CN110362873A - Soot blowing control method, system, medium and equipment - Google Patents
Soot blowing control method, system, medium and equipment Download PDFInfo
- Publication number
- CN110362873A CN110362873A CN201910532096.9A CN201910532096A CN110362873A CN 110362873 A CN110362873 A CN 110362873A CN 201910532096 A CN201910532096 A CN 201910532096A CN 110362873 A CN110362873 A CN 110362873A
- Authority
- CN
- China
- Prior art keywords
- heating surface
- cleaning
- local
- whole
- soot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000004071 soot Substances 0.000 title claims abstract description 58
- 238000007664 blowing Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000010438 heat treatment Methods 0.000 claims abstract description 127
- 238000004140 cleaning Methods 0.000 claims abstract description 88
- 108090000623 proteins and genes Proteins 0.000 claims description 50
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 18
- 239000003546 flue gas Substances 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 17
- 239000003517 fume Substances 0.000 claims description 9
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 5
- 239000001301 oxygen Substances 0.000 claims description 5
- 229910052760 oxygen Inorganic materials 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 230000008676 import Effects 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 241000544061 Cuculus canorus Species 0.000 claims description 2
- 238000000137 annealing Methods 0.000 claims description 2
- 230000001537 neural effect Effects 0.000 claims description 2
- 238000009825 accumulation Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000005457 optimization Methods 0.000 description 5
- 238000012546 transfer Methods 0.000 description 4
- 239000000428 dust Substances 0.000 description 3
- 238000003780 insertion Methods 0.000 description 3
- 230000037431 insertion Effects 0.000 description 3
- 238000013517 stratification Methods 0.000 description 3
- 241000282461 Canis lupus Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000010926 purge Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 230000005619 thermoelectricity Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23J—REMOVAL OR TREATMENT OF COMBUSTION PRODUCTS OR COMBUSTION RESIDUES; FLUES
- F23J1/00—Removing ash, clinker, or slag from combustion chambers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23J—REMOVAL OR TREATMENT OF COMBUSTION PRODUCTS OR COMBUSTION RESIDUES; FLUES
- F23J3/00—Removing solid residues from passages or chambers beyond the fire, e.g. from flues by soot blowers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Mechanical Engineering (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Incineration Of Waste (AREA)
Abstract
The invention relates to a soot blowing control method, a system, a medium and equipment, wherein the method comprises the following steps: calculating an integral cleaning factor of an integral heating surface in a boiler flue and a local cleaning factor of each local heating surface of the integral heating surface according to the collected boiler operation parameters; controlling the action of a soot blower corresponding to the integral heating surface according to the integral cleaning factor; and controlling the action of the soot blower corresponding to the corresponding local heating surface according to the local cleaning factor. According to the invention, on the basis of blowing soot on the whole heating surface based on the whole cleaning factor, local on-demand soot blowing under the condition of serious soot accumulation on the local heating surface is realized according to the established local cleaning factor, the soot blowing cost is reduced, and the blowing damage phenomenon on the heating surface caused by excessive soot blowing is prevented.
Description
Technical field
The present invention relates to boiler technology fields, and in particular to a kind of soot-blowing control method, system, medium and equipment.
Background technique
Boiler heating surface dust stratification slagging endangers the weight by lot of domestic and foreign researcher and power generation unit
Depending on.Currently, large coal-fired power plant boiler has been mounted with advanced slag-blowing equipmemt, what present soot blower system was taken is that one kind is built
The whole soot blowing strategy on the experiential basis of operations staff is found, the as dirty characteristic parameter of the whole ash of heating surface sets a limit
Value carries out whole soot blowing to heating surface when the dirty characteristic parameter of the whole ash of heating surface is more than limit value, at present the dirty journey of heating surface ash
The main characterization method of degree has grey fouling (thermal) resistance, heat transfer availability ratio, cleaning gene etc., and wherein cleaning gene application range is most wide,
Its principle is to measure the caloric receptivity of practical heating surface, and the caloric receptivity of heating surface, is used when then trying every possible means to obtain the cleaning of identical operating condition
Cleaning caloric receptivity when actual caloric receptivity and identical operating condition is compared, the dirty degree of the ash of Lai Fanying heating surface, when it is more than
When limit value, whole purging is carried out to heating surface with regard to starting soot blower, the energy consumption cost of this soot-blowing control method soot blowing is high, and
It is easy to appear the blow loss phenomenon generated by excessive soot blowing to heating surface.
Summary of the invention
In view of the above technical problems, the present invention provides a kind of soot-blowing control method, system, medium and equipment.
The technical scheme to solve the above technical problems is that a kind of soot-blowing control method, comprising:
According to collected boiler operating parameter, the whole cleaning gene of whole heating surface and described is calculated in boiler flue
The local cleaning gene in each local heating face of whole heating surface；
The movement of soot blower corresponding with whole heating surface is controlled according to the whole cleaning gene；
The movement of soot blower corresponding with corresponding local heating face is controlled according to the local cleaning gene.
For achieving the above object, the present invention also provides a kind of soot blower control systems based on cleaning gene, comprising:
Computing module, for calculating the entirety of whole heating surface in boiler flue according to collected boiler operating parameter
The local cleaning gene in each local heating face of cleaning gene and the whole heating surface；
First control module, for moving according to the whole cleaning gene control soot blower corresponding with whole heating surface
Make；
Second control module, for controlling soot blowing corresponding with corresponding local heating face according to the local cleaning gene
The movement of device.
The present invention also provides a kind of computer readable storage mediums, including instruction, when described instruction is run on computers
When, so that the computer is executed the above method.
The present invention also provides a kind of computer equipment, including memory, processor and be stored on the memory and
The computer program that can be run on the processor, the processor realize the above method when executing described program.
The beneficial effects of the present invention are: on the basis of carrying out soot blowing to whole heating surface based on whole cleaning gene, root
According to foundation local cleaning gene realize local heating's area ash serious situation under partial on demand soot blowing, reduce soot blowing at
This, while preventing the blow loss phenomenon generated by excessive soot blowing to heating surface.
Detailed description of the invention
Fig. 1 is thermocouple and ash gun space layout perspective view；
Fig. 2 is thermocouple and soot blower space layout side view；
Fig. 3 is local heating face thermocouple measuring point value arrangement map；
Fig. 4 is the schematic diagram of local heating face thermocouple insertion insertion heating surface preceding Bao Qiang and rear packet wall；
Fig. 5 is a kind of flow chart of the soot-blowing control method based on cleaning gene provided in an embodiment of the present invention；
Fig. 6 is SVM model training flow chart.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the invention.
The present invention is suitable for the soot-blowing control of the soot blower system of boiler back end ductwork internal heating surface, as shown in Figure 1, 2, boiler
In the flue gas flow channel of tail portion, flue is separated by central partition wall, the heating surface for respectively having multilayer complications to be distributed in the flue of two sides, each
Heating surface in layer is known as local heating face, and heating surface has low temperature superheater, and low-temperature reheater and economizer etc. are disposed with thermoelectricity
Even summation soot blower, thermocouple and soot blower spatial arrangement structure are as shown in Figure 1, 2, the space layout between each layer local heating face
Thermocouple, for measuring the flue-gas temperature flowed through between each layer local heating face.Thermocouple is arranged at each layer heating surface wall surface,
For measuring wall surface temperature, by taking certain unit as an example, low temperature superheater wall surface temperature threshold value is set as 545 DEG C, and 148 are arranged altogether
Monitoring point, measuring point are all disposed on horizontal pipe section, and temperature is about 459~475 DEG C, and 176 endwall faces are arranged in low-temperature reheater region
Thermocouple, threshold temperature are set as 560 DEG C, and measuring point temperature range is about 497~536 DEG C；These wall surface temperature data being capable of side
The dust stratification contamination of face reflection heating surface.
Flue-gas temperature side point arrangement is as shown in Figure 2,3, 4, and every eight thermocouples are respectively before insertion low temperature heating surface
Bao Qiang and rear packet wall divide 1 meter of depth at two thermocouple measuring points for measuring flue-gas temperature with a distance from wall surface.Thermocouple measurements are returned
Also to DCS system, flue-gas temperature and wall surface temperature are recorded.It is made even by the flue-gas temperature data that eight thermocouples of entrance are returned
For mean value it can be concluded that mean temperature at smoke inlet, exhanst gas outlet mean temperature, which calculates, uses identical method.Sonic soot blowing
Device is that packet wall paper in front and back is set, and every layer arrangement four is right, is resonant cavity type acoustic wave ash ejector, purges to space diagonal direction and realized with this
Soot blowing is coupled and by bracket as support without dead angle by header.
Fig. 5 is a kind of flow chart of soot-blowing control method provided in an embodiment of the present invention, as shown in figure 5, this method comprises:
S1, according to collected boiler operating parameter, calculate in boiler flue the whole cleaning gene of whole heating surface and
The local cleaning gene in each local heating face of the entirety heating surface；
Specifically, whole cleaning gene and local cleaning gene are the ratio between practical caloric receptivity and cleaning caloric receptivity, wherein meter
When calculating whole cleaning gene, practical caloric receptivity refer to flowing through in actual moving process the unit mass in each layer local heating face to
Total heat exchange amount of water, cleaning caloric receptivity refer to the unit mass that each layer local heating face is flowed through when clean conditions under corresponding load
Total heat exchange amount of water supply；When calculating local cleaning gene, practical caloric receptivity refers to being flowed through in actual moving process to this layer of office
The heat exchange amount of the unit mass water supply of portion's heating surface, cleaning caloric receptivity refer to flowing through this layer of office when clean conditions under corresponding load
The heat exchange amount of the unit mass water supply of portion's heating surface.
S2, the movement that soot blower corresponding with whole heating surface is controlled according to the whole cleaning gene；
S3, the movement that soot blower corresponding with corresponding local heating face is controlled according to the local cleaning gene.
Specifically, cleaning gene changes between 0~1.When heating surface is in cleaning completely, cleaning gene 1；When
When fouling of heating surface is serious, cleaning gene can be gradually reduced, and be equal to 0 when until not having heat transfer phenomenon.It therefore can be according to cleaning
The real-time change of the value of the factor monitors fouling of heating surface situation, to control the soot blowing movement of soot blower.
If whole cleaning gene is lower than given value, controls soot blower and whole soot blowing is carried out to whole heating surface；Entirety is blown
After the completion of ash, for the corresponding soot blower of face lower layer, local heating that local cleaning gene transfinites, soot blowing instruction, carry out office are issued
Portion's soot blowing.
A kind of soot-blowing control method based on cleaning gene provided in an embodiment of the present invention, based on whole cleaning gene pair
On the basis of whole heating surface carries out soot blowing, local heating's area ash serious situation is realized according to the local cleaning gene of foundation
Under partial on demand soot blowing, reduce soot blowing cost, while preventing the blow loss phenomenon generated by excessive soot blowing to heating surface.
Specifically, in this embodiment, step S1 is specifically included:
S1.1, whole heating surface and the whole heating surface in boiler flue are calculated separately according to fume side equation of heat balance
Each local heating face working medium practical caloric receptivity；
Specifically, fume side equation of heat balance are as follows:
Wherein, qsjFor practical caloric receptivity；For errors；h'y、h”yRespectively flue gas imports and exports section in heating surface
On average enthalpy；Δ α is air leakage coefficient；For the cold air for leaking into heating surface fume side corresponding with excess air coefficient
Enthalpy.Errors, air leakage coefficient and excess air coefficient can refer to the boiler specification of different power plant, heating surface and outlet
Average enthalpy calculates software I APWS-IF97 by water vapour according to out temperature pressure and show that out temperature pressure passes through electricity
Factory DCS returns data and obtains.
S1.2, the prediction model that the cleaning of collected boiler operating parameter input training in advance recepts the caloric, it is pre- respectively
Measure the cleaning caloric receptivity of whole heating surface and each local heating face working medium；
Specifically, the calculating for cleaning caloric receptivity, needs to establish prediction model by multi-parameter, to be predicted.
Support vector machines, neural algorithm, genetic algorithm, cuckoo algorithm, annealing algorithm etc. can be selected in prediction model, wherein supports
Vector machine has preferable prediction effect and more sensitive to kernel functional parameter optimizing on goal regression and classification.For model
Parameter optimization algorithm, have PSO parameter optimization, Genetic Algorithms parameter optimization, grey wolf algorithm GWO using more algorithm at present
Parameter optimization etc..Here, the algorithm of grey wolf algorithm supporting vector machine model can be selected, have speed fast, accuracy is high and right
In the small advantage of the requirement of sample size.
The kernel function of support vector machines be widely used there are three types of kernel function, multinomial kernel, radial basis function kernel
(Radial Basis Function, RBF) and Sigmoind kernel, since the input parameter of cleaning gene and prediction cleaning are inhaled
It is Nonlinear Mapping between heat, and RBF kernel functional parameter is more, can substantially meet number of parameters to model complexity
It influences, so RBF can be used as kernel function.The optimizing section of SVM parameter C and g are (0,100), the precision parameter ε of model
It is 0.05.When the mean square deviation of test samples reaches minimum value, parameter optimization stops.RBF kernel function is expressed as follows:
It is as follows for the training method of prediction model:
After soot blower carries out a soot blowing to whole heating surfaces, one group of boiler operating parameter is acquired every preset time,
And the practical heat absorption of whole heating surface and each local heating face working medium in boiler flue is calculated according to fume side equation of heat balance
Amount, the cleaning as working medium recept the caloric, multiple groups boiler operating parameter and corresponding cleaning caloric receptivity composing training collection；
The training set is learnt, the cleaning for fitting whole heating surface and each local heating face working medium respectively is inhaled
The relational expression of heat and boiler operating parameter, circulation execute the step, until being predicted according to the relational expression fitted clear
Clean caloric receptivity meets error requirements.
Specifically, different input quantities and cleaning caloric receptivity, i.e., is done the fitting of weight, to sentence by the learning process of training set
The disconnected input quantity with the positive correlation of cleaning caloric receptivity or negative correlation out, computer fit different input quantities after passing through study and clean
The relational expression of caloric receptivity, to predict test set data.
For support vector machines, the process of training study is exactly to construct optimal linear fit function: f (x)=wx+
B, in formula: w ∈ Rn, b ∈ R.Structural risk minimization principle is followed, converts convex quadratic programming problem for training learning process,
Avoid the local minimum phenomenon in solving.Its constraint condition are as follows:
Wherein, ε is precision parameter, ξiWithIt is the slack variable for measuring ε, | | w | | the complexity of and function f has
It closes.
The flow chart of whole training process is as shown in Figure 6.
The input quantity of the local cleaning gene selection prediction model in local heating face needs to consider following boiler operating parameter:
The inside and outside flue gas and low temperature feedwater for high temperature of heating surface tube wall, the flow of two kinds of working medium determines heat exchange amount, therefore to consider work
Mass flow amount；Fume side mainly needs to consider flue-gas temperature and flow；In the operating condition, the air output for flowing through heating surface is difficult to survey
Amount, thus in DCS oxygen amount and boiler load carry out the indirect flue gas flow that reflects；The caloric receptivity of water supply directly with low temperature superheater and
The feed temperature pressure of low-temperature reheater inlet and outlet is closely related, also takes into account these parameters；Each layer burner is given
Coal amount will have a direct impact on furnace flame centre height, to have an impact indirectly to the heat exchange amount of subsequent each heating surface, therefore
Coal-supplying amount also considers wherein；Wall surface temperature reflects the heat exchange degree of heating surface, and wall surface temperature is higher, then proves fouling of heating surface
Degree is more serious.
Since after boiler heating surface dust stratification, heat transfer coefficient necessarily declines, can not be conveyed so as to cause water vapour high
The heat that warm flue gas is had, heat transfer deterioration, tube wall temperature increase at this time, because heat can not be taken away, and exacerbate flue gas temperature
The raising of degree, thus the local cleaning gene in each local heating face with flue-gas temperature and wall surface temperature be it is related, by cigarette
Temperature degree and the anti-wall surface temperature the released input quantity new as model, can be improved the accuracy of prediction result, thus more
The dirty situation of ash of accurate prediction heating surface, provides control means for intelligent ash blowing technique.
In conclusion selection returns the boiler load of data acquisition by Power Plant DCS System, flows through the flow of heating surface working medium
Dgz, power pressure Pgz, flue gas flow Gyq, heating surface import and export work temperature Tjk,Tck, six feeder coal-supplying amount ni, oxygen amount δ
(O2), wall surface temperature TbmWith flue-gas temperature Tyq, the cleaning caloric receptivity (q of this ten kinds of parameters and heating surfaceqj) establish functional relation
Formula:
qqj=f (Dgz,Pgz,Gyq,Tjk,Tck,ni,δ(O2),Tbm,Tyq,B)
It is the cleaning caloric receptivity of predictable local heating face working medium according to the relational expression.
The calculating of the whole cleaning gene of whole heating surface is defeated according to the overall operation operating condition of specific heating surface progress model
Enter amount selection when to consider following parameter: in calculating process, due to inside and outside pipeline be respectively low temperature feedwater and high-temperature flue gas,
Consider the influence of main steam flow；Water supply caloric receptivity is directly related to the feed temperature of inlet and outlet, pressure.Load to burner hearth and
The heat exchange situation of convection heating surface is affected.While in order to reduce the complexity of system, over-fitting and nothing are prevented
The influence for closing distracter, in the algorithm rejects local parameter.
In conclusion obtaining main steam flow D from DCS control systemzzq, import and export feed pressure Pgs, temperature Tgs, give
Coal amount ni, oxygen amount δ (O2), load B data, using this six parameters as mode input.By analyzing above, finally construct whole
The relational expression of the cleaning caloric receptivity of body heating surface:
Qzt=f (Dzzq,Pgs,Tgs,ni,δ(O2),B)
Using each group input parameter as training set, by constructing Lagrangian (Lagrange) function, by training set minimum
Change structure risk function problem, be converted into and solve following new models, it may be assumed that
In formula,And aiFor Lagrange multiplier, solution obtains (a, a*).Since input quantity is multi-parameter, and power plant is each
There is no clearly unified linear relation between item parameter and caloric receptivity, therefore can only assume a Nonlinear Mapping Φ (x), makes
Different types of parameter is mapped in the feature space of some higher-dimension by it.It, can be in the feature space of the higher-dimension of higher-dimension
Think that cleaning caloric receptivity is linearly related with input parameter, thus can one obtain the processing optimal support vector machines of linear problem
Estimation function:
In formula: K (x, xi) it is kernel function, it is determined by algorithm itself, using RBF kernel function in the present embodiment；B is line
Property constant, determined by algorithm by iteration and optimizing come final, in this manner it is possible to convert nonlinear multivariable problem to linearly
Problem, to predict the cleaning caloric receptivity of each period.
S1.3, it practical is recepted the caloric and cleaning caloric receptivity calculates separately to obtain the whole clear of the whole heating surface according to described
The local cleaning gene of the clean factor and each local heating face.
The embodiment of the present invention provides a kind of soot blower control system based on cleaning gene, comprising:
Computing module, for calculating the entirety of whole heating surface in boiler flue according to collected boiler operating parameter
The local cleaning gene of cleaning gene and each local heating face；
First control module, for moving according to the whole cleaning gene control soot blower corresponding with whole heating surface
Make；
Second control module, for controlling soot blowing corresponding with corresponding local heating face according to the local cleaning gene
The movement of device.
The principle of work and power of modules is described in detail in foregoing teachings in the system, and which is not described herein again.
The present invention also provides a kind of computer readable storage mediums, including instruction, when described instruction is run on computers
When, so that the computer is executed the method and step in above method embodiment；Or storage the above system embodiment is each soft
The corresponding instruction of part module.
The present invention also provides a kind of computer equipment, including memory, processor and be stored on the memory and
The computer program that can be run on the processor, the processor are realized in above method embodiment when executing described program
Method and step.
In general, the present invention can effectively improve soot blowing efficiency, reduce soot blowing energy consumption, improves soot blowing total revenue, is protecting
Under the premise of demonstrate,proving safety, the economic benefit of power plant is improved.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of soot-blowing control method characterized by comprising
According to collected boiler operating parameter, the whole cleaning gene of whole heating surface and the entirety in boiler flue are calculated
The local cleaning gene in each local heating face of heating surface；
The movement of soot blower corresponding with the entirety heating surface is controlled according to the whole cleaning gene；
According to the movement of local cleaning gene control soot blower corresponding with the corresponding local heating face.
2. the method according to claim 1, wherein the entirety for calculating whole heating surface in boiler flue is clear
The local cleaning gene in each local heating face of the clean factor and the whole heating surface, specifically includes:
Each office of whole heating surface and the whole heating surface in boiler flue is calculated separately according to fume side equation of heat balance
The practical caloric receptivity of portion's heating surface working medium；
By the prediction model of the cleaning caloric receptivity of collected boiler operating parameter input training in advance, prediction obtains described respectively
The cleaning of whole heating surface and each local heating face working medium recepts the caloric；
According to the practical caloric receptivity and cleaning caloric receptivity calculate separately to obtain the whole heating surface whole cleaning gene and
The local cleaning gene in each local heating face.
3. according to the method described in claim 2, it is characterized in that, the fume side equation of heat balance are as follows:
Wherein, qsjFor practical caloric receptivity；For errors；h'y、h"yRespectively flue gas is on heating surface inlet and outlet section
Average enthalpy；Δ α is air leakage coefficient；For the cold air enthalpy for leaking into heating surface fume side corresponding with excess air coefficient.
4. according to the method described in claim 2, it is characterized in that, the training method of the prediction model are as follows:
After soot blower carries out a soot blowing to whole heating surfaces, one group of boiler operating parameter is acquired every preset time, and press
The practical caloric receptivity that whole heating surface and each local heating face working medium in boiler flue are calculated according to fume side equation of heat balance, makees
It recepts the caloric for the cleaning of working medium, multiple groups boiler operating parameter and corresponding cleaning caloric receptivity composing training collection；
The training set is learnt, fits the cleaning caloric receptivity of whole heating surface and each local heating face working medium respectively
With the relational expression of boiler operating parameter, circulation executes the step, until being inhaled according to the cleaning that the relational expression fitted is predicted
Heat meets error requirements.
5. according to the method described in claim 4, it is characterized in that, for training the cleaning of each local heating face working medium to absorb heat
The boiler operating parameter of the prediction model of amount includes boiler load, flow, temperature and the pressure of working medium in the local heating face,
Flue gas flow and temperature, coal-supplying amount, oxygen amount and wall surface temperature.
6. according to the method described in claim 4, it is characterized in that, what the cleaning for the whole heating surface working medium of training recepted the caloric
The boiler operating parameter of prediction model includes: boiler load, main steam flow, imports and exports feed pressure and temperature, coal-supplying amount and
Oxygen amount.
7. according to the described in any item methods of claim 2-6, which is characterized in that the prediction model uses support vector machines
SVM, neural algorithm, genetic algorithm, cuckoo algorithm or annealing algorithm.
8. a kind of soot blower control system characterized by comprising
Computing module, for according to collected boiler operating parameter, calculating the whole cleaning of whole heating surface in boiler flue
The local cleaning gene in each local heating face of the factor and the whole heating surface；
First control module, for moving according to the whole cleaning gene control soot blower corresponding with the entirety heating surface
Make；
Second control module, for according to local cleaning gene control soot blowing corresponding with the corresponding local heating face
The movement of device.
9. a kind of computer readable storage medium, including instruction, which is characterized in that when described instruction is run on computers,
The computer is set to execute method according to claim 1-7.
10. a kind of computer equipment, including memory, processor and be stored on the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor is realized when executing described program such as any one of claim 1-7
The method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910532096.9A CN110362873A (en) | 2019-06-19 | 2019-06-19 | Soot blowing control method, system, medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910532096.9A CN110362873A (en) | 2019-06-19 | 2019-06-19 | Soot blowing control method, system, medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110362873A true CN110362873A (en) | 2019-10-22 |
Family
ID=68216698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910532096.9A Pending CN110362873A (en) | 2019-06-19 | 2019-06-19 | Soot blowing control method, system, medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110362873A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114154272A (en) * | 2021-12-24 | 2022-03-08 | 广州涂涂乐科技有限公司 | Automatic cleaning control method and system applied to glue spraying equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090063113A1 (en) * | 2007-08-31 | 2009-03-05 | Emerson Process Management Power & Water Solutions, Inc. | Dual Model Approach for Boiler Section Cleanliness Calculation |
| CN105091932A (en) * | 2015-08-07 | 2015-11-25 | 江苏方天电力技术有限公司 | Tri-section rotary preheater segmented soot formation monitoring method |
| CN106093062A (en) * | 2016-06-16 | 2016-11-09 | 华南理工大学 | A kind of boiler heating surface dust stratification slagging scorification intelligent sootblowing based on CCD |
-
2019
- 2019-06-19 CN CN201910532096.9A patent/CN110362873A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090063113A1 (en) * | 2007-08-31 | 2009-03-05 | Emerson Process Management Power & Water Solutions, Inc. | Dual Model Approach for Boiler Section Cleanliness Calculation |
| CN105091932A (en) * | 2015-08-07 | 2015-11-25 | 江苏方天电力技术有限公司 | Tri-section rotary preheater segmented soot formation monitoring method |
| CN106093062A (en) * | 2016-06-16 | 2016-11-09 | 华南理工大学 | A kind of boiler heating surface dust stratification slagging scorification intelligent sootblowing based on CCD |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114154272A (en) * | 2021-12-24 | 2022-03-08 | 广州涂涂乐科技有限公司 | Automatic cleaning control method and system applied to glue spraying equipment |
| CN114154272B (en) * | 2021-12-24 | 2022-06-21 | 广州涂涂乐科技有限公司 | Automatic cleaning control method and system applied to glue spraying equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105972585B (en) | A kind of circulating fluidized bed boiler soot blowing and optimal system and method | |
| Lv et al. | A dynamic model for the bed temperature prediction of circulating fluidized bed boilers based on least squares support vector machine with real operational data | |
| CN103115356B (en) | The monitoring method of Supercritical CFB Boiler burning signal and optimal control method | |
| CN101598688B (en) | Boiler fouling monitoring and soot blowing optimization methods based on on-line measurement of coal quality | |
| CN106322412B (en) | Coal unit convection heating surface intelligent ash blowing method based on two-dimentional optimizing | |
| CN109695892B (en) | Method and device for protecting wall temperature of heating surface of boiler | |
| CN108716664B (en) | A kind of method and apparatus of on-line measurement burner hearth ash fouling coefficient | |
| CN111695249B (en) | Prediction method for heat efficiency of gas boiler | |
| CN112989694B (en) | Segmented monitoring system and method for ash on heating surface | |
| CN110207094A (en) | IQGA-SVR boiler heating surface fouling characteristics discrimination method based on principal component analysis | |
| Peña et al. | Towards soot-blowing optimization in superheaters | |
| Pattanayak et al. | Optimization of sootblowing frequency to improve boiler performance and reduce combustion pollution | |
| CN110390420A (en) | Superheater slagging prediction technique based on particle group optimizing artificial neural network | |
| Chandok et al. | Estimation of furnace exit gas temperature (FEGT) using optimized radial basis and back-propagation neural networks | |
| CN109829189A (en) | A kind of Boiler Furnace slagging thickness judgment method based on numerical simulation | |
| CN112628712A (en) | Secondary air closed-loop optimization control system based on air door resistance coefficient | |
| CN109141541A (en) | A kind of coal-fired power station boiler reheater working medium flow on-line correction method | |
| CN110362873A (en) | Soot blowing control method, system, medium and equipment | |
| CN103760191B (en) | Based on the full working scope boiler heating surface pollution monitoring method and apparatus of dynamic compensation | |
| CN115510904A (en) | Boiler heating surface ash deposition monitoring method based on time sequence prediction | |
| CN202216928U (en) | Fouling monitoring device for monitoring convection heating surfaces f boiler | |
| CN111242279A (en) | System and method for predicting slagging of hearth of ultra-supercritical pulverized coal boiler | |
| CN108895427B (en) | A kind of modification method of the feed temperature variation to direct current cooker exhaust gas temperature | |
| CN115326237A (en) | Wall temperature measuring method and system considering influence of boiler superheater oxide skin | |
| CN204536022U (en) | The heat exchange of system, the proving installation of drag characteristic emulation is utilized for smoke discharging residual heat |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191022 |