CN106200416A - Regulator control system that Combined Cycle Unit power is affected by atmospheric temperature and method - Google Patents
Regulator control system that Combined Cycle Unit power is affected by atmospheric temperature and method Download PDFInfo
- Publication number
- CN106200416A CN106200416A CN201610608517.8A CN201610608517A CN106200416A CN 106200416 A CN106200416 A CN 106200416A CN 201610608517 A CN201610608517 A CN 201610608517A CN 106200416 A CN106200416 A CN 106200416A
- Authority
- CN
- China
- Prior art keywords
- data
- generated output
- atmospheric temperature
- measuring point
- sample
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
-
- 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
- Y02E20/16—Combined cycle power plant [CCPP], or combined cycle gas turbine [CCGT]
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
Abstract
Regulator control system that Combined Cycle Unit power is affected by the atmospheric temperature of a kind of electric power energy-saving technical field and method, first pass through sensing measurement module and carry out sample data collection, obtain under different atmospheric temperature, standard generated output time, measuring point initial data on combined cycle generating unit and generated output data, be stored in measuring point initial data corresponding for same atmospheric temperature and generated output data in DBM as a sample group；Then simulation algorithm model is chosen some sample groups from DBM and is built raw sample data collection, and determines that raw sample data concentrates measuring point initial data and the maximum of generated output data and minima；The atmospheric temperature change fair curve on the impact of combined cycle generating unit generated output is obtained finally by BP neural computing.The present invention can carry out the correction of combined cycle generating unit generated output without carrying out test of many times debugging, assesses, for set optimization, energy-saving and emission-reduction, the foundation providing solid.
Description
Technical field
The present invention relates to the technology in a kind of electric power energy-saving field, specifically a kind of atmospheric temperature is to Combined Cycle Unit
The regulator control system of power impact and method.
Background technology
In recent years, coal price is high and the requirement of energy-saving and emission-reduction, promotes power plant's reform to reduce energy consumption, improves
Economy, therefore proposes the highest requirement for the evaluation criterion after power plant's performance evaluation.The comparable performance need of unit exists
The performance parameter that is given under a certain design conditions, the performance that i.e. unit is had under given boundary condition.Carry out at the scene
During performance test, for various reasons, it is impossible to make all of boundary condition all can meet design condition, accordingly, it would be desirable to performance
Boundary condition during test is modified, and is i.e. adapted to design condition, and unit could be given reasonably evaluation.After generally revising
The fair curve obtained is provided by maker, but unit is after running after a while, and particularly unit parts are through celebrating a festival
Can transform, change relative to original design, fair curve originally is the most applicable.
At present for pure burning low combustion value furnace gas Combined cycle gas-steam turbine unit, still lack atmospheric temperature change right
The fair curve of generated output impact.Complete the correction of generated output according to existing technical method, need to carry out a lot
On-the-spot test, and to adjust other each parameter according to the timing node of atmospheric temperature and to test at phase same level, electrical network and
Power plant all can not realize, and empirical risk is big, and the time is long, costly.
Summary of the invention
The present invention is directed to deficiencies of the prior art, it is proposed that a kind of atmospheric temperature is to Combined Cycle Unit power
The regulator control system of impact and method, it is not necessary to carry out test of many times debugging and can carry out pure burning low combustion value furnace gas Steam Combined
The correction of circulating generation unit performance, and realize the feedback regulation to unit, provide conscientiously for set optimization, energy-saving and emission-reduction assessment
Foundation reliably.
The present invention is achieved by the following technical solutions:
The present invention relates to a kind of regulation and control system that based on above-mentioned atmospheric temperature, Combined Cycle Unit power is affected modification method
System, including: sensing measurement module, DBM and simulation algorithm model, wherein: sensing measurement module and simulation calculation mould
Block is connected and exports acquired original data, and simulation algorithm model is connected with DBM and exports measuring point initial data and generating
Power data, DBM is connected with simulation algorithm model and exports raw sample data collection, and simulation algorithm model is according to sending out
Electrical power correction model and fair curve feedback regulation unit operation, to improve or to reduce generated output.
The present invention relates to the modification method that Combined Cycle Unit power is affected by the atmospheric temperature of said system, first pass through
Sensing measurement module carries out raw data acquisition, and carries out the nondimensionalization of data by simulation algorithm model and process, and obtains not
With under atmospheric temperature, a certain standard generated output time, the measuring point initial data on blast furnace gas steam combined cycle power generating unit
And generated output data, measuring point initial data corresponding for same atmospheric temperature and generated output data are deposited as a sample group
It is stored in DBM；Then simulation algorithm model is chosen some sample groups from DBM and is built raw sample data
Collection, and determine that raw sample data concentrates measuring point initial data and the maximum of generated output data and minima；Finally will survey
Intermediate objective data are obtained as input layer data by BP neural computing, by intermediate objective after some initial data normalization
The target output data obtained after data and generated output data normalization carry out Error Calculation, obtain generated output correction mould
Type；Choosing one group of measuring point initial data close to nominal parameter as radix, only change atmospheric temperature, simulation algorithm model is being sent out
Atmospheric temperature change repairing the impact of combined cycle generating unit generated output it is calculated on the basis of electrical power correction model
Positive curve.
Described standard generated output is 80MW, 90MW, 100MW, 110MW or 120MW.
Described raw sample data collection for include combined cycle generating unit run available minimum generated output and
Maximum generation power is in interior multiple sample groups.
Described BP neural computing comprises the following steps:
S1, raw sample data collection normalization:Wherein: i table
Show measuring point sequence number, i=1,2 ..., n；P represent raw sample data concentrate sample group sequence number, p=1,2 ..., N；N is former
The sample group quantity that beginning sample data is concentrated；x′ipRepresent that the measuring point of raw sample data concentration pth sample group i-th measuring point is former
Beginning data, xipFor x 'ipValue after normalization, referred to as measuring point input data；x′0pRepresent the generating merit that raw sample data is concentrated
Rate data, x0pFor x '0pValue after normalization, referred to as target output data；x′imin、x′imaxRepresent raw sample data collection respectively
The minima of middle i-th measuring point and maximum；x′0min、x′0maxRepresent raw sample data centralized power generation power minima and
Maximum；
S2, determine the number of middle hidden node and initialize the connection weight matrix of pth sample group, wherein p=1 is the most right
The input layer data rights matrix V of the 1st sample groupijWith middle hidden layer data rights matrix WjInitialize: in connection weight matrix
It is that the random number between 0～1 obtains original connection weight matrix, wherein that each element composes initial value: j represents middle hidden node sequence
Number, j=1,2 ..., m；VijIt is n × m rank weight matrixs, WjBeing 1 × m rank weight matrixs, m is middle the number of hidden nodes, and m is according to input
The number of layer data determines, input layer data amount check is the most, and m value is the biggest, and when input layer is 3～20 data, m value can be
Choose between 10～30；
S3, train original connection weight matrix for pth sample group, set up generated output correction model:
S31, determine middle hidden node data ypj:Wherein:In for
Between the index of hidden node data computing formula, e is the truth of a matter of natural logrithm；
S32, calculate intermediate objective data dp:Wherein:For intermediate objective
The index of data calculation formula；
S33, calculate target output data x0pCorresponding intermediate objective data dpError Ep:
S34, according to the original connection weight matrix of pth sample group, the connection weight matrix V of adjusting training p+1 sample groupij' and
Wj': Vij'=Vij+ΔVijp, Wj'=Wj+ΔWjp, Δ Vijp=η δyxi(p-1)+αΔVij(p-1), Δ Wjp=η δ0y(p-1)j+αΔ
Wj(p-1), wherein: Δ Wjp、ΔVijpFor calculating pth sample group to the increment adjusting connection weight matrix during pth+1 sample group；Δ
Wj(p-1)、ΔVij(p-1)For adjusting the increment of connection weight matrix, Δ W during p=1 during pth 1 sample group to pth sample groupj0And Δ
Vij0It is the original connection weight matrix of the 1st sample group to rest and reorganize the value after calculating through α；y(p-1)j、xi(p-1)For pth 1 sample group
Middle hidden node data and i-th measuring point input data；α, η are two coefficients arranged to accelerate convergence rate,
Typically take the Arbitrary Digit between 0～1, start to take 0.5 during computing, can carry out increasing by 5% or reducing according to convergence state afterwards
The adjustment of 5%；Intermediate variable δ0And δyjFor correction factor:
S35, make p=p+1, repeat step S34After completing the connection weight matrix training of whole sample group, calculate and always export by mistake
Difference EN:If ENIt is unsatisfactory for required precision, repeats step S2Again assignment calculates, until ENPrecision
Reach requirement；The V of required precision will be metij、Wj、m、x′0min、x′0max、x′iminWith x 'imaxChange coal as atmospheric temperature
The generated output correction model of gas steam combined cycle power generating unit generation power impact is saved in simulation algorithm model；
S4, generated output correction: choose a temperature every 2 DEG C in the range of 2 DEG C～35 DEG C of atmospheric temperatures, and keep it
Remaining measuring point initial data is in the state close to nominal parameter；By original for the measuring point close to nominal parameter under the conditions of said temperature
Data x '1p、x′2p、…、x′np, utilize the x ' in generated output correction modeliminWith x 'imaxRepeat S1, after normalization, obtain x1p、
x2p、…、xnp, in conjunction with the V in generated output correction modelij、Wjλ is calculated with mpj、λpWith intermediate objective data dp, last anti-normalizing
Change and obtain generated output data X ' at revised a certain temperature0=dp(x′0max-x′0min)+x′0min, and obtain 2 DEG C～35 DEG C
The fair curve that generated output is affected by the atmospheric temperature in the range of atmospheric temperature.
Technique effect
Compared with prior art, the present invention uses the method for BP neutral net, based on field measurement data and artificial intelligence
Combination, reduce the dependence to actual tests under conditions of precision ensureing；Only need to change atmospheric temperature just can be sent out
The output valve of electrical power, the on this basis operation of feedback regulation pure burning low-heat value gas gas-steam combined cycle set, with
Improve or reduce generated output, assess, for set optimization, energy-saving and emission-reduction, the foundation providing solid simultaneously.Big owing to have employed
The on-the-spot actual information of amount, therefore the correction result of gained is typically within 5%, meets the requirement of engineer applied.
Accompanying drawing explanation
Fig. 1 is the correction atmospheric temperature of the present invention change schematic diagram on generated output impact；
Fig. 2 is system construction drawing in the present invention；
Fig. 3 is BP neural net model establishing schematic diagram in the present invention.
Detailed description of the invention
Elaborating embodiments of the invention below, the present embodiment is carried out under premised on technical solution of the present invention
Implement, give detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following enforcement
Example.
Embodiment 1
As depicted in figs. 1 and 2, the impact of Combined Cycle Unit power is revised based on above-mentioned atmospheric temperature for the present embodiment
The regulator control system of method, including: sensing measurement module, DBM and simulation algorithm model, wherein: sensing measurement module
Being connected with simulation algorithm model and export acquired original data, simulation algorithm model is connected with DBM and to export measuring point former
Beginning data and generated output data, DBM is connected with simulation algorithm model and exports raw sample data collection, emulation meter
Calculation module is according to generated output correction model and fair curve feedback regulation unit operation, to improve or to reduce generated output.
As it is shown in figure 1, the present embodiment relates to the modification method of said system, comprise the following steps:
1) carry out raw data acquisition by sensing measurement module, and carried out the dimensionless of data by simulation algorithm model
Change processes, obtain under different atmospheric temperature, a certain standard generated output time, on blast furnace gas steam combined cycle power generating unit
The measuring point initial data of 15 measuring points and generated output data, measuring point initial data corresponding for same atmospheric temperature and generating merit
Rate data are stored in DBM as a sample group；
2) simulation algorithm model is chosen 250 sample groups from DBM and is built raw sample data collection, and determines
Raw sample data concentrates measuring point initial data and the maximum of generated output data and minima；
3) after measuring point initial data normalization, intermediate objective is obtained as input layer data by BP neural computing
The target output data obtained after intermediate objective data and generated output data normalization are carried out Error Calculation, obtain by data
Generated output correction model；
4) choose one group of measuring point initial data close to nominal parameter as radix, only change atmospheric temperature, simulation calculation
Module is calculated atmospheric temperature on the basis of generated output correction model and changes combined cycle generating unit generated output
The fair curve of impact.
As shown in table 1 below in the present embodiment 15 measuring points:
Table 1 measuring point list
As shown in table 2 below for raw sample data collection
Table 2 raw sample data collection
As it is shown on figure 3, described BP neural computing comprises the following steps:
S1, raw sample data collection normalization: first determine each measuring point original input data x 'ipMaximum and minimum
Value, as shown in table 3 below, then it is normalized, obtains table 4；
Each measuring point initial data x ' in 3250 sample groups of tableipAnd generated output data x '0pMaximum and minima
Wherein corresponding generated output data maximums x '0maxWith minima x '0minIt is respectively 116.6 and 72.7；
4 250 sample group measuring point input data x of tableipData x are exported with target0p
S2, determine the number m=12 of middle hidden node, and initialize the connection weight matrix of pth sample group, wherein p=
1, i.e. the input layer data rights matrix V to the 1st sample groupijWith middle hidden layer data rights matrix WjInitialize: for connection weight
In matrix, each element composes initial value is that the random number between 0～1 obtains original connection weight matrix, wherein: j represents middle hidden layer
Node ID, j=1,2 ..., m；VijIt is 15 × 12 rank weight matrixs, WjIt it is 1 × 12 rank weight matrix；
S3, train original connection weight matrix for pth sample group, set up generated output correction model:
S31, determine middle hidden node data ypj:Wherein:In for
Between the index of hidden node data computing formula, e is the truth of a matter of natural logrithm；
S32, calculate intermediate objective data dp:Wherein:For intermediate objective
The index of data calculation formula；
S33, calculate target output data x0pCorresponding intermediate objective data dpError Ep:
S34, according to the original connection weight matrix of pth sample group, the connection weight matrix V of adjusting training p+1 sample groupij' and
Wj': Vij'=Vij+ΔVijp, Wj'=Wj+ΔWjp, Δ Vijp=η δyxi(p-1)+αΔVij(p-1), Δ Wjp=η δ0y(p-1)j+αΔ
Wj(p-1), wherein: Δ Wjp、ΔVijpFor calculating pth sample group to the increment adjusting connection weight matrix during pth+1 sample group；Δ
Wj(p-1)、ΔVij(p-1)For adjusting the increment of connection weight matrix, Δ W during p=1 during pth 1 sample group to pth sample groupj0And Δ
Vij0It is the original connection weight matrix of the 1st sample group to rest and reorganize the value after calculating through α；y(p-1)j、xi(p-1)For pth 1 sample group
Middle hidden node data and i-th measuring point input data；α, η are two coefficients arranged to accelerate convergence rate；
Typically take the Arbitrary Digit between 0～1, start to take 0.5 during computing, can carry out increasing by 5% or reducing according to convergence state afterwards
The adjustment of 5%；Intermediate variable δ0And δyjFor correction factor:
S35, make p=p+1, repeat step S34After completing the connection weight matrix training of whole sample group, calculate and always export by mistake
Difference EN:If ENIt is unsatisfactory for required precision, repeats step S2Again assignment calculates, until ENPrecision
Reach requirement；The V of required precision will be metij、Wj、m、x′0min、x′0max、x′iminWith x 'imaxChange coal as atmospheric temperature
The generated output correction model of gas steam combined cycle power generating unit generation power impact is saved in simulation algorithm model；
S4, generated output correction: choose a temperature every 2 DEG C in the range of 2 DEG C～35 DEG C of atmospheric temperatures, and keep it
Remaining measuring point initial data is in the state close to nominal parameter；Gather the measuring point close to nominal parameter under the conditions of said temperature former
Beginning data x '1p、x′2p、…、x′np, utilize the x ' in generated output correction modeli minWith x 'imaxRepeat S1, obtain after normalization
x1p、x2p、…、xnp, in conjunction with the V in generated output correction modelij、Wjλ is calculated with mpj、λpWith intermediate objective data dp, the most instead
Normalization obtains generated output data X ' at revised a certain temperature0=dp(x0′max-x′0min)+x′0min, and obtain 2 DEG C～
The fair curve that generated output is affected by the atmospheric temperature in the range of 35 DEG C of atmospheric temperatures.
Claims (7)
1. an atmospheric temperature affects the regulator control system of modification method to Combined Cycle Unit power, it is characterised in that including: pass
Sensed quantity module, DBM and simulation algorithm model, wherein: sensing measurement module is connected with simulation algorithm model and defeated
Going out acquired original data, simulation algorithm model is connected with DBM and exports measuring point initial data and generated output data,
DBM is connected with simulation algorithm model and exports raw sample data collection, and simulation algorithm model is according to generated output correction
Model and fair curve feedback regulation unit operation, to improve or to reduce generated output.
2. the modification method of a system according to claim 1, it is characterised in that first pass through sensing measurement module and carry out
Raw data acquisition, and carry out the nondimensionalization of data by simulation algorithm model and process, obtains under different atmospheric temperature, a certain
During standard generated output, the measuring point initial data on blast furnace gas steam combined cycle power generating unit and generated output data,
Measuring point initial data and generated output data that same atmospheric temperature is corresponding are stored in DBM as a sample group；
Then simulation algorithm model is chosen some sample groups from DBM and is built raw sample data collection, and determines original sample
Measuring point initial data and the maximum of generated output data and minima in data set；Finally by after measuring point initial data normalization
Intermediate objective data are obtained by BP neural computing, by intermediate objective data and generated output data as input layer data
The target output data obtained after normalization carry out Error Calculation, obtain generated output correction model；Choose close to nominal parameter
One group of measuring point initial data as radix, only change atmospheric temperature, simulation algorithm model is at the base of generated output correction model
The atmospheric temperature change fair curve on the impact of combined cycle generating unit generated output it is calculated on plinth.
The modification method that Combined Cycle Unit power is affected by atmospheric temperature the most according to claim 2, is characterized in that, institute
The raw sample data collection stated is for including that combined cycle generating unit runs available minimum generated output and maximum generation merit
Rate is in interior multiple sample groups.
The modification method that Combined Cycle Unit power is affected by atmospheric temperature the most according to claim 2, is characterized in that, institute
The BP neural computing stated comprises the following steps:
S1, raw sample data collection normalization:Wherein: i represents measuring point
Sequence number, i=1,2 ..., n；P represent raw sample data concentrate sample group sequence number, p=1,2 ..., N；N is original sample
Sample group quantity in data set；x′ipRepresent that raw sample data concentrates the measuring point initial data of pth sample group i-th measuring point,
xipFor x 'ipValue after normalization, referred to as measuring point input data；x′0pRepresent the generated output data that raw sample data is concentrated,
x0pFor x '0pValue after normalization, referred to as target output data；x′imin、x′imaxRepresent that raw sample data concentrates i-th respectively
The minima of measuring point and maximum；x′0min、x′0maxRepresent minima and the maximum of raw sample data centralized power generation power；
S2, determine the number of middle hidden node and initialize the connection weight matrix of pth sample group, wherein p=1, i.e. to the 1st sample
The input layer data rights matrix V of this groupijWith middle hidden layer data rights matrix WjInitialize: for unit each in connection weight matrix
It is that the random number between 0～1 obtains original connection weight matrix, wherein that element composes initial value: j represents middle hidden node sequence number, j=
1,2 ..., m；VijIt is n × m rank weight matrixs, WjBeing 1 × m rank weight matrixs, m is middle the number of hidden nodes；
S3, train original connection weight matrix for pth sample group, set up generated output correction model:
S31Determine middle hidden node data ypj:Wherein:For middle hidden layer
The index of node data computing formula, e is the truth of a matter of natural logrithm；
S32, calculate intermediate objective data dp:Wherein:For intermediate objective data
The index of computing formula；
S33, calculate target output data x0pCorresponding intermediate objective data dpError Ep:
S34, according to the original connection weight matrix of pth sample group, the connection weight matrix V of adjusting training p+1 sample groupij' and Wj':
V′ij=Vij+ΔVijp, W 'j=Wj+ΔWjp, Δ Vijp=η δyxi(p-1)+αΔVij(p-1), Δ Wjp=η δ0y(p-1)j+αΔWj(p-1),
Wherein: Δ Wjp、ΔVijpFor calculating pth sample group to the increment adjusting connection weight matrix during pth+1 sample group；ΔWj(p-1)、Δ
Vij(p-1)For adjusting the increment of connection weight matrix, Δ W during p=1 during pth 1 sample group to pth sample groupj0With Δ Vij0It is the 1st
The original connection weight matrix of sample group value after α rests and reorganizes calculating；y(p-1)j、xi(p-1)Middle hidden layer for pth 1 sample group
Node data and i-th measuring point input data；α, η are two coefficients arranged to accelerate convergence rate, typically take 0～1
Between Arbitrary Digit, start to take 0.5 during computing, can carry out increasing by 5% according to convergence state afterwards or reduce the adjustment of 5%；
Intermediate variable δ0And δyjFor correction factor:
S35, make p=p+1, repeat step S34After completing the connection weight matrix training of whole sample group, calculate total output error EN:If ENIt is unsatisfactory for required precision, repeats step S2Again assignment calculates, until ENPrecision reach want
Ask；The V of required precision will be metij、Wj、m、x′0min、x′0max、x′iminWith x 'imaxChange coal gas steam as atmospheric temperature
The generated output correction model of combined cycle generating unit generated output impact is saved in simulation algorithm model；
S4, generated output correction: choose a temperature every 2 DEG C in the range of 2 DEG C～35 DEG C of atmospheric temperatures, and keep remaining to survey
Point initial data is in the state close to nominal parameter；By the measuring point initial data close to nominal parameter under the conditions of said temperature
x′1p、x′2p、…、x′np, utilize the x ' in generated output correction modeliminWith x 'imaxRepeat S1, after normalization, obtain x1p、
x2p、…、xnp, in conjunction with the V in generated output correction modelij、Wjλ is calculated with mpj、λpWith intermediate objective data dp, last anti-normalizing
Change and obtain generated output data X ' at revised a certain temperature0=dp(x′0max-x′0min)+x′0min, and obtain 2 DEG C～35 DEG C
The fair curve that generated output is affected by the atmospheric temperature in the range of atmospheric temperature.
5. the modification method according to the atmospheric temperature described in claim 2 or 4, Combined Cycle Unit power affected, its feature
It is, described measuring point totally 15 to measure following items respectively: blast furnace gas flow, blast furnace gas calorific value, blast furnace gas are for temperature
Degree, gas heater outlet temperature, blast furnace gas hydrogen volume mark, blast furnace gas carbon monoxide volume fraction, blast furnace gas
Carbon dioxide volume fraction, blast furnace gas nitrogen fraction, high-pressure steam pressure, high steam temperature, turbine discharge pressure
Power, Inlet Temperature of Circulating Water, waste heat boiler exhaust gas temperature, atmospheric pressure and atmospheric temperature.
The modification method that Combined Cycle Unit power is affected by atmospheric temperature the most according to claim 2, is characterized in that, institute
The standard generated output stated is 80MW, 90MW, 100MW, 110MW or 120MW.
The modification method that Combined Cycle Unit power is affected by atmospheric temperature the most according to claim 4, is characterized in that, institute
The m stated determines according to the number of input layer data, and input layer data amount check is the most, and m value is the biggest, when input layer is 3～20 numbers
According to time, m value can be chosen between 10～30.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610608517.8A CN106200416B (en) | 2016-07-29 | 2016-07-29 | The regulator control system and method that atmospheric temperature influences combined cycle unit power |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610608517.8A CN106200416B (en) | 2016-07-29 | 2016-07-29 | The regulator control system and method that atmospheric temperature influences combined cycle unit power |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106200416A true CN106200416A (en) | 2016-12-07 |
| CN106200416B CN106200416B (en) | 2018-11-23 |
Family
ID=57495949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610608517.8A Expired - Fee Related CN106200416B (en) | 2016-07-29 | 2016-07-29 | The regulator control system and method that atmospheric temperature influences combined cycle unit power |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106200416B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106970262A (en) * | 2017-03-30 | 2017-07-21 | 国网天津市电力公司 | It is a kind of to test the method that atmospheric temperature influences on Combined Cycle Unit generated output |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6681155B1 (en) * | 1998-08-31 | 2004-01-20 | Mitsubishi Chemical Corporation | Optimizing control method and optimizing control system for power plant |
| CN101929684A (en) * | 2010-07-30 | 2010-12-29 | 上海交通大学 | Coal consumption calculating method of composite firing low heat value gas unit |
| CN102799161A (en) * | 2012-08-13 | 2012-11-28 | 浙江大学 | Performance index correcting and comparing method and regulation control system of combined cycle generating unit |
-
2016
- 2016-07-29 CN CN201610608517.8A patent/CN106200416B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6681155B1 (en) * | 1998-08-31 | 2004-01-20 | Mitsubishi Chemical Corporation | Optimizing control method and optimizing control system for power plant |
| CN101929684A (en) * | 2010-07-30 | 2010-12-29 | 上海交通大学 | Coal consumption calculating method of composite firing low heat value gas unit |
| CN102799161A (en) * | 2012-08-13 | 2012-11-28 | 浙江大学 | Performance index correcting and comparing method and regulation control system of combined cycle generating unit |
Non-Patent Citations (1)
| Title |
|---|
| 张杨林子 等: "联合循环机组建模及环境参数对其性能的影响", 《电力科学与工程》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106970262A (en) * | 2017-03-30 | 2017-07-21 | 国网天津市电力公司 | It is a kind of to test the method that atmospheric temperature influences on Combined Cycle Unit generated output |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106200416B (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106874569B (en) | Variable-geometry split-shaft type gas turbine real-time simulation modeling method | |
| CN102693451B (en) | Method for predicting ammonia process flue gas desulphurization efficiency based on multiple parameters | |
| CN104734147B (en) | A kind of integrated energy system likelihood energy stream analysis method | |
| CN106682376B (en) | Whole-process steam turbine modeling and identification method for actual characteristics of parameters changing along with working conditions | |
| CN105303032B (en) | Influence the objective factor analysis method of generating set efficiency | |
| CN105201565B (en) | A kind of multicomputer steam-turbine real-time distribution method of flow based on piping-main scheme | |
| CN109420424A (en) | A kind of wet desulfurization of flue gas by limestone-gypsum method energy saving of system optimization method | |
| CN106842909A (en) | For the sign based on model of the pressure/load relation of power plant spatial load forecasting | |
| CN115238597A (en) | Construction method of source network carbon-loaded emission model of park level comprehensive energy system | |
| CN111950122A (en) | Operation optimization method for park comprehensive energy system | |
| CN101788789A (en) | Nonlinear predictive control method of unit plant based on chaos and hybrid optimization algorithm | |
| CN106321161A (en) | Activation control apparatus | |
| CN107831652A (en) | A kind of unit load intelligent optimized control method based on cold end system energy storage | |
| Wang et al. | An improved coordinated control strategy for boiler-turbine units supplemented by cold source flow adjustment | |
| Baghsheikhi et al. | Real-time exergoeconomic optimization of a steam power plant using a soft computing-fuzzy inference system | |
| CN108757059A (en) | A kind of steam turbine determines sliding pressure curve experiments optimization method in the case where throttling with vapour | |
| CN104573170A (en) | Method for determining initial pressure of optimal operation of steam turbine | |
| CN112016754A (en) | Power station boiler exhaust gas temperature advanced prediction system and method based on neural network | |
| CN111931436A (en) | Burner nozzle air quantity prediction method based on numerical simulation and neural network | |
| CN109375503B (en) | Steam waste heat cascade utilization optimization control method | |
| Chen et al. | Application of deep learning modelling of the optimal operation conditions of auxiliary equipment of combined cycle gas turbine power station | |
| CN106200416A (en) | Regulator control system that Combined Cycle Unit power is affected by atmospheric temperature and method | |
| JPH08339204A (en) | Autonomous adaptive optimization control system for thermal power station | |
| Ma et al. | Prediction of thermal system parameters based on PSO-ELM hybrid algorithm | |
| CN107102545A (en) | A kind of load optimal distribution of Combined Cycle Unit stopping process and remaining tolerance modified computing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170308 Address after: 200240 Dongchuan Road, Shanghai, No. 800, No. Applicant after: SHANGHAI JIAO TONG University Applicant after: BAOSHAN IRON & STEEL Co.,Ltd. Address before: 200240 Dongchuan Road, Shanghai, No. 800, No. Applicant before: Shanghai Jiao Tong University |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181123 Termination date: 20210729 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |