CN111522290A - Denitration control method and system based on deep learning method - Google Patents
Denitration control method and system based on deep learning method Download PDFInfo
- Publication number
- CN111522290A CN111522290A CN202010333937.6A CN202010333937A CN111522290A CN 111522290 A CN111522290 A CN 111522290A CN 202010333937 A CN202010333937 A CN 202010333937A CN 111522290 A CN111522290 A CN 111522290A
- Authority
- CN
- China
- Prior art keywords
- mainly
- outlet
- denitration
- nox
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/05—Programmable logic controllers, e.g. simulating logic interconnections of signals according to ladder diagrams or function charts
- G05B19/054—Input/output
-
- 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
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Strategic Management (AREA)
- Chemical & Material Sciences (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Analytical Chemistry (AREA)
- Crystallography & Structural Chemistry (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Automation & Control Theory (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Treating Waste Gases (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a denitration control method and a system based on a deep learning method, wherein the method comprises the following steps: determining variables related to the concentration of NOx at the outlet of an SCR reactor by analyzing the combustion principle of a boiler of a coal burning unit and the SCR denitration reaction mechanism, collecting historical operating data related to the NOx at the outlet of the SCR reactor, preprocessing the historical data by a discrete point and normalization method, establishing an intelligent outlet NOx concentration prediction model by adopting a deep belief network, obtaining the concentration of the NOx at the outlet at the current moment based on the real-time operating data, and analyzing the influence factors related to the NOx at the outlet of the SCR reactor in the step 101 by analyzing the combustion principle of the boiler of the coal burning unit and the SCR denitration reaction mechanism. By the method, the concentration of NOx at the outlet of the SCR reactor can be predicted in advance, the ammonia injection amount can be adjusted in time, and meanwhile, the provided control system adopts a deep learning method, so that the intelligent level of a denitration system can be greatly improved, and the workload of operators is reduced.
Description
Technical Field
The invention relates to the technical field of flue gas denitration of coal-fired power plants, in particular to a denitration control method and a denitration control system based on a deep learning method.
Background
With the issuance of a series of national policies and regulations, such as air pollution prevention and control laws, air pollutant emission standards of thermal power plants, pollution discharge fee collection and use management regulations, and comprehensive implementation of ultra-low emission and energy-saving modification working schemes of coal-fired power plants, the air pollutant emission of the coal-fired power plants is strictly regulated, and the ultra-low emission modification of flue gas is successively carried out in each power plant. The NOx emission concentration of a coal-fired power plant is required to be lower than 50mg/m3 after ultralow emission modification, a perfect denitration control technology of the coal-fired power plant is developed, and the emission of pollutants in the power plant is reduced as much as possible, so that the method becomes a necessary task for the power plant in China.
The existing commonly used denitration control technology mainly adopts a DCS cascade PID control system or an externally hung PLC control system, but the two methods have the defects of simple control strategy and low control precision of outlet NOx, so that the ammonia injection amount is insufficient or excessive, the nitrogen oxide is discharged in an excessive manner or an air preheater is blocked, and the normal operation of a denitration system or even a unit is influenced. Meanwhile, with the development of intelligent methods such as artificial intelligence and big data, the construction of the smart power plant draws more and more attention, and the denitration system is used as a miniature of the construction of the smart power plant, so that the intelligent construction of the denitration system becomes an essential research. The NOx concentration at the outlet of the denitration reactor has the problems of measurement lag, inaccurate measurement and the like, and the result of the measurement lag inevitably causes the 'failure' of a denitration control system, so that a better control effect cannot be achieved, and the normal operation of a unit is influenced. Therefore, the accurate prediction of NOx concentration at the outlet of the denitration reaction is realized, and the accurate and proper ammonia spraying of the denitration control system is an urgent problem to be solved in the denitration control process of the thermal power plant
Therefore, a denitration control method and a denitration control system based on a deep learning method are provided.
Disclosure of Invention
The invention aims to provide a denitration control method and a denitration control system based on a deep learning method, which can predict the concentration of NOx at the outlet of an SCR reactor in advance and adjust the ammonia injection amount in time, and meanwhile, the control system provided by the invention adopts the deep learning method, so that the intelligent level of a denitration system can be greatly improved, the workload of operators is reduced, and the problems in the background art are solved.
In order to achieve the purpose, the invention provides the following technical scheme: a denitration control method based on a deep learning method comprises the following steps:
101, determining variables related to the concentration of NOx at an outlet of an SCR (selective catalytic reduction) reactor by analyzing a boiler combustion principle of a coal burning unit and an SCR denitration reaction mechanism;
Preferably, through analysis of a combustion principle of a boiler of the coal burning unit and an SCR denitration reaction mechanism, relevant influence factors of the NOx at the outlet of the SCR in the step 101 include parameters such as unit load, total air volume, total coal volume, primary air volume, secondary air volume, flue gas oxygen content, ammonia injection volume, inlet NOx concentration and flue gas volume.
Preferably, the collected historical operating data related to the outlet NOx of the SCR is mainly an influencing factor related to the outlet NOx; the discrete point preprocessing method is mainly used for establishing data distribution according to historical data, if the value of a certain time deviates from an established distribution curve, the discrete point preprocessing method is regarded as an outlier, and the outlier is replaced by an interpolation method; the normalization method is mainly used for normalizing to be in a range of [0,1] by adopting an x ═ x-xmin)/(xmax-xmin) method so as to eliminate the influence of the dimension and the measuring range of each influencing factor in the SCR system.
Preferably, the Deep learning method is a Deep Belief neural network (DBN) method based on a TensorFlow framework, and is mainly used for establishing a prediction method of outlet NOx concentration according to the DBN method and establishing an intelligent ammonia injection control strategy. The DBN method is composed of a multilayer unsupervised Restricted Boltzmann Machine (RBM) and a BP neural network method, and comprises a visual layer, a hidden layer and an output layer, wherein the input of the visible layer, the hidden layer and the output layer is unit load, total air quantity, total coal quantity, primary air quantity, secondary air quantity, flue gas oxygen content and inlet NOx concentration, the output of the visible layer is outlet NOx concentration, and the training process mainly comprises two processes of pre-training and fine-tuning.
The training process is mainly RBM training, and an energy function between a visible layer and a hidden layer is established:
from the energy function, a joint probability function p (v, h) between the visual and the hidden layers is computed and each conditional probability distribution p (h | v) and p (v | h) is established. When the visual layer or the hidden layer is determined, the activation functions of the visual layer and the hidden layer are respectively as follows:
the learning parameter of the RBM training process is mainly wij、biAnd cjIn the training process, parameters are updated by adopting a contrast divergence algorithm, and the updating rule of each parameter is as follows:
Δw＝(Edata(vihj)-Erecon(vihj))
Δc＝(Edata(hj)-Erecon(hj))
Δb＝(Edata(vi)-Erecon(vi))
updating the parameter w according to the updating ruleij、biAnd cj. In the formula, v is a node of the visual layer, h is a node of the hidden layer, w is a weight matrix of the visual layer and the hidden layer, and b and c are offsets of the visual layer and the hidden layer respectively.
The fine tuning process is to set a layer of BP network at the end of the DBN network, receive the output characteristic vector of the RBM as the input characteristic vector thereof, fine tune the parameters by BP algorithm, and establish a global optimized prediction model.
Preferably, an initial prediction model is established according to the process, a DBN model is continuously trained according to operation data in a later operation process, so that the obtained model has self-learning and self-adaptive characteristics, and data such as real-time unit load, total air volume, total coal volume, primary air volume, secondary air volume, flue gas oxygen content, ammonia injection amount, inlet NOx concentration, flue gas amount and the like of the denitration reactor are input into the established DBN outlet NOx prediction model to obtain the outlet NOx concentration at the current moment.
The invention also provides a denitration control system based on the deep learning method, and the SCR inlet NOx modeling system comprises a field execution module, an instruction execution module and an intelligent decision module:
And 200, outputting an ammonia spraying valve instruction according to the parameters provided by the intelligent decision layer by an instruction execution module which is mainly a PLC (programmable logic controller).
Preferably, the data acquisition module is connected with the instruction execution module through an MODBUS communication protocol; the instruction execution module is connected with the intelligent decision module through a TCP/IP protocol.
Preferably, the workstation may employ a server model HP Z840(F5G73AV-SC 010).
Preferably, the database is an open-source MySQL database which is mainly used for storing collected historical data.
Preferably, the programming software adopts a Python3.7.4 version, mainly realizes an intelligent algorithm, the intelligent algorithm is mainly a Deep Belief Networks (DBN) method based on a TensorFlow framework, and mainly establishes a prediction method of outlet NOx concentration according to the DBN method and an intelligent ammonia injection control strategy.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method provided by the invention can predict the concentration of NOx at the outlet of the denitration reactor in advance, and solves the problems of lag and large delay in outlet NOx measurement;
(2) the method provided by the invention can adjust the ammonia spraying amount in time by predicting the NOx at the outlet in advance, so as to achieve the aim of accurate and proper ammonia spraying;
(3) the device provided by the invention adopts an intelligent method, so that the intelligent level of the denitration system is greatly improved, and the manpower and material resources in the control process of the denitration system are reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart of a denitration control method based on a deep learning method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a denitration control system based on a deep learning method according to an embodiment of the present invention.
Detailed Description
In the following, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 2, the present invention provides a technical solution:
as shown in fig. 1, a denitration control method based on a deep learning method provided in an embodiment of the present invention includes the following steps:
101, determining variables related to the concentration of NOx at an outlet of an SCR (selective catalytic reduction) reactor by analyzing a boiler combustion principle of a coal burning unit and an SCR denitration reaction mechanism;
Specifically, through analyzing the combustion principle of the boiler of the coal-fired unit and the mechanism of the SCR denitration reaction, the relevant influencing factors of the NOx at the outlet of the SCR in step 101 include parameters such as unit load, total air volume, total coal volume, primary air volume, secondary air volume, flue gas oxygen content, ammonia injection volume, inlet NOx concentration and flue gas volume.
Specifically, the collected historical operating data related to the outlet NOx of the SCR is mainly the influencing factor related to the outlet NOx; the discrete point preprocessing method is mainly used for establishing data distribution according to historical data, if the value of a certain time deviates from an established distribution curve, the discrete point preprocessing method is regarded as an outlier, and the outlier is replaced by an interpolation method; the normalization method is mainly used for normalizing to be in a range of [0,1] by adopting an x ═ x-xmin)/(xmax-xmin) method so as to eliminate the influence of the dimension and the measuring range of each influencing factor in the SCR system.
Specifically, the Deep learning method is mainly based on a Deep Belief neural network (DBN) method of a TensorFlow framework, and mainly establishes a prediction method of outlet NOx concentration according to the DBN method and an intelligent ammonia injection control strategy. The DBN method is composed of a multilayer unsupervised Restricted Boltzmann Machine (RBM) and a BP neural network method, and comprises a visual layer, a hidden layer and an output layer, wherein the input of the visible layer, the hidden layer and the output layer is unit load, total air quantity, total coal quantity, primary air quantity, secondary air quantity, flue gas oxygen content and inlet NOx concentration, the output of the visible layer is outlet NOx concentration, and the training process mainly comprises two processes of pre-training and fine-tuning.
The training process is mainly RBM training, and an energy function between a visible layer and a hidden layer is established:
from the energy function, a joint probability function p (v, h) between the visual and the hidden layers is computed and each conditional probability distribution p (h | v) and p (v | h) is established. When the visual layer or the hidden layer is determined, the activation functions of the visual layer and the hidden layer are respectively as follows:
the learning parameter of the RBM training process is mainly wij、biAnd cjIn the training process, parameters are updated by adopting a contrast divergence algorithm, and the updating rule of each parameter is as follows:
Δw＝(Edata(vihj)-Erecon(vihj))
Δc＝(Edata(hj)-Erecon(hj))
Δb＝(Edata(vi)-Erecon(vi))
updating the parameter w according to the updating ruleij、biAnd cj. In the formula, v is a node of the visual layer, h is a node of the hidden layer, w is a weight matrix of the visual layer and the hidden layer, and b and c are offsets of the visual layer and the hidden layer respectively.
The fine tuning process is to set a layer of BP network at the end of the DBN network, receive the output characteristic vector of the RBM as the input characteristic vector thereof, fine tune the parameters by BP algorithm, and establish a global optimized prediction model.
Specifically, an initial prediction model is established according to the process, and a DBN model needs to be continuously trained according to operation data in the later operation process, so that the obtained model has self-learning and self-adaptive characteristics. And inputting real-time data of unit load, total air volume, total coal volume, primary air volume, secondary air volume, flue gas oxygen content, ammonia injection volume, inlet NOx concentration, flue gas volume and the like of the denitration reactor into the established DBN outlet NOx prediction model to obtain the outlet NOx concentration at the current moment.
In order to achieve the above object, the present invention further provides a denitration control system based on a deep learning method, wherein the SCR inlet NOx modeling system includes a field execution module, an instruction execution module, and an intelligent decision module:
And 200, outputting an ammonia spraying valve instruction according to the parameters provided by the intelligent decision layer by an instruction execution module which is mainly a PLC (programmable logic controller).
More specifically, the data acquisition module is connected with the instruction execution module through an MODBUS communication protocol; the instruction execution module is connected with the intelligent decision module through a TCP/IP protocol.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method provided by the invention can predict the concentration of NOx at the outlet of the denitration reactor in advance, and solves the problems of lag and large delay in outlet NOx measurement;
(2) the method provided by the invention can adjust the ammonia spraying amount in time by predicting the NOx at the outlet in advance, so as to achieve the aim of accurate and proper ammonia spraying;
(3) the device provided by the invention adopts an intelligent method, so that the intelligent level of the denitration system is greatly improved, and the manpower and material resources in the control process of the denitration system are reduced.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A denitration control method and system based on a deep learning method are characterized in that: the denitration control method based on the deep learning method comprises the following steps:
step 101: determining variables related to the concentration of NOx at the outlet of the SCR reactor by analyzing the combustion principle of a boiler of the coal burning unit and the SCR denitration reaction mechanism;
step 201: collecting historical operating data related to NOx at an SCR outlet, and preprocessing the historical data by a discrete point and normalization method;
step 301: establishing an outlet NOx concentration intelligent prediction model by adopting a deep belief network;
step 401: and obtaining the outlet NOx concentration at the current moment based on the real-time operation data.
2. The denitration control method based on the deep learning method according to claim 1, characterized in that by analyzing the boiler combustion principle of the coal-fired unit and the SCR denitration reaction mechanism, the influence factors related to the NOx at the SCR outlet in the step 101 include parameters such as unit load, total air volume, total coal volume, primary air volume, secondary air volume, flue gas oxygen content, ammonia injection volume, inlet NOx concentration and flue gas volume.
3. The denitration control method based on the deep learning method as claimed in claim 1, wherein the collected historical operation data related to the SCR outlet NOx is mainly influence factors related to the outlet NOx, the discrete point preprocessing method mainly establishes the distribution of the data according to the historical data, if the value taken at a certain moment deviates from the established distribution curve, the discrete point is considered as an outlier, the outlier is replaced by an interpolation method, and the normalization method mainly adopts an x ═ x (min)/(xmax-xmin) method to normalize to the range of [0,1] so as to eliminate the influence of the dimension and the range of each influence factor in the SCR system.
4. The denitration control method based on the Deep learning method according to claim 1, wherein the Deep learning chemical method is a Deep Belief neural network (DBN) method based on a tensrflow framework, a prediction method of outlet NOx concentration is established mainly according to the DBN method, an intelligent ammonia injection control strategy is established, the DBN method is composed of a multilayer unsupervised Restricted Boltzmann Machine (RBM) and a BP neural network method, and comprises a visual layer, a hidden layer and an output layer, wherein the input is unit load, total air volume, total coal volume, primary air volume, secondary air volume, flue gas oxygen content, inlet NOx concentration, and the output is outlet NOx concentration, and the training process mainly comprises two processes of pre-training and fine-tuning.
The training process is mainly RBM training, and an energy function between a visible layer and a hidden layer is established:
from the energy function, a joint probability function p (v, h) between the visual and the hidden layers is computed and each conditional probability distribution p (h | v) and p (v | h) is established. When the visual layer or the hidden layer is determined, the activation functions of the visual layer and the hidden layer are respectively as follows:
the learning parameter of the RBM training process is mainly wij、biAnd cjThe contrast powder is adopted in the training processUpdating parameters by a degree algorithm, wherein the updating rule of each parameter is as follows:
Δw＝(Edata(vihj)-Erecon(vihj))
Δc＝(Edata(hj)-Erecon(hj))
Δb＝(Edata(vi)-Erecon(vi))
updating the parameter w according to the updating ruleij、biAnd cj. In the formula, v is a node of the visual layer, h is a node of the hidden layer, w is a weight matrix of the visual layer and the hidden layer, and b and c are offsets of the visual layer and the hidden layer respectively.
The fine tuning process is to set a layer of BP network at the end of the DBN network, receive the output characteristic vector of the RBM as the input characteristic vector thereof, fine tune the parameters by BP algorithm, and establish a global optimized prediction model.
5. The denitration control method based on the deep learning method as claimed in claim 1, wherein an initial prediction model is established according to the process, and the DBN model is continuously trained according to the operation data in the later operation process, so that the obtained model has self-learning and self-adaptive characteristics. And inputting real-time data of unit load, total air volume, total coal volume, primary air volume, secondary air volume, flue gas oxygen content, ammonia injection volume, inlet NOx concentration, flue gas volume and the like of the denitration reactor into the established DBN outlet NOx prediction model to obtain the outlet NOx concentration at the current moment.
6. The denitration control system based on the deep learning method is characterized in that the SCR inlet NOx modeling system comprises a field execution module, an instruction execution module and an intelligent decision module:
step 100, a field execution module mainly comprises a sensor, an actuator and a DCS; the sensor is mainly responsible for collecting data of the denitration reactor, and the collected data mainly comprises unit load, total air volume, total coal volume, primary air volume, secondary air volume, flue gas oxygen content, ammonia injection volume, inlet NOx concentration, flue gas volume, outlet NOx concentration and the like; the actuator is mainly an actuating mechanism and is responsible for executing the valve instruction fed back by the PLC.
And 200, outputting an ammonia spraying valve instruction according to the parameters provided by the intelligent decision layer by an instruction execution module which is mainly a PLC (programmable logic controller).
Step 300, the intelligent decision module is mainly a workstation, which implements intelligent decision of control logic parameters, and mainly includes a database and Python programming software. The workstation may employ a server model HP Z840(F5G73AV-SC 010); the database adopts an open-source MySQL database and is mainly used for storing collected historical data; the programming software adopts a Python3.7.4 version, mainly realizes an intelligent algorithm, the intelligent algorithm is mainly a Deep Belief Networks (DBN) method based on a TensorFlow frame, and a prediction method of outlet NOx concentration is mainly established according to the DBN method, so that an intelligent ammonia injection control strategy is established.
7. A denitration control system based on a deep learning method is characterized in that a data acquisition module is connected with an instruction execution module through an MODBUS communication protocol; the instruction execution module is connected with the intelligent decision module through a TCP/IP protocol.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010333937.6A CN111522290A (en) | 2020-04-24 | 2020-04-24 | Denitration control method and system based on deep learning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010333937.6A CN111522290A (en) | 2020-04-24 | 2020-04-24 | Denitration control method and system based on deep learning method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111522290A true CN111522290A (en) | 2020-08-11 |
Family
ID=71904361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010333937.6A Pending CN111522290A (en) | 2020-04-24 | 2020-04-24 | Denitration control method and system based on deep learning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111522290A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860701A (en) * | 2020-09-24 | 2020-10-30 | 大唐环境产业集团股份有限公司 | Denitration system working condition discrimination preprocessing method based on clustering method |
| CN111880504A (en) * | 2020-08-17 | 2020-11-03 | 大唐环境产业集团股份有限公司 | Intelligent dynamic partition ammonia injection control method and system |
| CN111921377A (en) * | 2020-09-25 | 2020-11-13 | 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 |
| CN112418284A (en) * | 2020-11-16 | 2021-02-26 | 华北电力大学 | Control method and system for SCR denitration system of full-working-condition power station |
| CN112619394A (en) * | 2020-11-24 | 2021-04-09 | 呼和浩特科林热电有限责任公司 | Denitration ammonia injection self-adaptive control method and device and denitration system |
| CN112651166A (en) * | 2020-11-24 | 2021-04-13 | 呼和浩特科林热电有限责任公司 | Denitration system inlet nitrogen oxide concentration prediction method and device and denitration system |
| CN112733441A (en) * | 2020-12-31 | 2021-04-30 | 华电国际电力股份有限公司天津开发区分公司 | Circulating fluidized bed boiler NOx emission concentration control system based on QGA-ELM network |
| CN116050262A (en) * | 2023-01-04 | 2023-05-02 | 中能建数字科技集团有限公司 | Safety state evaluation method, device and system of compressed air energy storage power station |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016186273A (en) * | 2015-03-27 | 2016-10-27 | いすゞ自動車株式会社 | Selective catalytic reduction device |
| CN108319146A (en) * | 2018-03-09 | 2018-07-24 | 西安西热控制技术有限公司 | A kind of method that radial base neural net is trained based on discrete particle cluster |
| CN108644805A (en) * | 2018-05-08 | 2018-10-12 | 南京归图科技发展有限公司 | Boiler intelligent combustion optimal control method based on big data |
| CN108664006A (en) * | 2018-07-02 | 2018-10-16 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of zonal control and Dynamic matrix control |
| CN108803309A (en) * | 2018-07-02 | 2018-11-13 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and model adaptation |
| CN108837699A (en) * | 2018-07-02 | 2018-11-20 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and PREDICTIVE CONTROL |
| CN109102126A (en) * | 2018-08-30 | 2018-12-28 | 燕山大学 | One kind being based on depth migration learning theory line loss per unit prediction model |
| CN109343349A (en) * | 2018-11-01 | 2019-02-15 | 大唐环境产业集团股份有限公司 | A kind of SCR denitrating flue gas Optimal Control System and method based on ammonia spraying amount compensator |
| CN110368808A (en) * | 2019-07-18 | 2019-10-25 | 华北电力科学研究院有限责任公司 | A kind of the ammonia spraying amount control method and system of SCR flue gas denitrification system |
-
2020
- 2020-04-24 CN CN202010333937.6A patent/CN111522290A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016186273A (en) * | 2015-03-27 | 2016-10-27 | いすゞ自動車株式会社 | Selective catalytic reduction device |
| CN108319146A (en) * | 2018-03-09 | 2018-07-24 | 西安西热控制技术有限公司 | A kind of method that radial base neural net is trained based on discrete particle cluster |
| CN108644805A (en) * | 2018-05-08 | 2018-10-12 | 南京归图科技发展有限公司 | Boiler intelligent combustion optimal control method based on big data |
| CN108664006A (en) * | 2018-07-02 | 2018-10-16 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of zonal control and Dynamic matrix control |
| CN108803309A (en) * | 2018-07-02 | 2018-11-13 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and model adaptation |
| CN108837699A (en) * | 2018-07-02 | 2018-11-20 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and PREDICTIVE CONTROL |
| CN109102126A (en) * | 2018-08-30 | 2018-12-28 | 燕山大学 | One kind being based on depth migration learning theory line loss per unit prediction model |
| CN109343349A (en) * | 2018-11-01 | 2019-02-15 | 大唐环境产业集团股份有限公司 | A kind of SCR denitrating flue gas Optimal Control System and method based on ammonia spraying amount compensator |
| CN110368808A (en) * | 2019-07-18 | 2019-10-25 | 华北电力科学研究院有限责任公司 | A kind of the ammonia spraying amount control method and system of SCR flue gas denitrification system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111880504A (en) * | 2020-08-17 | 2020-11-03 | 大唐环境产业集团股份有限公司 | Intelligent dynamic partition ammonia injection control method and system |
| CN111860701A (en) * | 2020-09-24 | 2020-10-30 | 大唐环境产业集团股份有限公司 | Denitration system working condition discrimination preprocessing method based on clustering method |
| CN111860701B (en) * | 2020-09-24 | 2021-01-26 | 大唐环境产业集团股份有限公司 | Denitration system working condition discrimination preprocessing method based on clustering method |
| CN111921377A (en) * | 2020-09-25 | 2020-11-13 | 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 |
| 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 |
| CN112418284A (en) * | 2020-11-16 | 2021-02-26 | 华北电力大学 | Control method and system for SCR denitration system of full-working-condition power station |
| CN112619394A (en) * | 2020-11-24 | 2021-04-09 | 呼和浩特科林热电有限责任公司 | Denitration ammonia injection self-adaptive control method and device and denitration system |
| CN112651166A (en) * | 2020-11-24 | 2021-04-13 | 呼和浩特科林热电有限责任公司 | Denitration system inlet nitrogen oxide concentration prediction method and device and denitration system |
| CN112619394B (en) * | 2020-11-24 | 2022-12-02 | 呼和浩特科林热电有限责任公司 | Denitration ammonia injection self-adaptive control method and device and denitration system |
| CN112733441A (en) * | 2020-12-31 | 2021-04-30 | 华电国际电力股份有限公司天津开发区分公司 | Circulating fluidized bed boiler NOx emission concentration control system based on QGA-ELM network |
| CN116050262A (en) * | 2023-01-04 | 2023-05-02 | 中能建数字科技集团有限公司 | Safety state evaluation method, device and system of compressed air energy storage power station |
| CN116050262B (en) * | 2023-01-04 | 2023-11-14 | 中能建数字科技集团有限公司 | Safety state evaluation method, device and system of compressed air energy storage power station |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111522290A (en) | Denitration control method and system based on deep learning method | |
| CN107243257B (en) | It is suitble to the intelligence spray ammonia control system of full load | |
| WO2020088485A1 (en) | Intelligent multi-pollutant ultra-low emission system and global optimization method | |
| CN111804146B (en) | Intelligent ammonia injection control method and intelligent ammonia injection control device | |
| CN111624876B (en) | Intelligent ammonia injection optimization control system | |
| CN109304086B (en) | Power station boiler SCR denitration refined ammonia injection control method | |
| CN112580250A (en) | Thermal power generating unit denitration system based on deep learning and optimization control method | |
| CN110263395A (en) | The power plant's denitration running optimizatin method and system analyzed based on numerical simulation and data | |
| CN111077869A (en) | Optimization control method and system for big data intelligent control bag-type dust collector | |
| CN113175678B (en) | Garbage incineration monitoring method and device | |
| CN112364562B (en) | Flue gas environment-friendly island cooperative control method and system | |
| CN112418284A (en) | Control method and system for SCR denitration system of full-working-condition power station | |
| CN113469449B (en) | Optimization control method and system for desulfurization system | |
| CN113433911A (en) | Denitration device ammonia injection accurate control system and method based on concentration accurate prediction | |
| CN111581581A (en) | Method and system for detecting NOx concentration at SCR inlet under multi-boundary condition | |
| CN111489605B (en) | Ammonia spraying optimization control simulation system based on Simulink and WinCC | |
| CN112232373A (en) | Method and system for predicting carbon content of boiler fly ash | |
| CN115145152A (en) | Boiler combustion and denitration process collaborative optimization control method | |
| CN109833773B (en) | Efficient denitration ammonia flow accurate control method | |
| CN109046021B (en) | SCR system accurate ammonia injection control method with strong self-adaptive capacity | |
| CN117744704A (en) | Flue gas pollution source acquisition monitoring system, method and readable storage medium | |
| CN113485111B (en) | Optimizing control method and system for pulping system | |
| CN115755599A (en) | Automatic control method, system, equipment and medium for corrosion prevention of garbage incinerator | |
| CN109933884A (en) | A method of towards coal unit SCR denitration system Neural network inverse control | |
| CN115034486A (en) | Prediction control method for iSNCR denitration of cement kiln flue gas |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200811 |
|
| RJ01 | Rejection of invention patent application after publication |