CN109886471A - Fired power generating unit load distribution method based on neural network and intelligent optimization algorithm - Google Patents
Fired power generating unit load distribution method based on neural network and intelligent optimization algorithm Download PDFInfo
- Publication number
- CN109886471A CN109886471A CN201910061923.0A CN201910061923A CN109886471A CN 109886471 A CN109886471 A CN 109886471A CN 201910061923 A CN201910061923 A CN 201910061923A CN 109886471 A CN109886471 A CN 109886471A
- Authority
- CN
- China
- Prior art keywords
- neural network
- optimization algorithm
- unit
- data
- power plant
- 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.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 57
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 54
- 238000009826 distribution Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 23
- 239000003245 coal Substances 0.000 claims abstract description 63
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000012886 linear function Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims abstract description 4
- 238000002360 preparation method Methods 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims description 8
- 239000002245 particle Substances 0.000 claims description 7
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical group [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 5
- 229910052760 oxygen Inorganic materials 0.000 claims description 5
- 239000001301 oxygen Substances 0.000 claims description 5
- 230000001052 transient effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 210000004218 nerve net Anatomy 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 210000000038 chest Anatomy 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- 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
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Feedback Control In General (AREA)
Abstract
The present invention relates to a kind of fired power generating unit load distribution method based on neural network and intelligent optimization algorithm, it include: the history data of each unit to be obtained from power plant dcs, and history net coal consumption rate data are obtained from power plant level of factory Sis Based On Pi Database；It is matrix form by history data and history net coal consumption rate data preparation, the input data as BP neural network input layer；Wherein, the hidden layer of BP neural network uses Sigmoid function, and output layer uses linear function, and Weight Training algorithm uses L-M optimization algorithm；Using didactic intelligent optimization algorithm, as optimizing main program, using the output of trained BP neural network in step 2 in optimizing main program, fitness function as intelligent optimization algorithm, the data run in optimizing main program are screened, until the optimum load commitment amount or the number of iterations of the current each unit in power plant reach and limit maximum value.The present invention realizes fired power generating unit load optimal distribution.
Description
Technical field
The invention belongs to thermal power generating technology field more particularly to a kind of fire based on neural network and intelligent optimization algorithm
Motor group load distribution method.
Background technique
With power plant automation and intelligentized continuous fast development, domestic more and more grid companies start to require
Power plant company upgrades to full factory's load scheduling mode by power grid to the Single Machine Scheduling mode of power plant unit.Compared to single machine
It dispatches, power plant (or power supply point) is considered as single scheduler object by power network dispatching system in full factory's load scheduling mode, by dispatching
Main website issues full factory's active command, to demand perfection each unit of factory according to itself reality according to set performance indicator or constraint condition
The closed-loop control of full factory's active power is completed in the variation of situation responsive electricity grid load instruction jointly.Full factory load scheduling, overcomes
The many disadvantages and disadvantage of Single Machine Scheduling system have been truly realized effective combination of safe operation of power system and economical operation.
And an important core in full factory load scheduling system, it is exactly the optimum distribution of power plant load.Generation current brand-name computer group
Sharing of load field is there are coal consumption performance data inaccuracy, unfounded, optimization algorithm poor universality, the problems such as real-time is insufficient.
Summary of the invention
The object of the present invention is to provide a kind of fired power generating unit sharing of load side based on neural network and intelligent optimization algorithm
Method, being trained using power plant's operation data has certain predictive and perspective BP neural network to coal consumption characteristic, and should
Fitness function of the BP neural network as subsequent intelligent optimizing algorithm, connects two kinds of advanced algorithm means, solves to concertedness
The certainly Optimizing Allocation of fired power generating unit load.
The present invention provides a kind of fired power generating unit load distribution method based on neural network and intelligent optimization algorithm, packet
It includes:
Step 1, the history data of each unit is obtained from power plant dcs, and from power plant
History net coal consumption rate data are obtained in grade Sis Based On Pi Database；
It step 2, is matrix form by history data and history net coal consumption rate data preparation, it is defeated as BP neural network
Enter the input data of layer；Wherein, the hidden layer of BP neural network uses Sigmoid function, and output layer uses linear function, weight
Training algorithm uses L-M optimization algorithm；
Step 3, using didactic intelligent optimization algorithm, as optimizing main program, step 2 is used in optimizing main program
In trained BP neural network output, as the fitness function of intelligent optimization algorithm, to what is run in optimizing main program
Data are screened, until the optimum load commitment amount or the number of iterations of the current each unit in power plant reach limit maximum value as
Only.
Further, history data includes thermal loss of steam turbine rate, Auxiliary System in Power Plant rate, boiler controller system in step 1
It is load, oxygen at furnace exit, each air port baffle opening, each coal pulverizer coal-supplying amount, a variety of in fire box temperature.
Further, step 2 includes:
The transient state operation data that unit is identified from history data is rejected.
Further, step 2 further include:
Continuous differencing is carried out to history net coal consumption rate data, to correspond to history data.
Further, step 3 includes:
70% in step 1 overall data is regard as training sample, for the training of BP neural network, remaining 30% conduct
Test sample, the test for BP neural network.
Further, step 3 specifically includes:
Unit load optimization distribution is executed as optimizing main program using particle swarm optimization algorithm, comprising:
According to the actual conditions of each of power plant unit and the requirement of dispatching of power netwoks, one group of sharing of load is randomly generated
Value, this group of apportioning cost each numerical value correspond to a load value of unit；
The class value is input in the corresponding BP neural network of trained every unit in step 2, through BP neural network
The corresponding coal consumption value of every unit is calculated；
The coal consumption value obtained is added, the total consumption of coal value of all units of full factory is obtained；
Based on particle swarm optimization algorithm, the size and renewal speed of sharing of load value are constantly updated, BP nerve net is passed through
Network constantly updates the coal consumption value of single unit, and optimization calculates the total consumption of coal value of unit, until total consumption of coal value no longer changes, exports
The total consumption of coal is worth corresponding each unit load, the actual instruction output as each unit load optimization distribution in power plant.
According to the above aspect of the present invention, the fired power generating unit load distribution method based on neural network and intelligent optimization algorithm, by making
Being trained with a large amount of power plant's operation datas has certain predictive and perspective BP neural network to coal consumption characteristic, may be implemented
Power plant's coal consumption characteristic is accurately quickly calculated, all reduces the back of production cost at progress " coal mixing combustion " in each high-power station now
Under scape, accurately and effectively coal consumption performance data is for instructing power plant safety economical operation to have important value；Carrying out power plant
During sharing of load calculates, used using didactic intelligent optimization algorithm compared in such current technology or system
The Traditional calculating methods such as " equal incremental " method there is better universality and push away for the better adaptability of data source
Wide property.Incessantly in this way, didactic intelligent optimization algorithm optimizing carries out power plant load optimizing distribution, calculating speed faster, is counted
It is higher to calculate precision, meets the requirement in power plant production process for real-time and accuracy；It is largely run using by power plant
The output for the BP neural network that data train, as the fitness function of subsequent intelligent optimizing algorithm, two kinds of connection is advanced
Algorithm means, concertedness come solve coal consumption performance data existing for generation current factory set reformation field inaccuracy,
It is unfounded, optimization algorithm poor universality, the problems such as real-time is insufficient.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention and the accompanying drawings.
Detailed description of the invention
Fig. 1 is that the present invention is based on the flow charts of neural network and the fired power generating unit load distribution method of intelligent optimization algorithm.
Fig. 2 is BP neural network structural schematic diagram of the present invention.
Fig. 3 is the algorithm schematic diagram that power plant sharing of load is carried out using the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
Join shown in Fig. 1, present embodiments provides a kind of fired power generating unit load based on neural network and intelligent optimization algorithm
Distribution method, comprising:
Step S1, obtains the history data of each unit from power plant dcs, and from power plant
History net coal consumption rate data are obtained in level of factory Sis Based On Pi Database；
History data and history net coal consumption rate data preparation are matrix form, as BP neural network by step S2
The input data of input layer；Wherein, the hidden layer of BP neural network uses Sigmoid function, and output layer uses linear function, power
It is worth training algorithm and uses L-M optimization algorithm；
Step S3, as optimizing main program, uses step using didactic intelligent optimization algorithm in optimizing main program
The output of trained BP neural network in S2, as the fitness function of intelligent optimization algorithm, to being run in optimizing main program
Data screened, until the optimum load commitment amount or the number of iterations of the current each unit in power plant reach restriction maximum value
Until.
The fired power generating unit load distribution method based on neural network and intelligent optimization algorithm, is instructed using power plant's operation data
Practising has certain predictive and perspective BP neural network to coal consumption characteristic, and using the BP neural network as subsequent intelligence
The fitness function of optimizing algorithm realizes fired power generating unit load optimal distribution.
In the present embodiment, history data includes thermal loss of steam turbine rate, Auxiliary System in Power Plant rate, boiler in step S1
It is unit load, oxygen at furnace exit, each air port baffle opening, each coal pulverizer coal-supplying amount, a variety of in fire box temperature.
In the present embodiment, step S2 includes:
The transient state operation data that unit is identified from history data is rejected.
In the present embodiment, step S2 further include:
Continuous differencing is carried out to history net coal consumption rate data, to correspond to history data.
In the present embodiment, step S3 includes:
70% in step S1 overall data is regard as training sample, for the training of BP neural network, remaining 30% work
Test for test sample, for BP neural network.
In the present embodiment, step S3 is specifically included:
Unit load optimization distribution is executed as optimizing main program using particle swarm optimization algorithm, comprising:
According to the actual conditions of each of power plant unit and the requirement of dispatching of power netwoks, one group of sharing of load is randomly generated
Value, this group of apportioning cost each numerical value correspond to a load value of unit；
The class value is input in the corresponding BP neural network of trained every unit in step S2, through BP neural network
The corresponding coal consumption value of every unit is calculated；
The coal consumption value obtained is added, the total consumption of coal value of all units of full factory is obtained；
Based on particle swarm optimization algorithm, the size and renewal speed of sharing of load value are constantly updated, BP nerve net is passed through
Network constantly updates the coal consumption value of single unit, and optimization calculates the total consumption of coal value of unit, until total consumption of coal value no longer changes, exports
The total consumption of coal is worth corresponding each unit load, the actual instruction output as each unit load optimization distribution in power plant.
Invention is further described in detail below.
Join shown in Fig. 2, Fig. 3, w indicates that the weight vector between network layer, b indicate the threshold value of each layer of network in Fig. 2.
The fired power generating unit load distribution method based on neural network and intelligent optimization algorithm uses trained BP nerve
The output of network differentiated by the supervision of the fitness function as the fitness function of its latter linked intelligent optimization algorithm,
To constantly update the globally optimal solution that iteration goes out set reformation.This method specifically includes the following steps:
One, thermal loss of steam turbine rate, the Auxiliary System in Power Plant rate, boiler controller system load, furnace of each unit in power plant are acquired
Operating parameter that thorax outlet oxygen amount, each air port baffle opening, each coal pulverizer coal-supplying amount, the power plants such as fire box temperature are easy to acquire and
Data.
Currently, the main index for measuring power plant set reformation system is still economic index, and most directly
Economic index be power plant net coal consumption rate, i.e. thermal power plant is often provided out the standard coal that 1kWh electric energy averagely consumes
Amount.Net coal consumption rate is typical non-linear, time-varying parameter, and not only measurement process is complicated, measuring result error is big, and measure at
This is higher, and the result measured can not accurately reflect unit net coal consumption rate characteristic interior for a period of time, this is because unit
Net coal consumption rate can over time and the variation of unit operating condition and constantly change.If by the measurement of certain net coal consumption rate
As a result the net coal consumption rate data even repeatedly measured in a period of time, as set reformation economy referring to according to
According to then probably cannot get the optimized results of set reformation, especially when the operating condition of unit and fuel product
When large change or fluctuation occur for matter.This has just deviated from the original intention that power plant carries out unit load optimization distribution.The present invention is logical
The steady-state operation parameter collected and be easy to acquire in each unit production process of power plant is crossed, such as by collecting dcs
(DCS) historical data recorded in, including temperature of power plant steam turbine heat consumption rate, Auxiliary System in Power Plant rate, boiler controller system load, burner hearth
Seven groups of data such as oxygen amount, each air port baffle opening, each coal pulverizer coal-supplying amount, fire box temperature are exported, to each of power plant unit
Net coal consumption rate carries out " hard measurement ".It is divided between the acquisition time of every group of operation data 30 minutes, the continuous acquisition 1 year item number
According to removing Temporal Data, each operation data 15000, overall data scale is 15000*7=105000.
Two, the operating parameter and net coal consumption rate data for each unit for being collected into step 1, as algorithm BP nerve net
The input data of network input layer, the hidden layer of BP neural network select Sigmoid method, and output layer uses linear function.
By the operation data being collected into step 1 and the acquirement from power plant's level of factory Sis Based On Pi Database (SIS)
Power plant's net coal consumption rate data are corresponded to, and these data are arranged together as binary system or decimal system file.It needs to illustrate
, since the net coal consumption rate frequency recorded in general power plant SIS is, need corresponding in order to carry out with operation data once a day
Continuous differencing is carried out to net coal consumption rate parameter.It regard 70% in overall data as training sample, the instruction for neural network
Practice, remaining 30% sample, is used for network test sample.Neural network hidden layer transfer function selects Sigmoid function, and output layer passes
Defeated function selects linear function, and Weight Training algorithms selection is L-M optimization algorithm, and the number of iterations is 5000 times.Trained mind
It through network, is verified using test sample, prediction result shows to predict error within an acceptable range.
Three, using didactic intelligent optimization algorithm, as optimizing main program, using being trained in step 2 in main program
Neural network output, the foundation as the fitness function of algorithm, as the data evolution iteration run in program.
With the development of computer technology and optimum theory, tabu search algorithm, simulated annealing, genetic algorithm, grain
The Heuristic Intelligent Algorithms such as swarm optimization are gradually applied in power plant unit load optimization distribution field.In the present invention, examine
The calculation amount for considering neural network is larger, if connected intelligent optimization algorithm is complicated, may cause the whole of algorithm
Body realization takes a long time, and then influences the real-time of power plant Load Distribution System.Thus, the present invention in, using calculation amount compared with
Main algorithm of the small particle swarm optimization algorithm (PSO) as load optimal distribution algorithm.Algorithm is first according to each of power plant unit
Actual conditions and dispatching of power netwoks requirement, be randomly generated one group of sharing of load value, this group of each numerical value of apportioning cost represents
One load value of unit.The class value is input in the corresponding neural network of trained every unit in step 2, through nerve
Network query function obtains the corresponding coal consumption value of every unit.These coal consumption values are added, the total consumption of coal value of all units of full factory is obtained.
Then, according to PSO algorithm principle, the size and renewal speed of sharing of load value are constantly updated, and constantly updates and calculates machine
The total consumption of coal value of group is considered as algorithmic statement until total consumption of coal value no longer changes.Export the corresponding each unit of the total consumption of coal value
Load, the actual instruction output as each unit load optimization distribution in power plant.
Four, algorithm terminates, and condition is the optimum load commitment amount of the current each unit in power plant during algorithm calculates, or repeatedly
Generation number reaches restriction maximum value.
The above is only a preferred embodiment of the present invention, it is not intended to restrict the invention, it is noted that for this skill
For the those of ordinary skill in art field, without departing from the technical principles of the invention, can also make it is several improvement and
Modification, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (6)
1. a kind of fired power generating unit load distribution method based on neural network and intelligent optimization algorithm characterized by comprising
Step 1, the history data of each unit is obtained from power plant dcs, and real from power plant level of factory
When supervisory information system in obtain history net coal consumption rate data；
It step 2, is matrix form by the history data and history net coal consumption rate data preparation, it is defeated as BP neural network
Enter the input data of layer；Wherein, the hidden layer of the BP neural network uses Sigmoid function, and output layer uses linear function,
Weight Training algorithm uses L-M optimization algorithm；
Step 3, using didactic intelligent optimization algorithm, as optimizing main program, step 2 is used in the optimizing main program
In trained BP neural network output, as the fitness function of the intelligent optimization algorithm, to the optimizing main program
The data of middle operation are screened, until the optimum load commitment amount or the number of iterations of the current each unit in power plant reach restriction
Until maximum value.
2. the fired power generating unit load distribution method according to claim 1 based on neural network and intelligent optimization algorithm,
Be characterized in that, history data described in step 1 include thermal loss of steam turbine rate, Auxiliary System in Power Plant rate, boiler controller system load,
It is oxygen at furnace exit, each air port baffle opening, each coal pulverizer coal-supplying amount, a variety of in fire box temperature.
3. the fired power generating unit load distribution method according to claim 2 based on neural network and intelligent optimization algorithm,
It is characterized in that, the step 2 includes:
The transient state operation data that unit is identified from history data is rejected.
4. the fired power generating unit load distribution method according to claim 3 based on neural network and intelligent optimization algorithm,
It is characterized in that, the step 2 further include:
Continuous differencing is carried out to the history net coal consumption rate data, to correspond to the history data.
5. the fired power generating unit load according to any one of claims 1 to 3 based on neural network and intelligent optimization algorithm point
Method of completing the square, which is characterized in that the step 3 includes:
70% in step 1 overall data is regard as training sample, for the training of BP neural network, remaining 30% conduct test
Sample, the test for BP neural network.
6. the fired power generating unit load distribution method according to claim 4 based on neural network and intelligent optimization algorithm,
It is characterized in that, the step 3 specifically includes:
Unit load optimization distribution is executed as optimizing main program using particle swarm optimization algorithm, comprising:
According to the actual conditions of each of power plant unit and the requirement of dispatching of power netwoks, one group of sharing of load value is randomly generated, it should
Group each numerical value of apportioning cost corresponds to a load value of unit；
The class value is input in the corresponding BP neural network of trained every unit in step 2, is calculated through BP neural network
Obtain the corresponding coal consumption value of every unit；
The coal consumption value obtained is added, the total consumption of coal value of all units of full factory is obtained；
Based on particle swarm optimization algorithm, the size and renewal speed of sharing of load value are constantly updated, not by BP neural network
The disconnected coal consumption value for updating single unit, optimization calculate the total consumption of coal value of unit, until total consumption of coal value no longer changes, it is total to export this
Coal consumption is worth corresponding each unit load, the actual instruction output as each unit load optimization distribution in power plant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910061923.0A CN109886471A (en) | 2019-01-22 | 2019-01-22 | Fired power generating unit load distribution method based on neural network and intelligent optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910061923.0A CN109886471A (en) | 2019-01-22 | 2019-01-22 | Fired power generating unit load distribution method based on neural network and intelligent optimization algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109886471A true CN109886471A (en) | 2019-06-14 |
Family
ID=66926613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910061923.0A Pending CN109886471A (en) | 2019-01-22 | 2019-01-22 | Fired power generating unit load distribution method based on neural network and intelligent optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109886471A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264113A (en) * | 2019-07-17 | 2019-09-20 | 深圳市智物联网络有限公司 | A kind of load allocation method of Biogas Generator Set, device and relevant device |
| CN110397951A (en) * | 2019-08-01 | 2019-11-01 | 广州发展集团股份有限公司 | A kind of Boiler Combustion Optimization System based on data-driven and intelligent algorithm, method and apparatus |
| CN110837226A (en) * | 2019-12-26 | 2020-02-25 | 华润电力技术研究院有限公司 | Thermal power generating unit operation optimization method based on intelligent optimization algorithm and related device |
| CN111639742A (en) * | 2020-05-22 | 2020-09-08 | 安徽科技学院 | System and method for diagnosing state fault of desulfurization and denitrification circulating pump |
| CN111682593A (en) * | 2020-05-29 | 2020-09-18 | 黑龙江苑博信息技术有限公司 | Thermal power generating unit coordination optimization method based on neural network model state observer |
| CN111853848A (en) * | 2020-06-29 | 2020-10-30 | 东北电力大学 | Optimization method for fuel quantity distribution among different-layer combustors of coal-fired boiler |
| CN112686422A (en) * | 2020-12-03 | 2021-04-20 | 华润电力技术研究院有限公司 | Method, device, equipment and medium for determining coal quality information of coal as fired in thermal power plant |
| CN113780648A (en) * | 2021-06-10 | 2021-12-10 | 朝阳燕山湖发电有限公司 | Multi-mode heat supply unit load distribution optimization method based on artificial neural network |
| CN113887827A (en) * | 2021-10-25 | 2022-01-04 | 国网安徽省电力有限公司电力科学研究院 | Coal blending combustion optimization decision method based on real-time carbon emission monitoring of thermal power generating unit |
| CN113987790A (en) * | 2021-10-26 | 2022-01-28 | 西安热工研究院有限公司 | Method, system, equipment and medium for adjusting optimal operation oxygen amount of thermal power generating unit |
| CN114418358A (en) * | 2021-12-31 | 2022-04-29 | 新奥数能科技有限公司 | Boiler scheduling method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN103729695A (en) * | 2014-01-06 | 2014-04-16 | 国家电网公司 | Short-term power load forecasting method based on particle swarm and BP neural network |
| CN106372756A (en) * | 2016-09-07 | 2017-02-01 | 南京工程学院 | Thermal power plant load optimization distribution method based on breeding particle swarm optimization |
| CN106920008A (en) * | 2017-02-28 | 2017-07-04 | 山东大学 | A kind of wind power forecasting method based on Modified particle swarm optimization BP neural network |
| CN107480815A (en) * | 2017-08-03 | 2017-12-15 | 国网河北省电力公司保定供电分公司 | A kind of power system taiwan area load forecasting method |
-
2019
- 2019-01-22 CN CN201910061923.0A patent/CN109886471A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN103729695A (en) * | 2014-01-06 | 2014-04-16 | 国家电网公司 | Short-term power load forecasting method based on particle swarm and BP neural network |
| CN106372756A (en) * | 2016-09-07 | 2017-02-01 | 南京工程学院 | Thermal power plant load optimization distribution method based on breeding particle swarm optimization |
| CN106920008A (en) * | 2017-02-28 | 2017-07-04 | 山东大学 | A kind of wind power forecasting method based on Modified particle swarm optimization BP neural network |
| CN107480815A (en) * | 2017-08-03 | 2017-12-15 | 国网河北省电力公司保定供电分公司 | A kind of power system taiwan area load forecasting method |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264113A (en) * | 2019-07-17 | 2019-09-20 | 深圳市智物联网络有限公司 | A kind of load allocation method of Biogas Generator Set, device and relevant device |
| CN110397951A (en) * | 2019-08-01 | 2019-11-01 | 广州发展集团股份有限公司 | A kind of Boiler Combustion Optimization System based on data-driven and intelligent algorithm, method and apparatus |
| CN110837226A (en) * | 2019-12-26 | 2020-02-25 | 华润电力技术研究院有限公司 | Thermal power generating unit operation optimization method based on intelligent optimization algorithm and related device |
| CN111639742A (en) * | 2020-05-22 | 2020-09-08 | 安徽科技学院 | System and method for diagnosing state fault of desulfurization and denitrification circulating pump |
| CN111682593A (en) * | 2020-05-29 | 2020-09-18 | 黑龙江苑博信息技术有限公司 | Thermal power generating unit coordination optimization method based on neural network model state observer |
| CN111682593B (en) * | 2020-05-29 | 2023-04-18 | 黑龙江苑博信息技术有限公司 | Thermal power generating unit coordination optimization method based on neural network model state observer |
| CN111853848B (en) * | 2020-06-29 | 2022-09-30 | 东北电力大学 | Optimization method for fuel quantity distribution among different-layer combustors of coal-fired boiler |
| CN111853848A (en) * | 2020-06-29 | 2020-10-30 | 东北电力大学 | Optimization method for fuel quantity distribution among different-layer combustors of coal-fired boiler |
| CN112686422B (en) * | 2020-12-03 | 2023-04-18 | 华润电力技术研究院有限公司 | Method, device, equipment and medium for determining coal quality information of coal as fired in thermal power plant |
| CN112686422A (en) * | 2020-12-03 | 2021-04-20 | 华润电力技术研究院有限公司 | Method, device, equipment and medium for determining coal quality information of coal as fired in thermal power plant |
| CN113780648A (en) * | 2021-06-10 | 2021-12-10 | 朝阳燕山湖发电有限公司 | Multi-mode heat supply unit load distribution optimization method based on artificial neural network |
| CN113780648B (en) * | 2021-06-10 | 2023-12-26 | 朝阳燕山湖发电有限公司 | Multi-mode heat supply unit load distribution optimization method based on artificial neural network |
| CN113887827A (en) * | 2021-10-25 | 2022-01-04 | 国网安徽省电力有限公司电力科学研究院 | Coal blending combustion optimization decision method based on real-time carbon emission monitoring of thermal power generating unit |
| CN113987790A (en) * | 2021-10-26 | 2022-01-28 | 西安热工研究院有限公司 | Method, system, equipment and medium for adjusting optimal operation oxygen amount of thermal power generating unit |
| CN113987790B (en) * | 2021-10-26 | 2024-09-06 | 西安热工研究院有限公司 | Method, system, equipment and medium for adjusting optimal operation oxygen amount of thermal power unit |
| CN114418358A (en) * | 2021-12-31 | 2022-04-29 | 新奥数能科技有限公司 | Boiler scheduling method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886471A (en) | Fired power generating unit load distribution method based on neural network and intelligent optimization algorithm | |
| CN106991539B (en) | Energy system optimal scheduling method and device | |
| Gopalakrishnan et al. | Operational planning of combined heat and power plants through genetic algorithms for mixed 0–1 nonlinear programming | |
| CN102360181B (en) | Low-temperature heat real-time optimization system based on general algorithm sequential quadratic programming (GA-SQP) mixed optimization strategy | |
| CN109583585A (en) | A kind of station boiler wall temperature prediction neural network model | |
| CN109767080B (en) | Demand side response evaluation method of community comprehensive energy system | |
| CN104181900A (en) | Layered dynamic regulation method for multiple energy media | |
| CN112365101A (en) | Thermal power generating unit peak regulation combined total coal consumption optimization method and system based on genetic algorithm | |
| Perekrest et al. | Administrative buildings heating automatic control based on maximum efficiency criterion | |
| CN109858125B (en) | Thermal power unit power supply coal consumption calculation method based on radial basis function neural network | |
| Ma et al. | Economic operation evaluation of active distribution network based on fuzzy Borda method | |
| CN102637020A (en) | Integrated-type control system of roll steel heating furnace | |
| CN114427684A (en) | Control method and control device for combustion furnace in natural gas purification process | |
| CN105633950B (en) | A kind of probabilistic multiple target Random-fuzzy Dynamic Optimal Power Flow Problem method for solving of consideration wind-powered electricity generation injection | |
| CN112394643B (en) | Scheduling method and system for thermoelectric system of iron and steel enterprise and computer readable storage medium | |
| CN106610589A (en) | Online hardware closed-loop network source coordination linear active-disturbance-rejection control method | |
| CN112950409A (en) | Production scheduling optimization method of gas and steam energy comprehensive utilization system | |
| CN113537541A (en) | Optimized navigation method for gas system of iron and steel enterprise | |
| CN111342456A (en) | Method and system for modeling energy system of transformer area | |
| CN113824116B (en) | Hybrid time scale DRL-based comprehensive energy online scheduling method | |
| CN114781274B (en) | Comprehensive energy system control optimization method and system for simulation and decision alternate learning | |
| CN115102164A (en) | Multi-unit collaborative optimization load distribution method, system, equipment and storage medium | |
| CN115579072A (en) | Intelligent water quality monitoring control system and method for heat supply pipe network | |
| CN109698498A (en) | Using the power grid security assessment system and method for voltage stability margin index | |
| Skakovsky et al. | Efficiency improvement for sugar plant boiler department work based on boiler units optimal loads distribution |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190614 |
|
| RJ01 | Rejection of invention patent application after publication |