CN105929109B - Flying marking measuring method - Google Patents
Flying marking measuring method Download PDFInfo
- Publication number
- CN105929109B CN105929109B CN201610239213.9A CN201610239213A CN105929109B CN 105929109 B CN105929109 B CN 105929109B CN 201610239213 A CN201610239213 A CN 201610239213A CN 105929109 B CN105929109 B CN 105929109B
- Authority
- CN
- China
- Prior art keywords
- sample
- historical data
- sample set
- auxiliary variable
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 27
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 27
- 239000003500 flue dust Substances 0.000 claims abstract description 23
- 239000003245 coal Substances 0.000 claims description 8
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 239000007789 gas Substances 0.000 claims description 4
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 238000004821 distillation Methods 0.000 claims description 3
- 239000003546 flue gas Substances 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 3
- 239000002956 ash Substances 0.000 description 26
- 238000001354 calcination Methods 0.000 description 18
- 239000013598 vector Substances 0.000 description 14
- 239000011159 matrix material Substances 0.000 description 12
- 238000005259 measurement Methods 0.000 description 11
- 239000000428 dust Substances 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 229910052698 phosphorus Inorganic materials 0.000 description 4
- 239000011574 phosphorus Substances 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000003556 assay Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000010881 fly ash Substances 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000010338 mechanical breakdown Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000010977 unit operation Methods 0.000 description 2
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003028 elevating effect Effects 0.000 description 1
- 230000019439 energy homeostasis Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 239000002075 main ingredient Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012628 principal component regression Methods 0.000 description 1
- 238000010926 purge Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000001073 sample cooling Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000005245 sintering Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000010025 steaming Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 208000016261 weight loss Diseases 0.000 description 1
- 230000004580 weight loss Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0091—Powders
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Non-Biological Materials By The Use Of Chemical Means (AREA)
Abstract
The present invention relates to thermal control process field, discloses a kind of flying marking measuring method, and this method includes：Historical data sample set is established according to the historical data values of unburned carbon in flue dust and corresponding to the auxiliary variable value of the historical data values；Selection and first sample collection similar in current working in the historical data sample set；Weight coefficient of auxiliary variable value and flying marking the value fitting concentrated according to the first sample for auxiliary variable；And the unburned carbon in flue dust of the current working is calculated according to the auxiliary variable value of current working and the weight coefficient.
Description
Technical field
The present invention relates to thermal control process field, in particular it relates to a kind of flying marking measuring method.
Background technology
In the actual production process of coal-burning power plant, technology or economically due to, many important parameters and
Economic parameters can not use conventional sensor direct measurement, have a strong impact on coal-burning power plant's economical operation.Unburned carbon in flue dust is firepower
One important indicator of power plant coal-fired boiler combustion efficiency, it reflects the size of coal-fired incomplete combustion loss.Mesh
Before, unburned carbon in flue dust online test method has calcination loss method and microwave detection method.
Calcination method weight-loss method e measurement technology is China electric power industry standard《Flying dust and clinker can right thing assay methods》And《Coal
Industry Analysis Method》In correlation technique, when the ash sample containing uncompleted burned carbon at a high temperature of regulation after calcination, due to ash
The carbon remained in sample afterburnt is made the quality of ash sample loss occur, and the loss on ignition by the use of ash sample calculates ash sample as foundation
In phosphorus content,
The quality (%) of phosphorus content=[ash sample adds ash sample after quality (g)-calcination of crucible to add the quality of crucible before calcination
(g)]/[quality (g) of crucible before ash sample adds quality (g)-receipts of crucible grey before calcination].
Fig. 1 shows the apparatus structure block diagram using calcination loss method measurement unburned carbon in flue dust.As shown in figure 1, calcination is lost
The main working process of weight method is to be collected into the ash sample in flue in the crucible of measuring unit by vibrator and sampler, by
Crucible is positioned over rotary-tray by elevating mechanism, then is sent into the crucible equipped with ash sample by the executing agency inside measuring unit and is burnt
Burn device (e.g., furnace heater) carry out high temperature sintering, electronic balance measure in real time receive ash before, receive ash after and calcination after weight
Signal, control unit are calculated the weight signal received, obtain the phosphorus content of flying dust and in the display screen of control unit
On shown, wherein can use hand control box control control unit be calculated or be shown.Ash sample after calcination passes through
In ash exhauster and vacuum generator the discharge air-returen flue of system.
But calcination loss method there are problems that in applying at the scene it is more following：
(1) problem of sampling.Device sample rate is slow, so sample time is grown, ash sample cooling is very fast, easily stifled ash.
(2) micro-wave oven heating problems.Laboratory heating-up temperature (power industry standard can not be reached first《Flying dust and clinker
Can right thing assay method》Middle proposition should carry out calcination at 810 ± 10 DEG C, and slow ash wants 1 hour, and fast ash wants 30 minutes), calcination temperature
Degree, time can not reach requirement, and because micro-wave heating characteristic and crucible contain the minimum requirements restriction of ash so that ash sample thickness
Go beyond the scope, thus can only be to the complete calcination in ash sample outer surface in crucible, and inside is former ash sample.Secondly, it is impossible to by code
Moisture (because of temperature difference changing factor in by flue, flying dust is it sometimes appear that dew condensation phenomenon) is first dried, volatile quantity is surveyed in calcination, so
There is moisture changing factor in weightless delta data.
(3) weigh problem.Electronic balance is arranged in in-site measurement cabinet and weighed in real time, and boiler operatiopn causes electronics day
It is flat to vibrate always, normal measurement accuracy can not be ensured.
(4) mechanical problem.Such device such as typically has extremely complex mechanical device and motor, laughed somebody to scorn at the rotatable parts, makes
Often occur the various mechanical breakdowns such as crucible broken, mechanical breakdown, electrical fault and crucible station mistake in, due to equipment therefore
Barrier can be related to complicated mechanical device, Electrical connections, gas circuit, grey road system, even if there is special messenger's maintenance, it is also difficult to solve
The problem of intricate.
(5) time lag problem.Device sample rate is slow, and needs machine operation, weighs, calcination so that detection cycle
Time is grown.
So the on-line measuring device of calcination loss method has in use at the scene, detection lag time is long, ash sample can not
Grill thoroughly, weigh the defects of inaccurate, stifled grey, failure rate of machinery is high, maintenance requirement is high, hardly possible is safeguarded.
The principle of microwave detection method is：Because fly ash combustible material Main Ingredients and Appearance is the dielectric constant of carbon and carbon, microwave test
Unit can utilize the microwave signal of fixed frequency emitted energy homeostasis, and the content of combustible is higher in flying dust, absorb microwave energy
Effect it is stronger.
The system of microwave detection method can use unpowered fly ash sampler, and the ash sample in flue is collected into microwave automatically surveys
In the measurement pipe that trial assembly is put, the height of grey position is collected by grey level controller automatic discrimination.When being collected into enough ash samples, system
Microwave resonance measurement is carried out to unburned carbon in flue dust.Control device opens the ash that magnetic valve access compressed air purging has been analyzed
Sample, according to program setting or setting manually, flying dust sampled pipeline can blow back flue or be sent into the grey container of receipts automatically, so as to
Chemically examined in chemical analysis.
Because the frequency characteristic of different material is different, material composition is complicated in flying dust, and it is mainly mineral during coal type change
Qualitative change prevents microwave detection method in coal type change from detecting unburned carbon in flue dust change.
The content of the invention
It is an object of the invention to provide a kind of flying marking measuring method, for realizing the online survey of unburned carbon in flue dust
Amount, improve the security and economy of unit operation.
To achieve these goals, the present invention provides a kind of flying marking measuring method, and this method includes：According to flying dust
The historical data values of phosphorus content and auxiliary variable value corresponding to the historical data values establish historical data sample set；Institute
State selection and first sample collection similar in current working in historical data sample set；The auxiliary concentrated according to the first sample
Variate-value and the fitting of flying marking value are directed to the weight coefficient of auxiliary variable；And according to the auxiliary variable value of current working and
The weight coefficient calculates the unburned carbon in flue dust of the current working.
Preferably, the selection in the historical data sample set and first sample Ji Bao similar in current working
Include：Calculate the auxiliary variable value of the current working and the auxiliary variable value of each sample in the historical data sample set
Coefficient correlation；And the sample chosen corresponding to the coefficient correlation for being more than first threshold forms the first sample collection.
Preferably, the coefficient correlation is calculated using Pearson product-moment correlation coefficient method.
Preferably, methods described also includes：Principal component analysis is carried out to the first sample collection to obtain comprising main auxiliary
Help the second sample set of variable；And the weight coefficient is fitted according to second sample set.
Preferably, using weight coefficient described in least square fitting.
Preferably, the auxiliary variable includes：The coal-supplying amount of each feeder, flue gas oxygen content, exhaust gas temperature, main steam
Pressure, main distillation amount, main steam temperature, total blast volume, economizer inlet flow rate value, economizer inlet pressure, economizer exit pressure
Power, generation load, coal characteristic, First air gross pressure, secondary air register aperture, after-flame throttle opening, Secondary Air stagnation pressure and burner hearth
Differential pressure, air preheater outlet temperature, burner pivot angle.
Preferably, methods described also includes：Update the historical data sample set.
Preferably, the renewal historical data sample set includes：Determined in the historical sample set multiple
Center of a sample；The distance of each is more than the situation of second predetermined value in emerging sample and the multiple center of a sample
Under, the emerging sample is added to the historical data sample set.
Preferably, the renewal historical data sample set further comprises：Using the emerging sample as
One new center of a sample is to update the multiple center of a sample；And between merging in multiple center of a sample after renewal
Distance be less than the 3rd threshold value Liang Ge center of a sample.
Preferably, the renewal historical data sample set further comprises：Multiple samples after the renewal
In the case that distance between in center is all higher than the 3rd threshold value, delete renewal after historical data sample set in institute
State each of multiple center of a sample apart from reckling.
Pass through above-mentioned technical proposal, the auxiliary variable of historical data sample set and current working based on unburned carbon in flue dust
Value calculates the unburned carbon in flue dust of current working, and scheme is simple and easy without complicated device, and can improve unit operation
Security and economy.
Other features and advantages of the present invention will be described in detail in subsequent specific embodiment part.
Brief description of the drawings
Accompanying drawing is for providing a further understanding of the present invention, and a part for constitution instruction, with following tool
Body embodiment is used to explain the present invention together, but is not construed as limiting the invention.In the accompanying drawings：
Fig. 1 shows the apparatus structure block diagram using calcination loss method measurement unburned carbon in flue dust；
Fig. 2 shows the flow chart of flying marking measuring method provided by the present invention in an embodiment；And
Fig. 3 shows the flow chart of renewal historical data sample set.
Embodiment
The embodiment of the present invention is described in detail below in conjunction with accompanying drawing.It should be appreciated that this place is retouched
The embodiment stated is merely to illustrate and explain the present invention, and is not intended to limit the invention.
Fig. 2 shows the flow chart of flying marking measuring method provided by the present invention in an embodiment.Such as Fig. 2 institutes
Show, the present invention provides a kind of flying marking measuring method, and this method includes：According to historical data values of unburned carbon in flue dust and right
The auxiliary variable value of historical data values described in Ying Yu establishes historical data sample set (step S10)；In the historical data sample
Selection and first sample collection (step S20) similar in current working in this set；The auxiliary concentrated according to the first sample becomes
Value and the fitting of flying marking value are directed to the weight coefficient (step S30) of auxiliary variable；And the auxiliary according to current working
Variate-value and the weight coefficient calculate the unburned carbon in flue dust (step S40) of the current working.
Flying marking measuring method provided by the present invention will specifically be introduced step by step below.
Step S10：According to the historical data values of unburned carbon in flue dust and the auxiliary variable value corresponding to the historical data values
Establish historical data sample set.
Wherein, relation be present between the multiple variables of unburned carbon in flue dust and scene, in order to reflect the more of extraction unburned carbon in flue dust
Aspect information, the auxiliary variable big with unburned carbon in flue dust correlation is chosen here.The auxiliary variable can include：Each feeder
Coal-supplying amount (assuming that there is five feeders, then should include feeder A coal-supplying amounts, feeder B coal-supplying amounts, feeder C to coal
Amount, feeder D coal-supplying amounts, feeder E coal-supplying amounts), flue gas oxygen content, exhaust gas temperature, main steam pressure, main distillation amount, main steaming
Stripping temperature, total blast volume, economizer inlet flow rate value, economizer inlet pressure, economizer exit pressure, generation load, ature of coal are special
Property, First air gross pressure, secondary air register aperture, after-flame throttle opening, Secondary Air stagnation pressure and burner hearth differential pressure, air preheater export
Temperature, burner pivot angle etc..In each sample in the historical sample set established comprising above-mentioned auxiliary variable value and
The data value of corresponding unburned carbon in flue dust.
Step S20：Selection and first sample collection similar in current working in the historical data sample set.
In this step, the auxiliary variable value of current working and each sample in historical data sample set can be calculated
The coefficient correlation of auxiliary variable value, coefficient correlation is higher, illustrates that the two correlation is higher, corresponding historical sample is more with working as
Preceding operating mode is close.Here Pearson product-moment correlation coefficient method can be used to calculate above-mentioned coefficient correlation.
If the auxiliary variable value of current working is expressed as X1=(x1, x2……xn), wherein x1, x2……xnRepresent current work
The value of different auxiliary variables in condition, the auxiliary variable value of historical sample is Y1=(y1, y2……yn), wherein y1, y2……ynTable
Show the value of different auxiliary variables in a certain historical sample, then Pearson product-moment correlation coefficient r calculation formula is：
In formula
SxxFor variable xiTo its averageSum of square of deviations, SyyFor variable yiTo its averageDeviation quadratic sum,
SxyFor xi、yiSum of square of deviations.R is known as individual event coefficient correlations of the vectorial X1 to Y1 (or vectorial Y1 is to X1), also referred to as
Coefficient correlation.
The span of correlation coefficient r is -1≤r≤1, and the absolute value of correlation coefficient r is between 1, vectorial X1 and Y1
Degree of correlation it is higher, the degree of correlation of the absolute value of correlation coefficient r between 0, vectorial X1 and Y1 is lower, is being calculated
The sample corresponding to the coefficient correlation more than first threshold is chosen in coefficient correlation out and forms above-mentioned first sample collection.This
In, first threshold can as the case may be depending on, do not make specific limitation.
Step 30：Auxiliary variable value and flying marking value fitting the adding for auxiliary variable concentrated according to first sample
Weight coefficient.Preferably, principal component analysis can be carried out for obtained first sample collection here to obtain comprising main auxiliary
Second sample set of variable, the main auxiliary variable value and the fitting of flying marking value in second sample set are for main
The weight coefficient of auxiliary variable.
Can use in one embodiment PCA the first sample collection that is obtained is carried out principal component analysis with
Obtain the second sample set.
PCA is a kind of statistical method of dimensionality reduction, and it is by means of an orthogonal transformation, by its component correlation
Former random vector changes into the incoherent new random vector of its component, and this is shown as on algebraically by the covariance of former random vector
Battle array is transformed into diagonal form battle array, is geometrically showing as, by former coordinate system transformation Cheng Xin orthogonal coordinate system, being allowed to point to sample point
The p orthogonal direction most opened is spread, dimension-reduction treatment then is carried out to multidimensional variable system, makes it to turn with a higher precision
Change low-dimensional variable system into, then by constructing appropriate cost function, low-dimensional system is further changed into unidimensional system.
Assuming that X is n × m data matrix, each of which row correspond to a variable, and first is corresponded to per a line
A sample in sample set.Matrix X can be decomposed into the apposition sum of m vector, i.e.,
In formula, ti∈RnIt is referred to as score vector, pi∈RmReferred to as load vector.X score vector is also referred to as X pivot.
It can be write as lower column matrix formation
X=TPT (3)
Wherein T=(t1,t2,…,tn) it is referred to as score matrix, P=(p1,p2,…,pm) it is referred to as matrix of loadings.
It is between each score vector and orthogonal, i.e., for any i and j, as i ≠ j, meet titj=0.It is each negative
It is between lotus vector and orthogonal, while the length of each load vector is 1, i.e.,
When having a certain degree of linearly related between the vector in matrix X, data matrix X change will be mainly reflected in
Foremost several loads vector direction on, projections of the data matrix X on rearmost several load vectors will very little,
They are mainly due to caused by measurement noise.It can thus say that matrix X is write as following formula after carrying out pivot decomposition
E is error matrix in formula, represents X in pk+1To pmDeng the change in load vector direction.Due to error matrix E master
If caused by measurement noise, E is neglected to the effect for often playing and removing measurement noise, without causing in data
The significantly sacrificing of useful information.Thus data X can be approximately represented as
In the formula that calculates (7) the carry out principal component analysis with regard to completing to be carried out for obtained first sample collection afterwards.
Because X preceding k master represents most changes in X data, therefore can be with X preceding k pivot come generation
Variable is originally inputted for those and carries out regression analysis, so just obtains following principal component regression model
In formula, matrix Y represents the second sample set after principal component analysis, B=(b1 b2 … bk)TMould is returned for pivot
Shape parameter.Calculated using least square method by following formula to obtain B
Then the model parameter θ of input variable is
Model parameter θ is calculated weight coefficient.Calculated weight coefficient is used to be multiplied by each weight coefficient
The auxiliary variable value can of corresponding current working calculates the unburned carbon in flue dust of current working.
Further, in order to reflect operating mode situation comprehensively, when there is new sample, it is necessary to update historical data sample collection
Close.L (l >=1) individual center of a sample is determined first in historical data sample set, is calculated in emerging sample and l sample
The distance of each in the heart, when each distance is all higher than threshold value δ, is then added to historical data sample collection by emerging sample
In conjunction, using the emerging sample as a new center of a sample, center of a sample's number is l+1.Calculate l+1 center of a sample
Distance each other, if the distance of two samples is less than threshold value σ, the Liang Ge center of a sample is merged.If two
The distance of individual sample is all higher than threshold value σ, calculates each sample and the distance of l+1 center of a sample in historical data base, reject away from
From a sample of minimum, so as to ensure that the sample number in historical data base keeps constant.
In actual use, unburned carbon in flue dust computational methods provided by the present invention can be programmed by supporting C language
PLC (controller of the S7 series of such as Siemens) is realized, is read by the form of Ethernet or hardwire
Enchashment field data (auxiliary variable value), and result of calculation is included in the monitor of operations staff.
The preferred embodiment of the present invention is described in detail above in association with accompanying drawing, still, the present invention is not limited to above-mentioned reality
The detail in mode is applied, in the range of the technology design of the present invention, a variety of letters can be carried out to technical scheme
Monotropic type, these simple variants belong to protection scope of the present invention.
It is further to note that each particular technique feature described in above-mentioned embodiment, in not lance
In the case of shield, can be combined by any suitable means, in order to avoid unnecessary repetition, the present invention to it is various can
The combination of energy no longer separately illustrates.
In addition, various embodiments of the present invention can be combined randomly, as long as it is without prejudice to originally
The thought of invention, it should equally be considered as content disclosed in this invention.
Claims (9)
1. a kind of flying marking measuring method, it is characterised in that this method includes：
Historical data is established according to the historical data values of unburned carbon in flue dust and corresponding to the auxiliary variable value of the historical data values
Sample set；
Selection and first sample collection similar in current working in the historical data sample set；
Principal component analysis is carried out to the first sample collection to obtain including the second sample set of main auxiliary variable；
Main auxiliary variable value and the fitting of flying marking value in second sample set are directed to the weighting of auxiliary variable
Coefficient；And
The unburned carbon in flue dust of the current working is calculated according to the auxiliary variable value of current working and the weight coefficient.
2. according to the method for claim 1, it is characterised in that described to choose and work as in the historical data sample set
First sample collection includes similar in preceding operating mode：
Calculate the auxiliary variable value and the auxiliary variable value of each sample in the historical data sample set of the current working
Coefficient correlation；And
Choose the sample corresponding to the coefficient correlation more than first threshold and form the first sample collection.
3. according to the method for claim 2, it is characterised in that the correlation is calculated using Pearson product-moment correlation coefficient method
Coefficient.
4. according to the method for claim 1, it is characterised in that use weight coefficient described in least square fitting.
5. according to the method for claim 1, it is characterised in that the auxiliary variable includes：The coal-supplying amount of each feeder,
Flue gas oxygen content, exhaust gas temperature, main steam pressure, main distillation amount, main steam temperature, total blast volume, economizer inlet flow rate value, province
Coal device inlet pressure, economizer exit pressure, generation load, coal characteristic, First air gross pressure, secondary air register aperture, after-flame
Throttle opening, Secondary Air stagnation pressure and burner hearth differential pressure, air preheater outlet temperature and burner pivot angle.
6. according to the method for claim 1, it is characterised in that methods described also includes：
Update the historical data sample set.
7. according to the method for claim 6, it is characterised in that the renewal historical data sample set includes：
Multiple center of a sample are determined in the historical sample set；
In the case that the distance of each is more than second predetermined value in emerging sample and the multiple center of a sample, by institute
State emerging sample and be added to the historical data sample set.
8. according to the method for claim 7, it is characterised in that the renewal historical data sample set is further wrapped
Include：
Using the emerging sample center of a sample new as one to update the multiple center of a sample；And
Distance between merging in multiple center of a sample after renewal is less than the Liang Ge center of a sample of the 3rd threshold value.
9. according to the method for claim 8, it is characterised in that the renewal historical data sample set is further wrapped
Include：
In the case that distance between in multiple center of a sample after the renewal is all higher than the 3rd threshold value, renewal is deleted
With each of the multiple center of a sample apart from reckling in historical data sample set afterwards.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610239213.9A CN105929109B (en) | 2016-04-18 | 2016-04-18 | Flying marking measuring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610239213.9A CN105929109B (en) | 2016-04-18 | 2016-04-18 | Flying marking measuring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105929109A CN105929109A (en) | 2016-09-07 |
| CN105929109B true CN105929109B (en) | 2018-02-23 |
Family
ID=56838284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610239213.9A Active CN105929109B (en) | 2016-04-18 | 2016-04-18 | Flying marking measuring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105929109B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529123B (en) * | 2016-10-10 | 2019-07-23 | 中国神华能源股份有限公司 | The measurement method and device of unburned carbon in flue dust |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN103413184A (en) * | 2013-08-05 | 2013-11-27 | 浙江大学 | Fly ash carbon content predicting system and method of circulating fluidized bedboiler |
| CN103729569A (en) * | 2014-01-20 | 2014-04-16 | 华北电力大学 | Soft measurement system for flue gas of power-station boiler on basis of LSSVM (Least Squares Support Vector Machine) and online updating |
| CN103728879A (en) * | 2014-01-20 | 2014-04-16 | 华北电力大学 | Power station boiler emission soft measuring method based on least squares support vector machine and on-line updating |
-
2016
- 2016-04-18 CN CN201610239213.9A patent/CN105929109B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN103413184A (en) * | 2013-08-05 | 2013-11-27 | 浙江大学 | Fly ash carbon content predicting system and method of circulating fluidized bedboiler |
| CN103729569A (en) * | 2014-01-20 | 2014-04-16 | 华北电力大学 | Soft measurement system for flue gas of power-station boiler on basis of LSSVM (Least Squares Support Vector Machine) and online updating |
| CN103728879A (en) * | 2014-01-20 | 2014-04-16 | 华北电力大学 | Power station boiler emission soft measuring method based on least squares support vector machine and on-line updating |
Non-Patent Citations (4)
| Title |
|---|
| 基于PSO-SVR的飞灰含碳量软测量研究;贺瑶等;《自动化与仪表》;20130430(第4期);第1-4页 * |
| 基于SVM和灰色预测的飞灰含碳量集成预测;周国雄等;《系统仿真学报》;20130430;第25卷(第4期);第729页2在线支持向量机的飞灰含碳量预测模型 * |
| 基于改进的KPCA和LSSVM飞灰含碳量的软测量建模;王真等;《山东电力技术》;20151031;第42卷(第10期);第40-43页 * |
| 运用事例推理技术确定飞灰含碳质量分数实时目标值;洪军等;《中国电力》;20070331;第40卷(第3期);第28-31页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105929109A (en) | 2016-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104200397B (en) | A kind of nuclear power station DCS system input design file and variable information data base consistency(-tance) method of calibration | |
| US20200184132A1 (en) | Apparatus and method for predicting deformation temperature of coal using predictive model | |
| Yan et al. | Determination of coal properties using laser-induced breakdown spectroscopy combined with kernel extreme learning machine and variable selection | |
| CN103092171A (en) | Cement digital management and control system | |
| CN110262450A (en) | The failure prediction method of various faults characteristic Cooperative Analysis towards steam turbine | |
| CN105929109B (en) | Flying marking measuring method | |
| CN109992844A (en) | A kind of boiler flyash carbon content prediction technique based on ADQPSO-SVR model | |
| CN104536396A (en) | Soft measurement modeling method used in cement raw material decomposing process in decomposing furnace | |
| Zhang et al. | Quantitative analysis of coal quality by laser-induced breakdown spectroscopy assisted with different chemometric methods | |
| CN113074459A (en) | Boiler control optimization method and system | |
| CN106529123B (en) | The measurement method and device of unburned carbon in flue dust | |
| CN113533622A (en) | Coal quality prediction method for coal mill based on neural network | |
| CN102994736B (en) | Correction method for annealing model of bell-type furnace | |
| Chong et al. | Prediction of gaseous emissions from a chain grate stoker boiler using neural networks of ARX structure | |
| CN207112772U (en) | Boiler hearth temperature on-line prediction system based on core offset minimum binary | |
| CN105279573B (en) | A kind of thermal power plant's coa consumption rate Economic Analysis Method | |
| Onat et al. | Prediction of combustion states from flame image in a domestic coal burner | |
| CN114813635B (en) | Method for optimizing combustion parameters of coal stove and electronic equipment | |
| Aints et al. | Determination of Heating Value of Estonian Oil Shale by Laser‐Induced Breakdown Spectroscopy | |
| CN116085823A (en) | Boiler combustion control method and system | |
| CN108875165A (en) | Boiler characteristics scaling method based on operation data | |
| CN108241789A (en) | The carbon containing measuring method of boiler slag and equipment based on adaptive weighted AWLS-SVR | |
| KR20150146094A (en) | Method of identifying cements using isotope ratio mass spectrometer | |
| CN110647560B (en) | Mechanism and brain-like intelligence combined online soft measurement method for coal quality of fired coal of power plant | |
| CN113743672A (en) | Coal mill economic coal powder fineness on-line analysis and operation optimization guidance method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100011 Shenhua building, 22 West Binhe Road, Dongcheng District, Beijing Patentee after: China Shenhua Energy Co.,Ltd. Patentee after: National Energy Group Guohua Power Co.,Ltd. Patentee after: Guoneng Guohua (Beijing) Electric Power Research Institute Co.,Ltd. Address before: 100011 Shenhua building, 22 West Binhe Road, Dongcheng District, Beijing Patentee before: China Shenhua Energy Co.,Ltd. Patentee before: BEIJING GUOHUA POWER Co.,Ltd. Patentee before: Shenhua Guohua (Beijing) Electric Power Research Institute Co.,Ltd. |