CN106056168A - Method for determining optimal value of operation condition of gas-steam combined cycle generating unit - Google Patents
Method for determining optimal value of operation condition of gas-steam combined cycle generating unit Download PDFInfo
- Publication number
- CN106056168A CN106056168A CN201610667080.5A CN201610667080A CN106056168A CN 106056168 A CN106056168 A CN 106056168A CN 201610667080 A CN201610667080 A CN 201610667080A CN 106056168 A CN106056168 A CN 106056168A
- Authority
- CN
- China
- Prior art keywords
- gas
- unit
- data mining
- optimal value
- index
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Abstract
The invention relates to a method for determining an optimal value of the operation condition of a gas-steam combined cycle generating unit, and the method comprises the following steps: S1, building an online monitoring and economical operation system of the gas-steam combined cycle generating unit, and collecting the measuring point parameters of the unit; S2, carrying out the classification and screening of the operation conditions of the unit through employing a clustering algorithm, obtaining N stable operation condition classes, and distributing the measuring point parameters, which can reflect the operation condition of the unit, to different stable operation condition classes; S3, carrying out the data mining of the optimal values of the measuring point parameters for each stable operation condition class, obtaining the optimal value of each stable operation condition class, calculating the confidence of each optimal value, and determining the final preferred value of each stable operation condition class according to the confidence. Compared with the prior art, the method facilitates the improvement of economical operation level of the unit.
Description
Technical field
The present invention relates to combined cycle generation technology, particularly relate to a kind of gas-steam combined circulating generation unit and run
The determination method of operation optimization value.
Background technology
After China carries out power system reform, carrying out the policy of " separating the factory and network, surf the Net at a competitive price ", each genco is necessary
It is devoted to improve the economy of unit operation, is effectively reduced cost of electricity-generating, increases economic efficiency, strengthen enterprise at electricity market
In competitiveness, so improve unit operation economy, save cost of electricity-generating be very important.Improve generating efficiency
Good method is exactly technological innovation, improves the performance of generating equipment, but the upgrading of technology needs to spend the biggest financial resources and material resources,
It it is a unrestrained long and complex process.So on the basis of existing generating equipment, the economy of unit operation to be improved it is necessary to
Try every possible means to improve unit operation management level, optimize the method for operation of unit, reduce the energy loss in power production process, from
And reduce the coal consumption amount of unit generated energy, and improving the economic operation level of generating set, this is that one feasible, short-term just can be shown in
The method of effect.
Gas-steam combined circulating generation unit is owing to having the saving energy, improving the comprehensive effects such as environment, by various countries
Government pays much attention to and gives policy support and regulation protection.Gradually rationalization and environmental requirement recently as energy resource structure
Step up, blast furnace gas is introduced fuel gas generation thus reasonable energy utilization as fuel and is noted by domestic and international knowledgeable people
Mesh, and gradually form market.The most at home and abroad employing blast furnace gas is as fuel, and uses the combustion gas of Experience of Using Single Bf Gas
Unit is few.Additionally blast furnace gas has the advantages that calorific value is low, dustiness is big, and its set structure also has certain with conventional combustion engine
Difference.
In order to improve the economy of unit operation, it is possible to use the method for data mining obtains the optimum of unit operation operating mode
Value, thus instruct the operation of unit to produce.But, traditional data digging method is mainly with fired power generating unit as object of study, right
Data are simply classified, statistics etc., can not really find the rule that data contain behind.At present, public in prior art
The method having opened the scheduling of a kind of gas-steam combined circulating generation unit multiple target multiconstraint optimization, comprises the following steps: 1, build
The unit multiple target schedule model problem mathematical model of certain period vertical；2, described period multiple constraint unit load optimization is designed
Object function；3, based on ant colony algorithm for optimization design multiple target, the unit load Optimized Operation scheme of multiple constraint period.Although the party
On the premise of method can be run guaranteeing unit safety, environmental protection, load between the full factory of real-time reasonable distribution each unit, but can not excavate
And determine the operating condition optimal value of unit, thus the economic operation level of this type of unit can not be improved.
Summary of the invention
Defect that the purpose of the present invention is contemplated to overcome above-mentioned prior art to exist and a kind of gas-steam combined is provided
The determination method of circulating generation unit operating condition optimal value.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of determination method of gas-steam combined circulating generation unit operating condition optimal value, comprises the following steps:
S1, builds gas-steam combined circulating generation unit on-line monitoring and Economical Operation System, gathers the measuring point of unit
Parameter；
S2, after utilizing clustering algorithm to classify the operating condition of described unit, screening obtains N number of steady running condition
Class, and will reflect that the described measuring point parameters spread of the operating condition of described unit is to different described steady running condition classes；
S3, for each described steady running condition class, is optimized the data mining of value, obtains described measuring point parameter
The optimal value of each described steady running condition class, calculates the confidence level of described optimal value, according to described confidence level and confidence level
The comparative result setting index determines the final preferred value of each described steady running condition class.
As preferably, in described step S1, described measuring point parameter include real-time generator end exert oneself, the volume of blast furnace gas
Flow, air compressor inlet temperature, combustion gas turbine exit gas temperature and the oxygen content of boiler export flue gas.
As preferably, in described step S2, described clustering algorithm is K-means clustering algorithm.
As preferably, described step S3 also includes building data mining index and carrying out clustering target；
The formula of described data mining index is as follows:
MG=w1*G1+w2*G2
In formula, MG is the data mining index of unit, G1For the economic indicator of unit, w1For economic indicator in unit data
Excavate the weight in index；G2For the environmental index of unit, w2For environmental index weight in unit data mining index；
Described cluster target refers to after obtaining described data mining index, determines different described steady running condition class
The threshold value of described data mining index, chooses the described measuring point parameter more than described threshold value.
As preferably, in described step S3, the method that described data mining utilizes is Apriori method.
As preferably, in described step S4, described confidence level formula is as follows:
In formula,And A ∩ B=Φ, I represent all item collection carrying out described data mining；
The definition of described confidence level is c=P (B | A), and this formula represents, the probability of B occurs in A event simultaneously.
As preferably, described confidence level sets index as 100%.
Compared with prior art, the present invention has the following advantages.
1, realize the excavation to gas-steam combined circulating generation unit operating condition optimal value, Result can be used
In the guidance that unit produces, thus improve the economic operation level of this type of unit；Using confidence level commenting as data mining results
Sentencing index, the final preferred value obtained more can improve the economic operation level of this type of unit.
2, by the measurement to multiple measuring point parameter, data more specificization and rationalization are made.
3, using K-means clustering algorithm, the classification making operating condition is more reasonable.
4, build data mining index and carry out cluster target can improve participate in data mining data sample size and
Effectiveness, thus improve data mining quality, make the result of data mining more have practical significance.
5, Apriori method is used to make data mining more reasonable.
Accompanying drawing explanation
Fig. 1 is the determination flow chart of combustion engine unit operation operation optimization value of the present invention.
Detailed description of the invention
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implement, give detailed embodiment and concrete operating process, but protection scope of the present invention be not limited to
Following embodiment.
Embodiment 1:
The present embodiment provides a kind of determination method of gas-steam combined circulating generation unit operating condition optimal value, point
It is 3 steps:
S1, collects the measuring point parameter of unit operation, as real-time generator end is exerted oneself the volume of (unit load), blast furnace gas
Flow, air compressor inlet temperature, air compressor outlet temperature, combustion gas turbine exit gas temperature and boiler export flue gas
Oxygen content.Here certain unit 49558 groups of service datas from JIUYUE in 2015 on October 30th, 1 day 1 are acquired.Part
Measuring point supplemental characteristic is as shown in table 1.
The measuring point supplemental characteristic classification of table 1 unit operation
S2, according to the operating states of the units constraints selected, utilizes k-means algorithm to carry out the operating condition of unit
Classification, obtains 8 steady running condition classes of this unit.Then, in the above data gathered, reflection unit operation shape is chosen
The measuring point parameter of state, as real-time generator end is exerted oneself (unit load) and blast furnace gas (such as low-heat value gas) volume flow
Deng, choose 49558 groups of data are distributed to different steady running condition classes by recycling k-means algorithm.Each stable fortune
The central value of row operating mode class is as shown in table 2.
The central value of table 2 steady running condition class
After obtaining the steady running condition class of unit, select operating mode 1, carry out the analysis of optimal value under this operating mode.According to
The practical situation of this unit, the target selection of data mining is the efficiency of gas turbine.By the data survey to operating mode 1, root
According to unit staff experience only when gas turbine efficiency more than 36.70% time, related data its is possible to reflection machine
Organize preferable running status.So selecting data mining index MG=36.70% here；Carry out clustering target, in operating mode 1
Rejected, by the data volume in operating mode 1 from the 10016 of initial data groups of minimizings less than each group data of this data mining index
It is 1532 groups of data.Before carrying out data mining, according to real-time generator end exert oneself (unit load) treat the class of mining data
Do not divide equally.Unit data classification in operating mode 1 is as shown in table 3.
Data unit operation classification in table 3 operating mode 1
S3, after classifying the data of operating mode 1, utilizes Apriori algorithm that the data under this operating mode are carried out data
Excavate, thus obtain the result of data mining, i.e. optimal value under unit operation operating mode.The data mining results of operating mode 1 such as table 4
Shown in.
Table 4 unit operation based on Apriori algorithm operating mode Result
The Result of table 4 is analyzed.First interval it can be seen that unit operation is at 99-103MW from unit load
The economic indicator of unit time interval, i.e. gas turbine proficiency is the highest, and this is consistent with the actual operating state of unit.And unit
Load from this interval more away from time, the economic indicator of unit reduce.This secondary data can also be verified by confidence indicator simultaneously
The reasonability of Result.
According to the data mining results to operating mode 1, it appeared that in table 4 in the case of two kinds of serial number 4 and 5, both met
Economic indicator, confidence level is 100% simultaneously, has reached the confidence indicator 100% set, it is taken as that this Result is machine
The optimal operational condition that group has.In order to obtain the final optimization pass value of operating mode 1, in the parameter calculated under both patterns in interval
Bit value is as final optimization pass value, and result is as shown in table 5.
Under table 5 data mining pattern, the parameter median in interval is analyzed
After obtaining gas-steam combined circulating generation unit operating condition optimal value, unit staff is according to this optimization
Value regulation unit operation.
In like manner can obtain the final optimization pass value of other operating modes.
Claims (7)
1. the determination method of a gas-steam combined circulating generation unit operating condition optimal value, it is characterised in that include with
Lower step:
S1, builds gas-steam combined circulating generation unit on-line monitoring and Economical Operation System, gathers the measuring point ginseng of unit
Number；
S2, after utilizing clustering algorithm to classify the operating condition of described unit, screening obtains N number of steady running condition class, and
To reflect that the described measuring point parameters spread of the operating condition of described unit is to different described steady running condition classes；
S3, for each described steady running condition class, is optimized the data mining of value, obtains each described measuring point parameter
The optimal value of described steady running condition class, calculates the confidence level of described optimal value, sets with confidence level according to described confidence level
The comparative result of index determines the final preferred value of each described steady running condition class.
The determination side of a kind of gas-steam combined circulating generation unit operating condition optimal value the most according to claim 1
Method, it is characterised in that in described step S1, described measuring point parameter include real-time generator end exert oneself, the volume flow of blast furnace gas
Amount, air compressor inlet temperature, combustion gas turbine exit gas temperature and the oxygen content of boiler export flue gas.
The determination side of a kind of gas-steam combined circulating generation unit operating condition optimal value the most according to claim 1
Method, it is characterised in that in described step S2, described clustering algorithm is K-means clustering algorithm.
The determination side of a kind of gas-steam combined circulating generation unit operating condition optimal value the most according to claim 1
Method, it is characterised in that described step S3 also includes: build data mining index and carry out clustering target；
The formula of described data mining index is as follows:
MG=w1*G1+w2*G2
In formula, MG is the data mining index of unit, G1For the economic indicator of unit, w1For economic indicator in unit data mining
Weight in index；G2For the environmental index of unit, w2For environmental index weight in unit data mining index；
Described cluster target refers to after obtaining described data mining index, determines the described of different described steady running condition class
The threshold value of data mining index, chooses the described measuring point parameter more than described threshold value.
The determination side of a kind of gas-steam combined circulating generation unit operating condition optimal value the most according to claim 1
Method, it is characterised in that in described step S3, the method that described data mining utilizes is Apriori method.
The determination side of a kind of gas-steam combined circulating generation unit operating condition optimal value the most according to claim 1
Method, it is characterised in that in described step S4, described confidence level formula is as follows:
In formula,And A ∩ B=Φ, I represent all item collection carrying out described data mining；
The definition of described confidence level is c=P (B | A), and this formula represents, the probability of B occurs in A event simultaneously.
The determination side of a kind of gas-steam combined circulating generation unit operating condition optimal value the most according to claim 1
Method, it is characterised in that described confidence level sets index as 100%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610667080.5A CN106056168B (en) | 2016-08-13 | 2016-08-13 | The determination method of gas-steam combined circulating generation unit operating condition optimal value |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610667080.5A CN106056168B (en) | 2016-08-13 | 2016-08-13 | The determination method of gas-steam combined circulating generation unit operating condition optimal value |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106056168A true CN106056168A (en) | 2016-10-26 |
| CN106056168B CN106056168B (en) | 2019-08-16 |
Family
ID=57481725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610667080.5A Expired - Fee Related CN106056168B (en) | 2016-08-13 | 2016-08-13 | The determination method of gas-steam combined circulating generation unit operating condition optimal value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106056168B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112288120A (en) * | 2019-07-26 | 2021-01-29 | 上海漕泾热电有限责任公司 | Production scheduling real-time optimization system and method for cogeneration unit |
| CN114035434A (en) * | 2021-11-22 | 2022-02-11 | 西南石油大学 | Operation optimization method of gas-steam combined cycle power generation system |
| CN114265309A (en) * | 2021-11-19 | 2022-04-01 | 江苏徐工工程机械研究院有限公司 | Engineering machinery optimization control strategy recommendation system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187804A (en) * | 2006-11-15 | 2008-05-28 | 北京华电天仁电力控制技术有限公司 | Thermal power unit operation optimization rule extraction method based on data excavation |
| 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 |
| CN102708180A (en) * | 2012-05-09 | 2012-10-03 | 北京华电天仁电力控制技术有限公司 | Data mining method in unit operation mode based on real-time historical library |
| CN104750973A (en) * | 2015-02-28 | 2015-07-01 | 河北省电力建设调整试验所 | Thermal power generating unit load (quasi) steady-state working condition clustering algorithm based on data smoothness functions |
| US20150185716A1 (en) * | 2013-12-31 | 2015-07-02 | General Electric Company | Methods and systems for enhancing control of power plant generating units |
-
2016
- 2016-08-13 CN CN201610667080.5A patent/CN106056168B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187804A (en) * | 2006-11-15 | 2008-05-28 | 北京华电天仁电力控制技术有限公司 | Thermal power unit operation optimization rule extraction method based on data excavation |
| 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 |
| CN102708180A (en) * | 2012-05-09 | 2012-10-03 | 北京华电天仁电力控制技术有限公司 | Data mining method in unit operation mode based on real-time historical library |
| US20150185716A1 (en) * | 2013-12-31 | 2015-07-02 | General Electric Company | Methods and systems for enhancing control of power plant generating units |
| CN104750973A (en) * | 2015-02-28 | 2015-07-01 | 河北省电力建设调整试验所 | Thermal power generating unit load (quasi) steady-state working condition clustering algorithm based on data smoothness functions |
Non-Patent Citations (1)
| Title |
|---|
| 王秋平 等: "基于数据挖掘的电站运行参数目标优化", 《电力科学与工程》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112288120A (en) * | 2019-07-26 | 2021-01-29 | 上海漕泾热电有限责任公司 | Production scheduling real-time optimization system and method for cogeneration unit |
| CN114265309A (en) * | 2021-11-19 | 2022-04-01 | 江苏徐工工程机械研究院有限公司 | Engineering machinery optimization control strategy recommendation system and method |
| CN114265309B (en) * | 2021-11-19 | 2023-09-05 | 江苏徐工工程机械研究院有限公司 | Engineering machinery optimization control strategy recommendation system and method |
| CN114035434A (en) * | 2021-11-22 | 2022-02-11 | 西南石油大学 | Operation optimization method of gas-steam combined cycle power generation system |
| CN114035434B (en) * | 2021-11-22 | 2023-09-01 | 西南石油大学 | Operation optimization method of gas-steam combined cycle power generation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106056168B (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103440528B (en) | Thermal power unit operation optimization method and device based on power consumption analysis | |
| CN108416691B (en) | Energy substitution environment-friendly potential calculation method | |
| CN106786764B (en) | A kind of hydrogen manufacturing capacity configuration optimizing method using hydrogen generating system consumption wind-powered electricity generation abandonment | |
| CN106786509B (en) | Based on the thermo-electrically combined scheduling method of more scenario simulations under large-scale wind power integration | |
| CN107103421A (en) | The overall evaluation system and its construction method of industry boiler energy-conservation scheme | |
| CN103742901A (en) | Method for determining consumption difference analysis optimized target value system of circulating fluidized bed unit | |
| CN109767080B (en) | Demand side response evaluation method of community comprehensive energy system | |
| CN103544372A (en) | Unit type selection method of micro gas turbine combined heat and power system | |
| CN106056168A (en) | Method for determining optimal value of operation condition of gas-steam combined cycle generating unit | |
| CN104182804A (en) | Prediction output uncertainty considered day-ahead power generation method of small hydropower and large and medium-sized hydropower station coordination | |
| Daneshvar et al. | Short term optimal hydro-thermal scheduling of the transmission system equipped with pumped storage in the competitive environment | |
| CN112994115A (en) | New energy capacity configuration method based on WGAN scene simulation and time sequence production simulation | |
| Zheng et al. | A factor analysis and self-organizing map based evaluation approach for the renewable energy heating potentials at county level: A case study in China | |
| CN109919401B (en) | Multi-dimensional energy efficiency analysis method of multi-energy complementary system | |
| CN110298534A (en) | F grades of gas-steam combined circulating generation unit energy consumption index on-line monitorings and power consumption analysis method | |
| CN113191542A (en) | Wisdom environmental protection carbon emission management service platform | |
| CN105184502B (en) | A kind of energy-saving and emission-reduction machine unit scheduling method based on unit pollutant emission | |
| CN107066770A (en) | The commercial plant vapour system method for on-line optimization accelerated based on GPU | |
| CN108256131A (en) | Distributed energy multidimensional Optimization Seeking Design method and apparatus | |
| CN115496336A (en) | Thermal power generating unit benefit evaluation method under peak regulation auxiliary service market mechanism | |
| Shi et al. | Comprehensive Energy Efficiency Evaluation of Distributed Energy System Model Based on Entropy Weight Method | |
| Li et al. | Multi-objective optimization for optimal placement and sizing of DG in distribution system | |
| Wang et al. | Study on Sustainability Evaluation and Analysis for Offshore Wind Power Projects Oriented Low-carbon. | |
| Gao et al. | A Review of Optimization of Microgrid Operation. Energies 2021, 14, 2842 | |
| Jiang et al. | Research on Energy Consumption Benchmark Index System and Evaluation of Thermal Power Unit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190816 |