CN109033536A - A kind of fire coal sub-prime utilizes the modeling method of pyrolysis kettle in cleaning treatment system - Google Patents
A kind of fire coal sub-prime utilizes the modeling method of pyrolysis kettle in cleaning treatment system Download PDFInfo
- Publication number
- CN109033536A CN109033536A CN201810698938.3A CN201810698938A CN109033536A CN 109033536 A CN109033536 A CN 109033536A CN 201810698938 A CN201810698938 A CN 201810698938A CN 109033536 A CN109033536 A CN 109033536A
- Authority
- CN
- China
- Prior art keywords
- coal
- kettle
- parameter
- prime
- cleaning treatment
- 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
- 238000000197 pyrolysis Methods 0.000 title claims abstract description 58
- 238000004140 cleaning Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 23
- 239000003245 coal Substances 0.000 title claims description 42
- 238000004519 manufacturing process Methods 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000012512 characterization method Methods 0.000 claims description 6
- 230000009977 dual effect Effects 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 239000000567 combustion gas Substances 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 claims description 3
- 108010074864 Factor XI Proteins 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 238000013499 data model Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000275 quality assurance Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Abstract
The invention discloses a kind of coal-fired sub-primes to utilize the modeling method that kettle is pyrolyzed in cleaning treatment system, the present invention passes through coal-fired sub-prime and utilizes cleaning treatment system data acquisition and modeling, coal-fired sub-prime is established using the operation characteristic model of cleaning treatment system pyrolysis kettle, a kind of established coal-fired sub-prime is pyrolyzed the modeling method of kettle running optimizatin using cleaning treatment system, and the stronger coal-fired sub-prime of the more accurate and generalization ability that can be established using this method is pyrolyzed kettle optimal operation model using cleaning treatment system.
Description
Technical field
The invention belongs to information control technology fields, are related to data modeling technology, more particularly to a kind of fire coal
Sub-prime utilizes the modeling method that kettle is pyrolyzed in cleaning treatment system.
Background technique
Coal-fired sub-prime is that coal-fired sub-prime utilizes heat in cleaning treatment system using the control for being pyrolyzed kettle in cleaning treatment system
Solution reaction and different product quality assurance most important key problem in technology, target be certain working condition and require under, according to
The case where being pyrolyzed kettle coal input quantity and coal quality parameter can obtain optimal heat by adjusting pyrolysis each burner operating parameter of kettle
Kettle state characteristic index is solved, thus benefit on the basis of making product meet production requirement.It is different coal-supplying amount, different
Each burner of coal quality situation and pyrolysis kettle gives wind and the difference to operating parameters such as combustion gas, all to the temperature point in pyrolysis kettle
Direct influence is distributed in cloth and pressure, and the oil supply of different burners and the credit union of matching to wind directly result in different reaction kettles
The case where interior Temperature and pressure distribution, and then determine that coal-fired sub-prime utilizes the product situation and yield feelings of cleaning treatment system
Condition, especially in the case where there is disturbance, Temperature and pressure distribution is more unstable.In certain appointed condition and product demand
Under, there is a kind of optimal operating parameter configuration (including each burner operating parameter) scheme for pyrolysis kettle, can make corresponding
Pyrolysis kettle state characteristic index it is optimal, to reach the target of production efficiency and maximizing the benefits.But in pyrolysis kettle
Temperature and pressure distribution with each burner operating parameter, pyrolysis kettle coal input quantity, coal quality parameter and pyrolysis kettle difference section product volume and
Quality parameter has extremely complex coupled relation, and the configuration that find optimal operating parameter is not easy to.Coal-fired sub-prime benefit
It is the art production process of new life a kind of with cleaning treatment system, is utilized mainly for coal-fired sub-prime and improve its utilization efficiency,
Coal-fired disposal of pollutants is reduced simultaneously, and running optimizatin control problem has not been solved yet.
In actual production, since it is emerging production technology, coal-fired sub-prime is main using the operation of cleaning treatment system
Or grope by staff, target also only maintains production to be normally carried out, therefore operating status is also in its production process
Very big can room for promotion.
, using modeling algorithm, each burning is returned out in a large amount of different production run parameter combinations by data modeling
Relational model in device operating parameter, pyrolysis kettle coal input quantity, coal quality parameter and pyrolysis kettle between axial Temperature and pressure distribution, under
The running optimizatin of one step is laid a solid foundation.So that this method is really achieved coal-fired sub-prime and utilizes cleaning treatment system production
Actual requirement is the key that the technology, and main bugbear includes the predictive ability and generalization ability for how improving model.
Summary of the invention
It is an object of the present invention to, using the bottleneck problem in cleaning treatment running Optimization, propose one for coal-fired sub-prime
The coal-fired sub-prime of kind is pyrolyzed the modeling method of kettle using cleaning treatment system.
The technical scheme is that utilizing cleaning treatment system data acquisition and modeling by coal-fired sub-prime, establish coal-fired
Sub-prime is pyrolyzed the operation characteristic model of kettle using cleaning treatment system, and a kind of coal-fired sub-prime established utilizes cleaning treatment system heat
The modeling method for solving kettle running optimizatin, the stronger coal-fired sub-prime of the more accurate and generalization ability that can be established using this method are utilized
Cleaning treatment system is pyrolyzed kettle optimal operation model.
The step of the method for the present invention includes:
Step (1) acquires coal-fired sub-prime using in cleaning treatment system production process, and each burner of pyrolysis kettle runs ginseng
Number, pyrolysis kettle coal input quantity, coal quality parameter, the characteristic index of the state of pyrolysis kettle difference section product volume and quality parameter, pyrolysis kettle;
It is specific to be pyrolyzed each burner operating parameter of kettle, pyrolysis kettle coal input quantity, coal quality parameter, pyrolysis kettle difference section product volume and quality ginseng
Number, pyrolysis kettle institute state characteristic index, by coal-fired sub-prime utilize cleaning treatment production process in real-time data signal library
System obtains, or directly measures analysis acquisition by instrument and equipment.
Each burner operating parameter is for the air output of each burner and to combustion gas tolerance;The pyrolysis kettle
The temperature and pressure that state characteristic index is axially distinct section in reaction kettle, M temperature being axially arranged according to reaction kettle inner wall
It is obtained with pressure monitoring point, M >=3;
After acquiring data, modeled.
Step (2) is used the algorithm modeled based on data regression to establish coal-fired sub-prime and utilizes cleaning treatment system burner
Multi-objective Model between operating parameter, pyrolysis kettle coal input quantity and coal quality parameter and pyrolysis kettle state characteristic index;Specifically:
It is modeled using algorithm of support vector machine, because algorithm of support vector machine model built generalization ability is stronger.For building
The input parameter of mould and the output parameter of characterization pyrolysis kettle state characteristic index are expressed asWherein xiIndicate i-th group
As input data parameter, input data parameter includes each burner operating parameter, pyrolysis kettle coal input quantity, coal quality parameter, yiTable
Show the parameter vector of i-th group of characterization pyrolysis kettle state characteristic index as output parameter, N is sample size, with actual motion
Established based on data coal-fired sub-prime using cleaning treatment system burner operating parameter, pyrolysis kettle coal input quantity and coal quality parameter with
The model being pyrolyzed between kettle state characteristic index;
Kernel function is selected as radial basis function:Wherein parameter " σ " is
The width of radial basis function, φ (x) is mapping function, if required objective function are as follows: f (xi)=w φ (xi)+b, f (xi) be
The pyrolysis kettle state characteristic index predicted value of model output, w are weight coefficient vector, and b is intercept.Introduce relaxation factor ξ* i≥0
And ξi>=0 and permission error of fitting ε, model is by constraining:
Under the conditions of, it minimizes:
It obtains, 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 about w, b, ξi,ξi *Minimal point and αi,γi,Maximal point, minimum are asked
Topic is converted into the maximization problems for seeking its dual problem.
LagrangianL is about w, b, ξ at saddle pointi,ξi *Minimal point obtains:
The dual function of Lagrangian can be obtained:
At this point,
According to Kuhn-Tucker condition theorem, there is following formula establishment in saddle point:
By above formula as it can be seen that αi·αi *=0, αiAnd αi *It all will not be simultaneously non-zero, can obtain:
B can be found out from above formula, obtains model.
The numerical value of penalty factor C and Radial basis kernel function parameter σ in model are determined using optimization algorithm optimizing;Complete modeling.
Preferably, the optimization method of the C and σ:
A. each dimension component for defining population position vector v is respectively the optimizing section of C and σ and C and σ;
B. the search target and the number of iterations of population are set, search target is set as the equal of prediction of the model to training sample
Variance, iteration time can be determining according to the demand of specific boiler real-time optimization, range are as follows: 10 to 1000 times;
C. when particle swarm algorithm complete the number of iterations or find sets requirement it is optimal when, stop calculating obtain it is corresponding optimal
Position vector, that is, obtain optimal C and σ parameter value.
The method of the present invention both can be with on-line optimization or with offline optimization, and invention passes through coal-fired sub-prime using clearly
Clean processing system data acquisition and modeling establish coal-fired sub-prime using the operation characteristic model of cleaning treatment system pyrolysis kettle, really
A kind of vertical coal-fired sub-prime using cleaning treatment system pyrolysis kettle running optimizatin modeling method, using this method can establish compared with
Kettle optimal operation model is pyrolyzed using cleaning treatment system for the stronger coal-fired sub-prime of accurate and generalization ability.
Specific embodiment
A kind of fire coal sub-prime utilize with modeling method that kettle is pyrolyzed in cleaning pretreatment system, specifically following steps:
(1) acquires coal-fired sub-prime and utilizes in cleaning treatment system production process, each burner operating parameter of pyrolysis kettle, heat
Solve kettle coal input quantity, coal quality parameter, pyrolysis kettle difference section product volume and the number such as quality parameter and the characteristic index of state for being pyrolyzed kettle
According to;It is specific to be pyrolyzed each burner operating parameter of kettle, pyrolysis kettle coal input quantity, coal quality parameter, pyrolysis kettle difference section product volume and product
Matter parameter and pyrolysis kettle institute state characteristic index, can by coal-fired sub-prime utilize cleaning treatment production process in real time data
Database Systems obtain, or directly measure analysis acquisition by instrument and equipment.
Each burner operating parameter is for the air output of each burner and to combustion gas tolerance;The pyrolysis kettle
Temperature and pressure that state characteristic index is axially distinct section in reaction kettle (can according to required different section output product volumes and
Quality needs, and M temperature and pressure monitoring point of reaction kettle inner wall axial direction, general M >=3 are arranged).
After acquiring data, modeled.
(2) is used the algorithm modeled based on data regression to establish coal-fired sub-prime and is run using cleaning treatment system burner
Multi-objective Model between parameter, pyrolysis kettle coal input quantity and coal quality parameter and pyrolysis kettle state characteristic index.Herein go out with support to
For amount machine algorithm, the explanation of specific modeling method is carried out:
It is modeled using algorithm of support vector machine, because algorithm of support vector machine model built generalization ability is stronger.For building
The input parameter of mould and the output parameter of characterization pyrolysis kettle state characteristic index are expressed asWherein xiIndicate i-th group
As input data parameter (including each burner operating parameter, pyrolysis kettle coal input quantity, coal quality parameter), yiIndicate i-th group of conduct
The parameter vector (temperature value and pressure value of M reaction kettle axial direction) of the characterization pyrolysis kettle state characteristic index of output parameter, N is
Sample size establishes coal-fired sub-prime using cleaning treatment system burner operating parameter, pyrolysis based on actual operating data
Model between kettle coal input quantity and coal quality parameter and pyrolysis kettle state characteristic index;
Kernel function is selected as radial basis function:Wherein parameter " σ " is
The width of radial basis function, φ (x) is mapping function, if required objective function are as follows: f (xi)=w φ (xi)+b, f (xi) be
The pyrolysis kettle state characteristic index predicted value of model output, w are weight coefficient vector, and b is intercept.Introduce relaxation factor ξ* i≥0
And ξi>=0 and permission error of fitting ε, model can be by constraining:
Under the conditions of, it minimizes:
It obtains, 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 about w, b, ξi,ξi *Minimal point and αi,γi,Maximal point, minimum are asked
Topic is converted into the maximization problems for seeking its dual problem.
LagrangianL is about w, b, ξ at saddle pointi,ξi *Minimal point obtains:
The dual function of Lagrangian can be obtained:
At this point,
According to Ku En-Plutarch (KKT) conditional theorem, there is following formula establishment in saddle point:
By above formula as it can be seen that αi·αi *=0, αiAnd αi *It all will not be simultaneously non-zero, can obtain:
B can be found out from above formula, obtains model.
The determination of the numerical value of penalty factor C and Radial basis kernel function parameter σ in model can be obtained using optimization algorithm optimizing
, in this patent only by taking population is calculated as an example, illustrate the optimization method of C and σ:
A. each dimension component for defining population position vector v is respectively the optimizing section of C and σ and C and σ;
B. the search target and the number of iterations of population are set, search target is set as the equal of prediction of the model to training sample
Variance, iteration time can determine that range generally exists: 10 to 1000 times according to the demand of specific boiler real-time optimization;
C. when particle swarm algorithm complete the number of iterations or find sets requirement it is optimal when, stop calculating obtain it is corresponding optimal
Position vector, that is, obtain optimal C and σ parameter value.Complete modeling.
Claims (2)
1. a kind of fire coal sub-prime utilizes the modeling method for being pyrolyzed kettle in cleaning treatment system, it is characterised in that the step of this method wraps
It includes:
Step (1) acquires coal-fired sub-prime and utilizes in cleaning treatment system production process, each burner operating parameter of pyrolysis kettle, heat
Solve the characteristic index of kettle coal input quantity, coal quality parameter, pyrolysis kettle difference section product volume and quality parameter, the state for being pyrolyzed kettle;Specifically
Each burner operating parameter of pyrolysis kettle, pyrolysis kettle coal input quantity, coal quality parameter, pyrolysis kettle difference section product volume and quality parameter,
Be pyrolyzed kettle institute state characteristic index, by coal-fired sub-prime utilize cleaning treatment production process in real-time data signal library system
It obtains, or analysis acquisition is directly measured by instrument and equipment;
Each burner operating parameter is for the air output of each burner and to combustion gas tolerance;The described pyrolysis kettle state
The temperature and pressure that characteristic index is axially distinct section in reaction kettle, the M temperature and pressure being axially arranged according to reaction kettle inner wall
Power monitoring point obtains, M >=3;
After acquiring data, modeled;
Step (2) is used the algorithm modeled based on data regression to establish coal-fired sub-prime and is run using cleaning treatment system burner
Multi-objective Model between parameter, pyrolysis kettle coal input quantity and coal quality parameter and pyrolysis kettle state characteristic index;;Specifically:
It is modeled using algorithm of support vector machine;For the input parameter of modeling and the output ginseng of characterization pyrolysis kettle state characteristic index
Number is expressed asWherein xiI-th group is indicated as input data parameter, input data parameter includes each burner operation
Parameter, pyrolysis kettle coal input quantity, coal quality parameter, yiIndicate i-th group of characterization pyrolysis kettle state characteristic index as output parameter
Parameter vector, N are sample size, and coal-fired sub-prime is established based on actual operating data and is transported using cleaning treatment system burner
Model between row parameter, pyrolysis kettle coal input quantity and coal quality parameter and pyrolysis kettle state characteristic index;
Kernel function is selected as radial basis function:Wherein parameter " σ " is radial base
The width of function, φ (x) is mapping function, if required objective function are as follows: f (xi)=w φ (xi)+b, f (xi) it is that model is defeated
Pyrolysis kettle state characteristic index predicted value out, w are weight coefficient vector, and b is intercept;Introduce relaxation factor ξ* i>=0 and ξi≥0
With permission error of fitting ε, model is by constraining:
Under the conditions of, it minimizes:
It obtains, wherein constant C > 0 is penalty coefficient;The minimization problem is a convex quadratic programming problem, introduces Lagrange
Function:
Wherein:For Lagrange's multiplier;
At saddle point, function L is about w, b, ξi,ξi *Minimal point and αi,γi,Maximal point, minimization problem turn
Turn to the maximization problems for seeking its dual problem;
LagrangianL is about w, b, ξ at saddle pointi,ξi *Minimal point obtains:
The dual function of Lagrangian can be obtained:
At this point,
According to Kuhn-Tucker condition theorem, there is following formula establishment in saddle point:
By above formula as it can be seen that αi·αi *=0, αiAnd αi *It all will not be simultaneously non-zero, can obtain:
B can be found out from above formula, obtains model;
The numerical value of penalty factor C and Radial basis kernel function parameter σ in model are determined using optimization algorithm optimizing;Complete modeling.
2. a kind of coal-fired sub-prime according to claim 1 is using the modeling method for being pyrolyzed kettle in cleaning treatment system, special
Sign is: the optimization method of the C and σ:
A. each dimension component for defining population position vector v is respectively the optimizing section of C and σ and C and σ;
B. the search target and the number of iterations of population are set, search target is set as the square of prediction of the model to training sample
Difference, iteration time can be determining according to the demand of specific boiler real-time optimization, range are as follows: 10 to 1000 times;
C. when particle swarm algorithm complete the number of iterations or find sets requirement it is optimal when, stop calculating and obtain corresponding optimal position
Vector is set, that is, obtains optimal C and σ parameter value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810698938.3A CN109033536A (en) | 2018-06-29 | 2018-06-29 | A kind of fire coal sub-prime utilizes the modeling method of pyrolysis kettle in cleaning treatment system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810698938.3A CN109033536A (en) | 2018-06-29 | 2018-06-29 | A kind of fire coal sub-prime utilizes the modeling method of pyrolysis kettle in cleaning treatment system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109033536A true CN109033536A (en) | 2018-12-18 |
Family
ID=65522108
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810698938.3A Pending CN109033536A (en) | 2018-06-29 | 2018-06-29 | A kind of fire coal sub-prime utilizes the modeling method of pyrolysis kettle in cleaning treatment system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109033536A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102184287A (en) * | 2011-05-05 | 2011-09-14 | 杭州电子科技大学 | Modelling method for combustion optimization of waste plastics oil refining |
CN102222128A (en) * | 2011-05-05 | 2011-10-19 | 杭州电子科技大学 | Method for combustion optimization of waste plastics oil refining |
CN107016176A (en) * | 2017-03-24 | 2017-08-04 | 杭州电子科技大学 | A kind of hybrid intelligent overall boiler burning optimization method |
CN107133460A (en) * | 2017-04-26 | 2017-09-05 | 中国能源建设集团广东省电力设计研究院有限公司 | A kind of online dynamic prediction method of boiler flyash carbon content |
-
2018
- 2018-06-29 CN CN201810698938.3A patent/CN109033536A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102184287A (en) * | 2011-05-05 | 2011-09-14 | 杭州电子科技大学 | Modelling method for combustion optimization of waste plastics oil refining |
CN102222128A (en) * | 2011-05-05 | 2011-10-19 | 杭州电子科技大学 | Method for combustion optimization of waste plastics oil refining |
CN107016176A (en) * | 2017-03-24 | 2017-08-04 | 杭州电子科技大学 | A kind of hybrid intelligent overall boiler burning optimization method |
CN107133460A (en) * | 2017-04-26 | 2017-09-05 | 中国能源建设集团广东省电力设计研究院有限公司 | A kind of online dynamic prediction method of boiler flyash carbon content |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102184287B (en) | Modelling method for combustion optimization of waste plastics oil refining | |
CN101620414B (en) | Method for optimizing cracking depth of industrial ethane cracking furnace on line | |
CN109033511B (en) | A kind of quality coal in cement kiln systems heat consumption analysis method of combined data driving and data mining | |
Yuan et al. | A spatial-temporal LWPLS for adaptive soft sensor modeling and its application for an industrial hydrocracking process | |
CN107016176A (en) | A kind of hybrid intelligent overall boiler burning optimization method | |
CN102222128B (en) | Method for combustion optimization of waste plastics oil refining | |
CN102004444A (en) | Multi-model predictive control method for component content in process of extracting rare earth | |
Yuan et al. | Identification heat user behavior for improving the accuracy of heating load prediction model based on wireless on-off control system | |
CN105242660A (en) | Multi-modal cigarette primary processing process online monitoring and fault diagnosis method based on relative change analysis | |
Chu et al. | Online complex nonlinear industrial process operating optimality assessment using modified robust total kernel partial M-regression | |
Wu et al. | Integrated soft sensing of coke-oven temperature | |
CN102925602A (en) | Furnace profile maintenance method for blast furnace operation | |
Wang et al. | Operation optimization of Shell coal gasification process based on convolutional neural network models | |
CN105808945B (en) | A kind of hybrid intelligent boiler efficiency burning optimization method | |
Gong et al. | Energy efficiency optimization of ethylene production process with respect to a novel FLPEM‐based material‐product nexus | |
Wang et al. | Soft-sensing modeling and intelligent optimal control strategy for distillation yield rate of atmospheric distillation oil refining process | |
CN114334025A (en) | Construction and verification method of cement clinker calcination environment variable | |
CN109033536A (en) | A kind of fire coal sub-prime utilizes the modeling method of pyrolysis kettle in cleaning treatment system | |
CN101301538A (en) | Fuzzy intelligent control system for casting water processing medicament | |
Yu et al. | Research on soft sensing of cement clinker f-CaO based on LS_SVM and burning zone temperature | |
Cheng et al. | Study of the comprehensive evaluation of energy efficiency of an oilfield heating furnace based on combination weighting method | |
CN109101683A (en) | Coal-fired sub-prime utilizes the model update method with cleaning pretreatment system pyrolysis kettle | |
Xie et al. | Energy efficiency analysis and optimization of industrial processes based on a novel data reconciliation | |
Sun et al. | Identification of control regularity of heating stations based on cross-correlation function dynamic time delay method | |
CN104673329A (en) | Internal-heating type continuous carbonization method of biomass moving bed and internal-heating type continuous carbonization device of biomass moving bed |
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: 20181218 |