CN109325294A - A kind of evidence characterization construction method of fired power generating unit air preheater performance state - Google Patents
A kind of evidence characterization construction method of fired power generating unit air preheater performance state Download PDFInfo
- Publication number
- CN109325294A CN109325294A CN201811116474.7A CN201811116474A CN109325294A CN 109325294 A CN109325294 A CN 109325294A CN 201811116474 A CN201811116474 A CN 201811116474A CN 109325294 A CN109325294 A CN 109325294A
- Authority
- CN
- China
- Prior art keywords
- air preheater
- performance
- state
- air
- performance state
- 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
- 238000012512 characterization method Methods 0.000 title claims abstract description 19
- 238000010276 construction Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 49
- 230000008569 process Effects 0.000 claims abstract description 32
- 239000000779 smoke Substances 0.000 claims description 16
- 239000003546 flue gas Substances 0.000 abstract description 25
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 abstract description 19
- 239000007789 gas Substances 0.000 abstract description 3
- 239000003517 fume Substances 0.000 abstract 1
- 230000008676 import Effects 0.000 abstract 1
- 230000007704 transition Effects 0.000 description 12
- 239000003245 coal Substances 0.000 description 7
- 238000010438 heat treatment Methods 0.000 description 6
- 230000008021 deposition Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007789 sealing Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000007418 data mining Methods 0.000 description 3
- 239000000428 dust Substances 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000007664 blowing Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 239000004071 soot Substances 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000921 elemental analysis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004868 gas analysis Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000011541 reaction mixture Substances 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E20/00—Combustion technologies with mitigation potential
- Y02E20/34—Indirect CO2mitigation, i.e. by acting on non CO2directly related matters of the process, e.g. pre-heating or heat recovery
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Computer Hardware Design (AREA)
- Pure & Applied Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Computational Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Quality & Reliability (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Computation (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Air Supply (AREA)
Abstract
This application provides a kind of evidences of fired power generating unit air preheater performance state to characterize construction method, which comprises according to predetermined period obtain unit load, flue gas pressure drop, fume side and air wide pre. drop, exhaust gas temperature, air preheater outlet air themperature and air preheater import air themperature data sample；The set of data samples that air preheater is in quasi-steady state process is obtained from the sample；Calculate the initial classes heart of each performance state of the set of data samplesAccording to the initial classes heart of each performance state, the typical performance regimes in each performance state are counted；Calculate the class heart of each typical performance regimesWith the class heart of transiting performance stateCalculate the confidence level that data sample is subordinate to each performance state；Construct air preheater performance state evidence characterization.It is capable of handling inaccurate, unascertained information, can effectively describe air preheater performance from a state to the evolution process of other states.
Description
Technical Field
The application relates to the technical field of thermal power unit air preheater equipment, in particular to an evidence representation construction method for a performance state of a thermal power unit air preheater.
Background
The air preheater is one of main auxiliary equipment of the thermal power generating unit, which improves the heat exchange performance of the boiler and reduces the heat loss, and the quality of the state of the air preheater has important influence on the economy and the safety of the thermal power generating unit. Particularly in recent years, accidents of thermal power generating units frequently occur due to abnormal states of air preheaters, and the state degradation of the thermal power generating units has a great influence on the energy efficiency of the units. In order to avoid the influence on the use of the thermal power generating unit caused by the abnormal state of the air preheater, the state of the air preheater needs to be supervised. But currently there is a lack of effective supervision of its status, mainly for the following reasons: firstly, due to the problems of detection cost or instruments and the like, the parameters related to the state of the system have inaccuracy and uncertainty; secondly, the method for detecting and diagnosing the state is not perfect.
Disclosure of Invention
The evidence characterization construction method for the performance state of the air preheater of the thermal power unit is used for constructing the evidence characterization of the performance state of the air preheater of the thermal power unit, can process inaccurate and uncertain information, and can effectively describe the evolution process of the performance of the air preheater from one state to other states.
The application provides an evidence characterization construction method for the performance state of an air preheater of a thermal power generating unit, which comprises the following steps:
acquiring data samples of unit load, smoke pressure drop, smoke side and air side pressure drop, smoke exhaust temperature, air temperature at an outlet of an air preheater and air temperature at an inlet of the air preheater according to a preset period;
acquiring a data sample set of the air preheater in a quasi-steady state process from the samples;
computing an initial centroid for each performance state of the set of data samples
According to the initial class centers of the performance states, typical performance states in the performance states are counted;
computing the class centers of typical performance statesAnd class of transitional performance states
Calculating the credibility of each performance state to which the data sample belongs;
and constructing an evidence representation of the performance state of the air preheater.
Optionally, in the above method, acquiring a data sample set of the air preheater in a quasi-steady-state process from the sample includes:
setting a time step K, and when the K is more than or equal to the K, enabling the air preheater to be in a quasi-steady-state process;
data sample set X of air preheater in quasi-steady state processl：Xl＝{Xk||xj,k+1-xj,k|≤Δj,j＝1,2,3,4,5,6,k＝1,2,3,…,Nl}，NlIs the data sample collected during the first quasi-steady state.
Optionally, in the above method, an initial centroid of each performance state of the data sample set is calculatedThe method comprises the following steps:
wherein,is XlThe k-th data sample in (a), are each XlMedium maximum and minimum values.
Optionally, in the foregoing method, according to the initial class center of each performance state, counting a typical performance state in each performance state includes:
calculating Euclidean distance of initial class center of each adjacent performance state
When in useIf ε is a given constant, then ω is considered to bekAnd { omega } andlmerging the two types of data samples in the same performance state;
Xl←Xk∪Xl，Nl←Nl+Nkl ═ L-1; repeating the above operations until no satisfaction can be foundClass (c); finally, c typical performance states [ omega ] different from each other are obtainedl},l＝1,2,…,c。
Optionally, in the above method, the class center of each typical performance state is calculatedAnd class of transitional performance statesThe method comprises the following steps:
class hearts of typical performance statesClass hearts of transitional performance states
The evidence characterization construction method for the performance state of the air preheater of the thermal power unit is used for constructing the evidence characterization of the performance state of the air preheater of the thermal power unit based on mechanism analysis and operation data mining, and the method for describing the performance state of the air preheater by adopting the evidence can process inaccurate and uncertain information and can effectively describe the evolution process of the performance of the air preheater from one state to other states (including a transition state).
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without any creative effort.
Fig. 1 is a structural flow chart of an evidence characterization construction method for a thermal power unit air preheater performance state provided in an embodiment of the present application;
FIG. 2 is a graph of sampled data in an example provided by an embodiment of the present application;
fig. 3 is a diagram illustrating an example of steady-state process determination provided in an embodiment of the present application;
FIG. 4 is a diagram illustrating exemplary class centers for typical performance states and transition states provided by an embodiment of the present application;
fig. 5 is a diagram of an example of an evidence construction result provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The air preheater of the thermal power generating unit utilizes the heat of the flue gas at the tail part of the boiler to heat the air required by the combustion of the boiler (the air preheater can be divided into a heat transfer type and a heat accumulation type according to a heat transfer mode) so as to achieve the purposes of recovering the heat of the flue gas, reducing the temperature of the discharged flue gas and improving the efficiency of the boiler.
For an air preheater, the indexes of air leakage and dust deposition degree are reduced under given working conditions, and the avoidance of low-temperature corrosion is an important index for measuring the working performance of the air preheater.
(1) Air preheater rationale:
the main indexes influencing the working performance of the air preheater of the thermal power generating unit are the air leakage rate, the dust deposition degree index and the lowest surface temperature of a heating surface. Wherein, the air leakage mainly comes from the direct air leakage of the air preheater. Thus, these three indices can be determined by the following relationships.
In the formula (1), G is the direct air leakage rate and the unit is t/h
In the formula (1), a is the air leakage coefficient and has no dimensional quantity
In the formula (1), A is the total area of the sealing gap and has a unit of m2
In the formula (1), g is the acceleration of gravity in m/s2
In the formula (1), ρaIs the air density in kg/m3
In the formula (1), Δ p is a pressure difference between the smoke side and the air side in MPa
In the formula (1), air density ρaIs substantially unchanged. The air leakage coefficient a depends on the structure of the air preheater equipment (such as the sealing weight, the sealing form and the like), and the air leakage coefficient and the sealing gap area of the equipment determined by the structure are basically kept unchanged. Furthermore, the pressure difference between the flue gas side and the air side is determined by the resistance of the boiler system. The resistance of the system depends on the overall design condition of the boiler (coal mill model, burner type, arrangement of the heating surface of the boiler and the like) and the soot blowing of the heating surface of the boiler during operation (the primary air pressure and the secondary air volume are timely adjusted according to the coal type, the unit load, the combination mode of the coal mills and the like to strengthen the soot blowing).
In the formula (2), λ is an index of degree of dust deposition
In the formula (2), Δ pyIs the flue gas pressure drop of the air preheater with the unit of MPa
In the formula (2), VyIs the volume of flue gas, in m3
In formula (2), GyIs the mass of the smoke in kg
In the formula (2), BjFor calculating the fuel quantity, the unit is t/h
In the formula (2), θpyThe smoke temperature is the unit of DEG C
In the formula (2), K is a constant and is a dimensionless quantity
In the formula (2), the amount of fuel BjThe calculation of (2) requires unit load, industrial analysis data of fire coal, flue gas analysis data and the like; mass G of flue gasyAnd flue gas volume VyThe calculation of (a) requires, in addition to the excess air factor a, also the elemental analysis data of the coal.
In addition, the lower the temperature of the heated surface of the air preheater, the more susceptible to low temperature corrosion. The lowest surface temperature can be determined by the following relationship.
In the formula (3), θpyThe smoke temperature is the unit of DEG C
In formula (3), tlkIs the cold air temperature in deg.C
In the formula (3), ak，ayRespectively air side and smoke sideHeat release coefficient in units of w/(m)2.k)
In formula (3), τk，τyThe residence time of the rotor in air and flue gas is expressed in s
In the formula (3), according to the related knowledge of heat transfer, the heating coefficients of the air side and the flue gas side are related to the flue gas and the air temperature at the inlet and the outlet of the air preheater respectively by using thetajy，θpy，tlk，trkAnd (4) showing.
In summary, the air leakage rate G, the index λ of the degree of ash deposition and the lowest surface temperature t of the heating surfaceminIs the main performance evaluation index of the air preheater, and the main influencing factors comprise operation parameters delta p and delta py、θjy、θpy、a、tlk、trkAir leakage coefficient a, total seal gap area A and V depending on the type and quality of coaly、Gy、BjAnd the like. For a unit with determined structure and certain coal types, the fuel quantity BjSmoke mass GyVolume V of flue gasyIs a parameter of random group load variation.
Therefore, the air leakage rate, the ash deposition degree index and the lowest temperature of the surface of the heating surface of the air preheater are mainly random group load Pel, excess air coefficient a and flue gas pressure drop delta pyInlet flue gas temperature theta of air preheaterjySmoke exhaust temperature thetapyInlet and outlet air temperature t of air preheaterlk、trkAnd the side pressure difference delta p of the flue gas and the air changes. And further analyzing the operation parameters, wherein the excess air coefficient is in positive correlation with the inlet flue gas temperature and the flue gas exhaust temperature of the air preheater according to the combustion characteristics of the boiler.
Therefore, the load Pel and the smoke side pressure drop delta p of the unit can be reducedySmoke exhaust temperature delta p, smoke air side pressure difference delta p, air inlet and outlet air temperature t of air preheaterlk、trkAs process parameters reflecting the performance state of the air preheater, the following are defined:
X:＝(x1,x2,x3,x4,x5,x6):＝(Pel,Δpy,Δp,θpy,trk,tlk) (4)
in equation (4), "'" is a vector transpose.
In equation (4), X is a vector reflecting a process parameter (column) of the air preheater, and X1＝Pel,x2＝Δpy,x3＝Δp,x4＝θpy,x5＝trk,x6＝tlk。
(2) Data mining of air preheater typical performance states
Carrying out data mining analysis on the air preheater to obtain a data sample Xi＝(x1i,x2i,x3i,x4i,x5i,x6i) ', i-1, 2, …, and the typical performance state ω that is embedded in these data samplesl1,2, …, the method is as follows:
judging whether the air preheater reaches or is in a quasi-steady state process according to the formula (5):
|xj,k+1-xj,k|≤Δj,j＝1,2,3,4,5,6,k＝1,2,3,…(5)
in formula (5), ΔjFor the jth process parameter x of the air preheaterjIs detected.
And giving a proper time step K, and when the K is larger than or equal to the K, considering that the air preheater reaches a quasi-steady-state process. Once the air preheater reaches a quasi-steady state, a data sample set X for the quasi-steady state process can be obtainedl:
Xl＝{Xk||xj,k+1-xj,k|≤Δj,j＝1,2,3,4,5,6,k＝1,2,3,…,Nl} (6)
In formula (6), NlIs the first quasi-steady stateThe amount of data samples collected during the process.
After c different quasi-steady-state processes are obtained, c typical performance states omega of the air preheater are obtainedl1,2, …, c. These data samples for the quasi-steady state process constitute a data sample set for the air preheater:
in equation (7), reference ∪ is a collective and operation.
In equation (7), N is the number of samples of the obtained data sample set X.
(3) Evidence characterization and definition of air preheater performance states
Evidence theory is an effective tool for effectively processing inaccurate and uncertain information, wherein evidence characterization and definition are the basis of the evidence theory. Given a typical set of performance states for an air preheater, omega, { omega ═ omega }1,ω2,…,ωcThen any evidence m describing the current performance of the thermal device can be defined as follows:
in formula (8), 2ΩTo the power of the set omega.
In formula (8), a is an arbitrary subset of Ω.
In equation (8), m (a) is the confidence level that the current performance state of the air preheater belongs to state set a.
Set a describes the inaccuracy of the value of the current state of the air preheater, and m (a) describes the confidence, i.e., uncertainty, that the current performance state belongs to state set a. For example, assume that air preheater performance can be defined as three typical states Ω ═ ω1,ω2,ω3Then evidence mi:mi(ω1)＝0.3,mi({ω1,ω20.7 describes the air preheater performance slave state ω1Towards a transition state { omega1,ω2Derivation of where 0.3 and 0.7 respectively characterize the uncertainty of the air preheater's membership to different performance states, a ═ ω1,ω2The inaccuracy of the air preheater performance state is described.
(4) Evidence m of air preheater performance statusiConstruction of
First, in order to eliminate the influence of different variable dimensions, the original variables are normalized according to equation (10).
In the formula (10), the compound represented by the formula (10),is XlThe k-th data sample in (a),are each XlMedium maximum and minimum values.
Calculating each typical performance state [ omega ]lAnd a transition state [ omega ]l,ωl+11,2, …, class center of c-1:
conversely, the centroid corresponding to the original variable space can be obtained by equation (13):
in formula (13), A ∈ F, F { { ω: { { ω { (ω) }1},{ω1,ω2},{ω2},{ω2,ω3}…,{ωc-1},{ωc-1,ωc},{ωc} is the typical set of performance states for an air preheater.
Next, the degree of likelihood (/ uncertainty) that each data sample belongs to each performance state is calculated:
in the formula (14), the reaction mixture is,is composed ofEuclidean distance to performance state a.
In formula (14), F { { ω { (ω)1},{ω1,ω2},{ω2},{ω2,ω3}…,{ωc-1},{ωc-1,ωc},{ωc} is the typical set of performance states for an air preheater.
When the transition state [ omega ] is not consideredl,ωl+11,2, …, c-1, a piece of evidence mi(A) Degenerated to a probability distribution or a fuzzy number.
(5) Evidence characterization (set) of air preheater performance status
Based on the above description, based on the availability of the air preheater process parameter data samples X, evidence characterizations (sets) for reflecting the air preheater performance states can be constructed as follows:
{(Xi,mi)|i＝1,2,…,N} (15)
in formula (15), XiThe ith data sample of X.
In formula (15), miCorresponds to X as defined by formula (13)iEvidence of air preheater performance status.
Specifically, as shown in fig. 1, the evidence characterization construction method for the performance state of the air preheater of the thermal power generating unit provided by the embodiment of the present application includes:
s101: and acquiring data samples of unit load, flue gas pressure drop, pressure drop of a flue gas side and an air side, smoke exhaust temperature, air temperature at an outlet of the air preheater and air temperature at an inlet of the air preheater according to a preset period.
Data sample (unit load x) during normal operation of thermal power engine1Pel, pressure drop x of flue gas2＝ΔpyFlue gas side and air side pressure drop x3Δ p, exhaust gas temperature x4＝θpyOutlet air temperature x of air preheater5＝trkInlet air temperature x of air preheater6＝tlk) The sampling period of (a) is 1 second. Typically, for raw second-level data samples, a data screening window of 60 sampling periods is established, with a 1-minute average as a representative data sample.
S1O 2: and acquiring a data sample set of the air preheater in a quasi-steady state process from the samples.
Setting a time step K, and when the K is more than or equal to the K, enabling the air preheater to be in a quasi-steady-state process;
data sample set X of air preheater in quasi-steady state processl：Xl＝{Xk||xj,k+1-xj,k|≤Δj,j＝1,2,3,4,5,6,k＝1,2,3,…,Nl}，NlIs the data sample collected during the first quasi-steady state.
Specifically, ① sets l to 1 initially,if N is presentl>K, then the l-th typical performance state { ω llAnd its corresponding data sample set Xl② L +1, repeating operation ① until all original normal operation data samples are completely traversed and searched, ③ obtaining L character state set.
S103: computing an initial centroid for each performance state of the set of data samples
Calculating the initial class center of each performance state according to the formula (11)In particular, the method comprises the following steps of,
wherein,is XlThe k-th data sample in (a), are each XlMedium maximum and minimum values.
S1O 4: and counting typical performance states in the performance states according to the initial class centers of the performance states.
Calculating each typical performance state [ omega ]lEuclidean distance between class centersIf the distance between two different classes is close,namely:(ε is a given constant, which determines that the number of final typical state kernels should be between 2-10), then consider { ωkAnd { omega } andlmerging the two types of data samples in the same performance state; xl←Xk∪Xl，Nl←Nl+NkL ═ L-1; repeating the above operations until no satisfaction can be foundClass (c); finally, c typical performance states [ omega ] different from each other are obtainedl},l＝1,2,…,c。
S1O 5: computing the class centers of typical performance statesAnd class of transitional performance states
Each typical performance state (ω l) is calculated from equations (11), (12), and (13), respectivelylAnd the transient performance state ωl,ωl+1Center of 1,2, …, c-1And
s106: and calculating the credibility of the data sample belonging to each performance state.
Calculating the confidence (/ uncertainty) that each data sample belongs to each performance state according to the formula (14)
S1O 7: and constructing an air preheater energy state evidence characterization.
A heater performance state evidence characterization (set) is constructed according to equation (15).
The evidence characterization construction method for the performance state of the air preheater of the thermal power generating unit, provided by the embodiment of the application, is described in detail below by combining specific examples:
take a supercritical unit #1 high pressure heater in a certain place as an example.
Step 1: original normal sample (unit load x)1＝pelPressure drop x of flue gas2＝ΔpyFlue gas side and air side pressure drop x3Δ p, exhaust gas temperature x4＝θpyOutlet air temperature x of air preheater5＝trkInlet air temperature x of air preheater6＝tlk) And (4) preprocessing. In the example, the sampling time is about 3200 minutes, the original operation data is data samples of 1 second level, the arithmetic mean value of 60 periods is taken as a representative data sample, and finally 3150 samples are selected. The sampled data is schematically shown in fig. 2.
Step 2: establishing a unit load x for each selected process parameter1＝pelGiven a change threshold delta1And 6, judging whether the air preheater is in a quasi-steady state process according to the formula (5).
The specific implementation is that ① sets l as 1 initially, if N is Nl>K: -20, the l-th typical performance state ω is obtainedlAnd its corresponding data sample set Xl② l +1, repeating operation ① until all original normal operation data samples are completely searched, ③ obtaining l 34 characteristic state set, the steady state process judgment diagram of the example is shown in fig. 3.
And step 3: each performance state { ω is calculated from equation (11)lHeart-like core of 1,2,3(the superscript "0" here means initialClass heart). The class centers are sorted according to the load rise, and the results are respectively:
and 4, step 4: calculating each typical performance state [ omega ]lEuclidean distance between class centersIf it is notThen consider ω to bekAnd { omega } andlmerging the two types of data samples in the same performance state; xl←Xk∪Xl，Nl←Nl+NkL ═ L-1; repeating the above operations until no satisfaction can be foundClass (c); finally, 5 typical performance states different from each other are obtainedState { omegal},l＝1,2,…,5。
And 5: each representative performance state { ω is calculated according to equations (11), (12), and (13), respectivelylAnd the transient performance state ωl,ωl+11,2, …, 4-like centerAnd
typical performance state and transition state centroids are shown in fig. 4.
Step 6: the confidence (/ uncertainty) that each data sample belongs to each performance state is calculated according to equation (14)iFor example, {616.02MW,0.97Mpa,9.74Mpa,118.83 ℃,329.88 ℃,22.01 ℃ } the calculated confidence for each performance state is:
mi{ω1)＝0.0395；mi(ω1,ω2)＝0.8742；mi(ω2)＝0.0565；mi(ω2,ω3)＝0.0160；
mi(ω3)＝0.0074；mi(ω3,ω4)＝0.0028；mi(ω4)＝0.0015；mi(ω4,ω5)＝0.0011；
mi(ω5)＝0.0010；
due to the assignment to the transition state ω1,ω2The confidence of is highest, so XiThe value {616.02MW,0.97MPa,9.74MPa,118.83 deg.C, 329.88 deg.C, 22.01 deg.C } should belong to ω1And omega2The transition class of (1).
And 7: a heater performance state evidence characterization (set) is constructed according to equation (15). { (X)i,mi)|i＝1,2,…,N}，XiThe ith data sample of X. m isiIs represented by step 6 corresponding to XiEvidence of regenerative heater performance state. Taking a certain segment of real-time data as an example, the evidence construction result is shown in figure 5, and the first part of the segment belongs to omega5Then through a transition class (ω)4,ω5) Transition is omega4Also through the transition class (omega)4,ω5) Re-transition to ω5. At omega4In a state, has occurredFerry (omega)4,ω5) The phenomenon of the belief mutation shows that there is a direction of omega5A trend of state transition. The above process can be described by the evidence constructed by this patent as seen in fig. 5.
It should be noted that, in the present specification, all the embodiments are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment is mainly described as a difference from the other embodiments, and related parts may be referred to the part of the description of the method embodiment. Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (5)
1. An evidence characterization construction method for a performance state of an air preheater of a thermal power generating unit is characterized by comprising the following steps:
acquiring data samples of unit load, smoke pressure drop, smoke side and air side pressure drop, smoke exhaust temperature, air temperature at an outlet of an air preheater and air temperature at an inlet of the air preheater according to a preset period;
acquiring a data sample set of the air preheater in a quasi-steady state process from the samples;
computing an initial class of performance states for the set of data samplesHeart with heart-shaped
According to the initial class centers of the performance states, typical performance states in the performance states are counted;
computing the class centers of typical performance statesAnd class of transitional performance states
Calculating the credibility of each performance state to which the data sample belongs;
and constructing an evidence representation of the performance state of the air preheater.
2. The method of claim 1, wherein obtaining a data sample set of the air preheater in a quasi-steady state process from the samples comprises:
setting a time step K, and when the K is more than or equal to the K, enabling the air preheater to be in a quasi-steady-state process;
data sample set X of air preheater in quasi-steady state processl：Xl＝{Xk||xj,k+1-xj,k|≤Δj,j＝1,2,3,4,5,6,k＝1,2,3,…,Nl}，NlIs the data sample collected during the first quasi-steady state.
3. The method of claim 2, wherein an initial centroid is computed for each performance state of the set of data samplesThe method comprises the following steps:
wherein, is XlThe k-th data sample in (a),are each XlMedium maximum and minimum values.
4. The method of claim 3, wherein counting typical ones of the performance states based on the initial centroid for the performance states comprises:
calculating Euclidean distance of initial class center of each adjacent performance state
When in useIf ε is a given constant, then ω is considered to bekAnd { omega } andlmerging the two types of data samples in the same performance state;
Xl←Xk∪Xl，Nl←Nl+Nkl ═ L-1; repeating the above operations until no satisfaction can be foundClass (c); finally, c typical performance states [ omega ] different from each other are obtainedl},l＝1,2,…,c。
5. The method of claim 4, wherein the centroid of each representative performance state is calculatedAnd class of transitional performance statesThe method comprises the following steps:
class hearts of typical performance statesClass hearts of transitional performance states
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811116474.7A CN109325294B (en) | 2018-09-25 | 2018-09-25 | Evidence characterization construction method for performance state of air preheater of thermal power generating unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811116474.7A CN109325294B (en) | 2018-09-25 | 2018-09-25 | Evidence characterization construction method for performance state of air preheater of thermal power generating unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109325294A true CN109325294A (en) | 2019-02-12 |
| CN109325294B CN109325294B (en) | 2023-08-11 |
Family
ID=65265446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811116474.7A Active CN109325294B (en) | 2018-09-25 | 2018-09-25 | Evidence characterization construction method for performance state of air preheater of thermal power generating unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109325294B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112564100A (en) * | 2020-12-03 | 2021-03-26 | 山东电力研究院 | Method and system for evaluating maximum output of thermal power generating unit in real time based on differential pressure of air preheater |
| CN118090356A (en) * | 2024-04-23 | 2024-05-28 | 杭州湘亭科技有限公司 | Concentrated collection system of radioactive effluent krypton-85 waste gas |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006087854A1 (en) * | 2004-11-25 | 2006-08-24 | Sharp Kabushiki Kaisha | Information classifying device, information classifying method, information classifying program, information classifying system |
| CN101924623A (en) * | 2010-08-03 | 2010-12-22 | 北京邮电大学 | Method and device for merging data |
| CN102636991A (en) * | 2012-04-18 | 2012-08-15 | 国电科学技术研究院 | Method for optimizing running parameters of thermal power unit and based on fuzzy set association rule |
| US20120296675A1 (en) * | 2006-02-13 | 2012-11-22 | Silverman David G | Method and System for Assessing, Quantifying, Coding & Communicating a Patient's Health and Perioperative Risk |
| US20140156657A1 (en) * | 2012-12-05 | 2014-06-05 | Siamese Systems Incorporated | System and method for documenting evidence |
| CN104217113A (en) * | 2014-09-03 | 2014-12-17 | 广西电网有限责任公司 | Reliability evaluation method of independent wind and light storage system based on energy storage probability model |
| CN104870699A (en) * | 2012-12-28 | 2015-08-26 | 默克专利股份有限公司 | Liquid doping media for the local doping of silicon wafers |
| CN105188035A (en) * | 2015-08-11 | 2015-12-23 | 重庆邮电大学 | Indoor WLAN (Wireless Local Area Network) augmentation manifold alignment localization method based on transition probability hotspot mapping |
| CN105678320A (en) * | 2015-12-30 | 2016-06-15 | 山东大学 | Matrix-decomposition-based method for realizing stateful data in Bayesian network |
| CN106599271A (en) * | 2016-12-22 | 2017-04-26 | 江苏方天电力技术有限公司 | Emission monitoring time series data abnormal value detection method for coal-fired unit |
| CN107330467A (en) * | 2017-07-03 | 2017-11-07 | 云南昆船设计研究院 | A kind of Forecasting Methodology influenceed based on piece cigarette morphological feature on tobacco structure |
| CN107330597A (en) * | 2017-06-22 | 2017-11-07 | 南京南瑞继保电气有限公司 | Blast funnace hot blast stove power consumption state various dimensions appraisal procedure based on Fuzzy Pattern Recognition |
| CN107392238A (en) * | 2017-07-12 | 2017-11-24 | 华中师范大学 | Outdoor knowledge of plants based on moving-vision search expands learning system |
| CN107438398A (en) * | 2015-01-06 | 2017-12-05 | 大卫·伯顿 | Portable wearable monitoring system |
| CN107665261A (en) * | 2017-10-25 | 2018-02-06 | 北京奇虎科技有限公司 | Video duplicate checking method and device |
| CN107909179A (en) * | 2017-09-29 | 2018-04-13 | 北京理工大学 | The prediction model construction method and vehicle energy management method of a kind of plug-in hybrid vehicle driving cycle |
| CN108388922A (en) * | 2018-03-08 | 2018-08-10 | 云南电网有限责任公司电力科学研究院 | A kind of recognition methods and system for the major-minor equipment state exception of fired power generating unit |
| CN108445865A (en) * | 2018-03-08 | 2018-08-24 | 云南电网有限责任公司电力科学研究院 | A kind of method and system for the major-minor equipment dynamic alert of fired power generating unit |
-
2018
- 2018-09-25 CN CN201811116474.7A patent/CN109325294B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006087854A1 (en) * | 2004-11-25 | 2006-08-24 | Sharp Kabushiki Kaisha | Information classifying device, information classifying method, information classifying program, information classifying system |
| US20120296675A1 (en) * | 2006-02-13 | 2012-11-22 | Silverman David G | Method and System for Assessing, Quantifying, Coding & Communicating a Patient's Health and Perioperative Risk |
| CN101924623A (en) * | 2010-08-03 | 2010-12-22 | 北京邮电大学 | Method and device for merging data |
| CN102636991A (en) * | 2012-04-18 | 2012-08-15 | 国电科学技术研究院 | Method for optimizing running parameters of thermal power unit and based on fuzzy set association rule |
| US20140156657A1 (en) * | 2012-12-05 | 2014-06-05 | Siamese Systems Incorporated | System and method for documenting evidence |
| CN104870699A (en) * | 2012-12-28 | 2015-08-26 | 默克专利股份有限公司 | Liquid doping media for the local doping of silicon wafers |
| CN104217113A (en) * | 2014-09-03 | 2014-12-17 | 广西电网有限责任公司 | Reliability evaluation method of independent wind and light storage system based on energy storage probability model |
| CN107438398A (en) * | 2015-01-06 | 2017-12-05 | 大卫·伯顿 | Portable wearable monitoring system |
| CN105188035A (en) * | 2015-08-11 | 2015-12-23 | 重庆邮电大学 | Indoor WLAN (Wireless Local Area Network) augmentation manifold alignment localization method based on transition probability hotspot mapping |
| CN105678320A (en) * | 2015-12-30 | 2016-06-15 | 山东大学 | Matrix-decomposition-based method for realizing stateful data in Bayesian network |
| CN106599271A (en) * | 2016-12-22 | 2017-04-26 | 江苏方天电力技术有限公司 | Emission monitoring time series data abnormal value detection method for coal-fired unit |
| CN107330597A (en) * | 2017-06-22 | 2017-11-07 | 南京南瑞继保电气有限公司 | Blast funnace hot blast stove power consumption state various dimensions appraisal procedure based on Fuzzy Pattern Recognition |
| CN107330467A (en) * | 2017-07-03 | 2017-11-07 | 云南昆船设计研究院 | A kind of Forecasting Methodology influenceed based on piece cigarette morphological feature on tobacco structure |
| CN107392238A (en) * | 2017-07-12 | 2017-11-24 | 华中师范大学 | Outdoor knowledge of plants based on moving-vision search expands learning system |
| CN107909179A (en) * | 2017-09-29 | 2018-04-13 | 北京理工大学 | The prediction model construction method and vehicle energy management method of a kind of plug-in hybrid vehicle driving cycle |
| CN107665261A (en) * | 2017-10-25 | 2018-02-06 | 北京奇虎科技有限公司 | Video duplicate checking method and device |
| CN108388922A (en) * | 2018-03-08 | 2018-08-10 | 云南电网有限责任公司电力科学研究院 | A kind of recognition methods and system for the major-minor equipment state exception of fired power generating unit |
| CN108445865A (en) * | 2018-03-08 | 2018-08-24 | 云南电网有限责任公司电力科学研究院 | A kind of method and system for the major-minor equipment dynamic alert of fired power generating unit |
Non-Patent Citations (8)
| Title |
|---|
| ANDREAS RAUH: "Design and experimental validation of control strategies for commercial gas preheating systems", 《2013 18TH INTERNATIONAL CONFERENCE ON METHODS & MODELS IN AUTOMATION & ROBOTICS (MMAR)》 * |
| ANDREAS RAUH: "Design and experimental validation of control strategies for commercial gas preheating systems", 《2013 18TH INTERNATIONAL CONFERENCE ON METHODS & MODELS IN AUTOMATION & ROBOTICS (MMAR)》, 31 December 2013 (2013-12-31) * |
| 许彦斌: "基于工况划分的机组优化运行寻优方法", 《节能技术》 * |
| 许彦斌: "基于工况划分的机组优化运行寻优方法", 《节能技术》, 31 March 2018 (2018-03-31) * |
| 陈仁祥: "振动谱表征空间滚动轴承寿命状态方法研究", 《中国优秀博士学位论文全文数据库工程科技Ⅱ辑》 * |
| 陈仁祥: "振动谱表征空间滚动轴承寿命状态方法研究", 《中国优秀博士学位论文全文数据库工程科技Ⅱ辑》, 15 May 2013 (2013-05-15) * |
| 顾慧: "热工过程海量数据挖掘技术研究与应用", 《中国优秀博士学位论文全文数据库工程科技Ⅱ辑》 * |
| 顾慧: "热工过程海量数据挖掘技术研究与应用", 《中国优秀博士学位论文全文数据库工程科技Ⅱ辑》, 15 December 2017 (2017-12-15) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112564100A (en) * | 2020-12-03 | 2021-03-26 | 山东电力研究院 | Method and system for evaluating maximum output of thermal power generating unit in real time based on differential pressure of air preheater |
| 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 |
| CN118090356A (en) * | 2024-04-23 | 2024-05-28 | 杭州湘亭科技有限公司 | Concentrated collection system of radioactive effluent krypton-85 waste gas |
| CN118090356B (en) * | 2024-04-23 | 2024-07-19 | 杭州湘亭科技有限公司 | Concentrated collection system of radioactive effluent krypton-85 waste gas |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109325294B (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583585B (en) | Construction method of power station boiler wall temperature prediction neural network model | |
| CN113011010A (en) | Boiler fault diagnosis method and diagnosis system based on structural mechanism and operation data | |
| CN107326137B (en) | Blast funnace hot blast stove burns stove process operating parameters multistage matching optimization method at times | |
| CN109325294A (en) | A kind of evidence characterization construction method of fired power generating unit air preheater performance state | |
| CN106055520B (en) | System and method for predicting drum water level of circulating fluidized bed domestic garbage incineration boiler | |
| CN109376858B (en) | Method for predicting performance of condensing heat exchanger based on partial load rate | |
| CN110207094B (en) | IQGA-SVR boiler heating surface contamination characteristic identification method based on principal component analysis | |
| CN102176221A (en) | Coke furnace temperature predicting method based on dynamic working conditions in coke furnace heating and burning process | |
| CN113517037B (en) | Method and system for predicting sintering ore FeO by fusing data and knowledge | |
| CN103631140A (en) | Method for automatically regulating temperature of flame path of coke oven in heating and combusting procedures on basis of performance evaluation | |
| CN109829189B (en) | Hearth slagging thickness judgment method based on numerical simulation | |
| Liu et al. | Abnormal energy identification of variable refrigerant flow air-conditioning systems based on data mining techniques | |
| CN115700330A (en) | Boiler reheater temperature deviation prediction method based on time-space fusion deep neural network | |
| Xia et al. | Incipient chiller fault diagnosis using an optimized least squares support vector machine with gravitational search algorithm | |
| CN109655275B (en) | Gas turbine cycle heat economy diagnosis method based on sensitivity coefficient method | |
| CN111242279A (en) | System and method for predicting slagging of hearth of ultra-supercritical pulverized coal boiler | |
| CN113532138B (en) | Roller kiln firing zone anomaly detection algorithm based on decision fusion frame | |
| CN112051082A (en) | Fault diagnosis method in operation of heat exchanger of heat supply system | |
| CN115512455A (en) | Heating furnace steel billet temperature prediction method integrating mechanism and model migration | |
| CN104460653B (en) | A kind of heating furnace monitoring system evaluation method | |
| Wang et al. | A steady-state detection method based on Gaussian discriminant analysis for the on-line gas turbine process | |
| CN109840563A (en) | A kind of Fault Diagnosis of Fan method based on three-dimensional membership function fuzzy logic system | |
| CN116009393A (en) | Automatic control method for load deviation under deep peak regulation of thermal generator set | |
| CN103699782B (en) | Coal feeding amount soft measuring method of middle-speed powder milling and preparation system | |
| WO2020253485A1 (en) | Dbscan-based outer surface temperature measurement method for cracking furnace tube |
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 |