CN110486749B - Thermal power generating unit boiler combustion optimization control method and system - Google Patents
Thermal power generating unit boiler combustion optimization control method and system Download PDFInfo
- Publication number
- CN110486749B CN110486749B CN201910807438.3A CN201910807438A CN110486749B CN 110486749 B CN110486749 B CN 110486749B CN 201910807438 A CN201910807438 A CN 201910807438A CN 110486749 B CN110486749 B CN 110486749B
- Authority
- CN
- China
- Prior art keywords
- boiler
- combustion
- real
- time
- boiler combustion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000002485 combustion reaction Methods 0.000 title claims abstract description 194
- 238000005457 optimization Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000012360 testing method Methods 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000012937 correction Methods 0.000 claims abstract description 11
- 238000007418 data mining Methods 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 15
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 13
- 239000001301 oxygen Substances 0.000 claims description 13
- 229910052760 oxygen Inorganic materials 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000000779 smoke Substances 0.000 claims description 8
- 238000010977 unit operation Methods 0.000 claims description 7
- 239000000446 fuel Substances 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 230000017525 heat dissipation Effects 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 239000003245 coal Substances 0.000 description 27
- 230000006870 function Effects 0.000 description 12
- 239000002956 ash Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 239000002893 slag Substances 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000007774 longterm Effects 0.000 description 7
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 239000010881 fly ash Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 4
- 229910052799 carbon Inorganic materials 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000010304 firing Methods 0.000 description 4
- 230000001105 regulatory effect Effects 0.000 description 4
- 239000007789 gas Substances 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 238000000227 grinding Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012843 least square support vector machine Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 239000000843 powder Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 240000004282 Grewia occidentalis Species 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- RHZUVFJBSILHOK-UHFFFAOYSA-N anthracen-1-ylmethanolate Chemical compound C1=CC=C2C=C3C(C[O-])=CC=CC3=CC2=C1 RHZUVFJBSILHOK-UHFFFAOYSA-N 0.000 description 1
- 239000003830 anthracite Substances 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000003546 flue gas Substances 0.000 description 1
- 239000003077 lignite Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- IJGRMHOSHXDMSA-UHFFFAOYSA-N nitrogen Substances N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23N—REGULATING OR CONTROLLING COMBUSTION
- F23N5/00—Systems for controlling combustion
Abstract
The application relates to a thermal power generating unit boiler combustion optimization control method and a system, comprising the following steps: (1) analyzing and processing historical operating data to obtain a steady-state operating data set; (2) data mining is carried out on the steady-state operation data set, historical optimal combustion efficiency of the boiler under different load working conditions is obtained, and a combustion optimization reference value of the boiler is determined; (3) analyzing and processing the combustion test data, and establishing a boiler combustion model; (4) analyzing and processing the real-time operation data to obtain real-time dynamic operation data sets of the boiler at different operation moments; (5) optimizing the real-time operation data by adopting an optimization algorithm to obtain a real-time control increment; (6) and superposing the operation control reference and the real-time control increment to obtain a combustion optimization control instruction, and performing online correction on the operation state of boiler combustion. The boiler combustion optimization control method has strong adaptability and wide application range, and solves the problem of weak expandability and adaptability of boiler combustion control.
Description
Technical Field
The application belongs to the technical field of information and control, and particularly relates to a thermal power generating unit boiler combustion optimization control method and system.
Background
The energy structure of China is gradually optimized, and the requirements on the improvement of the energy efficiency and the flexibility of the thermal power generating unit, the treatment of emissions and the like are further strengthened. Therefore, power generation enterprises urgently need to excavate the potential of unit operation, improve unit operation efficiency, reduce pollutant discharge, reduce production cost to improve enterprise competitiveness.
To achieve the above objective, boiler combustion optimization techniques are desirable. The method mainly comprises three layers of equipment, operation and control: the method comprises the following steps that (I), combustion adjustment of a boiler is realized through modification of a combustor, an air door, a heating surface and other equipment; secondly, guiding operators to adjust the boiler combustion by detecting important parameters of the boiler combustion on line; and thirdly, on the basis of a Distributed Control System (DCS), combustion optimization of the boiler is realized by adopting an advanced control algorithm or an artificial intelligence technology.
Although the boiler combustion adjustment test can roughly optimize individual equipment and working condition points of a unit, the overall combustion working condition cannot be systematically controlled, and test conditions (such as long-term stable limit load) are often difficult to meet. The boiler equipment is optimized from the control aspect without any transformation, the historical operating data, the combustion test data and the original DCS control logic of the boiler can be fully utilized, the real-time operating state data of the boiler and the advanced control algorithm are combined to automatically and flexibly adjust the unit, the frequent operation of operators can be reduced, and the unit can safely, efficiently and environmentally operate in a wider load operation range. Therefore, the data-driven combustion optimization automatic control technology has the advantages of low investment, low risk and obvious effect, and has great research value and application potential.
At present, closed-loop control of burning key parameters such as grinding outlet temperature, powder feeding rate, air supply quantity and oxygen quantity is usually realized by adjusting the opening degree of equipment such as a primary air door, a secondary air door and an air feeder blade in DCS control logic, the set value of the closed-loop control is usually determined according to boiler plant design parameters or boiler test parameters, and the parameters can be changed along with long-term operation of a unit.
In recent years, research on advanced control technology of combustion optimization is also developed, but the achievements mainly focus on modeling and optimizing methods of a boiler combustion process, the utilization degree of data related to boiler combustion is not enough, and expandability and adaptability are not strong.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method and the system for optimally controlling the boiler combustion of the thermal power generating unit are provided for solving the problems that the operation efficiency of the thermal power generating unit is low, the pollutant emission of boiler combustion is high in the prior art and the problems that the expandability and adaptability of the boiler combustion control are poor at present.
The technical scheme adopted by the invention for solving the technical problems is as follows: a thermal power generating unit boiler combustion optimization control method comprises the following steps:
step 1: collecting historical operation data, combustion test data and real-time operation data of boiler combustion of the thermal power generating unit;
step 2: analyzing and processing the historical operating data, calculating the boiler combustion efficiency corresponding to each historical operating time, and simultaneously performing steady-state detection on the boiler combustion process to obtain boiler operating parameters so as to obtain steady-state operating data sets corresponding to the boilers at different historical operating times;
and step 3: data mining is carried out on the steady-state operation data set to obtain historical optimal combustion efficiency of the boiler under different load working conditions, and the boiler operation state data corresponding to the historical optimal combustion efficiency is a combustion optimization reference value of the boiler;
and 4, step 4: analyzing and processing the combustion test data, extracting a test data set of boiler operation, and establishing a boiler combustion model according to the test data set and a steady-state operation data set;
and 5: analyzing and processing the real-time operation data of boiler combustion, calculating the real-time combustion efficiency of the boiler, and obtaining real-time dynamic operation data sets corresponding to different operation moments of the boiler;
step 6: optimizing the real-time operation data by adopting an optimization algorithm according to the real-time dynamic operation data set and the boiler combustion model to obtain a real-time control increment in the boiler combustion optimization control process;
and 7: and (4) superposing the operation control reference and the real-time control increment obtained in the steps (3) and (6) to obtain a combustion optimization control instruction for online correction of the real-time operation state data of boiler combustion in the unit operation process.
Further, according to the thermal power generating unit boiler combustion optimization control method provided by the application, step 2 includes performing steady-state detection on the boiler combustion process by adopting a piecewise curve fitting method.
Further, according to the thermal power generating unit boiler combustion optimization control method provided by the application, in the step 2 and the step 5, the combustion efficiency of the boiler comprises the following steps of adopting a heat loss method for on-line calculation:
η＝100-q2-q3-q4-q5-q6
wherein eta is the combustion efficiency of the boiler;
q2heat loss due to smoke exhaust;
q3heat loss for chemical incomplete combustion;
q4heat loss due to incomplete combustion of machinery;
q5loss of heat dissipation for the boiler;
q6is the physical heat loss of the ash.
Further, according to the thermal power generating unit boiler combustion optimization control method provided by the application, in the step 4, the boiler combustion model modeling method comprises a modeling method of a least square support vector machine which takes a radial basis function as a kernel function.
Further, according to the thermal power generating unit boiler combustion optimization control method provided by the application, input variables of a boiler combustion model comprise unit load, fuel ash content, fuel volatile matter, low-order calorific value, environment temperature, oxygen content, primary air pressure, opening degree of each layer of secondary air door and opening degree of each layer of burnout air door; and the output variables of the boiler combustion model are boiler combustion efficiency, NOx concentration at a denitration inlet and total power of a fan.
Further, according to the thermal power generating unit boiler combustion optimization control method provided by the application, in the step 4, if large pulse interference is to be suppressed, real-time filtering is performed by using an amplitude limiting filtering method or a median filtering method; if the small-amplitude high-frequency noise is to be suppressed, real-time filtering is performed by adopting an arithmetic mean method, a moving mean method, a weighted moving mean method or a first-order lag method.
Further, according to the thermal power generating unit boiler combustion optimization control method provided by the application, in the step 6, the optimization algorithm comprises a particle swarm algorithm, an ant colony algorithm and a genetic algorithm.
The application also provides a thermal power generating unit boiler combustion optimal control system, includes:
the data collection module is used for collecting historical operation data, combustion test data and real-time operation data of boiler combustion of the thermal power generating unit;
the historical operation data processing module is used for analyzing and processing historical operation data, calculating the boiler combustion efficiency corresponding to each historical operation time, and simultaneously performing stable state detection on the boiler combustion process to obtain stable state operation data sets corresponding to the boiler at different historical operation times;
the combustion test data processing module is used for analyzing and processing combustion test data, extracting a test data set of boiler operation, and establishing a boiler combustion model according to the test data set and a steady-state operation data set;
the real-time operation data processing module is used for analyzing and processing the real-time operation data, calculating the real-time combustion efficiency of the boiler and obtaining real-time dynamic operation data sets corresponding to different operation moments of the boiler;
the optimization processing module is used for optimizing the real-time operation data to obtain a real-time control increment in the boiler combustion optimization control process;
and the online correction module is used for sending a combustion optimization control command and performing online correction on the real-time operation state data of boiler combustion in the unit operation process.
The invention has the beneficial effects that: the method of the invention fully utilizes the steady-state and dynamic operation information of the boiler, is not limited to specific steady-state detection, data processing, model construction and algorithm optimization technology, is suitable for boilers with different combustion types such as front and rear wall opposed firing, four-corner tangential firing, W flame firing and the like, and can optimize the full load range under the normal operation working condition of the unit. The method can be used for online optimization control and can also be used for offline operation reference.
Drawings
The technical solution of the present application is further explained below with reference to the drawings and the embodiments.
FIG. 1 is a flow chart of a method of an embodiment of the present application;
FIG. 2 is a graph of boiler combustion efficiency versus load for an embodiment of the present application;
FIG. 3 is a graph of oxygen versus load for the examples of the present application;
FIG. 4 is a schematic illustration of a primary interface display of a combustion optimization control system according to an embodiment of the present application.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The technical solutions of the present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Examples
The embodiment provides a thermal power generating unit boiler combustion optimization control method, as shown in fig. 1, including:
step 1: multi-source data collection
Collecting historical operating data, combustion test data and real-time operating data of the boiler of the thermal power generating unit;
Calculating different historical operation moments t according to historical operation data of the thermal power generating unit boiler operationi(i-1, 2,3 …) corresponding toBoiler combustion efficiency;
meanwhile, steady-state detection is carried out on the operation process of the thermal power generating unit boiler, and steady-state operation data sets corresponding to different historical operation moments are obtained
The size of the steady state operation data set is continuously increased along with the long-term operation of the thermal power generating unit.
The steady state operation data set comprises different historical operation time tiCorresponding adjustable variable of receivable instruction
Unadjustable quantity of state
And different historical operating times tiCorresponding boiler combustion efficiency
And step 3: establishing boiler combustion optimization control benchmark
Data mining is carried out on steady-state operation data sets corresponding to different historical operation moments to obtain historical optimal combustion efficiency of the boiler under different load working conditions, boiler operation state data points corresponding to the optimal combustion efficiency are obtained, the boiler operation state data corresponding to the moments of the boiler operation state data points are boiler combustion optimization datum reference values, boiler combustion optimization datum curves are obtained, and therefore a control datum for boiler combustion optimization control is obtained;
and 4, step 4: establishing boiler combustion model
According to the combustion test data of the boiler, firstly, data processing is carried out on the combustion test data, a test data set of boiler operation is extracted, and then the data set is combined with a steady-state operation data set to establish a boiler combustion model.
With the long-term operation of the thermal power generating unit and the continuous change of the operation condition, the self-adaptive training and updating of the boiler combustion model can be carried out irregularly by utilizing the long-term accumulated historical steady-state data set, so that the iterative construction and the improvement of the boiler combustion model are realized.
And 5: establishing a real-time dynamic operational data set for a boiler
Collecting real-time operation data of the boiler of the thermal power generating unit in real time, filtering the real-time operation data in real time, calculating the real-time combustion efficiency of the boiler, and obtaining different operation moments tj(j ═ 1,2,3 …) corresponding real-time dynamic operational data sets
Wherein the real-time dynamic operation data set comprises different operation moments tjCorresponding adjustable variable of receivable instruction
Unadjustable quantity of state
And different operating times tjCorresponding boiler combustion efficiency
Step 6: optimization of real-time operating state parameters
And (4) optimizing the real-time running state parameters in the real-time dynamic running data set by combining the real-time dynamic running data set and the boiler combustion model and adopting an optimization algorithm to obtain a real-time control increment of boiler combustion optimization control.
The optimization algorithm of this embodiment adopts a particle swarm algorithm, and in other embodiments, an ant colony algorithm, a genetic algorithm, and the like may also be adopted.
The objective function of the optimizing algorithm comprises boiler combustion efficiency, nitrogen oxide concentration at a denitration inlet and power consumption of each large fan. When the real-time running state parameters are optimized, the boiler combustion efficiency is used as a main optimization target according to the weight in the objective function, and the nitrogen oxide concentration emission and the fan power consumption at the denitration inlet are used as secondary optimization targets.
And 7: real-time running state online correction
And (4) superposing the control reference and the real-time control increment of the boiler combustion optimization control obtained in the steps (3) and (6) to obtain a combustion optimization control instruction for online correction of the real-time operation state data of the boiler combustion in the unit operation process.
The combustion optimization control instruction of the embodiment can be used for performing online correction on real-time operation state data of a boiler in the operation process of the thermal power generating unit after the thermal power generating unit is put into the combustion optimization control mode, and can be displayed on an operation picture to be used as a control reference of an operation operator.
The combustion optimization control mode input conditions comprise that a power supply is normal, communication signals are normal, the regulated quantity is in an automatic state, the regulated equipment has no fault, the load is higher than a stable combustion condition, and a RUN BACK event does not occur; and when any one of the conditions is not met, automatically exiting the combustion optimization control mode.
In a further embodiment, a steady-state detection technology is adopted in the step 2 to perform steady-state detection of the boiler combustion process, and the selectable steady-state detection methods include three types: (1) a steady state detection method based on statistical theory; (2) a steady state detection method based on trend extraction; (3) a steady state detection method based on mechanism analysis.
In the calculation method of the boiler combustion efficiency in the step 2 and the step 5, in one embodiment, the boiler combustion efficiency can be calculated on line by adopting a heat loss method.
The input variables for the boiler combustion efficiency calculation include: the system comprises a smoke discharge excess air coefficient, a smoke discharge temperature, an environment reference temperature, a CO discharge concentration, a coal application base low calorific value, a received base ash content, a part of fly ash in total ash amount in a furnace, a part of slag amount in total ash amount in the furnace, a fly ash carbon content, a slag carbon content, a boiler rated load, an actual boiler load, a fly ash specific heat capacity, a slag specific heat capacity, a furnace cavity discharged slag temperature and a smoke discharge oxygen content.
As an embodiment, step 4 may further adopt a modeling method of an artificial neural network to establish a boiler combustion model. The artificial neural network can adopt a BP network, an RBF network, an ART network, a Hopfield network or a convolution network. In other embodiments, a support vector machine or fuzzy modeling may also be adopted, and the support vector machine may adopt a common support vector machine or a least square support vector machine; the fuzzy modeling may employ a Mamdani fuzzy model or a T-S fuzzy model.
As a further optimized embodiment, the real-time filtering of the real-time operation data in step 5 requires a moderate adjustment of the parameters for different fluctuation amplitudes and fluctuation times. In the embodiment, in order to overcome the large pulse interference, an amplitude limiting filtering method is adopted for real-time filtering, and a median filtering method can be selected in other embodiments; in order to suppress the small-amplitude high-frequency noise, a moving average method is selected for real-time filtering, and in other embodiments, an arithmetic average method, a weighted moving average method or a first-order lag method may also be selected for real-time filtering.
The boiler combustion optimization control method of the application is further described below by taking a certain 600MW coal-fired unit boiler combustion system as an example:
the boiler combustion system of the embodiment adopts a front wall and rear wall opposed firing mode, and 12 low-nitrogen burners are respectively arranged on the front wall and the rear wall in three layers. 12 over-fire air nozzles are oppositely arranged on the uppermost layers of the front wall and the rear wall. The powder process system is designed into six medium-speed mills, and each mill corresponds to a layer of combustor on the front wall or the rear wall.
According to the combustion optimization control architecture shown in fig. 1, part of key technologies are externally arranged in an independent controller, and data communication is performed with the DCS in a reliable manner, so as to realize the combustion optimization control function.
The optimization control method of the embodiment is specifically as follows:
step 1, establishment of steady state operation data set
In the process of processing historical operating data, a piecewise curve fitting method is adopted to perform steady state detection in the boiler combustion process, so that the influence of data noise can be well overcome.
And calculating the boiler combustion efficiency corresponding to different historical operation moments according to historical operation data, and performing filtering processing on the boiler combustion efficiency by adopting a sliding average method with different time scales before the boiler combustion efficiency is calculated.
Through the steps, a boiler steady-state operation state data set is obtained, and the adjustable variables of the steady-state operation state data set comprise the opening degree of each layer of secondary air doors, the opening degree of a burnout air door, the swing angle of a combustor, the starting and stopping state of a coal mill, the oxygen amount, the coal feeding amount of each layer, the primary air pressure, the primary air amount, the differential pressure of an air box and the outlet temperature of the coal mill.
The unadjustable state quantity of the steady-state operation state data comprises unit load, coal quality parameters, environment temperature, furnace outlet temperature, main steam flow, main steam pressure, reheat steam temperature and reheat steam pressure.
In the embodiment, the boiler combustion efficiency is calculated on line by adopting a heat loss method, and the calculation formula is as follows:
η＝100-q2-q3-q4-q5-q6
q2＝(k1+k2αpy)(tpy-tref)/100
q3＝k3Φ(CO)/9net，ar
in the formula: eta is the combustion efficiency of the boiler;
q2heat loss due to smoke exhaust;
q3heat loss for chemical incomplete combustion;
q4heat loss due to incomplete combustion of machinery;
q5loss of heat dissipation for the boiler;
q6physical heat loss of ash,%;
k1、k2as a coefficient, k for bituminous and anthracite coals1＝0.4，k2For lignite, k ═ 3.551＝1.0，k2＝3.7；
αpyThe excess air coefficient of the exhaust smoke;
tpyis the temperature of the exhaust gas;
trefambient reference temperature, deg.C;
k3is a coefficient;
phi (CO) is the emission concentration of CO,%;
Qnet,arthe coal-fired application base low-grade heating value is kJ/kg;
Asdto receive basal ash,%;
αfhand alphalzThe amount of fly ash and the amount of slag account for the total amount of ash in the furnace;
Cfh,cand Clz,cThe carbon content of fly ash and the carbon content of slag are percent respectively;
qeis the heat dissipation loss under the rated load of the boiler,%;
Dedthe rated load of the boiler;
d is the actual load of the boiler, MW;
cfhis a sum of clzRespectively is the specific heat capacity of fly ash and the specific heat capacity of slag, kJ/(kg.K);
tlzthe temperature of the slag discharged from the hearth is DEG C;
Φ(O2) Oxygen content in flue gas,%.
Oxygen content phi (O) of exhausted smoke2) The calculation formula of (a) is as follows:
in the formula: delta is the air leakage rate of the air preheater,%; phieco(O2) To saveOxygen content at the outlet of the coal device,%.
Based on the long-term operation data of a certain unit, the relation between the boiler combustion efficiency and the load is shown in figure 2. It can be seen that the combustion efficiency of the boiler shows a trend of increasing before decreasing with increasing load, and reaches the highest value at intermediate load. The highest boiler combustion efficiency under different load working conditions can be obtained along the upper envelope line of the data points in the graph, so that data points enabling the boiler to operate optimally can be determined, and each state data of the time of the data points is the combustion optimization state reference value.
Identifying the coal quality: firstly, all coal quality test data of nearly two years are counted, main operation parameters (such as load, main steam temperature, main steam pressure, main steam flow, hearth temperature, exhaust gas temperature and the like) related to the coal quality are mined through correlation analysis, the coal quality is divided into more than ten sample models, and a coal quality identification module is established based on a sample model set. In the operation process, if the identified coal quality parameters are similar to the parameters in a certain sample, the system automatically inputs the coal quality parameters in the sample model into an efficiency calculation formula; if the identified coal quality parameters are different from the parameters in all samples too much, the system selects the sample coal quality parameters closest to the identified coal quality parameters to input an efficiency calculation formula, sends a new coal sample alarm to remind operators to confirm, and when all the sample parameters are confirmed to be inconsistent with the new test report, the parameters in the test report need to be manually input into the system, and the system automatically updates a sample model set.
The characteristic running state and the coal type information of the boiler are identified from the historical data by improving methods such as a least square method, a maximum likelihood method and the like, and the combustion process of the boiler is adjusted on line according to the characteristic running state and the coal type information. Firstly, the coal for boiler combustion can be identified as a plurality of characteristic models by correlating data such as load, main steam pressure, hearth temperature, exhaust gas temperature, coal feeder outlet temperature, coal consumption calculation and the like, so as to correct adjustable quantities such as coal feeding quantity, primary air quantity, grinding outlet temperature and the like. Secondly, the time for starting and stopping the coal mill and the combustion stability of high load and low load can be judged through main operating parameters (such as load and main steam pressure) of the boiler, and further combustion optimization parameters and limit values are adjusted. And thirdly, the running state of each large fan and the blockage condition of the air preheater can be respectively judged by analyzing the power loss of each large fan and the pressure difference between the inlet and the outlet of the air preheater by combining the running state (such as air pressure) of the boiler.
As shown in FIG. 3, the relationship between oxygen amount and load is shown, and it can be seen from the graph that as the load increases, the oxygen amount is in a descending trend, and the descending range is changed from large to small, and the oxygen amount is kept stable in a certain range (3% -4%) after the load is higher than 500 MW.
Coal quality can be identified through data mining, a combustion optimization reference curve can be obtained according to historical highest combustion efficiency data points under various load working conditions, and a control reference of boiler combustion optimization control is determined.
And step 3: establishing boiler combustion model
Modeling is performed by using an LSSVM (least squares support vector machine) method using a radial basis function as a kernel function.
The model input variables comprise unit load, fuel ash content, fuel volatile, low-order calorific value, environmental temperature, oxygen content, primary air pressure, opening degree of each layer of secondary air door, opening degree of each layer of burnout air door and the like.
And the model output variables are the boiler combustion efficiency, the NOx concentration at the denitration inlet and the total power of the fan.
By using the long-term accumulated historical steady-state data set, the model can be irregularly and adaptively trained and updated.
And 4, step 4: optimization of real-time operating state parameters
When the real-time running state parameters are optimized, the boiler combustion efficiency is used as a main optimization target according to the weight in the objective function, and the NOx emission and the fan power consumption are used as secondary optimization targets. The optimization method is based on a standard particle swarm optimization algorithm, quadratic decreasing processing is carried out on the rate inertia weight (0.4-0.9) along with the increase of the number of iterations, the linear change interval of a local acceleration factor (from large to small) and a global acceleration factor (from small to large) is (0.5,2.5), and the initial position of the particle is based on a corresponding chaotic sequence of Logistic mapping.
In addition, the optimized real-time control increment is subjected to the amplitude limiting processing, and the amplitude limiting range is increased along with the increase of real-time power.
Step 5, correcting the real-time running state on line
The control reference and the real-time control increment of boiler combustion optimization control are superposed to obtain a combustion optimization control instruction, and the combustion optimization control instruction can be output to an on-line control system through a undisturbed switching module and a safety control module after being put into a combustion optimization control mode to perform on-line correction on real-time operation state data of a boiler in the operation process of a unit on the one hand, and can be displayed on an operation picture to be used as a control reference of an operation operator on the other hand.
The combustion optimization control mode input conditions comprise that a power supply is normal, a communication signal is normal, a regulated quantity is in an automatic state, a regulated device has no fault, a load is higher than a stable combustion condition, and a RUN BACK event does not occur; when any one of the conditions is not met, combustion optimization is automatically exited. The judgment conditions of the communication signal abnormality include 0/1 that the stop time of the heartbeat signal is long enough, the holding time of the signal which should continuously change is long enough, and a hardware fault signal. When the inter-system communication is abnormal, the signal output from the combustion optimization system to the operation control system needs to be maintained so as to prevent the key instruction in the operation control system from being mistakenly set to zero.
The undisturbed switching means that the control command cannot jump at the moment of switching into or out of the combustion optimization control mode; on one hand, the continuity of the signals between the systems needs to be ensured, and on the other hand, a logic control mode of mutual tracking of a manual instruction and an automatic instruction is adopted.
The safety control module is used for performing increment amplitude limitation and change rate limitation on a command signal input from the combustion optimization system in the control logic of the real-time control system so as to prevent the risk of combustion instability caused by improper control.
Fig. 4 is a main screen of the combustion optimization control, and the opening of each secondary air door and the corresponding parameters such as the amount of coal supplied and the amount of air flow are displayed on the screen in accordance with the layout in the furnace. On the one hand, optimized target values and actual values of oxygen amount, boiler efficiency, NOx concentration at a denitration outlet/inlet and CO emission concentration are displayed above the picture for operators to refer to; on the other hand, main boiler combustion parameters such as air quantity, coal consumption, fan power consumption and the like are displayed so as to reflect the boiler combustion operation state in real time.
In addition, dynamic legends such as "input/output", "parameter configuration", "optimization curve" layer damper icons and optimization buttons can be clicked on the screen to enter a specific operation panel or screen.
In light of the foregoing description of the preferred embodiments according to the present application, it is to be understood that various changes and modifications may be made without departing from the spirit and scope of the invention. The technical scope of the present application is not limited to the contents of the specification, and must be determined according to the scope of the claims.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Claims (8)
1. A thermal power generating unit boiler combustion optimization control method is characterized by comprising the following steps:
step 1: collecting historical operation data, combustion test data and real-time operation data of boiler combustion of the thermal power generating unit;
step 2: analyzing and processing the historical operating data, calculating the boiler combustion efficiency corresponding to each historical operating time, and simultaneously performing steady-state detection on the boiler combustion process to obtain boiler operating parameters so as to obtain steady-state operating data sets corresponding to the boilers at different historical operating times;
and step 3: data mining is carried out on the steady-state operation data set to obtain historical optimal combustion efficiency of the boiler under different load working conditions, and the boiler operation state data corresponding to the historical optimal combustion efficiency is a combustion optimization reference value of the boiler;
and 4, step 4: analyzing and processing the combustion test data, extracting a test data set of boiler operation, and establishing a boiler combustion model according to the test data set and a steady-state operation data set;
and 5: analyzing and processing the real-time operation data of boiler combustion, calculating the real-time combustion efficiency of the boiler, and obtaining real-time dynamic operation data sets corresponding to different operation moments of the boiler;
step 6: optimizing the real-time operation data by adopting an optimization algorithm according to the real-time dynamic operation data set and the boiler combustion model to obtain a real-time control increment in the boiler combustion optimization control process;
and 7: and (4) superposing the operation control reference and the real-time control increment obtained in the steps (3) and (6) to obtain a combustion optimization control instruction for online correction of the real-time operation state data of boiler combustion in the unit operation process.
2. The thermal power generating unit boiler combustion optimization control method according to claim 1, characterized in that step 2 includes performing steady-state detection of the boiler combustion process by using a piecewise curve fitting method.
3. The thermal power generating unit boiler combustion optimization control method according to claim 1, wherein in the step 2 and the step 5, the combustion efficiency of the boiler comprises online calculation by a heat loss method, specifically:
η＝100-q2-q3-q4-q5-q6
wherein eta is the combustion efficiency of the boiler;
q2heat loss due to smoke exhaust;
q3heat loss for chemical incomplete combustion;
q4heat loss due to incomplete combustion of machinery;
q5loss of heat dissipation for the boiler;
q6is the physical heat loss of the ash.
4. The thermal power generating unit boiler combustion optimization control method according to claim 3, wherein in the step 4, the modeling method of the boiler combustion model comprises a modeling method using a least squares support vector machine with a radial basis function as a kernel function.
5. The thermal power generating unit boiler combustion optimization control method according to claim 4, wherein the input variables of the boiler combustion model include unit load, fuel ash, fuel volatile matter, low calorific value, ambient temperature, oxygen amount, primary air pressure, opening degree of each layer of secondary air doors, and opening degree of each layer of burnout air doors; and the output variables of the boiler combustion model are boiler combustion efficiency, NOx concentration at a denitration inlet and total power of a fan.
6. The thermal power generating unit boiler combustion optimization control method according to claim 1, wherein in the step 5, if large pulse interference is to be suppressed, real-time filtering is performed by using a limiting filtering method or a median filtering method; if the small-amplitude high-frequency noise is to be suppressed, real-time filtering is performed by adopting an arithmetic mean method, a moving mean method, a weighted moving mean method or a first-order lag method.
7. The thermal power generating unit boiler combustion optimization control method according to claim 1, wherein in step 6, the optimization algorithm includes a particle swarm algorithm, an ant colony algorithm and a genetic algorithm.
8. A combustion optimization control system adopting the thermal power generating unit boiler combustion optimization control method according to any one of claims 1 to 7, characterized by comprising:
the data collection module is used for collecting historical operation data, combustion test data and real-time operation data of boiler combustion of the thermal power generating unit;
the historical operation data processing module is used for analyzing and processing historical operation data, calculating the boiler combustion efficiency corresponding to each historical operation time, and simultaneously performing stable state detection on the boiler combustion process to obtain stable state operation data sets corresponding to the boiler at different historical operation times;
the combustion test data processing module is used for analyzing and processing combustion test data, extracting a test data set of boiler operation, and establishing a boiler combustion model according to the test data set and a steady-state operation data set;
the real-time operation data processing module is used for analyzing and processing the real-time operation data, calculating the real-time combustion efficiency of the boiler and obtaining real-time dynamic operation data sets corresponding to different operation moments of the boiler;
the optimization processing module is used for optimizing the real-time operation data to obtain a real-time control increment in the boiler combustion optimization control process;
and the online correction module is used for sending a combustion optimization control command and performing online correction on the real-time operation state data of boiler combustion in the unit operation process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910807438.3A CN110486749B (en) | 2019-08-29 | 2019-08-29 | Thermal power generating unit boiler combustion optimization control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910807438.3A CN110486749B (en) | 2019-08-29 | 2019-08-29 | Thermal power generating unit boiler combustion optimization control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110486749A CN110486749A (en) | 2019-11-22 |
| CN110486749B true CN110486749B (en) | 2020-10-30 |
Family
ID=68555040
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910807438.3A Active CN110486749B (en) | 2019-08-29 | 2019-08-29 | Thermal power generating unit boiler combustion optimization control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110486749B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111477284B (en) * | 2020-04-02 | 2021-01-15 | 盐城工学院 | Interactive cement production simulation method |
| CN111596548B (en) * | 2020-05-29 | 2023-04-07 | 华润电力技术研究院有限公司 | Boiler secondary air regulating and controlling method, device, equipment and medium |
| CN112058079A (en) * | 2020-09-03 | 2020-12-11 | 西安热工研究院有限公司 | SCR inlet NO based on index prediction modelXConcentration prediction system and method |
| CN112346363A (en) * | 2020-10-13 | 2021-02-09 | 北京京东尚科信息技术有限公司 | Equipment control method and device |
| CN112564100B (en) * | 2020-12-03 | 2023-02-07 | 国网山东省电力公司电力科学研究院 | Method and system for evaluating maximum output of thermal power generating unit in real time based on differential pressure of air preheater |
| CN113266843B (en) * | 2021-04-08 | 2022-08-30 | 华中科技大学 | Combustion optimization method, system and device for coal-fired boiler |
| CN113266833B (en) * | 2021-04-15 | 2022-08-23 | 华中科技大学 | Combustion optimization method, system and device of garbage incinerator |
| CN113391615B (en) * | 2021-05-10 | 2024-04-02 | 中国大唐集团科学技术研究院有限公司西北电力试验研究院 | Variable time pulse algorithm for probability statistics |
| CN113467392B (en) * | 2021-06-18 | 2024-03-26 | 中国大唐集团科学技术研究院有限公司中南电力试验研究院 | Open-loop combustion control optimization method for coal-fired boiler |
| CN113834092B (en) * | 2021-10-12 | 2023-02-14 | 中国矿业大学 | Combustion optimization control method for gas-fired boiler |
| CN115459810B (en) * | 2022-11-11 | 2023-04-28 | 北京智芯微电子科技有限公司 | Pulse interference suppression method, device, chip and equipment for power line carrier communication |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102679391A (en) * | 2012-05-21 | 2012-09-19 | 常州市新港热电有限公司 | Combustion online optimizing method of boiler |
| KR20160104481A (en) * | 2015-02-26 | 2016-09-05 | 두산중공업 주식회사 | System for controlling optimized combustion on boiler |
| CN105974793B (en) * | 2016-05-04 | 2018-07-31 | 华中科技大学 | A kind of power boiler burning intelligent control method |
| CN106773669B (en) * | 2016-11-21 | 2019-11-05 | 华北电力大学（保定） | A kind of fired power generating unit control method for coordinating of fuel value real-time adaptive correction |
| CN109519957B (en) * | 2018-09-29 | 2019-11-12 | 东南大学 | A kind of ultra-supercritical boiler closed loop optimized control method of combustion |
| CN109670629B (en) * | 2018-11-16 | 2021-09-07 | 浙江蓝卓工业互联网信息技术有限公司 | Coal-fired boiler thermal efficiency prediction method based on long-short term memory neural network |
-
2019
- 2019-08-29 CN CN201910807438.3A patent/CN110486749B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110486749A (en) | 2019-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110486749B (en) | Thermal power generating unit boiler combustion optimization control method and system | |
| US8515582B2 (en) | Control system for operation of a fossil fuel power generating unit | |
| CN103576655B (en) | A kind of power boiler burning subspace modeling and Multipurpose Optimal Method and system | |
| CN103322547B (en) | Boiler control and combustion optimization method | |
| EP1921280B1 (en) | Systems and methods for multi-level optimizing control systems for boilers | |
| CN101556038B (en) | Optimization control system for stable operation and economical combustion of circulating fluidized-bed boiler | |
| CN110260356B (en) | Energy-saving control method of fluidized bed boiler | |
| CN105276611A (en) | Adjustment and optimization method and system for combustion of power plant boiler | |
| CN111306572B (en) | Intelligent combustion optimizing energy-saving control system for boiler | |
| CN104061588A (en) | Low-nitrogen combustion control method and system based on secondary air door air regulation control | |
| CN112628712A (en) | Secondary air closed-loop optimization control system based on air door resistance coefficient | |
| CN110762540A (en) | Combustion decision method and automatic combustion control method and system for garbage incinerator | |
| CN106168381A (en) | The control system of boiler combustion, method and apparatus | |
| CN105605609A (en) | Thermal power plant boiler combustion oxygen amount optimizing method | |
| CN110699502B (en) | Method for high-precision prediction of gas consumption of blast furnace hot blast stove | |
| CN103870877B (en) | A kind of boiler combustion intelligent control method based on neutral net | |
| CN108488831B (en) | Boiler combustion control system and method | |
| CN106873377A (en) | Coke oven heating-combustion process fire path temperature Automatic adjustment method under uncertain disturbance | |
| TWI691821B (en) | Operating condition evaluation device, operating condition evaluation method, and boiler control system | |
| CN202511321U (en) | Chain boiler combustion specialist and self-optimalizing control system based on information fusion technology | |
| WO2022252414A1 (en) | Coal-air synchronous dynamic coordinated control method for coal-fired unit | |
| CN211526443U (en) | Automatic combustion control system of garbage incinerator | |
| JP7374590B2 (en) | KPI improvement support system and KPI improvement support method | |
| Zhao et al. | Modeling and optimization of efficiency and NOx emission at a coal-fired utility boiler | |
| CN111736637A (en) | Steam temperature control system and method based on hearth temperature measurement |
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 |