CN112699600B - Thermal power operating parameters and NOxMethod for analyzing partial return between emission concentrations - Google Patents
Thermal power operating parameters and NOxMethod for analyzing partial return between emission concentrations Download PDFInfo
- Publication number
- CN112699600B CN112699600B CN202011539732.XA CN202011539732A CN112699600B CN 112699600 B CN112699600 B CN 112699600B CN 202011539732 A CN202011539732 A CN 202011539732A CN 112699600 B CN112699600 B CN 112699600B
- Authority
- CN
- China
- Prior art keywords
- emission concentration
- regression model
- unit
- fitting
- working condition
- 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 claims abstract description 54
- 239000002131 composite material Substances 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims abstract description 22
- 238000004519 manufacturing process Methods 0.000 claims abstract description 20
- 238000010977 unit operation Methods 0.000 claims abstract description 13
- 238000000611 regression analysis Methods 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims abstract description 5
- 230000008859 change Effects 0.000 claims description 9
- 239000003245 coal Substances 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 2
- 150000001875 compounds Chemical class 0.000 claims description 2
- 229910052760 oxygen Inorganic materials 0.000 claims description 2
- 239000001301 oxygen Substances 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 12
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000013507 mapping Methods 0.000 abstract description 4
- 210000002569 neuron Anatomy 0.000 description 11
- 230000006872 improvement Effects 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
- Treating Waste Gases (AREA)
Abstract
The invention discloses a partial return analysis method between thermal power operation parameters and NO x emission concentration, which is based on unit operation history working condition data, and comprises the steps of firstly establishing a basic composite regression model between unit production operation composite multi-working-condition parameters and NO x emission concentration of a thermal power unit through a machine learning process by utilizing artificial intelligence; setting a single operation parameter as a variable, setting a constant value by referring to an application scene by other operation parameters, and obtaining partial regression analysis sample data by using a basic composite regression model; and selecting a proper fitting function type to fit the sample data, and obtaining a partial regression model between the unit operation parameters and the NO x emission concentration through parameter estimation. The invention can intuitively grasp the numerical mapping between different operation parameters and the NO x emission concentration, optimize the operation parameters and guide the production process of the optimizing unit.
Description
Technical Field
The invention belongs to the technical field of thermal power production optimization operation control analysis, and particularly relates to a method for analyzing the deviation between thermal power operation parameters and NO x emission concentration.
Background
The production process of the thermal power generating unit relates to complex heat transfer, mass transfer, working and other processes, has great regulation difficulty, is easily influenced by climate, unstable coal source, unit performance and other variable factors, and is difficult to establish a reliable model between unit operation parameters and NO x emission concentration through mechanism analysis; the simulation technology based on the mechanism model is used for simplifying and supposing the physical process, so that a certain gap exists between the production process of the real unit and the analysis of the mechanism model; the simulation analysis technology based on the mechanism model is generally used for qualitative analysis between unit operation parameters and NO x emission concentration, namely trend analysis, and cannot obtain relation model description based on exact numerical mapping.
In recent years, by means of a big data analysis technology, related researchers establish an intelligent analysis diagnosis model between unit production operation parameters and NO x emission concentration through artificial intelligence, so that difficulties existing in mechanism analysis modeling are overcome, but NO x emission control analysis diagnosis based on the big data analysis technology fuses a plurality of operation parameters, and partial regression analysis between different operation parameters and NO x emission is lacked. In the running process of the unit, the emission of NO x of the unit is required to be minimized only by adjusting a certain running parameter under the condition of stabilizing most running parameters, such as the total air quantity of secondary air, and a partial regression model between the running parameters and the emission concentration of NO x is required to provide necessary analysis and regulation basis in the process, so that blindness of experience regulation is avoided.
In summary, whether based on reasoning of a mechanism analysis model or based on diagnosis of an artificial intelligence big data analysis model, the current diagnostic analysis between unit operation parameters and NO x emission concentration is generally applicable to an analysis composite model, which fuses a plurality of parameters as input variables, and it is difficult to clearly define numerical mappings between different operation parameters and NO x emission concentration, namely a partial regression model.
Disclosure of Invention
The invention aims to realize the accurate guiding and adjustment of the running parameters of a certain specific thermal power unit to reduce the NO x emission concentration, and particularly realizes the accurate guiding and adjustment by a partial regression analysis method between the running parameters of the thermal power unit and the NO x emission concentration.
In order to achieve the above object, the present invention provides a method for analyzing a deviation between an operation parameter of thermal power and an emission concentration of NO x, the method comprising:
s101: collecting working condition data in the operation period of the thermal power generating unit to obtain a historical working condition data set;
S102: based on the historical working condition data set, establishing a basic composite regression model between the composite operation parameters of the unit and the NO x emission concentration;
S103: obtaining the predicted output of the NO x emission concentration corresponding to the variable operation parameter by using a basic composite regression model;
S104, performing S104; performing data fitting on the predicted output based on the variable operating parameters and the NO x emission concentration by a fitting method;
S105: estimating each parameter in the fitting formula by an estimation method to obtain a partial regression model between the variable operation parameters and the NO x emission concentration;
and S106, carrying out data analysis according to the partial regression model to obtain an analysis result.
As a further improvement of the invention, an artificial intelligent model is utilized to establish a basic composite regression model between the composite multi-parameter of unit production operation and the NO x emission concentration through a machine learning process; the artificial intelligence model comprises one or more of a neural network, a support vector machine and a Bayesian network.
As a further improvement of the invention, the basic multiple regression model is a multiple-input single-output model, the input is the unit operation composite multiple parameters, and the output is the NO x emission concentration.
As a further improvement of the present invention, the fitting method includes a linear fitting method and a nonlinear fitting method, wherein the function model used for nonlinear fitting includes one or more of exponential type, sine and cosine function type, and polynomial fitting function.
As a further improvement of the invention, the estimation method in the partial regression model between the variable operating parameter and the NO x emission concentration obtained by estimating each parameter in the fitting formula by the estimation method comprises a least square method.
Collecting working condition data in the operation period of the thermal power generating unit to obtain a historical working condition data set, and particularly collecting secondary air quantity, NO x concentration at an inlet of a denitration system and other working condition data related to NO x emission through a DCS system; and storing all the working condition data and the NO x emission concentration data to form a historical working condition database.
As a further improvement of the invention, a basic composite regression model between the composite operation parameters of the unit and the NO x emission concentration is established based on the historical working condition data set; the method specifically comprises the step of establishing a composite basic regression model between composite multi-parameters of unit production operation and NO x emission concentration by adopting a Bp neural network.
As a further improvement of the invention, the estimation method is used for estimating each parameter in the fitting formula to obtain a partial regression model between the variable operating parameter and the NO x emission concentration,
Setting the record data of the secondary air quantity in the historical working condition dataset as { X i }, and obtaining the change { Y i } of the concentration of NO x caused by the change of the secondary air quantity by a basic regression model;
The data set { X i}、{Yi } is used as an independent variable and an output quantity sample of the partial regression analysis,
And (3) performing nonlinear curve fitting on the sample by taking the trigonometric function as a mother function to obtain a partial regression model between the secondary air quantity and the NO x emission concentration.
Compared with the prior art, the invention has the following advantages:
1. The invention provides a partial return analysis method between thermal power unit operation parameters and NO x emission concentration, which can be used for accurately analyzing numerical mapping models between different operation parameters and unit NO x emission concentration, can be flexibly applied to different production conditions, and is used for guiding adjustment of the thermal power unit operation parameters so as to improve unit production optimization efficiency. By applying the method, the purpose of optimizing production and improving efficiency can be achieved without increasing hardware cost and investment in the thermal power generating unit, and potential hidden danger caused by experience adjustment can be avoided.
2. The invention provides an explicit numerical regression model between unit operation parameters and NO x emission concentration, and an analysis method based on mechanism modeling simulation in the prior art can only carry out trend analysis on the relation between the operation parameters and NO x emission and cannot give a definite numerical model;
3. The invention carries out partial regression analysis aiming at the relation between different operation parameters and NO x emission concentration, and provides an exact numerical model, while the prior art is mostly aimed at the relation analysis between the unit operation compound multi-parameter and NO x emission concentration, so that the relation between different operation parameters and NO x emission concentration is difficult to identify and is explicitly expressed.
Drawings
FIG. 1 is a schematic diagram of a method for analyzing the partial return between the thermal power operation parameter and the NO x emission concentration according to the invention;
FIG. 2 is a diagram of a neural network for a method of analyzing the partial return between thermal power operating parameters and NO x emissions concentration in accordance with the present invention;
FIG. 3 is a graph of the secondary air volume versus the set of NO x discharge concentration points in an example of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the drawings and specific examples, but is not limited thereto. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention discloses a method for analyzing the deviation between a thermal power operation parameter and the emission concentration of NO x, which comprises the following steps:
S101: collecting working condition data in the operation period of the thermal power generating unit to obtain a historical working condition data set; the historical working condition data set comprises unit operation composite multi-parameter and unit NO x emission concentration data, and different data are collected at the same frequency.
S102: based on the historical working condition data set, a basic composite regression model between the composite operation parameters of the unit and the NO x emission concentration is established, and specifically, the basic composite regression model between the composite multi-parameters of the unit production operation and the NO x emission concentration is established by utilizing an artificial intelligent model through machine learning; the artificial intelligent model comprises a neural network, a support vector machine and one of Bayesian networks;
S103: obtaining the predicted output of the NO x emission concentration corresponding to the variable operation parameter by using a basic composite regression model;
Specifically, the operation parameters participating in the partial regression analysis in the operation composite multi-parameter are made to be variable, and the rest operation parameters are constant and are called as background parameters. In order to improve the accuracy of analysis, the value of the background parameter should be smaller than the maximum value of the corresponding parameter record in the historical working condition data set and larger than the minimum value of the corresponding parameter record; the variable is also valued within the range of variation recorded for that variable in the historical operating condition dataset. Under the above conditions, the predicted output of the NO x emission concentration corresponding to the variable operation parameter is obtained by using the basic multiple regression model.
S104, performing S104; performing data fitting on the predicted output based on the variable operating parameters and the NO x emission concentration by a fitting method;
And carrying out data fitting based on the variable operation parameters and the predicted output of the NO x emission concentration index, wherein a fitting function in the fitting can be an exponential type, a polynomial fitting function and the like, a partial regression model between the variable operation parameters and the NO x emission concentration is obtained through estimating each parameter in a fitting formula, and a least square method and other parameter estimation methods can be adopted for the parameter estimation method.
The fitting method comprises a linear fitting method and a nonlinear fitting method, wherein a function model used for nonlinear fitting comprises one or more of an exponential type, a sine and cosine function type and a polynomial fitting function.
S105: estimating each parameter in the fitting formula by an estimation method to obtain a partial regression model between the variable operation parameters and the NO x emission concentration;
and S106, carrying out data analysis according to the partial regression model to obtain an analysis result.
In specific implementation, the invention discloses a partial regression analysis between the secondary air quantity of a coal-fired unit with subcritical parameters of a certain power plant and the NO x emission concentration at the inlet of a denitration system, and the further application background of the embodiment is that in order to ensure production output and keep stable production working conditions, the unit load, the total coal quantity, the total air quantity and the total water supply quantity of a boiler are kept at stable levels according to requirements, and in order to reduce the generation quantity of NO x and reduce the investment of environmental protection links, the unit production process is optimized in a secondary air quantity adjustment mode, and the comprehensive production efficiency of the unit is improved.
In the embodiment, the unit optimization efficiency is specifically measured by the amount of generated NO x, a partial regression model between the secondary air quantity and the NO x emission concentration can be directly obtained based on the application of the embodiment, NO x emission fluctuation caused by the secondary air quantity change in the whole secondary air quantity adjustable interval can be observed by means of the partial regression model, and the optimal working condition value of the secondary air quantity and the lowest NO x emission concentration are judged;
The specific process of this embodiment is as follows:
Under the normal running condition of the unit, the step S101 is further expanded, and the secondary air quantity, the NO x concentration at the inlet of the denitration system and other working condition data related to NO x emission are recorded through the DCS, wherein the working condition data comprise load, total air quantity, boiler water supply quantity, total coal quantity, E coal mill current, F coal mill current, oxygen quantity at the inlet of the denitration system and inlet temperature of the denitration system. All recorded operating condition data and NO x emission concentration are read and stored every 5 seconds, and related data are collected and recorded for 24 hours to form a historical operating condition database.
Step S102 is further expanded, a Bp neural network is adopted to establish a composite basic regression model between unit production operation composite multiple parameters (load, total air quantity, secondary air quantity, boiler water supply quantity and total coal quantity) and NO x emission concentration, the neural network adopts a three-layer structure, namely an input layer, a middle layer and an output layer, the input layer has 5 input ends, the middle layer adopts 10 neurons, the output layer comprises an output end, and the output value is the emission concentration of a denitration system inlet NO x;
a neural network structure diagram as shown in fig. 2; each hidden layer neuron of the model is linked with each input through a weight, and the effective input received by the ith (i is more than or equal to 1 and less than or equal to 8) neuron of the hidden layer is Wherein x= [ X 1,X2,X3,X4,X5 ] is an input vector, and W i＝[Wi1,Wi2,Wi3,Wi4,Wi5]|1≤i≤10 is a link weight vector between the hidden layer neuron and the input layer. The hidden layer neuron activation function is f i (x) =tan (x) =1/(arctan (x) +1), and the effective output of each hidden layer neuron isWhere α i is a constant bias. The model output layer neurons and each hidden layer neuron are also linked by weights, the output layer neuron activation function is a linear function, and the effective output is/>Wherein the method comprises the steps ofAnd beta is constant bias for the link weight vector between the output layer neuron and the hidden layer neuron. After the model is created, starting a machine learning process, using 80% of the historical working condition data set for training and learning the Bp neural network model, and using 20% of working condition records as a test set for verifying the accuracy of the trained Bp neural network model.
Step S103 is further expanded, and a composite basic regression model is obtained through the process, wherein the model is a multi-input single-output model, the input is a composite multi-parameter for unit production operation, and the output is the NO x concentration at the inlet of the denitration system.
Step S104 is further expanded, working condition parameters (load, total air quantity, boiler water supply quantity and total coal quantity) are respectively set to stable working condition values according to application scenes, the stable working condition values are used as constant input of a composite basic regression model, and generally, the values of all the constant operation parameters are in the range of the change interval of the history working condition data set on each operation parameter record; the secondary air volume is used as the variable input of the basic regression model, and takes the value in the range of the variation interval recorded in the historical working condition data set, and in the embodiment, the recorded data { X i } of the secondary air volume in the historical working condition data set is taken. After the input conditions were set as described above, the change { Y i } in the concentration of NO x due to the change in the secondary air quantity was obtained from the basic regression model.
Further expanding the step S105, taking the data set { X i}、{Yi } as an independent variable and output quantity sample of the partial regression analysis, and carrying out nonlinear curve fitting on the sample by taking a trigonometric function as a mother function according to the characteristics of the sample to obtain a numerical regression model between the secondary air quantity and the NO x emission concentration, namely a partial regression model, wherein the numerical regression model is shown as a formula (1):
y＝a1sin(b1x+c1)+a2sin(b2x+c2)+a3sin(b3x+c3)+a4sin(b4x+c4)+a5sin(b5x+c5)
The fitting process adopts a least square method to estimate the parameters of the model, and the estimated values of all parameter values in the model are listed below:
a1＝714.2,b1＝0.003438,c1＝2.403；
a2＝361,b2＝0.007211,c2＝-0.03716；
a3＝86.42,b3＝0.01586,c3＝-1.498；
a4＝119.7,b4＝0.025,c4＝-3.946；
a5＝94.79,b5＝0.02572,c5＝4.536
Other types of fitting functions, such as exponential functions, may also be used in the fitting process, depending on the choice of fitting effect. The input and output sample point set { X i}、{Yi } used in the fitting process is fitting data, and a partial regression model curve obtained by fitting;
FIG. 3 shows a fitted curve of secondary air volume and NO x emission concentration point set; in this embodiment, the sample data { X i } does not cover the whole adjustable interval of the secondary air volume, so that the secondary air volume takes a value in the adjusting range, in this embodiment, the adjustable interval of the secondary air volume reference total air volume is 1150-1800 Nm 3/h, according to the fitting model, the NO x emission concentration continuously fluctuates along with the change of the secondary air volume, the fluctuation range is 276.5846mg/Nm 3-771.1134mg/Nm3, and the NO x emission concentration of the unit is 276.5846mg/Nm 3, which is the lowest emission level that can be achieved by the unit when the secondary air volume is adjusted to 1573Nm 3/h.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (5)
1. A method for analyzing a bias back between an operating parameter of a thermal power and an emission concentration of NO x, the method comprising:
s101: collecting working condition data in the operation period of the thermal power generating unit to obtain a historical working condition data set;
S102: based on the historical working condition data set, establishing a basic composite regression model between the composite operation parameters of the unit and the NO x emission concentration;
S103: obtaining the predicted output of the NO x emission concentration corresponding to the variable operation parameter by using a basic composite regression model;
s104: performing data fitting on the predicted output based on the variable operating parameters and the NO x emission concentration by a fitting method;
S105: estimating each parameter in the fitting formula by an estimation method to obtain a partial regression model between the variable operation parameters and the NO x emission concentration;
s106: carrying out data analysis according to the partial regression model to obtain an analysis result;
the historical working condition data set comprises unit operation compound multi-parameter and unit NO x emission concentration data;
Recording secondary air quantity, NO x concentration at a denitration system inlet and other working condition data related to NO x emission through a DCS system, and storing all working condition data and NO x emission concentration data to form a historical working condition database;
The working condition data related to NO x emission comprises load, total air quantity, boiler water supply quantity, total coal quantity, coal mill current, denitration system inlet oxygen quantity and denitration system inlet temperature;
A plurality of different data are collected at the same frequency;
Based on the historical working condition data set, establishing a basic composite regression model between the composite operation parameters of the unit and the NO x emission concentration; specifically, a composite basic regression model between composite multiparameter of unit production operation and NO x emission concentration is established by adopting a Bp neural network;
Estimating each parameter in the fitting formula to obtain a partial regression model between the variable operating parameter and the NO x emission concentration,
Firstly, setting record data of secondary air quantity in a historical working condition dataset as { X i }, and obtaining the change { Y i } of NO x concentration caused by secondary air quantity change by a basic regression model;
secondly, taking the data set { X i}、{Yi } as an independent variable and output quantity sample of the partial regression analysis;
And finally, performing nonlinear curve fitting on the sample by taking the trigonometric function as a mother function to obtain a partial regression model between the secondary air quantity and the NO x emission concentration.
2. The method for partial return analysis between thermal power operation parameters and NOx emission concentration according to claim 1, wherein an artificial intelligent model is utilized to establish a basic composite regression model between unit production operation composite multi-parameters and the NOx x emission concentration through machine learning.
3. The method for partial return analysis between thermal power operation parameters and NO x emission concentration according to claim 2, wherein the basic multiple regression model is a multiple-input single-output model, the input is a unit operation composite multiple parameter, and the output is NO x emission concentration.
4. A method of analyzing the partial return between thermal power operating parameters and NO x emissions according to any one of claims 1 to 3, wherein the fitting method includes linear fitting and nonlinear fitting methods, and wherein the function model used for nonlinear fitting includes one or more of exponential type, sine-cosine function type, and polynomial fitting function.
5. The method of partial regression analysis between thermal power operating parameters and NO x exhaust concentration as defined in claim 4, wherein the estimation method in the partial regression model between variable operating parameters and NO x exhaust concentration is obtained by estimating each parameter in the fitting equation by the estimation method, including the least squares method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011539732.XA CN112699600B (en) | 2020-12-23 | 2020-12-23 | Thermal power operating parameters and NOxMethod for analyzing partial return between emission concentrations |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011539732.XA CN112699600B (en) | 2020-12-23 | 2020-12-23 | Thermal power operating parameters and NOxMethod for analyzing partial return between emission concentrations |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112699600A CN112699600A (en) | 2021-04-23 |
| CN112699600B true CN112699600B (en) | 2024-06-07 |
Family
ID=75509314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011539732.XA Active CN112699600B (en) | 2020-12-23 | 2020-12-23 | Thermal power operating parameters and NOxMethod for analyzing partial return between emission concentrations |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112699600B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008052542A1 (en) * | 2006-11-02 | 2008-05-08 | Fls Automation A/S | A SYSTEM AND A METHOD FOR PREDICTION OF NOx EMISSION AND/OR FREE LIME CONCENTRATION IN A CEMENT KILN |
| CN106408223A (en) * | 2016-11-30 | 2017-02-15 | 华北电力大学（保定） | Short-term load prediction based on meteorological similar day and error correction |
| CN110032747A (en) * | 2018-12-05 | 2019-07-19 | 太原理工大学 | A kind of coal-burning boiler NOxDischarge On-line Measuring Method |
| CN110986085A (en) * | 2019-11-21 | 2020-04-10 | 东南大学 | Four-corner tangential boiler combustion optimization control method based on air distribution mode optimization |
| CN111222685A (en) * | 2019-11-21 | 2020-06-02 | 江苏方天电力技术有限公司 | Boiler wide-load NOx emission concentration prediction method based on model migration |
| CN111804146A (en) * | 2020-06-29 | 2020-10-23 | 远光软件股份有限公司 | Intelligent ammonia injection control method and intelligent ammonia injection control device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2458351A1 (en) * | 2010-11-30 | 2012-05-30 | Alstom Technology Ltd | Method of analyzing and controlling a combustion process in a gas turbine and apparatus for performing the method |
-
2020
- 2020-12-23 CN CN202011539732.XA patent/CN112699600B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008052542A1 (en) * | 2006-11-02 | 2008-05-08 | Fls Automation A/S | A SYSTEM AND A METHOD FOR PREDICTION OF NOx EMISSION AND/OR FREE LIME CONCENTRATION IN A CEMENT KILN |
| CN106408223A (en) * | 2016-11-30 | 2017-02-15 | 华北电力大学（保定） | Short-term load prediction based on meteorological similar day and error correction |
| CN110032747A (en) * | 2018-12-05 | 2019-07-19 | 太原理工大学 | A kind of coal-burning boiler NOxDischarge On-line Measuring Method |
| CN110986085A (en) * | 2019-11-21 | 2020-04-10 | 东南大学 | Four-corner tangential boiler combustion optimization control method based on air distribution mode optimization |
| CN111222685A (en) * | 2019-11-21 | 2020-06-02 | 江苏方天电力技术有限公司 | Boiler wide-load NOx emission concentration prediction method based on model migration |
| CN111804146A (en) * | 2020-06-29 | 2020-10-23 | 远光软件股份有限公司 | Intelligent ammonia injection control method and intelligent ammonia injection control device |
Non-Patent Citations (7)
| Title |
|---|
| Comparative study of computational intelligence approaches for NOx reduction of coal-fired boiler;Zhongbao Wei;《Energy》;第55卷(第15期);683-692 * |
| Comparative study of regression modeling methods for online coal calorific value prediction from flame radiation features;Lijun Xu;《Fuel》;164-172 * |
| 变负荷工况下NOx 排放量预测控制;唐振浩;《化工进展》;343-348 * |
| 基于小波PLS电站锅炉NO_x自适应预测;戴新;尹金和;齐咏生;郝光;李引龙;;《能源与节能》;20150320(第03期);全文 * |
| 多元线性回归方法预测燃气轮机发电机组性能;刘闯等;《中国电机工程学报》;4731-4736 * |
| 火电机组运行参数及优化效率间的偏回归分析;成艳亭;《2021中国自动化大会论文集》;20220131;全文 * |
| 锅炉燃烧优化中NOx预测模型研究进展;卓建坤;《燃烧科学与技术》;第22卷(第6期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112699600A (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109062053B (en) | Denitration ammonia injection control method based on multivariate correction | |
| CN113433911B (en) | Accurate control system and method for ammonia spraying of denitration device based on accurate concentration prediction | |
| CN114721263B (en) | Intelligent regulation and control method for cement decomposing furnace based on machine learning and intelligent optimization algorithm | |
| CN111783947A (en) | Energy consumption prediction method based on LSTM neural network | |
| CN112232373A (en) | Method and system for predicting carbon content of boiler fly ash | |
| CN114186476A (en) | Boiler combustion online optimization method based on historical working conditions | |
| CN117871771B (en) | Big data-based gas energy monitoring method | |
| CN111401652A (en) | Boiler optimization method and system based on CO online detection | |
| CN108762086B (en) | Secondary reheat steam temperature control device and control system based on model predictive control | |
| CN112699600B (en) | Thermal power operating parameters and NOxMethod for analyzing partial return between emission concentrations | |
| CN113887116A (en) | Power station boiler dynamic operation main steam temperature delay characteristic modeling method | |
| CN117031938A (en) | Fuzzy neural network control method for urban solid waste incineration hearth temperature | |
| CN110684547A (en) | Optimized control method for biomass pyrolysis carbonization kiln | |
| CN113742989B (en) | Combustion optimization control method and device, storage medium and electronic equipment | |
| Ahamed et al. | Reinforcement learning controllers for automatic generation control in power systems having reheat units with GRC and dead-band | |
| CN114896860B (en) | Soft measurement method for carbon content of fly ash based on LightGBM and XGBoost combined model | |
| CN117991639B (en) | Multi-target combustion optimization control method and device for coal-fired power plant based on machine learning | |
| CN111459030B (en) | Self-adaptive modeling method for closed-loop combustion optimization of boiler | |
| CN117937474B (en) | New energy station energy storage management method and system | |
| CN117993667B (en) | Multi-element information fusion-based generator set combustion optimization system and method | |
| CN118367609B (en) | Intelligent data optimization processing system of new energy station | |
| CN115573819A (en) | Gas turbine T-S model optimization method based on multi-model predictive control algorithm | |
| Ye et al. | Day-Ahead Load Forecasting Method Considering Cumulative Effect of Temperature | |
| CN117668715A (en) | Modeling method for intelligent prediction of NOx emission of thermal power plant based on GRU | |
| CN117195431A (en) | Valve-regulating flow optimization method, device, equipment and medium for turbine of generator set |
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 |