CN108182553A - A kind of coal-fired boiler combustion efficiency On-line Measuring Method - Google Patents
A kind of coal-fired boiler combustion efficiency On-line Measuring Method Download PDFInfo
- Publication number
- CN108182553A CN108182553A CN201810107733.3A CN201810107733A CN108182553A CN 108182553 A CN108182553 A CN 108182553A CN 201810107733 A CN201810107733 A CN 201810107733A CN 108182553 A CN108182553 A CN 108182553A
- Authority
- CN
- China
- Prior art keywords
- svm
- operating mode
- individual
- combustion efficiency
- boiler combustion
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 137
- 238000002485 combustion reaction Methods 0.000 title claims abstract description 78
- 238000005259 measurement Methods 0.000 claims abstract description 98
- 238000005457 optimization Methods 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000013480 data collection Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 38
- 238000012360 testing method Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000012546 transfer Methods 0.000 claims description 8
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 6
- 239000012141 concentrate Substances 0.000 claims description 6
- 239000003546 flue gas Substances 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 208000011580 syndromic disease Diseases 0.000 claims description 4
- 241000208340 Araliaceae Species 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
- 230000006978 adaptation Effects 0.000 claims description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 231100000219 mutagenic Toxicity 0.000 claims description 3
- 230000003505 mutagenic effect Effects 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims 1
- 230000000875 corresponding effect Effects 0.000 abstract description 11
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 230000002596 correlated effect Effects 0.000 abstract description 2
- 238000010248 power generation Methods 0.000 description 6
- 239000003245 coal Substances 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 3
- 210000000038 chest Anatomy 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000000334 grey box Nutrition 0.000 description 1
- 244000085685 grey box Species 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000003380 propellant Substances 0.000 description 1
- 238000003303 reheating Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Regulation And Control Of Combustion (AREA)
Abstract
The present invention proposes a kind of coal-fired boiler combustion efficiency On-line Measuring Method, obtains the procedure parameter of boiler for producing process, calculates corresponding moment boiler combustion efficiency；The standardisation process parameter sets after feature extraction are determined using Boosted tree methods；Producing condition classification is carried out to the standardisation process parameter sets after feature extraction using K neighbors grader；For all kinds of floor data collection：The LS SVM measurement models of all kinds of operating modes are established, the LS SVM measurement models of all kinds of operating modes are optimized using differential evolution algorithm, obtain the LS SVM measurement models of the boiler combustion efficiency of all kinds of operating modes after final optimization pass；Coal-fired boiler combustion efficiency is measured using the LS SVM measurement models of the boiler combustion efficiency of all kinds of operating modes；This method can realize that high accuracy data driving modeling obtains real-time boiler combustion efficiency according to correlated variables, disclosure satisfy that production requirement.
Description
Technical field
The invention belongs to thermal power generation control technology fields, and in particular to a kind of coal-fired boiler combustion efficiency on-line measurement side
Method.
Background technology
Thermal power generation is the major way of China's power generation, the power generations such as the far super hydroelectric generation of generated energy, wind-power electricity generation
Mode.In thermal power generation production process, coal fired power generation is occupied an leading position, generating set have power is big, stability is good, into
The characteristics of this is low.Coal-burning boiler is the important production equipment in coal-burning power plant, and effect is the energy of release that coal burns in burner hearth
Amount is converted to the thermal energy of high temperature and high pressure steam.Coal-fired boiler combustion efficiency refers to the heat that coal actually discharges in combustion
It accounts for after its completely burned and discharges the ratio of heat, the burning degree of reactive fuel.It is coal-burning boiler production to improve efficiency of combustion
Important indicator, and accurately measuring boiler combustion efficiency is the basis for improving boiler combustion efficiency, reduces operation and maintenance cost
Key.
Coal-fired boiler combustion process includes complicated physicochemical change, by fuel temperature, propellant composition, boiler load etc.
The influence of many factors, and there is strong nonlinearity relationship between parameter, these features cause boiler combustion efficiency to be difficult to online
It is accurate to measure.At present in existing boiler combustion efficiency measuring method, mechanism method, which carries out boiler combustion efficiency calculating, to be reflected
Past boiler combustion efficiency, it is impossible to predict the development trend of boiler combustion efficiency；It is another kind of to be based on statistical data method, such as
ARMA model, grey-box model etc., can predict boiler combustion efficiency trend, but there are required data volume is big, meter
The problem of calculation process is complicated, to noise-sensitive.
Invention content
In view of the deficiencies of the prior art, the present invention proposes a kind of coal-fired boiler combustion efficiency On-line Measuring Method, including with
Lower step：
Step 1：The procedure parameter of boiler for producing process is obtained by SIS in Thermal Power PlantQ, and according to mechanism
Model calculates corresponding moment boiler combustion efficiency, obtains the data acquisition system DATA={ X of boiler for producing processk, Tk| k=1 ...,
K }, wherein, Xk∈RnFor the procedure parameter in k-th of sample, TkFor the boiler combustion efficiency of k-th of sample, K is data acquisition system
Middle sample size, n are procedure parameter dimension；
Step 2：The procedure parameter of the data acquisition system of boiler for producing process is standardized using transfer function, is obtained
Data acquisition system SDATA={ S after to standardizationk, Tk| k=1 ..., K }, wherein, Sk∈RnFor the standardization in k-th of sample
Procedure parameter；
Step 3：The importance of the procedure parameter after standardization is determined using Boosted tree methods, extraction importance is big
In the procedure parameter of importance threshold gamma, the standardisation process parameter sets CDATA={ C after feature extraction are obtainedk, Tk| k=
1 ..., K }, wherein,The standardisation process parameter being characterized in k-th of sample after choosing, ncAfter being characterized extraction
Standardisation process parameter dimension；
Step 4：Operating mode is carried out to the standardisation process parameter sets CDATA after feature extraction using K- neighbors grader
Classification, obtains all kinds of floor data collection LDATAi={ Lp(i), Tp(i)| p (i)=1 ..., P (i) }, and by all kinds of floor data collection
LDATAiIt is divided into training dataset xLDATAi={ Lh(i), Th(i)| h (i)=1 ..., H (i) } and test data set cLDATAi
={ Le(i), Te(i)| e (i)=1 ..., E (i) }；
Wherein, i=1,2 ..., I, I be operating mode quantity,For the process ginseng in i-th p-th of sample of class operating mode
Number, Tp(i)For the boiler combustion efficiency in i-th p-th of sample of class operating mode, P (i) is the i-th class floor data set sample size, h
(i) h-th of the sample number concentrated for the i-th class operating mode training data, H (i) are the i-th class operating mode training data set sample number
Amount, e (i) are e-th of sample number in the i-th class working condition measurement data set, and E (i) is the i-th class working condition measurement data acquisition system sample
Quantity；The procedure parameter in i-th h-th of sample of class operating mode, T are concentrated for training datah(i)It is concentrated for training data
Boiler combustion efficiency in i-th h-th of sample of class operating mode,It is concentrated in i-th e-th of sample of class operating mode for test data
Procedure parameter, Te(i)The boiler combustion efficiency in i-th e-th of sample of class operating mode is concentrated for test data；
Step 5：For all kinds of floor data collection：By all kinds of operating mode training dataset xLDATAiAs input, establish all kinds of
The LS-SVM measurement models of operating mode optimize the LS-SVM measurement models of all kinds of operating modes using differential evolution algorithm, use
Test data set cLDATAiThe LS-SVM measurement models of optimization are tested, obtain the pot of all kinds of operating modes after final optimization pass
The LS-SVM measurement models of stove efficiency of combustion；
By taking the i-th class operating mode as an example, performed according to following steps：
A：Initialize differential evolution algorithm parameter；
The differential evolution algorithm parameter, including：Group size Nα, individual dimension D, greatest iteration algebraically G, mutagenic factor
F, crossover probability CR ∈ [0,1], the differential evolution algorithm population L of initializationα, 0, wherein, α=1,2 ... Nα；
B：LS-SVM parameter values are obtained according to individual information each in population, obtain NαGroup LS-SVM parameter values；
C：Using radial basis function as LS-SVM kernel functions, for the corresponding LS-SVM parameter values of individual each in population with
And i-th class operating mode training dataset establish LS-SVM measurement models, training obtain NαA LS-SVM measurement models；
The LS-SVM models of the i-th class operating mode are as follows：
Wherein, h (i)=1,2 ..., H (i), H (i) are that the training data of the i-th class operating mode concentrates number of training mesh, L(i)
The new samples data of calculating boiler combustion efficiency are needed for the i-th class operating mode,Data L for the i-th class operating mode of corresponding input(i)'s
LS-SVM measurement model output valves, ah(i)、b(i)For the LS-SVM measurement model parameters of the i-th class operating mode, Lh(i)For the i-th class operating mode
Training data concentrates the procedure parameter of h-th of training sample, K (L(i), Lh(i)) LS-SVM measurement models for the i-th class operating mode
Kernel function；
Kernel function K (the L of the LS-SVM measurement models of the i-th class operating mode(i), Lh(i)) as follows：
Wherein, σ(i) 2The width of LS-SVM kernel functions for the i-th class operating mode；
D：The test data of i-th class operating mode is inputted into the LS-SVM models of the i-th class operating mode that each individual is established in population,
Calculate the root-mean-square error value ε of the LS-SVM models of the i-th class operating mode that each individual is established in populationα, i.e., per each and every one in population
The fitness function value f of bodyα=εα；
The root-mean-square error value ε of the LS-SVM models of the i-th class operating mode that each individual is established in the populationαCalculating it is public
Formula is as follows：
Wherein,To be corresponded in the i-th class working condition measurement data set that measurement model is calculated using the α individual
The LS-SVM measurement model output valves of procedure parameter in e-th of sample；
E：Judge whether current iteration number g reaches greatest iteration algebraically G, if so, iteration terminates, obtain optimal L S-
SVM parameters and model parameter ah(i)、b(i), obtain the LS-SVM surveys of the boiler combustion efficiency of the i-th class operating mode after final optimization pass
Model is measured, performs step 6, otherwise, performs F；
F：The g times iteration population is updated, enables iterative algebra g=g+1, returns to B.
F-1：For the α individual L of current iterationα, g, randomly select three individuals in current populationWithIt willWithDifference variation after with individualIt is synthesized into row vector, obtains the variation individual V of the g times iterationα, g,
Wherein, z1, z2, z3∈ [1, Nα]；
It is described to incite somebody to actionWithDifference variation after with individualIt is synthesized into row vector, obtains the variation of the g times iteration
Individual Vα, gCalculation formula it is as follows：
F-2：By the variation individual V of the g times iterationα, gWith the α individual L of the g times iterationα, gCrossover operation is carried out, it is raw
Into the new individual U of the g times iterationα, g；
J-th of component of the new individual of described the g times iteration of generationFormula it is as follows：
Wherein, j=1 ..., D, randjIt is the random number in [0,1] section, randnαThe random integers of ∈ [1, D]；
F-3：Determine the new individual U of the g times iterationα, gWith the α individual L of the g times iterationα, gFitness function
Value, using the small individual of fitness function value as the g+1 times iteration population at individual Lα, g+1, as next-generation individual；
The g+1 times iteration population at individual Lα, g+1Calculation formula it is as follows：
Wherein, f (*) is corresponding individual adaptation degree functional value；
F-4：Iterative algebra g=g+1 is enabled, returns to B.
Step 6：Preserve the LS-SVM measurement models of the boiler combustion efficiency of all kinds of operating modes after optimization；
Step 7：The on-line measurement value of the procedure parameter of boiler for producing process is read in real time, is fired using the boiler of all kinds of operating modes
The LS-SVM measurement models for burning efficiency measure coal-fired boiler combustion efficiency；
Step 7-1：The on-line measurement value of the procedure parameter of boiler for producing process is read in real time, using transfer function to boiler
The procedure parameter of production process is standardized, the procedure parameter after being standardized
Step 7-2：According to the procedure parameter after standardizationSorted out with the cluster centre distance of all kinds of operating modes, it is defeated
In the LS-SVM measurement models for entering the boiler combustion efficiency after the optimization of determining operating mode classification, the online of boiler combustion efficiency is obtained
Measured value.
The meter being standardized using transfer function to the procedure parameter of the data acquisition system of boiler for producing process
It is as follows to calculate formula：
The procedure parameter of the boiler for producing process includes：Economizer feed temperature, superheater wall temperature, the stove of per time instance
Thorax flue gas pressures, main steam pressure, main steam temperature, reheat steam turbine set, reheater steam pressure, reheater steam temperature, stove
It is thorax flue-gas temperature, high-pressure feed water temperature, high-pressure feed water pressure, superheater attemperator vapor (steam) temperature, generator active power, primary
Wind rate of discharge, First air wind-warm syndrome, Secondary Air wind-warm syndrome, Secondary Air inlet flow rate, superheater attemperator inlet flow rate, to flow
Amount, main steam flow, total blast volume, to oxygen amount, coal-supplying amount, secondary air register position feedback.
Beneficial effects of the present invention：
The present invention proposes a kind of coal-fired boiler combustion efficiency On-line Measuring Method, and this method can be realized according to correlated variables
High accuracy data driving modeling obtains real-time boiler combustion efficiency, disclosure satisfy that production requirement；It is applied widely, it is applicable to not
With the vector expression of data source, there is good adaptability；Can easily with other link shared informations, convenient for for other rings
The operation of section provides reference information.
Description of the drawings
Fig. 1 is the flow chart of coal-fired boiler combustion efficiency On-line Measuring Method in the specific embodiment of the invention；
Fig. 2 be in the specific embodiment of the invention using differential evolution algorithm to the LS-SVM measurement models of all kinds of operating modes into
The process flow diagram flow chart of row optimization；
Fig. 3 is the boiler combustion efficiency obtained in the specific embodiment of the invention using DE-LSSVM model modelings；
Fig. 4 is the boiler combustion efficiency obtained in the specific embodiment of the invention using DE-LSSVM model measurements.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, in present embodiment, the hardware environment of operation：PC machine one, CPU：2.50GHz RAM：2.00GB software loop
Border：MATLAB R2014a, operating platform：Windows XP.
The present invention proposes a kind of coal-fired boiler combustion efficiency On-line Measuring Method, as shown in Figure 1, including the following steps：
Step 1：The procedure parameter of boiler for producing process is obtained by SIS in Thermal Power PlantQ, and according to mechanism
Model calculates corresponding moment boiler combustion efficiency, obtains the data acquisition system DATA={ X of boiler for producing processk, Tk| k=1 ...,
K }, wherein, Xk∈RnFor the procedure parameter in k-th of sample, TkFor the boiler combustion efficiency of k-th of sample, K is data acquisition system
Middle sample size, n are procedure parameter dimension.
In present embodiment, the procedure parameter of 93 initial boiler for producing processes of use includes：Province's coal of per time instance
Device feed temperature (3 measurement points), superheater wall temperature (4 measurement points), burner hearth flue gas pressures (17 measurement points), main steam pressure
Power (3 measurement points), main steam temperature (4 measurement points), reheat steam turbine set, reheater steam pressure (5 measurement points), reheating
Device vapor (steam) temperature (4 measurement points), chamber flue gas temperature (6 measurement points), high-pressure feed water temperature, high-pressure feed water pressure, overheat
Device attemperator vapor (steam) temperature (8 measurement points), generator active power, First air rate of discharge (4 measurement points), First air wind
Warm (6 measurement points), Secondary Air wind-warm syndrome (6 measurement points), Secondary Air inlet flow rate (2 measurement points), superheater attemperator enter
Mouthful flow (4 measurement points), feedwater flow, main steam flow, total blast volume, to oxygen amount, coal-supplying amount, secondary air register position feedback (8
A measurement point), data acquisition system details is as shown in table 1.
In present embodiment, the data acquisition system DATA={ X of boiler for producing processk, Tk| k=1 ..., 807 }, data acquisition system
Middle sample size K=807, procedure parameter dimension n=93.
The data acquisition system details of 1 boiler for producing process of table
| Input dimension | Export dimension | Sample interval | Number of training | Test sample number |
| 93 | 1 | 1min | 486 | 321 |
Step 2：The procedure parameter of the data acquisition system of boiler for producing process is standardized using transfer function, is obtained
Data acquisition system SDATA={ S after to standardizationk, Tk| k=1 ..., K }, wherein, Sk∈RnFor the standardization in k-th of sample
Procedure parameter.
In present embodiment, it is described using transfer function to the procedure parameter of the data acquisition system of boiler for producing process into rower
Shown in the calculation formula such as formula (1) of standardization processing：
Step 3：The importance of the procedure parameter after standardization is determined using Boosted tree methods, extraction importance is big
In the procedure parameter of importance threshold gamma, the standardisation process parameter sets CDATA={ C after feature extraction are obtainedk, Tk| k=
1 ..., K }, wherein,The standardisation process parameter being characterized in k-th of sample after choosing, ncAfter being characterized extraction
Standardisation process parameter dimension.
In present embodiment, importance threshold gamma=0.1 determines the process after standardization using Boosted tree methods
The importance of parameter obtains the standardisation process parameter sets after feature extraction, as shown in table 2, the standardization after feature extraction
The dimension n of procedure parameterc=16.
Standardisation process parameter after 2 feature extraction of table
Step 4：Operating mode is carried out to the standardisation process parameter sets CDATA after feature extraction using K- neighbors grader
Classification, obtains all kinds of floor data collection LDATAi={ Lp(i), Tp(i)| p (i)=1 ..., P (i) }, and by all kinds of floor data collection
LDATAiIt is divided into training dataset xLDATAi={ Lh(i), Th(i)| h (i)=1 ..., H (i) } and test data set cLDATAi
={ Le(i), Te(i)| e (i)=1 ..., E (i) }；
Wherein, i=1,2 ..., 6,For the procedure parameter in i-th p-th of sample of class operating mode, Tp(i)For the i-th class
Boiler combustion efficiency in p-th of sample of operating mode, P (i) are the i-th class floor data set sample size, and h (i) is the i-th class operating mode
H-th of sample number that training data is concentrated, H (i) are the i-th class operating mode training data set sample size, and e (i) is the i-th class work
E-th of sample number that condition test data is concentrated, E (i) are the i-th class working condition measurement data acquisition system sample size；For
Training data concentrates the procedure parameter in i-th h-th of sample of class operating mode, Th(i)For the i-th class operating mode h in training set data set
Boiler combustion efficiency in a sample,For the process ginseng in i-th e-th of sample of class operating mode in test set data acquisition system
Number, Te(i)For the boiler combustion efficiency in i-th e-th of sample of class operating mode in test set data acquisition system.
In present embodiment, the standardisation process parameter sets after feature extraction are classified to obtain I=6 classes, it is all kinds of
Operating mode training dataset and test data set are as shown in table 3,
3 all kinds of operating mode training datasets of table and test data set
Step 5：For all kinds of floor data collection：By all kinds of operating mode training dataset xLDATAiAs input, establish all kinds of
The LS-SVM measurement models of operating mode optimize the LS-SVM measurement models of all kinds of operating modes using differential evolution algorithm, use
Test data set cLDATAiThe LS-SVM measurement models of optimization are tested, obtain the pot of all kinds of operating modes after final optimization pass
The LS-SVM measurement models of stove efficiency of combustion.
In present embodiment, by taking the 6th class operating mode as an example, detailed process is as shown in Figure 2.
A：Initialize differential evolution algorithm (DE) parameter.
The differential evolution algorithm parameter, including：Group size Nα=50, individual dimension D=2, greatest iteration algebraically G=
500, mutagenic factor F=0.8, crossover probability CR=0.7, the differential evolution algorithm population L of initializationα, 0, wherein, α=1,
2 ..., 50.
In present embodiment, the α individual of differential evolution algorithm population of initialization is
J-th of component of the α individual of differential evolution algorithm population of initializationCalculation formula such as formula (2) shown in：
Wherein, j=1,2,To specify search for space lower threshold,To refer to
Determine search space upper limit threshold, rand is the random number in [0,1] section.
B：LS-SVM parameter values are obtained according to individual information each in population, obtain NαGroup LS-SVM parameter values.
In present embodiment, LS-SVM parameter values specifically include the width cs of penalty factor and radial basis function2。
C：Using radial basis function as LS-SVM kernel functions, for the corresponding LS-SVM parameter values of individual each in population with
And the 6th class operating mode training dataset establish LS-SVM measurement models, training obtain 50 LS-SVM measurement models.
Shown in the LS-SVM models such as formula (3) of the 6th class operating mode：
Wherein, h (6)=1,2 ..., H (6), H (6) are for the 6th class operating mode training data concentration number of training mesh value
141, L(6)The new samples data of calculating boiler efficiency are needed for the 6th class operating mode,It needs to calculate boiler combustion for corresponding input
The sample data L of efficiency(6)LS-SVM measurement model output valves, ah(6)、b(6)LS-SVM measurement models for the 6th class operating mode
Parameter, Lh(6)Training data for the 6th class operating mode concentrates the procedure parameter of h-th of sample, K (L(6), Lh(6)) measured for LS-SVM
The kernel function of model.
In present embodiment, the kernel function K (L of the LS-SVM measurement models of the 6th class operating mode(6), Lh(6)) such as formula (4) institute
Show：
Wherein, σ(6) 2The width of LS-SVM kernel functions for the 6th class operating mode.
D：By the LS-SVM moulds of the 6th class operating mode that each individual is established in the test data input population of the 6th class operating mode
Type calculates the root-mean-square error value ε of the LS-SVM models of the 6th class operating mode that each individual is established in populationα, i.e., it is every in population
The fitness function value f of individualα=εα。
The root-mean-square error value ε of the LS-SVM models of the 6th class operating mode that each individual is established in the populationαCalculating
Shown in formula such as formula (5)：
Wherein, e (6) is e-th of sample number in the 6th class working condition measurement data set；E (6) is the 6th class working condition measurement
Data set sample number magnitude is 92；For the 6th class working condition measurement being calculated using the corresponding measurement model of the α individual
The LS-SVM measurement model output valves of the procedure parameter in e-th of sample in data set, Te(6)For the 6th class working condition measurement number
The boiler combustion efficiency actual value being calculated according to the procedure parameter correspondence in e-th of sample of concentration.
E：Judge whether current iteration number g reaches greatest iteration algebraically 500, if so, iteration terminates, obtain optimal
LS-SVM parameters and model parameter ah(6)、b(6), obtain the LS- of the boiler combustion efficiency of the 6th class operating mode after final optimization pass
SVM measurement models perform step 6；Otherwise, F is performed；
F：The g times iteration population is updated, enables iterative algebra g=g+1, returns to B.
F-1：For the α individual L of current iterationα, g, randomly select three individuals in current populationWithIt willWithDifference variation after with individualIt is synthesized into row vector, obtains the variation individual V of the g times iterationα, g,
Wherein, z1, z2, z3∈ [1,50].
It, will in present embodimentWithDifference variation after with individualIt is synthesized into row vector, obtains the g times repeatedly
The variation individual V in generationα, gCalculation formula such as formula (6) shown in：
F-2：By the variation individual V of the g times iterationα, gWith the α individual L of the g times iterationα, gCrossover operation is carried out, it is raw
Into the new individual U of the g times iterationα, g。
In present embodiment, j-th of component of the new individual of the g times iteration is generatedFormula such as formula (7) shown in：
Wherein, randjIt is the random number in [0,1] section, randnαThe random integers of ∈ [1,2].
F-3：Determine the new individual U of the g times iterationα, gWith the α individual L of the g times iterationα, gFitness function
Value, using the small individual of fitness function value as the g+1 times iteration population at individual Lα, g+1, as next-generation individual.
In present embodiment, the new individual U of the g+1 times iteration is determined by formula (5)α, g+1With the α of the g times iteration
Individual Lα, gFitness function value.
The g+1 times iteration population at individual Lα, g+1Calculation formula such as formula (8) shown in：
Wherein, f (*) is corresponding individual adaptation degree functional value.
F-4：Iterative algebra g=g+1 is enabled, returns to B.
Step 6：Preserve the LS-SVM measurement models of the boiler combustion efficiency of all kinds of operating modes after optimization.
Step 7：The on-line measurement value of the procedure parameter of boiler for producing process is read in real time, is fired using the boiler of all kinds of operating modes
The LS-SVM measurement models for burning efficiency measure coal-fired boiler combustion efficiency.
In present embodiment, sample data example is as shown in table 4.
4 sample data example of table
Step 7-1：The on-line measurement value of the procedure parameter of boiler for producing process is read in real time, using transfer function to boiler
The procedure parameter of production process is standardized, the procedure parameter C after being standardizedo, sample data example such as 4 institute of table
Show.
Step 7-2：According to the procedure parameter C after standardizationoSorted out with the cluster centre distance of all kinds of operating modes, such as table
It shown in 5, inputs in the LS-SVM measurement models of the boiler combustion efficiency after the optimization for determining operating mode classification, obtains boiler combustion effect
The on-line measurement value of rate.
In present embodiment, with sample data example.The cluster centre of procedure parameter value and all kinds of operating modes after standardization
Distance is sorted out, according to majority vote method, the LS- of the boiler combustion efficiency after the final optimization for determining input third class operating mode
In SVM measurement models, the on-line measurement value for obtaining boiler combustion efficiency is 85.8810%, and mechanism model calculates corresponding moment pot
Stove efficiency of combustion is 86.0010%, error amount 0.1196%.
Procedure parameter and the cluster centre distance of all kinds of operating modes after the standardization of table 5
Using coal-fired boiler combustion efficiency On-line Measuring Method (DE-LSSVM) modeling proposed by the invention and measure mistake
The result that poor statistical analysis technique obtains as shown in table 6 and table 7, is fired with the boiler that the modeling and measurement of DE-LSSVM models obtain
Burn efficiency as shown in Figure 3 and Figure 4.
6 boiler combustion efficiency modeling result statistical analysis of table
7 boiler combustion efficiency model measurement result statistical analysis of table
As seen from Table 6, occur when modeling maximum square error is the 6th class operating mode DE-LSSVM model modelings
0.2968%, it models when maximum average relative error is the 6th class operating mode DE-LSSVM model modelings and occurs 0.0345%；From table 7
In find out occur 1.8525% when maximum square error is the 6th class operating mode DE-LSSVM model measurements during measurement；It measures most
0.0474% occurred when average relative error is the 6th class operating mode DE-LSSVM model measurements greatly.It is modeled in actual motion
Process off-line carries out, and the calculating time is time of measuring, and in an experiment, every group of data average calculation times are 1.719ms.It is calculating
Two aspects of time and measurement accuracy, institute's extracting method of the present invention can better meet production needs.
Claims (5)
1. a kind of coal-fired boiler combustion efficiency On-line Measuring Method, which is characterized in that include the following steps：
Step 1：The procedure parameter of boiler for producing process is obtained by SIS in Thermal Power PlantQ, and according to mechanism model
Corresponding moment boiler combustion efficiency is calculated, obtains the data acquisition system DATA={ X of boiler for producing processk, Tk| k=1 ..., K },
In, Xk∈RnFor the procedure parameter in k-th of sample, TkFor the boiler combustion efficiency of k-th of sample, K is sample in data acquisition system
Quantity, n are procedure parameter dimension；
Step 2：The procedure parameter of the data acquisition system of boiler for producing process is standardized using transfer function, is marked
Data acquisition system SDATA={ S after standardizationk, Tk| k=1 ..., K }, wherein, Sk∈RnFor the standardisation process in k-th of sample
Parameter；
Step 3：The importance of the procedure parameter after standardization is determined using Boosted tree methods, extraction importance is more than weight
The procedure parameter of the property wanted threshold gamma obtains the standardisation process parameter sets CDATA={ C after feature extractionk, Tk| k=1 ...,
K }, wherein,The standardisation process parameter being characterized in k-th of sample after choosing, ncThe standard being characterized after extraction
Change the dimension of procedure parameter；
Step 4：Operating mode point is carried out to the standardisation process parameter sets CDATA after feature extraction using K- neighbors grader
Class obtains all kinds of floor data collection LDATAi={ Lp(i), Tp(i)| p (i)=1 ..., P (i) }, and by all kinds of floor data collection
LDATAiIt is divided into training dataset xLDATAi={ Lh(i), Th(i)| h (i)=1 ..., H (i) } and test data set cLDATAi
={ Le(i), Te(i)| e (i)=1 ..., E (i) }；
Wherein, i=1,2 ..., I, I be operating mode quantity,For the procedure parameter in i-th p-th of sample of class operating mode,
Tp(i)For the boiler combustion efficiency in i-th p-th of sample of class operating mode, P (i) is the i-th class floor data set sample size, h (i)
For the i-th class operating mode training data concentrate h-th of sample number, H (i) be the i-th class operating mode training data set sample size, e
(i) it is e-th of sample number in the i-th class working condition measurement data set, E (i) is the i-th class working condition measurement data acquisition system sample number
Amount；The procedure parameter in i-th h-th of sample of class operating mode, T are concentrated for training datah(i)I-th is concentrated for training data
Boiler combustion efficiency in h-th of sample of class operating mode,It is concentrated in i-th e-th of sample of class operating mode for test data
Procedure parameter, Te(i)The boiler combustion efficiency in i-th e-th of sample of class operating mode is concentrated for test data；
Step 5：For all kinds of floor data collection：By all kinds of operating mode training dataset xLDATAiAs input, all kinds of operating modes are established
LS-SVM measurement models, the LS-SVM measurement models of all kinds of operating modes are optimized using differential evolution algorithm, using test
Data set cLDATAiThe LS-SVM measurement models of optimization are tested, obtain the boiler combustion of all kinds of operating modes after final optimization pass
Burn the LS-SVM measurement models of efficiency；
Step 6：Preserve the LS-SVM measurement models of the boiler combustion efficiency of all kinds of operating modes after optimization；
Step 7：The on-line measurement value of the procedure parameter of boiler for producing process is read in real time, is imitated using the boiler combustion of all kinds of operating modes
The LS-SVM measurement models of rate measure coal-fired boiler combustion efficiency；
Step 7-1：The on-line measurement value of the procedure parameter of boiler for producing process is read in real time, using transfer function to boiler for producing
The procedure parameter of process is standardized, the procedure parameter after being standardized
Step 7-2：According to the procedure parameter after standardizationSorted out with the cluster centre distance of all kinds of operating modes, input determines
In the LS-SVM measurement models of boiler combustion efficiency after the optimization of operating mode classification, the on-line measurement of boiler combustion efficiency is obtained
Value.
2. coal-fired boiler combustion efficiency On-line Measuring Method according to claim 1, which is characterized in that described using conversion
The calculation formula that the procedure parameter of the data acquisition system of function pair boiler for producing process is standardized is as follows：
3. coal-fired boiler combustion efficiency On-line Measuring Method according to claim 1, which is characterized in that the boiler for producing
The procedure parameter of process includes：Economizer feed temperature, superheater wall temperature, burner hearth flue gas pressures, the main steam pressure of per time instance
Power, main steam temperature, reheat steam turbine set, reheater steam pressure, reheater steam temperature, chamber flue gas temperature, high-pressure feed water
Temperature, high-pressure feed water pressure, superheater attemperator vapor (steam) temperature, generator active power, First air rate of discharge, First air wind
Temperature, Secondary Air wind-warm syndrome, Secondary Air inlet flow rate, superheater attemperator inlet flow rate, feedwater flow, main steam flow, total blast volume,
To oxygen amount, coal-supplying amount, secondary air register position feedback.
4. coal-fired boiler combustion efficiency On-line Measuring Method according to claim 1, which is characterized in that described for all kinds of
Floor data collection：By all kinds of operating mode training dataset xLDATAiAs input, the LS-SVM measurement models of all kinds of operating modes are established,
The LS-SVM measurement models of all kinds of operating modes are optimized using differential evolution algorithm, using test data set cLDATAiTo excellent
The LS-SVM measurement models of change are tested, and the LS-SVM for obtaining the boiler combustion efficiency of all kinds of operating modes after final optimization pass is measured
Model by taking the i-th class operating mode as an example, is performed according to following steps：
A：Initialize differential evolution algorithm parameter；
The differential evolution algorithm parameter, including：Group size Nα, individual dimension D, greatest iteration algebraically G, mutagenic factor F are handed over
Pitch probability CR ∈ [0,1], the differential evolution algorithm population L of initializationα, 0, wherein, α=1,2 ... Nα；
B：LS-SVM parameter values are obtained according to individual information each in population, obtain NαGroup LS-SVM parameter values；
C：Using radial basis function as LS-SVM kernel functions, for the corresponding LS-SVM parameter values of individual each in population and the
The LS-SVM measurement models that the training dataset of i class operating modes is established, training obtain NαA LS-SVM measurement models；
The LS-SVM models of the i-th class operating mode are as follows：
Wherein, h (i)=1,2 ..., H (i), H (i) are that the training data of the i-th class operating mode concentrates number of training mesh, L(i)It is
I class operating modes need to calculate the new samples data of boiler combustion efficiency,Data L for the i-th class operating mode of corresponding input(i)LS-
SVM measurement model output valves, ah(i)、b(i)For the LS-SVM measurement model parameters of the i-th class operating mode, Lh(i)Instruction for the i-th class operating mode
Practice the procedure parameter of h-th of training sample in data set, K (L(i), Lh(i)) for the i-th class operating mode LS-SVM measurement models core
Function；
Kernel function K (the L of the LS-SVM measurement models of the i-th class operating mode(i), Lh(i)) as follows：
Wherein, σ(i) 2The width of LS-SVM kernel functions for the i-th class operating mode；
D：By the LS-SVM models of the i-th class operating mode that each individual is established in the test data input population of the i-th class operating mode, calculate
The root-mean-square error value ε of the LS-SVM models of the i-th class operating mode that each individual is established in populationα, i.e., each individual in population
Fitness function value fα=εα；
The root-mean-square error value ε of the LS-SVM models of the i-th class operating mode that each individual is established in the populationαCalculation formula such as
Shown in lower：
Wherein,For using the e in the α individual the i-th class working condition measurement data set for corresponding to measurement model and being calculated
The LS-SVM measurement model output valves of procedure parameter in a sample；
E：Judge whether current iteration number g reaches greatest iteration algebraically G, if so, iteration terminates, obtain optimal L S-SVM ginsengs
Number and model parameter ah(i)、b(i), obtain the LS-SVM measurement moulds of the boiler combustion efficiency of the i-th class operating mode after final optimization pass
Type performs step 6, otherwise, performs F；
F：The g times iteration population is updated, enables iterative algebra g=g+1, returns to B.
5. coal-fired boiler combustion efficiency On-line Measuring Method according to claim 4, which is characterized in that the F include with
Lower step：
F-1：For the α individual L of current iterationα, g, randomly select three individuals in current populationWith
It willWithDifference variation after with individualIt is synthesized into row vector, obtains the variation individual V of the g times iterationα, g, wherein,
z1, z2, z3∈ [1, Nα]；
It is described to incite somebody to actionWithDifference variation after with individualIt is synthesized into row vector, obtains the variation individual of the g times iteration
Vα, gCalculation formula it is as follows：
F-2：By the variation individual V of the g times iterationα, gWith the α individual L of the g times iterationα, gCrossover operation is carried out, generates g
The new individual U of secondary iterationα, g；
J-th of component of the new individual of described the g times iteration of generationFormula it is as follows：
Wherein, j=1 ..., D, randjIt is the random number in [0,1] section, randnαThe random integers of ∈ [1, D]；
F-3：Determine the new individual U of the g times iterationα, gWith the α individual L of the g times iterationα, gFitness function value, will
The small individual of fitness function value is as the g+1 times iteration population at individual Lα, g+1, as next-generation individual；
The g+1 times iteration population at individual Lα, g+1Calculation formula it is as follows：
Wherein, f (*) is corresponding individual adaptation degree functional value；
F-4：Iterative algebra g=g+1 is enabled, returns to B.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810107733.3A CN108182553B (en) | 2018-02-02 | 2018-02-02 | Coal-fired boiler combustion efficiency online measurement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810107733.3A CN108182553B (en) | 2018-02-02 | 2018-02-02 | Coal-fired boiler combustion efficiency online measurement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108182553A true CN108182553A (en) | 2018-06-19 |
| CN108182553B CN108182553B (en) | 2022-04-01 |
Family
ID=62552103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810107733.3A Active CN108182553B (en) | 2018-02-02 | 2018-02-02 | Coal-fired boiler combustion efficiency online measurement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108182553B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492319A (en) * | 2018-11-23 | 2019-03-19 | 东北电力大学 | A kind of power plant boiler flue gas oxygen content flexible measurement method |
| CN110017470A (en) * | 2019-02-27 | 2019-07-16 | 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 | Boiler combustion multiobjective optimization control method based on differential evolution algorithm |
| CN110532674A (en) * | 2019-08-27 | 2019-12-03 | 东北电力大学 | A kind of coal-fired power station boiler fire box temperature measurement method |
| CN113420461A (en) * | 2021-07-20 | 2021-09-21 | 山东恒拓科技发展有限公司 | Cement decomposing furnace online simulation system and establishing method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070250215A1 (en) * | 2006-04-25 | 2007-10-25 | Pegasus Technologies, Inc. | System for optimizing oxygen in a boiler |
| 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 |
| CN105605610A (en) * | 2016-01-13 | 2016-05-25 | 上海交通大学 | Boiler combustion optimization method based on particle swarm algorithm |
| 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 |
| CN106527176A (en) * | 2016-10-21 | 2017-03-22 | 哈尔滨理工大学 | MFOA (modified fruit fly optimization algorithm)-SVM (support vector machine)-based boiler thermal efficiency and NOX modeling method |
-
2018
- 2018-02-02 CN CN201810107733.3A patent/CN108182553B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070250215A1 (en) * | 2006-04-25 | 2007-10-25 | Pegasus Technologies, Inc. | System for optimizing oxygen in a boiler |
| US20110224830A1 (en) * | 2006-04-25 | 2011-09-15 | Pegasus Technologies, Inc. | Control system for operation of a fossil fuel power generating unit |
| 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 |
| CN105605610A (en) * | 2016-01-13 | 2016-05-25 | 上海交通大学 | Boiler combustion optimization method based on particle swarm algorithm |
| 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 |
| CN106527176A (en) * | 2016-10-21 | 2017-03-22 | 哈尔滨理工大学 | MFOA (modified fruit fly optimization algorithm)-SVM (support vector machine)-based boiler thermal efficiency and NOX modeling method |
Non-Patent Citations (5)
| Title |
|---|
| 赵文杰 等: "基于多LS-SVM集成模型的锅炉NO_x排放量建模", 《电子测量与仪器学报 》 * |
| 陈南锟: "基于最小二乘支持向量机的燃煤锅炉燃烧优化研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 陈涛: "基于DE-SVM非线性组合预测模型的研究", 《计算机工程与应用》 * |
| 顾燕萍 等: "基于最小二乘支持向量机的电站锅炉燃烧优化", 《中国电机工程学报》 * |
| 默一鸣: "特征选择 GBDT 特征重要度", 《HTTPS://BLOG.CSDN.NET/YIMINGSILENCE/ARTICLE/DETAILS/71713751百度快照》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492319A (en) * | 2018-11-23 | 2019-03-19 | 东北电力大学 | A kind of power plant boiler flue gas oxygen content flexible measurement method |
| CN109492319B (en) * | 2018-11-23 | 2022-08-12 | 东北电力大学 | Soft measurement method for oxygen content of boiler flue gas of thermal power plant |
| CN110017470A (en) * | 2019-02-27 | 2019-07-16 | 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 | Boiler combustion multiobjective optimization control method based on differential evolution algorithm |
| CN110532674A (en) * | 2019-08-27 | 2019-12-03 | 东北电力大学 | A kind of coal-fired power station boiler fire box temperature measurement method |
| CN110532674B (en) * | 2019-08-27 | 2022-08-12 | 东北电力大学 | Method for measuring temperature of boiler furnace of coal-fired power plant |
| CN113420461A (en) * | 2021-07-20 | 2021-09-21 | 山东恒拓科技发展有限公司 | Cement decomposing furnace online simulation system and establishing method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108182553B (en) | 2022-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106249728B (en) | A kind of thermal power generation unit on-line performance monitoring method based on characteristics of components | |
| CN108182553A (en) | A kind of coal-fired boiler combustion efficiency On-line Measuring Method | |
| CN106089328A (en) | Steam turbine pitch rating curve discrimination method based on DCS data mining | |
| CN115238597B (en) | Construction method of source network carbon-loaded emission model of park level comprehensive energy system | |
| CN105787211B (en) | For the Combined Cycle Heat Recovery Boiler pressure method of adjustment of combustion gas turbine deterioration | |
| CN102494714A (en) | Synchronous reckoning method of utility boiler efficiency and coal heat value as well as ash content and moisture content | |
| CN107796851A (en) | Blast furnace gas boiler as-fired coal gas calorific value and boiler thermal output on-line monitoring method | |
| CN104571022B (en) | Power consumption analysis model experimental systems and method based on coal consumption Yu controllable factor relationship | |
| CN113095591B (en) | Consumption difference analysis method for self-optimization of operation parameters of thermal power generating unit | |
| CN111881405B (en) | Real-time calculation method for content of combustible in fly ash of coal-fired boiler | |
| CN106936627A (en) | A kind of thermal power generating equipment performance monitoring method based on big data analysis mining | |
| CN105259758A (en) | Thermal power unit operating parameter intelligent online optimization method based on massive historical data | |
| CN110207094B (en) | IQGA-SVR boiler heating surface contamination characteristic identification method based on principal component analysis | |
| CN104122291B (en) | Ultra supercritical coal-fired unit water wall is to the real-time discrimination method of refrigerant heat transfer speed | |
| CN106960113A (en) | A kind of divisions of responsibility method on single shaft combined cycle generating unit performances acceptance Zhong Ji Dao Yulu islands | |
| CN103699786A (en) | Energy consumption difference analysis method for load varying of ultra-supercritical generating unit of thermal power plant | |
| CN106096310A (en) | A kind of steam extraction heat supply unit is for thermal condition performance calculation method | |
| CN109709911B (en) | On-line measuring method and system for leakage of circulating working medium of thermal power generating unit | |
| CN104483152B (en) | The heat consumption rate assay method of non-reheat backheat combined-circulation unit | |
| Eke et al. | Exergy and Environmental Assessment of a Steam Power Plant: A Case Study of Nigeria | |
| CN106289754B (en) | A kind of fired power generating unit component capabilities variation determination method based on Statistical Control Technique | |
| CN110298502A (en) | Based on the boiler optimum oxygen calculation method that efficiency is optimal | |
| CN113468732A (en) | System and method for determining production cost for heat supply of steam extraction heat supply unit | |
| CN103886370B (en) | It is suitable for the power boiler burning performance neural network model of different coal pulverizer combination | |
| CN110273715A (en) | A kind of Turbo-generator Set remodeling method based on No. 0 hydrophobic mode of high-pressure heater |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |