CN107016176A - A kind of hybrid intelligent overall boiler burning optimization method - Google Patents
A kind of hybrid intelligent overall boiler burning optimization method Download PDFInfo
- Publication number
- CN107016176A CN107016176A CN201710182707.2A CN201710182707A CN107016176A CN 107016176 A CN107016176 A CN 107016176A CN 201710182707 A CN201710182707 A CN 201710182707A CN 107016176 A CN107016176 A CN 107016176A
- Authority
- CN
- China
- Prior art keywords
- boiler
- coal
- index
- coal pulverizer
- parameter
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
Abstract
The invention discloses a kind of hybrid intelligent overall boiler burning optimization method, the present invention is for boiler combustion efficiency and the problem in the optimization of coal pulverizer power consumption, construct one it is simple and practical with boiler efficiency positive correlation index, the index is combined with coal pulverizer indicator of power consumption, a kind of overall boiler burning optimization method with stronger learning ability is proposed, economy is optimized.The technical scheme is that the data acquisition for passing through boiler, index and coal pulverizer indicator of power consumption for boiler combustion efficiency set up model, using means such as parallel optimized algorithm optimizing, establish a kind of method of overall boiler burning optimization, the efficiency of overall boiler burning optimization can be effectively improved using this method, can both implement offline optimization can also carry out online burning optimization in real time.
Description
Technical field
The invention belongs to information and control technology field, it is related to automatic technology, more particularly to a kind of mixing
Intelligent boiler efficiency combustor optimization method.
Background technology
The burning optimization of boiler is the important technical of energy-saving and emission-reduction, and its target is in certain boiler load condition
Under, by adjusting boiler wind speed adjustment, obtaining high-efficiency operation state to operational factors such as coals.The air distribution of boiler, run to coal etc.
The collocation of parameter has direct influence on boiler combustion status, different air distribution, the configuration meeting to operating parameters such as coal and oxygen amount
Directly result in different boiler efficiency situations.Meanwhile, the operation of coal pulverizer has extreme influence to boiler combustion efficiency, moreover, mill
Coal machine power consumption is also the major part of the station service of power plant, therefore in order to be able to preferably obtain Economic model, it is necessary to
Coal pulverizer is connected with boiler combustion, optimized together, so as to obtain comprehensive most effective fruit.For given boiler,
Under certain loading condiction, for efficiency of combustion, there is a kind of optimal operating parameter allocation plan, efficiency of combustion can be made
Optimize, still, there is extremely complex coupled relation between the operating parameter of boiler, to find the configuration of optimal operating parameter
It is not easy to.For boiler efficiency, have some calculate need data can not also real-time online obtain, more cause
Online real-time optimization is carried out to boiler efficiency difficult very big.For given coal pulverizer, it is present in boiler combustion similar
Situation.With the continuous progress of science and technology, boiler operatiopn automaticity is improved constantly, but boiler combustion and coal pulverizer fortune
Row optimization problem never has to be resolved well.
The burning of boiler and coal pulverizer operation mainly carry out the experiment of different operating modes by commissioning staff in practice, for tool
The operational factor that boiler, coal pulverizer and the coal situation of body have been found by substantial amounts of experiment is configured, to be supplied to operation people
Member makees reference, and such a method is time-consuming, laborious and parameter combination that can test is limited, therefore is found most by pilot scale study
Also there is larger room for promotion in excellent parameter configuration, and this method can't be realized and carried out online according to real-time change situation
Optimization.
The professional knowledge run by boiler combustion and coal pulverizer and experimental analysis, build one and boiler efficiency positive correlation
And calculate simple, the online index calculated in real time can be realized, while coal pulverizer power consumption is taken into account, and then using it as target
Comprehensive combustion parameter optimization is carried out, so as to reach the online burning optimization target to boiler efficiency and coal pulverizer power consumption.It is logical
Data mining is crossed, in a large amount of different operational factor combinations, using the method for machine learning, operational factor and construction is excavated
Relational model between index, burning and coal pulverizer running optimizatin in conjunction with optimized algorithm to progress boiler are very potential
Method.This method is really achieved the actual requirement of boiler for producing, be the problem for perplexing engineers and technicians, main bugbear
Including, how to construct with boiler efficiency positive correlation index, how to improve prediction and the generalization ability of model, how to improve model
How incremental learning ability, to enrich the target of boiler combustion optimization, makes up to and takes into account more fully optimizing for indices
Purpose.
The content of the invention
It is an object of the present invention to run the problem in complex optimum for boiler combustion efficiency and coal pulverizer, one is constructed
It is simple and practical with boiler efficiency positive correlation and to include the index of coal pulverizer power consumption, propose a kind of there is stronger incremental learning ability
Boiler combustion optimization, optimize economy.
The technical scheme is that by the data acquisition of boiler, the index and coal-grinding for boiler combustion efficiency are electromechanical
Index Establishment model is consumed, using means such as parallel optimized algorithm optimizing, a kind of intelligent boiler burning complex optimum is established
Method, the efficiency of overall boiler burning optimization can be effectively improved using this method, and can both implement offline optimization can also be carried out
Online burning optimization in real time.The present invention's comprises the concrete steps that：
Step (1) is based on boiler combustion professional knowledge and experimental study, construction and the positively related finger of the boiler combustion thermal efficiency
MarkWherein Δ T=T1-T2, T1Temperature is characterized for burner hearth, can be measured and obtained by non-contact type temperature measurement instrument, such as
Obtained by infrared non-contact type temperature measurement instrument, or by the DCS system of boiler combustion, T2Temperature is characterized for back-end ductwork,
Temperature after temperature or economizer, can obtain from the DCS system of boiler combustion or direct measurement is obtained after desirable air preheater；To be every
Ton is coal-fired to produce flue gas coefficient of discharge, and the coefficient is relevant with ature of coal, can calculate and obtain according to coal elements analyze data, calculation formula is
The ripe and extensive use formula in industry calculating；Also it can return and obtain according to the experiment of coal and correspondence boiler, such as required precision
It is less high, it can also be obtained according to corresponding specific empirical equation；Q is unit time Coal-fired capacity.
Largely calculate and test through applicant, as a result show index η and boiler combustion efficiency positive correlation.Therefore it can pass through
Optimizing index η and then the target for realizing optimization boiler combustion efficiency, index η calculate simple, can avoid boiler efficiency and calculate institute
Mass data is needed, especially those data that can not also accurately obtain online at present, such as flying marking and clinker are carbon containing, referred to
Calculating data needed for mark η can be obtained online, it is possible to which real-time online optimizes, and then reach real-time online optimization boiler effect
The purpose of rate.
Step (2) is in boiler combustion process, and the operation conditions of coal pulverizer has extreme influence to boiler combustion, therefore is directed to
Coal pulverizer is modeled using intelligent modeling method, and this patent is modeled using algorithm of support vector machine, and model output is coal-grinding power consumption
Index μ, input quantity is coal pulverizer operational factor：Fineness of pulverized coal, pulverized-coal concentration, primary air velocity, material position, drum speed, First air
Temperature.These operational factor numerical value can be obtained from DCS system.Input parameter and index μ output parameter for modeling sample
It is expressed asWherein xiRepresent i-th group of coal pulverizer operational factor vector as input data, yiRepresent i-th group of conduct
Output parameter characteristic index μ, N are sample size, based on actual operating data, set up coal pulverizer operational factor and index μ
Between model.Following mathematical modeling process is ripe general SVMs theoretical modeling process, and its mathematical derivation is found in
General SVMs theory book, only makees briefly narration herein.
SVMs kernel function elects RBF as：
σ is the width of RBF, and the representation is canonical form；φ (x) is mapping function, if required target
Function is：f(xi)=w φ (xi)+b, f (xi) for model export boiler combustion status characteristic index predicted value, w for power
Weight coefficient vector, b is intercept.Introduce relaxation factor ξ* i>=0 and ξi>=0 and allow error of fitting ε, and set in sample point and have k (0
≤ k ＜ N) individual point error beyond allow error of fitting ε, model can by constraint：
Under the conditions of, minimize：
Obtain, wherein constant C>0 is penalty coefficient.The minimization problem is a convex quadratic programming problem, introduces glug
Bright day function：
Wherein：For Lagrange's multiplier.
At saddle point, function L is on w, b, ξi,ξi *Minimal point, be alsoMaximal point, minimization problem
It is converted into the maximization problems for seeking its dual problem.
LagrangianL is on w, b, ξ at saddle pointi,ξi *Minimal point, is obtained：
The dual function of Lagrangian can be obtained：
Now,
According to Ku En-Plutarch (KKT) conditional theorem, there is following formula establishment in saddle point：
From above formula, αi·αi *=0, αiAnd αi *All without being simultaneously non-zero, it can obtain：
B can be obtained from above formula, model is obtained.
The determination of penalty factor C and Radial basis kernel function parameter σ numerical value in model, is obtained using optimized algorithm optimizing, this
Only illustrate C and σ optimization method so that heredity is calculated as an example in patent：
A. the initial vector v of setting genetic algorithm each dimension component is respectively C and σ, and C and σ optimizing is interval；
B. setting Genetic algorithm searching target, crossover probability are set to 0.25, mutation probability 0.25, select probability and are set to 0.25
It it is 100-10000 times with iterations, search target predicts the standard deviation of modeling and inspection data to minimize；
C. when genetic algorithm completes iteration, that is, optimal C and σ parameter values are obtained.
Step (3), the model set up between index η and boiler operating parameter；Described boiler operating parameter includes each layer
Primary air velocity, fineness of pulverized coal, wind point concentration, wind-warm syndrome, the secondary wind speed of each layer, furnace outlet flue gas oxygen content and burnout degree
Speed.Wherein, in primary air velocity, fineness of pulverized coal, wind point wind-warm syndrome of concentration and previous step in coal pulverizer operational factor once
Wind speed, fineness of pulverized coal, wind point wind-warm syndrome of concentration are identical parameters.Specific modeling method as modeling method in step (2),
It is not repeated herein.
Step (4) utilize particle swarm optimization algorithm combination institute established model, for index η and μ carry out boiler operating parameter and
The complex optimum of coal pulverizer configuration, is comprised the following steps that：
D. each dimension component for defining population position vector x is respectively boiler operating parameter and coal pulverizer operational factor, phase
A parameter is only taken with part；
E. the search target and iterations of population are set, search target is index：(η-μ), iterations can be according to tool
The demand of the boiler real-time optimization of body determines that scope typically exists：10 to 10000 times；
F. the Search Range of each operational factor, identical ginseng are set according to the design of actual boiler and coal pulverizer and service requirement
Number Search Range is identical, and initialized location vector x, the search target then set according to previous step and the operation of built coal pulverizer
The prediction of indicator of power consumption μ models and the prediction of boiler operatiopn thermal efficiency index η models, calculating is iterated with particle cluster algorithm,
Search for optimal location of the population in parameter vector space；
G. when particle cluster algorithm complete iterations or find sets requirement it is optimal when, stop calculating and obtain corresponding optimal
Position vector, that is, obtain optimal boiler operating parameter combination and optimal coal pulverizer operational factor operative combination.
Boiler efficiency and the online real-time optimization of coal pulverizer power consumption are always a problem for perplexing industry research personnel, because
It calculates complicated and required data and all can not obtained in real time.The inventive method be specifically construct one with boiler efficiency just
Related and calculating is simple to realize the online index calculated in real time, and the index is combined with coal pulverizer indicator of power consumption, and further
Collection boiler real time data simultaneously utilizes data mining algorithm, is modeled for the index, with reference to fortune of the optimizing algorithm to boiler
Row is optimized, to reach efficient target.The inventive method both can also offline optimization with on-line optimization.
Embodiment
A kind of hybrid intelligent boiler efficiency burning optimization method, specifically following steps：
(1) boiler combustion professional knowledge and experimental study, construction and the positively related index of the boiler combustion thermal efficiency are based onWherein Δ T=T1-T2, T1Temperature is characterized for burner hearth, can be measured and obtained by non-contact type temperature measurement instrument, it is such as logical
Infrared non-contact type temperature measurement instrument is crossed, or is obtained by the DCS system of boiler combustion, T2Temperature is characterized for back-end ductwork, can
Temperature after temperature or economizer is taken after air preheater, can be obtained from the DCS system of boiler combustion or direct measurement is obtained；To be per ton
Fire coal produces flue gas coefficient of discharge, and the coefficient is relevant with ature of coal, can calculate and obtain according to coal elements analyze data, calculation formula is into
The ripe and extensive use formula in industry calculating；Also acquisition, such as required precision can be returned not according to the experiment of coal and correspondence boiler
It is too high, it can also be obtained according to corresponding specific empirical equation；Q is unit time Coal-fired capacity.
Largely calculate and test through applicant, as a result show index η and boiler combustion efficiency positive correlation.Therefore it can pass through
Optimizing index η and then the target for realizing optimization boiler combustion efficiency, index η calculate simple, can avoid boiler efficiency and calculate institute
Mass data is needed, especially those data that can not also accurately obtain online at present, such as flying marking and clinker are carbon containing, referred to
Calculating data needed for mark η can be obtained online, it is possible to which real-time online optimizes, and then reach real-time online optimization boiler effect
The purpose of rate.
(2) in boiler combustion process, the operation conditions of coal pulverizer has extreme influence to boiler combustion, therefore for coal-grinding
Machine is modeled using intelligent modeling method, and this patent is modeled using algorithm of support vector machine, and model output is coal-grinding indicator of power consumption
μ, input quantity is coal pulverizer operational factor：Fineness of pulverized coal, pulverized-coal concentration, primary air velocity, material position, drum speed, a wind-warm syndrome.This
A little operational factor numerical value can be obtained from DCS system.It is expressed as the input parameter of modeling sample and index μ output parameterWherein xiRepresent i-th group of coal pulverizer operational factor vector as input data, yiRepresent that i-th group is joined as output
Number characteristic index μ, N are sample size, based on actual operating data, the mould set up between coal pulverizer operational factor and index μ
Type.Following mathematical modeling process is ripe general SVMs theoretical modeling process, and its mathematical derivation is found in general
SVMs theory book, only makees briefly narration herein.
SVMs kernel function elects RBF as：
σ is the width of RBF, and the representation is canonical form；φ (x) is mapping function, if required target
Function is：f(xi)=w φ (xi)+b, f (xi) for model export boiler combustion status characteristic index predicted value, w for power
Weight coefficient vector, b is intercept.Introduce relaxation factor ξ* i>=0 and ξi>=0 and allow error of fitting ε, and set in sample point and have k (0
≤ k ＜ N) individual point error beyond allow error of fitting ε, model can by constraint：
Under the conditions of, minimize：
Obtain, wherein constant C>0 is penalty coefficient.The minimization problem is a convex quadratic programming problem, introduces glug
Bright day function：
Wherein：For Lagrange's multiplier.
At saddle point, function L is on w, b, ξi,ξi *Minimal point, be alsoMaximal point, minimization problem
It is converted into the maximization problems for seeking its dual problem.
LagrangianL is on w, b, ξ at saddle pointi,ξi *Minimal point, is obtained：
The dual function of Lagrangian can be obtained：
Now,
According to Ku En-Plutarch (KKT) conditional theorem, there is following formula establishment in saddle point：
From above formula, αi·αi *=0, αiAnd αi *All without being simultaneously non-zero, it can obtain：
B can be obtained from above formula, model is obtained.
The determination of penalty factor C and Radial basis kernel function parameter σ numerical value in model, can be obtained using optimized algorithm optimizing
, only illustrate C and σ optimization method so that heredity is calculated as an example in this patent：
D. the initial vector v of setting genetic algorithm each dimension component is respectively C and σ, and C and σ optimizing is interval；
E. setting Genetic algorithm searching target, crossover probability are set to 0.25, mutation probability 0.25, select probability and are set to 0.25
It it is 100-10000 times with iterations, search target predicts the standard deviation of modeling and inspection data to minimize；
F. when genetic algorithm completes iteration, that is, optimal C and σ parameter values are obtained.
(3) model, set up between index η and boiler operating parameter；Described boiler operating parameter includes each layer once
Wind speed, fineness of pulverized coal, wind point concentration, wind-warm syndrome, the secondary wind speed of each layer, furnace outlet flue gas oxygen content and after-flame wind speed.
Wherein, primary air velocity, fineness of pulverized coal, wind divide the First air in coal pulverizer operational factor in wind-warm syndrome of concentration and previous step
Speed, fineness of pulverized coal, wind point wind-warm syndrome of concentration are identical parameters.Specific modeling method as modeling method in step (2),
This is not repeated.
(4) utilizes particle swarm optimization algorithm combination institute established model, and boiler operating parameter and coal-grinding are carried out for index η and μ
The complex optimum of machine configuration, is comprised the following steps that：
D. each dimension component for defining population position vector x is respectively boiler operating parameter and coal pulverizer operational factor, phase
A parameter is only taken with part；
E. the search target and iterations of population are set, search target is index：(η-μ), iterations can be according to tool
The demand of the boiler real-time optimization of body determines that scope typically exists：10 to 10000 times；
F. the Search Range of each operational factor, identical ginseng are set according to the design of actual boiler and coal pulverizer and service requirement
Number Search Range is identical, and initialized location vector x, the search target then set according to previous step and the operation of built coal pulverizer
The prediction of indicator of power consumption μ models and the prediction of boiler operatiopn thermal efficiency index η models, calculating is iterated with particle cluster algorithm,
Search for optimal location of the population in parameter vector space；
G. when particle cluster algorithm complete iterations or find sets requirement it is optimal when, stop calculating and obtain corresponding optimal
Position vector, that is, obtain optimal boiler operating parameter combination and optimal coal pulverizer operational factor operative combination.
Claims (2)
1. a kind of hybrid intelligent overall boiler burning optimization method, it is characterised in that：The step of this method, includes：
Step (1) is based on boiler combustion professional knowledge and experimental study, construction and the positively related index of the boiler combustion thermal efficiencyWherein Δ T=T1-T2, T1Temperature, T are characterized for burner hearth2Temperature is characterized for back-end ductwork；For coal-fired generation per ton
Flue gas coefficient of discharge, Q is unit time Coal-fired capacity；
Step (2) is modeled for coal pulverizer using intelligent modeling method, is modeled using algorithm of support vector machine, model output is
Coal-grinding indicator of power consumption μ, input quantity is coal pulverizer operational factor：Fineness of pulverized coal, pulverized-coal concentration, primary air velocity, material position, cylinder turns
Speed, a wind-warm syndrome；These operational factor numerical value are obtained from DCS system；For modeling sample input parameter and index μ it is defeated
Go out parameter to be expressed asWherein xiRepresent i-th group of coal pulverizer operational factor vector as input data, yiRepresent i-th
Group is sample size as output parameter characteristic index μ, N, based on actual operating data, set up coal pulverizer operational factor with
Model between index μ；
Following mathematical modeling process is ripe general SVMs theoretical modeling process, and its mathematical derivation is found in general
SVMs theory book, only makees briefly narration herein；
SVMs kernel function elects RBF as：
σ is the width of RBF, and the representation is canonical form；φ (x) is mapping function, if required object function
For：f(xi)=w φ (xi)+b, f (xi) for model export boiler combustion status characteristic index predicted value, w be weight system
Number vector, b is intercept；Introduce relaxation factor ξ* i>=0 and ξi>=0 and allow error of fitting ε, and set and have k point in sample point
Error is beyond error of fitting ε, 0≤k ＜ N are allowed, and model can be by constraint：
Under the conditions of, minimize：
Obtain, wherein constant C>0 is penalty coefficient；The minimization problem is a convex quadratic programming problem, introduces Lagrange
Function：
Wherein：αi,γi,For Lagrange's multiplier；
At saddle point, function L is on w, b, ξi,ξi *Minimal point, be also αi,, γi,Maximal point, minimization problem turns
Turn to the maximization problems for seeking its dual problem；
LagrangianL is on w, b, ξ at saddle pointi,ξi *Minimal point, is obtained：
The dual function of Lagrangian can be obtained：
Now,
According to Kuhn-Tucker condition theorem, there is following formula establishment in saddle point：
From above formula, αi·αi *=0, αiAnd αi *All without being simultaneously non-zero, it can obtain：
B can be obtained from above formula, model is obtained；
The determination of penalty factor and Radial basis kernel function parameter σ numerical value in model, is obtained using optimized algorithm optimizing；
Step (3), the model set up between index η and boiler operating parameter；Described boiler operating parameter includes each layer once
Wind speed, fineness of pulverized coal, wind point concentration, wind-warm syndrome, the secondary wind speed of each layer, furnace outlet flue gas oxygen content and after-flame wind speed；
Wherein, primary air velocity, fineness of pulverized coal, wind divide the First air in coal pulverizer operational factor in wind-warm syndrome of concentration and previous step
Speed, fineness of pulverized coal, wind point wind-warm syndrome of concentration are identical parameters；Specific modeling method is as modeling method in step (2)；
Step (4) utilizes particle swarm optimization algorithm combination institute established model, and boiler operating parameter and coal-grinding are carried out for index η and μ
The complex optimum of machine configuration, is comprised the following steps that：
A. each dimension component for defining population position vector x is respectively boiler operating parameter and coal pulverizer operational factor, identical portions
Divide and only take a parameter；
B. the search target and iterations of population are set, search target is index：(η-μ), iterations is according to specific pot
The demand of stove real-time optimization determines that scope is：10 to 10000 times；
C. the Search Range of each operational factor is set according to the design of actual boiler and coal pulverizer and service requirement, identical parameters are sought
Excellent scope is identical, and initialized location vector x, the search target then set according to previous step and built coal pulverizer operation power consumption
The prediction of index μ models and the prediction of boiler operatiopn thermal efficiency index η models, calculating is iterated with particle cluster algorithm, search
Optimal location of the population in parameter vector space；
D. when particle cluster algorithm complete iterations or find sets requirement it is optimal when, stop calculating and obtain corresponding optimal position
Vector is put, that is, obtains optimal boiler operating parameter combination and optimal coal pulverizer operational factor operative combination.
2. a kind of hybrid intelligent overall boiler burning optimization method according to claim 1, it is characterised in that：C's and σ seeks
Excellent method comprises the following steps：
A, each dimension component for the initial vector v for setting genetic algorithm are respectively C and σ, and C and σ optimizing is interval；
B, setting Genetic algorithm searching target, crossover probability are set to 0.25, mutation probability 0.25, select probability and are set to 0.25 and change
Generation number is 100-10000 times, and search target predicts the standard deviation of modeling and inspection data to minimize；
C, when genetic algorithm complete iteration, that is, obtain optimal C and σ parameter values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710182707.2A CN107016176A (en) | 2017-03-24 | 2017-03-24 | A kind of hybrid intelligent overall boiler burning optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710182707.2A CN107016176A (en) | 2017-03-24 | 2017-03-24 | A kind of hybrid intelligent overall boiler burning optimization method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107016176A true CN107016176A (en) | 2017-08-04 |
Family
ID=59445418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710182707.2A Pending CN107016176A (en) | 2017-03-24 | 2017-03-24 | A kind of hybrid intelligent overall boiler burning optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107016176A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038306A (en) * | 2017-12-11 | 2018-05-15 | 太原理工大学 | A kind of method of power boiler burning modeling and optimization towards magnanimity high dimensional data |
| CN108764604A (en) * | 2018-04-04 | 2018-11-06 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Large-sized Coal-fired Power group pulverizing optimization control method based on Intelligent evolution algorithm |
| CN108940596A (en) * | 2018-07-12 | 2018-12-07 | 浙江大学 | A kind of electric dust removing system optimal control method based on mixed model |
| CN109033536A (en) * | 2018-06-29 | 2018-12-18 | 杭州电子科技大学 | A kind of fire coal sub-prime utilizes the modeling method of pyrolysis kettle in cleaning treatment system |
| CN109145361A (en) * | 2018-06-29 | 2019-01-04 | 杭州电子科技大学 | A kind of fire coal sub-prime utilizes optimizing operation method with cleaning pretreatment system |
| CN109685264A (en) * | 2018-12-20 | 2019-04-26 | 华润电力技术研究院有限公司 | Thermal power unit operation optimization method, device and computer equipment |
| CN111222625A (en) * | 2018-11-26 | 2020-06-02 | 斗山重工业建设有限公司 | Apparatus for generating learning data for combustion optimization and method thereof |
| WO2020134801A1 (en) * | 2018-12-26 | 2020-07-02 | 厦门邑通软件科技有限公司 | Energy-saving optimization method of cement raw material vertical mill system |
| CN111612210A (en) * | 2020-04-10 | 2020-09-01 | 杭州电子科技大学 | Online optimization method for coal powder fineness of coal mill |
| CN111612211A (en) * | 2020-04-10 | 2020-09-01 | 杭州电子科技大学 | Predictive modeling method for coal powder fineness of coal mill |
| CN113742989A (en) * | 2020-05-27 | 2021-12-03 | 国家能源投资集团有限责任公司 | Combustion optimization control method and device, storage medium and electronic equipment |
| CN114046493A (en) * | 2021-11-02 | 2022-02-15 | 国家能源集团华北电力有限公司廊坊热电厂 | Boiler combustion optimization system and terminal |
Citations (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101038277A (en) * | 2007-04-19 | 2007-09-19 | 东北大学 | Soft measurement method for coal power fineness in powdering producer |
| CN101078526A (en) * | 2007-07-03 | 2007-11-28 | 浙江大学 | Power boiler burning optimization method and device based on infra red radiation energy signal |
| CN101078525A (en) * | 2007-06-25 | 2007-11-28 | 周振华 | Automatic optimization control method of boiler air-supply volume |
| CN101122258A (en) * | 2006-08-09 | 2008-02-13 | 马龙根 | Coal powder gas turbine generation system and process for producing coal powder two-phase flow fuel |
| CN101270311A (en) * | 2007-03-23 | 2008-09-24 | 卢英进 | Grinding burning-rate accelerator for coal, preparation method and application thereof |
| CN101334666A (en) * | 2008-07-15 | 2008-12-31 | 西安艾贝尔科技发展有限公司 | Double-inlet double-outlet steel ball coal mill straight blowing type milling system optimized control method |
| CN101358869A (en) * | 2008-03-17 | 2009-02-04 | 西安艾贝尔科技发展有限公司 | Material level measuring device for steel ball coal mill and optimization and control method of powder-making process by bin type steel ball coal mill |
| CN101498457A (en) * | 2009-03-02 | 2009-08-05 | 杭州电子科技大学 | Boiler combustion optimizing method |
| CN101498458A (en) * | 2009-03-02 | 2009-08-05 | 杭州电子科技大学 | Model updating method for on-line boiler combustion optimization |
| CN101498459A (en) * | 2009-03-02 | 2009-08-05 | 杭州电子科技大学 | Modeling method for boiler combustion optimization |
| CN102226904A (en) * | 2011-05-25 | 2011-10-26 | 浙江省电力试验研究院 | Soft measurement method for air quantity of primary air of large-scale boiler in power station |
| CN102750424A (en) * | 2012-07-16 | 2012-10-24 | 杭州电子科技大学 | Method for optimizing combustion of biomass furnace |
| CN102773144A (en) * | 2011-05-10 | 2012-11-14 | 北京能为科技发展有限公司 | Secondary grinding device of coal mill |
| CN102778538A (en) * | 2012-07-06 | 2012-11-14 | 广东电网公司电力科学研究院 | Soft measuring method based on improved SVM (Support Vector Machine) for measuring boiler unburned carbon content in fly ash |
| CN102799939A (en) * | 2012-07-16 | 2012-11-28 | 杭州电子科技大学 | Biomass furnace combustion-optimized model updating method |
| CN102842066A (en) * | 2012-07-16 | 2012-12-26 | 杭州电子科技大学 | Modeling method for combustion optimization of biomass furnace |
| CN102853447A (en) * | 2012-05-09 | 2013-01-02 | 北京华电天仁电力控制技术有限公司 | On-line coal powder pipeline wind-powder leveling method |
| CN102982390A (en) * | 2012-11-02 | 2013-03-20 | 广东电网公司电力科学研究院 | Boiler combustion efficiency predicting method based on support vector machine incremental algorithm |
| CN103234327A (en) * | 2013-04-22 | 2013-08-07 | 纪宏舜 | Brown coal drying method for bituminous coal boiler fully burning brown coal in thermal power plant |
| CN103324862A (en) * | 2013-07-11 | 2013-09-25 | 中国石油大学(华东) | Coal-fired boiler optimization method based on improved neural network and genetic algorithm |
| CN103400015A (en) * | 2013-08-15 | 2013-11-20 | 华北电力大学 | Composition modeling method for combustion system based on numerical simulation and test operation data |
| CN103939939A (en) * | 2014-03-13 | 2014-07-23 | 青岛立宇科技开发有限公司 | Digitized combustion control and optimization method and system for pulverized coal boiler |
| CN104571018A (en) * | 2014-12-04 | 2015-04-29 | 上海交通大学 | Method for optimizing load distribution of coal-fired power station coal milling system online |
| CN104992028A (en) * | 2015-07-17 | 2015-10-21 | 华北电力大学（保定） | Fossil power generation unit coal blending scheme acquisition method |
| CN105447256A (en) * | 2015-12-04 | 2016-03-30 | 河北省电力建设调整试验所 | Excitation enhancement simulation genetic optimization method |
| CN105488266A (en) * | 2015-11-25 | 2016-04-13 | 江苏方天电力技术有限公司 | Actual power generation power prediction method of thermal power generating unit |
| CN105631151A (en) * | 2016-01-06 | 2016-06-01 | 陈威宇 | Modeling method for pulverized coal fired boiler combustion optimization |
| CN105787211A (en) * | 2016-03-24 | 2016-07-20 | 华南理工大学 | Pressure adjustment method for combined cycle heat recovery boiler with deteriorated gas turbine |
| CN105808945A (en) * | 2016-03-07 | 2016-07-27 | 杭州电子科技大学 | Mixed intelligent boiler combustion efficiency optimization method |
| WO2016137393A1 (en) * | 2015-02-23 | 2016-09-01 | Solar Pv Exchange Pte Ltd | Systems and methods relating to electricity generation |
| CN106327021A (en) * | 2016-08-31 | 2017-01-11 | 西安艾贝尔科技发展有限公司 | Boiler combustion optimization air distribution method based on online model prediction |
-
2017
- 2017-03-24 CN CN201710182707.2A patent/CN107016176A/en active Pending
Patent Citations (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101122258A (en) * | 2006-08-09 | 2008-02-13 | 马龙根 | Coal powder gas turbine generation system and process for producing coal powder two-phase flow fuel |
| CN101270311A (en) * | 2007-03-23 | 2008-09-24 | 卢英进 | Grinding burning-rate accelerator for coal, preparation method and application thereof |
| CN101038277A (en) * | 2007-04-19 | 2007-09-19 | 东北大学 | Soft measurement method for coal power fineness in powdering producer |
| CN101078525A (en) * | 2007-06-25 | 2007-11-28 | 周振华 | Automatic optimization control method of boiler air-supply volume |
| CN101078526A (en) * | 2007-07-03 | 2007-11-28 | 浙江大学 | Power boiler burning optimization method and device based on infra red radiation energy signal |
| CN101358869A (en) * | 2008-03-17 | 2009-02-04 | 西安艾贝尔科技发展有限公司 | Material level measuring device for steel ball coal mill and optimization and control method of powder-making process by bin type steel ball coal mill |
| CN101334666A (en) * | 2008-07-15 | 2008-12-31 | 西安艾贝尔科技发展有限公司 | Double-inlet double-outlet steel ball coal mill straight blowing type milling system optimized control method |
| CN101498457A (en) * | 2009-03-02 | 2009-08-05 | 杭州电子科技大学 | Boiler combustion optimizing method |
| CN101498458A (en) * | 2009-03-02 | 2009-08-05 | 杭州电子科技大学 | Model updating method for on-line boiler combustion optimization |
| CN101498459A (en) * | 2009-03-02 | 2009-08-05 | 杭州电子科技大学 | Modeling method for boiler combustion optimization |
| CN102773144A (en) * | 2011-05-10 | 2012-11-14 | 北京能为科技发展有限公司 | Secondary grinding device of coal mill |
| CN102226904A (en) * | 2011-05-25 | 2011-10-26 | 浙江省电力试验研究院 | Soft measurement method for air quantity of primary air of large-scale boiler in power station |
| CN102853447A (en) * | 2012-05-09 | 2013-01-02 | 北京华电天仁电力控制技术有限公司 | On-line coal powder pipeline wind-powder leveling method |
| CN102778538A (en) * | 2012-07-06 | 2012-11-14 | 广东电网公司电力科学研究院 | Soft measuring method based on improved SVM (Support Vector Machine) for measuring boiler unburned carbon content in fly ash |
| CN102799939A (en) * | 2012-07-16 | 2012-11-28 | 杭州电子科技大学 | Biomass furnace combustion-optimized model updating method |
| CN102750424A (en) * | 2012-07-16 | 2012-10-24 | 杭州电子科技大学 | Method for optimizing combustion of biomass furnace |
| CN102842066A (en) * | 2012-07-16 | 2012-12-26 | 杭州电子科技大学 | Modeling method for combustion optimization of biomass furnace |
| CN102982390A (en) * | 2012-11-02 | 2013-03-20 | 广东电网公司电力科学研究院 | Boiler combustion efficiency predicting method based on support vector machine incremental algorithm |
| CN103234327A (en) * | 2013-04-22 | 2013-08-07 | 纪宏舜 | Brown coal drying method for bituminous coal boiler fully burning brown coal in thermal power plant |
| CN103324862A (en) * | 2013-07-11 | 2013-09-25 | 中国石油大学(华东) | Coal-fired boiler optimization method based on improved neural network and genetic algorithm |
| CN103400015A (en) * | 2013-08-15 | 2013-11-20 | 华北电力大学 | Composition modeling method for combustion system based on numerical simulation and test operation data |
| CN103939939A (en) * | 2014-03-13 | 2014-07-23 | 青岛立宇科技开发有限公司 | Digitized combustion control and optimization method and system for pulverized coal boiler |
| CN104571018A (en) * | 2014-12-04 | 2015-04-29 | 上海交通大学 | Method for optimizing load distribution of coal-fired power station coal milling system online |
| WO2016137393A1 (en) * | 2015-02-23 | 2016-09-01 | Solar Pv Exchange Pte Ltd | Systems and methods relating to electricity generation |
| CN104992028A (en) * | 2015-07-17 | 2015-10-21 | 华北电力大学（保定） | Fossil power generation unit coal blending scheme acquisition method |
| CN105488266A (en) * | 2015-11-25 | 2016-04-13 | 江苏方天电力技术有限公司 | Actual power generation power prediction method of thermal power generating unit |
| CN105447256A (en) * | 2015-12-04 | 2016-03-30 | 河北省电力建设调整试验所 | Excitation enhancement simulation genetic optimization method |
| CN105631151A (en) * | 2016-01-06 | 2016-06-01 | 陈威宇 | Modeling method for pulverized coal fired boiler combustion optimization |
| CN105808945A (en) * | 2016-03-07 | 2016-07-27 | 杭州电子科技大学 | Mixed intelligent boiler combustion efficiency optimization method |
| CN105787211A (en) * | 2016-03-24 | 2016-07-20 | 华南理工大学 | Pressure adjustment method for combined cycle heat recovery boiler with deteriorated gas turbine |
| CN106327021A (en) * | 2016-08-31 | 2017-01-11 | 西安艾贝尔科技发展有限公司 | Boiler combustion optimization air distribution method based on online model prediction |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038306A (en) * | 2017-12-11 | 2018-05-15 | 太原理工大学 | A kind of method of power boiler burning modeling and optimization towards magnanimity high dimensional data |
| CN108764604A (en) * | 2018-04-04 | 2018-11-06 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Large-sized Coal-fired Power group pulverizing optimization control method based on Intelligent evolution algorithm |
| CN109033536A (en) * | 2018-06-29 | 2018-12-18 | 杭州电子科技大学 | A kind of fire coal sub-prime utilizes the modeling method of pyrolysis kettle in cleaning treatment system |
| CN109145361A (en) * | 2018-06-29 | 2019-01-04 | 杭州电子科技大学 | A kind of fire coal sub-prime utilizes optimizing operation method with cleaning pretreatment system |
| CN108940596A (en) * | 2018-07-12 | 2018-12-07 | 浙江大学 | A kind of electric dust removing system optimal control method based on mixed model |
| CN111222625A (en) * | 2018-11-26 | 2020-06-02 | 斗山重工业建设有限公司 | Apparatus for generating learning data for combustion optimization and method thereof |
| CN111222625B (en) * | 2018-11-26 | 2024-04-05 | 斗山重工业建设有限公司 | Apparatus for generating learning data |
| CN109685264A (en) * | 2018-12-20 | 2019-04-26 | 华润电力技术研究院有限公司 | Thermal power unit operation optimization method, device and computer equipment |
| WO2020134801A1 (en) * | 2018-12-26 | 2020-07-02 | 厦门邑通软件科技有限公司 | Energy-saving optimization method of cement raw material vertical mill system |
| CN111612210A (en) * | 2020-04-10 | 2020-09-01 | 杭州电子科技大学 | Online optimization method for coal powder fineness of coal mill |
| CN111612211A (en) * | 2020-04-10 | 2020-09-01 | 杭州电子科技大学 | Predictive modeling method for coal powder fineness of coal mill |
| CN113742989A (en) * | 2020-05-27 | 2021-12-03 | 国家能源投资集团有限责任公司 | Combustion optimization control method and device, storage medium and electronic equipment |
| CN114046493A (en) * | 2021-11-02 | 2022-02-15 | 国家能源集团华北电力有限公司廊坊热电厂 | Boiler combustion optimization system and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107016176A (en) | A kind of hybrid intelligent overall boiler burning optimization method | |
| CN101498457B (en) | Boiler combustion optimizing method | |
| CN101498459B (en) | Modeling method for boiler combustion optimization | |
| CN202101268U (en) | Boiler furnace temperature field distribution control system | |
| CN106594794B (en) | A kind of hybrid intelligent boiler efficiency burning optimization model update method | |
| CN103576655B (en) | A kind of power boiler burning subspace modeling and Multipurpose Optimal Method and system | |
| Lv et al. | A dynamic model for the bed temperature prediction of circulating fluidized bed boilers based on least squares support vector machine with real operational data | |
| CN101187804A (en) | Thermal power unit operation optimization rule extraction method based on data excavation | |
| CN101441442B (en) | Control device for plant, control device for thermal power plant, and gas concentration estimation device of coal-burning boiler | |
| CN103092171B (en) | Cement digital management and control system | |
| CN105808945B (en) | A kind of hybrid intelligent boiler efficiency burning optimization method | |
| CN102252343B (en) | Method for optimizing combustion of porous medium combustor | |
| CN102750424B (en) | Method for optimizing combustion of biomass furnace | |
| CN102778538A (en) | Soft measuring method based on improved SVM (Support Vector Machine) for measuring boiler unburned carbon content in fly ash | |
| CN104061588A (en) | Low-nitrogen combustion control method and system based on secondary air door air regulation control | |
| CN104534507A (en) | Optimal control method for combustion of boiler | |
| CN107274027A (en) | A kind of many coal coal mixing combustion optimization methods of coal unit | |
| CN102842066A (en) | Modeling method for combustion optimization of biomass furnace | |
| KR20210029807A (en) | Boiler coal saving control method | |
| CN111881554A (en) | Optimization control method for boiler changing along with air temperature | |
| Xia et al. | An online case-based reasoning system for coal blends combustion optimization of thermal power plant | |
| Cai et al. | On-line monitoring the performance of coal-fired power unit: A method based on support vector machine | |
| CN103728071A (en) | Maximum power output measuring method for thermal power generating unit | |
| CN114580265A (en) | Load scheduling and distributing method and platform for multi-furnace multi-machine complex production system | |
| Xu et al. | A new online optimization method for boiler combustion system based on the data-driven technique and the case-based reasoning principle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170804 |