as a feedback correction signal into the prediction model output y (k+i) at time k+i, that is, the feedback corrected predicted value y p (k+i) is: y p(k+i)＝y(k+i)+r(ym (k) -y (k)). The feedback correction link considers the model prediction error at the previous moment, and can improve the model prediction accuracy to a certain extent, thereby improving the control quality of the prediction control.
Step 406, calculating a first objective function value and a second objective function value of each individual by using the first objective function and the second objective function according to the predicted outlet NO x concentration, the predicted outlet ammonia escape amount and the corrected predicted outlet NO x concentration at each predicted time point in the predicted time period corresponding to each individual.
Step 407, determining an individual with the smallest first objective function in the individuals meeting the second objective function in the population as an optimal individual of the L-th iteration, and setting an individual with larger first objective function value in the optimal individual of the L-th iteration and the global optimal individual of the L-1-th iteration as a global optimal individual of the L-th iteration;
Step 408, determining whether the iteration number is greater than the iteration number threshold, and obtaining a second determination result.
And 409, if the second determination result indicates no, increasing the number of iterations by 1, updating the population by adopting the genetic, mutation and recombination modes in the genetic algorithm, and returning to the step of determining whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount at each control time point in each individual in the population is between the lower limit value and the upper limit value of the valve opening, thereby obtaining a first determination result.
And step 410, if the second judgment result indicates that the global optimum is the optimal ammonia injection amount, outputting the global optimum of the L-th iteration.
Wherein the first objective function is:
wherein J 1 denotes a first objective function value, For the predicted outlet ammonia slip at time k+i.s 1, M 2 is the liquid ammonia price, P is the number of predicted time points in the predicted time period, Q gas is the flue gas flow,M 1 is the oxygen content of the flue gas, M 1 is the pollution discharge cost,The ammonia spraying amount at the moment k+j.s 2 is j, the j is the j-th control time point, s 2 is the control step length, M is the number of the control time points in the prediction time period, N is the generating capacity of the unit, M 3 is the electricity price patch price, omega 1 is a first weight coefficient, and omega 2 is a second weight coefficient;
the second objective function is:
Wherein J 2 is the second objective function value, P is the number of predicted time points in the predicted time period, r (k+i·s 1) is the expected value of the concentration of the outlet NO x at the time of k+i·s 1, ||Δu (k+j·s 2) || is the difference between the ammonia injection amount at the time of k+j·s 2 and the expected ammonia injection amount, J is the jth control time point, s 2 is the control step length, M is the number of control time points in the predicted time period, ω 3 is the third weight coefficient.
The objective function of the invention comprises ammonia escape amount, flue gas flow, flue gas oxygen content, nitrogen oxide discharge amount, pollution discharge cost price, ammonia flow, liquid ammonia price, unit power generation amount and electricity price subsidy price.
And 105, controlling the SCR out-of-stock system according to the optimal ammonia injection amount.
The invention also provides a control system of the SCR denitration system of the all-condition power station, which comprises:
the historical operation data acquisition module is used for acquiring historical operation data of the SCR denitration system.
And the clustering module is used for dividing the historical operation data into a plurality of load intervals by adopting a clustering algorithm to obtain the historical operation data of the plurality of load intervals.
The training module is used for training the neural network model by utilizing the historical operation data of each load interval respectively to obtain an SCR denitration system output prediction model of each load interval; the SCR denitration system outputs a prediction model for predicting the concentration of the outlet NO x and the escape of the outlet ammonia of the SCR denitration system at each prediction time point in the prediction time period according to the current working state data of the SCR denitration system and the ammonia spraying amount of each control time point in the prediction time period; the working state data comprise unit load, NO x concentration at an inlet of the SCR denitration system and flue gas flow.
The neural network model comprises an input layer, an output layer and an implicit layer, wherein the input layer comprises 4 neurons, the output layer comprises 2 neurons, and the output layer comprises 5 neurons.
The SCR denitration system output prediction model selection module is used for acquiring an SCR denitration system output prediction model of a load section where a unit load corresponding to a load instruction is located according to the load instruction of the SCR denitration system.
The optimal ammonia injection amount determining module is used for determining the ammonia injection amount which is optimal for the multi-objective optimization function by adopting a genetic algorithm according to the output prediction model of the SCR denitration system in the load section where the unit load corresponding to the load instruction is located, and the ammonia injection amount is used as the optimal ammonia injection amount.
The optimal ammonia injection amount determining module specifically comprises: the initialization submodule is used for initializing the population of the genetic algorithm by taking the ammonia spraying amount of each control time point in the prediction time period as an individual; the first judging submodule is used for judging whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount of each individual control time point in the population is between the lower limit value and the upper limit value of the valve opening or not, and obtaining a first judging result; an individual updating sub-module, configured to replace, if the first determination result indicates no, an ammonia injection amount in an individual having a valve opening of the SCR denitration system smaller than a lower limit value of the valve opening with an ammonia injection amount corresponding to the lower limit value of the valve opening, and replace an ammonia injection amount in an individual having a valve opening of the SCR denitration system larger than an upper limit value of the valve opening with an ammonia injection amount corresponding to the upper limit value of the valve opening; the prediction submodule is used for inputting each individual in the population into the SCR denitration system to output a prediction model, and obtaining the predicted outlet NO x concentration and the predicted outlet ammonia escape amount of each predicted time point in the prediction time period corresponding to each individual; a syndrome module for using the formulaCorrecting the predicted outlet NO x concentration of each predicted time point in the predicted time period corresponding to each individual to obtain corrected predicted outlet NO x concentration of each predicted time point in the predicted time period corresponding to each individual; wherein,The predicted outlet NO x concentration corrected for the time k+i.s 1,The predicted outlet NO x concentration at time k+i.s 1,For a predicted outlet NO x concentration at time k,The concentration of the actual outlet NO x of the SCR denitration system at the moment k is i, i represents the ith prediction time point, s 1 is the prediction step length, and r is the correction coefficient; an objective function value calculation sub-module, configured to calculate a first objective function value and a second objective function value of each individual by using the first objective function and the second objective function, respectively, according to the predicted outlet NO x concentration, the predicted outlet ammonia escape amount, and the corrected predicted outlet NO x concentration at each predicted time point in the predicted time period corresponding to each individual; the optimal individual determining sub-module is used for determining an individual with the smallest first objective function in the individuals meeting the second objective function in the population as an optimal individual of the L-th iteration, and setting the optimal individual of the L-th iteration and an individual with larger first objective function value in the global optimal individual of the L-1-th iteration as the global optimal individual of the L-th iteration; the second judging sub-module is used for judging whether the iteration times are larger than the iteration times threshold value or not, and obtaining a second judging result; a population updating sub-module, configured to increase the number of iterations by 1 if the second determination result indicates no, update the population by adopting a genetic, mutation and recombination method in a genetic algorithm, and return to the step of determining whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount at each control time point in each individual in the population is between the lower limit value and the upper limit value of the valve opening, thereby obtaining a first determination result; and the optimal ammonia injection quantity output sub-module is used for outputting a global optimal individual of the L-th iteration as the optimal ammonia injection quantity if the second judgment result shows that the global optimal individual is the optimal ammonia injection quantity.
And the control module is used for controlling the SCR out-of-stock system according to the optimal ammonia injection amount.
Wherein the first objective function is:
wherein J 1 denotes a first objective function value, For the predicted outlet ammonia slip at time k+i.s 1, M 2 is the liquid ammonia price, P is the number of predicted time points in the predicted time period, Q gas is the flue gas flow,M 1 is the oxygen content of the flue gas, M 1 is the pollution discharge cost,The ammonia injection amount at the moment k+j.s 2 is j, the j is the j-th control time point, s 2 is the control step length, M is the number of control time points in the prediction time period, N is the generating capacity of the unit, M 3 is the electricity price patch price, omega 1 is a first weight coefficient, and omega 2 is a second weight coefficient.
The second objective function is:
Wherein J 2 is the second objective function value, P is the number of predicted time points in the predicted time period, r (k+i·s 1) is the expected value of the concentration of the outlet NO x at the time of k+i·s 1, ||Δu (k+j·s 2) || is the difference between the ammonia injection amount at the time of k+j·s 2 and the expected ammonia injection amount, J is the jth control time point, s 2 is the control step length, M is the number of control time points in the predicted time period, ω 3 is the third weight coefficient.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
1. The method can better overcome the defects of large inertia and large delay of the SCR denitration system, improve the response speed of ammonia injection amount control to unit load change, and improve the dynamic adjustment quality of the SCR denitration system;
2. By adopting a multi-target control mode, the upper and lower limit of the valve opening, the valve action rate limit and the emission concentration of the outlet NO x, the ammonia escape and the economic index of the denitration system are considered in the prediction control, the influence on the system performance due to the saturation of an actuating mechanism is avoided, the ammonia injection amount can be reduced as much as possible on the basis that the concentration of the outlet NO x reaches a target value, and the running cost and the ammonia escape rate are effectively reduced;
3. the predictive control technology has the advantages of low model requirement, easy online calculation and good control effect.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The principles and embodiments of the present invention have been described herein with reference to specific examples, which are intended to be only illustrative of the methods and concepts underlying the invention, and not all examples are intended to be within the scope of the invention as defined by the appended claims.
Claims (8)
1. The control method of the SCR denitration system of the all-condition power station is characterized by comprising the following steps of:
acquiring historical operation data of an SCR denitration system;
dividing the historical operation data into a plurality of load intervals by adopting a clustering algorithm to obtain the historical operation data of the load intervals;
Training a neural network model by utilizing historical operation data of each load interval respectively to obtain an SCR denitration system output prediction model of each load interval; the SCR denitration system outputs a prediction model for predicting the concentration of the outlet NO x and the escape of the outlet ammonia of the SCR denitration system at each prediction time point in the prediction time period according to the current working state data of the SCR denitration system and the ammonia spraying amount of each control time point in the prediction time period; the working state data comprise unit load, NO x concentration at an inlet of the SCR denitration system and flue gas flow;
According to a load instruction of the SCR denitration system, obtaining an SCR denitration system output prediction model of a load section where a unit load corresponding to the load instruction is located;
According to an output prediction model of the SCR denitration system in a load zone where a unit load corresponding to a load instruction is located, determining the ammonia injection quantity which is optimal for a multi-objective optimization function by adopting a genetic algorithm, and taking the ammonia injection quantity as the optimal ammonia injection quantity;
controlling an SCR (selective catalytic reduction) out-of-stock system according to the optimal ammonia injection amount;
The output prediction model of the SCR denitration system in the load zone where the unit load corresponding to the load instruction is located adopts a genetic algorithm to determine the ammonia injection quantity which is optimal for the multi-objective optimization function, and the ammonia injection quantity is used as the optimal ammonia injection quantity and specifically comprises the following steps:
initializing a population of a genetic algorithm by taking the ammonia spraying amount of each control time point in a predicted time period as an individual;
Judging whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount of each individual control time point in the population is between the lower limit value and the upper limit value of the valve opening or not, and obtaining a first judgment result;
If the first judgment result shows that the ammonia injection amount in the individual with the valve opening of the SCR denitration system smaller than the lower limit value of the valve opening is replaced by the ammonia injection amount corresponding to the lower limit value of the valve opening, and the ammonia injection amount in the individual with the valve opening of the SCR denitration system larger than the upper limit value of the valve opening is replaced by the ammonia injection amount corresponding to the upper limit value of the valve opening;
inputting each individual in the population into an SCR denitration system to output a prediction model, and obtaining predicted outlet NO x concentration and predicted outlet ammonia escape quantity of each predicted time point in a predicted time period corresponding to each individual;
Using the formula Correcting the predicted outlet NO x concentration of each predicted time point in the predicted time period corresponding to each individual to obtain corrected predicted outlet NO x concentration of each predicted time point in the predicted time period corresponding to each individual; wherein,The predicted outlet NO x concentration corrected for the time k+i.s 1,The predicted outlet NO x concentration at time k+i.s 1,For a predicted outlet NO x concentration at time k,The concentration of the actual outlet NO x of the SCR denitration system at the moment k is i, i represents the ith prediction time point, s 1 is the prediction step length, and r is the correction coefficient;
Calculating a first objective function value and a second objective function value of each individual by using the first objective function and the second objective function respectively according to the predicted outlet NO x concentration, the predicted outlet ammonia escape amount and the corrected predicted outlet NO x concentration at each predicted time point in the predicted time period corresponding to each individual;
determining an individual with the smallest first objective function in the individuals meeting the second objective function in the population as an optimal individual of the L-th iteration, setting the optimal individual of the L-th iteration as the global optimal individual of the L-th iteration when the first objective function value of the optimal individual of the L-th iteration is greater than or equal to the first objective function value of the global optimal individual of the L-1 th iteration, otherwise setting the global optimal individual of the L-1 th iteration as the global optimal individual of the L-th iteration;
Judging whether the iteration times are larger than an iteration times threshold value or not, and obtaining a second judgment result;
If the second judgment result indicates no, increasing the number of iterations by 1, updating the population by adopting genetic, mutation and recombination modes in a genetic algorithm, and returning to the step of judging whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount at each control time point in each individual in the population is between the lower limit value and the upper limit value of the valve opening or not to obtain a first judgment result;
And if the second judgment result shows that the overall optimal individual in the L-th iteration is output as the optimal ammonia injection amount.
2. The control method of an all-condition power station SCR denitration system according to claim 1, wherein the neural network model comprises an input layer, an output layer and an implicit layer, the input layer comprises 4 neurons, the output layer comprises 2 neurons, and the output layer comprises 5 neurons.
3. The control method of an SCR denitration system of an all-condition power station according to claim 1, wherein the first objective function is:
wherein J 1 denotes a first objective function value, For the predicted outlet ammonia slip at time k+i.s 1, M 2 is the liquid ammonia price, P is the number of predicted time points in the predicted time period, Q gas is the flue gas flow,M 1 is the oxygen content of the flue gas, M 1 is the pollution discharge cost,The ammonia injection amount at the moment k+j.s 2 is j, the j is the j-th control time point, s 2 is the control step length, M is the number of control time points in the prediction time period, N is the generating capacity of the unit, M 3 is the electricity price patch price, omega 1 is a first weight coefficient, and omega 2 is a second weight coefficient.
4. The control method of an SCR denitration system of an all-condition power station according to claim 1, wherein the second objective function is:
Wherein J 2 is the second objective function value, P is the number of predicted time points in the predicted time period, r (k+i·s 1) is the expected value of the concentration of the outlet NO x at the time of k+i·s 1, ||Δu (k+j·s 2) || is the difference between the ammonia injection amount at the time of k+j·s 2 and the expected ammonia injection amount, J is the jth control time point, s 2 is the control step length, M is the number of control time points in the predicted time period, ω 3 is the third weight coefficient.
5. Control system of full operating mode power station SCR deNOx systems, its characterized in that, control system includes:
the historical operation data acquisition module is used for acquiring historical operation data of the SCR denitration system;
the clustering module is used for dividing the historical operation data into a plurality of load intervals by adopting a clustering algorithm to obtain the historical operation data of the load intervals;
The training module is used for training the neural network model by utilizing the historical operation data of each load interval respectively to obtain an SCR denitration system output prediction model of each load interval; the SCR denitration system output prediction model is used for predicting the outlet NOx concentration and outlet ammonia escape of the SCR denitration system at each prediction time point in the prediction time period according to the current working state data of the SCR denitration system and the ammonia injection amount of each control time point in the prediction time period; the working state data comprise unit load, NOx concentration at an inlet of the SCR denitration system and flue gas flow;
The SCR denitration system output prediction model selection module is used for acquiring an SCR denitration system output prediction model of a load section where a unit load corresponding to a load instruction is located according to the load instruction of the SCR denitration system;
The optimal ammonia injection amount determining module is used for determining the ammonia injection amount which is optimal for a multi-objective optimization function by adopting a genetic algorithm according to an output prediction model of the SCR denitration system in a load zone where the unit load corresponding to the load instruction is located, and the ammonia injection amount is used as the optimal ammonia injection amount;
The control module is used for controlling the SCR denitration system according to the optimal ammonia injection amount;
the optimal ammonia injection amount determining module specifically comprises:
The initialization submodule is used for initializing the population of the genetic algorithm by taking the ammonia spraying amount of each control time point in the prediction time period as an individual;
The first judging submodule is used for judging whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount of each individual control time point in the population is between the lower limit value and the upper limit value of the valve opening or not, and obtaining a first judging result;
An individual updating sub-module, configured to replace, if the first determination result indicates no, an ammonia injection amount in an individual having a valve opening of the SCR denitration system smaller than a lower limit value of the valve opening with an ammonia injection amount corresponding to the lower limit value of the valve opening, and replace an ammonia injection amount in an individual having a valve opening of the SCR denitration system larger than an upper limit value of the valve opening with an ammonia injection amount corresponding to the upper limit value of the valve opening;
the prediction submodule is used for inputting each individual in the population into the SCR denitration system to output a prediction model, and obtaining the predicted outlet NOx concentration and the predicted outlet ammonia escape amount of each predicted time point in the prediction time period corresponding to each individual;
A syndrome module for using the formula Correcting the predicted outlet NOx concentration of each predicted time point in the predicted time period corresponding to each individual to obtain corrected predicted outlet NOx concentration of each predicted time point in the predicted time period corresponding to each individual; wherein,For the predicted outlet NOx concentration corrected at time k + i-s 1,For a predicted outlet NOx concentration at time k + i-s 1,For a predicted outlet NOx concentration at time k,The actual outlet NOx concentration of the SCR denitration system at the moment k is i, i represents the ith prediction time point, s 1 is the prediction step length, and r is the correction coefficient;
an objective function value calculation sub-module, configured to calculate a first objective function value and a second objective function value of each individual by using the first objective function and the second objective function, respectively, according to the predicted outlet NOx concentration, the predicted outlet ammonia slip amount, and the corrected predicted outlet NOx concentration at each predicted time point in the predicted time period corresponding to each individual;
The optimal individual determining submodule is used for determining an individual with the smallest first objective function in the individuals meeting the second objective function in the population as an optimal individual of the L-th iteration, setting the optimal individual of the L-th iteration as the global optimal individual of the L-th iteration when the first objective function value of the optimal individual of the L-th iteration is greater than or equal to the first objective function value of the global optimal individual of the L-1-th iteration, otherwise setting the global optimal individual of the L-1-th iteration as the global optimal individual of the L-th iteration;
The second judging sub-module is used for judging whether the iteration times are larger than the iteration times threshold value or not, and obtaining a second judging result;
A population updating sub-module, configured to increase the number of iterations by 1 if the second determination result indicates no, update the population by adopting a genetic, mutation and recombination method in a genetic algorithm, and return to the step of determining whether the valve opening of the SCR denitration system corresponding to the ammonia injection amount at each control time point in each individual in the population is between the lower limit value and the upper limit value of the valve opening, thereby obtaining a first determination result;
And the optimal ammonia injection quantity output sub-module is used for outputting a global optimal individual of the L-th iteration as the optimal ammonia injection quantity if the second judgment result shows that the global optimal individual is the optimal ammonia injection quantity.
6. The control system of an all-condition power plant SCR denitration system of claim 5, wherein said neural network model comprises an input layer, an output layer and an implicit layer, said input layer comprising 4 neurons, said output layer comprising 2 neurons, said output layer comprising 5 neurons.
7. The control system of an all-condition power plant SCR denitration system of claim 5, wherein said first objective function is:
wherein J 1 denotes a first objective function value, For the predicted outlet ammonia slip at time k+i.s 1, M 2 is the liquid ammonia price, P is the number of predicted time points in the predicted time period, Q gas is the flue gas flow,M 1 is the oxygen content of the flue gas, M 1 is the pollution discharge cost,The ammonia injection amount at the moment k+j.s 2 is j, the j is the j-th control time point, s 2 is the control step length, M is the number of control time points in the prediction time period, N is the generating capacity of the unit, M 3 is the electricity price patch price, omega 1 is a first weight coefficient, and omega 2 is a second weight coefficient.
8. The control system of an all-condition power plant SCR denitration system of claim 5, wherein said second objective function is:
Wherein J 2 is the second objective function value, P is the number of predicted time points in the predicted time period, r (k+i·s 1) is the expected value of the concentration of the outlet NO x at the time of k+i·s 1, ||Δu (k+j·s 2) || is the difference between the ammonia injection amount at the time of k+j·s 2 and the expected ammonia injection amount, J is the jth control time point, s 2 is the control step length, M is the number of control time points in the predicted time period, ω 3 is the third weight coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011276325.4A CN112418284B (en) | 2020-11-16 | 2020-11-16 | Control method and system of SCR denitration system of all-condition power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011276325.4A CN112418284B (en) | 2020-11-16 | 2020-11-16 | Control method and system of SCR denitration system of all-condition power station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112418284A CN112418284A (en) | 2021-02-26 |
| CN112418284B true CN112418284B (en) | 2024-08-27 |
Family
ID=74831225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011276325.4A Active CN112418284B (en) | 2020-11-16 | 2020-11-16 | Control method and system of SCR denitration system of all-condition power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112418284B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113380338B (en) * | 2021-06-16 | 2022-06-10 | 哈电发电设备国家工程研究中心有限公司 | Method for measuring, correcting and predicting NOx concentration at inlet of cyclone separator |
| CN113433911B (en) * | 2021-06-30 | 2022-05-20 | 浙江大学 | Accurate control system and method for ammonia spraying of denitration device based on accurate concentration prediction |
| CN113485106B (en) * | 2021-07-07 | 2023-03-24 | 山西大学 | Method for controlling concentration of nitrogen oxide in thermal power plant |
| CN114053865A (en) * | 2021-11-03 | 2022-02-18 | 华能铜川照金煤电有限公司 | Generalized predictive control method suitable for SCR denitration control system of coal-fired boiler |
| CN114609986A (en) * | 2022-03-16 | 2022-06-10 | 中国中材国际工程股份有限公司 | Cement decomposing furnace denitration regulation and control optimization system and method based on predictive control |
| CN115309129A (en) * | 2022-10-11 | 2022-11-08 | 华电电力科学研究院有限公司 | SCR denitration efficiency automatic optimization regulation and control method and system |
| CN116832614B (en) * | 2023-05-24 | 2024-05-24 | 华能国际电力股份有限公司上海石洞口第二电厂 | Ammonia spraying amount control method and system for SCR denitration system |
| CN116880172B (en) * | 2023-06-29 | 2024-10-18 | 华能国际电力股份有限公司上海石洞口第二电厂 | Low-load denitration ammonia injection optimization control method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107243257A (en) * | 2017-05-08 | 2017-10-13 | 浙江大学 | It is adapted to the intelligence spray ammonia control system of full load |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7536232B2 (en) * | 2004-08-27 | 2009-05-19 | Alstom Technology Ltd | Model predictive control of air pollution control processes |
| CN106599586B (en) * | 2016-12-19 | 2019-05-28 | 北京国能中电节能环保技术股份有限公司 | SCR neural network based intelligently sprays ammonia optimization method and device |
| CN106681381A (en) * | 2017-01-03 | 2017-05-17 | 华北电力大学 | SCR denitration system ammonia spraying quantity optimal control system and method based on intelligent feedforward signals |
| CN107544288B (en) * | 2017-09-26 | 2021-06-04 | 天津拓科思科技有限公司 | Denitration optimization control method and system |
| CN109062053B (en) * | 2018-08-31 | 2022-11-29 | 江苏国信靖江发电有限公司 | Denitration ammonia injection control method based on multivariate correction |
| CN111581581B (en) * | 2020-04-23 | 2021-02-02 | 大唐环境产业集团股份有限公司 | Method and system for detecting NOx concentration at SCR inlet under multi-boundary condition |
| CN111522290A (en) * | 2020-04-24 | 2020-08-11 | 大唐环境产业集团股份有限公司 | Denitration control method and system based on deep learning method |
| CN111921377B (en) * | 2020-09-25 | 2021-01-26 | 大唐环境产业集团股份有限公司 | SCR denitration ammonia injection control method and system based on mechanism and data driving |
-
2020
- 2020-11-16 CN CN202011276325.4A patent/CN112418284B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107243257A (en) * | 2017-05-08 | 2017-10-13 | 浙江大学 | It is adapted to the intelligence spray ammonia control system of full load |
Non-Patent Citations (1)
| Title |
|---|
| SCR脱硝系统多目标优化控制研究;杨婷婷等;《中国电机工程学报》;第41卷(第14期);4905-4911 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112418284A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112418284B (en) | Control method and system of SCR denitration system of all-condition power station | |
| CN105629736B (en) | The fired power generating unit SCR denitration Disturbance Rejection forecast Control Algorithm of data-driven | |
| CN107243257B (en) | It is suitble to the intelligence spray ammonia control system of full load | |
| CN109062053B (en) | Denitration ammonia injection control method based on multivariate correction | |
| CN104826492B (en) | Improvement method for selective catalytic reduction flue gas denitrification and ammonia injection control system | |
| CN112580250A (en) | Thermal power generating unit denitration system based on deep learning and optimization control method | |
| CN106599586B (en) | SCR neural network based intelligently sprays ammonia optimization method and device | |
| CN113433911B (en) | Accurate control system and method for ammonia spraying of denitration device based on accurate concentration prediction | |
| CN105629738A (en) | SCR (Selective Catalytic Reduction) flue gas denitration system control method and apparatus | |
| CN105786035A (en) | Thermal power set SCR denitration optimization control system based on heuristic prediction control technology | |
| CN111968708B (en) | SCR denitration ammonia injection amount prediction method based on random forest and LSTM neural network | |
| CN111522290A (en) | Denitration control method and system based on deep learning method | |
| CN111897373B (en) | Model prediction-based ammonia injection flow adjusting method for SCR denitration device | |
| CN111552175B (en) | Overall optimization scheduling and rapid variable load control method for supercritical coal-fired power plant-carbon capture system after chemical adsorption combustion | |
| CN115524976A (en) | SCR system ammonia injection amount adjusting method considering boiler combustion state | |
| CN113363976B (en) | Scene graph-based wind-solar-water complementary power generation system medium-term optimization scheduling method | |
| CN109833773A (en) | A kind of NO_x Reduction by Effective ammonia flow accuracy control method | |
| CN114558447A (en) | Ammonia injection amount optimization control device and method based on SCR denitration system | |
| CN117270387A (en) | SCR denitration system low ammonia escape control method and system based on deep learning | |
| Liu et al. | Value distribution DDPG with dual-prioritized experience replay for coordinated control of coal-fired power generation systems | |
| CN109933884A (en) | A method of towards coal unit SCR denitration system Neural network inverse control | |
| CN116345450A (en) | Intelligent scheduling method of wind-light-water complementary system based on deep reinforcement learning | |
| CN113836819B (en) | Bed temperature prediction method based on time sequence attention | |
| CN114053865A (en) | Generalized predictive control method suitable for SCR denitration control system of coal-fired boiler | |
| CN112627953A (en) | Ship SCR system ammonia injection amount control method based on ARMAX and MMPC |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |