CN113761794A - Boiler soot blowing optimization method for complementing pollution factors based on time series prediction algorithm - Google Patents
Boiler soot blowing optimization method for complementing pollution factors based on time series prediction algorithm Download PDFInfo
- Publication number
- CN113761794A CN113761794A CN202110942851.8A CN202110942851A CN113761794A CN 113761794 A CN113761794 A CN 113761794A CN 202110942851 A CN202110942851 A CN 202110942851A CN 113761794 A CN113761794 A CN 113761794A
- Authority
- CN
- China
- Prior art keywords
- pollution
- soot blowing
- time
- time period
- boiler
- 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
- 239000004071 soot Substances 0.000 title claims abstract description 125
- 238000007664 blowing Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 45
- 238000005457 optimization Methods 0.000 title claims abstract description 24
- 238000010438 heat treatment Methods 0.000 claims abstract description 67
- 230000008859 change Effects 0.000 claims abstract description 16
- 238000011109 contamination Methods 0.000 claims abstract description 14
- 230000002159 abnormal effect Effects 0.000 claims abstract description 12
- 239000003546 flue gas Substances 0.000 claims description 21
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 20
- 238000012546 transfer Methods 0.000 claims description 19
- 238000007477 logistic regression Methods 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- OIGNJSKKLXVSLS-VWUMJDOOSA-N prednisolone Chemical compound O=C1C=C[C@]2(C)[C@H]3[C@@H](O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 OIGNJSKKLXVSLS-VWUMJDOOSA-N 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 238000005338 heat storage Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 7
- 230000006641 stabilisation Effects 0.000 description 6
- 238000011105 stabilization Methods 0.000 description 6
- 239000000779 smoke Substances 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 230000008021 deposition Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000002893 slag Substances 0.000 description 3
- 239000003245 coal Substances 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 230000003442 weekly effect Effects 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- QIVBCDIJIAJPQS-VIFPVBQESA-N L-tryptophane Chemical compound C1=CC=C2C(C[C@H](N)C(O)=O)=CNC2=C1 QIVBCDIJIAJPQS-VIFPVBQESA-N 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000010926 purge Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/12—Timing analysis or timing optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Incineration Of Waste (AREA)
Abstract
The invention relates to a boiler soot blowing optimization method for complementing pollution factors based on a time series prediction algorithm, which comprises the following steps of: calculating a pollution factor of the heating surface; eliminating abnormal data; grabbing in a steady state working condition time period; and (4) complementing the pollution factors in the unsteady time period by using a time series prediction algorithm. The invention has the beneficial effects that: according to the method, the pollution factors of the steady-state working condition time period are calculated by grabbing the steady-state working condition, and the pollution factors under the non-steady-state working condition are supplemented according to a time sequence prediction algorithm, so that soot blowing is guided. The pollution factor obtained by directly calculating according to the heat balance is difficult to accurately reflect the actual contamination condition of the heating surface in real time due to the change of the heat storage capacity of the heating surface under the unstable state working condition, and the pollution factor is easy to fluctuate greatly, so that a large amount of mistaken soot blowing operations are avoided. The method is simple and reasonable, has good effect in practical application, does not need to add additional equipment and measuring points, and has remarkable technical and economic benefits.
Description
Technical Field
The invention belongs to the technical field of coal-fired power plants, and particularly relates to a coal-fired boiler soot blowing optimization method for complementing pollution factors based on a time series prediction algorithm.
Background
During the combustion of pulverized coal, the non-combustible ash and other mineral components of the coal-fired power station boiler can be deposited on the heating surface, and the coal-fired power station boiler mainly comprises slag bonding at a high-temperature area such as a water-cooled wall and the like, and ash deposition on the heating surface of a tail flue. The thermal resistance of ash and dirt deposited on the heating surface is greatly higher than that of a metal pipe wall, and if the ash and dirt is not removed in time, a series of problems of heat transfer performance reduction of the heating surface, smoke exhaust temperature rise, flue resistance increase, high-temperature corrosion, heating surface abrasion aggravation and the like can be caused. At present, a large coal-fired power plant boiler avoids serious dust accumulation and slag bonding on a heating surface by a method of installing soot blowers, and the number of the soot blowers of the coal-fired power plant boiler with the level of more than 300MW is usually 60-180, and the soot blowers are arranged at the upper part of a hearth, a horizontal flue, a vertical flue and the like.
Most of the existing coal-fired power plants adopt a timed and quantitative soot blowing scheme, namely soot blowing operation with the same time is carried out every day according to fixed time to form a fixed soot blowing period, but the fixed soot blowing period is set only by considering the shift of operators and lacks data support, the soot accumulation condition of a heating surface cannot be judged visually, the heating surface with serious soot accumulation can not be swept in time, the heat transfer performance of the heating surface is reduced, and the main steam temperature and the exhaust gas temperature are higher; it is also possible to cause frequent purging of lightly heated surfaces of soot deposits, resulting in wasted soot blowing steam and shortened tube wall life.
Through searching in the prior art, part of researchers calculate the pollution factors of all heating surfaces through heat balance calculation or neural network, two-dimensional optimization searching algorithm and the like, so that the soot blowing interval and frequency are judged. The method comprises the steps that a Soot-blower Advisor expert system jointly developed by a foreign New York State electric power gas company and a general physical company, an Optimax system boiler cleaning module developed by ABB of Switzerland, a Smart Process (TM) system of West House company and other Soot blowing optimization systems or platforms calculate the actual heat transfer quantity of each Soot blower area according to data such as the smoke temperature of part of a heating surface inlet and outlet, working medium temperature and the like, and pollution factors are solved, so that Soot blowing is guided. The Chinese patent application No. 2016107782348 discloses a coal-fired unit convection heating surface intelligent soot blowing method based on two-dimensional optimization, which determines a pollution factor by calculating an ideal heat exchange coefficient and an actual heat exchange coefficient of a convection heating surface and monitors the cleaning condition of the convection heating surface on line. The chinese patent application No. 2009100332364 discloses a boiler soot monitoring and soot blowing optimization method based on coal quality on-line measurement, wherein a counter-flue gas flow process carries out on-line monitoring and analysis calculation on soot deposition and slag deposition on each main convection heating surface and the temperature of flue gas at a furnace outlet.
In the calculation process of the soot blowing optimization system, the actual heat transfer coefficient is calculated according to the parameters such as the temperature and the flow of the actual flue gas side and the working medium side of each heating surface, and meanwhile, the pollution factor of the heating surface can be calculated according to the ideal heat transfer coefficient, so that whether soot blowing is needed on the heating surface is judged. However, the above method has disadvantages: under the unsteady state working condition, such as the large fluctuation of the boiler load or the short time after the soot blowing of the heating surface is completed, due to the change of the heat storage capacity of the heating surface, the pollution factor is difficult to accurately reflect the actual contamination condition of the heating surface in real time, so that the large fluctuation of the pollution factor under the unsteady state working condition occurs, and if the pollution factor under the unsteady state working condition obtained by actual calculation is directly used for judging whether the soot blowing is needed or not, the large amount of false soot blowing can be caused.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a coal-fired boiler soot blowing optimization method for complementing pollution factors based on a time series prediction algorithm.
The coal-fired boiler soot blowing optimization method for complementing pollution factors based on the time series prediction algorithm comprises the following steps of:
step 2, cleaning data according to the upper limit and the lower limit of the pollution factor, the boiler load, the quality of the data of the working medium measuring points and other factors, and removing abnormal data;
step 3, grabbing in a steady-state working condition time period;
step 3.1, grabbing a time period which is not influenced by soot blowing: judging a soot blowing time period by using a soot blower action current measuring point, a soot blower starting instruction measuring point and a soot blower exit instruction measuring point, and capturing the soot blowing time period; introducing the stable time t after soot blowing, and determining a soot blowing time period and an unstable time period influenced by soot blowing, wherein the rest time period is a time period not influenced by soot blowing;
step 3.2, capturing during the stable time period of the boiler load;
and 3.3, capturing in a steady state working condition time period: taking the intersection part of the time period which is not influenced by soot blowing and the boiler load stable time period obtained in the step 3.1 as a steady-state working condition time period, wherein the non-intersection part is an unsteady-state working condition time period;
step 4, complementing the pollution factors in the unsteady time period by using a time sequence prediction algorithm;
and 5, judging whether to perform soot blowing according to the pollution factor change trend.
Preferably, step 1 specifically comprises the following steps:
step 1.1, according to the basic principle of heat balance of the whole boiler and each local heating surface, calculating the inlet flue gas temperature of each heating surface section by section according to the opposite direction of flue gas flow by utilizing the existing on-line working medium side parameter and flue gas side parameter;
step 1.2, calculating actual heat transfer coefficient and ideal heat transfer coefficient of each heating surface according to parameters such as inlet flue gas temperature, outlet flue gas temperature, working medium inlet and outlet temperature, flue gas flow, working medium flow, structural size of the heating surface and the like of each heating surface;
step 1.3, calculating the pollution factor of the heated surface according to the formula (1):
in the above formula, KsjIs the actual heat transfer coefficient of the heated surface and has the unit of W/(m)2*K)；KlxIs the ideal heat transfer coefficient of the heated surface and has the unit of W/(m)2K); f is a pollution factor.
Preferably, the abnormal data removed in step 2 includes abnormal data such as shutdown abnormal data and station damage.
Preferably, the steady-state working condition in the step 3 is that the heating surface is blowing soot or just completes blowing soot, and the load of the boiler is stable.
Preferably, step 3.2 comprises the steps of:
step 3.2.1, screening all boiler load data at a certain time point and in a period tau thereafter to obtain the highest load value D in the period taumaxAnd a minimum load value DminCalculating the load fluctuation Δ D within the time period τ:
ΔD＝Dmax-Dmin (2)
in the above formula Dmax、DminAnd Δ D is in units of t/h or MW;
when the load fluctuation delta D in the time period tau meets the following formula (3), the time period tau is the working condition of stable boiler load;
ΔD≤x*Ded (3)
in the above formula, x is the proportion of the preset normal fluctuation range of the load in the rated load; dedThe rated load of the boiler is t/h or MW;
and 3.2.2, screening the boiler load data at all time points and in the time period tau after the time points by a method of moving a time window according to the step 3.2.1 to obtain the stable time period of the boiler load.
Preferably, in step 3.2.1, the boiler is in a load-stable mode within the range of the fluctuation ratio.
Preferably, the step 4 specifically comprises the following steps:
step 4.1, calculating the pollution factor in the time period of the steady-state working condition by adopting the method for calculating the pollution factor of the heating surface in the step 1;
step 4.2, complementing and calculating the pollution factors in the unsteady state working condition time period by a time prediction algorithm; the time series prediction algorithm adopts a logistic regression model of prophet algorithm:
F(t)＝g(t)+s(t)+h(t) (4)
in the above formula, t is time; f (t) is a function of the time variation of the pollution factor; g (t) represents a growth function for fitting aperiodic variations; s (t) is used to indicate periodic changes, such as weekly, yearly, seasonal, etc.; h (t) shows changes caused by special reasons such as holidays, festivals and the like; i.e. the time sequence is divided into a superposition of 3 sections (soot blowing period, non-steady state period affected by soot blowing, period unaffected by soot blowing); for the time series prediction of the pollution factors, no obvious periodic change and obvious holiday change exist, so that the influence of s (t) and h (t) can be ignored;
the growth of g (t) adopts a logistic regression function model, and the logistic regression function model is shown as the following formulas (5) and (6):
in the above formulas (5) and (6), t is time; c (t) is the saturation value (carrying capacity); k is the swell ratio; m is a bias parameter; function a (t) represents an indicative function of the time node as a function of the growth rate k; delta is indicated at the time stamp sjThe amount of change in the growth rate; sjThe time at which the increase rate changes at the jth transition point; gamma is sjThe smoothing offset of (d); a isj(t) is an indicative function of the time node at which the jth transition point varies with the growth rate k at time t;
and 4.3, presetting the upper limit and the lower limit of the pollution factor, the time interval of data, the prediction period and the time sequence data with the time stamp according to the prophet algorithm model, and supplementing the pollution factor in the unsteady state working condition time period.
Preferably, step 5 specifically comprises the following steps:
step 5.1, performing statistical analysis on the historical pollution factors of the heating surface, setting the condition that the pollution factors are less than or equal to a fixed numerical value as a cleaning working condition of the heating surface, and defining the fixed numerical value of the pollution factors as a minimum pollution factor Fmin；
Step 5.2, counting the change range of the pollution factors of the heating surface before and after multiple times of soot blowing in history, and calculating an average value to obtain the reduction range delta F of the pollution factors of the heating surface after soot blowing:
ΔFi＝Fb,i-Fa,i (7)
in the above formulae (7) to (8), Δ FiThe variation range of the pollution factors of the heating surface before and after the ith soot blowing is obtained; fb,iPollution factors of the heating surface before the ith soot blowing; fa,iThe pollution factor of the heated surface after the ith soot blowing is obtained; n is the number of statistics, and is generally at least 1 year of data;
step 5.3, calculating the critical pollution factor FljAnd generating a critical pollution factor table;
Flj＝Fmin+ΔF (9)
in the above formula, FminIs the minimum pollution factor FminDelta F is the reduction amplitude of the pollution factor of the heating surface after soot blowing;
step 5.4, judging whether the actual pollution factor is larger than the critical pollution factor, if so, further judging whether parameters such as boiler load, main steam temperature and the like meet the necessary soot blowing conditions, if so, blowing soot, and if not, blowing soot; if the actual pollution factor is less than or equal to the critical pollution factor, the critical pollution factor is continuously calculated to generate a critical pollution factor table.
Preferably, the minimum contamination factor F in step 5.1minAverage of all historical contamination factors minus 2 times the standard deviation of the historical contamination factors:
Fmin＝μ-2σ (10)
in the above formula, μ is the average value of the historical contamination factors, and σ is the standard deviation of the historical contamination factors.
Preferably, in step 5.4, a critical pollution factor table under each subdivision condition is generated according to subdivision conditions of parameters such as unit load, feedwater flow and the like.
Preferably, the step 5.1 to the step 5.3 may also determine the critical pollution factor by judging the energy balance between the soot blowing profit and the soot blowing steam consumption according to the completed historical pollution factor data obtained in the step 1 to the step 4.
The invention has the beneficial effects that: according to the method, the pollution factors of the steady-state working condition time period are calculated by grabbing the steady-state working condition, and the pollution factors under the non-steady-state working condition are supplemented according to a time sequence prediction algorithm, so that soot blowing is guided. The pollution factor obtained by directly calculating according to the heat balance is difficult to accurately reflect the actual contamination condition of the heating surface in real time due to the change of the heat storage capacity of the heating surface under the unstable state working condition, and the pollution factor is easy to fluctuate greatly, so that a large amount of mistaken soot blowing operations are avoided. The method is simple and reasonable, has good effect in practical application, does not need to add additional equipment and measuring points, and has remarkable technical and economic benefits.
Drawings
FIG. 1 is a flowchart of model training according to a second embodiment of the present invention;
fig. 2 is a flowchart of model operation in the second embodiment of the present invention.
FIG. 3 is a schematic diagram of a time period during which the load of the boiler is stable according to a second embodiment of the present invention.
Detailed Description
The present invention will be further described with reference to the following examples. The following examples are set forth merely to aid in the understanding of the invention. It should be noted that, for a person skilled in the art, several modifications can be made to the invention without departing from the principle of the invention, and these modifications and modifications also fall within the protection scope of the claims of the present invention.
Example one
The embodiment of the application provides a coal-fired boiler soot blowing optimization method for complementing pollution factors based on a time series prediction algorithm, which comprises the following steps:
step 2, cleaning data according to the upper limit and the lower limit of the pollution factor, the boiler load, the quality of the data of the working medium measuring points and other factors, and removing abnormal data;
step 3, grabbing in a steady-state working condition time period;
step 3.1, grabbing a time period which is not influenced by soot blowing: judging a soot blowing time period by using a soot blower action current measuring point, a soot blower starting instruction measuring point and a soot blower exit instruction measuring point, and capturing the soot blowing time period; introducing the stable time t after soot blowing, and determining a soot blowing time period and an unstable time period influenced by soot blowing, wherein the rest time period is a time period not influenced by soot blowing;
step 3.2, capturing during the stable time period of the boiler load;
step 3.2.1, screening all boiler load data at a certain time point and in a period tau thereafter to obtain the highest load value D in the period taumaxAnd a minimum load value DminCalculating the load fluctuation Δ D within the time period τ:
ΔD＝Dmax-Dmin (2)
in the above formula Dmax、DminAnd Δ D is in units of t/h or MW;
when the load fluctuation delta D in the time period tau meets the following formula (3), the time period tau is the working condition of stable boiler load;
ΔD≤x*Ded (3)
in the above formula, x is the proportion of the preset normal fluctuation range of the load in the rated load; dedThe rated load of the boiler is t/h or MW;
3.2.2, screening the boiler load data at all time points and in the time period tau after the time points by a method of moving a time window according to the step 3.2.1 to obtain a boiler load stable time period;
and 3.3, capturing in a steady state working condition time period: taking the intersection part of the time period which is not influenced by soot blowing and the boiler load stable time period obtained in the step 3.1 as a steady-state working condition time period, wherein the non-intersection part is an unsteady-state working condition time period;
step 4, complementing the pollution factors in the unsteady time period by using a time sequence prediction algorithm;
step 4.1, calculating the pollution factor in the time period of the steady-state working condition by adopting the method for calculating the pollution factor of the heating surface in the step 1;
step 4.2, complementing and calculating the pollution factors in the unsteady state working condition time period by a time prediction algorithm; the time series prediction algorithm adopts a logistic regression model of prophet algorithm:
F(t)＝g(t)+s(t)+h(t) (4)
in the above formula, t is time; f (t) is a function of the time variation of the pollution factor; g (t) represents a growth function for fitting aperiodic variations; s (t) is used to indicate periodic changes, such as weekly, yearly, seasonal, etc.; h (t) shows changes caused by special reasons such as holidays, festivals and the like; i.e. the time sequence is divided into a superposition of 3 sections (soot blowing period, non-steady state period affected by soot blowing, period unaffected by soot blowing); for the time series prediction of the pollution factors, no obvious periodic change and obvious holiday change exist, so that the influence of s (t) and h (t) can be ignored;
the growth of g (t) adopts a logistic regression function model, and the logistic regression function model is shown as the following formulas (5) and (6):
in the above formulae (5) and (6), t isTime; c (t) is the saturation value (carrying capacity); k is the swell ratio; m is a bias parameter; function a (t) represents an indicative function of the time node as a function of the growth rate k; delta is indicated at the time stamp sjThe amount of change in the growth rate; sjThe time at which the increase rate changes at the jth transition point; gamma is sjThe smoothing offset of (d); a isj(t) is an indicative function of the time node at which the jth transition point varies with the growth rate k at time t;
4.3, presetting the upper limit and the lower limit of the pollution factor, the time interval of data, a prediction period and time sequence data with a time stamp according to a prophet algorithm model, and supplementing the pollution factor in the unsteady state working condition time period;
and 5, judging whether to perform soot blowing according to the pollution factor change trend.
Example two
On the basis of the first embodiment, the second embodiment of the present application provides an application of the soot blowing optimization method of the first embodiment for completing the pollution factor based on the time series prediction algorithm in the soot blowing optimization process of a 1000MW coal-fired boiler:
first, model training
The process of model training is shown in fig. 1.
the boiler is provided with a low-temperature superheater, a low-temperature reheater inlet section, flue gas temperature online measuring points of all heating surface inlets and outlets of a downstream flue and working medium temperature measuring points of all heating surface inlets and outlets, so that the existing online working medium side parameters and the existing flue gas side parameters are utilized, the influence of radiation heat transfer and convection heat transfer is considered, and the flue gas temperatures of the high-temperature reheater inlet, the high-temperature superheater inlet and the screen type superheater inlet are calculated section by section according to the opposite directions of flue gas flow. Calculating actual heat transfer coefficient and ideal heat transfer coefficient according to the flue gas inlet and outlet temperature of each heating surface, working medium inlet and outlet temperature, flue gas and working medium flow, heating surface structure size and other parameters, and calculating the pollution factor of the heating surface according to the formula (1), namely obtaining a pollution factor calculated value.
In the above formula, KsjIs the actual heat transfer coefficient of the heated surface and has the unit of W/(m)2*K)；KlxIs the ideal heat transfer coefficient of the heated surface and has the unit of W/(m)2K); f is a pollution factor.
Step 2, data cleaning;
and according to factors such as load, upper and lower limits of pollution factors, data quality of relevant smoke and working medium measuring points and the like, cleaning the data, and eliminating abnormal data such as shutdown, measuring point damage and the like. The following data were mainly washed out:
1) the load is less than 0MW or more than 1050 MW;
2) the calculated value of the pollution factor is less than or equal to 0 or more than or equal to 1;
3) and the smoke temperature, the working medium temperature and the working medium flow point have no reading or abnormal reading.
Step 3, grabbing in a steady-state working condition time period;
and 3.1, grabbing in a time period not influenced by soot blowing. And judging the soot blowing time period by using the measuring points of soot blower action current, soot blower starting instruction, soot blower exiting instruction and the like, and simultaneously setting the stable time after soot blowing to be 30min, wherein the rest time period is the time period which is not influenced by soot blowing.
Step 3.2, capturing during the stable time period of the boiler load;
1) screening all boiler load data in a certain time point and a period tau thereafter to obtain the highest load value D in the time periodmaxAnd a minimum load value DminAnd thus the load fluctuation Δ D in the period of time is calculated as shown in equation (2):
ΔD＝Dmax-Dmin (2)
in the above formula Dmax、DminAnd Δ D is in units of t/h or MW;
and delta D is less than or equal to x DedAs a requirement for boiler load stabilization. When the value of tau is smaller and the value of x is larger, correspondingly capturing the obtained load stabilization time periodThe more stages, the worse the actual load stability; conversely, when the value of τ is larger and the value of x is smaller, the number of sections of the load stabilization time period which satisfies the condition is relatively smaller, but the actual load stability of the obtained load stabilization time period is also better. In this embodiment, τ is selected within a range of 10-60 min, and x is selected within a range of 3% -10%.
2) And screening the boiler load data at all time points and within the period tau after the time points by a method of moving a time window according to the method to obtain the working condition period with stable boiler load.
The schematic diagram of the boiler load stabilization time period obtained by screening is shown in fig. 3, wherein a dark curve part, a marked square frame part and a marked oval frame part in the schematic diagram are load stabilization working condition time periods obtained by selecting different values of tau and x (according to the directions of reducing tau and increasing x) and increasing the tau and the x in sequence.
Step 3.3, grabbing in a steady-state working condition time period;
the intersection part of the time period not affected by soot blowing and the working condition time period with stable boiler load is the steady-state working condition time period, and the other time periods are the non-steady-state working condition time periods.
Step 4, complementing the pollution factors in the unsteady time period by using a time sequence prediction algorithm;
and 4.1, calculating the result of the pollution factor in the time period of the steady-state working condition by adopting the method in the step 1.
4.2, the pollution factors in the unsteady state working condition time period are obtained by complementing calculation through a time prediction algorithm; the time series prediction algorithm can adopt, but is not limited to, a logistic regression model of prophet algorithm, and other time series algorithms such as a piecewise function model of prophet algorithm, an ARMA algorithm model and the like can also be used for the calculation of the step. The logistic regression model adopting the prophet algorithm needs to preset the upper and lower limits of the pollution factors, the time interval of data, the prediction period and the time sequence data with the time stamp, so that the pollution factors in the unsteady state working condition time period can be compensated and calculated.
And 4.3, obtaining the pollution factors in all time periods (including steady-state and non-steady-state working conditions).
Step 5, calculating a critical pollution factor and generating a critical pollution factor table;
step 5.1, performing statistical analysis on the historical pollution factors of the heating surface, and setting the pollution factors as minimum pollution factors F when the pollution factors are smaller than or equal to a certain value and are the cleaning working condition of the heating surfacemin。FminThe calculation method of (2) is as follows (8), i.e., the average of all the historical contamination factors minus the standard deviation of 2 times.
And 5.2, calculating the change range of the pollution factors of the heating surface before and after each normal soot blowing in history, and calculating the average value to obtain the pollution factor reduction range delta F of the heating surface after soot blowing.
Step 5.3, calculating the critical contamination factor F as shown in the following formula (7)ljAnd generating a critical pollution factor table.
ΔFi＝Fb,i-Fa,i (7)
Model operation
The process of model operation is shown in figure 2.
The steps 1, 2, 3 and 4 of the model operation process are the same as the model training process.
The step 5 of the model operation process is as follows: and when judging whether the actual pollution factor is larger than the critical pollution factor, if so, judging that soot blowing is necessary on the heating surface, otherwise, continuing to calculate.
Claims (10)
1. A boiler soot blowing optimization method for complementing pollution factors based on a time series prediction algorithm is characterized by comprising the following steps of:
step 1, calculating pollution factors of a heating surface;
step 2, according to the upper limit and the lower limit of the pollution factor, the boiler load and the data quality of the working medium measuring points, cleaning the data and eliminating abnormal data;
step 3, grabbing in a steady-state working condition time period;
step 3.1, grabbing a time period which is not influenced by soot blowing: judging a soot blowing time period by using a soot blower action current measuring point, a soot blower starting instruction measuring point and a soot blower exit instruction measuring point, and capturing the soot blowing time period; introducing the stable time t after soot blowing, and determining a soot blowing time period and an unstable time period influenced by soot blowing, wherein the rest time period is a time period not influenced by soot blowing;
step 3.2, capturing during the stable time period of the boiler load;
and 3.3, capturing in a steady state working condition time period: taking the intersection part of the time period which is not influenced by soot blowing and the boiler load stable time period obtained in the step 3.1 as a steady-state working condition time period, wherein the non-intersection part is an unsteady-state working condition time period;
step 4, complementing the pollution factors in the unsteady time period by using a time sequence prediction algorithm;
and 5, judging whether to perform soot blowing according to the pollution factor change trend.
2. The boiler soot blowing optimization method for complementing pollution factors based on the time series prediction algorithm as claimed in claim 1, wherein the step 1 specifically comprises the following steps:
step 1.1, calculating the inlet flue gas temperature of each heating surface section by section according to the opposite direction of flue gas flow by utilizing the existing on-line working medium side parameters and flue gas side parameters;
step 1.2, calculating actual heat transfer coefficient and ideal heat transfer coefficient of each heating surface according to inlet flue gas temperature, outlet flue gas temperature, working medium inlet and outlet temperature, flue gas flow, working medium flow and structural size of the heating surface;
step 1.3, calculating the pollution factor of the heated surface according to the formula (1):
in the above formula, KsjIs the actual heat transfer coefficient of the heated surface and has the unit of W/(m)2*K)；KlxIs the ideal heat transfer coefficient of the heated surface and has the unit of W/(m)2K); f is a pollution factor.
3. The boiler soot blowing optimization method for complementing pollution factors based on the time series prediction algorithm according to claim 1, characterized in that: the abnormal data removed in the step 2 comprise shutdown abnormal data and measuring point damage abnormal data.
4. The boiler soot blowing optimization method for complementing pollution factors based on the time series prediction algorithm according to claim 1, characterized in that: and 3, performing stable working conditions that soot blowing is performed on the heating surface or soot blowing is just completed and the load of the boiler is stable.
5. The boiler soot blowing optimization method for complementing pollution factors based on the time series prediction algorithm as claimed in claim 1, wherein the step 3.2 comprises the following steps:
step 3.2.1, screening all boiler load data at a certain time point and in a period tau thereafter to obtain the highest load value D in the period taumaxAnd a minimum load value DminCalculating the load fluctuation Δ D within the time period τ:
ΔD＝Dmax-Dmin (2)
in the above formula Dmax、DminAnd Δ D is in units of t/h or MW;
when the load fluctuation delta D in the time period tau meets the following formula (3), the time period tau is the working condition of stable boiler load;
ΔD≤x*Ded (3)
in the above formula, x is the proportion of the preset normal fluctuation range of the load in the rated load; dedThe rated load of the boiler is t/h or MW;
and 3.2.2, screening the boiler load data at all time points and in the time period tau after the time points by a method of moving a time window according to the step 3.2.1 to obtain the stable time period of the boiler load.
6. The boiler soot blowing optimization method for complementing pollution factors based on the time series prediction algorithm according to claim 5, wherein the method comprises the following steps of: and 3.2.1, in the fluctuation proportion range, the boiler is in a load stable working condition.
7. The boiler soot blowing optimization method for complementing pollution factors based on the time series prediction algorithm as claimed in claim 1, wherein the step 4 specifically comprises the following steps:
step 4.1, calculating the pollution factor in the time period of the steady-state working condition by adopting the method for calculating the pollution factor of the heating surface in the step 1;
step 4.2, complementing and calculating the pollution factors in the unsteady state working condition time period by a time prediction algorithm; the time series prediction algorithm adopts a logistic regression model of prophet algorithm:
F(t)＝g(t)+s(t)+h(t) (4)
in the above formula, t is time; f (t) is a function of the time variation of the pollution factor; g (t) represents a growth function for fitting aperiodic variations; s (t) is used to indicate a periodic variation; h (t) indicates changes due to special causes;
the growth of g (t) adopts a logistic regression function model, and the logistic regression function model is shown as the following formulas (5) and (6):
in the above formulas (5) and (6), t is time; c (t) is a saturation value; k is the swell ratio; m is a bias parameter; function a (t) represents an indicative function of the time node as a function of the growth rate k; delta is indicated at the time stamp sjThe amount of change in the growth rate; sjA time of the jth transition point; gamma is sjThe smoothing offset of (d); a isj(t) is an indicative function of the time node at which the jth transition point varies with the growth rate k at time t;
and 4.3, presetting the upper limit and the lower limit of the pollution factor, the time interval of data, the prediction period and the time sequence data with the time stamp according to the prophet algorithm model, and supplementing the pollution factor in the unsteady state working condition time period.
8. The boiler soot blowing optimization method for complementing pollution factors based on the time series prediction algorithm as claimed in claim 1, wherein the step 5 specifically comprises the following steps:
step 5.1, performing statistical analysis on the historical pollution factors of the heating surface, setting the condition that the pollution factors are less than or equal to a fixed numerical value as a cleaning working condition of the heating surface, and defining the fixed numerical value of the pollution factors as a minimum pollution factor Fmin；
Step 5.2, counting the change range of the pollution factors of the heating surface before and after multiple soot blowing, and calculating the average value to obtain the reduction range delta F of the pollution factors of the heating surface after soot blowing:
ΔFi＝Fb,i-Fa,i (7)
in the above formulae (7) to (8), Δ FiThe variation range of the pollution factors of the heating surface before and after the ith soot blowing is obtained; fb,iPollution factors of the heating surface before the ith soot blowing; fa,iThe pollution factor of the heated surface after the ith soot blowing is obtained; n is the number of times of statistics;
step 5.3, calculating the critical pollution factor FljAnd generating a critical pollution factor table;
Flj＝Fmin+ΔF (9)
in the above formula, FminIs the minimum pollution factor FminDelta F is the reduction amplitude of the pollution factor of the heating surface after soot blowing;
step 5.4, judging whether the actual pollution factor is larger than the critical pollution factor, if the actual pollution factor is larger than the critical pollution factor, further judging whether the parameters meet the necessary soot blowing conditions, performing soot blowing when the necessary soot blowing conditions are met, and otherwise, not performing soot blowing; if the actual pollution factor is less than or equal to the critical pollution factor, the critical pollution factor is continuously calculated to generate a critical pollution factor table.
9. The boiler soot blowing optimization method for complementing pollution factors based on time series prediction algorithm as claimed in claim 8, wherein the minimum pollution factor F in step 5.1minAverage of all historical contamination factors minus 2 times the standard deviation of the historical contamination factors:
Fmin＝μ-2σ (10)
in the above formula, μ is the average value of the historical contamination factors, and σ is the standard deviation of the historical contamination factors.
10. The boiler soot blowing optimization method for complementing pollution factors based on the time series prediction algorithm as claimed in claim 8, wherein in step 5.4, a critical pollution factor table under each subdivision condition is generated according to the subdivision conditions of unit load and feedwater flow.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110942851.8A CN113761794B (en) | 2021-08-17 | 2021-08-17 | Boiler soot blowing optimization method for supplementing pollution factors based on time sequence prediction algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110942851.8A CN113761794B (en) | 2021-08-17 | 2021-08-17 | Boiler soot blowing optimization method for supplementing pollution factors based on time sequence prediction algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113761794A true CN113761794A (en) | 2021-12-07 |
| CN113761794B CN113761794B (en) | 2024-05-31 |
Family
ID=78790083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110942851.8A Active CN113761794B (en) | 2021-08-17 | 2021-08-17 | Boiler soot blowing optimization method for supplementing pollution factors based on time sequence prediction algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113761794B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114285032A (en) * | 2021-12-23 | 2022-04-05 | 广东电网有限责任公司 | Power distribution network line load peak prediction method and device, computer equipment and medium |
| CN115510904A (en) * | 2022-09-26 | 2022-12-23 | 天津大学 | Boiler heating surface ash deposition monitoring method based on time sequence prediction |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013206363A (en) * | 2012-03-29 | 2013-10-07 | Hitachi Ltd | Plant control device and thermal power generation plant control device |
| CN103604132A (en) * | 2013-12-06 | 2014-02-26 | 太原理工大学 | System for online monitoring of gathered dust on convection heating surface of boiler |
| CN106322412A (en) * | 2016-08-30 | 2017-01-11 | 上海交通大学 | Coal-fired unit convection heating surface intelligent soot blowing method based on two-dimensional optimization |
| CN108278625A (en) * | 2018-01-19 | 2018-07-13 | 华能国际电力股份有限公司上海石洞口第电厂 | A kind of coal-burning boiler high temperature reheater ash-blowing method |
| CN112283689A (en) * | 2020-10-29 | 2021-01-29 | 西安工业大学 | On-line monitoring system and detection method for accumulated ash on heating surface of coal-fired power station boiler |
| CN112307650A (en) * | 2020-11-27 | 2021-02-02 | 浙江浙能技术研究院有限公司 | Multi-step prediction method for ultra-supercritical boiler heating surface pipe wall overtemperature early warning |
| CN112989694A (en) * | 2021-03-08 | 2021-06-18 | 浙江大学 | Segmented monitoring system and method for ash on heating surface |
-
2021
- 2021-08-17 CN CN202110942851.8A patent/CN113761794B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013206363A (en) * | 2012-03-29 | 2013-10-07 | Hitachi Ltd | Plant control device and thermal power generation plant control device |
| CN103604132A (en) * | 2013-12-06 | 2014-02-26 | 太原理工大学 | System for online monitoring of gathered dust on convection heating surface of boiler |
| CN106322412A (en) * | 2016-08-30 | 2017-01-11 | 上海交通大学 | Coal-fired unit convection heating surface intelligent soot blowing method based on two-dimensional optimization |
| CN108278625A (en) * | 2018-01-19 | 2018-07-13 | 华能国际电力股份有限公司上海石洞口第电厂 | A kind of coal-burning boiler high temperature reheater ash-blowing method |
| CN112283689A (en) * | 2020-10-29 | 2021-01-29 | 西安工业大学 | On-line monitoring system and detection method for accumulated ash on heating surface of coal-fired power station boiler |
| CN112307650A (en) * | 2020-11-27 | 2021-02-02 | 浙江浙能技术研究院有限公司 | Multi-step prediction method for ultra-supercritical boiler heating surface pipe wall overtemperature early warning |
| CN112989694A (en) * | 2021-03-08 | 2021-06-18 | 浙江大学 | Segmented monitoring system and method for ash on heating surface |
Non-Patent Citations (4)
| Title |
|---|
| MACIEJ BUJALSKI 等: "The algorithm of steam soot blowers operation based on the monitoring of fouling factors of heating surfaces of a coal-fired boiler under operating conditions", E3S WEB OF CONFERENCES, vol. 82, 31 December 2019 (2019-12-31), pages 1 - 12 * |
| YUANHAO SHI 等: "A Neural-Network-Based Method for Ash Fouling Prediction of Heat Transfer Surface in Coal-Fired Power Plant Boiler", IEEE ACCESS, vol. 9, 11 August 2021 (2021-08-11), pages 109584 - 109604, XP011871093, DOI: 10.1109/ACCESS.2021.3100145 * |
| 何源 等: "基于时序聚类的吹灰预测模型", 计算机工程, vol. 34, no. 10, 31 May 2008 (2008-05-31), pages 244 - 246 * |
| 姚凯 等, 电站系统工程, vol. 34, no. 6, 30 November 2018 (2018-11-30), pages 24 - 26 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114285032A (en) * | 2021-12-23 | 2022-04-05 | 广东电网有限责任公司 | Power distribution network line load peak prediction method and device, computer equipment and medium |
| CN114285032B (en) * | 2021-12-23 | 2024-05-03 | 广东电网有限责任公司 | Power distribution network line load peak value prediction method and device, computer equipment and medium |
| CN115510904A (en) * | 2022-09-26 | 2022-12-23 | 天津大学 | Boiler heating surface ash deposition monitoring method based on time sequence prediction |
| CN115510904B (en) * | 2022-09-26 | 2023-08-01 | 天津大学 | Boiler heating area ash monitoring method based on time sequence prediction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113761794B (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113761794B (en) | Boiler soot blowing optimization method for supplementing pollution factors based on time sequence prediction algorithm | |
| EP3521748B1 (en) | Dual model approach for boiler section cleanliness calculation | |
| US7383790B2 (en) | Method and apparatus for controlling soot blowing using statistical process control | |
| CN103759277B (en) | Coal-fired power station boiler intelligent ash blowing closed loop control method, device and system | |
| CN109583585B (en) | Construction method of power station boiler wall temperature prediction neural network model | |
| KR890000451B1 (en) | Enhanced sootblowing system | |
| US4466383A (en) | Boiler cleaning optimization with fouling rate identification | |
| CN112283689B (en) | On-line monitoring system and detection method for accumulated ash on heating surface of coal-fired power plant boiler | |
| WO2006086175A2 (en) | Method and apparatus for optimizing operation of a power generating plant using artificial intelligence techniques | |
| CN109654518B (en) | Soot blowing optimization method for heating surface of coal-fired power plant boiler | |
| CN109695892B (en) | Method and device for protecting wall temperature of heating surface of boiler | |
| CN106773955A (en) | A kind of boiler soot-blowing optimizes system and its optimization method | |
| CN112381210B (en) | Coal-fired unit water-cooling wall temperature prediction neural network model | |
| CN110207094A (en) | IQGA-SVR boiler heating surface fouling characteristics discrimination method based on principal component analysis | |
| CN110888403A (en) | Intelligent soot blowing closed-loop control system based on minimum loss boiler convection heating surface | |
| CN109858125A (en) | A kind of fired power generating unit net coal consumption rate calculation method based on radial base neural net | |
| CN116720446B (en) | Method for monitoring thickness of slag layer of water-cooled wall of boiler in real time | |
| Li et al. | Prediction of pollution state of heating surface in coal-fired utility boilers | |
| CN112304657A (en) | Method for dividing key easy-scaling groups of air preheater and monitoring heat exchange efficiency state | |
| CN211854055U (en) | Control system for controlling boiler soot blower | |
| CN113946789B (en) | Method for calculating garbage incineration amount of four-furnace three-machine garbage incineration power plant in real time | |
| CN111242279A (en) | System and method for predicting slagging of hearth of ultra-supercritical pulverized coal boiler | |
| CN113052391B (en) | Boiler heating surface coking on-line prediction method | |
| CN113887116A (en) | Power station boiler dynamic operation main steam temperature delay characteristic modeling method | |
| CN106382842A (en) | Pipe explosion monitoring method and system for cement plant waste heat recovery multi-loop heat exchanger |
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 |